KR101944374B1 - Apparatus and method for detecting abnormal object and imaging device comprising the same - Google Patents

Abstract

According to an embodiment of the present invention, provided is an apparatus for detecting an abnormal object which can detect an object which has a high possibility to get diseased on image data obtained by photographing the inside of a breeding farm. The apparatus comprises: a data processing unit for generating position distribution data representing position distribution of a plurality of objects using image data generated by using an image including the plurality of objects; a motion detecting unit for generating movement data representing the movement of a moving object among the plurality of objects by using the image data; and a control unit for generating abnormal object data representing an abnormal object by comparing the position distribution data of the image data with the operation data.

Description

TECHNICAL FIELD [0001] The present invention relates to an apparatus and method for detecting an abnormal object, and an imaging apparatus including the same.

An embodiment of the present invention relates to an apparatus and method for detecting an abnormal object, and an imaging apparatus including the same.

As the consumption of livestock products increases, various measures have been proposed on how to efficiently manage livestock.

In the past, humans have been able to grasp the state of each livestock and to treat or isolate livestock with abnormal symptoms. However, there is a problem that a lot of manpower is needed to manage all livestock if the number of livestock is large.

In addition, if an infectious disease occurs in some livestock, most of the livestock may be killed. Therefore, a method for quickly and accurately judging whether a livestock is abnormal is required.

In addition, due to the development of transportation means, disease occurring in a specific area is not limited to a specific place but is rapidly spread throughout the nation. In the judgment of diseases of livestock, the temperature measurement method according to fever is used as a criterion for determining the presence or absence of disease. However, since uniform temperature measurement is performed on many livestock, there is a difficulty in judging diseases according to the state of each livestock individual. In addition, such a disease judgment method by temperature measurement has difficulties in detecting an individual at an early stage of disease occurrence.

An object of the present invention is to provide an apparatus and method for detecting an anomaly object which is highly susceptible to diseases on image data captured inside a kennel, and an imaging apparatus including the same.

According to an embodiment of the present invention, a data processing unit generates position distribution data representing a position distribution of the plurality of objects using image data generated from an image including a plurality of objects; A motion detector for generating motion data representing movement of the motion object among the plurality of objects using the image data; And a controller for comparing the position distribution data and the motion data of the image data to generate ideal object data representing an abnormal object.

Wherein the controller compares the position distribution data and the motion data with respect to a plurality of pieces of image data to calculate a cumulative number of motion detection accumulation times and an accumulated cumulative number of motion detection of the plurality of entities, To generate the abnormal entity data.

The control unit may control pixel display of the plurality of objects on the image data according to the abnormal entity data.

The controller may increment the pixel value of the corresponding entity according to the number of accumulation of motion detection.

The controller may increment the pixel value of the corresponding entity according to the number of consecutive motion non-detection accumulation times.

The controller may control a pixel value of a corresponding entity to a first set value when the accumulated number of motion non-detection times exceeds a first threshold value.

The controller may control a pixel value of a corresponding entity to a first set value when the number of consecutive motion non-detection cumulative times exceeds a first threshold value.

The first set value may be a maximum value of the pixel value.

The controller may stepwise decrease the pixel value of the corresponding entity according to the number of accumulated motion detection times.

The controller may stepwise decrease the pixel value of the corresponding entity according to the number of consecutive motion detection cumulative counts.

The controller may control the pixel value of the motion-detected entity to a second set value.

The control unit may exclude the entity detected as the motion on the abnormal entity data.

The controller may control a pixel value of a corresponding entity to a second set value when the cumulative number of motion detection exceeds a second threshold value.

The controller may exclude an entity whose motion detection cumulative count exceeds a second threshold value on the abnormal entity data.

The controller may control the pixel value of the corresponding entity to a second set value when the accumulated number of successive motion detection exceeds the second threshold value.

The controller may exclude an entity whose motion detection cumulative count exceeds a second threshold value on the abnormal entity data.

The second set value may be a pixel value of the original image data.

According to an embodiment of the present invention, there is provided an image processing apparatus including: a data processing unit for generating first position distribution data representing a position distribution of a plurality of objects using first image data generated from a first image including a plurality of objects; A motion detection unit for generating first motion data indicating motion of the motion entity among the plurality of the objects using the first image data; And a controller for comparing the first position distribution data and the first operation data to generate first abnormal entity data representing an abnormal entity.

Wherein the data processing unit generates second position distribution data representing a position distribution of the plurality of objects using second image data generated from a second image including the plurality of objects, Wherein the controller generates second operation data representing movement of the operation entity among the plurality of entities, wherein the control section compares the first ideal entity data, the second position distribution data, and the second operation data, Lt; / RTI >

Wherein the control unit compares the first abnormal entity data with the second positional distribution data and the second operation data to calculate the accumulated number of motion detection of the plurality of entities and the cumulative number of non-detection of the motion ratio of the plurality of entities, The second abnormal entity data can be generated according to the cumulative number of times and the cumulative number of motion non-detection times.

The controller may control pixel display of the plurality of entities on the image data according to the second ideal entity data.

According to an embodiment of the present invention, there is provided an image processing apparatus including: a photographing unit photographing a first image including a plurality of objects to generate first image data; A data processing unit for generating first position distribution data indicating a position distribution of the plurality of objects using the first image data; A motion detection unit for generating first motion data indicating motion of the motion entity among the plurality of the objects using the first image data; And a controller for comparing the first position distribution data and the first operation data to generate first abnormal entity data representing an abnormal entity.

According to an embodiment of the present invention, there is provided an image processing method comprising: capturing a first image including a plurality of objects to generate first image data; Generating first position distribution data indicating a position distribution of the plurality of objects using the first image data; Generating first operation data indicating movement of an operation entity among the plurality of entities using the first image data; And comparing the first position distribution data and the first operation data to generate first abnormal entity data representing an abnormal entity.

The abnormal object detecting apparatus and method and the imaging apparatus including the abnormal object detecting apparatus according to the present invention can detect an abnormal object highly likely to be infected with the disease on the image data photographed inside the kennel.

In addition, the abnormal entity and the normal entity can be visually distinguished and displayed.

In addition, abnormal objects can be tracked and monitored.

In addition, a notification or warning can be sent to the manager when an abnormal object occurs.

In addition, it is possible to reduce the amount of computation of the analysis data and improve the computation speed.

1 is a conceptual diagram of a kennel management system according to an embodiment of the present invention.
2 is a block diagram of an image pickup apparatus according to an embodiment of the present invention.
3 to 15 are views for explaining the operation of the controller according to the embodiment of the present invention.
16 to 17 are flowcharts of an abnormal entity detection method according to an embodiment of the present invention.

The present invention is capable of various modifications and various embodiments, and specific embodiments are illustrated and described in the drawings. It should be understood, however, that the invention is not intended to be limited to the particular embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.

The terms including ordinal, such as second, first, etc., may be used to describe various elements, but the elements are not limited to these terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the second component may be referred to as a first component, and similarly, the first component may also be referred to as a second component. And / or < / RTI > includes any combination of a plurality of related listed items or any of a plurality of related listed items.

It is to be understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, . On the other hand, when an element is referred to as being "directly connected" or "directly connected" to another element, it should be understood that there are no other elements in between.

The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In the present application, the terms "comprises" or "having" and the like are used to specify that there is a feature, a number, a step, an operation, an element, a component or a combination thereof described in the specification, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the contextual meaning of the related art and are to be interpreted as either ideal or overly formal in the sense of the present application Do not.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings, wherein like or corresponding elements are denoted by the same reference numerals, and redundant description thereof will be omitted.

FIG. 1 is a conceptual diagram of a breeding ground according to an embodiment of the present invention, and FIG. 2 is a block diagram of an imaging apparatus according to an embodiment of the present invention.

Referring to Figs. 1 and 2, the kennel 10 refers to a house for breeding livestock. The livestock may be various kinds of animals which are collectively kept in poultry such as poultry, pig, etc. as well as poultry such as chicken and duck.

The image capturing apparatus 100 can detect the environment in the breeding ground 10 and transmit it to at least one of the management server 200 and the air conditioner 300. [ For this purpose, the image capturing apparatus 100 can communicate with the management server 200 and the air conditioner 300 in a wired or wireless manner. Although the image capturing apparatus 100 is illustrated as communicating with the management server 200 and the air conditioner 300 respectively, the image capturing apparatus 100 is not limited to this, and the image capturing apparatus 100 may communicate with the management server 200, (200) may communicate with the air conditioner (300).

A plurality of image pickup devices may be disposed in the breeding hut 10. The imaging apparatus 100 can transmit the image data photographed by the photographing section 111 to the management server 200. [ Alternatively, a separate data collection device 150 may be disposed in the cul-de-sac 10 to collect image data from the plurality of image capture devices 100 and transmit the collected image data to the management server 200. In order to accurately analyze the state inside the breeding habits 10, the image data of the imaging apparatus 100 can have high quality and high capacity. Accordingly, a large bandwidth may be required to transmit the image data photographed by the plurality of image sensing apparatuses 100 to the remote management server 200 in real time, thereby lowering the transmission speed. Therefore, in the separate data collection device 150, video data is collected from the image pickup device 100 in the breeding ground 10, encoded and transmitted to the management server 200, thereby reducing the communication bandwidth and improving the transmission speed have. Alternatively, the image pickup apparatus 100 may perform a primary analysis for analyzing the state of the breeding ground 10 using the image data, and then transmit the processed data to the data collection device or the management server 200. That is, the imaging apparatus 100 can selectively manage only the data necessary for the state analysis of the kennel 10 and transmit it to the data collection device 150 or to the management server 200, thereby efficiently managing communication resources. Or the image pickup apparatus 100 may first analyze the internal state of the breeding ground 10 using the image data of the breeding ground 10 and transmit the result to the data collection device 150 or to the management server 200 Lt; / RTI >

The management server 200 may be a server including a personal computer (PC), a tablet PC, a portable terminal, and the like. When the image capturing apparatus 100 transmits the environment in the breeding ground 10 to the management server 200, the administrator can recognize the environment in the breeding ground 10 through the screen output to the management server 200 or the like. For example, when the image capturing apparatus 100 captures an abnormal situation in the kennel 10 and transmits the abnormal situation to the management server 200, the manager displays the abnormal state in the kennel 10 through the screen output to the management server 200 It is possible to recognize that a situation has occurred and can respond to an abnormal situation at an early stage. Here, the abnormal situation may be, for example, the occurrence of diseased livestock, the pregnancy of livestock, the growth period of the livestock, the humidity in the kennel 10, the temperature, the concentration of the specific molecule or the like.

In the case where the management server 200 is a central server that receives information from a plurality of breeding grounds 10, the manager may not have easy access to the management server 200. In this case, the management server 200 can transmit information about the abnormal situation to the breeding ground 10 through a portable terminal of another administrator or the like.

In addition, the management server 200 can analyze the state of the vat using the data transmitted from the image capturing apparatus 100 or the data collecting apparatus 150. For example, the management server 100 can receive data processed primarily from the plurality of image pickup apparatuses 100 or the data collection apparatus 150, and perform more accurate analysis of the state of the kennel. The management server 200 may perform data communication with the communication unit 115 of the image sensing apparatus 100 or may perform data communication with a communication module (not shown) installed in the data acquisition apparatus 150. [ The management server 200 can receive the original image photographed by the imaging apparatus 100 and the processed image data primarily processed. At this time, the processed image data may mean data that is subjected to a primary analysis on the original image in the duck farm management apparatus 100 or the image pickup apparatus 100 and is encoded.

The air conditioner (300) is a device for controlling the temperature of the cage (10). When the image capturing apparatus 100 captures more than the temperature in the cage 10 and transmits the captured image to the management server 200, the administrator can recognize that the temperature inside the cage 10 has exceeded the temperature displayed on the screen output to the management server 200 And the air conditioner 300 can be controlled to normalize the temperature in the breeding ground 10. Alternatively, when the image capturing apparatus 100 detects temperature or more in the cage 10 and directly delivers the image to the air conditioner 300, the air conditioner 300 may normalize the temperature in the cage 10 directly. For example, if the temperature in the kennel 10 is lower or higher than the temperature appropriate for the animal to live in, the movement of the animals tends to slow down. Accordingly, the image capturing apparatus 100, the management server 200, or the air conditioner 300 can detect temperature or more in the cage 10 and normalize the temperature in the cage 10.

The air conditioner 300 can adjust the humidity of the breeding ground 10. When humidity abnormality occurs in the breeding farm 10, the humidity in the breeding farm 10 can be normalized by controlling the air conditioning system 300.

The image capturing apparatus 100 includes an image capturing section 111, a data processing section 112, a motion detecting section 113, a control section 114, a communication section 115, a display section 116, a user interface section 117, A data base 119, a light source 120, and a pan tilt unit 121. In the embodiment of the present invention, the abnormal object detection apparatus including the data processing unit 112, the motion detection unit 113, the control unit 114, and the communication unit 115 is illustrated as being included in the image sensing apparatus 100. However, the abnormal entity detection device may be formed in a separate module form and included in the data collection device 150 or the management server 200. Alternatively, the abnormal object detection device may be implemented as an independent product in the form of a separate device. When the abnormal object detection apparatus is applied in the form of a module or a device separate from the image sensing apparatus 100, the abnormal object detection apparatus can receive image data from the image sensing apparatus 100 via the communication unit 115. [ The data processing unit and the motion detection unit may be included in the control unit and implemented as a single processor. In the embodiments of the present invention, functions of a data processing unit, a motion detection unit, and a control unit will be described for convenience of explanation.

Hereinafter, an example in which the abnormal object detection apparatus is included in the image sensing apparatus 100 will be described.

A plurality of imaging apparatuses 100 may be installed in the cage 10. [ For example, the imaging device 100 may include at least one upper imaging device disposed on the upper portion of the cage 10 and at least one side imaging device disposed on the side of the cage. Each of the upper image pickup device and the side image pickup device may be an IP camera capable of communication in a wired or wireless manner and capable of real-time video transmission. In the present embodiment, one image pickup device 100 is arranged above the breeding ground.

The photographing unit 111 may photograph an image including a plurality of objects to generate image data. In the embodiment of the present invention, the plurality of entities may mean poultry raised inside the breeding ground.

The photographing unit 111 may generate a plurality of image data using a plurality of images sequentially photographed. For example, the photographing unit 111 may generate the first image data by photographing the first image including the plurality of objects, and may generate the second image data by photographing the second image including the plurality of objects. have. The first image and the second image may be images sequentially captured in time, and one image data may mean a single frame. The photographing unit 111 may generate the first image data and the second image data using the first image and the second image sequentially photographed.

The photographing unit 111 may be an image sensor that photographs a subject using a complementary metal-oxide semiconductor (COMS) module or a charge coupled device (CCD) module. Here, the input image frame is provided to the COMS module or the CCD module in the photographing unit 111 through the lens, and the COMS module or the CCD module converts the optical signal of the subject passing through the lens into an electrical signal (image data) do.

The photographing section 111 may include a fisheye lens or a wide-angle lens having a wide viewing angle. Thus, it is possible for one imaging device 100 to photograph the entire space inside the breeding hosepip.

Further, the photographing unit 111 may be a depth camera. The photographing unit 111 may be driven by any one of various depth recognition methods, and the image photographed through the photographing unit 111 may include depth information. The photographing unit 111 may be, for example, a Kinect sensor. The Kinect sensor is a structured light projection type depth camera, which can acquire three-dimensional information of a scene by projecting a pattern image defined using a projector or a laser and acquiring an image projected through a camera. Such a Kinect sensor includes an infrared radiator for irradiating a pattern using an infrared laser, and an infrared camera for capturing an infrared image, and an RGB camera functioning as a general web cam is disposed between the infrared radiator and the infrared camera. In addition, the Kinect sensor may further include a pan tilt unit 121 for adjusting the microphone arrangement and the angle of the camera.

The basic principle of a Kinect sensor is that when a laser pattern irradiated from an infrared radiator is projected and reflected on an object, the distance to the object surface is obtained using the position and size of the pattern at the reflection point. According to this principle, the photographing unit 111 may irradiate the laser pattern with the space inside the house, and sense the laser pattern reflected from the object, thereby generating image data including the object-specific depth information.

The data processing unit 112 may generate position distribution data indicating the position distribution of a plurality of objects using the image data. The data processing unit 112 generates first position distribution data indicating a position distribution of a plurality of objects using the first image data generated by including a plurality of objects, The second position distribution data representing the position distribution of the plurality of objects can be generated using the data.

In the embodiment of the present invention, the location distribution data may mean a heat map of poultry detected on the image data.

For example, the data processing unit 112 detects an outline of an object in the image data, compares the outline of the object with the outline of the animal object stored in advance in the database 119, and outputs an outline matching with the outline of the animal object stored in advance Can be detected as an animal. At this time, the outline of the animal entity stored in the database 119 may be an outline of at least one animal entity, and the data processing section 112 may detect an entity having an outline matched as described above as an animal entity, It is also possible to judge the kind of animals.

For example, the data processing unit 112 extracts feature points of an object in the image data, and if the extracted feature points match the feature points of the animal object stored in the database 119 in advance, An individual can be detected as an animal. At this time, the data processing unit 112 extracts feature points from the images of two objects to be compared, and performs SIFT (Scale Invariant Feature Transform) or SURF (Speeded Up Robust Features) for matching feature points descriptors of the extracted two objects. Algorithm can be used.

In addition, for example, the data processing unit 112 can detect an animal entity based on the outline of the entities in the image data. More specifically, the data processing unit 112 generates an edge image by detecting the outline of the entities in the image data, detects the outline from the foreground image data, which is a background image of the breeding ground previously stored in the database 119, And an animal object can be detected from a different image obtained by subtracting the background edge image from the edge image. At this time, the data processing unit 112 generates an edge image by detecting the outline of an entity appearing in the frame as an edge by using gradient information of the image data frame. Here, the gradient information means a sum of absolute values of differences as values generated from difference values between adjacent pixels among predetermined pixels in a frame, and an edge means a boundary line between objects using the gradient information.

In addition, the data processing unit 112 can generate a background edge image by detecting the edge of the object corresponding to the background from the image data of the foreground in the photographed cage. At this time, the background edge image may be an image obtained by detecting the outline of entities of a predetermined area as a background, but it is also possible to compare a plurality of image data frames in the foreground in the captured cage 10 for a predetermined number of times or more It may be an image of the outline of the appearing object in the background.

Also, the data processing unit 112 can detect an animal object in the image data using the object detection classifier. In this case, the object detection classifier is learned by constructing a training DB from the images of animal objects photographed by different posture or external environment of the animal object. The object detection classifier includes SVM (Support Vector Machine), neural network, AdaBoost algorithm , And so on. Specifically, the data processing unit 112 detects an edge of the foreground corresponding to the foreground from the image data of the background in the taken cage, applies the edge of the foreground object detected from the image data, An animal detection object can be detected by applying an object detection classifier to a region of data.

The data processing unit 112 reduces noise from the image data photographed by the photographing unit 111 and performs a color gamut correction process based on gamma correction, color filter array interpolation, color matrix, Image signal processing for improving image quality such as color correction and color enhancement can be performed. The data processing unit 112 can perform color processing, blur processing, edge emphasis processing, image analysis processing, image recognition processing, image effect processing, and the like.

The motion detecting unit 113 may generate motion data indicating movement of the motion entity among a plurality of motion vectors using the image data. The motion detecting unit 113 can detect a motion at a specific point, a specific entity, or a specific pixel on the distribution diagram using a single image data or a plurality of continuous image data.

For example, the motion detection unit 113 generates first motion data indicating motion of the motion entity among a plurality of motion vectors using the first motion vector data, It is possible to generate the second operation data.

The motion detection unit 113 can detect motion of the motion entity using the Dense Optical Flow scheme. The motion detecting unit 113 can detect a motion for each pixel by calculating a motion vector for all the pixels on the image data. In the case of the Dense Optical Flow method, since the motion vector is calculated for all the pixels, the detection accuracy is improved but the calculation amount is relatively increased. Therefore, the Dense Optical Flow method can be applied to a specific area where detection accuracy is very high, such as a kennel suspected to have an abnormal situation or a kennel with a large number of individuals.

Or the motion detection unit 113 may detect motion of the motion entity using the Sparse Optical Flow scheme. The motion detecting unit 113 can detect a motion by calculating a motion vector only for some characteristic pixels that are easy to track, such as edges in an image. Sparse Optical Flow reduces the computational complexity but only results on limited pixels. Therefore, the Sparse Optical Flow method can be applied to a specific area where the number of individuals is small or where there is no duplication of objects.

Alternatively, the motion detecting unit 113 can detect motion of the motion entity using Block Matching. The motion detecting unit 113 can detect motion by dividing the image evenly or non-uniformly and calculating motion vectors for the divided regions. Since the block matching computes the motion vectors for each partition, the computation amount is reduced, but the detection accuracy is relatively low because the result for each motion vector is calculated. Therefore, the block matching method can be applied to a specific area where the number of entities is small or where the entities do not overlap.

Alternatively, the motion detection unit 113 can detect the motion of the motion entity using the Continuous Frame Difference method. The motion detecting unit 113 may compare consecutive image frames on a pixel-by-pixel basis, and calculate a value of the difference to detect motion. Since the Continuous Frame Difference method detects motion using the inter-frame difference value, the overall computation amount decreases, but detection accuracy for a bulky object or a duplicated object may be relatively low. In addition, the Continuous Frame Difference method can not distinguish the background image from the non-moving object, so the accuracy may be relatively low. Therefore, the Continuous Frame Difference method can be applied to a specific area where the number of individuals is small or the individuals do not overlap.

Or the motion detection unit 113 can detect motion of the motion entity using the background subtraction method. The motion detecting unit 113 may compare the consecutive image frames on a pixel-by-pixel basis while initially learning the background image, and calculate a value corresponding to the difference to detect motion. Background subtraction method can distinguish background image from non-moving object because it learns background image in advance. Therefore, a separate process for filtering the background image is required, so that the amount of calculation is increased but the accuracy is improved. Therefore, the background subtraction method can be applied to a specific area where a detection accuracy is very high, such as a breeding ground suspected to have an abnormal situation or a breeding ground having a large number of individuals. In the background subtraction method, the background image can be continuously updated.

The motion detecting unit 113 detects the motion on the distribution map by using an appropriate method according to the environment in the breeding ground and the setting of the outside.

The control unit 114 may generate abnormal object data representing an abnormal object by comparing the position distribution data and the operation data of the image data. The control unit 114 may, for example, compare the first position distribution data and the first operation data to generate first abnormal entity data representing the abnormal entity. The control unit 114 may generate first abnormal entity data indicating the information on the object whose motion is not detected on the first positional distribution data by comparing the first positional distribution data with the first operation data. That is, the controller 114 can estimate that the motion is not detected on the first position distribution data indicating the position of the object, and generate the first abnormal object data. That is, the first abnormal entity data may be data obtained by judging whether or not an individual is diseased using the positional distribution of the object and the motion detection information with respect to the single image data. The position distribution data and the motion data are compared with each other to calculate the cumulative number of motion detection accumulations and the cumulative number of motion ratio detections of a plurality of entities and generate abnormal object data according to the cumulative number of motion detection times and the cumulative number of motion non- The control unit may, for example, generate the second ideal entity data by comparing the first ideal entity data, the second position distribution data, and the second operation data. The control unit compares the first abnormal entity data with the second motion distribution data and the second motion data to compute the cumulative number of motion detection accumulations of the plurality of entities and the accumulated cumulative detections of the plurality of entities, The second abnormal entity data can be generated according to the number of times. That is, the second abnormal entity data may indicate the result of determining whether the patient is diseased or not by using the position information and the motion detection information accumulated for a plurality of image data.

The controller 114 may control the pixel display of the plurality of objects on the image data according to the cumulative number of motion detection and the cumulative number of motion ratio detection of the abnormal object data. The control unit may, for example, control the pixel display of the plurality of objects on the image data according to the second ideal object data. Here, the display of a pixel may include all concepts for displaying a pixel corresponding to an arbitrary point, such as the saturation of the pixel, the brightness of the pixel, the color of the pixel, the outline of the pixel, In the embodiment of the present invention, the display of the pixels can be controlled through adjustment of pixel values. The pixel value can be adjusted stepwise, and in the case of a pixel with a high pixel value, the pixel value can be visually emphasized rather than a low pixel. However, the present invention is not limited to this, and it can be set that a pixel having a low pixel value is emphasized and displayed as a pixel having a high pixel value.

Hereinafter, one pixel represents one entity in order to describe the motion-detected pixel and the entity. This is for convenience of explanation, and in practice, a plurality of pixels represent one entity. That is, in order to detect only the motion of some body regions of the poultry and determine an abnormal situation, a method of controlling the display of the pixels by detecting the motion for each pixel will be used.

The controller 114 classifies the abnormal entity as the abnormal entity as the motion of the specific entity is not detected, and displays the pixel value differently as the normal entity as the motion is detected.

Hereinafter, Figs. 3 to 16 illustrate image data taken from an image pickup apparatus installed on the upper part of a cage. In Figs. 3 to 11, nk (k is a natural number between 3 and -1) denotes frames that are sequential in time, "0" is a case in which motion is detected in each frame, "X" . 3 to 6, the pixel value of each object of the image data is set to "0 ", and the pixel value of each object of the image data is set to" 5 " In FIG. 3 to FIG. 16, one piece of image data may mean a single frame. For example, if the (n-1) th frame is the first image data, the nth frame may mean the second image data. If the n-th frame is the first image data, the (n + 1) -th frame may mean the second image data. 3 is a view for explaining the operation of the control unit according to the embodiment of the present invention. Referring to FIG. 3, the controller may increment the pixel value corresponding to an arbitrary point or entity according to the accumulated number of times of motion detection. In FIG. 3, the cumulative number of times of detecting the motion non-detection of the object A is five. Therefore, the control unit increases the pixel value of the object A by five steps. The cumulative number of times of detection of the motion non-detection of the object B is three. Therefore, the control unit increments the pixel value of the object B by three steps. The cumulative number of motion non-detection of the object C is 2. Therefore, the control unit increases the pixel value of the object C by two steps. According to the embodiment of FIG. 3, as the total cumulative count of the motion detection ratio of the object becomes larger, the pixel value increases and can be emphasized and displayed. That is, the higher the pixel value on the distribution chart, the more emphasis can be displayed in red, and the lower the pixel value, the closer to the original data value can be displayed. According to this, even if the motion is detected during a certain frame, if the total number of motion non-detection accumulation times is large, the controller can highlight the object even if it is suspected of a low probability of disease .

4 is a view for explaining the operation of the control unit according to the embodiment of the present invention. Referring to FIG. 4, the controller may increment the pixel value of the corresponding entity according to the cumulative number of successive motion non-detection counts. In FIG. 4, the cumulative number of consecutive motion non-detection counts of entity A is five. Therefore, the control unit increases the pixel value of the object A by five steps. The cumulative number of consecutive motion non-detection of the object B is 2. Thus, the control unit increments the pixel value of object B by two steps. The cumulative number of consecutive motion non-detection of the object C is 1. Therefore, the control unit increments the pixel value of the object C by one step. According to the embodiment of FIG. 4, as the total cumulative count of consecutive motion non-detection times of an entity becomes larger, the pixel value increases and can be emphasized and displayed. According to this, even if the accumulated number of times of motion detection is large, the control unit can display it so as to be close to the normal entity if the cumulative number of motion non-detection counts is not large.

5 is a view for explaining the operation of the control unit according to the embodiment of the present invention. Referring to FIG. 5, the controller may control a pixel value of a corresponding entity to a first set value when the accumulated number of motion non-detection times exceeds a first threshold value. Here, the first threshold and the first set value may be set through the user interface unit. Or through a control command of the management server. In Fig. 5, the first threshold value is set to two. The first set value may mean the maximum value of the pixel value. In FIG. 5, the first set value may mean the maximum red value of the pixel. 5, the cumulative number of motion non-detection times of entity A exceeds the first threshold value 5 times. Therefore, the control unit controls the pixel value of the object A to the maximum red value. The cumulative number of times of non-detection of the motion of the object B is 3, which exceeds the first threshold value. Therefore, the control unit controls the pixel value of the object B to the maximum red value. The cumulative number of consecutive motion non-detection counts of the object C is 1 and does not exceed the first threshold value. Therefore, the control unit maintains the pixel value of the object C in the current state. According to the embodiment of FIG. 5, when the total cumulative count of the motion detection ratio of the object exceeds a predetermined number, the pixel value can be maximally emphasized and displayed.

6 is a view for explaining the operation of the control unit according to the embodiment of the present invention. Referring to FIG. 6, the controller may control a pixel value of a corresponding entity to a first set value when the cumulative number of motion non-detection counts exceeds a first threshold value. Here, the first threshold and the first set value may be set through the user interface unit. Or through a control command of the management server. In Fig. 6, the first threshold value is set to two times. The first set value may mean the maximum value of the pixel value. In FIG. 6, the first set value may mean the maximum red value of the pixel. The cumulative number of consecutive motion non-detection times of the object A exceeds the first threshold value 5 times. Therefore, the control unit controls the pixel value of the object A to the maximum red value. The cumulative number of consecutive motion non-detection times of the object B is 2 and does not exceed the first threshold value. Therefore, the control unit maintains the pixel value of the object B in the current state. The cumulative number of consecutive motion non-detection counts of the object C is 1 and does not exceed the first threshold value. Therefore, the control unit maintains the pixel value of the object C in the current state. According to the embodiment of FIG. 6, it is possible to discriminate an abnormal object according to a stricter criterion by maximizing the pixel value only when the number of consecutive frames of the object does not exceed the first threshold value.

7 is a view for explaining the operation of the control unit according to the embodiment of the present invention. Referring to FIG. 7, the controller may stepwise decrease the pixel value of the corresponding entity according to the cumulative number of motion detection times. The cumulative number of motion detection of the object A is 5. Therefore, the control unit decreases the pixel value of the object A by five steps. The cumulative number of motion detection of the object B is 3. Thus, the control unit reduces the pixel value of object B by three steps. The cumulative number of motion detection of the object C is 2. Accordingly, the control unit decreases the pixel value of the object C by two steps. According to the embodiment of FIG. 7, as the total cumulative count of the motion detection times of the object becomes larger, the pixel value decreases and can be emphasized and displayed. That is, the lower the pixel value on the distribution chart, the closer it is to the original data value or it can be dimly displayed. According to this, even if the motion is not detected for a certain frame, the controller can emphasize and display the motion object close to the normal object if the accumulated number of motion detection is large.

8 is a view for explaining the operation of the control unit according to the embodiment of the present invention. Referring to FIG. 8, the controller may stepwise decrease the pixel value of the corresponding entity according to the cumulative number of motion detection accumulations. In FIG. 8, the cumulative number of successive motion detection of the object A is five. Therefore, the control unit decreases the pixel value of the object A by five steps. The cumulative number of successive motion detection of the object B is 2. Therefore, the control unit decreases the pixel value of object B by two steps. The cumulative number of successive motion detection of the object C is 1. Therefore, the control unit decreases the pixel value of the object C by one step. According to the embodiment of FIG. 8, as the cumulative number of times of successive motion detection of the object becomes larger, the pixel value decreases and can be emphasized. According to this, even if the cumulative number of motion detection is large, the control unit can display it so as to be close to the abnormal object if the cumulative number of cumulative motion detection is not large.

9 is a view for explaining the operation of the control unit according to the embodiment of the present invention. Referring to FIG. 9, the controller may control the pixel value of the motion-detected entity to a second set value. Here, the second set value may be set through the user interface unit. Or through a control command of the management server. In FIG. 9, the second set value is the pixel value of the original image data. In Fig. 9, object A to object C have detected motion more than once during all of the image frames of n-1 to n + 3. Accordingly, the controller sets the pixel values of the objects A to C as the pixel values of the original image data. According to this, an entity whose motion is detected even once during the analysis image frame period can be classified as a normal entity and displayed as a pixel value of the original image data.

10 is a view for explaining the operation of the control unit according to the embodiment of the present invention. Referring to FIG. 10, the controller may control the pixel value of the corresponding entity to a second set value when the cumulative number of motion detection times exceeds a second threshold value. Here, the second threshold value and the second set value may be set through the user interface unit. Or through a control command of the management server. In Fig. 10, the second threshold value is set to two. The second set value is the pixel value of the original image data. In FIG. 10, the cumulative number of motion detection times of entity A exceeds the second threshold value 5 times. Therefore, the control unit controls the pixel value of the object A as the pixel value of the original image data. The cumulative number of motion detection times of the object B exceeds 3 and exceeds the second threshold value. Accordingly, the control unit controls the pixel value of the object B as the pixel value of the original image data. The cumulative number of successive motion detection of the object C does not exceed the second threshold value by one. Therefore, the control unit maintains the pixel value of the object C in the current state. According to the embodiment of FIG. 10, when the cumulative total number of motion detection times of an object exceeds a specific number, the pixel value may be displayed as a pixel value of the original image data.

11 is a view for explaining the operation of the control unit according to the embodiment of the present invention. Referring to FIG. 11, the controller may control a pixel value of a corresponding object to a second set value when the cumulative number of successive motion detection times exceeds a second threshold value. Here, the second threshold value and the second set value may be set through the user interface unit. Or through a control command of the management server. In Fig. 11, the second threshold value is set to two. The second set value is the pixel value of the original image data. 11, the cumulative number of motion detection times of entity A exceeds the second threshold value 5 times. Therefore, the control unit controls the pixel value of the object A as the pixel value of the original image data. The cumulative number of motion detection times of entity B is 2 and does not exceed the second threshold. Therefore, the control unit maintains the pixel value of the object B in the current state. The cumulative number of successive motion detection of the object C does not exceed the second threshold value by one. Therefore, the control unit maintains the pixel value of the object C in the current state. According to the embodiment of FIG. 11, the pixel value can be displayed as the pixel value of the original image data only when the total cumulative count of consecutive motion detection times of the object exceeds a specific number.

12 is a view for explaining the operation of the control unit according to the embodiment of the present invention. Referring to FIG. 12, the control unit may control the corresponding pixel values of the object in which the motion is detected to a second set value, and exclude it from the ideal object data, so that it can be excluded from the analysis object. Here, the second set value may be set through the user interface unit. Or through a control command of the management server. 12, the second set value is the pixel value of the original image data. 12, in the case of the object A, the control unit sets the pixel value of the object A in the n-1 frame in which the motion is detected as the original image data pixel value, and then excludes the object pixel from the analysis during the n to n + 3 frame periods. In the case of the object B, the control unit sets the pixel value of the object B as the original image data pixel value in the n frames in which the motion is detected, and excludes it from the analysis object for the n + 1 to n + 3 frame periods thereafter. In the case of entity C, the controller sets the pixel value of the object C to the original image data pixel value in the n + 2 frame in which the motion is detected, and excludes it from the analysis object during the n + 3 frame period thereafter.

13 is a view for explaining the operation of the control unit according to the embodiment of the present invention. Referring to FIG. 13, the controller may control a pixel value corresponding to an entity whose cumulative number of motion detection times exceeds a second threshold to a second set value, and exclude it from abnormal object data, thereby excluding the pixel value from the analysis object. Here, the second threshold value and the second set value may be set through the user interface unit. Or through a control command of the management server. In Fig. 13, the second threshold value is set to one. The second set value is the pixel value of the original image data. In Fig. 13, in the case of entity A, the number of motion accumulation detection times is two in n frames. Therefore, the controller sets the pixel value of the object A as the original image data pixel value in the n frame, and excludes it from the analysis object during the (n + 1) to (n + 3) frame period thereafter. In case of entity B, the number of motion accumulation detection times in the (n + 2) frame is two. Therefore, the controller sets the pixel value of the object B as the original image data pixel value in the (n + 2) -th frame, and excludes it from the analysis object during the (n + 3) -th frame period. In the case of entity C, since the cumulative number of motion detection times is less than two times during the analysis frame period, the control unit continuously performs the analysis in the subsequent frame to control the pixel value.

14 is a view for explaining the operation of the control unit according to the embodiment of the present invention. 14, the controller may control the pixel value corresponding to the object in which the cumulative number of cumulative motion detection cumulative times exceeds the second threshold to a second set value, and exclude it from the abnormal object data, have. Here, the second threshold value and the second set value may be set through the user interface unit. Or through a control command of the management server. In Fig. 14, the second threshold is set to one. The second set value is the pixel value of the original image data. In Fig. 14, in the case of entity A, the number of consecutive motion accumulation detection times in n frames appears twice. Therefore, the controller sets the pixel value of the object A as the original image data pixel value in the n frame, and excludes it from the analysis object during the (n + 1) to (n + 3) frame period thereafter. In the case of the object B and the object C, since the cumulative number of successive motion detection is less than two times during the analysis frame period, the control unit continuously performs the analysis in the subsequent frame to control the pixel value.

In the case of FIGS. 12 to 14, it can be determined that the entity satisfying a specific condition is determined to be a normal entity according to the number of motion detection times. Thus, the speed, accuracy, and efficiency of the image data captured inside the breeding ground where hundreds of thousands of poultry live in a few hundred or fewer animals can be greatly improved.

15 is a view for explaining the operation of the control unit according to the embodiment of the present invention. Referring to FIG. 15, the controller may control a pixel value corresponding to an object whose motion detection cumulative count is equal to or greater than a second threshold value to a second set value, and exclude the pixel value from analysis. Here, the second threshold value and the second set value may be set through the user interface unit. Or through a control command of the management server. In Fig. 15, the second threshold is set to two. The second set value may be implemented by any means for preventing the corresponding object or the corresponding pixel from being visually displayed. The second set value may be implemented, for example, by a masking process, a mosaic process, a transparent pixel process, or the like for the object or the corresponding pixel. Accordingly, when the object is classified as a normal object, the object is not visually displayed on the image data, and the abnormal object can be discriminated more accurately.

Referring again to FIGS. 1 and 2, the controller 114 may perform various commands for the operation of the image capturing apparatus 100.

The control unit 114 can perform an operation of the image capturing apparatus 100 by executing an instruction stored in the user interface unit 117 or the database 119, for example.

Or the control unit 114 can control various operations of the image capturing apparatus 100 by using the command received from the management server 200. [

The control unit 114 may control the photographing unit 11 to track and photograph a point or an object whose cumulative number of times of motion detection is equal to or greater than a third set value. The third set value may be set through the user interface unit 117 or through a control command of the management server 200. [ The control unit 114 controls the photographing unit 111 to track and photograph a specific area having an abnormal object to generate image data, thereby enabling continuous monitoring.

At this time, the control unit 114 may control the pan tilt unit 121 of the image pickup apparatus 100 to perform tracking photographing. The pan tilt section 121 can drive two motors in a pan (horizontal direction) and a tilt (vertical direction) to control the photographing area of the photographing section 111. The pan tilt unit 121 can adjust the direction of the shooting unit 111 to capture a specific area under the control of the controller 114. [ In addition, the pan tilt unit 121 may adjust the direction of the shooting unit 111 to track a specific object under the control of the controller 114.

The communication unit 115 can perform data communication with another imaging device, the data collection device 150, or the management server 200. For example, the communication unit 115 may be a wireless LAN (WLAN), a Wi-Fi, a Wireless Broadband (Wibro), a World Interoperability for Microwave Access The mobile terminal can perform data communication using a long distance communication technology such as Packet Access, IEEE 802.16, Long Term Evolution (LTE), and Wireless Mobile Broadband Service (WMBS).

Or communication unit 115 may include Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wide Band (UWB), ZigBee, and Near Field Communication (NFC). The wired communication technology can perform data communication using a short distance communication technology such as USB communication, Ethernet, serial communication, and optical / coaxial cable.

For example, the communication unit 115 may perform data communication with another imaging device or data collection device 150 using a local communication technique, and may perform data communication with the management server 200 using a remote communication technique However, the present invention is not limited thereto, and various communication technologies can be used in consideration of various matters of the breeding ground 10.

The communication unit 115 can transmit the original image data photographed by the photographing unit 111 to the data collection device 150 or the management server 200. [

Alternatively, the communication unit 115 may transmit at least one of the image data, the position distribution data, the operation data, and the coordinate information having the pixel value adjusted to at least one of the data collection device 150 and the remote management server 200. In this case, the coordinate information may refer to a point suspected of being an abnormal entity or a coordinate of an object.

The data transmitted through the communication unit 115 may be compressed data encoded through the encoding unit 118.

The display unit 116 may be a liquid crystal display (LCD), a thin film transistor liquid crystal display (TFT LCD), an organic light emitting diode (OLED), a flexible display ), A three-dimensional display (3D display), and an electronic ink display (e-ink display).

The display unit 116 may display at least one of image data and distribution data whose pixel values are adjusted through the control unit 114. [

Also, the display unit 116 can output the original image data photographed by the photographing unit 111 on the screen.

In addition, the display unit 116 may output various user interfaces or graphic user interfaces to the screen.

The user interface unit 117 generates input data for controlling the operation of the image sensing apparatus 100. The user interface unit 117 may include a key pad, a dome switch, a touch pad, a jog wheel, a jog switch, and the like. When the display unit 116 and the touch pad have a mutual layer structure to constitute a touch screen, the display unit 116 can be used as an input device in addition to the output device.

The user interface unit 117 can receive various commands for operation of the image capturing apparatus.

The encoding unit 118 encodes the original image data photographed by the photographing unit 111 or the processed image data processed through the data processing unit 112, the motion detecting unit 113, and the control unit 114 into digital signals. For example, the encoding unit 118 may encode image data according to H.264, H.265, Moving Picture Experts Group (MPEG), and Motion JPEG standard (Motion JPEG) standards.

The database 119 may be a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (for example, SD or XD memory, etc.) A random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a PROM Programmable Read-Only Memory). In addition, the image sensing apparatus 100 may operate in association with web storage or operate a web storage that performs a storage function of the database 119 on the Internet.

The database 119 may store image data taken by the photographing unit 111 and may store image data for a certain period of time.

In addition, the database 119 may store data, programs, and the like necessary for the imaging apparatus 100 to operate.

In addition, the database 119 may store various user interfaces (UI) or graphical user interfaces (GUI).

The light source unit 120 can irradiate light in a direction that is directed by the control of the controller 114. For example, the light source unit 120 may include at least one laser diode (LD), a light emitting diode (LED). The light source unit can irradiate light of various wavelength ranges under the control of the control unit.

For example, the light source unit 120 may irradiate light of an infrared wavelength band for night image capturing. Alternatively, the light source unit 120 may irradiate ultraviolet light for photochemotherapy of cattle in a cage.

16 is a flowchart of an abnormal entity detection method according to an embodiment of the present invention.

Referring to FIG. 16, first, the photographing section photographs an image including a plurality of objects. The photographing unit is disposed inside the breeding ground to photograph a plurality of objects including poultry (S1601).

Next, the photographing unit generates image data using an image including a plurality of objects. One piece of image data may mean a single frame. The data processor sequentially generates a plurality of image data using an image (S1602).

Next, the data processing unit generates the position distribution data indicating the position distribution of the plurality of objects using the image data. The data processing unit generates position distribution data for a plurality of image data generated in a time-series manner (S1603).

Next, the motion detection unit generates motion data representing the movement of the motion entity among the plurality of entities using the image data. The data processor generates operation data for a plurality of image data generated in a time-series manner (S1604).

The generation of the position distribution data and the generation of the operation data may be performed simultaneously, or any one of the data generation processes may be performed first. However, the data generation step of any one of the position distribution data generation and the operation data need not necessarily be preceded by another data generation step.

Next, the control unit compares the position distribution data of the image data and the operation data to generate abnormal object data representing the abnormal object. The control unit compares the motion detection cumulative count and the cumulative motion detection cumulative count of the plurality of objects by comparing the position distribution data and the motion data with respect to the plurality of video data, and outputs the abnormal object data according to the accumulated motion detection cumulative count and the cumulative motion detection cumulative count (S1605).

Next, the control unit controls pixel display of a plurality of objects on the image data according to the cumulative number of motion detection and the cumulative number of motion ratio detection of abnormal object data. In operation S1606, the control unit classifies the normal object and the abnormal object according to the number of times the motion of the specific object is not detected and the number of times the motion is detected, and displays the pixel value corresponding to the normal object and the abnormal object differently on the image data.

The abnormal entity detection method according to the embodiment may be expressed by Equation (1).

[Equation 1]

_{Pixel t = Pixel t-1 (} 1-μ) + ㎼ t - F t

In Equation (1), μ can be changed according to the setting in the updateparameter.

In Equation (1), Pixel _t and Pixelt-1 are abnormal object data, which may indicate the pixel concentration as a value for displaying the presence or absence of an ideal object in pixels. A pixel having a higher probability that an abnormal object exists is displayed in a darker color. For example, if there is no probability that an ideal object exists, it is displayed as a primary color (white). The higher the probability of an ideal object is, the closer it is to red. . Therefore, Pixel _t and Pixelt-1 can be set to have a value between 0 and 1, and the closer to 0, the closer to the primary color (white), and the closer to 1, the reder.

In Equation (1), Pixel _{t - 1} is ideal object data of the immediately preceding frame in which the position distribution data and the operation data are accumulated. In Equation 1, Pixel _t And is updated by applying position distribution data and motion data of the current frame.

In Equation (1), Wt may be position distribution data of the current frame. The position distribution data may have a value between 0 and 1 as a probability of existence of an object in the corresponding pixel. The update parameter μ may be applied to the position distribution data. μ may be a very small value, for example 0.001. That is, the position distribution data is gradually accumulated in the pixel for a long time to be displayed on the pixel.

In Equation (1), F _t may be operation data of the current frame. The motion data is obtained by calculating the absolute value of the motion vector and may have a value of 0 or more. The size of the motion vector corresponds to the speed of the object, and therefore can have a value of 1 or more. When the operation data is not reflected in the operation data and the operation is detected in the corresponding pixel, the display of the corresponding pixel is controlled to be initialized.

Alternatively, the abnormal entity detection method according to the embodiment may be expressed by Equation (2) below.

&Quot; (2) "

Pixel _t = Pixel _t-1 (1-μ + ε) + ㎼ _t -F _t

※: update parameter, ε: offset parameter

In Equation (2), offset parameter? Is added in Equation (1), and the same explanation as Equation (1) is omitted. The offset parameter ε is a parameter that adjusts the accumulation of the position distribution data and can have a value of 1/10 to 1/100 relative to μ.

Alternatively, the abnormal entity detection method according to the embodiment may apply Equation 3 or Equation 4 as follows.

&Quot; (3) "

Pixelt = Pixelt-1 (1-μ) + μWt - κFt

&Quot; (4) "

_{Pixel t = Pixel t-1 (} 1-μ + ε) + ㎼ t - κF t

※: update parameter, ε: offset parameter, κ: update parameter

Equation (3) or (4) is obtained by multiplying the operation data F _t by the update parameter κ, and the same contents as in Equations (1) and (2) are omitted. constant κ is a parameter that adjusts the accumulation of operation data.

The abnormal entity detection method according to Equations (1) to (4) can additionally apply the following Equation (5).

&Quot; (5) "

max (Equation 1, 2, 3 or 4, 0)

Equation (5) is a formula for preventing the value of Equation (1), (2), (3) or (4) from falling below zero. For example, when the magnitude of the operation data (F _t ) is greater than the sum of the other parameter values and the value of Equation 1, 2, 3 or 4 becomes a negative value smaller than 0, Which is a control method for correcting the error.

17 is a flowchart of an abnormal entity detection method according to an embodiment of the present invention.

Referring to FIG. 17, the photographing unit first photographs a first image including a plurality of objects. The photographing unit is disposed inside the breeding ground and photographs a plurality of objects including poultry (S1701).

Next, the photographing unit generates first image data using a first image including a plurality of objects. The first image data may indicate a single frame (S1702).

Next, the data processing unit generates the first position distribution data indicating the position distribution of the plurality of objects using the first image data (S1703).

Next, the motion detection unit generates the first motion data indicating motion of the motion entity among the plurality of entities using the first image data (S1704).

The generation of the first position distribution data and the generation of the first operation data may be performed simultaneously or any one of the data generation processes may be performed first. However, any one of the generation of the first position distribution data and the generation of the first operation data need not necessarily precede the other data generation steps.

Next, the control unit compares the first position distribution data and the first operation data to generate first abnormal entity data representing the abnormal entity. In operation S1705, the controller compares the first position data and the first motion data with respect to the first image data, and generates the first abnormal entity data according to motion of the plurality of objects.

Next, the photographing section photographs a second image including a plurality of objects (S1706).

Next, the photographing unit generates second image data using a second image including a plurality of objects. The second image data may indicate a single frame (S1707).

Next, the data processing unit generates second position distribution data indicating the position distribution of the plurality of objects using the second image data (S1708).

Next, the motion detection unit generates second motion data indicating motion of the motion entity among the plurality of entities using the second image data (S1709).

The generation of the second position distribution data and the generation of the second operation data may be performed simultaneously, or any one of the data generation processes may be performed first. However, any one of the second position distribution data generation and the second operation data generation step need not necessarily be preceded by another data generation step.

Next, the control unit compares the first ideal entity data, the second position distribution data, and the second operation data to generate second ideal entity data. The control unit compares the first abnormal entity data with the second motion distribution data and the second motion data to compute the cumulative number of motion detection accumulations of the plurality of entities and the accumulated cumulative detections of the plurality of entities, The second abnormal entity data is generated according to the number of times (S1710).

Next, the control unit controls pixel display of a plurality of objects on the image data according to the second ideal object data. The control unit classifies the normal object and the abnormal object according to the number of times the motion of the specific object is not detected and the number of times the motion is detected, and displays the pixel value corresponding to the normal object and the abnormal object differently on the image data (S1711).

Although steps S1701 to S1711 are briefly shown as generating the first ideal entity data and the second ideal entity data, the abnormal entity data is constantly generated and updated as the image data generation through the image capturing is continuously performed, And controls the display.

As used in this embodiment, the term " portion " refers to a hardware component such as software or an FPGA (field-programmable gate array) or ASIC, and 'part' performs certain roles. However, 'part' is not meant to be limited to software or hardware. &Quot; to " may be configured to reside on an addressable storage medium and may be configured to play one or more processors. Thus, by way of example, 'parts' are intended to be broadly interpreted as including the constituent elements, such as software components, object oriented software components, class components and task components, and processes, , Subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. The functions provided in the components and components may be further combined with a smaller number of components and components or further components and components. In addition, the components and components may be implemented to play back one or more CPUs in a device or a secure multimedia card.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the present invention as defined by the following claims It can be understood that

100:
111:
112:
113:
114:
115:
116:
117: User interface section
118:
119: Database
120: Light source
121: Pan tilt part

Claims (37)

A data processing unit for generating position distribution data representing a position distribution of the plurality of objects using image data generated from an image including a plurality of objects;
A motion detector for generating motion data representing movement of the motion object among the plurality of objects using the generated image data; And
And a controller for comparing the position distribution data and the operation data to generate abnormal entity data representing an abnormal entity,
Wherein the location distribution data is data on which the presence or absence of an entity is displayed as a probability on a pixel-
Wherein the operation data is data indicating whether or not a motion exists for each pixel on the image data,
Wherein the abnormal entity data includes data indicating the presence or absence of an abnormal entity for each pixel as a probability,
The data in which the existence of the abnormal entity is displayed as a probability includes data indicating the presence or absence of the generated abnormal entity as a probability, data in which the existence of the entity is indicated as a probability, Detection device.
The method according to claim 1,
Wherein the control unit calculates a cumulative number of motion detection accumulations and a cumulative cumulative motion accumulation count per pixel for each of the plurality of image data using the data indicating the presence or absence of the motion, And generating the abnormal object data by reflecting the data and the presence or absence of the object on data displayed as a probability.
3. The method of claim 2,
Wherein the control unit controls pixel display of the plurality of objects on the image data according to the abnormal entity data.
The method of claim 3,
Wherein the controller increments the pixel value corresponding to the motion non-detection cumulative count of the operation data step by step.
The method of claim 3,
Wherein the controller increments the corresponding pixel values in accordance with the number of consecutive motion non-detection accumulation times of the operation data.
The method of claim 3,
Wherein the control unit controls the pixel value corresponding to the motion non-detection cumulative count of the operation data when the cumulative number of times of motion non-detection exceeds the first threshold to a first set value.
The method of claim 3,
Wherein the control unit controls the pixel value corresponding to the continuous motion non-detection cumulative count of the operation data to exceed a first threshold value to a first set value.
8. The method according to claim 6 or 7,
Wherein the first set value is a maximum value of the pixel values.
The method of claim 3,
Wherein the control unit gradually reduces the pixel value corresponding to the motion detection cumulative count of the operation data.
The method of claim 3,
Wherein the controller gradually reduces the pixel values corresponding to the consecutive motion detection cumulative counts of the operation data.
The method of claim 3,
Wherein the control unit controls the pixel value in which motion is detected in the operation data to a second set value.
12. The method of claim 11,
Wherein the control unit excludes, on the abnormal entity data, a pixel whose motion has been detected in the operation data.
The method of claim 3,
Wherein the control unit controls the pixel value corresponding to the motion detection cumulative count of the operation data when the cumulative number of motion detection exceeds the second threshold to a second set value.
14. The method of claim 13,
Wherein the control section excludes, on the abnormal entity data, a pixel whose motion detection cumulative number of operation data exceeds a second threshold value.
The method of claim 3,
Wherein the control unit controls the pixel value corresponding to the continuous motion detection cumulative count of the motion data to exceed a second threshold value to a second set value.
16. The method of claim 15,
Wherein the control unit excludes, on the abnormal entity data, a pixel whose consecutive motion detection cumulative count of the operation data exceeds a second threshold value.
17. The method according to any one of claims 11 to 16,
And the second set value is a pixel value of the original image data.
The method according to claim 1,
Wherein the data processing unit extracts feature points of the object from the image data, and generates the position distribution data indicating a presence or absence of the object by using a learning algorithm.
The method of claim 3,
Wherein the control unit initializes a pixel value in which motion is detected in the operation data.
The method according to claim 1,
Wherein the control unit adds the difference data of the data indicating the existence of the entity as a probability and the data indicating the presence or absence of the motion to the data displayed as the probability of existence of the previously generated ideal entity, Object detecting device.
A photographing unit photographing an image including a plurality of objects and generating image data;
A data processing unit for generating position distribution data representing a position distribution of the plurality of objects using the image data;
A motion detector for generating motion data representing movement of the motion object among the plurality of objects using the image data; And
And a controller for comparing the position distribution data and the operation data to generate abnormal entity data representing an abnormal entity,
Wherein the location distribution data is data on which the presence or absence of an entity is displayed as a probability on a pixel-
Wherein the operation data is data indicating whether or not a motion exists for each pixel on the image data,
Wherein the abnormal entity data includes data indicating the presence or absence of an abnormal entity for each pixel as a probability,
Wherein the data indicating the presence or absence of the abnormal entity is displayed as data indicating the presence or absence of the generated abnormal entity as a probability, data indicating the presence or absence of the entity as a probability, .
22. The method of claim 21,
Wherein the control unit calculates a cumulative number of motion detection accumulations and a cumulative cumulative motion accumulation count per pixel for each of the plurality of image data using the data indicating the presence or absence of the motion, And generating the abnormal object data by reflecting the data and the presence or absence of the object on data displayed as a probability.
22. The method of claim 21,
Wherein the control unit adds the difference data of the data indicating the existence of the entity as a probability and the data of the presence or absence of the motion to the data displayed as the probability of existence of the past abnormal entity created in the past, Device.
22. The method of claim 21,
Wherein the control unit controls pixel display on the image data according to the abnormal entity data.
Capturing an image including a plurality of objects to generate image data;
Generating position distribution data indicating a position distribution of the plurality of objects using the image data;
Generating motion data indicating movement of an operation object among the plurality of objects using the image data; And
Comparing the position distribution data and the operation data to generate abnormal entity data representing an abnormal entity,
Wherein the location distribution data is data on which the presence or absence of an entity is displayed as a probability on a pixel-
Wherein the operation data is data indicating whether or not a motion exists for each pixel on the image data,
Wherein the abnormal entity data includes data indicating the presence or absence of an abnormal entity for each pixel as a probability,
The data in which the existence of the abnormal entity is displayed as a probability includes data indicating the presence or absence of the generated abnormal entity as a probability, data in which the existence of the entity is indicated as a probability, Detection method.
26. The method of claim 25,
Wherein the generating of the abnormal entity data comprises:
A motion detection unit for calculating a cumulative number of motion detection accumulations and a cumulative number of motion accumulation per pixel for each of the plurality of image data using the data indicating the presence or absence of the motion, And generating the abnormal object data by reflecting the presence or absence of the object on data displayed as a probability.
26. The method of claim 25,
Wherein the step of generating the abnormal entity comprises:
Generating the abnormal entity data by adding the difference value of the data indicating the presence or absence of the entity as the probability and the data indicating the presence or absence of the motion to the data displayed as the probability of existence of the abnormal entity generated in the past Anomaly detection method.
26. The method of claim 25,
And controlling pixel display on the image data according to the abnormal entity data. delete delete delete delete delete delete delete delete delete

Images