JP5105972B2 - Coordinate conversion method, parameter adjustment method, and monitoring system - Google Patents

Description

  The present invention relates to a monitoring system.

  For example, using an imaging device such as a television camera (TV camera), an object that enters the monitoring target area is monitored. In addition, a technique in which a device or a system automatically performs monitoring instead of manned monitoring by a monitor is being studied.

  As an example of a technique for automatically detecting an object that enters a monitoring target area, a monitoring technique using a method called a background difference method has been widely used. The object detection method based on the background difference method calculates a difference in luminance (or pixel value) between an input image obtained from an imaging device or the like and a reference background image on which an object to be detected is not reflected, and the detected value is Monitoring is performed on the assumption that an object to be detected exists in a change area larger than a predetermined threshold value (threshold value) or that there is a possibility of such an object. As a method for monitoring an object to be detected, in addition to the background subtraction method, by calculating a difference between frames using a difference between a plurality of input images obtained at different times and a motion of a local portion between two images. There is an optical flow method for detecting the flow of motion in an image, and an appropriate method is implemented according to the environmental conditions of the monitoring target area.

In the monitoring system, in order to determine whether the object detected by the method from the captured image is really an object to be detected, reference information (for example, size information of the object to be detected is widely used) Judgment is made by comparing the information of the object extracted from the input image. This reference information needs to be set in advance before operating the monitoring system. For example, when the size information is used as the reference information used in the above example, the apparent size of the object on the image changes according to the distance between the camera and the object. In other words, if the object is close to the camera (lower part of the image), it will appear larger on the image, and if it is away from the camera (upper part of the image), it will appear smaller. You must set the size to see the object to be viewed. In the conventional method, the size on the image of the object to be detected is specified at at least two positions on the image, and the size on the image of the object existing at the position not specified is set at the specified position. A method of interpolating from the size on the image is taken. In this method, in principle, if there is size information of an object to be detected at two positions, the size information at an arbitrary position on the image can be interpolated. Usually, however, the number of positions of the object specified on the image It is necessary to increase the size and reduce the size setting error, which is a very complicated operation.
JP 2001-273500 A JP-A-2005-57743

  In the conventional monitoring system, as described above, in order to determine whether the object extracted from the input image is an object to be detected, it is necessary to set information on the object to be detected on the image. In this setting, in order to reduce an error, it is necessary to set a lot of information, and there is a problem that the setting work becomes very complicated.

  The present invention has been made in view of such a conventional situation, and converts an object expressed in a first coordinate system extracted from a captured input image into a second coordinate system similar to a map of a monitoring area. Thus, an object of the present invention is to provide a coordinate conversion method, a parameter adjustment method, and a monitoring system that can solve a change in apparent information due to a position on an image and can set a monitoring system with less work.

In order to solve the above-described problem, the present invention processes an input image obtained by imaging a monitoring area by means of an imaging device having an imaging lens and an imaging element, and based on information on an object to be detected. It is determined whether or not the object extracted from the image is an object to be detected, and the first coordinate system of the input image obtained by the means such as the imaging device is set to the height of installation of the means such as the imaging device, and Monitoring having a coordinate system conversion means for converting to a second coordinate system based on at least three parameters: a depression angle looking down from the height of installation of the means such as an imaging device and a viewing angle or a focal length of the means such as the imaging device In the system,
The viewing angle or the focal length is calculated based on the size of the imaging element included in the unit such as the imaging device and the focal length of the imaging lens included in the unit such as the imaging device, or
The depression angle to be looked down from the installation height is calculated based on at least two of the width information of any one coordinate of the rectangle or the line segment set in the first coordinate system, or
The installation height is calculated based on at least one of height information of any one coordinate of a rectangle or a line segment set in the first coordinate system. This is a characteristic parameter adjustment method.

  A monitoring system is characterized by using the parameter adjustment method described above.

  According to the present invention, at least three of the height of installation of the means such as the imaging device, the depression angle looking down from the height of installation of the means such as the imaging installation, and the viewing angle or focal length of the means such as the imaging device The information of the object extracted from the input image is converted from the first coordinate system to the second coordinate system based on the parameters, and it is determined whether the object extracted from the input image is to be detected by the three parameters. By doing so, it is possible to reduce the setting work of the monitoring system, and to realize a coordinate conversion method, a parameter adjustment method, and a monitoring system that can be easily set by the operator.

  A first embodiment according to the present invention will be described with reference to the drawings. FIG. 1 is a block diagram showing a configuration of a monitoring system according to the present invention. The monitoring system of this example includes an imaging device 101, an object detection device 102, a display device 103, a setting device 104, and access lines 105 to 107. The imaging device 101 captures an area to be monitored, and the captured input image detects an object that enters the monitoring target area by the object detection device 102. The detection image, the detection result, and the setting device 104 Information obtained by using values calculated from camera parameters set in advance is displayed on the display device 103. The access lines 105 to 107 may be connected to a network such as an analog telephone network, an ISDN network, a digital leased line network, or the Internet.

  By tracking the intruding object and controlling the TV camera so that areas other than the monitoring target such as private houses and privacy that are not the monitoring target are not reflected in the field of view of the TV camera, the object that has entered the monitoring area is accurately Detect and track.

  A tracking method for tracking an intruding object with an imaging device configured to be able to control at least one of the imaging direction and zoom, captures one frame of an image from the imaging device, detects the current position of the intruding object from the image, and The current or predicted field of view of the imaging device is calculated, and it is determined whether or not the calculated current or predicted field of view includes the imaging prohibited region. If not, the imaging device is configured based on the detection information of the intruding object. It is configured to control at least one of an imaging direction and zoom, and to display the alarm / tracking information by imaging the current or predicted visual field range with the imaging device.

  Next, the operation of the setting device 104 will be described with reference to FIG. FIG. 2 is an example of an operation screen of the setting device 104. The operation screen 201 includes an image display unit 202, a depression angle parameter setting 203, a height parameter setting 204, a viewing angle parameter setting 205, a parameter setting button 206, a live button 207, and a file selection button 208. Hereinafter, three values set by the depression angle parameter setting 203, the height parameter setting 204, and the viewing angle parameter setting 205 are referred to as camera parameters. Also, when setting camera parameters for the first time, default values (for example, 45 ° for the depression angle parameter, 1.0 [m] for the height parameter, and 45 ° for the viewing angle parameter) are set in advance. It shall be.

  In the image display unit 202, an input image represented by a first coordinate system (hereinafter referred to as a camera coordinate system) obtained by the imaging device 101 is displayed on a second coordinate system (hereinafter referred to as world coordinates) based on camera parameters. The image converted to (system) is displayed.

  Here, two methods for displaying an image on the image display unit 202 will be described. As a first method, when the live button 207 is pressed, the latest image captured by the imaging apparatus 101 is transmitted from the area setting apparatus, and the acquired image is converted into an image of the world coordinate system and displayed. As a second method, a still image captured by the imaging apparatus 101 is prepared in advance, a file selection dialog is displayed by pressing a file selection button, and when an image to be displayed is selected, the corresponding image is displayed in the world coordinate system. Convert to image and display. For example, when the image of FIG. 4 is displayed on the operation screen 201, it is converted into an image of the world coordinate system and displayed like the image of the image display unit 202. A means for converting an image into a world coordinate system image will be described later.

  In the above description, the image to be used is a still image, but a moving image may be used. In this case, a button for playing back a moving image and a button for pause (not shown) are added to the operation screen 201, and camera parameters are set with the moving image paused.

  Next, a method for setting camera parameters will be described with reference to FIGS. The camera parameters are changed using three of the depression angle parameter setting 203, the height parameter setting 204, and the lateral viewing angle parameter setting 205. In the depression angle parameter setting 203, the depression angle 501 of the imaging apparatus 101 is set. In the height parameter setting 204, the height 502 where the imaging apparatus 101 is installed is set. In the viewing angle setting 205, the horizontal viewing angle 601 of the imaging apparatus 101 is set. The operator sets the depression angle, height, and viewing angle parameters of the installed imaging apparatus 101 using each setting. Note that the vertical viewing angle 503 of the imaging device 101 is determined by the aspect ratio (aspect ratio) of the imaging device of the imaging device 101 to be used. For example, when an element having a ratio of 4 to 3 is used, The viewing angle 503 in the vertical direction is 75% of the viewing angle 601 in the horizontal direction. Therefore, since the viewing angle in the vertical direction and the horizontal direction of the imaging device 101 is essentially one piece of information, the viewing angle of the imaging device 101 is set as a representative by the viewing angle 601 in the horizontal direction. When the parameters for each setting are changed, the image in the world coordinate system of the image display unit 202 is updated based on the changed parameters.

  Another method for setting camera parameters will be described. When calculating the camera parameters of the depression angle, height, and viewing angle of the installed image sensing device 101 from the input image, while looking at the image of the world coordinate system displayed on the image display unit 202, the width and height are considered regardless of the position of the image. The camera parameters can be set by changing the depression angle parameter setting 203, the height parameter setting 204, and the horizontal viewing angle parameter setting 205 so that the angle becomes constant. For example, as in the image of the image display unit 202 shown in FIG. 3, roads and the like are made parallel by making the width constant, and the height of road signs of the same height installed in different places is made constant. Adjust each setting slider so that the height remains constant. At this time, auxiliary lines for confirming whether the lines are parallel may be displayed. Also, make sure that structures that appear in the input image, such as windows, fences, bridge railings, etc., that can be considered to have a constant height, have the same height on the converted image displayed in the image display 202. This makes it easy to set camera parameters. In this case, in order to confirm whether the structure that can be regarded as having a constant height is the same height on the converted image displayed on the image display 202, for example, a line is drawn on the image and the structure is The length of the line may be displayed on the operation screen 201.

  Here, a method for saving the set camera parameters will be described. By pressing the parameter setting button 206, the three parameters set by the depression angle parameter setting 203, the height parameter setting 204, and the horizontal viewing angle parameter setting 205 are stored in, for example, a file, and the access line 106 is set. To the object detection device 102. When the object detection device 102 receives a file storing camera parameters, each parameter of the file is read and used as a camera parameter for determining whether or not the object extracted from the input image is an object to be detected.

  Next, a method for obtaining real coordinates from image coordinates using set camera parameters will be described. Here, the depression angle of the imaging device 101 is θT, the installation height of the imaging device 101 is H, the horizontal viewing angle of the imaging device 101 is θH, and the vertical viewing angle of the imaging device 101 is θV. Since the vertical viewing angle θV of the imaging device 101 is calculated from the horizontal viewing angle θH of the imaging device 101 as described above, the described depression angle θT, height H, and viewing angle θH are shown in FIG. Match the described camera parameters.

Each position on the image of the camera coordinate system included in the field of view is calculated using the angle of view θT, height h, field angle θH which is the horizontal viewing angle, and field angle θV which is the vertical viewing angle of the imaging device. Can be converted to a coordinate system.
For example, an example of converting a certain point (x ′, y ′) on the input image into world coordinates (x, y) is shown below.
For example, the depression angle θy for imaging the pixel represented by (x ′, y ′) on the image is represented by (Expression 1) when the number of pixels in the vertical direction of the input image is 480 pixels.
(Formula 1)

Further, the rotation angle θx for imaging the pixel (x ′, y ′) in the camera coordinates is expressed by (Expression 2) when the number of pixels of the input image is 640.
(Formula 2)

Therefore, the pixel at an arbitrary position represented by (x ′, y ′) on the input image in the camera coordinate system is obtained by (Equation 3) as the coordinates (x, y) of the world image in the world coordinate system. .
(Formula 3)






That is, the world image is obtained by performing coordinate conversion on the input image according to (Expression 1) to (Expression 3). Note that the coordinates of the position of the visual field range can be changed by panning, tilting, or zooming of the imaging apparatus. Further, the image converted into the world coordinate system can be returned to the camera coordinate system by performing the inverse conversion of the conversion expressed by (Expression 1) to (Expression 3).

In addition, the angle of view θH that is the horizontal viewing angle of the imaging device and the angle of view θV that is the vertical viewing angle are determined using the focal length f, the imaging element size horizontal width H, and the imaging element size vertical width V. For example, it can be expressed by Scheme 4 and Diagram 5.
(Formula 4)



(Formula 5)



In other words, if there is information on the focal length and the size of the image sensor, the focal length can be used for conversion to the world coordinate system as a camera parameter that is substituted for the information on the viewing angle.

  The image display unit 202 displays an image obtained by converting the input image based on the four points P1, P2, P3, and P4 expressed in the world coordinate system calculated by the above formula. The image displayed on the image display unit 202 in FIG. 2 is input with the four points P1 ′, P2 ′, P3 ′, and P4 ′ on the image display unit 202 corresponding to the four points P1, P2, P3, and P4 as vertices. The image is converted and displayed. For example, P1 ′ and P2 ′ can be displayed below the image display unit 202, and P3 ′ and P4 ′ can be displayed above the image display unit 202. It is also possible to display an image with a limit on the depth distance (distance represented by LF in the above formula) displayed on the image display 202 from the imaging device 101. For example, the depth is 25 [m]. When the restriction is applied, a portion where the Y coordinate of the converted pixel is 25 [m] or more is prevented from being displayed on the image display unit 202. Furthermore, it is also possible to display an image with a restriction on the distance from the imaging device 101 to the near side displayed on the image display 202 (distance represented by LN in the above formula). m], the portion where the Y coordinate of the converted pixel is 10 [m] or more is prevented from being displayed on the image display unit 202.

  By doing so, it is possible to set the camera parameters to be converted from the camera coordinate system to the world coordinate system. Furthermore, in the conventional camera coordinate system, the position, size, and area of the object extracted from the input image It is possible to determine what has been determined in the world coordinate system. In other words, an object extracted from an input image while taking into account the difference in the apparent size of the object at each position on the input image, a world coordinate system similar to a map (each position The same object has the same size). Therefore, it is not necessary to set the difference in the apparent size of the object in the monitoring system.

  In the present invention, the depression angle, height, and viewing angle of the imaging device 101 installed in the area setting are used as camera parameters, but the elevation angle is substituted for the depression angle, and the focal length is substituted for the viewing angle (in this case, the imaging device to be used). It is also possible to set as a parameter that information on the size of 101 image sensors is required).

A second embodiment according to the present invention will be described with reference to the drawings.
In this embodiment, camera parameters (focal length in units of pixels, camera depression angle, camera height) required to use the present invention (the coordinate conversion method, parameter adjustment method, and monitoring system) are converted into an imaging device. By estimating using an object with a known size in the captured image or the element size of the imaging device, it can be easily set in an interactive format (called a wizard), and even if the camera parameter is unknown This is a method that makes it possible to determine the position and size in the world coordinate system.

The configuration of the monitoring system according to the present invention is the same as that of the first embodiment except for the internal configuration of the setting device 104. The operation of the setting device 104 in the second embodiment will be described with reference to FIG.
FIG. 7 is an example of an operation screen of the setting device 104. The operation screen 700 has two display parts, an image display part 701 and a parameter determination wizard display part 702. The image display unit 701 displays an input image in the camera coordinate system obtained by the imaging device 101. It is assumed that the size (width: w × height: h) of the input image in this example is 640 × 480 (pix). The wizard display unit 702 includes an instruction 703 for a user who handles the setting device 104, a step number 704, an information setting window 705, and a “next” button 706. In this example, camera parameters are determined and set by performing several input / output operations on the image display unit 701 and the information setting window 705 in accordance with an instruction 703 to the user displayed on the wizard display unit 702. To do.

An example of the camera parameter setting operation of the setting device 104 is shown below.
Step 1 is the first operation in the wizard. In step 1, the camera parameter of the focal length of the pixel unit of the imaging device used for this monitoring system is set. At the start of the camera parameter setting operation, as an example, it is assumed that an instruction 703 to the user for executing step 1 and an information setting window 705 are displayed as shown in FIG. Assume that an input form 707 and a CCD size selection form 708 are provided. In step 1, the user inputs the focal length of the lens of the imaging device in mm on the focal length input form 707. Also, one size of the CCD image pickup element used in the image pickup apparatus is selected from the CCD size selection form 708. In the CCD size selection form 708, commonly used CCD size, for example, 2/3 inch (width W: 8.8 mm x height H: 6.6 mm), 1/2 inch (W: 6.4 mm x H: 4.8 mm) Are described on the wizard and can be selected by a selection formula. However, the user may be able to directly input the sizes W and H of any CCD image sensor. When the input is completed, the input information is stored in the setting device by pressing a “next” button 706, and the process proceeds to the next process, for example, step 2. The imaging apparatus used in this example has a focal length of 8.4 mm and a CCD size of 2/3 inch, and inputs the information to the information setting window 704 as shown in FIG. The focal length Fmm obtained in step 1 of this example is calculated by using the CCD image sensor size H and V and the input image pixel size w and h as a convenient measure for calculating the camera parameters. Convert to unit value Fp. (Formula 6) is an example of the calculation formula.
(Formula 6)

  Next, the operation of step 2 will be described. In step 2, at least two or more rectangular areas or line segments with known actual width [m] are selected on the image display unit 701, and the correspondence between the coordinates of each rectangle and line segment and the actual width is selected. Set camera parameters for camera depression. For example, the depression angle of the imaging apparatus 101 can be calculated based on the value obtained above. For example, when it is known that the road 709 in the display unit 701 is constant as the actual width 3 [m] regardless of the apparent width on the image, as shown in FIG. Draw rectangles 901 and 902 on the top and near. The rectangles 901 and 902 are drawn in a straight or polygonal shape using an input device such as a mouse. The coordinate information and the like of the two selected rectangles 901 and 902 are automatically displayed on the wizard display unit 702. For example, when setting with a rectangle, for the rectangle 901, the rectangular coordinates 903, pixel width 904, pixel height 905, and rectangle 902 are the rectangular coordinates 906, pixel width 907, and pixel height 908, respectively. 702 is displayed. In the case of a line segment, the coordinates of the end points, the pixel width, and the pixel height are displayed on the wizard display unit 702 (not shown). Next, the actual widths of the rectangles 901 and 902 or line segments are input to the actual width input forms 909 and 910, respectively. In this example, the actual widths of the rectangle 901 and the rectangle 902 are set to 3 [m]. When the “Next” button 706 is pressed after the input is completed, the depression angle of the imaging device 101 is instantaneously calculated using the coordinates of the rectangles 901 and 902 and the actual width value, and the wizard display unit 702 For example, the screen for performing the operation of step 3 is updated.

As an example, the depression angle θelv of the imaging device 101 is actually set to (x11, y11) for the start point (upper left) and (x12, y12) for the end point (lower right) of the camera coordinates of the selected rectangle (1) 901 input in step 2. The width 909 is W1, the start point (upper left) of the selected rectangle (2) 902 is (x21, y21), the end point (lower right) is (x22, y22), the actual width 910 is W2, and the imaging device 101 When the focal length is Fp, it is calculated by (Equation 7).
(Formula 7)

  Next, the operation of step 3 will be described. In step 3, at least one rectangular area or line segment with a known actual height [m] is selected on the image display unit 701, and the camera height is determined from the correspondence between the coordinates of the selected area and the actual height. Set the camera parameters. Thereby, for example, the height of the imaging apparatus 101 can be calculated. As an example, when the actual height of a humanoid object on the display unit 701 is known to be 1.8 [m], a rectangle 131 is drawn on the image display unit 701 so as to surround the object as shown in FIG. The rectangle 131 is drawn in the form of a straight line or a polygon using an input device such as a mouse. The information of the selected rectangle 131 is automatically displayed on the wizard display unit 702, for example, the coordinates 132 and the pixel size 133. Next, the actual height of the rectangle 132 is input to the actual height input form 134, respectively. In this example, since the actual width of the rectangle 132 is known as 1.8 [m], the value is input to the input form 134. After completing the input, by pressing the “Next” button 706, the height of the imaging device 101 is instantaneously calculated using the coordinates of the rectangle 132, the actual height 134, and the depression angle of the imaging device 101 calculated in step 2. Is calculated.

As an example, the height Hc of the imaging device 101 is set such that the start point (upper left) of the camera coordinates 132 of the selected rectangle 131 input in step 3 is (x31, y31), the end point (lower right) is (x32, y32), and the actual When the height 134 is H3, the calculation is performed as follows using the focal length Fp and the depression angle θelv of the imaging apparatus 101.
(Formula 8)

As described above, the estimated values of the camera parameters such as the height Hc and the depression angle θelv of the imaging device 101 are obtained by Step 1, Step 2, and Step 3. In this embodiment, these processes are divided into steps 1 to 3 and performed in three stages, but the values obtained in steps 1 to 3 are input in a single step, for example. However, the process may be performed in one stage.
Next, the operation of step 4 will be described. In step 4, it is confirmed whether the size of the object existing in the image can be estimated correctly using the camera parameter estimated value calculated above. That is, based on the camera parameter estimation value, the input image is converted from the camera coordinate system to the temporary world coordinate system, and whether or not the size of any object in the image is correctly estimated on the temporary world coordinate system. By confirming, the validity of the camera parameter estimation value is examined. The reason why this operation is necessary is that the input in Steps 1 to 3, for example, selection of a rectangle or the like is performed manually, so that there is a possibility that an error occurs in the calculation and the desired value cannot be estimated correctly. It depends. In this example, the user selects an arbitrary area on the image display unit 701 as, for example, a rectangle 141 in FIG. The rectangle 141 to be selected is desirably an area where the size information is known or the approximate size information can be estimated by subjective judgment or the like. It is assumed that the rectangle 141 selected in this example is a humanoid object and can be subjectively estimated or known to have a height of about 1.8 m and a width of about 0.7 m. Next, using the coordinates 142 of the selected rectangle 141 in the camera coordinate system, based on the world coordinate system converted by the camera parameter estimated values, the actual width estimated value 144 and height estimated value 145 of the rectangle 141 are obtained. Calculate and display on the wizard 702 instantly. The values of the displayed estimated values 144 and 145 are compared with known or predictable size information, and it is determined by a specific determination criterion whether the difference is within an allowable range. As an example, when the estimated values of 1.7 m in height and 0.7 m in width are obtained for the selection rectangle 141 of the present embodiment, if the user sets the allowable error range of the estimated value to be ± 0.3 m, the estimated value is It is within the allowable range, and it can be said that the size information is correctly estimated by the camera parameter estimation value. A series of operations from selecting an arbitrary rectangle on the image display unit 701 and obtaining the estimated width value 144 and the estimated height value 145 can be performed any number of times in Step 4. Therefore, camera parameter estimation values can be evaluated for all regions such as objects having different distances and sizes. When it is confirmed that the camera parameter estimated value is sufficiently correct, the camera parameter estimated value is determined as a camera parameter in the monitoring system by pressing the “confirm” button 146. The determined parameter is displayed, for example, as a camera setting value 150 in FIG. 12, and can be set in the object detection apparatus 102. On the other hand, if it is not possible to determine that the camera parameter estimated value is appropriate, the “redo” button 147 is pressed, and the steps are repeated from the middle to reestimate the camera parameters.
Since step 4 is for confirming the estimated camera parameter, step 4 may be omitted if the error of the camera parameter estimated by the wizard need not be considered in practice.

  As described above, it is possible to set camera parameters for conversion from the camera coordinate system to the world coordinate system, and the actual coordinates are obtained from arbitrary image coordinates in the input image by the coordinate conversion method described in the first embodiment. I can do it. In this embodiment, in particular, even if the camera parameters are unknown and the world coordinate system cannot be used in the past, it is possible to easily estimate and set the camera parameters in the wizard format. Processing based on the world coordinate system such as size determination can be used more easily on the monitoring system.

It is an example of a structure of the monitoring system of this invention. It is a figure for demonstrating an example of the operation screen of the setting apparatus of this invention. It is a figure for demonstrating an example of the operation screen of the setting apparatus of this invention. It is a figure for demonstrating the display of the setting apparatus of this invention. It is a figure for demonstrating the setting method of this invention. It is a figure for demonstrating the setting method of this invention. It is a figure which shows an example of the operation screen of the setting apparatus of this invention. It is a figure for demonstrating the setting method of this invention. It is a figure for demonstrating the setting method of this invention. It is a figure for demonstrating the setting method of this invention. It is a figure for demonstrating the setting method of this invention. It is a figure for demonstrating the setting method of this invention.

Explanation of symbols

101: imaging device, 102: object detection device, 103: display device, 104: setting device, 105: access line, 106: access line, 107: access line, 203: depression angle parameter setting, 204: height parameter setting, 205 : Viewing angle parameter setting, 206: parameter setting button, 207: live button, 208: file selection button 208, 501: depression angle of imaging device, 502: height of imaging device installation, 503: vertical viewing field of imaging device Angle, 601: Horizontal viewing angle of imaging device, 700: Operation screen, 701: Image display unit, 702: Wizard display unit, 703: Instruction to user, 704: Step number, 705: Information setting window, 706: “Next” button, 707: Focal length input form, 708: CCD size selection form, 709: Road, 901: Selection rectangle, 902: Selection rectangle, 903: Coordinates of selection rectangle, 904: Pixel width of selection rectangle, 905: Pixel of selected rectangle Height, 906: Coordinate of selected rectangle, 907: Pixel width of selected rectangle, 908: Pixel height of selected rectangle, 909: Actual width input form of selected rectangle, 910: Actual width input form of selected rectangle, 131: Selected Rectangle, 132: Coordinate of selected rectangle, 133: Pixel width of selected rectangle, 134: Pixel height of selected rectangle, 141: Selected rectangle, 142: Coordinate information of selected rectangle, 143: Pixel size of selected rectangle, 144: Selected Estimated actual width of rectangle, 145: Estimated actual height of selected rectangle, 146: Confirm button, 147: Redo button, 150: Camera setting value

Claims (4)

Processing the input image obtained by imaging the result monitoring region to an imaging equipment having an imaging lens and an imaging device, the first coordinate system thus obtained input image on the imaging equipment, the imaging equipment the height of the installation, and the depression angle overlooking the height of installation of the imaging equipment, into a second coordinate system based on at least three parameters of the viewing angle or the focal length of the imaging equipment, should be detected based on the object information, a Contact Keru parameter adjustment method in a monitoring system object extracted from the image is determined in the second coordinate system whether an object to be detected,
The viewing angle or focal length, the size of the imaging element the imaging equipment has, and is calculated based on the focal length of the imaging instrumentation imaging lens location has,
Before Ki俯 angle is calculated based on two width information in the rectangular or line segments set in the first coordinate system,
The installation height of the previous SL parameter adjustment wherein the benzalkonium calculated based on one of the height of the rectangle or a line segment set in the first coordinate system. An input image obtained by imaging a monitoring area by an imaging device having an imaging lens and an imaging element is processed, and it is determined whether an object extracted from the image is an object to be detected based on information on the object to be detected. The input image in the camera coordinate system obtained by the imaging device is at least of the installation height of the imaging device, the depression angle looking down from the installation height of the imaging device, and the viewing angle or focal length of the imaging device A parameter adjustment method in a surveillance system that converts to a world coordinate system based on three parameters,
A first step of the operation screen having the said monitoring system displays the focal length input form and the imaging device size selection form, accepts input of focal length F mm in size and the image pickup lens of the image pickup device,
An operation of displaying the input image and two actual width input forms on the operation screen and drawing two rectangular areas or line segments on the displayed input image using an input device included in the monitoring system; An operation of inputting the actual width value of the two rectangular areas or line segments to the two actual width input forms, and the coordinates of the drawn two rectangular areas or line segments in the camera coordinate system; A second step of calculating the depression angle θelv based on the two actual width values input and the input in the first step;
An operation for displaying the input image and the actual height input form on the operation screen, and drawing one rectangular area or line segment on the displayed input image using the input device, and the actual width input form And an operation of inputting the actual height value of the one rectangular area or line segment, and the coordinates of the drawn one rectangular area or line segment in the camera coordinate system and the two input A third step of calculating a height Hc of the installation based on a width value, an input in the first step, and a depression angle θelv calculated in the second step;
The input image is displayed on the operation screen, and an operation for drawing a rectangular region or a line segment corresponding to an arbitrary object on the displayed input image using the input device is received, and the rectangle corresponding to the object is displayed. Based on the coordinates of the area or line segment in the camera coordinate system and the three parameters obtained in the first to third steps, the width or height value of the object in the world coordinate system is estimated. And a fourth step for prompting the user to confirm the correctness of the estimation,
A parameter adjustment method, wherein the first to fourth steps are advanced in a wizard format. The parameter adjustment method according to claim 2,
In the first step, the focal length Fp in pixels is set.
Calculated by
In the second step, the starting point and the ending point are (x11, y11) and (x12, y12) for one of the drawn rectangular areas or line segments, the actual width is W1, and the starting point for the other rectangular area or line segment And the end point (x21, y21) and (x22, y22), the actual width W2, and the depression angle θelv
Calculated by
In the third step, the height Hc of the installation is set with the drawn width and the starting point of the rectangular region or line segment drawn as (x31, y31) and (x32, y32), the actual width as H3.
Calculated by
The parameter adjustment method according to claim 4, wherein the fourth step receives an instruction to redo the parameter adjustment in the first to fourth steps when the estimation accuracy is not sufficient. Monitoring system using a parameter adjustment method according to any one of claims 1 to 3.