JP6443144B2 - Information output device, information output program, information output method, and information output system - Google Patents

Description

  The present invention relates to an information output device, an information output program, an information output method, and an information output system.

  Conventionally, a technique for determining whether or not a cover is attached to a license plate of a vehicle is known (see, for example, Patent Document 1). For example, in Patent Document 1, an image area of a license plate is extracted from an image including a vehicle, a luminance difference between an average luminance of a number portion of the plate image region and an average luminance of a background portion is calculated, and the calculated luminance difference And a standard luminance difference (threshold), a technique for determining whether or not a cover is attached is disclosed.

JP 2013-196392 A

  However, since the brightness of the image area of the license plate also changes depending on the time zone when the image is captured, weather conditions, and the like, it is difficult to set an appropriate value as a threshold for determining whether or not the cover is attached. In particular, when the cover is colorless and transparent, it is difficult to set the threshold because there is little change in luminance depending on whether or not the cover is attached.

  In one aspect, the present invention provides an information output device, an information output program and an information output method, and an information output system that can accurately determine and output that a cover is attached to a license plate. For the purpose.

  In one aspect, the information output device obtains the brightness value of the road surface in a predetermined area and the brightness value of the license plate area of the vehicle from images obtained by capturing the road surface and the vehicle, and the vehicle number from the license plate area. An acquisition unit that acquires information, a storage unit that stores the luminance value and the number information together with date and time information when the image is captured, as the information of the image, and the acquisition unit detects the road surface from the first image. When the brightness value and the brightness value of the license plate area are acquired, the storage unit stores the image of the road surface and the vehicle captured in a predetermined time zone based on the time when the first image was captured. A plurality of second images in which the luminance value of the road surface is a luminance value within a predetermined range based on the luminance value of the road surface of the first image are selected, and a plurality of license plate regions of the second image A determination unit that determines whether or not a cover is attached to the license plate projected on the first image, based on a comparison result of the luminance value and the luminance value of the license plate region of the first image; When the determination unit determines that the cover is attached to the license plate, the acquisition unit outputs number information acquired from the first image and information indicating that the cover is attached. And an output unit.

  As one aspect, it is possible to accurately determine and output that the cover is attached to the license plate.

It is a figure showing roughly the composition of the surveillance system concerning one embodiment. FIG. 2A is a diagram illustrating the hardware configuration of the recognition apparatus, and FIG. 2B is a diagram illustrating the hardware configuration of the server. It is a functional block diagram of a recognition apparatus and a server. It is a figure which shows the data structure of recognition result DB. It is a flowchart which shows the process of a recognition apparatus. It is a figure which shows the still image by which the vehicle was imaged. FIG. 7A is a diagram illustrating a road surface region, and FIG. 7B is a diagram illustrating a road surface region from which a luminance value is acquired. It is a flowchart which shows a cover presence determination process. It is a figure for demonstrating step S58 of FIG. It is a flowchart which shows a road surface area extraction process. It is a figure for demonstrating step S76 of FIG.

  Hereinafter, a monitoring system as an embodiment of the information output system will be described in detail with reference to FIGS.

  FIG. 1 schematically shows a configuration of a monitoring system 100 according to an embodiment. As shown in FIG. 1, the monitoring system 100 includes a plurality of monitoring cameras 10 as imaging devices, a plurality of recognition devices 20, and a server 70 as an information output device. The monitoring camera 10 and the recognition device 20 are connected by a communication cable or the like, and the recognition device 20 and the server 70 are connected to a network 80 such as the Internet.

  For example, the monitoring camera 10 is installed in the vicinity of a road, and images the road and vehicles traveling on the road at predetermined time intervals. As an example, the monitoring camera 10 captures a still image, and transmits still image data (still image data) to the recognition device 20. Note that the monitoring camera 10 may capture a moving image and transmit a frame included in the moving image to the recognition device 20.

  The recognition device 20 is provided in the vicinity of each monitoring camera 10 corresponding to each monitoring camera 10, receives still image data captured by the monitoring camera 10, and receives information (recognition result) from the still image data. ) Or still image data is transmitted to the server 70. The recognition result includes the brightness value of the part (plate part) corresponding to the license plate in the still image, such as the serial number (four-digit number) recognized from the license plate in the still image, and the road surface in the still image. The brightness value of the corresponding part (road surface area), the iris value (F value) of the monitoring camera 10 and the like are included.

  FIG. 2A shows the hardware configuration of the recognition device 20. As shown in FIG. 2A, the recognition device 20 includes a CPU (Central Processing Unit) 90, a ROM (Read Only Memory) 92, a RAM (Random Access Memory) 94, and a storage unit (here, an HDD (Hard Disk Drive)). ) 96, a network interface 97, a portable storage medium drive 99, and the like. Each component of the recognition device 20 is connected to a bus 98. The CPU 90 executes the program stored in the ROM 92 or the HDD 96 or the program read from the portable storage medium 91 by the portable storage medium drive 99, thereby causing the recognition device 20 to function as each unit shown in FIG. .

  Specifically, as illustrated in FIG. 3, when the CPU 90 executes a program, the recognition device 20 functions as an image acquisition unit 32, a vehicle presence / absence determination unit 34, an information recognition unit 36, and a transmission unit 38.

  The image acquisition unit 32 acquires still images captured by the monitoring camera 10 at a predetermined interval (for example, every several seconds) and transmits the still images to the vehicle presence / absence determination unit 34. The vehicle presence / absence determination unit 34 determines whether or not the vehicle is captured in the still image received from the image acquisition unit 32. The vehicle presence / absence determination unit 34 determines, for example, whether or not the vehicle is imaged using template matching using a template image of the vehicle. However, the present invention is not limited to this, and it may be determined by another method whether or not the vehicle is imaged.

  The information recognition unit 36 recognizes the serial number recognized from the license plate in the still image, the luminance value of the license plate area in the still image, and the luminance value of the portion (road surface area) corresponding to the road surface in the still image, The iris value of the monitoring camera 10 is recognized from Exif (Exchangeable image file format) information attached to the still image. In the following, a license plate area in a still image is simply referred to as a “plate portion”.

  The transmission unit 38 transmits the information recognized by the information recognition unit 36 and the still image data acquired by the image acquisition unit 32 to the server 70. The transmission unit 38 transmits only still image data to the server 70 when the vehicle presence / absence determination unit 34 determines that there is no vehicle.

  Returning to FIG. 1, the server 70 receives the still image data and the information recognized from the still image transmitted from each recognition device 20, and whether or not the vehicle in the still image has a cover on the license plate. Is a device that determines the output and outputs the determination result. The server 70 has a hardware configuration as shown in FIG. Specifically, as shown in FIG. 2B, the server 70 includes a CPU 190, a ROM 192, a RAM 194, a storage unit (HDD) 196 as a storage device, a network interface 197, a portable storage medium drive 199, and the like. I have. Each component of the server 70 is connected to the bus 198. The CPU 190 executes a program (including an information output program) stored in the ROM 192 or the HDD 196, or a program (including an information output program) read from the portable storage medium 191 by the portable storage medium drive 199. The server 70 functions as each unit shown in FIG. FIG. 3 also shows a recognition result DB (database) 52 and an image DB 54 as storage units stored in the HDD 196 of the server 70 or the like.

  As illustrated in FIG. 3, when the CPU 190 executes the program, the server 70 functions as a reception unit 42 as an acquisition unit, a cover presence / absence determination unit 44 as a determination unit, an output unit 46, and a road surface area extraction unit 48. To do.

  The reception unit 42 receives still image data and information transmitted from the transmission unit 38 of the recognition apparatus 20 and stores the received still image data and information in the recognition result DB 52. In addition, when only the still image data is transmitted from the transmission unit 38 (when the recognized information is not transmitted), the reception unit 42 transmits the still image data to the road surface region extraction unit 48. To do.

  Based on the data and information stored in the recognition result DB 52, the cover presence / absence determination unit 44 determines whether or not the vehicle in the still image has a cover on the license plate.

  When there is a vehicle with a cover on the license plate, the output unit 46 displays the vehicle number information and information indicating that the cover is attached with a terminal (for example, police) connected to the network 80. Terminal).

  The road surface area extraction unit 48 uses the still image data received from the reception unit 42 to extract the road surface area (the area where the vehicle travels) of the still image captured by each monitoring camera 10, and recognizes the recognition device 20. To the information recognition unit 36.

  Here, the data structure of the recognition result DB 52 will be described with reference to FIG. The recognition result DB 52 has fields of “date and time”, “point”, “imaging direction”, “serial number”, “iris value”, “plate portion luminance value”, and “road surface region luminance value”. Information on the date and time when the still image was captured is stored in the “date and time” field, and information on the location where the still image is captured (the location where the captured surveillance camera 10 is installed) is stored in the “location” field. Is stored, and information on the direction in which the captured surveillance camera 10 is facing is stored in the “imaging direction” field. The “serial number” field stores information on the serial number of the license plate recognized from the still image, and the “iris value” field stores the iris value (F) of the surveillance camera 10 at the time when the still image was captured. Value) is stored. The field “brightness value of the plate portion” stores the luminance value obtained from the plate portion of the still image, and the field “brightness value of the road surface region” stores the luminance value from the road surface region of the still image. The obtained luminance value is stored. The image DB 54 is a database that stores images, but a description of the data structure and the like is omitted. As the license plate information (plate information), in addition to the “serial number”, a kana character or the like such as a classification number or a transportation branch may be stored in the recognition result DB 52.

(Processing of recognition device 20)
Next, the processing of the recognition device 20 will be described in detail along the flowchart of FIG. 5 with appropriate reference to other drawings. As a premise of the processing in FIG. 5, the imaging range of a certain monitoring camera 10 is fixed, and the road surface area through which the vehicle passes in the imaging range is indicated by hatching in FIG. It shall be specified. A method for extracting the road surface area will be described later.

  In the process of FIG. 5, first, in step S <b> 10, the image acquisition unit 32 acquires still image data captured by the monitoring camera 10. Specifically, the image captured by the monitoring camera 10 is digitized and loaded into the memory. Next, in step S12, the vehicle presence / absence determination unit 34 determines whether or not the vehicle is imaged in the acquired still image data. When judgment here is affirmed, it transfers to step S14. If the determination in step S12 is negative, the process proceeds to step S20.

  When the process proceeds to step S14, that is, as shown in FIG. 6, when the vehicle is captured in the still image, the information authentication unit 36 performs plate information recognition processing from the acquired still image data. To do. Specifically, the information authentication part 36 extracts a vehicle part from a still image, and extracts, for example, a white, substantially rectangular area from the vehicle part as a plate part. And the information recognition part 36 recognizes the serial number (four-digit number) described in the number plate by performing the character recognition of the plate part, or the brightness value of the plate part (here, as an example) (It is assumed that the brightness value of the background part (white part) other than the characters is obtained). Note that the luminance value of the plate portion may be an average value of luminance values at a plurality of points in the plate portion.

  Next, in step S16, the information authentication unit 36 is hatched in FIG. 7B from the position of the extracted plate portion in the still image and the position of the road surface area shown in FIG. 7A. The range of the road surface area ahead of the plate portion is specified, and the luminance value of the specified range is calculated. Note that the information authentication unit 36 may obtain an average value of luminance values at a plurality of points in the specified range, or obtain a luminance value at one point in the specified range as the luminance value of the specified range. .

  Next, in step S18, the information authentication unit 36 converts the recognition result into text. The recognition result includes a serial number, a brightness value of the license plate portion, a brightness value of the road surface area, an installation location and an imaging direction of the monitoring camera 10 that can be acquired from Exif information attached to the data of the still image, and imaging The date / time and iris value are also included. Thereafter, the process proceeds to step S20.

  After step S18 or after the determination in step S12 is denied, the process proceeds to step S20, and the transmission unit 38 compresses the still image data acquired by the image acquisition unit 32.

  Next, in step S <b> 22, the transmission unit 38 creates transmission data and transmits it to the server 70. Here, if the determination in step S12 is affirmative, the transmission data includes compressed data (S20) of a still image in which the vehicle is imaged and a recognition result (S18) that is converted into text. . On the other hand, if the determination in step S12 is negative, the transmission data is compressed still image data (S20) in which the vehicle is not captured.

  If the determination in step S12 is negative, steps S20 and S22 may not be performed every time. For example, steps S20 and S22 may be performed when the determination in step S12 is denied only once in a predetermined time (for example, 5 minutes).

  As described above, when the process of step S22 is completed, the entire process of FIG. Note that the processing of FIG. 5 is repeatedly executed at predetermined time intervals (for example, at intervals of about once every several seconds).

(Processing of server 70)
Next, processing of the server 70 will be described. The server 70 executes a cover presence / absence determination process shown in FIG. 8 and a road surface area extraction process shown in FIG.

(Cover presence / absence determination process (FIG. 8))
Hereinafter, the cover presence / absence determination process will be described with reference to FIG. In the process of FIG. 8, first, in step S <b> 50, the reception unit 42 stands by until a recognition result is received from the recognition device 20. In this case, when the recognition result is received from the transmission unit 38 of the recognition device 20 (that is, when the process of step S22 is executed after the determination of step S12 in FIG. 5 is affirmed), the reception unit 42 performs the step The process proceeds to S52.

  In step S52, the receiving unit 42 stores the recognition result in the recognition result DB 52 and stores still image data in the image DB 54. Note that the image stored in the recognition result DB 52 this time corresponds to a first image that is an image to be processed and determined. The recognition result DB 52 stores recognition results received in the past from each recognition device 20.

  Next, in step S54, the cover presence / absence determination unit 44 creates a search condition based on the recognition result received this time. In this case, the cover presence / absence determination unit 44 sets, for example, a date and time, an imaging direction, a luminance value of a road surface area, and an iris value range as search conditions. For example, the date and time range can be set to one week before the still image capturing date received this time, and the current still image capturing time ± 1 hour. It can be said that the date / time range is set to a date / time range that is likely to be an environment similar to the current still image capturing environment. Further, for example, the range of the imaging direction can be set to the same direction as the imaging direction of the current still image. Further, for example, the range of the brightness value of the road surface area can be set to I-20 to I + 20 or the like, where I is the brightness value of the road surface area of the still image received this time. The range of the iris value can be set to F−0.2 to F + 0.2 or the like, where F is the iris value when the still image received this time is captured.

  Next, in step S56, the cover presence / absence determination unit 44 searches the recognition result DB 52 for a recognition result that satisfies the created search condition. Note that the recognition result of the image hit by the main search corresponds to the recognition result of the comparison target image (second image). Next, in step S58, the cover presence / absence determination unit 44 compares the brightness value of the searched plate part of the recognition result (hit) with the brightness value of the plate part included in the current recognition result. Next, in step S60, the cover presence / absence determination unit 44 determines whether or not the current recognition result is an outlier. Here, as a method for determining whether or not the value is an outlier, the following methods (1) and (2) can be adopted as an example.

 (1) The average of the brightness values of the plate part included in the searched (hit) recognition result is calculated, and when the brightness value of the current plate part falls below the average value by 10% or more, it is an outlier. Judge.

 (2) Calculate the standard deviation (σ) of the brightness value of the plate part included in the retrieved (hit) recognition result, and if the brightness value of the current plate part is not included in 3σ, Judge that there is.

  FIG. 9 schematically shows an example in which the determination in step S60 (determination (2) above) is affirmed. As shown in FIG. 9, when the brightness value (black circle) of the current plate portion is out of the range where other brightness values (white circles) exist, it is determined in step S60 that the current recognition result is an outlier. It has come to be.

  The determination methods (1) and (2) above are based on the assumption that there are a plurality of searched (hit) recognition results. However, when there is one hit recognition result, for example, When the difference from the brightness value of the plate portion included in the recognition result is equal to or greater than a predetermined value, it may be determined that the value is an outlier. Alternatively, when there is one hit search result, it may be determined that the determination is impossible and the fact may be output.

  If the determination in step S60 is negative, that is, if the value is not an outlier, the cover is not attached to the license plate, and the entire process of FIG. 8 is terminated without performing any special process.

  On the other hand, if the determination in step S60 is affirmed, the process proceeds to step S62, and the output unit 46 obtains a serial number included in the recognition result and information indicating that there is a high possibility that the cover is attached. Output to an external device (for example, a terminal used by the police). In this case, still image data may also be transmitted to an external device.

  Next, in step S64, the output unit 46 excludes the current recognition result (the recognition result stored in the recognition result DB 52 in step S52) from the recognition result DB 52. That is, in the subsequent process of FIG. 8, the current recognition result is not recognized. This makes it possible to accurately determine whether or not the cover is attached. In addition, after the process of step S64 is performed, the whole process of FIG. 8 is complete | finished.

(Road surface area extraction process (FIG. 10))
Next, the road surface area extraction process by the road surface area extraction unit 48 of the server 70 will be described in detail with reference to FIG.

  In the process of FIG. 10, first, in step S <b> 70, the road surface area extraction unit 48 waits until a predetermined timing comes. In the present embodiment, the predetermined timing is assumed to be, for example, every month.

  When the predetermined timing arrives, the process proceeds to step S72, and the road surface area extraction unit 48 specifies one of the recognition devices 20 existing on the network 80.

  Next, in step S74, the road surface area extraction unit 48 acquires still image data received from the identified recognition device 20. In addition, the vehicle is not reflected in the still image data received by the road surface area extraction unit 48 from the recognition device 20 as described above (see, for example, FIGS. 11A and 11B).

  Next, in step S76, the road surface region extraction unit 48 extracts a region (road surface region) that does not change from the acquired still image data. By this processing, it is possible to extract a range excluding a portion with a change such as a sidewalk. In addition, since the still image acquired in step S74 is an image in which the traveling vehicle is not shown, a range (road surface area) in which the vehicle travels is extracted as a portion having no change in step S74. .

  Next, in step S78, the road surface area extraction unit 48 transmits road surface area information to the recognition device 20 specified in step S72. In this case, as an example, image data in which the range of the road surface area as shown in FIG. 7A is specified is transmitted. The road surface area extraction unit 48 may transmit information specifying the range of the road surface area with coordinate values to the recognition device 20 (information recognition unit 36).

  Next, in step S80, the road surface area extraction unit 48 determines whether all the recognition devices have been specified in step S72. If the determination in step S80 is negative, the process returns to step S72, and the road surface area extraction unit 48 specifies the next recognition device, specifies the road surface region in the still image captured by the recognition device, and determines the road surface region. Processing such as transmission of information is executed.

  As described above, by executing the processing of FIG. 10, the road surface area information can be transmitted to each recognition device 20 at a predetermined timing (for example, every month). Thus, even when the road surface condition changes due to construction or the like, the cover presence / absence determination process of FIG. 8 can be performed with high accuracy.

  As described above in detail, according to the present embodiment, in the server 70, the reception unit 42 acquires the brightness value of the road surface area in front of the vehicle and the plate portion acquired from the image of the road surface and the vehicle. The brightness value and the vehicle number information acquired from the plate part are acquired. The recognition result DB 52 stores each luminance value, number information, and date / time information when the image is captured as a recognition result. Then, the cover presence / absence determination unit 44, when the luminance value of the road surface and the luminance value of the plate unit are acquired from an image (first image) with the receiving unit 42, is a predetermined time period based on the time when an image is captured. Among the images in which the road surface and the vehicle are captured in the (date and time range with similar environment), the luminance value of the road surface stored in the recognition result DB 52 is a luminance value within a predetermined range based on the luminance value I of the road surface of a certain image. A plurality of images (second images) that are (I-20 to I + 20) are selected, and an image based on the comparison result of the brightness values of the plate portions of the selected plurality of images and the brightness values of the plate portions of a certain image It is determined whether or not a cover is attached to the license plate projected on the screen. Further, when the cover presence / absence determination unit 44 determines that the cover is attached to the license plate, the output unit 46 outputs number information and information indicating that the cover is attached. As a result, by comparing the brightness values of the license plates using images with similar images and conditions, whether the cover is attached to the license plate is not affected by changes in sunshine conditions, etc. Can be accurately determined and output. Further, it is not necessary to set a threshold value for determining whether or not the cover is attached, and it is possible to reduce labor and cost for setting the threshold value.

  In the present embodiment, when the cover presence / absence determination unit 44 determines that the cover is attached to the license plate, the recognition result that is the basis of the determination is not stored in the recognition result DB 52. Thereby, only the information (recognition result) of the image in which the cover is not attached to the license plate can be stored in the recognition result DB 42, so that the determination accuracy of the cover presence / absence determination unit 44 can be improved.

  In the present embodiment, the cover presence / absence determination unit 44 compares the luminance values of the plurality of plate units with the luminance values of the plate units included in the recognition result, as in steps S58 and S60. Compared with the case of comparing with the luminance value of the part, it is possible to determine the presence / absence of the cover with high accuracy.

  Further, in the present embodiment, since a recognition result having a similar imaging direction and iris value is searched, it is possible to determine whether or not the cover is attached more accurately.

  In the above embodiment, the case has been described in which the iris value is acquired and used for the cover presence / absence determination process as the imaging condition of the monitoring camera 10, but is not limited thereto. Other values may be acquired as the imaging conditions of the monitoring camera 10 and used for the cover presence / absence determination process.

  In the above embodiment, in step S58 of FIG. 8, the cover presence / absence determination unit 44 calculates the brightness value of the plate part included in the searched recognition result and the brightness value of the plate part included in the current recognition result. Although the case of comparison has been described, the present invention is not limited to this. For example, when calculating the contrast value of the plate unit in the recognition device 20, the cover presence / absence determination unit 44 determines the contrast value of the plate unit included in the searched recognition result and the plate unit included in the current recognition result. Contrast values may be compared. For example, when the recognition device 20 calculates the character recognition rate (matching rate) of the license plate, the cover presence / absence determination unit 44 includes the matching rate included in the searched recognition result and the current recognition result. The matching rates may be compared. In these cases, the same process as in the above embodiment is performed except that the contrast value and the matching rate are used instead of the luminance value in step S58.

  In the above embodiment, in FIG. 5, when still images are captured at predetermined time intervals and it is detected that the vehicle is captured, the processing in steps S14 to S18 is performed on the image captured at the detected timing. However, the present invention is not limited to this. For example, when it is detected that the vehicle passes, a still image may be captured, and the processes of steps S14 to S18 may be performed on the image.

  In the above embodiment, the case where the monitoring system 100 includes the server 70 has been described. However, the present invention is not limited thereto, and the server 70 may be omitted. In this case, each recognition device 20 may have the function of the server 70 of FIG.

  The above processing functions can be realized by a computer. In that case, a program describing the processing contents of the functions that the processing apparatus should have is provided. By executing the program on a computer, the above processing functions are realized on the computer. The program describing the processing contents can be recorded on a computer-readable recording medium (except for a carrier wave).

  When the program is distributed, for example, it is sold in the form of a portable recording medium such as a DVD (Digital Versatile Disc) or a CD-ROM (Compact Disc Read Only Memory) on which the program is recorded. It is also possible to store the program in a storage device of a server computer and transfer the program from the server computer to another computer via a network.

  The computer that executes the program stores, for example, the program recorded on the portable recording medium or the program transferred from the server computer in its own storage device. Then, the computer reads the program from its own storage device and executes processing according to the program. The computer can also read the program directly from the portable recording medium and execute processing according to the program. Further, each time the program is transferred from the server computer, the computer can sequentially execute processing according to the received program.

  The above-described embodiment is an example of a preferred embodiment of the present invention. However, the present invention is not limited to this, and various modifications can be made without departing from the scope of the present invention.

In addition, regarding the description of the embodiment, the following additional notes are disclosed.
(Additional remark 1) The acquisition part which acquires the luminance value of the road surface of a predetermined area | region and the luminance value of the license plate area | region of the said vehicle from the image by which the road surface and the vehicle were imaged, and acquires the number information of the said vehicle from the said license plate area | region When,
As the information of the image, a storage unit that stores the luminance value and the number information together with date and time information when the image is captured,
When the acquisition unit acquires the brightness value of the road surface and the brightness value of the license plate area from the first image, the image of the road surface and the vehicle captured in a predetermined time zone based on the time when the first image was captured A plurality of second images in which the luminance value of the road surface stored in the storage unit is a luminance value within a predetermined range based on the luminance value of the road surface of the first image, and a plurality of the second images are selected. Whether or not a cover is attached to the license plate projected on the first image based on the comparison result of the luminance value of the license plate region of the second image and the luminance value of the license plate region of the first image A determination unit for determining
When the determination unit determines that a cover is attached to the license plate, the acquisition unit outputs number information acquired from the first image and information indicating that the cover is attached. An output unit to
An information output device comprising:
(Supplementary note 2) The supplementary note 1, wherein the storage unit does not store the information of the first image when the determination unit determines that a cover is attached to the license plate. Information output device.
(Supplementary Note 3) The supplementary note 1 or 2, wherein the determination unit selects a plurality of the second images from images whose imaging date / time is within a predetermined period from the imaging date / time of the first image. The information output device described in 1.
(Additional remark 4) The said memory | storage part memorize | stores the imaging direction of an image as information of the said image,
Any one of appendices 1 to 3, wherein the determination unit selects a plurality of the second images from images whose imaging direction is within a predetermined range based on the imaging direction of the first image. The information output device described in 1.
(Additional remark 5) The said memory | storage part memorize | stores the setting value of the imaging device which imaged the image as information of the said image,
The determination unit selects a plurality of the second images from images in which a setting value of the imaging device that captured the first image is within a predetermined range based on a setting value of the imaging device that captured the first image. 5. The information output device according to any one of supplementary notes 1 to 4,
(Additional remark 6) From the image where the road surface and the vehicle were imaged, the luminance value of the road surface of the predetermined area and the luminance value of the license plate area of the vehicle are acquired, the number information of the vehicle is acquired from the license plate area,
As the information of the image, each of the luminance value and the number information are stored together with date and time information when the image is captured,
When the road surface luminance value and the license plate region luminance value are acquired from the first image in the acquisition process, the road surface and the vehicle are imaged in a predetermined time zone based on the time when the first image was imaged. Among the images, a plurality of second images in which the brightness value of the road surface stored in the storing process is a brightness value within a predetermined range based on the brightness value of the road surface of the first image are selected, Whether or not a cover is attached to the license plate projected on the first image based on the comparison result of the luminance value of the license plate region of the second image and the luminance value of the license plate region of the first image Determine whether
When it is determined in the determination process that a cover is attached to the license plate, the number information acquired from the first image in the acquisition process, information indicating that the cover is attached, Output,
An information output program for causing a computer to execute processing.
(Supplementary Note 7) If the determination process determines that a cover is attached to the license plate, the storage process does not store the information on the first image. Information output program described in 1.
(Additional remark 8) In the said determination process, the said 2nd image selects two or more from the image whose imaging date is within the predetermined period from the imaging date of the said 1st image, or 6 characterized by the above-mentioned 7. The information output program according to 7.
(Additional remark 9) In the said process to memorize | store, the imaging direction of an image is memorize | stored as information of the said image,
Any one of appendices 6 to 8, wherein, in the determination process, a plurality of the second images are selected from images whose imaging direction is within a predetermined range based on the imaging direction of the first image. The information output program described in
(Additional remark 10) In the process to memorize | store, the setting value of the imaging device which imaged the image is memorize | stored as information of the image,
In the determination process, a plurality of the second images are selected from images in which a setting value of an imaging device that has captured the first image is within a predetermined range based on a setting value of the imaging device that has captured the first image; The information output program according to any one of appendices 6 to 9, characterized by:
(Additional remark 11) From the image which imaged the road surface and the vehicle, the luminance value of the road surface of a predetermined area and the luminance value of the license plate area of the vehicle are acquired, the number information of the vehicle is acquired from the license plate area,
As the information of the image, each of the luminance value and the number information are stored together with date and time information when the image is captured,
When the road surface luminance value and the license plate region luminance value are acquired from the first image in the acquisition process, the road surface and the vehicle are imaged in a predetermined time zone based on the time when the first image was imaged. Among the images, a plurality of second images in which the brightness value of the road surface stored in the storing process is a brightness value within a predetermined range based on the brightness value of the road surface of the first image are selected, Whether or not a cover is attached to the license plate projected on the first image based on the comparison result of the luminance value of the license plate region of the second image and the luminance value of the license plate region of the first image Determine whether
When it is determined in the determination process that a cover is attached to the license plate, the number information acquired from the first image in the acquisition process, information indicating that the cover is attached, Output,
An information output method, wherein a computer executes a process.
(Additional remark 12) When it is determined in the determination process that a cover is attached to the license plate, the storage process does not store the information of the first image. Information output method described in 1.
(Additional remark 13) In the said determination process, a plurality of said 2nd images are selected from the images whose imaging date and time are within a predetermined period from the imaging date and time of said 1st image. 12. The information output method according to 12.
(Additional remark 14) In the process to memorize | store, the imaging direction of an image is memorize | stored as information of the image,
Any one of appendices 11 to 13, wherein, in the determination process, a plurality of the second images are selected from images whose imaging direction is within a predetermined range based on the imaging direction of the first image. Information output method described in Crab.
(Supplementary Note 15) In the storing process, as the image information, a setting value of an imaging device that captured an image is stored,
In the determination process, a plurality of the second images are selected from images in which a setting value of an imaging device that has captured the first image is within a predetermined range based on a setting value of the imaging device that has captured the first image; The information output method according to any one of appendices 11 to 14, characterized in that:
(Supplementary Note 16) Recognition that obtains the brightness value of the road surface of the predetermined area and the brightness value of the license plate area of the vehicle from the image obtained by imaging the road surface and the vehicle, and obtains the vehicle number information from the license plate area Equipment,
The information output device according to any one of appendices 1 to 5, which acquires a brightness value of a road surface of the predetermined area, a brightness value of a license plate area of the vehicle, and number information of the vehicle from the recognition device;
An information output system comprising:
(Additional remark 17) The information output system of Additional remark 16 further equipped with the imaging device which images the said image.

10 Surveillance camera (imaging device)
20 recognition device 42 receiving unit (acquiring unit)
44 Cover presence / absence determination unit (determination unit)
46 output unit 52 recognition result DB (storage unit)
70 server (information output device)
100 Monitoring system (information output system)

Claims (8)

An acquisition unit that acquires a luminance value of a road surface of a predetermined area and a luminance value of a license plate area of the vehicle from an image obtained by imaging a road surface and a vehicle, and acquires the vehicle number information from the license plate area;
As the information of the image, a storage unit that stores the luminance value and the number information together with date and time information when the image is captured,
When the acquisition unit acquires the brightness value of the road surface and the brightness value of the license plate area from the first image, the image of the road surface and the vehicle captured in a predetermined time zone based on the time when the first image was captured A plurality of second images in which the luminance value of the road surface stored in the storage unit is a luminance value within a predetermined range based on the luminance value of the road surface of the first image, and a plurality of the second images are selected. Whether or not a cover is attached to the license plate projected on the first image based on the comparison result of the luminance value of the license plate region of the second image and the luminance value of the license plate region of the first image A determination unit for determining
When the determination unit determines that a cover is attached to the license plate, the acquisition unit outputs number information acquired from the first image and information indicating that the cover is attached. An output unit to
An information output device comprising:   2. The information output device according to claim 1, wherein when the determination unit determines that a cover is attached to the license plate, the storage unit does not store information on the first image. .   3. The determination unit according to claim 1, wherein the determination unit selects a plurality of the second images from images whose imaging date / time is within a predetermined period from the imaging date / time of the first image. 4. Information output device. The storage unit stores an imaging direction of an image as information on the image,
4. The method according to claim 1, wherein the determination unit selects a plurality of the second images from images whose imaging direction is within a predetermined range based on the imaging direction of the first image. The information output device according to claim 1. The storage unit stores setting values of an imaging device that has captured an image as information on the image,
The determination unit selects a plurality of the second images from images in which a setting value of the imaging device that captured the first image is within a predetermined range based on a setting value of the imaging device that captured the first image. The information output device according to any one of claims 1 to 4, wherein the information output device is characterized. From the image of the road surface and the vehicle imaged, obtain the luminance value of the road surface of the predetermined area and the luminance value of the license plate area of the vehicle, obtain the number information of the vehicle from the license plate area,
As the information of the image, each of the luminance value and the number information are stored together with date and time information when the image is captured,
When the road surface luminance value and the license plate region luminance value are acquired from the first image in the acquisition process, the road surface and the vehicle are imaged in a predetermined time zone based on the time when the first image was imaged. Among the images, a plurality of second images in which the brightness value of the road surface stored in the storing process is a brightness value within a predetermined range based on the brightness value of the road surface of the first image are selected, Whether or not a cover is attached to the license plate projected on the first image based on the comparison result of the luminance value of the license plate region of the second image and the luminance value of the license plate region of the first image Determine whether
When it is determined in the determination process that a cover is attached to the license plate, the number information acquired from the first image in the acquisition process, information indicating that the cover is attached, Output,
An information output program for causing a computer to execute processing. From the image of the road surface and the vehicle imaged, obtain the luminance value of the road surface of the predetermined area and the luminance value of the license plate area of the vehicle, obtain the number information of the vehicle from the license plate area,
As the information of the image, each of the luminance value and the number information are stored together with date and time information when the image is captured,
When the road surface luminance value and the license plate region luminance value are acquired from the first image in the acquisition process, the road surface and the vehicle are imaged in a predetermined time zone based on the time when the first image was imaged. Among the images, a plurality of second images in which the brightness value of the road surface stored in the storing process is a brightness value within a predetermined range based on the brightness value of the road surface of the first image are selected, Whether or not a cover is attached to the license plate projected on the first image based on the comparison result of the luminance value of the license plate region of the second image and the luminance value of the license plate region of the first image Determine whether
When it is determined in the determination process that a cover is attached to the license plate, the number information acquired from the first image in the acquisition process, information indicating that the cover is attached, Output,
An information output method, wherein a computer executes a process. A recognition device that acquires the brightness value of the road surface of the predetermined area and the brightness value of the license plate area of the vehicle from the image obtained by imaging the road surface and the vehicle, and acquires the number information of the vehicle from the license plate area;
The information output device according to any one of claims 1 to 5, wherein a luminance value of a road surface of the predetermined region, a luminance value of a license plate region of the vehicle, and number information of the vehicle are acquired from the recognition device. ,
An information output system comprising:

Images