JP4708192B2 - Dynamic camera color correction device and video search device using the same - Google Patents

Description

  The present invention relates to a dynamic camera color correction apparatus that corrects an image obtained by being picked up by a camera, and a video search apparatus using the dynamic camera color correction apparatus.

As a conventional device for tracking and searching a person or object using a camera, a device using color information of the person or object is often used. When using color information, in order to correct the influence of individual camera differences and the light source environment, there is a method of capturing a specific color pattern such as a color chart once with an installed camera and individually introducing the camera pattern (for example, Patent Document 1).
Japanese Patent Laid-Open No. 11-186487

  However, in the case of a monitoring system, it is always installed indoors, outdoors, and anywhere. Especially in the outdoors, the appearance of the color of the monitoring object depends on the time, weather, etc. due to dynamic changes such as sunlight. It changes every moment. For this reason, it is necessary to dynamically update the camera parameters once introduced into the installed camera, and it is indispensable to update the camera parameters in consideration of the number of installed cameras and the variety of sunshine environments.

  The present invention has been made in view of the above circumstances, and uses a color correction apparatus that can appropriately correct the color of an image without being affected by changes in an imaging environment such as a camera installation environment or a sunshine environment. An object of the present invention is to provide a video search apparatus.

  A dynamic camera color correction apparatus according to the present invention is a camera color correction apparatus that performs color correction of an image input from an imaging unit that images a monitoring area, and that performs color interpolation that determines a color correction parameter from a specific color chart. Means, color correction means for performing color correction of an image captured by the imaging means based on the color correction parameter, and outputting a color correction image, background extraction means for extracting a background image from the color correction image, and A background confirmation unit for confirming whether or not the background image is a background, a color extraction unit for extracting color information from the confirmed background image, and the color correction parameter when the extracted color information changes. And a color comparison unit to be changed.

  With this configuration, the background image in the monitoring area is extracted, the change in the color of the background image is confirmed, and the color correction parameter is sequentially updated, so that the captured image is automatically acquired regardless of the change in the imaging environment of the imaging means. Color correction can be performed.

  In addition, the dynamic camera color correction apparatus of the present invention has a configuration including reference table means for storing the color information of the background image in association with the position information of the background image.

  In the dynamic camera color correction apparatus of the present invention, the color correction unit updates the color correction parameters of the entire color space based on the color correction parameters changed by the color comparison unit. .

  With this configuration, it is possible to perform color correction with higher accuracy by performing color complementation using the color of the changed background pixel and updating the entire color correction parameter by the color complementing means.

  The dynamic camera color correction apparatus of the present invention detects pixel information of the background image, and causes the color comparison unit to function according to a difference between the pixel information of the background image and reference pixel information. It has the structure provided with the update timing discrimination | determination means to discriminate | determine.

  With this configuration, it is possible to know the timing for color comparison.

  In the dynamic camera color correction apparatus according to the present invention, the update timing determination unit divides the background image into predetermined regions and calculates an average of luminance values of the regions.

  With this configuration, it is possible to reduce the processing load on the CPU or DSP that performs color correction, such as updating the color correction parameter only when the sunshine fluctuation occurs more frequently than in the initial operation by the update timing determination unit.

  The dynamic camera color correction apparatus according to the present invention further includes first and second buffers for storing images corrected by the color correction unit, and the background extraction unit stores the image stored in the first buffer. A plurality of background image groups 1 are extracted from the image, the background confirmation unit extracts a plurality of background image groups 2 from the image stored in the second buffer, and the color comparison unit includes the background image group 1 and the background image. The pixel information of the image group 2 is detected, and the color comparison process is performed based on changes in the pixel information of the background image group 1 and the background image group 2.

  In the dynamic camera color correction apparatus according to the present invention, the background extracting unit generates a histogram for each pixel of the image stored in time series in the first buffer to extract a high-frequency luminance. The background confirmation unit has a configuration in which a histogram is generated for each pixel of an image stored in the second buffer in time series to extract a high-frequency luminance.

  With this configuration, a plurality of background pixels are extracted by the background extraction unit and the background confirmation unit, so that color correction can be performed with high accuracy even when a leaf or flag shakes.

  The dynamic camera color correction apparatus of the present invention is configured to include background change confirmation means for confirming whether or not an object in the background image confirmed by the background confirmation means has moved.

  In the dynamic camera color correction apparatus of the present invention, the background change confirmation unit has a configuration for obtaining a difference between the background image of the previous frame and the current background image.

  With this configuration, the background change confirmation means compares the background image (group) of the previous frame with the current background image (group), so that the parked vehicle included in the background image moves, etc. Even so, color correction can be performed with high accuracy.

  According to another aspect of the present invention, there is provided a dynamic camera color correction apparatus according to any one of the above and a moving area extraction unit that extracts a moving area in an image from a captured image corrected by the color correction unit. Determining whether or not a person is included in the region extracted by the moving region extraction unit, and extracting a person region from the region; and a region for dividing the person region extracted by the person determination unit into blocks A division unit, a representative color calculation unit that extracts color information and texture information from each of the regions divided by the region division unit, and color information and texture information extracted by the representative color calculation unit are stored. A person who calculates a score by comparing the database, the color information and texture information stored in the database, and the color information and texture information of the person the user wants to search And search means has a configuration and a search result display means for displaying the score calculated by the person searching device.

  With this configuration, by performing dynamic color correction with a dynamic camera color correction apparatus, it is possible to perform a highly accurate person search without being affected by individual differences in cameras, fluctuations in sunlight, and the like.

  According to another aspect of the present invention, there is provided a dynamic camera color correction apparatus according to any one of the above and a moving area extraction unit that extracts a moving area in an image from a captured image corrected by the color correction unit. Determining whether or not a person is included in the region extracted by the moving region extraction unit, and extracting a person region from the region; and a region for dividing the person region extracted by the person determination unit into blocks A division unit, a representative color calculation unit that extracts color information and texture information from each of the regions divided by the region division unit, and color information and texture information extracted by the representative color calculation unit are stored. Compare the database, the color information and texture information stored in the database with the color information and texture information of the person that the user wants to search, calculate the score, and specify Stores the person search means for transmitting a reproduction command to reproduce the captured image of the score, the compression means for compressing the captured image corrected by the color correction means by a predetermined compression method, and the captured image compressed by the compression means And a storage unit that reads out a captured image compressed by the compression unit stored in the storage based on a reproduction command transmitted from the person search unit and expands the image by a predetermined expansion method, and expands the expanded image by the expansion unit And a display means for displaying the captured image.

  In the video search device of the present invention, the compression unit has a configuration in which an arbitrary frame is intermittently compressed from the captured image corrected by the color correction unit and compressed by a predetermined compression method.

  With this configuration, dynamic color correction is performed dynamically using a dynamic camera color correction device, and the color-corrected video is stored in the storage and displayed on the display means, thereby affecting the effects of individual camera differences, fluctuations in sunlight, etc. The desired person can be reproduced without receiving the video.

  Furthermore, a video search apparatus according to the present invention is a video search apparatus connected to a plurality of cameras. The dynamic camera color correction apparatus according to any one of the above and a captured image corrected by the color correction unit. A moving area extracting means for extracting a moving area in the image, a person determining means for determining whether a person is included in the area extracted by the moving area extracting means, and extracting a person area from the area; Area dividing means for dividing the person area extracted by the person discrimination means, representative color calculating means for extracting color information and texture information from each area divided by the area dividing means, and a specific person's Search person database storing color information and texture information, color information and texture information stored in the search person database, and color information calculated by the representative color calculation means And the person who transmits the camera switching command to display the captured image corrected by the color correction unit in which the person detected by the representative color calculation unit is imaged A matching unit; a video switching unit that switches to a camera that captures the captured image corrected by the color correction unit based on a camera switching command transmitted by the person matching unit; and the color correction unit that is switched by the video switching unit. And a display unit that displays the corrected captured image on a monitor.

  With this configuration, the dynamic camera color correction device dynamically performs color correction, and the person matching unit compares whether or not the person is stored in advance in the search person DB. By switching the cameras, monitoring can be performed even if a desired person moves between cameras without being affected by individual differences of cameras, fluctuations in sunlight, and the like.

  The present invention automatically extracts a background image in a monitoring area, confirms a change in the color of the background image, and updates a color correction parameter sequentially, thereby automatically capturing an image regardless of a change in the imaging environment of the imaging means. It is possible to provide a dynamic camera color correction device having an effect that the image can be color-corrected and a video search device using the same.

  Hereinafter, a dynamic camera color correction apparatus according to an embodiment of the present invention will be described with reference to the drawings.

(First embodiment)
FIG. 1 shows a configuration of a dynamic camera color correction apparatus according to a first embodiment of the present invention. The dynamic camera color correction apparatus 100 is connected to a camera 110 that outputs a color image. The dynamic camera color correction apparatus 100 includes a color complement unit 126 that determines a color correction parameter from a specific color chart, a color correction unit 120 that performs color correction of an image captured by the camera 110 based on the color correction parameter, a color A background extraction unit 121 that extracts background information from a video (color correction image) input via the correction unit 120, a background confirmation unit 122 that checks whether a pixel of a video input via the color correction unit 120 is a background pixel, and a background A color extraction unit 123 that calculates pixel position information and color information from images output from the extraction unit 121 and the background confirmation unit 122, a reference table 124 that tabulates background pixel position information and color information, and a reference table 124 Is compared with the position information and color information extracted via the background confirmation unit 122 and the color extraction unit 123, and Composed of color comparison unit 125 issues a color correction value change instruction to the color correction unit 120 in the case had. The color correction parameter is built in the color correction unit.

  In FIG. 1, the cameras 110 connected to the dynamic camera color correction apparatus 100 are merely examples, and the number of cameras 110 is not limited. 1 represents a video signal. For example, when the camera 110 is an NTSC-compliant signal, the thick arrow is an NTSC-compliant signal.

  The dynamic camera color correction apparatus 100 configured as described above will be described in terms of two types, an initial operation operation and a normal operation operation. The initial operation operation is an operation that is performed only once when the camera is installed in order to perform dynamic color correction. The normal operation is an operation for performing dynamic color correction using the initial value set during the initial operation, and is a main part of the present invention.

  First, the initial operation operation will be described with reference to FIG. 2, FIG. 3, and FIG. Suppose that the same object is imaged with a camera. When shooting in the morning, the sun's light is weak, so it looks dark. When shooting in the day, it's bright because the sun's light is strong. When shooting in the evening, it appears red. For this reason, it is necessary to perform color correction so that the color space captured in the morning and the color space captured in the evening become the color space captured in the daytime.

  2A is a schematic diagram of a color chart, FIG. 2B is an example of a theoretical UV color space and a theoretical UV value of the color chart, and FIG. It is an example of a UV value when a color space and a color chart are captured by a camera.

  For example, the RGB color space is 0 to 255 for R (red), 0 to 255 for G (green), and 0 to 255 for B, and the color space has 255 × 255 × 255 = 16.7 million colors. In order to make the color space the same, it is only necessary to image 16.77 million colors with a camera and perform color correction. However, preparing 16.77 million colors and imaging with a camera may increase the number of man-hours. Not right. Therefore, a three-dimensional RGB color space is converted into a two-dimensional UV space excluding luminance information, and a color chart 200 (FIG. 2 (a)) having several representative colors in the UV space is imaged with a camera. A method of complementing colors other than the representative color is generally used.

  FIG. 2B shows a range 210 in which the UV color space can be theoretically expressed in the UV color space. Also, theoretical values 211a, 211b, 211c,..., 211n of the representative colors of the color chart 200 are shown. When an image (comprising three RGB colors) obtained by capturing the representative colors of the color chart 200 with the camera 110 is converted again into the UV space, the UV values 221a, 221b, 221c shown in FIG. ... Take 221n.

  Since it is known that the theoretical value 211a and the UV value 221a, the theoretical value 211b and the UV value 221b,..., The theoretical value 211n and the UV value 221n correspond to each other, the color space 220 other than the representative color (FIG. 2C) Can be supplemented. The number of representative colors in FIG. 2 is shown as an example, and the number of representative colors is not limited. Further, the color space is not limited to the UV color space.

  FIG. 3 is a flowchart for explaining an initial operation operation of the dynamic camera color correction apparatus according to the first embodiment of the present invention. First, the camera 110 images the color chart 200 (S300). The color complementing unit 126 extracts the color chart 200 from the captured image of the camera 110 (S301), and compares the unique color of the color chart 200 with the color of the color chart 200 captured by the camera 110 (S302). Based on the comparison result, the color complementation unit 126 performs color complementation for colors other than the color chart 200, and transmits color correction parameters to the color correction unit 120 (S303).

  FIG. 4 is a schematic diagram for explaining the color correction operation of the dynamic camera color correction apparatus. For example, when the color chart 200 is imaged in the daytime when the amount of sunlight is large, the imaging color chart 400 of the camera 110 is captured in a brilliant manner. However, the color correction unit 120 performs the color correction 402 based on the color correction parameter, so that the color chart 402 is output as a color chart 402 in a unique color space of the color chart 200.

  Returning to FIG. 3, the camera 110 images the monitoring area (S304). The captured image is color-corrected by the color correction unit 120 based on the color correction parameter (S305) and input to the background extraction unit 121. The image captured by the camera 110 has a foreground and a background. The foreground is always moving, such as a person or a car, and the background is something without movement, such as a wall or the ground. The background extraction unit 121 generates a background image by extracting only background information excluding foreground information (S306).

  An example of an algorithm for performing background extraction (generation of a background image) is shown. It can be assumed that the camera-captured image group, which is a camera-captured image of several frames, contains much more information in the background than in the foreground. A background image is generated by setting a mode value for each pixel in a frame as a background pixel using a least square median method that takes a mode value from an arbitrary number of populations.

  From the background image extracted by the background extraction unit 121, the color extraction unit 123 acquires color information excluding luminance signals such as Y (luminance) U and V (color), for example (S307). The converted color information is stored in the reference table 124 in association with the position information of the background pixel (S308).

  FIG. 5 shows an example of a reference table. This reference table is an example in which the camera 110 is NTSC compliant and the color information is YUV standard. The position is 720 × 480, and U, V ranges from 16 to 240.

  FIG. 6 is a flowchart for explaining the normal operation operation of the dynamic camera color correction apparatus according to the first embodiment of the present invention. The normal operation operation will be described with reference to FIG. The camera 110 images the monitoring area (S600). The captured image is color-corrected by the color correction unit 120 (S601) and input to the background confirmation unit 122.

  The background confirmation unit 122 confirms whether it is the background or the foreground from the input captured image in units of pixels by using a difference method or a motion vector method (S602). For example, when the difference method is used, a difference between the captured image of the current frame and the captured image of the previous frame is obtained, a motion region is extracted, and a region other than the motion region is assumed to be the background.

  For the pixel confirmed as background by the background confirmation unit 122, the color extraction unit 123 acquires color information excluding the luminance signal (S603). The algorithm for obtaining color information is the same as that in step S307. The extracted color information and the position information of the pixel are sent to the color comparison unit 125 (S604).

  The color comparison unit 125 compares the color information sent in S604 with the color information stored in the reference table 124 based on the position information (S605). If the values of the color information are different (S606), it is determined that the color space set during the initial setting operation has changed due to sunshine fluctuations, etc., and the color comparison unit 125 instructs the color correction unit 122 to change the color correction value. The color information of the reference table 124 and the color information via the background confirmation unit 122 are transmitted (S606).

  Based on the color information in the reference table 124 and the color information via the background confirmation unit 122, the color correction unit 120 updates the color correction parameters so that the background color at the current time is output as the background color during the initial setting operation. (Change) (S607). If the color information values are not different (S606), the process returns to step S600.

  According to the dynamic camera color correction apparatus of the first embodiment of the present invention, the background position / color information captured by the camera 110 at the time of initial installation by the background extraction unit 121 and the color extraction unit 123. Is stored in the reference table 124, the background confirmation unit 122 and the color extraction unit 123 extract the background of the camera 110 in operation, and the color comparison unit 125 compares whether the color space has changed due to sunshine fluctuations and performs color correction. By updating the color correction parameter in the unit 122, the captured image can be automatically and appropriately color-corrected regardless of changes in the imaging environment such as the installation environment of the camera 110 and sunshine fluctuations.

(Second Embodiment)
Next, a dynamic camera color correction apparatus according to the second embodiment of the present invention will be described. FIG. 7 shows a configuration of a dynamic camera color correction apparatus according to the second embodiment of the present invention. 7 that are the same as those in FIG. 1 are given the same reference numerals, and descriptions thereof are omitted.

  7, the dynamic camera color correction apparatus 700 according to the present embodiment includes the color correction unit 120, the background extraction unit 121, the background confirmation unit 122, the color extraction unit 123, the reference table 124, which are described in the first embodiment. In addition to the color comparison unit 125, a color complementing unit 726 is provided.

  The dynamic camera color correction apparatus 700 configured as described above will be described in terms of two types, an initial operation operation and a normal operation operation. Since the initial operation operation is the same as steps S300 to S308 in FIG. 3 described above, description thereof is omitted.

  The normal operation operation will be described with reference to FIGS. FIG. 8 is an example of the UV value when the UV color space and the background color are captured by the camera. FIG. 9 is a flowchart for explaining the operation of the dynamic camera color correction apparatus according to the second embodiment of the present invention. Here, steps S900 to S907 in FIG. 9 are the same as steps S600 to S607 in FIG.

  The UV color space imaged by the camera 110 is, for example, a UV color space 220 shown in FIG. Further, the U and V values of the background pixels stored in the reference table 124 are assumed to be 801a, 802b,. It is assumed that the background pixel color 801a changes to 811a due to sunshine fluctuations or the like.

  The color complementing unit 726 searches for colors close to the background pixel colors 801a and 811a from the background pixel colors 801a, 802b,..., 801n (S908). When 801b is close as shown in FIG. 8, the color complementing unit 726 performs color complementation using 811a, 801c,..., 801n excluding the colors 801a and 801b, and updates the color correction parameters (S909).

  As described above, according to the dynamic camera color correction apparatus of the second embodiment of the present invention, the color complementation unit 726 performs color complementation using the changed background pixel color, and the entire color correction parameter. By updating, color correction with higher accuracy can be performed.

(Third embodiment)
Next, a dynamic camera color correction apparatus according to the third embodiment of the present invention will be described. FIG. 10 shows the configuration of a dynamic camera color correction apparatus according to the third embodiment of the present invention. In FIG. 10, the same reference numerals are given to portions common to FIGS. 1 and 7, and description thereof is omitted.

  10, the dynamic camera color correction apparatus 1000 according to the present embodiment includes the color correction unit 120, the background extraction unit 121, the background confirmation unit 122, the color extraction unit 123, and the reference table 124 described in the first embodiment. In addition to the color comparison unit 125 and the color complementing unit 726 described in the second embodiment, an update timing determination unit 1027 is provided.

  The dynamic camera color correction apparatus 1000 configured as described above will be described in terms of two types, that is, an initial operation operation and a normal operation operation. Since the initial operation operation is the same as steps S300 to S308 in FIG. 3 described above, description thereof is omitted.

  The normal operation operation will be described with reference to FIGS. FIG. 11 is a flowchart for explaining the operation of the dynamic camera color correction apparatus according to the third embodiment of the present invention. Here, Steps S1100 to S1109 in FIG. 11 are the same as Steps S900 to S909 in FIG. FIG. 12 shows an example of a background image divided into blocks.

  The update timing determination unit 1027 divides the background image input from the background confirmation unit 122 into N × M rectangles as shown in FIG. 12 (S1110). The 16 divisions of N = 4 and M = 4 shown in FIG. 12 show an example and do not limit the number of divisions of N and M. The update timing determination unit 1027 calculates the average of the luminance values for each divided area (S1111).

  In the case of the first normal operation operation, the average of the luminance values of the respective areas in the first operation is stored as the average of the luminance values in the initial operation operation (S1112). The update timing determination unit 1027 compares the average luminance value during the initial operation operation with the average luminance value of the current frame for each of the divided regions (S1113).

  If there is a significant change in the brightness value (S1113: YES), it is determined that sunshine fluctuation has occurred, and the process proceeds to steps S1103 to S1109. If there is no significant change in the luminance value (S1113: NO), it is determined that no sunshine fluctuation has occurred, and the process returns to step S1100.

  According to the dynamic camera color correction apparatus of the third embodiment of the present invention, the update timing determination unit 1027 detects the luminance value of the background image, and the luminance value of the background image and the initial operation time It is determined whether or not the color comparison unit 125 is made to function according to the difference between the brightness value (the reference brightness value) and the color correction parameter is updated only when sunshine fluctuations occur more than in the initial operation. Thus, the processing load on the CPU or DSP that performs color correction can be reduced. Note that the update timing determination unit may determine whether or not to cause the color comparison unit 125 to function based on the color information.

(Fourth embodiment)
Next, a dynamic camera color correction apparatus according to the fourth embodiment of the present invention will be described. FIG. 13 shows the configuration of a dynamic camera color correction apparatus according to the fourth embodiment of the present invention. In FIG. 13, the same reference numerals are given to portions common to FIGS. 1, 7, and 10, and description thereof is omitted.

  13, the dynamic camera color correction apparatus 1300 according to the present embodiment includes the color correction unit 120, the color extraction unit 123, the reference table 124, the color comparison unit 125 described in the first embodiment, and the embodiment. In addition to the color complementing unit 726 described in 2 and the update timing determination unit 1027 described in Embodiment 3, a background extraction unit 1321, a background confirmation unit 1322, a buffer 1328, and a buffer 1329 are provided.

  With respect to the dynamic camera color correction apparatus 1300 configured as described above, two types of initial operation operation and normal operation operation will be described. First, the initial operation operation will be described with reference to FIGS. FIG. 14 is a flowchart for explaining the operation of the dynamic camera color correction apparatus according to the fourth embodiment of the present invention. Here, Steps S1400 to S1405 in FIG. 14 are the same as Steps S300 to S305 in FIG.

  15A is an example of the current image, FIGS. 15B and 15C are examples of the background pixel, and FIG. 15D is a histogram created for the background pixel in time series. It is an example. When a leaf exists in front of the house as shown in FIG. 15A and the leaf is shaken by wind or the like, the rectangular pixel in FIG. 15A has the leaf shown in FIG. 15B, FIG. 15C. There are two types of background colors for the house. Therefore, the background extraction unit 1321 needs to extract two types of background colors.

  Hereinafter, an example of an algorithm for extracting two types of background colors will be described. The captured image that has been color-corrected by the color correction unit 120 based on the color correction parameter is stored in the buffer 1328 (S1406). The background extraction unit 1321 generates a histogram (FIG. 15D) for each pixel of the captured images stored in time series (S1407). From the generated histogram, for example, using the Mixture of Gaussian method, the threshold method, and the like, the high-frequency luminance b (leaf luminance) and luminance c (house luminance) are extracted (S1408). In FIG. 15 (d), the horizontal axis is the luminance, but the luminance is not limited and may include a color.

  The color extraction unit 123 acquires two pieces of color information obtained by removing luminance signals such as Y (luminance) U and V (color) from the position information and pixel information of each pixel of luminance b and luminance c (S1409). The converted color information is stored in the reference table 124 in association with the pixel position information and the two color information (S1410).

  Next, the normal operation operation will be described with reference to FIG. FIG. 16 is a flowchart for explaining the operation of the dynamic camera color correction apparatus according to the fourth embodiment of the present invention. Here, Steps S1600 to S1609 in FIG. 16 are the same as Steps S900 to S909 in FIG.

  An image of the monitoring area captured by the camera 110 is stored in the buffer 1329 (S1614). The background confirmation unit 1322 generates a histogram (FIG. 15D) for each pixel of the captured images stored in time series (S1615). From the generated histogram, for example, using the Mixture of Gaussian method or the threshold method, the luminance b (leaf luminance) and the luminance c (house luminance) are extracted (S1616).

  The update timing determination unit 1027 divides the background image into N × M rectangles as shown in FIG. 12 (S1617). Note that the 16 divisions of N = 4 and M = 4 in FIG. 12 show an example, and the number of divisions of N and M is not limited.

  For each divided area, the average of the luminance values is calculated for two types of areas, luminance b and luminance c (S1618). In the case of the first normal operation operation, the average of the luminance values of the respective areas in the first operation is stored as the average of the luminance values in the initial operation operation (S1619). For each of the divided areas, the average of the two types of luminance values during the initial operation operation is compared with the average of the two types of luminance values of the current frame (S1620).

  If there is a significant change in either of the two compared luminance values (S1620: YES), the process proceeds to step S1603 to step S1609. If there is no significant change in either of the two compared luminance values (S1620: NO), the process returns to step S1600. Moreover, although the algorithm which extracts two types of background colors was described, it does not restrict | limit to two types.

  According to such a dynamic camera color correction apparatus of the fourth embodiment of the present invention, a background extraction unit 1321 and a background confirmation unit 1322 extract a plurality of background pixels, so that a leaf, a flag, etc. Even when shaking occurs, color correction can be performed with high accuracy.

(Fifth embodiment)
Next, a dynamic camera color correction apparatus according to the fifth embodiment of the present invention will be described. FIG. 17 shows the configuration of a dynamic camera color correction apparatus according to the fifth embodiment of the present invention. In FIG. 17, the same reference numerals are given to portions common to FIGS. 1, 7, 10, and 13 and the description thereof is omitted.

  17, the dynamic camera color correction apparatus 1700 according to the present embodiment includes the color correction unit 120, the color extraction unit 123, the reference table 124, the color comparison unit 125 described in the first embodiment, and the embodiment. 2 in addition to the color complementing unit 726 described in the second embodiment, the update timing determining unit 1027 described in the third embodiment, the background extraction unit 1321, the background confirmation unit 1322, the buffer 1328, and the buffer 1329 described in the fourth embodiment. A change confirmation unit 1730 is provided.

  With respect to the dynamic camera color correction apparatus 1700 configured as described above, two types of operations, that is, an initial operation and a normal operation will be described. Since the initial operation operation is the same as Steps S1400 to S1410 in FIG. 14 described above, description thereof is omitted.

  The normal operation operation will be described with reference to FIGS. 18 and 19 are flowcharts for explaining the operation of the dynamic camera color correction apparatus according to the fifth embodiment of the present invention. Here, steps S1800 to S1820 in FIG. 18 are the same as steps S1600 to S1620 in FIG.

  The background image (group) extracted by the background confirmation unit 1322 is sent to the background change confirmation unit 1730. The background change confirmation unit 1730 obtains a difference between the background image (group) of the previous frame and the current background image (group) (S1821).

  The background change confirmation unit 1730 overwrites and saves the current background image (group) over the background image (group) of the previous frame (S1822). When there is a size difference in the difference result (S1823: YES), the process proceeds to step S1904 to step S1910 (see FIG. 19).

  Steps S1904 to S1910 in FIG. 19 are the same as steps S1404 to S1410 in FIG. When there is no large difference in the difference result (S1823: NO), the process proceeds to steps S1817 to S1820 and steps S1803 to S1809.

  According to the dynamic camera color correction apparatus of the fourth embodiment of the present invention, the background change confirmation unit 1730 uses the background image (group) of the previous frame and the current background image (group). By comparing these, even if the parked vehicle or the like included in the background image moves, color correction can be performed with high accuracy.

(Sixth embodiment)
Next, a video search apparatus including a dynamic camera color correction apparatus according to the sixth embodiment of the present invention will be described. FIG. 20 shows a configuration of a video search apparatus including a dynamic camera color correction apparatus according to the sixth embodiment of the present invention. In FIG. 20, parts that are the same as those in FIG.

  In FIG. 20, the video search apparatus according to the present embodiment includes a camera 110, a monitoring apparatus 2000, a database (DB) 2035, a person search unit 2036, a search result display unit 2037, and a keyboard / mouse 2038.

  The monitoring apparatus 2000 includes the dynamic camera color correction apparatus 100 according to the first embodiment described above, a moving area extraction unit 2031, a person determination unit 2032, an area division unit 2033, and a representative color calculation unit 2034.

  The accumulation operation and search operation of the video search apparatus according to the sixth embodiment configured as described above will be described. First, the accumulation operation will be described with reference to FIGS. FIG. 21 is a flowchart for explaining the operation of the video search apparatus including the dynamic camera color correction apparatus in the sixth embodiment of the present invention. FIG. 22 is an explanatory diagram thereof. Note that the operation of the dynamic camera color correction apparatus 100 is the same as the operation of the first embodiment described above, and a description thereof will be omitted.

  The captured image processed by the color correction unit 120 is input to the moving region extraction unit 2031 (S2100). The moving region extraction unit 2031 performs background difference processing for calculating a difference value between the input captured image and a background image held in advance (S2101).

  Next, the moving region extraction unit 2031 determines whether or not there is a motion in the captured image (S2102). Specifically, in the background difference processing in S2102, the moving region extraction unit 2031 determines that there is motion in the video if the difference value is larger than a predetermined value, and otherwise moves the image. Judge that there is no.

  Note that the moving region extraction unit 2031 performs processing other than the background difference processing in S2101, and determines whether or not there is motion in the image according to the result of processing other than the background difference processing in S2102. Also good.

  When the video corresponding to the captured image input to the moving area extraction unit 2031 has a motion, the moving area extraction unit 2031 extracts the moving area in the video (S2103). Further, the moving region extraction unit 2031 outputs the captured image of the moving region to the person determination unit 2032.

  When the captured image of the moving area is input from the moving area extraction unit 2031, the person determination unit 2032 performs elliptical Hough processing (S 2104). Next, the person determination unit 2032 determines whether or not the captured image of the moving region satisfies the condition that it is a person (S2105).

  Specifically, when the human determination unit 2032 can detect an elliptical region that is likely to be a human face in the moving region by the elliptical hough process in S2104, the moving region is a person. It is determined that the condition is satisfied. If an elliptical area that is likely to be a person's face cannot be detected, it is determined that the moving area does not satisfy the condition of being a person.

  In S2104, the person determination unit 2032 performs a process other than the elliptical Hough process (for example, a process for deriving the shape, size, etc. of the entire accumulation target moving area). In S2105, the person determination unit 2032 performs a process other than the elliptical Hough process. It may be determined whether or not the condition that the moving area is a person is satisfied according to the result.

  If the condition that the moving area is a person is not satisfied (S2105: NO), the process returns to step S2100. When the condition that the moving area is a person is satisfied (S2105: YES), the person determining unit 2032 outputs the captured image of the moving area to the area dividing unit 2033.

  The area dividing unit 2033 divides the moving area captured image from the person determining unit 2032 into a plurality of block areas (S2106). For example, the area dividing unit 2033 divides the head, upper body, lower body, and shoes into four parts as shown in FIG. The dividing algorithm may be the K-Mean method or the iterative region expansion method. Note that the number of divisions of the moving area, the shape of the block area, and the division algorithm are not particularly limited.

  The area dividing unit 2033 outputs the captured image corresponding to each divided block area to the representative color calculating unit 2034. The representative color calculation unit 2034 represents each block area with a predetermined color conversion algorithm (for example, converting an RGB color system into an HSV color system, a Lab color system, or a YUV color system). A color is calculated (S2107). For example, an average value of colors in the region, a mode value, or the entire histogram may be used.

  Further, the representative color calculation unit 2034 acquires texture information of each block area (S2108). For example, a space-frequency analysis method using two-dimensional Gabor transformation, or an edge histogram in the vertical, horizontal, and diagonal directions may be used.

  Next, the representative color calculation unit 2034 outputs representative color information and texture information to the DB 2035. The DB 2035 accumulates representative color information and texture information (S2109). The DB 2035 may store the identification number of the captured camera 110, the imaging date and time, and the thumbnail image in association with the representative color information and texture information.

  By repeating the processes in steps S2100 to S2109 described above, representative color information and texture information corresponding to a plurality of persons are accumulated in the DB 2035.

  Next, the search operation will be described with reference to FIG. FIG. 23 is a flowchart for explaining the operation of the video search apparatus including the dynamic camera color correction apparatus according to the sixth embodiment of the present invention.

  First, the user transmits a person search command to the person search unit 2036 via the keyboard / mouse 2038 (S2300). The person search command may be, for example, a thumbnail image stored in the DB 2035, eleven perceptual representative colors such as red, blue, and yellow, the date and time, and the camera 110 identification number.

  In addition, the upper body has a red and black stripe texture on the lower body, and is captured by camera number 1 between 10:10 on November 11, 2005 and 20:45 on November 11, 2005. A refined search such as searching for a person may be performed.

  When the person search command is input, the person search unit 2036 reads representative color information and texture information corresponding to the person corresponding to the person search command from the DB 2035 (S2301). For example, when a person with camera number 1 and a person search command are issued, the person imaged by camera number 2 is not read.

  Next, the person search unit 2036 calculates a score of representative color information and texture information corresponding to the read person according to the person search command (S2302). For example, assume that representative color information and texture information of person A, person B, and person C are read from the DB 2035. Further, it is assumed that the person search command is similar to the color of the upper body of the person D.

  The color information of the upper body of the person A is two-dimensional coordinates (A1, A2), the color information of the upper body of the person B is two-dimensional coordinates (B1, B2), and the color information of the upper body of the person C is two-dimensional coordinates (C1, C2). If the color information of the upper body of the person D is two-dimensional coordinates (D1, D2), the Euclidean distance between the D coordinates and the A, B, C coordinates is calculated. Note that the score may be calculated by a method other than the Euclidean distance.

  Next, the search result display unit 2037 displays, for example, thumbnail images in the order of the scores calculated by the person search unit 2036 (S2303). Note that the monitoring device 2000 replaces the dynamic camera color correction device 100 with the dynamic camera color correction device 700 according to the second embodiment, the dynamic camera color correction device 900 according to the third embodiment, and the embodiment. 4 dynamic camera color correction apparatuses 1300 and the dynamic camera color correction apparatus 1700 of the fifth embodiment may be provided.

  In the monitoring apparatus 2000 of the present embodiment, the dynamic camera color correction apparatus 100 may be mounted inside the camera 110. In addition, the moving region extraction unit 2031, the person determination unit 2032, the region division unit 2033, and the representative color calculation unit 2034 in the monitoring apparatus 2000 according to the sixth embodiment may be mounted inside the camera 110.

According to the sixth embodiment of the present invention as described above, the dynamic camera color correction apparatus 100 is subjected to dynamic color correction to be affected by individual differences in the camera, fluctuations in sunlight, and the like. The person search can be performed with high accuracy.

(Seventh embodiment)
Next, a video search apparatus including a dynamic camera color correction apparatus according to a seventh embodiment of the present invention will be described. FIG. 24 shows the configuration of a video search apparatus including a dynamic camera color correction apparatus according to the seventh embodiment of the present invention. In FIG. 24, the same reference numerals are given to the portions common to FIGS.

  In FIG. 24, the video search apparatus according to the present embodiment includes a camera 110, a monitoring apparatus 2000, a DB 2035, a person search unit 2036, a keyboard / mouse 2038 described in the sixth embodiment, a compression unit 2439, a storage 2440, A development unit 2441 and a display unit 2442 are provided.

  The monitoring device 2000 includes the above-described dynamic camera color correction device 100 according to the first embodiment, the moving region extraction unit 2031 according to the above-described sixth embodiment, the person determination unit 2032, the region division unit 2033, and the representative color calculation unit. 2034.

  The DB storage operation, storage storage operation, and display operation of the video search apparatus according to the seventh embodiment configured as described above will be described. The accumulation operation is the same as Step S2100 to Step S2109 in FIG.

  The storage accumulation operation will be described with reference to FIG. FIG. 25 is a flowchart for explaining the operation of the video search apparatus including the dynamic camera color correction apparatus in the seventh embodiment of the present invention.

  The color correction unit 120 outputs the color-corrected captured image to the compression unit 2439 (S2500). The compression unit 2439 compresses the captured image using a predetermined compression method (S2501), and the compressed captured image is accumulated in the storage 2440 (S2502). Here, as the predetermined compression method, for example, an MPEG (Moving Picture Experts Group) method, a JPEG (Joint Photographic Experts Group) method, or the like is used.

  The storage 2440 may store the identification number of the captured camera 110 and the imaging date and time in association with the compressed image. The captured image is stored in the storage 2440 by repeating the processes in steps S 2500 to S 2502 described above.

  The display operation will be described with reference to FIG. FIG. 26 is a flowchart for explaining the operation of the video search apparatus including the dynamic camera color correction apparatus in the seventh embodiment of the present invention. Here, step S2600 to step S2602 in FIG. 26 are the same as step S2300 to step S2302 in FIG.

  A person reproduction command is transmitted to the expansion unit 2441 so as to reproduce the image of the person with the highest score calculated by the person search unit 2036 (S2603). For example, in the case where the highest score is a person imaged with camera number 1 on November 11, 2005 at 10:10:00, the person reproduction command is from November 11, 2005, 10:10:00 to The compressed image of camera number 1 on November 11, 2005, 10:11:00 is to be expanded.

  The decompressing unit 2441 reads the compressed image from the storage 2440 according to the person reproduction command (S2604), and decompresses the compressed image using a predetermined decompression method (S2605). Here, the predetermined expansion method is an expansion method corresponding to the compression method of the compression unit 2439. The expanded image is displayed on the display unit 2442 (S2606).

  Note that the monitoring device 2000 replaces the dynamic camera color correction device 100 with the dynamic camera color correction device 700 according to the second embodiment, the dynamic camera color correction device 900 according to the third embodiment, and the embodiment. 4 dynamic camera color correction apparatuses 1300 and the dynamic camera color correction apparatus 1700 of the fifth embodiment may be provided.

  Further, the compression unit 2439 may select a frame to be compressed, and may compress intermittently. As a result, the amount of data handled can be reduced. Further, the dynamic camera color correction apparatus 100 may be mounted inside the camera 110. Further, the moving region extraction unit 2031, the person determination unit 2032, the region division unit 2033, and the representative color calculation unit 2034 may be mounted inside the camera 110.

  According to the seventh embodiment of the present invention as described above, the dynamic camera color correction apparatus 100 performs color correction dynamically, accumulates the color-corrected video in the storage 2440, and the display unit 2442. By displaying, a desired person can be played back without being affected by individual differences of cameras, fluctuations in sunlight, and the like.

(Eighth embodiment)
Next, a video search apparatus including a dynamic camera color correction apparatus according to an eighth embodiment of the present invention will be described. FIG. 27 shows the configuration of a video search apparatus including a dynamic camera color correction apparatus according to the seventh embodiment of the present invention. In FIG. 27, parts common to FIGS. 1, 20, and 24 are denoted by the same reference numerals and description thereof is omitted.

  In FIG. 27, the video search apparatus according to the present embodiment includes a camera 110, the monitoring apparatus 2000 and the display unit 2442 described in the sixth embodiment, and a person matching unit 2743 and a video switching unit 2745. .

  The monitoring device 2000 includes the above-described dynamic camera color correction device 100 according to the first embodiment, the moving region extraction unit 2031 according to the above-described sixth embodiment, the person determination unit 2032, the region division unit 2033, and the representative color calculation unit. 2034.

  The video search apparatus according to the eighth embodiment configured as described above will be described with reference to FIG. FIG. 28 is a flowchart for explaining the operation of the video search apparatus including the dynamic camera color correction apparatus according to the eighth embodiment of the present invention. Here, steps S2800 to S2808 in FIG. 28 are the same as steps S2100 to S2108 in FIG.

  The representative color information and texture information of the person generated by the representative color calculation unit 2034 are sent to the person matching unit 2743. The search person DB 2744 stores representative color information and texture information of a specific person in advance.

  The person matching unit 2743 reads the representative color information and texture information stored in the search person DB 2744 (S2809). The representative color information and texture information read from the search person DB 2744 are compared with the representative color information and texture information sent from the representative color calculation unit 2034 (S2810), and it is determined whether they are the same person. The comparison method may be, for example, the Euclidean distance described in the above-described score calculation (see S2302).

  If they are the same person (S2811: YES), a camera switching command is transmitted to the video switching unit 2745 so that the camera identification number corresponding to the representative color calculation unit 2034 that generated the representative color information and texture information of the person is displayed on the monitor. (S2812). The switched captured image is displayed on the display unit 2442 (S2813). If they are not the same person (S2811: NO), the process returns to step S2800.

  Note that the monitoring device 2000 replaces the dynamic camera color correction device 100 with the dynamic camera color correction device 700 according to the second embodiment, the dynamic camera color correction device 900 according to the third embodiment, and the embodiment. 4 dynamic camera color correction apparatuses 1300 and the dynamic camera color correction apparatus 1700 of the fifth embodiment may be provided.

  Further, the dynamic camera color correction apparatus 100 may be mounted inside the camera 110. Further, the moving region extraction unit 2031, the person determination unit 2032, the region division unit 2033, and the representative color calculation unit 2034 may be mounted inside the camera 110.

  According to the seventh embodiment of the present invention, the dynamic camera color correction apparatus 100 performs color correction dynamically, and the person matching unit 2743 determines whether the person stored in the search person DB 2744 in advance. In the case of the same person, the video switching unit 2745 switches the camera so that monitoring is performed even if a desired person moves between cameras without being affected by individual differences in cameras, fluctuations in sunlight, etc. can do.

  The present invention has an effect of being able to appropriately correct the color of an image without being affected by fluctuations in an imaging environment such as a camera installation environment and a sunshine environment, and a dynamic camera color correction apparatus and an image using the same Useful for search devices.

1 is a block diagram of a dynamic camera color correction apparatus according to a first embodiment of the present invention. Schematic diagram (a) of the color chart in the first embodiment of the present invention, an example (b) of the theoretical UV color space and the theoretical UV value of the colorization chart, and the UV color space and the colorization chart. Example of UV value when imaged by camera (c) FIG. 3 is a flowchart for explaining the operation of the dynamic camera color correction apparatus according to the first embodiment of the present invention. Schematic diagram for explaining the color correction operation of the dynamic camera color correction apparatus according to the first embodiment of the present invention. An example of a reference table of the dynamic camera color correction apparatus according to the first embodiment of the present invention FIG. 3 is a flowchart for explaining the operation of the dynamic camera color correction apparatus according to the first embodiment of the present invention. The block diagram of the dynamic camera color correction apparatus in the 2nd Embodiment of this invention An example (a) of the UV value when the UV color space and the background color are imaged by the camera in the second embodiment of the present invention, and another example of the UV value when the UV color space and the background color are imaged by the camera ( b) Flow chart for explaining the operation of the dynamic camera color correction apparatus in the second embodiment of the present invention The block diagram of the dynamic camera color correction apparatus in the 3rd Embodiment of this invention Flow chart for explaining the operation of the dynamic camera color correction apparatus according to the third embodiment of the present invention. An example (a) of a block-divided background image and an example (b) of a block-divided background image according to the third embodiment of the present invention The block diagram of the dynamic camera color correction apparatus in the 4th Embodiment of this invention Flow chart for explaining the operation of the dynamic camera color correction apparatus in the fourth embodiment of the present invention Example of current image (a), example of background pixel (b), example of background pixel (c), and example of histogram created in time series for background pixels (d) in the fourth embodiment of the present invention Flow chart for explaining the operation of the dynamic camera color correction apparatus in the fourth embodiment of the present invention The block diagram of the dynamic camera color correction apparatus in the 5th Embodiment of this invention Flow chart for explaining the operation of the dynamic camera color correction apparatus in the fifth embodiment of the present invention Flow chart for explaining the operation of the dynamic camera color correction apparatus in the fifth embodiment of the present invention Block diagram of a video search apparatus including a dynamic camera color correction apparatus according to a sixth embodiment of the present invention Flowchart for explaining the operation of the video search apparatus including the dynamic camera color correction apparatus according to the sixth embodiment of the present invention Mimic diagram for explaining the operation of the video search apparatus including the dynamic camera color correction apparatus according to the sixth embodiment of the present invention. Flowchart for explaining the operation of the video search apparatus including the dynamic camera color correction apparatus according to the sixth embodiment of the present invention Block diagram of a video search apparatus including a dynamic camera color correction apparatus according to a seventh embodiment of the present invention Flowchart for explaining the operation of the video search apparatus including the dynamic camera color correction apparatus in the seventh embodiment of the present invention Flowchart for explaining the operation of the video search apparatus including the dynamic camera color correction apparatus in the seventh embodiment of the present invention Block diagram of a video search apparatus including a dynamic camera color correction apparatus according to an eighth embodiment of the present invention Flowchart for explaining the operation of the video search apparatus including the dynamic camera color correction apparatus according to the eighth embodiment of the present invention

Explanation of symbols

100, 700, 1000, 1300, 1700 Dynamic inter-camera color correction device 2000 Monitoring device 110 Camera 120 Color correction unit 121, 1321 Background extraction unit 122, 1322 Background confirmation unit 123 Color extraction unit 124 Reference table 125 Color comparison unit 126 , 726 Color complementation unit 1027 Update timing discrimination unit 1328, 1329 Buffer 1730 Background change confirmation unit 2031 Moving region extraction unit 2032 Human discrimination unit 2033 Region division unit 2034 Representative color calculation unit 2035 DB
2036, 2436 Person search unit 2037 Search result display unit 2038 Keyboard / mouse 2439 Compression unit 2440 Storage 2441 Development unit 2442 Display unit 2743 Person matching unit 2744 Search person DB
2745 Video switching unit 200 Example of color chart 210 Theoretical UV color space 211 Example of color chart UV value 220 UV color space after camera imaging 221 Example of color chart UV value after camera imaging 400 Color after camera imaging Chart image 401 Color correction processing block 402 Color chart image after color correction 800, 810 UV color space after camera imaging 801, 811 Example of UV value of background color after camera imaging

Claims (14)

A camera color correction device that performs color correction of an image input from an imaging unit that images a monitoring area,
Color complementing means for determining color correction parameters from a specific color chart;
Color correction means for performing color correction of an image captured by the imaging means based on the color correction parameter and outputting a color correction image;
Background extraction means for extracting a background image from the color correction image;
Background confirmation means for confirming whether or not the background image is a background;
Color extraction means for extracting color information from the confirmed background image;
A dynamic camera color correction apparatus comprising: color comparison means for changing the color correction parameter when the extracted color information changes.   2. The dynamic camera color correction apparatus according to claim 1, further comprising reference table means for storing color information of the background image in association with position information of the background image.   2. The dynamic camera color correction apparatus according to claim 1, wherein the color correction unit updates the color correction parameters of the entire color space based on the color correction parameters changed by the color comparison unit.   2. An update timing determination unit that detects pixel information of the background image and determines whether or not to cause the color comparison unit to function according to a difference between the pixel information of the background image and reference pixel information. The dynamic camera color correction device described.   The dynamic camera color correction apparatus according to claim 4, wherein the update timing determination unit divides the background image into predetermined regions and calculates an average of luminance values of the regions. Comprising first and second buffers for storing images corrected by the color correcting means;
The background extraction means extracts a plurality of background image groups 1 from images stored in the first buffer,
The background confirmation unit extracts a plurality of background image groups 2 from the images stored in the second buffer,
5. The color comparison unit detects pixel information of the background image group 1 and the background image group 2, and performs the color comparison processing based on a change in pixel information of the background image group 1 and the background image group 2. The dynamic camera color correction device described. The background extraction means generates a histogram for each pixel of the image stored in time series in the first buffer to extract a high-frequency luminance,
The dynamic camera color correction apparatus according to claim 6, wherein the background confirmation unit generates a histogram for each pixel of an image stored in the second buffer in time series to extract a high-frequency luminance.   5. The dynamic camera color correction apparatus according to claim 4, further comprising background change confirmation means for confirming whether an object in the background image confirmed by the background confirmation means has moved.   9. The dynamic camera color correction apparatus according to claim 8, wherein the background change confirmation unit obtains a difference between the background image of the previous frame and the current background image. A dynamic camera color correction apparatus according to any one of claims 1 to 9,
A moving area extracting means for extracting a moving area in the image from the captured image corrected by the color correcting means;
Determining whether or not a person is included in the area extracted by the moving area extracting means, and extracting a person area from the area;
Area dividing means for dividing the person area extracted by the person determining means into blocks;
Representative color calculation means for extracting color information and texture information from each area divided into blocks by the area dividing means;
A database for storing color information and texture information extracted by the representative color calculation means;
A person search means for comparing the color information and texture information stored in the database with the color information and texture information of a person the user wants to search, and calculating a score;
A video search apparatus comprising search result display means for displaying the score calculated by the person search means. A dynamic camera color correction apparatus according to any one of claims 1 to 9,
A moving area extracting means for extracting a moving area in the image from the captured image corrected by the color correcting means;
Determining whether or not a person is included in the area extracted by the moving area extracting means, and extracting a person area from the area;
Area dividing means for dividing the person area extracted by the person determining means into blocks;
Representative color calculation means for extracting color information and texture information from each area divided into blocks by the area dividing means;
A database for storing color information and texture information extracted by the representative color calculation means;
The color information and texture information stored in the database is compared with the color information and texture information of the person that the user wants to search, a score is calculated, and a reproduction command is transmitted to reproduce the captured image of a specific score. Person search means;
Compression means for compressing the captured image corrected by the color correction means by a predetermined compression method;
A storage for storing captured images compressed by the compression means;
An expansion unit that reads out a captured image compressed by the compression unit stored in the storage based on a reproduction command transmitted by the person search unit, and expands the image using a predetermined expansion method;
A video search apparatus comprising: display means for displaying the captured image developed by the expansion means.   12. The video search apparatus according to claim 11, wherein the compression unit intermittently compresses an arbitrary frame from the captured image corrected by the color correction unit and compresses the frame using a predetermined compression method. A video search device connected to a plurality of cameras,
A dynamic camera color correction apparatus according to any one of claims 1 to 9,
A moving area extracting means for extracting a moving area in the image from the captured image corrected by the color correcting means;
Determining whether or not a person is included in the area extracted by the moving area extracting means, and extracting a person area from the area;
Area dividing means for dividing the person area extracted by the person determining means into blocks;
Representative color calculation means for extracting color information and texture information from each area divided into blocks by the area dividing means;
A search person database storing color information and texture information of a specific person,
The color information and texture information stored in the search person database is compared with the color information and texture information calculated by the representative color calculation means, and the representative color calculation means detects that they are of the same person A person matching means for transmitting a camera switching command to display a captured image corrected by the color correction means in which a person is imaged;
Video switching means for switching to a camera that captures the captured image corrected by the color correction means based on the camera switching command transmitted by the person matching means;
A video search apparatus comprising: display means for monitoring and displaying a captured image corrected by the color correction means switched by the video switching means. A color correction apparatus that performs color correction of an image input from an imaging unit that images a monitoring area based on a color correction parameter,
Means for extracting a background region in the image;
Means for extracting color information of the background region;
Means for comparing the color information of the background area stored in the reference table means at the time of initial operation with the extracted color information;
Means for changing the color correction parameter based on a comparison result;
A color correction apparatus comprising: