JP5142204B2 - Image processing apparatus, image processing method, and program - Google Patents

Description

  The present invention relates to an image processing device, an image processing method, and a program. The present invention particularly relates to an image processing apparatus and an image processing method for processing an image, and a program for the image processing apparatus.

There is known an image compression / transmission apparatus in which an arbitrary frame is set in a video signal, and a quantization table is changed inside and outside the frame (see, for example, Patent Document 1). There is also known an image monitoring and recording apparatus that recognizes the danger situation from the movement of a person in the surveillance area and changes the report destination, the image recording method, and the like according to the recognized danger situation (for example, , See Patent Document 2).
JP-A-9-205648 JP 2007-124526 A

  According to the technique of the above patent document, the number of gradations, dynamic range, and number of colors cannot be selected for each image area. In addition, when outputting a plurality of images taken by a plurality of cameras, it is not possible to select the number of images to be output for each subject imaged in different areas of the image. For this reason, there is a possibility that the data amount of other subject images cannot be efficiently reduced while maintaining the desired subject image data amount.

  In order to solve the above-described problem, according to a first aspect of the present invention, there is provided an image processing device, a feature region detecting unit that detects a feature region from an image, and an image including a feature region in the image and a feature region in the image. An image conversion unit that converts an image with a different number of gradations in the other region, and an output unit that outputs an image obtained by conversion by the image conversion unit.

  According to a second aspect of the present invention, there is provided an image processing method, wherein a feature region detection step of detecting a feature region from an image, and the image are divided into a feature region in the image and a region other than the feature region in the image. An image conversion stage for converting to a logarithmic image and an output stage for outputting an image obtained by conversion in the image conversion stage are provided.

  According to a third aspect of the present invention, there is provided a program for an image processing apparatus, wherein the computer has a feature region detection unit that detects a feature region from the image, and the image has a feature region in the image and a region other than the feature region in the image. And an image conversion unit that converts the images into different gradation numbers, and an output unit that outputs an image obtained by conversion by the image conversion unit.

  According to the fourth aspect of the present invention, in the image processing device, the feature region detecting unit that detects the feature region from the image, and the number of colors in which the image is different between the feature region in the image and the region other than the feature region in the image An image conversion unit that converts the image into an image and an output unit that outputs an image obtained by conversion by the image conversion unit.

  According to a fifth aspect of the present invention, there is provided an image processing method comprising: a feature region detection stage for detecting a feature region from an image; and the number of colors in which the image is different between a feature region in the image and a region other than the feature region in the image. An image conversion stage for converting the image into an image, and an output stage for outputting the image obtained by the conversion in the image conversion stage.

  According to a sixth aspect of the present invention, there is provided a program for an image processing apparatus, wherein a computer detects a feature region from an image, a feature region detection unit, and the image includes a feature region in the image and a region other than the feature region in the image. And an image conversion unit that converts the images into different color numbers, and an output unit that outputs an image obtained by conversion by the image conversion unit.

  According to the seventh aspect of the present invention, there is provided an image processing device, a feature region detection unit that detects a feature region from an image, and an image having a dynamic range that is different between a feature region in the image and a region other than the feature region in the image. An image conversion unit that converts the image into an image and an output unit that outputs an image obtained by conversion by the image conversion unit.

  According to an eighth aspect of the present invention, there is provided an image processing method comprising: a feature region detection step of detecting a feature region from an image; and an image having a dynamic range different between a feature region in the image and a region other than the feature region in the image. An image conversion stage for converting the image into an image, and an output stage for outputting the image obtained by the conversion in the image conversion stage.

  According to a ninth aspect of the present invention, there is provided a program for an image processing apparatus, wherein a computer detects a feature region from an image, a feature region detection unit, and the image includes a feature region in the image and a region other than the feature region in the image. And an image conversion unit that converts images into different dynamic ranges, and an output unit that outputs an image obtained by conversion by the image conversion unit.

  According to a tenth aspect of the present invention, an image processing apparatus, an image acquisition unit that acquires a plurality of captured images captured from a plurality of different imaging positions, and a feature region detection unit that detects a feature region from the captured images A first number of in-feature area images that are images of the subject imaged in the feature areas respectively generated from the first number of captured images, and a second number of images different from the first number An output unit that outputs a second number of out-of-feature area images that are generated from the images and that are out-of-feature area images.

  According to an eleventh aspect of the present invention, there is provided an image processing method, an image acquisition stage for acquiring a plurality of captured images captured from a plurality of different imaging positions, and a feature area detection stage for detecting a feature area from the captured images. A first number of in-feature area images that are images of the subject imaged in the feature areas respectively generated from the first number of captured images, and a second number of images different from the first number And outputting a second number of out-of-feature area images, each of which is an image outside the out-of-feature area respectively generated from the image.

  According to a twelfth aspect of the present invention, there is provided a program for an image processing apparatus, wherein the computer acquires an image acquisition unit that acquires a plurality of captured images captured from a plurality of different imaging positions, and detects a feature region from the captured image A feature area detection unit, a first number of feature area images that are images of subjects imaged in the feature areas respectively generated from the first number of captured images, and a second number different from the first number It is made to function as an output part which outputs the 2nd number of image outside a feature region which is an image outside the feature region respectively generated from the number of captured images.

  The above summary of the invention does not enumerate all necessary features of the present invention. In addition, a sub-combination of these feature groups can also be an invention.

  Hereinafter, the present invention will be described through embodiments of the invention, but the following embodiments do not limit the invention according to the claims. In addition, not all the combinations of features described in the embodiments are essential for the solving means of the invention.

  FIG. 1 shows an example of an image processing system 10 according to an embodiment. The image processing system 10 can function as a monitoring system as described below.

  The image processing system 10 includes a plurality of imaging devices 100a to 100d (hereinafter collectively referred to as imaging devices 100) that capture the monitoring target space 150, an image processing device 120 that processes captured images captured by the imaging device 100, and communication. It includes a network 110, an image processing device 170, an image DB 175, and a plurality of display devices 180a-d (hereinafter collectively referred to as display devices 180). The image processing device 170 and the display device 180 are provided in a space 160 different from the monitoring target space 150.

  The imaging device 100a includes an imaging unit 102a and a captured image compression unit 104a. The imaging unit 102a captures a plurality of captured images by continuously capturing the monitoring target space 150. The captured image obtained by the imaging unit 102a may be a RAW format captured image. The captured image compression unit 104a synchronizes the RAW format captured image captured by the imaging unit 102a, compresses the captured moving image including a plurality of captured images obtained by the synchronization by MPEG encoding, and the like. Generate data. Thus, the imaging device 100a encodes the captured moving image obtained by capturing the monitoring target space 150 to generate captured moving image data. The imaging device 100a outputs the captured moving image data to the image processing device 120.

  Note that the imaging device 100b, the imaging device 100c, and the imaging device 100d have the same configuration as that of the imaging device 100a, and thus description of each component of the imaging device 100b, the imaging device 100c, and the imaging device 100d is omitted. In this way, the image processing device 120 acquires the captured moving image data generated by each of the plurality of imaging devices 100 from each of the plurality of imaging devices 100.

  Then, the image processing device 120 decodes the captured moving image data acquired from the imaging device 100 and acquires the captured moving image. The image processing apparatus 120 has different types of features such as an area where a person 130 is imaged, an area where a moving body 140 such as a vehicle is imaged, etc., from each of a plurality of captured images included in the acquired captured video. A plurality of feature regions are detected. Then, the image processing apparatus 120 compresses the image of the feature area with an intensity according to the type of the feature, and compresses the image of the area other than the feature area with an intensity stronger than the compression intensity for compressing the image of each feature area. To do.

  Note that the image processing apparatus 120 converts the image of each feature region in the captured image into an image having the number of colors and / or the number of gradations according to the feature type of the feature region. In addition, when calculating the motion vector in the inter-frame compression, the image processing apparatus 120 increases the motion vector search range for calculating the motion vector as the difference in the position of the similar feature region between the plurality of captured images increases. Make it wider.

  Note that the image processing device 120 generates feature area information including information for specifying the feature area detected from the captured image. Then, the image processing apparatus 120 attaches the feature area information to the compressed moving image data and transmits the feature area information to the image processing apparatus 170 through the communication network 110.

  The image processing device 170 receives the compressed moving image data associated with the feature area information from the image processing device 120. Then, the image processing device 170 expands the received compressed moving image data using the associated feature area information to generate a display moving image, and supplies the generated display moving image to the display device 180. At this time, the image processing apparatus 170 may generate a moving image for display in which the images of the feature areas are displayed with the same size. The display device 180 displays the display moving image supplied from the image processing device 170.

  The image processing apparatus 170 may record the compressed moving image data in the image DB 175 in association with the feature area information associated with the compressed moving image data. Note that the image DB 175 may include a nonvolatile recording medium such as a hard disk, and may store compressed moving image data and feature area information in the recording medium.

  Then, in response to a request from the display device 180, the image processing device 170 reads the compressed moving image data and the feature area information from the image DB 175, and decompresses and displays the read compressed moving image data using the feature region information. A moving image may be generated and supplied to the display device 180.

  The feature area information is text data including the position of the feature area, the size of the feature area, the number of feature areas, identification information for identifying the captured image in which the feature area is detected, or the like, or compressed or encrypted into the text data. It may be data that has been processed. Then, the image processing apparatus 170 identifies captured images that satisfy various search conditions based on the position of the feature region, the size of the feature region, the number of feature regions, and the like included in the feature region information. Then, the image processing device 170 may decode the identified captured image and provide the decoded captured image to the display device 180.

  As described above, according to the image processing system 10, since the feature region is recorded in association with the moving image, it is possible to quickly search and find a picked-up image group that meets a predetermined condition in the moving image. Also, according to the image processing system 10, only a captured image group that meets a predetermined condition can be decoded, so that a partial moving image that meets the predetermined condition can be displayed promptly in response to a reproduction instruction.

  FIG. 2 shows an example of a block configuration of the image processing apparatus 120. The image processing apparatus 120 includes an image acquisition unit 250, an image quality acquisition unit 204, a condition acquisition unit 205, an output image number acquisition unit 208, a threshold acquisition unit 209, a feature region detection unit 203, a compression control unit 210, a compression unit 230, and an association. A processing unit 206 and an output unit 207 are provided. The image acquisition unit 250 includes a compressed image acquisition unit 201 and a compressed moving image expansion unit 202.

  The compressed image acquisition unit 201 acquires a compressed moving image. Specifically, the compressed image acquisition unit 201 acquires encoded captured moving image data generated by the imaging device 100. The compressed moving image expansion unit 202 expands the captured moving image data acquired by the compressed image acquisition unit 201 to generate a plurality of captured images included in the captured moving image. Specifically, the compressed moving image decompression unit 202 decodes the encoded captured moving image data acquired by the compressed image acquisition unit 201, and generates a plurality of captured images included in the captured moving image. The captured image included in the captured moving image may be a frame image and a field image. In this way, the image acquisition unit 250 acquires a plurality of moving images captured by each of the plurality of imaging devices 100.

  The captured image in the present embodiment is an example of a moving image constituent image in the present invention, and the image processing device 120 and the image processing device 170 may process a simple image such as a still image in addition to the captured image. .

  The plurality of captured images obtained by the compressed moving image decompression unit 202 are supplied to the feature region detection unit 203 and the compression unit 230. The feature region detection unit 203 detects a feature region from a moving image including a plurality of captured images. Specifically, the feature region detection unit 203 detects a feature region from each of the plurality of captured images. Note that the captured moving image described above may be an example of a moving image in the following description.

  For example, the feature region detection unit 203 detects an image region whose image content changes in a moving image as a feature region. For example, the feature region detection unit 203 detects a region including an object that meets a predetermined condition as a feature region. Specifically, the condition acquisition unit 205 acquires a condition to which an object included in the feature area should be adapted. Then, the feature region detection unit 203 detects a region including an object that meets the conditions acquired by the condition acquisition unit 205 as a feature region.

  Specifically, the feature region detection unit 203 may detect an image region including a moving object as a feature region. Note that the feature region detection unit 203 may detect a plurality of feature regions having different types of features from each of the plurality of captured images. Note that the type of feature may be an index of the type of object such as a person and a moving object. The type of the object may be determined based on the degree of coincidence of the shape of the object or the color of the object. As described above, the feature region detection unit 203 may detect a plurality of feature regions having different types of included objects from a plurality of captured images.

  Note that the condition acquisition unit 205 may acquire a condition indicating a shape to which an object included in the feature region should be adapted. Then, the feature region detection unit 203 may detect a region including an object having a shape that matches the shape indicated by the condition acquired by the condition acquisition unit 205 as a feature region. Specifically, the feature region detection unit 203 extracts an object that matches a predetermined shape pattern with a matching degree equal to or higher than a predetermined matching degree from each of the plurality of captured images, and includes the extracted object. A region in the captured image may be detected as a feature region having the same feature type. Note that a plurality of shape patterns may be determined for each type of feature. As an example of the shape pattern, a shape pattern of a human face can be exemplified. Different face patterns may be determined for each of a plurality of persons. Thereby, the feature region detection unit 203 can detect different regions each including a different person as different feature regions. As described above, the feature region detection unit 203 may detect a region including an object having a predetermined shape as a feature region. The feature region detection unit 203 includes, in addition to the person's face, a part of the human body such as the head of the person or the hand of the person, or at least a part of a living body other than the human body. Can be detected as a feature region. The living body includes a specific tissue existing inside the living body such as a tumor tissue or a blood vessel inside the living body. In addition to the living body, the feature region detection unit 203 may detect, as the feature region, a region in which a card such as money, a cash card, a vehicle, or a license plate of the vehicle is captured.

  In addition to pattern matching by template matching or the like, the feature region detection unit 203 detects feature regions based on learning results by machine learning (for example, Adaboost) described in, for example, Japanese Patent Application Laid-Open No. 2007-188419. It can also be detected. For example, an image feature amount extracted from a predetermined subject image and an image feature amount extracted from a subject image other than the predetermined subject are extracted from the predetermined subject image. Learn the features of the image features. Then, the feature region detection unit 203 may detect a region from which an image feature amount having a feature that matches the learned feature is extracted as a feature region. Thereby, the feature region detection unit 203 can detect a region where a predetermined subject is imaged as a feature region.

  As described above, the feature region detection unit 203 detects a plurality of feature regions from a plurality of captured images included in each of a plurality of moving images. Then, the feature region detection unit 203 supplies information indicating the detected feature region to the compression control unit 210. Note that the information indicating the feature region includes coordinate information of the feature region indicating the position of the feature region, type information indicating the type of the feature region, and information for identifying the captured moving image in which the feature region is detected.

  The compression control unit 210 includes a feature region specifying unit 212, a position difference calculating unit 214, a search region determining unit 216, a resolution determining unit 262, a gradation number determining unit 264, a color number determining unit 266, and a dynamic range determining unit 268. . The feature region specifying unit 212 specifies a feature region having a high correlation among a plurality of captured images included in the moving image. The position difference calculation unit 214 calculates the position difference between the feature regions having a high correlation identified by the feature region identification unit 212.

  Then, the search area determination unit 216 determines a narrower motion vector search area as the position difference is smaller. Specifically, the search area determination unit 216 narrows the motion vector search area in which the motion vector used for compressing the image included in the feature area in the captured image is smaller as the position difference is smaller. decide. Specific examples of the operations of the feature region specifying unit 212, the position difference calculating unit 214, and the search region determining unit 216 will be described later.

  The compression control unit 210 controls the compression processing of the moving image by the compression unit 230 according to the feature region based on the information indicating the feature region acquired from the feature region detection unit 203. For example, the compression unit 230 compresses the captured image by reducing the resolution of the region other than the feature region in the captured image included in the moving image. Thus, the compression unit 230 compresses each image region in the captured image with an intensity corresponding to the importance. The compression control unit 210 supplies information indicating the motion vector search region determined by the search region determination unit 216 to the compression unit 230. Then, the compressing unit 230 compresses the moving image using the motion vector calculated by searching the motion vector search region determined by the search region determining unit 216. A more specific internal compression operation of the compression unit 230 will be described later.

  Note that the feature region specifying unit 212 specifies a feature region whose image content matching degree is greater than a predetermined value as a feature region having a high correlation. For example, the feature region specifying unit 212 specifies a feature region in which the difference value of the feature region image between a plurality of captured images is smaller than a predetermined value as a feature region having a high correlation. Note that the threshold value acquisition unit 209 may acquire a threshold value of the degree of coincidence of image contents in the feature region from the outside of the image processing apparatus 120. Then, the feature region specifying unit 212 may specify a feature region having an image content matching degree larger than the threshold as a feature region having a high correlation. In addition, the feature region specifying unit 212 may specify a feature region having a magnitude matching degree larger than a predetermined value as a feature region having a high correlation. For example, the threshold value acquisition unit 209 acquires a threshold value of the degree of coincidence in the feature region from the outside of the image processing apparatus 120. Then, the feature region specifying unit 212 specifies a feature region having a magnitude matching degree larger than the threshold as a feature region having a high correlation.

  In addition, the feature region specifying unit 212 may specify a feature region having a correlation larger than a predetermined value with respect to the position of the feature region in the captured image as a feature region having a high correlation. Specifically, the feature region specifying unit 212 may specify a feature region having a correlation larger than a predetermined value regarding a change in the position of the feature region between a plurality of captured images as a feature region having a high correlation. . More specifically, the feature region specifying unit 212 sets a feature region having a correlation larger than a predetermined value with respect to the moving direction of the feature region position between the plurality of captured images as a feature region having a high correlation. May be specified. In addition, the feature region specifying unit 212 may specify a feature region having a correlation larger than a predetermined value regarding the moving speed of the position of the feature region between a plurality of captured images as a feature region having a high correlation. . Note that the threshold acquisition unit 209 may acquire a threshold of a correlation value related to the position of the feature region from the outside of the image processing apparatus 120. The feature region specifying unit 212 may specify a feature region having a correlation value larger than the threshold with respect to the position of the feature region in the moving image composition image as a feature region having a high correlation.

  Note that the position difference calculation unit 214 calculates the position difference of the feature region having a high correlation between the captured image compressed by the inter-frame prediction and the captured image that is the basis of the predicted image. For example, the position difference calculation unit 214 calculates the position difference of a feature region having a high correlation between a captured image processed as an I frame and a captured image processed as a P frame. In addition, the position difference calculation unit 214 may be configured such that a captured image processed as an I frame or a P frame and a captured image processed as an I frame or a P frame or a B frame. As described above, the position difference of the feature region having a high correlation with the captured image processed may be calculated.

  When the feature region detection unit 203 detects a plurality of feature regions from the captured image, the feature region specifying unit 212 has a high correlation for each of the plurality of feature regions detected from the captured image by the feature region detection unit 203. Identify feature regions. Then, the position difference calculation unit 214 calculates a position difference for each of the plurality of feature areas detected from the captured image by the feature area detection unit 203. Then, the search region determination unit 216 determines a narrower motion vector search range as the maximum position difference calculated for each of the plurality of feature regions detected from the captured image by the feature region detection unit 203 is smaller. Note that the search region determination unit 216 may determine a narrower motion vector search range as the average value of the positional differences calculated for each of the plurality of feature regions detected from the captured image by the feature region detection unit 203 is smaller. Good.

  As described above, the search region determination unit 216 limits the motion vector search range according to the amount of motion of the feature region. For this reason, the compression unit 230 can calculate a motion vector at high speed, and can quickly provide a compressed moving image to the image processing apparatus 170.

  Note that the resolution determination unit 262 determines the resolution in each of the plurality of feature regions in accordance with the feature types of the plurality of feature regions. In addition, the gradation number determination unit 264 determines the gradation number of the pixel value in each of the plurality of feature regions according to the feature types of the plurality of feature regions. For example, the gradation number determination unit 264 converts the gradation numbers in the image obtained by conversion by the image conversion unit 241 described later, based on the frequency distribution of gradation values in the images of the plurality of feature regions, into the plurality of features. Decide for each of the areas.

  In addition, the color number determination unit 266 determines the number of colors that represent the pixel values in each of the plurality of feature regions according to the feature types of the plurality of feature regions. For example, the color number determination unit 266 determines the number of colors in the image obtained by conversion by the image conversion unit 241 for each of the plurality of feature regions based on the color frequency distribution in the images of the plurality of feature regions. It's okay.

  In addition, the dynamic range determination unit 268 determines the dynamic range of the image in each of the plurality of feature regions according to the types of features of the plurality of feature regions. For example, the dynamic range determination unit 268 calculates the dynamic range in the image obtained by conversion by the image conversion unit 241 for each of the plurality of feature regions based on the frequency distribution of the gradation values in the images of the plurality of feature regions. decide. Note that the resolution determination unit 262, the gradation number determination unit 264, the color number determination unit 266, and the dynamic range determination unit 268 further determine the resolution, gradation number, color number, and dynamic range in the background area, respectively.

  Note that the resolution, the number of gradations, the number of colors, and the dynamic range may be specified from the outside of the image processing apparatus 120. Specifically, the image quality acquisition unit 204 acquires at least one of the resolution, the number of gradations, the number of colors, and the dynamic range in association with the feature of the feature region. Then, the resolution determination unit 262 may determine the resolution in each of the plurality of feature regions as the resolution acquired by the image quality acquisition unit 204 in association with the feature type of the feature region. Further, the gradation number determination unit 264 may determine the gradation number in each of the plurality of feature areas as the gradation number acquired by the image quality acquisition unit 204 in association with the feature type of the feature area. The color number determination unit 266 may determine the number of colors in each of the plurality of feature areas as the number of colors acquired by the image quality acquisition unit 204 in association with the feature type of the feature area. The dynamic range determination unit 268 may determine the resolution in each of the plurality of feature areas as the dynamic range acquired by the image quality acquisition unit 204 in association with the feature type of the feature area.

  Information indicating the resolution determined by the resolution determining unit 262, the number of gradations determined by the number of gradation determining unit 264, the number of colors determined by the color number determining unit 266, and the dynamic range determined by the dynamic range determining unit 268 is compressed. Supplied to the unit 230. The compression unit 230 compresses the captured image by converting the image of each region in the captured image into an image having the resolution, the number of gradations, the number of colors, and the dynamic range.

  Note that the output image number acquisition unit 208 acquires the number of captured images to be output in association with the features of the feature region from the outside of the image processing apparatus 120. For example, when the image processing device 120 outputs a captured image captured by some of the plurality of imaging devices 100, the output image number acquisition unit 208 outputs the captured image from the output unit 207. The number of imaging devices 100 to be acquired is acquired from the outside of the image processing device 120 in association with the features of the feature region. The number acquired by the output image number acquisition unit 208 is supplied to the compression unit 230. The compression unit 230 selects and compresses the number of captured images supplied from the output image number acquisition unit 208 among the captured images supplied from the image acquisition unit 250 for each feature region. In this way, the output unit 207 is an image within the feature region generated from each of the plurality of feature regions in the captured image, and is acquired by the output image number acquisition unit 208 in association with the features of the plurality of feature regions. A number of feature region images can be output.

  The association processing unit 206 associates information specifying the feature area detected from the captured image with the captured image. Specifically, the association processing unit 206 associates information for specifying a feature area detected from a captured image with a compressed moving image including the captured image as a moving image constituent image. Then, the output unit 207 outputs the compressed moving image in which the feature area is associated by the association processing unit 206 to the image processing apparatus 170.

  Then, the output unit 207 records the compressed moving image acquired from the image processing apparatus 120 in the image DB 175. As described above, the output unit 207 records each piece of information indicating the position of the plurality of feature regions detected by the feature region detection unit 203 in the image DB 175 in association with information for identifying the captured image in which the feature region is detected. To do.

  FIG. 3 shows an example of a block configuration of the compression unit 230. The compression unit 230 includes an image division unit 232, a plurality of fixed value conversion units 234a-c (hereinafter, may be collectively referred to as a fixed value conversion unit 234), and a plurality of image conversion units 241a-d (hereinafter, image conversion units). And an image conversion unit 240 including a plurality of compression processing units 236a to 236d (hereinafter may be collectively referred to as compression processing units 236).

  The image dividing unit 232 acquires a plurality of captured images from the image acquisition unit 250. Then, the image dividing unit 232 divides the plurality of captured images into a feature region and a background region other than the feature region. Specifically, the image dividing unit 232 divides the plurality of captured images into each of a plurality of feature areas and a background area other than the feature areas. As described above, the image dividing unit 232 divides each of the plurality of captured images into the feature region and the background region.

  The image conversion unit 241 converts the captured image into an image having a different number of gradations in a feature area in the captured image and an area other than the feature area in the image. Specifically, the image conversion unit 241 converts an image in a region other than the feature region in the image into an image having a smaller number of gradations than the feature region.

  More specifically, the image conversion unit 241 converts an image of a plurality of feature areas in the image into an image having a predetermined number of gradations according to the features of the feature area. The image conversion unit 241 converts the images of the plurality of feature regions in the image into images having a predetermined number of gradations according to the feature types of the feature regions. Note that the image conversion unit 241 converts the images of the plurality of feature areas in the image into images having a predetermined number of gradations according to the types of objects included in the feature areas. Thus, the feature type in the present embodiment may be the type of object included in the feature region.

  Note that the number of gradations of each image region is determined by the gradation number determination unit 264 as described above. Then, the image conversion unit 241 converts the images of the plurality of feature regions in the image into images having the gradation numbers determined by the gradation number determination unit 264, respectively.

  In addition, the image conversion unit 241 converts the captured image into an image having a different number of colors in the feature region in the captured image and the region other than the feature region in the image. Specifically, the image conversion unit 241 converts an image in a region other than the feature region in the image into an image having fewer colors than the feature region. Note that the image conversion unit 241 may convert an image of a region other than the feature region in the captured image into an image represented by a color generated from a smaller number of color components than the feature region.

  In addition, the image conversion unit 241 may convert the images of the plurality of feature regions in the captured image into images having a predetermined number of colors according to the features of the feature regions. Note that the image conversion unit 241 may convert the images of the plurality of feature regions in the captured image into images represented by combinations of colors determined in advance according to the features of the feature regions. Specifically, the image conversion unit 241 converts the images of the plurality of feature regions in the captured image into images represented by colors generated from a predetermined number of color components according to the features of the feature regions. You can do it.

  Note that the number of colors in each image region is determined by the color number determination unit 266 as described above. Then, the image conversion unit 241 converts the images of the plurality of feature regions in the captured image into images having the number of colors determined by the color number determination unit 266, respectively.

  The image conversion unit 241 converts the captured image into an image having a different dynamic range between a feature region in the captured image and a region other than the feature region in the image. Note that the image conversion unit 241 converts an image of a region other than the feature region in the image into an image having a dynamic range wider than the feature region. Specifically, the image conversion unit 241 converts images of a plurality of feature regions in the image into images having a dynamic range that is determined in advance according to the features of the feature regions. The image conversion unit 241 converts the images of the plurality of feature regions in the image into images having a dynamic range determined in advance according to the feature types of the feature regions.

  Note that the dynamic range in each image region is determined by the dynamic range determination unit 268 as described above. Then, the image conversion unit 241 converts the images of the plurality of feature regions in the image into images having a dynamic range determined by the dynamic range determination unit 268, respectively. Note that the image conversion unit 241 may convert the image of the feature region and the background region into the above-described combined image of the number of gradations, the number of colors, and the dynamic range.

  Then, the compression processing unit 236 compresses the feature region image, which is the feature region image, and the background region image, which is the background region image, with different strengths. Specifically, the compression processing unit 236 compresses a feature area moving image including a plurality of feature area images and a background area moving image including a plurality of background area images with different strengths.

  Specifically, the image dividing unit 232 generates a feature area moving image for each of a plurality of feature types by dividing a plurality of captured images. Then, the fixed value unit 234 fixes the pixel values of the regions other than the feature regions of the respective feature types for each of the feature region images included in the plurality of feature region moving images generated for each feature type. To do. Specifically, the fixed value converting unit 234 sets pixel values in regions other than the feature region to predetermined pixel values. Then, the compression processing unit 236 compresses a plurality of feature area moving images for each feature type. For example, the compression processing unit 236 performs MPEG compression on a plurality of feature area moving images for each feature type.

  The fixed value unit 234a, the fixed value unit 234b, and the fixed value unit 234c are a feature region moving image of the first feature type, a feature region moving image of the second feature type, and a third feature type, respectively. The feature area video of is fixed. Then, the compression processing unit 236a, the compression processing unit 236b, and the compression processing unit 236c are the feature region moving image of the first feature type, the feature region moving image of the second feature type, and the feature of the third feature type. Compress area video.

  Note that the compression processing units 236a-c compress the feature area moving image with a predetermined strength according to the type of feature. For example, the compression processing unit 236 may convert the feature area moving image to a different resolution determined in advance according to the type of the feature, and compress the converted feature area moving image. In addition, when compressing the feature region moving image by MPEG encoding, the compression processing unit 236 may compress the feature region moving image with different quantization parameters determined in advance according to the feature type.

  Note that the compression processing units 236a-c may insert a code indicating that the data can be decoded from the head of the encoded data sequence obtained by encoding the macroblock including the feature region. . As the code, a synchronization recovery marker can be exemplified. Note that the compression processing units 236a-c may insert the above code at the head of each of a plurality of encoded data sequences obtained by encoding all the macroblocks including the feature region. Note that the compression processing units 236a-c may insert the code only at the head of a plurality of continuous encoded data strings obtained by encoding a macroblock including a feature region. Note that the compression processing units 236a-c encode not only the encoded data sequence obtained by encoding the DC component of the macroblock but also the encoded data obtained by encoding the AC component of the macroblock including the feature region. The above code is inserted at the beginning of the column.

  The compression processing unit 236d compresses the background area moving image. Note that the compression processing unit 236d may compress the background region moving image with a strength higher than the strength of any of the compression processing units 236a-c. The feature area moving image and the background area moving image compressed by the compression processing unit 236 are supplied to the association processing unit 206.

  In this manner, the captured image obtained by the conversion by the image conversion unit 241 is output from the output unit 207. Specifically, information for specifying a plurality of feature regions detected by the feature region detection unit 203 is output in association with a captured image obtained by conversion by the image conversion unit 241. Specifically, information for specifying a plurality of feature regions detected by the feature region detection unit 203 and information for specifying features of the plurality of feature regions are associated with images obtained by conversion by the image conversion unit 241. Output from the output unit 207.

  Since regions other than the feature region have been fixed values by the fixed value unit 234, when the compression processing unit 236 performs predictive encoding by MPEG encoding or the like, the region other than the feature region may be connected to the predicted image. The amount of difference between the images can be significantly reduced. Therefore, the compression rate of the feature area moving image can be significantly increased.

  Note that the compression unit 230 compresses with a different compression method depending on the area of the feature region. For example, the compression unit 230 compresses with a different compression method according to the total area of one or more feature regions detected from one captured image. More specifically, the compression unit 230 compresses by the first compression method when the total area is equal to or smaller than a predetermined threshold, and compresses by the second compression method when the total area is equal to or larger than the threshold. For example, the compression unit 230 compresses the feature region and the region other than the feature region with different strengths as described above on the condition that the total area is equal to or less than the threshold value. The operation in the second compression method when the total area is equal to or greater than the threshold will be described below.

  When the total area is equal to or larger than the threshold, the compression processing unit 236c that compresses the captured image with the highest image quality among the compression processing units 236 performs compression processing on the entire image area. Specifically, the fixed value unit 234c supplies the supplied captured image to the image conversion unit 241c without performing a fixed value process. Then, the image conversion unit 241c converts the captured image into a preset image quality. When the total area is equal to or greater than the threshold, the image conversion unit 241c does not have to perform image quality conversion on the captured image. Then, the compression processing unit 236c compresses the captured image supplied from the image conversion unit 241c. Note that the compression processing unit 236c compresses a plurality of captured images as moving images as described above.

  As described above, when the total area is equal to or larger than the threshold value, the compression unit 230 executes a compression process equivalent to the compression process performed when it is assumed that the entire region of the captured image is detected as the feature region. According to the operation of the first compression method, the image of the feature region is encoded by the compression processing unit 236d and any one of the compression processing units 236a to 236c and output together. For this reason, if the first compression method is used when the total area is remarkably large, the amount of code for the overlap exceeds the amount of code reduction due to the reduction in image quality of the background area. A situation may arise.

  Therefore, when the above threshold value at which such a situation is predicted to occur is determined in advance and the total area is equal to or greater than the threshold value, the entire image of the captured image is displayed in the compression processing unit 236c as described above. By compressing, it may be possible to prevent the code amount from exceeding as described above. Note that when the total area is equal to or greater than the threshold, the feature region detection unit 203 may reduce the temporal frequency of detecting the feature region. For example, the feature region detection unit 203 may detect a feature region from some captured images among a plurality of captured images captured continuously. At this time, the feature region detection unit 203 may detect the feature region from a smaller number of captured images when the total area is larger. Thereby, the time required for feature region detection can be shortened.

  Note that the compression processing unit 236a, the compression processing unit 236b, and the compression processing unit 236d may compress the captured image even when the total area is equal to or greater than the threshold value. In this case, the output unit 207 may not transmit at least the compressed data compressed by the compression processing unit 236a, the compression processing unit 236b, and the compression processing unit 236d to the image processing apparatus 170. In addition, the compression processing unit 236a, the compression processing unit 236b, and the compression processing unit 236d are supplied with captured images whose entire surface is fixed, and the compression processing unit 236a, the compression processing unit 236b, and the compression processing unit 236d. Compressed data output from may be transmitted. As described above, the compression unit 230 may easily prevent an increase in the amount of data transmitted to the image processing apparatus 170 by changing the compression processing method according to the total area. .

  In this figure, each of the plurality of compression processing units 236 included in the compression unit 230 compresses a plurality of feature region images and a background region image. However, in another embodiment, the compression unit 230 performs one compression process. A single compression processing unit 236 may compress a plurality of feature region images and background region images with different intensities. For example, a plurality of feature region images and a background region image are sequentially supplied to one compression processing unit 236 in a time-sharing manner, and the one compression processing unit 236 differs from the plurality of feature region images and the background region image. You may compress sequentially by intensity.

  In addition, the one compression processing unit 236 quantizes the image information of the plurality of feature regions and the image information of the background region with different quantization coefficients, respectively, thereby converting the images of the plurality of feature regions and the images of the background region. They may be compressed with different strengths. Also, an image obtained by converting a plurality of feature region images and a background region image into images of different image quality is supplied to one compression processing unit 236, and the one compression processing unit 236 includes a plurality of feature region images and Each image in the background area may be compressed. The image quality conversion process may be performed by one image conversion unit 240. Further, as described above, one compression processing unit 236 quantizes with a different quantization coefficient for each region, or one compression processing unit 236 compresses an image converted into a different image quality for each region. The compression processing unit 236 may compress one image, or may compress each of the images divided by the image dividing unit 232 as described with reference to FIG. When one compression processing unit 236 compresses one image, the image dividing unit 232 does not need to perform the dividing process and the fixed value converting unit 234 does not perform the fixing process. The dividing unit 232 and the fixed value unit 234 may not be provided.

  FIG. 4 shows an example of a block configuration of the image processing apparatus 170. The image processing apparatus 170 includes an image acquisition unit 301, an association analysis unit 302, a feature area information acquisition unit 360, an extension control unit 310, an extension unit 320, a synthesis unit 330, an instruction acquisition unit 390, a feature area selection unit 370, an image generation A unit 380 and an output unit 340.

  The image acquisition unit 301 acquires the compressed moving image compressed by the compression unit 230. Specifically, the image acquisition unit 301 acquires a compressed moving image including a plurality of feature region moving images and a background region moving image including the first captured image and the second captured image as moving image constituent images. More specifically, the image acquisition unit 301 acquires a compressed moving image with feature area information attached thereto.

  The association analysis unit 302 separates the compressed moving image acquired from the image DB 175 into a plurality of feature region moving images, background region moving images, and feature region information, and supplies the plurality of feature region moving images and background region moving images to the decompressing unit 320. To do. Further, the association analysis unit 302 analyzes the feature region information and supplies the feature region position and the feature type to the extension control unit 310 and the feature region information acquisition unit 360.

  As described above, the feature area information acquisition unit 360 acquires information indicating the positions of the feature areas in the plurality of captured images included in the moving image. The feature region information acquired by the feature region information acquisition unit 360 is supplied to the synthesis unit 330, the feature region selection unit 370, and the image generation unit 380.

  The decompression control unit 310 controls the decompression processing by the decompression unit 320 according to the position of the feature region and the feature type acquired from the association analysis unit 302. For example, the decompression control unit 310 decompresses each region of the moving image indicated by the compressed moving image to the decompressing unit 320 according to the compression method in which the compression unit 230 compresses each region of the moving image according to the position of the feature region and the type of feature. Let

  Hereinafter, the operation of each component included in the extension unit 320 will be described. The decompression unit 320 includes a plurality of decoders 322a-d (hereinafter collectively referred to as decoders 322). The decoder 322 decodes one of the plurality of encoded characteristic area moving images and background area moving images. Specifically, the decoder 322a, the decoder 322b, the decoder 322c, and the decoder 322d decode the first feature region moving image, the second feature region moving image, the third feature region moving image, and the background region moving image, respectively.

  The synthesizing unit 330 synthesizes a plurality of feature area moving images and background area moving images expanded by the expanding unit 320 to generate one display moving image. Specifically, the combining unit 330 generates one display moving image by combining the image of the feature region on the captured image included in the plurality of feature region moving images with the captured image included in the background region moving image. The synthesizer 330 supplies the generated display moving image to the output unit 340. The output unit 340 outputs the feature area information and the display moving image acquired from the association analysis unit 302 to the display device 180.

  Of the plurality of captured images included in the moving image generated by the synthesis unit 330, the image in the feature region is supplied to the feature region selection unit 370. The feature region selection unit 370 selects a plurality of feature regions that meet a predetermined condition from the plurality of feature regions. Specifically, the feature region selection unit 370 selects a plurality of feature regions having a predetermined type of feature from among a plurality of feature regions having different feature types. More specifically, the feature region selection unit 370 selects a plurality of feature regions including a predetermined object from among a plurality of feature regions that include different objects.

  Then, the image generation unit 380 generates a display image by reducing or enlarging each of the plurality of feature region images selected by the feature region selection unit 370. As described above, the image generation unit 380 reduces or enlarges each of the feature region images included in each of the plurality of captured images based on the position indicated by the information acquired by the feature region information acquisition unit 360. A display image having a size is generated.

  The display image generated by the image generation unit 380 is supplied to the output unit 340. Note that the output unit 340 may display the display image on the display device 180 by superimposing or synthesizing the display image on the display moving image generated by the combining unit 330.

  As described above, the image generation unit 380 displays the images of the feature areas with the same size when a particular type of feature area is detected or when a feature area including a particular object is detected. Display image to be generated can be generated. For this reason, the image of the feature region is always displayed with the same size. Therefore, according to the image processing system 10, it is possible to provide a monitoring video that is easy for the supervisor to see.

  Note that the feature region selection unit 370 may select a plurality of feature regions detected from the moving image over a period longer than a predetermined time length among the plurality of feature regions. In this case, it is possible to provide an image of an object that appears in a moving image for a long time. In addition, the feature region selection unit 370 may select a plurality of feature regions having a correlation higher than a predetermined value from among the plurality of feature regions.

  The above-described operation in the image processing apparatus 170 may be performed when the instruction acquisition unit 390 acquires an instruction to display a display image. That is, when the instruction acquisition unit 390 acquires an instruction, the image generation unit 380 generates a plurality of captured images based on the positions of a plurality of feature regions indicated by information associated with a moving image and recorded in the image DB 175. Display images having substantially the same size may be generated by reducing or enlarging each of the images of the feature regions included.

  In addition, when the instruction acquisition unit 390 acquires an instruction, the decompression unit 320 specifies a plurality of captured images identified by information recorded by associating information indicating the positions of the plurality of feature regions. . Then, the expansion unit 320 expands a partial moving image in a period including a display timing at which a plurality of identified captured images are displayed in the compressed moving image. As described above, the expansion unit 320 expands a specific partial moving image in the moving image when the instruction acquisition unit 390 acquires the instruction. Then, when the instruction acquisition unit 390 acquires the instruction, the image generation unit 380 is expanded by the expansion unit based on the positions of the plurality of feature areas indicated by the information recorded in association with the compressed moving image. A display image is generated by reducing or enlarging each of the images of the plurality of feature regions in the plurality of captured images included in the partial moving image. For this reason, according to the image processing apparatus 170, the display image can be promptly provided to the display apparatus 180.

  FIG. 5 shows an example of another block configuration of the compression unit 230. The compression unit 230 in this configuration compresses a plurality of captured images by a spatial scalable encoding process corresponding to the type of feature.

  The compression unit 230 in this configuration includes an image quality conversion unit 510, a difference processing unit 520, and an encoding unit 530. The difference processing unit 520 includes a plurality of inter-layer difference processing units 522a-d (hereinafter collectively referred to as inter-layer difference processing units 522). Encoding section 530 includes a plurality of encoders 532a-d (hereinafter collectively referred to as encoders 532).

  The image quality conversion unit 510 acquires a plurality of captured images from the image acquisition unit 250. In addition, the image quality conversion unit 510 acquires information specifying the feature region detected by the feature region detection unit 203 and information specifying the type of feature in the feature region. Then, the image quality conversion unit 510 duplicates the captured image, and generates captured images of the number of types of features in the feature area. Then, the image quality conversion unit 510 converts the generated captured image into an image having a resolution corresponding to the type of feature.

  For example, the image quality conversion unit 510 has a captured image converted to a resolution corresponding to the background area (hereinafter referred to as a low resolution image), and a captured image converted to the first resolution corresponding to the type of the first feature ( Hereinafter, referred to as a first resolution image), a captured image converted to a second resolution corresponding to the second feature type (hereinafter referred to as a second resolution image), and a third feature type. The captured image converted to the third resolution (hereinafter referred to as a third resolution image) is generated. Here, it is assumed that the first resolution image has a higher resolution than the low resolution image, the second resolution image has a higher resolution than the first resolution image, and the third resolution image has a higher resolution than the second resolution image.

  Then, the image quality conversion unit 510 converts the low resolution image, the first resolution image, the second resolution image, and the third resolution image into the inter-layer difference processing unit 522d, the inter-layer difference processing unit 522a, and the inter-layer difference processing unit 522b, respectively. And to the inter-layer difference processing unit 522c. The image quality conversion unit 510 supplies a moving image to each of the inter-layer difference processing units 522 by performing the above-described image quality conversion processing on each of the plurality of captured images.

  Note that the image quality conversion unit 510 may convert the frame rate of the moving image supplied to each of the inter-layer difference processing unit 522 in accordance with the feature type of the feature region. For example, the image quality conversion unit 510 may supply, to the inter-layer difference processing unit 522d, a moving image having a lower frame rate than the moving image supplied to the inter-layer difference processing unit 522a. In addition, the image quality conversion unit 510 may supply a moving image having a lower frame rate than the moving image supplied to the inter-layer difference processing unit 522b to the inter-layer difference processing unit 522a, and a frame lower than the moving image supplied to the inter-layer difference processing unit 522c. The rate movie may be supplied to the inter-tier difference processing unit 522b. Note that the image quality conversion unit 510 may convert the frame rate of the moving image supplied to the inter-layer difference processing unit 522 by thinning out the captured image according to the feature type of the feature region.

  The inter-layer difference processing unit 522d and the encoder 532d predictively encode a background area moving image including a plurality of low-resolution images. Specifically, the inter-layer difference processing unit 522 generates a difference image from a predicted image generated from another low-resolution image. Then, the encoder 532d quantizes the transform coefficient obtained by converting the difference image into a spatial frequency component, and encodes the quantized transform coefficient by entropy coding or the like. Note that such predictive encoding processing may be performed for each partial region of the low-resolution image.

  Further, the inter-layer difference processing unit 522a predictively encodes the first feature region moving image including the plurality of first resolution images supplied from the image quality conversion unit 510. Similarly, the inter-layer difference processing unit 522b and the inter-layer difference processing unit 522c each predictively encode a second feature area moving image including a plurality of second resolution images and a third feature area moving image including a plurality of third resolution images. To do. Hereinafter, specific operations of the inter-layer difference processing unit 522a and the encoder 532a will be described.

  The inter-layer difference processing unit 522a decodes the first resolution image encoded by the encoder 532d, and expands the decoded image to an image having the same resolution as the first resolution. Then, the inter-layer difference processing unit 522a generates a difference image between the enlarged image and the low resolution image. At this time, the inter-layer difference processing unit 522a sets the difference value in the background area to zero. Then, the encoder 532a encodes the difference image in the same manner as the encoder 532d. Note that the encoding processing by the inter-layer difference processing unit 522a and the encoder 532a may be performed for each partial region of the first resolution image.

  Note that, when the first resolution image is encoded, the inter-layer difference processing unit 522a calculates the code amount predicted when the difference image with the low resolution image is encoded, and the other first resolution image. The amount of code predicted when the difference image between the generated prediction image and the prediction image is encoded is compared. In the case where the latter code amount is smaller, the inter-layer difference processing unit 522a generates a difference image from the predicted image generated from the other first resolution image. In addition, the inter-layer difference processing unit 522a, when it is predicted that the code amount is smaller when encoded without taking the difference from the low-resolution image or the predicted image, It is not necessary to take a difference between them.

  Note that the inter-layer difference processing unit 522a does not have to set the difference value in the background area to zero. In this case, the encoder 532a may set the encoded data for difference information in an area other than the feature area to zero. For example, the encoder 532a may set the conversion coefficient after conversion to a frequency component to zero. Note that the motion vector information when the inter-layer difference processing unit 522d performs predictive encoding is supplied to the inter-layer difference processing unit 522a. The inter-layer difference processing unit 522a may calculate a motion vector for a predicted image using the motion vector information supplied from the inter-layer difference processing unit 522d.

  Note that the operations of the inter-layer difference processing unit 522b and the encoder 532b are that the second resolution image is encoded, and the first resolution after encoding by the encoder 532a when the second resolution image is encoded. The operations of the inter-layer difference processing unit 522b and the encoder 532b are substantially the same as the operations of the inter-layer difference processing unit 522a and the encoder 532a, except that the difference from the image may be taken. To do. Similarly, the operations of the inter-layer difference processing unit 522c and the encoder 532c are that the third resolution image is encoded, and when the third resolution image is encoded, after the encoding by the encoder 532b. Except for the fact that a difference from the second resolution image may be obtained, the operation is substantially the same as the operation of the inter-layer difference processing unit 522a and the encoder 532a, and thus the description thereof is omitted.

  As described above, the image quality conversion unit 510 generates, from each of the plurality of captured images, a low image quality image with a low image quality and a feature region image with higher image quality than the low image quality at least in the feature region. Then, the difference processing unit 520 generates a feature region difference image indicating a difference image between the feature region image in the feature region image and the feature region image in the low-quality image. Then, the encoding unit 530 encodes the feature region difference image and the low quality image.

  In addition, the image quality conversion unit 510 generates a low-quality image with reduced resolution from a plurality of captured images, and the difference processing unit 520 includes a feature region image in the feature region image and a feature region image in the low-quality image. A feature region difference image between the image and the image enlarged is generated. Further, the difference processing unit 520 has a spatial frequency component in which the difference between the feature region image and the enlarged image in the feature region is converted into the spatial frequency region, and the data amount of the spatial frequency component is in the region other than the feature region. A reduced feature area difference image is generated.

  As described above, the compression unit 230 performs hierarchical encoding by encoding image differences between a plurality of layers having different resolutions. As is clear from this, a part of the compression method by the compression unit 230 of this configuration is H.264. It is clear that a compression scheme according to H.264 / SVC is included. Note that when the image processing apparatus 170 decompresses such a layered compressed moving image, the moving image data of each layer is decoded, and the difference is taken for the region encoded by the inter-layer difference. The captured image having the original resolution can be generated by the addition process with the captured image decoded in the hierarchy.

  FIG. 6 shows an example of a captured moving image obtained by the imaging apparatus 100. The captured moving image A captured by the imaging apparatus 100a includes a plurality of captured images 600-1 to 600-3 (hereinafter collectively referred to as captured images 600). The captured moving image B captured by the image capturing apparatus 100b includes a plurality of captured images 610-1 to 610-3 (hereinafter collectively referred to as captured images 610), and the captured moving image C captured by the image capturing apparatus 100c includes a plurality of captured images 620. The captured moving image D captured by the imaging device 100d includes a plurality of captured images 630-1 to 630-3 (hereinafter collectively referred to as captured images 630). .

  Note that it is assumed that the imaging regions of the imaging device 100a, the imaging device 100b, the imaging device 100c, and the imaging device 100d overlap at least partially. Then, it is assumed that the imaging device 100a, the imaging device 100b, the imaging device 100c, and the imaging device 100d are imaging the overlapping imaging regions from different directions.

  The feature region detection unit 203 includes head regions 601-1 to 601-3 (hereinafter collectively referred to as a head region 601) and body region 602-1 to 602 (hereinafter referred to as a body region) as examples of the feature regions. 602) and moving body regions 603-1 to 603-3 (hereinafter collectively referred to as moving body region 603) are detected from captured image 600. The feature region detection unit 203 also includes head regions 611-1 to 611-3 (hereinafter collectively referred to as a head region 611) and body region 612-1 to 3 (hereinafter referred to as a body region) as examples of the feature regions. 612) is detected from the captured image 610. The feature region detection unit 203 also includes head regions 621-1 to 621-3 (hereinafter collectively referred to as a head region 621) and body region 622-1 to 362 (hereinafter referred to as a body region). 622) is detected from the captured image 620. The feature region detection unit 203 also includes head regions 631-1 to 63-3 (hereinafter collectively referred to as a head region 631) and body region regions 632-1 to 63-3 (hereinafter referred to as body region) as examples of feature regions. 632) is detected from the captured image 630.

  As described above, when the image acquisition unit 301 acquires a plurality of captured images captured from the plurality of imaging devices 100 provided at different positions, the output unit 207 determines the number of images to be output for each region. Good. For example, the output unit 207 outputs a predetermined number of feature region images according to the type of the feature region. Specifically, for the head region, the output unit 207 captures all four captured images obtained by the four imaging devices 100, for example, the captured image 600-1, the captured image 610-1, and the captured image. 620-1 and the image of the head region generated from the captured image 630-1 (the image of the head region 601-1, the image of the head region 611-1, the image of the head region 621-1, the head region) 631) is to be output.

  In addition, the output unit 207, for the body part region, is generated from three captured images captured by different imaging devices 100, for example, the captured image 600-1, the captured image 610-1, and the captured image 620-1. It is determined that the image of the body region (the image of the body region 602-1, the image of the body region 612-1, the image of the body region 622-1) should be output. The output unit 207 determines that two captured images captured by the two imaging devices 100 should be output for the moving body region, and one image captured by the one imaging device 100 for the background region. It is determined that the captured image should be output.

  Note that, among the captured image 600-1, the captured image 610-1, the captured image 620-1, and the captured image 630-1, the moving body region is detected only in the captured image 600-1, and therefore the output unit 207. Determines that the image of the moving body region 603-1 in the captured image 600-1 should be output. The output unit 207 determines that the background area image in the captured image 600-1 should be output for the background area.

  Note that the output unit 207 may select the captured image 600 according to the priority assigned in advance to the imaging device 100. For example, the output unit 207 may preferentially select the captured image 600 captured by the imaging device 100 having a higher assigned priority. Then, the output unit 207 outputs an image of the determined number of images among the image of the feature region and the image of the background region included in the selected captured image 600.

  As described above, the output unit 207 includes the first number of feature region images that are images of the subject imaged in the feature region respectively generated from the first number of captured images, and the first number. A second number of out-of-feature area images, which are images of the subject imaged outside the feature area, respectively generated from the different second number of captured images, are output. Then, the output unit 207 outputs the first number of in-feature area images respectively generated from the first number of captured images larger than the second number. In addition, when a plurality of feature areas are detected, the output unit 207 determines in advance according to the features of the plurality of feature areas among the plurality of in-feature area images generated from each of the feature areas in the captured image. A predetermined number of images in the feature area are output.

  As described above, according to the image processing system 10, it is possible to provide an image in which the subject imaged in the characteristic region is captured from more directions than the subject imaged in the background region. Therefore, the subject imaged in the feature area can be analyzed with high accuracy later. Further, according to the image processing system 10, since the image of the background area in the captured image captured from some of the imaging devices 100 is not transmitted, the amount of transmitted data can be significantly reduced.

  FIG. 7 shows an example of a histogram 700 of gradation values in the feature area or background area. A characteristic length 710 represents the spread of the distribution indicated by the histogram 700. In addition, as an example of the characteristic length 710, a half width can be illustrated.

  The gradation number determination unit 264 determines a predetermined gradation number according to the feature type of the feature region. In addition, the gradation number determination unit 264 determines a predetermined gradation number that is smaller than the predetermined gradation number for the feature region for the background area. Then, the gradation number determination unit 264 determines a smaller gradation number as the characteristic length 710 is shorter. For example, the gradation number determination unit 264 obtains a value obtained by subtracting a number inversely proportional to the length of the characteristic length 710 from a gradation number determined in advance according to the type of feature in the feature area. It may be determined as a logarithm.

  Thus, when the distribution spread indicated by the histogram 700 in the image region is smaller, the compression unit 230 converts the image in the image region into an image having a smaller number of gradations. For this reason, a compression rate increases.

  FIG. 8 shows an example of a conversion curve for gradation conversion. The dynamic range determination unit 268 previously stores a plurality of conversion curves for converting input pixel values, such as a conversion curve 810 and a conversion curve 820. Then, the dynamic range determining unit 268 selects one conversion curve for each region from a plurality of conversion curves stored in advance. Note that the dynamic range determination unit 268 may select a conversion curve showing a wide dynamic range for the feature region, and may select a conversion curve having a dynamic range narrower than the feature region for the background region.

  FIG. 9 shows an example of a selection method in which the compression control unit 210 selects a compression parameter for each region. The compression control unit 210 stores a type ID, which is information for identifying the type of region, information for identifying a histogram pattern, information for identifying a gradation conversion method, and information for identifying a color set in association with each other. . The type ID indicates information that identifies the feature region or the background region, and the feature type of the feature region. The information for identifying the histogram pattern may be information indicating the histogram distribution described in relation to FIG. As an example, the information identifying the histogram may be a characteristic length 710.

  The information for identifying the gradation conversion method may be information for identifying the LUT. The LUT may be an LUT that realizes conversion using the conversion curve described with reference to FIG. The information for identifying the color set may be a color set indicating a combination of colors that can be used as pixel values.

  The dynamic range determination unit 268 specifies information for identifying the LUT stored in association with the type ID matching the region and the information identifying the pattern matching the histogram pattern in the region. Then, the dynamic range determination unit 268 supplies the LUT information specified by the information to the compression unit 230. In this way, the dynamic range determination unit 268 determines the dynamic range for each region.

  The number-of-colors determination unit 266 specifies the color set stored in association with the type ID that matches the area and the information that identifies the pattern that matches the histogram pattern in the area. The color number determination unit 266 supplies the color set specified by the information to the compression unit 230. In this way, the color number determination unit 266 determines the number of colors to be used for each region.

  The color set stored in association with the feature area is formed from colors expressed by three or more primary colors (for example, 5 primary colors or 7 primary colors), and is stored in association with the background area. The color set may be formed from colors expressed in three primary colors (for example, RGB). In addition, the color set stored in association with the feature region includes a color having a color difference component, and the color set stored in association with the background region may not include a color having a color difference component. Note that the color conversion, dynamic range conversion, resolution conversion, and gradation number conversion are performed by the image conversion unit 241 or the image quality conversion unit 510.

  FIG. 10 shows an example of the motion vector search range. The feature area detection unit 203 uses a feature area 1010-1 and a feature area 1010-3 (hereinafter referred to as a feature area 1010) from a captured image 1000-1 and a captured image 1000-3 (hereinafter collectively referred to as a captured image 1000), respectively. ) Is detected. Further, it is assumed that the feature region 1010-1 and the feature region 1010-3 are specified by the feature region specifying unit 212 as feature regions having high correlation.

  In this case, the position difference calculation unit 214 calculates a position difference between the feature region 1010-1 and the feature region 1010-3. When the center of gravity of the feature region 1010-3 is (x1, y1) and the center of gravity of the feature region 1010-1 is (x2, y2), the positional difference is (x2-x1, y2-y1). To do. Then, the search area determination unit 216 determines an area 1020 including (x2, y2) as a motion vector search range.

At this time, the search area determination unit 216 may determine a smaller area 1020 when the position difference is smaller. The motion vector search range determined by the search area determination unit 216 is supplied to the compression unit 230. The compression unit 230 calculates a motion vector by performing a motion prediction process within the motion vector search range determined by the search region determination unit 216 when the feature region 1010-3 is compressed between frames.

  In this manner, the search area determination unit 216 determines the compressed captured image 1000-3 and the predicted image in the inter-frame prediction from the position of the feature area having a high correlation in the captured image 1000-3 compressed by the inter-frame prediction. A captured image 1000-3 that is compressed into a region in the vicinity of the position in the captured image 1000-1 that is the source of the predicted image that is separated by the positional difference of the feature region that has a high correlation with the original captured image 1000-1. A motion vector search region in which a motion vector used for compressing an image included in the feature region is calculated. Therefore, since the compression unit 230 only has to predict motion within a narrowed range, it is possible to reduce the amount of calculation when calculating a motion vector. For this reason, the motion vector can be calculated at high speed, and the compression speed is improved. Further, the compression unit 230 can calculate the motion vector with higher accuracy. Note that the search region determination unit 216 may determine a motion vector search region that is longer than the width in the direction perpendicular to the direction in the moving direction of the feature region indicated by the position difference.

  FIG. 11 shows an example of the dependence of the search area width on the size of the position difference. Note that the position difference calculation unit 214 calculates a position difference expressed in units of pixels in each of the x direction and the y direction.

  As indicated by the line 1100 indicating the dependency, the search area determination unit 216 monotonously increases the width of the motion vector search range until the position difference calculated by the position difference calculation unit 214 reaches a predetermined ΔNα. When the position difference calculated by the position difference calculation unit 214 is greater than or equal to ΔNα, the search region determination unit 216 sets the width of the motion vector search region as the upper limit value ΔNβ. As described above, the search region determination unit 216 determines a motion vector search region having a predetermined width when the size of the position difference is larger than the predetermined value. Note that the threshold value acquisition unit 209 acquires the threshold value of the position difference from the outside of the image processing apparatus 120. Then, the search area determination unit 216 determines a motion vector search area having a predetermined width when the position difference is larger than the threshold. As described above, since an upper limit is set for the width of the motion vector search region, it is possible to prevent the motion vector search range from becoming unnecessarily large.

  FIG. 12 shows the importance level of the partial area in the feature area. The feature region detection unit 203 detects a plurality of regions having different importance levels in the head region 1200 as an example of the feature region. For example, the feature region detection unit 203 includes an eye region 1210a and an eye region 1210b (hereinafter collectively referred to as an eye region 1210), a mouth region 1220, a nose region 1230, and an ear region 1240a in the head region 1200. And ear region 1240b (hereinafter collectively referred to as ear region 1240).

  It is assumed that the importance level is higher in the order of the eye region 1210, the nose region 1230, the mouth region 1220, and the ear region 1240. Information indicating the position of each region in the head region 1200 detected by the feature region detection unit 203 is supplied to the compression unit 230. Then, the compression unit 230 compresses the image of each region in the head region 1200 with an intensity corresponding to the importance.

  Specifically, the compression unit 230 sets the spatial frequency filter strength and / or the code amount for the image of each region in the head region 1200 so that the code amount becomes a target code amount determined according to the importance of each region. Alternatively, the quantization coefficient is controlled. The degree of importance may be determined in advance based on the accuracy rate of person identification. As described above, the compression unit 230 compresses each region having different importance detected hierarchically from the head region 1200 according to the importance. Thereby, the image processing apparatus 170 can detect and recognize a person with higher accuracy even from a compressed captured image.

  Further, the feature region detection unit 203 further detects a plurality of regions having different importance levels in the eye region 1210. For example, the feature region detection unit 203 includes an eye region 1212a and an eye region 1212a (hereinafter collectively referred to as eye region 1212), an eyebrow region 1214a and an eyebrow region 1214b (hereinafter referred to as eyebrow region 1214) in the eye region 1210. ). The eye area 1212 may be more important than the eyebrow area 1214. And the compression part 230 may compress the image of each area | region in the eye part area | region 1210 with the intensity | strength according to the importance similarly to the compression process with respect to each area | region in the head area | region 1200. FIG.

  FIG. 13 shows a display example by the display device 180. The display area by the display device 180 includes a moving image area 1300 and an attention image area 1301. The image processing device 170 provides the display device 180 with moving image data in which the moving image obtained by the combining unit 330 is displayed in the moving image area 1300. Further, the image processing device 170 provides the display device 180 with moving image data in which the display image generated by the image generation unit 380 is displayed in the attention image area 1301.

  Specifically, the image generation unit 380 is a head image 1311a that is an image of a person's head region 1310a-c (hereinafter collectively referred to as a head region 1310) included in the moving image displayed in the moving image area 1300. -C (hereinafter collectively referred to as a head image 1311) is generated. The head region 1310 may be an example of a feature region, and the head image 1311 may be an example of the display image.

  At this time, the image generation unit 380 generates a head image 1311 having a uniform size by enlarging or reducing the image of the head region 1310. Thereby, since the head image 1311 is displayed with the same size, the monitoring image is easy to see for the observer.

  Further, the image generation unit 380 generates a head image 1311 displayed at a different position from the image of the head region 1310. Note that the image generation unit 380 may generate a head image 1311 in which displayed areas do not overlap. In this manner, the image generation unit 380 generates display images in which images of a plurality of feature areas are displayed simultaneously at different predetermined positions.

  Note that the image generation unit 380 may generate a moving image including a plurality of head images 1311. For example, the image generation unit 380 may generate a plurality of head images 1311 from images of the head region 1310 in each of a plurality of captured images included in the moving image. At this time, the feature region selection unit 370 has a plurality of heads having a correlation higher than a predetermined value for the image contents of the lower region of the head region 1310 among the plurality of head regions 1310 in each of the plurality of captured images. A partial area 1310 is selected.

  For example, the feature region selection unit 370 extracts clothing texture information from the image of the region below the head region 1310 in each of the plurality of captured images. Then, the feature region selection unit 370 selects a plurality of head regions 1310 above the lower region where the extracted texture information matches with a degree of matching greater than a predetermined value as the head region 1310 having a high correlation. Good. In addition, the feature region selection unit 370 selects a plurality of head regions 1310 above the lower region where the combination of colors included matches with a degree of coincidence greater than a predetermined value. You may choose as

  Then, the image generation unit 380 may generate a moving image in which the plurality of head images 1311a are continuously displayed at the same position. As described above, the image generation unit 380 displays the images of the feature regions respectively included in the plurality of captured images based on the positions indicated by the information acquired by the feature region information acquisition unit 360 at substantially the same positions. A display image may be generated. At this time, the image generation unit 380 may generate a display image in which the images of the feature areas where the same subject is captured are displayed at substantially the same position.

  In the example of this figure, all the head images 1311 have the same size, but the image generation unit 380 generates a head image 1311 having a predetermined size according to the position of the head region 1310. May be. For example, the image generation unit 380 may generate a larger head image 1311 from the image of the head region 1310 at a more important position. In the example of this figure, the image generation unit 380 has a head larger than the other head image 1311 from the head region 1310 (for example, the head region 1310b) at a position where the distance from the counter is shorter than a predetermined distance. A partial image 1311 may be generated. Therefore, according to the image processing system 10, an image of a person located in an important area can be highlighted.

  As described above, the image generation unit 380 may generate a display image having a size corresponding to the position of the plurality of feature regions by reducing or enlarging each of the images of the plurality of feature regions. Note that the image generation unit 380 reduces or enlarges each of the images of the plurality of feature areas, and generates a display image having a size corresponding to the position of the subject in the real space indicated by the position where the plurality of feature areas exist. You can do it. In addition, the image generation unit 380 reduces or enlarges each of the plurality of feature area images, and generates a display image having a size corresponding to the size of the subject in the real space indicated by the plurality of feature area sizes. May be.

  Note that the image generation unit 380 may generate a display image in which images of a plurality of feature areas are simultaneously displayed at predetermined positions according to the display timing in the moving image. For example, the image generation unit 380 may generate a head image 1311 that is displayed in a predetermined direction in the display order. The position where the image of the feature area is displayed is at least one of the size of the feature area, the size of the specific subject included in the feature area, and the image content of the lower area of the head (for example, the clothes area). May be determined according to

  FIG. 14 shows another example of the block configuration of the image processing apparatus 170. The image processing apparatus 170 having this configuration improves the image quality of the feature region by performing super-resolution processing on the image of the feature region. The image processing apparatus 170 having this configuration includes an image acquisition unit 301, an association analysis unit 302, an expansion control unit 310, an expansion unit 320, an image generation unit 380, a feature region information acquisition unit 360, a feature region selection unit 370, and an illumination condition specification. A unit 372, a direction identification unit 374, a correlation value acquisition unit 376, a model storage unit 350, and an output unit 340. The image generation unit 380 includes an image enlargement unit 332 and a synthesis unit 330.

  The image acquisition unit 301 acquires the compressed moving image compressed by the compression unit 230. Specifically, the image acquisition unit 301 acquires a compressed moving image including a plurality of feature area moving images and a background area moving image. More specifically, the image acquisition unit 301 acquires a compressed moving image with feature area information attached thereto. The compressed moving image may be an example of an input moving image to the image processing apparatus 170. A captured image included as a moving image constituent image in the compressed moving image may be an example of an input image to the image processing device 170. As described above, the image acquisition unit 301 acquires the captured image whose image quality is reduced by the compression unit 230 as an input image.

  Then, the association analysis unit 302 separates the compressed moving image into a plurality of feature region moving images, a background region moving image, and feature region information, and supplies the plurality of feature region moving images and background region moving images to the decompressing unit 320. Further, the association analysis unit 302 analyzes the feature region information and supplies the feature region position and the feature type to the extension control unit 310 and the feature region information acquisition unit 360. In this way, the feature region information acquisition unit 360 can acquire information indicating the feature region in each of the plurality of captured images, for example, information indicating the position of the feature region.

  The decompression control unit 310 controls the decompression processing by the decompression unit 320 according to the position of the feature region and the feature type acquired from the association analysis unit 302. For example, the decompression control unit 310 decompresses each region of the moving image indicated by the compressed moving image to the decompressing unit 320 according to the compression method in which the compression unit 230 compresses each region of the moving image according to the position of the feature region and the type of feature. Let

  Hereinafter, the operation of each component included in the extension unit 320 will be described. The decompression unit 320 includes a plurality of decoders 322a-d (hereinafter collectively referred to as decoders 322). The decoder 322 decodes one of the plurality of encoded characteristic area moving images and background area moving images. Specifically, the decoder 322a, the decoder 322b, the decoder 322c, and the decoder 322d decode the first feature region moving image, the second feature region moving image, the third feature region moving image, and the background region moving image, respectively. The decompressing unit 320 supplies the first feature region moving image, the second feature region moving image, the third feature region moving image, and the background region moving image obtained by decoding to the image generating unit 380.

  The image generation unit 380 generates one display moving image based on the first feature region moving image, the second feature region moving image, the third feature region moving, the background region moving image, and the feature region information. Then, the output unit 340 outputs the feature area information and the display moving image acquired from the association analysis unit 302 to the display device 180 or the image DB 175. The image DB 175 associates the position of the feature region indicated by the feature region information, the feature type of the feature region, and the number of feature regions with the information for identifying the captured image included in the display moving image, and the non-volatile memory such as a hard disk. May be recorded on the recording medium.

  The feature region selection unit 370 selects a first feature region and a second feature region having a correlation higher than a predetermined value from the feature regions in each of the plurality of captured images. Specifically, the correlation value acquisition unit 376 acquires a threshold related to the correlation. Then, the feature region selection unit 370 selects a first feature region and a second feature region that have a higher correlation than the threshold acquired by the correlation value acquisition unit 376 from among the feature regions in each of the plurality of moving image constituent images.

  For example, the feature region selection unit 370 selects a first feature region and a second feature region in which the degree of coincidence of image contents is higher than a predetermined value from the feature regions detected from each of the plurality of captured images. Good.

  In addition, the feature region selection unit 370 may select the first feature region and the second feature region based on the position of the feature region in each of the plurality of captured images. For example, the feature region selection unit 370 includes a first feature region that is a feature region in which the change amount of the moving speed in the compressed moving image is smaller than a predetermined value based on the change amount of the position of the feature region across the plurality of captured images. A second feature region may be selected. In addition, the feature region selection unit 370 is a first feature region that is a feature region in which the change amount of the moving direction in the input moving image is smaller than a predetermined value based on the change direction of the position of the feature region across the plurality of captured images. A second feature region may be selected. Then, the feature region selection unit 370 supplies information indicating the selected first feature region and second feature region to the image generation unit 380.

  Then, the image generation unit 380 uses the image of the first feature region, the image of the second feature region, and the positional difference between the first feature region and the second feature region, and the first feature region image and the second feature region. 2. Generate a high-quality image with a higher resolution than the image of the feature region. For example, the image generation unit 380 generates a high-quality image by combining the image of the first feature area and the image of the second feature area based on the positional difference. For example, the image generation unit 380 generates a high-quality image by superimposing the image of the first feature area and the image of the second feature area by shifting the position difference.

  Note that the feature region selection unit 370 may select three or more feature regions having a correlation higher than a predetermined value from the feature regions detected from each of the plurality of captured images. Then, the image generation unit 380 may generate a high-quality image having a higher resolution than the image of the three or more feature regions using the image of the three or more feature regions and the difference in the positions of the three or more feature regions. .

  The image enlargement unit 332 enlarges an image in a region other than the feature region in the captured image to an image having the same resolution as the high-quality image. The synthesizing unit 330 then synthesizes the image obtained by the image enlarging unit 332 and the high-quality image to generate one captured image as a moving image constituent image of the display moving image. In this way, the image generation unit 380 enlarges the image of the region other than the feature region in the captured image to an image having the same resolution as the high-quality image, and combines the enlarged image and the high-quality image. Thus, one captured image is generated. The image generation unit 380 generates a display moving image including the plurality of captured images as a moving image constituent image by performing the above processing on each of the plurality of captured images.

  Note that the image generation unit 380 may generate a high-quality image by adapting the image of the object included in the feature region to the mathematical model. Specifically, the model storage unit 350 stores a model in which an object is represented by feature parameters. More specifically, the model storage unit 350 stores a model in which an object is expressed with statistical feature parameters. For example, the model storage unit 350 stores a model in which an object is represented by principal components (for example, principal component vectors) based on principal component analysis.

  Note that the model storage unit 350 may store a model in which the shape of an object is expressed using principal components based on principal component analysis. In addition, the model storage unit 350 may store a model in which the color of an object is expressed by a principal component based on principal component analysis.

  Then, the image generation unit 380 adapts the image of the object included in the feature area in the captured image to the model, thereby converting the image of the object included in the feature area in the captured image into a high-quality image with higher image quality than the captured image. Convert to

  The model storage unit 350 stores an object model viewed from a different direction in association with the direction. Then, the direction specifying unit 374 specifies the direction in which the object imaged in the feature area in the captured image is captured. Then, the image generation unit 380 adapts the image of the object included in the feature region in the captured image to the model stored in the model storage unit 350 in association with the direction specified by the direction specifying unit 374, thereby increasing the height. It may be converted to a quality image.

  The model storage unit 350 stores models of objects illuminated under different illumination conditions in association with the illumination conditions. And the illumination condition specific | specification part 372 specifies the illumination conditions with which the object currently imaged by the feature area in the input image was illuminated. Then, the image generation unit 380 adapts the image of the object included in the feature region in the input image to the model stored in the model storage unit 350 in association with the illumination condition specified by the illumination condition specifying unit 372. , Convert to high-quality image. As described above, the image generation unit 380 generates a high-quality image having a higher resolution than the input captured image by adapting the image of the object included in the feature region in the input captured image to the model.

  Then, the output unit 340 outputs an image including the high-quality image and an image other than the feature region. Specifically, the output unit 340 outputs a display moving image including the captured image obtained by the combining unit 330 as a moving image constituent image as described above.

  FIG. 15 shows an example of feature points on a human face. As described with reference to FIG. 14, the model storage unit 350 stores a model that represents an object with a feature parameter. Hereinafter, as an example of a generation method for generating a model stored in the model storage unit 350, a case where a model of a human face, which is an example of an object, is generated using an AAM method will be described.

  As shown in FIG. 15, n feature points representing the face shape are set for each of a plurality of face images (hereinafter referred to as sample images) representing a human face portion as a sample. Here, it is assumed that the number of feature points is smaller than the number of pixels of the face image. For each feature point, which part of the face is shown may be determined in advance, for example, the first feature point is the left end of the left eye and the eleventh feature point is the center between the eyebrows. Each feature point may be set manually or automatically by a recognition process.

Then, the average shape of the face is calculated based on the feature points set in each sample image. Specifically, the average of the position coordinates for each feature point indicating the same part in each sample image is obtained. Then, principal component analysis is performed based on the feature points representing the face shape in each sample image and the position coordinates of the average shape. As a result, an arbitrary face shape S can be expressed by S = S ₀ + Σp _i b _i (i = 1 to n).

Here, S is the shape vector is represented by arranging the position coordinates of each feature point of the face shape (x1, y1, ···, x n, y n) is, S ₀ is of the feature points in the average face shape the average face shape vectors represented side by side position coordinates, p _i is the eigenvector representing the i-th principal component of the face shape obtained by the principal component analysis, b _i represents a weighting factor for each eigenvector p _i.

FIG. 16 schematically shows an example of a change in face shape when the weighting coefficient b is changed. In the figure, how the face shape changes when the values of the weighting coefficients b ₁ and b ₂ for the eigenvectors p ₁ and p ₂ of the top two principal components obtained by the principal component analysis are changed. Represents. a) shows the change in the face shape when changing the weighting coefficients b _1, b) shows a change of face shape when changing the weighting coefficients b _2. In both a) and b), the central one of the three face shapes for each principal component shows an average face shape.

In this example, as a result of the principal component analysis, a component contributing to the contour shape of the face is extracted as the first principal component. By changing the weighting coefficient b ₁ , a) from the elongated face shown at the left end a ) It can be seen that the face shape has changed to the round face shown at the right end. Similarly, the second principal component are extracted component contributing to the length of the open and closed states and jaw of the mouth, by varying the weighting factor b _2, b) mouth, as shown at the left end open It can be seen that the face shape changes from a face with a long chin in the state to a face with a short chin with the mouth closed as shown at the right end. It should be noted that what shape element each component contributes to depends on human interpretation. Through the principal component analysis, a sample representing a larger shape difference in each used sample image is extracted as a lower-order principal component.

  FIG. 17 shows an example of an image obtained by converting a sample image into an average face shape. Each sample image is converted into an average face shape (warping). Specifically, the shift amount between each sample image and the average face shape is calculated for each feature point. Then, based on the shift amount, the shift amount to the average face shape for each pixel of each sample image is calculated, and each sample image is warped to the average face shape for each pixel.

Then, principal component analysis is performed using the pixel values of the R, G, and B color components of each pixel for each sample image after conversion to the average face shape as variables. As a result, the pixel values of the R, G, and B color components under the average face shape of an arbitrary face image can be approximated by A = A ₀ + Σq _i λ _i (i = 1 to m).

  Here, A is a vector (r1, g1, b1, r2, g2, b2,..., Which is expressed by arranging the pixel values of the R, G, and B color components of each pixel under the average face shape. rm, gm, bm). Note that r, g, and b are pixel values of R, G, and B color components, 1 to m are subscripts for identifying each pixel, and m is the total number of pixels in the average face shape. The arrangement order of the vector components is not limited to the above order.

A ₀ is an average vector expressed by arranging average values of pixel values of R, G, and B color components for each pixel of each sample image in the average face shape, and q _i is a face obtained by principal component analysis. The eigenvector representing the i-th principal component for the pixel values of the R, G, B color components, λ _i represents a weighting coefficient for each eigenvector q _i .

FIG. 18 schematically shows an example of a change in pixel value when the weighting coefficient q is changed. This figure schematically shows how the face pixel values change when the values of the weighting coefficients λ ₁ and λ ₂ for the eigenvectors q ₁ and q ₂ of the top two principal components obtained by principal component analysis are changed. It expresses. a) shows the change of the pixel value when the weighting coefficient λ ₁ is changed, and b) shows the change of the pixel value when the weighting coefficient λ ₂ is changed. In both a) and b), the center of the three face shapes for each principal component indicates an average pixel value.

In this example, the results of principal component analysis, the first principal component are extracted component contributing to the presence or absence of beard, by varying the weighting factor lambda _1, from the face without beard shown in a) left a) It can be seen that the face changes to the dark face shown at the right end. As the second principal component, a component contributing to the darkness of the eyebrows is extracted, and by changing the weighting coefficient λ ₂ , b) the face with a thin eyebrow as shown at the left end, and b) the face shown at the right end. It can be seen that the navel changes to a dark face.

As described above, the face model is generated by the processing described with reference to FIGS. This model represents a face by a plurality of eigenvectors p _i representing the face shape and eigenvectors q _i representing the pixel values of the face under the average face shape. The total number of eigenvectors of the model is significantly smaller than the number of pixels forming the face image. In the above example, the shape and pixel value are expressed by separate weighting coefficients b _i and λ _i for the face shape and the pixel values of the R, G, and B color components. Since there is a correlation between pixel value variations of color components and color components, it is possible to perform principal component analysis on feature parameters including both feature points and pixel values.

  Next, an example of processing in which the image generation unit 380 increases the resolution of the feature region image using the model stored in the model storage unit 350 will be described. The image generation unit 380 normalizes the input face image included in the feature region, and calculates pixel values of R, G, and B color components in average face shaping. Note that the input face image is not necessarily an image from the front, or the illumination condition may be different from the illumination condition when a sample image is captured. Therefore, normalization here refers not only to the process of aligning the feature points of the front face described above, but also to converting the orientation of the input face image obtained by imaging from the diagonal to the face image captured from the front. And conversion processing into a face image captured in a shooting environment equivalent to that of the sample image, such as shadow removal processing for removing the influence of shadows due to illumination.

Then, the image generation unit 380 calculates the weighting coefficient λ _i by projecting the difference from the pixel value for the average face onto the principal component vector q _i . Specifically, the image generation unit 380 can calculate the weighting coefficient λ _i by the inner product with the principal component vector q _i . Then, the image generation unit 380 calculates the pixel value A under the average face shape using the calculated weighting coefficient λ _i , the average face pixel value A ₀ , and the principal component vector q _i .

The image generation unit 380 also calculates the facial feature point S by the same process as the pixel value A calculation process described above. Specifically, the image generation unit 380 calculates the weighting coefficient b _i by projecting the difference in the position of the feature point with respect to the average face to the principal component vector p _i , and calculates the calculated weighting coefficient b _i , Using the average face feature point S ₀ and the principal component vector p _i , the feature point A is calculated. Then, the image generation unit 380 performs an inverse conversion process on the image represented by the pixel value A and the feature point A except for the process of aligning the feature points in the normalization process.

  Through the above processing, the image generation unit 380 generates a high-quality image with higher image quality than the captured image from the image of the feature region in the captured image output from the output unit 207. Specifically, the image generation unit 380 has a higher resolution image, a sharper image, an image with less noise, and a greater number of gradations than the image of the feature region in the captured image output from the output unit 207. It is possible to generate an image with a large number of images or an image with a larger number of colors.

  FIG. 19 shows an example of a model stored in the model storage unit 350 in a table format. The model storage unit 350 stores a model for each combination of a plurality of facial expressions and a plurality of directions. Expressions include faces and true faces in each state of emotions, and directions include front, upper, lower, right, left, and rear. The image generation unit 380 specifies facial expressions and face directions based on the image contents of the face image included in the feature region, and stores them in the model storage unit 350 in association with the specified combinations of facial expressions and directions. The above-described reconstruction process can be performed using the existing model.

  The image generation unit 380 can specify a facial expression from the shape of the mouth and / or eyes, and can specify the direction of the face from the positional relationship of the eyes, mouth, nose, and ears. The image processing apparatus 120 may specify the facial expression and the face direction, and the output unit 207 may output the facial expression and the face direction in association with the captured image.

  In addition to the facial expression and orientation, the model storage unit 350 may store the model in association with the illumination condition as described above. For example, the model storage unit 350 may store the model in association with the illumination intensity and the illumination direction. Then, the image generation unit 380 may specify the illumination condition for the face based on the image content of the face image included in the feature region. For example, the image generation unit 380 identifies the illumination intensity and the illumination direction based on the position and size of the shadow, and associates the model stored in the model storage unit 350 with the identified illumination intensity and illumination direction. The above-described reconstruction process can be performed.

  In the above example, the generation of a model expressing the entire face and the reconstruction process using the model have been described. In addition to such a model of the entire face, the image processing system 10 can use a model for each part of the face. In addition, the image processing system 10 can use a model of a face (or a part of a face) for each gender and / or race. The image processing system 10 can store a model for each type of object that the image processing system 10 is to monitor, such as a vehicle and a ship, in addition to a human model. The image generation unit 380 can also select and reconfigure a model according to the type of object included in the feature region. Such a type may be detected by the image processing apparatus 120 and transmitted to the image processing apparatus 170 in association with the captured image.

  As described above, the model storage unit 350 can store models of different types of objects in association with the types. Then, the feature area information acquisition unit 360 acquires information indicating the type of object imaged in the feature area in the input image. Then, the image generation unit 380 stores the image of the object included in the feature region in the captured image in association with the type of the object captured in the feature region acquired by the feature region information acquisition unit 360, and is stored in the model storage unit 350. The image is converted into a high-quality image by adapting to the model.

  According to the image processing system 10 described above, the feature region is super-resolved using a model, while the background region is not super-resolved using a model. For this reason, the calculation amount of the super-resolution processing can be significantly reduced. In addition, since the image quality is not improved in the low importance area such as the background area, the data amount of the image can be reduced. In addition, according to the image processing system 10, since the information specifying the feature area is transmitted to the image processing apparatus 170, it is possible to prevent the background area containing only low-quality information from being erroneously super-resolved. Can be prevented.

  As described above, the model storage unit 350 stores learning data for each face part (for example, eyes, nose, mouth, etc.) as an example of information for identifying the type of object. Here, the learning data may include a low frequency component and a high frequency component of the image of the object respectively extracted from a large number of sample images of the object in addition to the model. As described above, the model storage unit 350 functions as an object image information storage unit that stores the high-frequency component of the object image in association with the type of the object. The low frequency components of the object image are clustered into a plurality of clusters in each of the plurality of object types by clustering the low frequency components of the object image for each of the plurality of object types by the K-means method or the like. May have been. In addition, a typical low frequency component (for example, centroid value) may be determined for each cluster.

  Then, the image generation unit 380 extracts a low frequency component from the image of the object included in the captured image. Then, the image generation unit 380 has a cluster in which a value suitable for the extracted low-frequency component is determined as a representative low-frequency component among the low-frequency component clusters extracted from the sample image of the object of the object type. Is identified. Then, the image generation unit 380 specifies a cluster of high frequency components associated with the low frequency component included in the specified cluster. In this way, the image generation unit 380 can identify a cluster of high frequency components that are correlated with the low frequency components extracted from the objects included in the captured image. Then, the image generation unit 380 may convert the image of the object into a higher quality image with higher frequency components that represent the identified cluster of higher frequency components. For example, the image generation unit 380 may add the high-frequency component selected for each object with a weight corresponding to the distance from the center of each object to the processing target position on the face to the object image. Note that the representative high-frequency component may be generated by closed-loop learning. As described above, the image generation unit 380 selects and uses desired learning data for each object from the learning data generated by learning for each object. There are cases where image quality can be improved.

  As described above, the image processing apparatus 170 can reconstruct the image of the feature region using the principal component analysis (PCA). As an image reconstruction method by the image processing apparatus 170 and a learning method for the image reconstruction, in addition to learning and image reconstruction by principal component analysis (PCA), local preserving projection (LPP) , Linear discriminant analysis (LDA), independent component analysis (ICA), multidimensional scaling (MDS), support vector machine (support vector regression), neural network, hidden Markov model, Bay Inference, maximum posterior probability estimation, iterative backprojection, Wavelet transform, locally linear embedding (locally linea) Techniques such as reembedding (LLE) and Markov random field (MRF) can be used.

  As described above, the image processing apparatus 170 performs high resolution processing on the image of the feature area, thereby improving the image quality of the image of the feature area. Note that the image processing apparatus 170 performs processing that combines the processing of the image processing apparatus 170 described with reference to FIGS. 1 to 13 and the processing of the image processing apparatus 170 described with reference to FIGS. 14 to 19. can do. For example, as described with reference to FIGS. 1 to 13, the image processing apparatus 170 obtains a captured image obtained by performing the super-resolution processing described with reference to FIGS. 14 to 19 in the feature region. The number of feature areas, the position of the feature area, the size of the feature area, the information specifying the type of object included in the feature area, and the like are recorded in the image DB 175. Then, as described with reference to FIGS. 1 to 13, the image processing apparatus 170 responds to an instruction from the supervisor, the number of feature areas associated with the captured image, the position of the feature area, and the feature Based on information such as the size of the region and the type of object included in the feature region, for example, images of the feature region can be displayed at the same position with the same size.

  FIG. 20 shows an example of an image processing system 20 according to another embodiment. The configuration of the image processing system 20 in the present embodiment is the image described with reference to FIG. 1 except that the imaging devices 100a-d have image processing units 804a-d (hereinafter collectively referred to as image processing units 804). The configuration of the processing system 10 is the same.

  The image processing unit 804 has components other than the image acquisition unit 250 among the components included in the image processing apparatus 120. The functions and operations of the constituent elements included in the image processing unit 804 are replaced with that the constituent elements included in the image processing device 120 process the captured moving image obtained by the decompression processing by the compressed moving image decompression unit 202. The functions and operations of the components included in the image processing apparatus 120 may be substantially the same except that the captured moving image captured by the imaging unit 102 is processed. Also in the image processing system 20 having such a configuration, substantially the same effect as that described in relation to the image processing system 10 from FIGS. 1 to 13 can be obtained.

  Note that the image processing unit 804 acquires a captured moving image including a plurality of captured images expressed in the RAW format from the imaging unit 102, and RAWs the captured images expressed in the RAW format included in the acquired captured moving image. You can compress it as it is. Note that the image processing unit 804 may detect one or more feature regions from a plurality of captured images expressed in the RAW format. The image processing unit 804 may compress a captured moving image including a plurality of compressed captured images in the RAW format. Note that the image processing unit 804 can compress the captured moving image by the compression method described as the operation of the image processing apparatus 120 in relation to FIGS. The image processing apparatus 170 can acquire a plurality of captured images represented in the RAW format by expanding the moving image acquired from the image processing unit 804. The image processing apparatus 170 enlarges each of the plurality of captured images expressed in the RAW format acquired by decompression for each region, and performs synchronization processing for each region. At this time, the image processing apparatus 170 may perform synchronization processing with higher accuracy in the feature region than in the region other than the feature region.

  Then, the image processing device 170 may perform super-resolution processing as described in relation to FIGS. 14 to 19 on the image of the feature region in the captured image obtained by the synchronization processing. Note that as described with reference to FIGS. 1 to 19, the image processing apparatus 170 calculates the weighting coefficient described above in the super-resolution processing. In this case, the image of the object included in the feature region is represented by the principal component vector and the weighting coefficient. The data amount of the weighting coefficient and the principal component vector is the pixel data of the object image itself. Significantly smaller than the amount. Therefore, the image processing unit 804 may calculate the above-described weighting coefficient from the image of the object included in the feature area in the compression processing for compressing the image of the feature area in the plurality of captured images acquired from the imaging unit 102. That is, the image processing unit 804 can compress the image of the object included in the feature region by representing the principal component vector and the weighting coefficient. Then, the image processing unit 804 may transmit the principal component vector and the weighting coefficient to the image processing apparatus 170. In the image processing apparatus 170, the image of the object included in the feature region can be reconstructed using the principal component vector and the weighting coefficient acquired from the image processing unit 804 as described above.

  As described above, the image processing unit 804 represents the object included in the image of the feature region by adapting the image of the object included in the image of the feature region in the captured image to the model in which the object is expressed by the feature parameter. The feature parameter value in the model may be calculated. Then, the image processing unit 804 may output the calculated feature parameter value and an image of an area other than the feature area. Then, the image processing apparatus 170 generates an object image by applying the characteristic parameter value acquired from the image processing unit 804 to the model, and uses the generated object image and an image of an area other than the characteristic area. One captured image may be generated.

  FIG. 21 shows an exemplary hardware configuration of the image processing apparatus 120 and the image processing apparatus 170. The image processing device 120 and the image processing device 170 include a CPU peripheral unit, an input / output unit, and a legacy input / output unit. The CPU peripheral section includes a CPU 1505, a RAM 1520, a graphic controller 1575, and a display device 1580 that are connected to each other by a host controller 1582. The input / output unit includes a communication interface 1530, a hard disk drive 1540, and a CD-ROM drive 1560 that are connected to the host controller 1582 by the input / output controller 1584. The legacy input / output unit includes a ROM 1510, a flexible disk drive 1550, and an input / output chip 1570 connected to the input / output controller 1584.

  The host controller 1582 connects the RAM 1520, the CPU 1505 that accesses the RAM 1520 at a higher transfer rate, and the graphic controller 1575. The CPU 1505 operates according to the contents of the programs stored in the ROM 1510 and the RAM 1520 and controls each unit. The graphic controller 1575 acquires image data generated by the CPU 1505 or the like on a frame buffer provided in the RAM 1520 and displays the image data on the display device 1580. Alternatively, the graphic controller 1575 may include a frame buffer that stores image data generated by the CPU 1505 or the like.

  The input / output controller 1584 connects the host controller 1582 to the hard disk drive 1540, the communication interface 1530, and the CD-ROM drive 1560, which are relatively high-speed input / output devices. The hard disk drive 1540 stores programs and data used by the CPU 1505. The communication interface 1530 is connected to the network communication device 1598 to transmit / receive programs or data. The CD-ROM drive 1560 reads a program or data from the CD-ROM 1595 and provides it to the hard disk drive 1540 and the communication interface 1530 via the RAM 1520.

  The input / output controller 1584 is connected to the ROM 1510, the flexible disk drive 1550, and the relatively low-speed input / output device of the input / output chip 1570. The ROM 1510 stores a boot program that is executed when the image processing device 120 and the image processing device 170 are started, or a program that depends on the hardware of the image processing device 120 and the image processing device 170. The flexible disk drive 1550 reads a program or data from the flexible disk 1590 and provides it to the hard disk drive 1540 and the communication interface 1530 via the RAM 1520. The input / output chip 1570 connects various input / output devices via the flexible disk drive 1550 or a parallel port, serial port, keyboard port, mouse port, and the like.

  A program executed by the CPU 1505 is stored in a recording medium such as the flexible disk 1590, the CD-ROM 1595, or an IC card and provided by the user. The program stored in the recording medium may be compressed or uncompressed. The program is installed in the hard disk drive 1540 from the recording medium, read into the RAM 1520, and executed by the CPU 1505. The program executed by the CPU 1505 causes the image processing apparatus 120 to function as each component included in the image processing apparatus 120 described with reference to FIGS. 1 to 20, and causes the image processing apparatus 170 to function as illustrated in FIGS. 1 to 20. It is made to function as each component which image processing apparatus 170 which was explained related has.

  The program shown above may be stored in an external storage medium. As the storage medium, in addition to the flexible disk 1590 and the CD-ROM 1595, an optical recording medium such as a DVD or PD, a magneto-optical recording medium such as an MD, a tape medium, a semiconductor memory such as an IC card, or the like can be used. Further, a storage device such as a hard disk or a RAM provided in a server system connected to a dedicated communication network or the Internet is used as a recording medium, and is provided to the image processing device 120 and the image processing device 170 as a program via the network. Also good. As described above, the computer controlled by the program functions as the image processing device 120 and the image processing device 170.

  As mentioned above, although this invention was demonstrated using embodiment, the technical scope of this invention is not limited to the range as described in the said embodiment. It will be apparent to those skilled in the art that various modifications or improvements can be added to the above-described embodiment. It is apparent from the scope of the claims that the embodiments added with such changes or improvements can be included in the technical scope of the present invention.

1 is a diagram illustrating an example of an image processing system 10 according to an embodiment. 2 is a diagram illustrating an example of a block configuration of an image processing apparatus 120. FIG. 3 is a diagram illustrating an example of a block configuration of a compression unit 230. FIG. 2 is a diagram illustrating an example of a block configuration of an image processing apparatus 170. FIG. It is a figure which shows an example of the other block structure of the compression part 230. FIG. 3 is a diagram illustrating an example of a captured moving image obtained by the imaging apparatus 100. FIG. It is a figure which shows an example of the histogram 700 of the gradation value in a characteristic area or a background area. It is a figure which shows an example of the conversion curve for gradation conversion. It is a figure which shows an example of the selection method in which the compression control part 210 selects a compression parameter for every area | region. It is a figure which shows an example of a motion vector search range. It is a figure which shows an example of the dependence of the search area width with respect to the magnitude | size of a position difference. It is a figure which shows the importance level of the partial area | region in a characteristic area. 12 is a diagram showing a display example by the display device 180. FIG. It is a figure which shows an example of the block configuration of the image processing apparatus 170 in another structure. It is a figure which shows an example of the feature point in a human face. It is a figure which shows typically an example of the change of the face shape at the time of changing the weighting coefficient b. It is a figure which shows an example of the image obtained by converting a sample image into an average face shape. It is a figure which shows typically an example of the change of the pixel value at the time of changing the weighting coefficient q. It is a figure which shows an example of the model which the model storage part 350 has stored in the table format. It is a figure which shows an example of the image processing system 20 which concerns on other embodiment. 2 is a diagram illustrating an example of a hardware configuration of an image processing device 120 and an image processing device 170. FIG.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 Image processing system 20 Image processing system 100 Image pick-up apparatus 102 Image pick-up part 104 Image pick-up image compression part 110 Communication network 120 Image processing apparatus 130 Person 140 Mobile body 150 Monitoring object space 160 Space 170 Image processing apparatus 175 Image DB
180 Display device 201 Compressed image acquisition unit 202 Compressed moving image decompression unit 203 Feature region detection unit 204 Image quality acquisition unit 205 Condition acquisition unit 206 Association processing unit 207 Output unit 208 Output image number acquisition unit 209 Threshold acquisition unit 210 Compression control unit 212 Features Region specifying unit 214 Position difference calculation unit 216 Search region determination unit 230 Compression unit 232 Image division unit 234 Fixed value unit 236 Compression processing unit 240 Image conversion unit 241 Image conversion unit 250 Image acquisition unit 262 Resolution determination unit 264 Tone number determination Unit 266 color number determination unit 268 dynamic range determination unit 301 image acquisition unit 302 association analysis unit 310 expansion control unit 320 expansion unit 322 decoder 332 image enlargement unit 330 synthesis unit 340 output unit 350 model storage unit 360 feature area information acquisition unit 370 Feature Area Selection Unit 372 Lighting Condition Specification Unit 374 direction specifying unit 376 correlation value acquiring unit 380 image generating unit 390 instruction acquiring unit 510 image quality converting unit 520 difference processing unit 522 inter-layer difference processing unit 530 encoding unit 532 encoder 600 captured image 601 head region 602 body region 603 Moving body region 610 Captured image 611 Head region 612 Body region 620 Captured image 621 Head region 622 Body region 630 Captured image 631 Head region 632 Body region 700 Histogram 710 Characteristic length 810 Conversion curve 820 Conversion curve 804 Image Processing unit 1000 Captured image 1010 Feature area 1020 Area 1100 Line 1200 Head area 1210 Eye area 1212 Eye area 1214 Eyebrow area 1220 Mouth area 1230 Nose area 1240 Ear area 1300 Movie area 1301 Attention image area 1310 Head area 1311 Head image 15 5 CPU
1510 ROM
1520 RAM
1530 Communication interface 1540 Hard disk drive 1550 Flexible disk drive 1560 CD-ROM drive 1570 Input / output chip 1575 Graphic controller 1580 Display device 1582 Host controller 1584 Input / output controller 1590 Flexible disk 1595 CD-ROM
1598 Network communication device

Claims (28)

An image processing apparatus for converting and outputting an image,
From the image, the feature region detecting unit for detecting a plurality of characteristic regions containing different types of objects to each other,
For each of the plurality of feature regions, a gradation number determination unit that determines the number of gradations of each feature region in the image obtained by the conversion according to the frequency distribution of the gradation values in the image of each feature region When,
The images of the plurality of feature regions are respectively converted into images having the number of gradations determined by the number-of-tones determination unit, and an image of a region other than the plurality of feature regions in the image is smaller than the number of feature regions An image conversion unit for converting to a number of images;
An output unit for outputting an image obtained by conversion by the image conversion unit,
The number-of-gradations determination unit determines the number of gradations determined in advance according to the type of object included in each feature region as the half-value width of the frequency distribution of the gradation values in each of the plurality of feature regions is shorter. Processing apparatus for determining a smaller number of gradations with respect to. The gradation number determination unit subtracts a value inversely proportional to the half-value width in each of the plurality of feature areas from a gradation number determined in advance according to the type of object included in each of the plurality of feature areas. The image processing apparatus according to claim 1, wherein the obtained value is determined as the number of gradations of each feature region in the image obtained by the conversion by the image conversion unit. The image according to claim 1, wherein the image conversion unit further converts the image into an image having a different number of colors in the plurality of feature regions in the image and regions other than the plurality of feature regions in the image. Processing equipment. The image processing apparatus according to claim 3, wherein the image conversion unit converts an image of a region other than the plurality of feature regions in the image into an image having a smaller number of colors than the plurality of feature regions. The image conversion unit converts an image of an area other than the plurality of feature areas in the image into an image represented by a color generated from a smaller number of color components than the plurality of feature areas. Image processing apparatus. 6. The image conversion unit according to claim 3, wherein the image conversion unit converts the images of the plurality of feature regions in the image into images having a predetermined number of colors according to the features of the feature regions. 7. Image processing device. 7. The image conversion unit according to claim 3, wherein the image conversion unit converts the images of the plurality of feature regions in the image into images having a predetermined number of colors according to the types of objects included in the feature regions. The image processing apparatus according to item. The image processing apparatus includes:
A color set indicating a combination of colors that can be used in the feature region is stored in association with the type of object included in the feature region and the half-value width ,
As colors that can be used for each of the plurality of feature regions in the image obtained by the conversion by the image conversion unit, the color is stored in association with the type of object included in each feature region and the half-value width in each feature region. A color number determining unit that selects a combination of colors indicated by the color set;
The image conversion unit uses the combination of colors selected by the color number determination unit for each of the plurality of feature regions, so that the images of the plurality of feature regions in the image are included in the feature regions. The image processing apparatus according to claim 6, wherein the image processing apparatus converts the image into an image having a predetermined number of colors according to the type of the image. 7. The image conversion unit according to claim 3, wherein the image conversion unit converts the images of the plurality of feature regions in the image into images each represented by a combination color predetermined according to the feature of the feature region. The image processing apparatus according to item. The image conversion unit converts the images of the plurality of feature regions in the image into images represented by colors generated from a predetermined number of color components according to the features of the feature regions, respectively. An image processing apparatus according to 1. A color number determination unit that determines, for each of the plurality of feature regions, the number of colors in the image obtained by the conversion by the image conversion unit based on a color frequency distribution in the images of the plurality of feature regions; ,
The image processing apparatus according to claim 6, wherein the image conversion unit converts the images of the plurality of feature regions in the image into images having the number of colors determined by the color number determination unit. It further includes an image quality acquisition unit that acquires the number of colors in association with the features of the feature region,
The image according to claim 6, wherein the image conversion unit converts the images of the plurality of feature regions in the image into images of the number of colors acquired by the image quality acquisition unit in association with the features of the respective feature regions. Processing equipment. The image conversion unit further converts the image into an image having a different dynamic range between the plurality of feature regions in the image and regions other than the plurality of feature regions in the image. The image processing apparatus according to item. The image processing apparatus according to claim 13, wherein the image conversion unit converts an image of a region other than the plurality of feature regions in the image into an image having a dynamic range wider than the plurality of feature regions. The image processing device according to claim 13, wherein the image conversion unit converts the images of the plurality of feature regions in the image into images having a dynamic range determined in advance according to the features of the feature regions. The image processing device according to claim 15, wherein the image conversion unit converts the images of the plurality of feature regions in the image into images having a dynamic range determined in advance according to the type of the object included in the feature region. . A dynamic range determination unit that determines a dynamic range in an image obtained by conversion by the image conversion unit based on a frequency distribution of gradation values in the images of the plurality of feature regions, for each of the plurality of feature regions; In addition,
The image processing apparatus stores an LUT that performs gradation conversion on an input pixel value in association with the type of object included in the feature region and the half width .
The dynamic range determination unit selects the LUT stored in association with the type of object included in each of the plurality of feature regions and the half-value width in each feature region. Determine the dynamic range for each of the
The image conversion unit performs gradation conversion on each feature region with the LUT selected by the dynamic range determination unit for each of the plurality of feature regions, thereby converting the images of the plurality of feature regions in the image into feature regions. The image processing apparatus according to claim 16, wherein each of the images is converted into an image having a predetermined dynamic range according to the type of object included in the image. A dynamic range determination unit that determines a dynamic range in an image obtained by conversion by the image conversion unit based on a frequency distribution of gradation values in the images of the plurality of feature regions, for each of the plurality of feature regions; In addition,
The image processing device according to claim 15, wherein the image conversion unit converts the images of the plurality of characteristic regions in the image into images having a dynamic range determined by the dynamic range determination unit. It further includes an image quality acquisition unit that acquires a dynamic range in association with the feature of the feature region,
The image according to claim 15, wherein the image conversion unit converts the images of the plurality of feature regions in the image into images having a dynamic range acquired by the image quality acquisition unit in association with the features of the feature regions. Processing equipment. 20. The output unit according to claim 1, wherein the output unit outputs information specifying the plurality of feature regions detected by the feature region detection unit in association with an image obtained by conversion by the image conversion unit. The image processing apparatus according to one item. The output unit corresponds to the image obtained by converting the information identifying the plurality of feature regions detected by the feature region detection unit and the information identifying the features of the plurality of feature regions by the image conversion unit. The image processing apparatus according to claim 19, wherein the image processing apparatus outputs the image. An image acquisition unit that acquires a plurality of captured images captured from a plurality of different imaging positions as the images to be converted;
The output unit includes the first number of in-feature region images that are images of the subject imaged in the plurality of feature regions respectively generated from the first number of the images, and the first number. The second number of out-of-feature region images, which are images outside the plurality of feature regions respectively generated from the second number of the images different from the second number, are output. Image processing device. 23. The image processing apparatus according to claim 22, wherein the output unit outputs the first number of images in the feature region, each generated from the first number of the images larger than the second number. The image processing apparatus according to claim 22 or 23, wherein the image acquisition unit acquires a plurality of captured images captured from a plurality of different imaging directions as the images to be converted. 25. The output unit according to claim 22, wherein the output unit outputs a number of images in the feature area that are generated from each of the plurality of feature areas in the image according to features of the plurality of feature areas. The image processing apparatus according to any one of claims. An output image number acquisition unit for acquiring the number of images to be output in association with the features of the feature region;
The output unit outputs the number of images in the feature area, which is generated from each of the plurality of feature areas in the image, in correspondence with the features of the plurality of feature areas and acquired by the output image number acquisition unit. The image processing apparatus according to claim 25. Computer
A program for causing an image processing apparatus according to any one of claims 1 to 26 to function. An image processing method for converting and outputting an image,
From the image, the feature region detecting step of detecting a plurality of characteristic regions containing different types of objects to each other,
For each of the plurality of feature regions, a gradation number determination step for determining the number of gradations of each feature region in the image obtained by the conversion according to the frequency distribution of the gradation values in the image of each feature region When,
The images of the plurality of feature regions are respectively converted into images having the number of gradations determined in the gradation number determination step, and images of regions other than the plurality of feature regions in the image are less than the plurality of feature regions. An image conversion stage to convert to a logarithmic image;
An output step of outputting the image obtained by the conversion in the image conversion step,
In the step of determining the number of gradations, as the half value width of the frequency distribution of the gradation values in each of the plurality of feature regions is shorter, the number of gradations that is determined in advance according to the type of object included in each feature region Image processing method for determining a smaller number of gradations relative to.

Images