Representative image generation device and representative image generation method

Abstract

A representative image generation device includes circuitry that identifies a selected image from a plurality of recorded images of an object. The plurality of recorded images are captured as the object traverses a predetermined area. The device prepares the selected image for display on a display device, wherein the selected image provides a visual recognizability of the object greater than a predetermined threshold.

What is claimed is: 
     
         1 . An imaging processing apparatus, comprising:
 circuitry configured to:
 detect a target object from a moving-image video based on motion detection; 
 track the target object that moves in the moving-image video; and 
 generate a representative image of the target object. 
   
     
     
         2 . The imaging processing apparatus according to  claim 1 , wherein the circuitry is further configured to:
 determine a visual recognizability of the target object while the target object is tracked; and   generate the representative image based on a result of the determined visual recognizability of the target object.   
     
     
         3 . The imaging processing apparatus according to  claim 2 , wherein the circuitry is further configured to:
 determine the visual recognizability of the target object in each of a plurality of frames of the moving-image video; and   generate the representative image from an image of a frame with a highest visual recognizability of the target object among the plurality of frames.   
     
     
         4 . The imaging processing apparatus according to  claim 2 , wherein the circuitry is further configured to:
 determine the visual recognizability of the target object in each of a plurality of frames of the moving-image video; and   generate the representative image from an image of a frame with the visual recognizability of the target object greater than a determined threshold among the plurality of frames.   
     
     
         5 . The imaging processing apparatus according to  claim 2 , wherein the circuitry is further configured to:
 calculate a weighting factor for each of a plurality of factors that indicates the visual recognizability of the target object in each of a plurality of frames of the moving-image video;   calculate, based on the weighting factor, a score of an image of a frame with a higher visual recognizability of the target object among the plurality of frames; and   generate, based on the calculated score, the representative image from the image of the frame with the higher visual recognizability of the target object among the plurality of frames.   
     
     
         6 . The imaging processing apparatus according to  claim 5 , wherein
 the weighting factor has a larger value as the visual recognizability of the target object is higher, and   the circuitry is further configured to generate the representative image from the image of the frame having a greatest sum of weighting factors among the plurality of frames.   
     
     
         7 . The imaging processing apparatus according to  claim 5 , wherein
 the weighting factor has a larger value as the visual recognizability of the target object is higher, and   the circuitry is further configured to generate the representative image from the image of the frame, among the plurality of frames, having a sum of weighting factors greater than or equal to a determined threshold.   
     
     
         8 . The imaging processing apparatus according to  claim 5 , wherein
 the circuitry is further configured to generate, based on a sum of weighting factors for a current frame greater than a sum of weighting factors for a previous frame, the representative image and update the representative image created from the previous frame.   
     
     
         9 . The imaging processing apparatus according to  claim 5 , wherein
 the target object is a person, and   the plurality of factors includes at least one of a size of the person, an aspect ratio of the person, a tracking direction of the person, human-likeness of the person, a direction of a face of the person, color information on the person, moving speed of the person, noise included in an image of the person, or luminance of the person.   
     
     
         10 . The imaging processing apparatus according to  claim 1 , wherein
 the circuitry is further configured to detect, from the moving-image video, the target object that satisfies a determined condition, and   the determined condition is one of that the target object has intruded on a determined no-entry area, or that the target object has crossed a determined specified line.   
     
     
         11 . A method, comprising:
 detecting a target object from a moving-image video based on motion detection;   tracking the target object that moves in the moving-image video; and   generating a representative image of the target object.   
     
     
         12 . The method according to  claim 11 , further comprising:
 determining a visual recognizability of the target object while the target object is tracked; and   generating the representative image based on a result of the determined visual recognizability of the target object.   
     
     
         13 . The method according to  claim 12 , further comprising:
 determining the visual recognizability of the target object in each of a plurality of frames of the moving-image video; and   generating the representative image from an image of a frame with a highest visual recognizability of the target object among the plurality of frames.   
     
     
         14 . The method according to  claim 12 , further comprising:
 determining the visual recognizability of the target object in each of a plurality of frames of the moving-image video; and   generating the representative image from an image of a frame with the visual recognizability of the target object greater than a determined threshold among the plurality of frames.   
     
     
         15 . The method according to  claim 12 , further comprising:
 calculating a weighting factor for each of a plurality of factors that indicates the visual recognizability of the target object in each of a plurality of frames of the moving-image video;   calculating, based on the weighting factor, a score of an image of a frame with a higher visual recognizability of the target object among the plurality of frames; and   generating, based on the calculated score, the representative image from the image of the frame with the higher visual recognizability of the target object among the plurality of frames.   
     
     
         16 . The method according to  claim 15 , wherein
 the weighting factor has a larger value as the visual recognizability of the target object is higher.   
     
     
         17 . The method according to  claim 16 , further comprising generating the representative image from the image of the frame having a greatest sum of weighting factors among the plurality of frames. 
     
     
         18 . The method according to  claim 16 , further comprising generating the representative image from the image of the frame, among the plurality of frames, having a sum of weighting factors greater than or equal to a determined threshold. 
     
     
         19 . The method according to  claim 12 , further comprising generating, based on a sum of weighting factors for a current frame greater than a sum of weighting factors for a previous frame, the representative image and update the representative image created from the previous frame. 
     
     
         20 . A non-transitory computer-readable medium having stored thereon, computer-executable instructions which, when executed by a processor, cause the processor to execute operations, the operations comprising:
 detecting a target object from a moving-image video based on motion detection;   tracking the target object that moves in the moving-image video; and   generating a representative image of the target object.