Image processing device, image processing method, and image processing system

Abstract

The present disclosure provides an image processing device, image processing method, and image processing system that are capable of deciding a cutout region in accordance with change in the detection position of the same object between frame images captured at different times. The image processing device includes: a first region setting unit configured to set a first region including a detection position of an object in a cutout region in a first frame image; and a cutout region deciding unit configured to decide a cutout region in a second frame image subsequent to the first frame image, on the basis of a positional relation between the first region and a detection position of the object in the second frame image.

1 . An image processing device comprising:
 processing circuitry configured to:   set a first region in a first frame image on based on a positional relation between the first region in a second frame image that is previous to the first frame image and a detection position of an object in the first frame image, and   set a cutout region in the first frame image based on the first region in the first frame image.   
     
     
         2 . The image processing device according to  claim 1 , wherein the processing circuitry further configured to generate a cutout image by cutting out the cutout region in the first frame image. 
     
     
         3 . The image processing device according to  claim 1 , wherein the first region in the second frame image is a region used for deciding whether to use the detection position of the object in the first frame image for changing a position of the cutout region. 
     
     
         4 . The image processing device according to  claim 2 , wherein the first region in the second frame image is a region used for deciding not to use the detection position of the object in the first frame image for changing a position of the cutout region when the first region in the second frame image includes the detection position of the object in the first frame image. 
     
     
         5 . The image processing device according to  claim 1 , wherein the first region is a dead zone region. 
     
     
         6 . The image processing device according to  claim 1 , wherein the first region in the first frame image includes at least a part of the object in the first frame image. 
     
     
         7 . The image processing device according to  claim 1 , wherein the processing circuitry is further configured to determine whether to set a position of the first region in the first frame image the same as the first region in the second frame image based on the positional relation between the first region in the second frame image and the detection position of the object in the first frame image. 
     
     
         8 . The image processing device according to  claim 1 , wherein when the first region in the second frame image includes the detection position of the object in the first frame image, the processing circuitry is further configured to set a position of the first region in the first frame image the same as the first region in the second frame image. 
     
     
         9 . The image processing device according to  claim 1 , wherein a first position of the center of the cutout region in the first frame image is the same as a second position of the center of the first region in the first frame image 
     
     
         10 . The image processing device according to  claim 1 , wherein the processing circuitry is further configured to:
 set one of plurality of objects as a tracking target,   set the first region in the first frame image on based on the positional relation between the first region in the second frame image and the detection position of the tracking target in the first frame image, and   set the cutout region in the first frame image based on the first region in the first frame image.   
     
     
         11 . The image processing device according to  claim 1 , wherein the processing circuitry further configured to set the first region in the first frame image at a position where the first region in the second frame image is moved in a direction of the detection position of the object in the first frame image by the minimum distance between an outline of the first region in the second frame image and the detection position in the first frame image when the first region in the second frame image does not include the detection position of the object in the first frame image. 
     
     
         12 . The image processing device according to  claim 1 , wherein the processing circuitry further configured to set the first region in the first frame image such that the detection position of the object in the first frame image overlaps an outline of the first region in the first frame image when the first region in the second frame image does not include the detection position of the object in the first frame image. 
     
     
         13 . The image processing device according to  claim 1 , wherein the processing circuitry further configured to set the first region in the first frame image such that the detection position of the object in the first frame image is not out of the first region in the first frame image surrounded by an outline of the first region in the first frame image when the first region in the second frame image does not include the detection position of the object in the first frame image. 
     
     
         14 . The image processing device according to  claim 12 , wherein the detection position of the object in the second frame image overlaps the outline of the first region in the second frame image. 
     
     
         15 . The image processing device according to  claim 12 , wherein the processing circuitry further configured to set the first region in a third frame image subsequent to the first frame image such that the detection position of the object in the third frame image overlaps the outline of the first region in the third frame image when the first region in the first frame image does not include the detection position of the object in the third frame image. 
     
     
         16 . A method for image processing, the method comprising:
 setting, by processing circuitry, a first region in a first frame image on based on a positional relation between the first region in a second frame image that is previous to the first frame image and a detection position of an object in the first frame image; and   setting a cutout region in the first frame image based on the first region in the first frame image.   
     
     
         17 . The method according to  claim 16 , wherein the first region in the second frame image is a region used for deciding whether to use the detection position of the object in the first frame image for changing a position of the cutout region. 
     
     
         18 . The method according to  claim 16 , further comprising:
 setting the first region in the first frame image such that the detection position of the object in the first frame image overlaps an outline of the first region in the first frame image when the first region in the second frame image does not include the detection position of the object in the first frame image.   
     
     
         19 . An image processing system comprising:
 processing circuitry configured to:   
       set a first region in a first frame image on based on a positional relation between the first region in a second frame image that is previous to the first frame image and a detection position of an object in the first frame image, and 
       set a cutout region in the first frame image based on the first region in the first frame image. 
     
     
         20 . The image processing system according to  claim 19 , wherein the first region in the second frame image is a region used for deciding whether to use the detection position of the object in the first frame image for changing a position of the cutout region.