Processing apparatus, mobile object, processing method, and storage medium
A processing apparatus converts a first image into a second image with a lower resolution than a resolution of the first image, specifies a target region including a predetermined objective target in the second image on the basis of the second image, and specifies a target region including the objective target in the first image on the basis of the specified target region in the second image.
1. A processing apparatus comprising:
a storage device configured to store instructions; and
one or more processors,
wherein the one or more processors execute the instructions stored in the storage device to:
convert a first image into a second image with a lower resolution than a resolution of the first image, and
specify a target region including a predetermined objective target in the second image on the basis of the second image and specify a target region including the objective target in the first image on the basis of the specified target region in the second image,
wherein the one or more processors execute the instructions to specify the target region including the objective target in the first image before conversion into the second image on the basis of the target region in the second image and execute predetermined image recognition processing on the specified target region in the first image
wherein the predetermined image recognition processing includes processing for recognizing a gesture of the objective target on the basis of information regarding a specific region in the target region in the first image, and
wherein the predetermined image recognition processing includes the processing of recognizing the gesture using, with priority, the information regarding the specific region with a high degree of chronological change in motions of the objective target in two or more specific regions in the target region in the first image.
2. The processing apparatus according to claim 1 , wherein the one or more processors execute the instructions to analyze the second image obtained by converting the first image captured at a first clock time and the second image obtained by converting the first image captured at a second clock time later than the first clock time and track, in the second image corresponding to the second clock time, an objective target included in the target region in the second image corresponding to the first clock time.
3. The processing apparatus according to claim 1 , wherein the one or more processors execute the instructions to track the objective target in the second image on the basis of a change in position of the objective target in second images in a time series manner obtained by converting first images captured in a time series manner.
4. The processing apparatus according to claim 1 ,
wherein the objective target is a person, and
the one or more processors execute the instructions to track the person in the second image on the basis of one or more pieces of information out of a color of clothes of the person, a gender of the person, and a hairstyle of the person obtained from the second image, which is obtained by converting the first image captured in the past, or stored in a storage.
5. The processing apparatus according to claim 1 , wherein the predetermined image recognition processing includes specifying the specific region on the basis of recognition of a skeleton or joint points in the target region in the first image.
6. The processing apparatus according to claim 5 , wherein the predetermined image recognition processing includes processing of regarding a region including arms or hands of the objective target as the specific region on the basis of a result of recognizing the skeleton or the joint points.
7. The processing apparatus according to claim 1 , wherein the two or more specific regions include at least a specific region specified as a region including a right arm or a right hand of the objective target and a specific region specified as a region including a left arm or a left hand of the objective target.
8. The processing apparatus according to claim 1 ,
wherein the objective target is a person, and
the one or more processors execute the instructions to extract a region including a face of the person in the first image, match feature amounts of the face included in the extracted region with feature amounts of the face of the person stored in a storage in advance, and track the person as the objective target.
9. The processing apparatus according to claim 1 ,
wherein the objective target is a person, and
the one or more processors execute the instructions to
track, in the second image obtained by converting the first image captured at a second clock time later than a first clock time, the person included in the target region of the second image obtained by converting the first image captured at the first clock time, and
extract a region including arms or hands of the person tracked in the first image captured at the second clock time on the basis of a result of the tracking and recognize a gesture of the person on the basis of the extracted region.
10. A processing apparatus according to claim 1 , wherein the one or more processors execute the instructions to control a mobile object on the basis of the gesture.
11. A mobile object comprising:
the processing apparatus according to claim 1 mounted therein.
12. A processing method comprising, by a computer:
converting a first image into a second image with a lower resolution than a resolution of the first image; and
specifying a target region including a predetermined objective target in the second image on the basis of the second image and specifying a target region including the objective target in the first image on the basis of the specified target region in the second image,
wherein the specifying the target region comprises specifying the target region including the objective target in the first image before conversion into the second image on the basis of the target region in the second image and execute predetermined image recognition processing on the specified target region in the first image
wherein the predetermined image recognition processing includes processing for recognizing a gesture of the objective target on the basis of information regarding a specific region in the target region in the first image, and
wherein the predetermined image recognition processing includes the processing of recognizing the gesture using, with priority, the information regarding the specific region with a high degree of chronological change in motions of the objective target in two or more specific regions in the target region in the first image.
13. A non-transitory computer storage medium storing instructions causing a computer to execute:
converting a first image into a second image with a lower resolution than a resolution of the first image; and
specifying a target region including a predetermined objective target in the second image on the basis of the second image and specifying a target region including the objective target in the first image on the basis of the specified target region in the second image,
wherein the specifying the target region comprises specifying the target region including the objective target in the first image before conversion into the second image on the basis of the target region in the second image and execute predetermined image recognition processing on the specified target region in the first image
wherein the predetermined image recognition processing includes processing for recognizing a gesture of the objective target on the basis of information regarding a specific region in the target region in the first image, and
wherein the predetermined image recognition processing includes the processing of recognizing the gesture using, with priority, the information regarding the specific region with a high degree of chronological change in motions of the objective target in two or more specific regions in the target region in the first image.