Image processing device and method for moving gesture recognition using difference images
An image processing device includes a difference image generation unit which generates a difference image by obtaining a difference between frames of a cutout image which is obtained by cutting out a predetermined region on a photographed image; a feature amount extracting unit which extracts a feature amount from the difference image; and a recognition unit which recognizes a specific movement of an object on the photographed image based on the feature amount which is obtained from the plurality of difference images which are aligned in time sequence.
1. An image processing device, comprising:
a central processing unit (CPU) configured to:
detect one of a part of a body or the body as a target to be recognized from a photographed image, wherein the photographed image is aligned in time sequence; and
set a recognition region on the photographed image based on the detected one of the part of the body or the body;
track the recognition region in the photographed image;
extract a feature amount from the tracked recognition region in the photographed image;
determine a movement in the set recognition region based on a magnitude of a motion vector in the set recognition region;
recognize a specific movement of the one of the part of the body or the body based on the determined movement;
generate a frame that denotes the recognition region; and
control display of the frame.
2. The image processing device according to claim 1 ,
wherein the CPU is further configured to recognize a gesture by the one of the part of the body or the body based on the extracted feature amount.
3. The image processing device according to claim 1 , wherein the CPU is further configured to determine a plurality of sub-regions based on the tracked recognition region in the photographed image.
4. The image processing device according to claim 3 ,
wherein the CPU is further configured to determine the plurality of sub-regions based on the detected one of the part of the body or the body.
5. The image processing device according to claim 3 , wherein the CPU is further configured to generate a difference image in each of the plurality of sub-regions in the set recognition region.
6. The image processing device according to claim 1 ,
wherein the CPU is further configured to recognize a gesture of the one of the part of the body or the body as the specific movement.
7. The image processing device according to claim 1 ,
wherein the CPU is further configured to control display of an image, wherein the image denotes a position of the frame.
8. The image processing device according to claim 1 ,
wherein the CPU is further configured to control a plurality of display devices to display the frame and an image that denotes a position of the frame.
9. The image processing device according to claim 1 ,
wherein the CPU is further configured to control a display device to display a gesture recognition process.
10. The image processing device according to claim 1 ,
wherein the CPU is further configured to extract the feature amount based on an average luminance of a plurality of pixels in the photographed image.
11. An image processing method, comprising:
detecting one of a part of a body or the body as a target to be recognized from a photographed image, wherein the photographed image is aligned in time sequence; and
setting a recognition region on the photographed image based on the detected one of the part of the body or the body;
tracking the set recognition region in the photographed image;
extracting a feature amount from the tracked recognition region in the photographed image;
determining a movement in the set recognition region based on a magnitude of a motion vector in the set recognition region;
recognizing a specific movement of the one of the part of the body or the body based on the determined movement;
generating a frame denoting the recognition region; and
controlling display of the frame.
12. A non-transitory computer readable medium having stored thereon computer-readable instructions, which when executed by a computer, cause the computer to execute operations, the operations comprising:
detecting one of a part of a body or the body as a target to be recognized from a photographed image, wherein the photographed image is aligned in time sequence; and
setting a recognition region on the photographed image based on the detected one of the part of the body or the body;
tracking the set recognition region in the photographed image;
extracting a feature amount from the tracked recognition region in the photographed image;
determining a movement in the set recognition region based on a magnitude of a motion vector in the set recognition region;
recognizing a specific movement of the one of the part of the body or the body based on the determined movement;
generating a frame denoting the recognition region; and
controlling display of the frame.