Image processing apparatus, method, and program
The present invention relates to an image processing apparatus, method, and program that can extract an object from an input image more easily and more accurately. A face detecting unit ( 31 ) detects a face from an input image, a mask area setting unit ( 33 ) sets a mask area which masks a person in the input image based on a position of the face detected by the face detecting unit ( 31 ), a background model updating unit ( 51 ) updates a background image by learning areas other than the mask area in the input image as the background image, and a separating unit ( 54 ) separates the input image into the background image and a foreground image which is an area of the person in the input image based on the background image updated by the background model updating unit ( 51 ) and the input image. The present invention can be applied to, for example, an image processing apparatus that extracts a person from an input image.
1. An image processing apparatus comprising:
a central processing unit (CPU) configured to:
detect a dynamic body from a second frame of an input image;
set an area of the dynamic body in the second frame as a mask area based on a position of the dynamic body in the second frame;
update a background image of a first frame previous to the second frame by learning areas other than the mask area in the second frame as the background image; and
separate the second frame of the input image into a background image, and a foreground image that is an area of the dynamic body in the input image, based on the updated background image of the first frame and the second frame of the input image.
2. The image processing apparatus according to claim 1 , wherein the CPU is configured to:
detect the dynamic body for each frame of the input image;
the mask area when a change in the position of the dynamic body between the second frame and the first frame is larger than a given threshold; and
update the background image of the first frame by learning, as the background image, the area other than the mask area that is set when the change in the position of the dynamic body between the second frame and the first frame is larger than the given threshold.
3. The image processing apparatus according to claim 2 , wherein the CPU is configured to:
an area of the dynamic body in the first frame of the input image as an initial mask area; and
learn areas other than the mask area that is set when the change in the position of the dynamic body between the second frame and the first frame is larger than the given threshold and when an area corresponding to at least a portion of the initial mask area remains not learned as the background image.
4. The image processing apparatus according to claim 3 , wherein the CPU is configured to:
store the updated background image of the first frame; and
update the background image based on the second frame of the input image, and the stored background image when the change in the position of the dynamic body between the second frame and the first frame is larger than the given threshold.
5. The image processing apparatus according to claim 4 , wherein the CPU is configured to:
update the background image based on the input image, and the stored background image for a predetermined number of frames when all the correspondence areas are learned as the background image.
6. An image processing method comprising:
a device configured to:
detect a dynamic body from a second frame of an input image;
set an area of the dynamic body in the second frame as a mask area based on a position of the dynamic body in the second frame;
update a background image of a first frame previous to the second frame by learning areas other than the mask area in the second frame as the background image; and
separate the second frame of the input image into a background image, and a foreground image that is an area of the dynamic body in the input image, based on the updated background image of the first frame and the second frame of the input image.
7. A non-transitory computer-readable recording medium having stored thereon, a set of computer-executable instructions for causing a computer to perform steps comprising:
detecting a dynamic body from a second frame of an input image;
setting an area of the dynamic body in the second frame as a mask area based on a position of the dynamic body in the second frame;
updating a background image of a first frame previous to the second frame by learning areas other than the mask area in the second frame as the background image; and
separating the second frame of the input image into a background image, and a foreground image that is an area of the dynamic body in the input image, based on the updated background image of the first frame and the second frame of the input image.
8. The image processing apparatus according to claim 1 , wherein the CPU is configured to:
detect a face of the dynamic body from the second frame of the input image.
9. The image processing apparatus according to claim 8 , wherein the CPU is further configured to:
estimate the area of the dynamic body based on a face area of the detected face of the dynamic body.
10. The image processing apparatus according to claim 9 , wherein the CPU is configured to:
determine a change in the position of the dynamic body between the second frame and the first frame by comparing coordinates of center of gravity of the face area in the second frame and the first frame.
11. The image processing apparatus according to claim 9 , wherein the CPU is configured to:
detect the face area as a rectangular area represented by coordinates of a upper-left vertex and lower-right vertex of the rectangular area.
12. The image processing apparatus according to claim 1 , wherein the CPU is configured to:
set an area set by a user as an initial mask area when the dynamic body is determined in the area set by the user.