Method and apparatus for performing segmentation of an image
A method and system for segmenting a plurality of images. The method comprises the steps of segmenting the image through a novel clustering technique that is, generating a composite depth map including temporally stable segments of the image as well as segments in subsequent images that have changed. These changes may be determined by determining one or more differences between the temporally stable depth map and segments included in one or more subsequent frames. Thereafter, the portions of the one or more subsequent frames that include segments including changes from their corresponding segments in the temporally stable depth map are processed and are combined with the segments from the temporally stable depth map to compute their associated disparities in one or more subsequent frames. The images may include a pair of stereo images acquired through a stereo camera system at a substantially similar time.
1. A method for performing segmentation in a stereo image capture device, comprising the steps of:
determining one or more segments present in a first image acquired at a first time;
determining one or more segments present in a second image acquired at the first time corresponding to one or more of the one or more segments present in the first image;
determining a disparity of one of the one or more segments in the first image;
assigning the determined disparity to every pixel comprising the one of the one or more segments in the first image;
determining a disparity of one or more of the one or more segments in the second image;
determining one or more corresponding segments in the first and second images that include at least one pixel having different disparity values between the first and second images; and
for each corresponding segment of the determined one or more corresponding segments in the first and second images, assigning a disparity of the corresponding segment in the first image to every pixel in the respective corresponding segment in the second image.
2. The method of claim 1 , wherein the first and second images comprise a stereo pair of images.
3. The method of claim 2 , further comprising the step of generating a composite segmentation image in accordance with the one or more segments present in the first and second images.
4. A computer program stored in a non-transitory storage medium for performing segmentation in a stereo image capture device, the computer program, when implemented on a processor, causes the processor to perform the steps of:
determining one or more segments present in a first image acquired at a first time;
determining one or more segments present in a second image acquired at the first time corresponding to one or more of the one or more segments present in the first image;
determining a disparity of one of the one or more segments in the first image;
assigning the determined disparity to every pixel comprising the one of the one or more segments in the first image;
determining a disparity of one or more of the one or more segments in the second image;
determining one or more corresponding segments in the first and second images that include at least one pixel having different disparity values between the first and second images; and
for each corresponding segment of the determined one or more corresponding segments in the first and second images, assigning a disparity of the corresponding segment in the first image to every pixel in the respective corresponding segment in the second image.
5. The computer program of claim 4 , wherein the first and second images comprise a stereo pair of images.
6. The computer program of claim 4 , further comprising generating a composite segmentation image in accordance with the one or more segments present in the first and second images.