초록 ▼

A method and a system for progressive stereo matching of digital images representing a scene. In general, the present invention uses a progressive iterative technique that includes a disparity gradient limit principle and a least commitment strategy. The progressive iterative technique finds general

A method and a system for progressive stereo matching of digital images representing a scene. In general, the present invention uses a progressive iterative technique that includes a disparity gradient limit principle and a least commitment strategy. The progressive iterative technique finds generally unambiguous pixel matches by beginning with a few reliable pixel matches and finding progressively more unambiguous pixel matches. Unambiguous pixel matches found in the previous iteration are used to define the search ranges for each pixel to guide matching in the current iteration. Unambiguous pixel matches in the current iteration then are found using a novel correlation technique and based on a correlation score associated with a pixel match. The search range is capable of being rotated, and is part of a novel correlation technique of the present invention that provides a more robust estimate of pixel match reliability. Potential pixel matches found in the search ranges are tested for ambiguity and any unambiguous matches are selected and added to the set of reliable pixel matches. The ambiguity testing includes determining a correlation score for the pixel match and classifying the match based on the correlation score. The present invention also includes a system for progressive image matching that incorporates the method of the present invention.

대표청구항 ▼

1. A method of progressively stereo matching a first and a second digital image having pixels, comprising: determining a set of previous unambiguous matches between pixels of the first digital image and the second digital image; defining a search range based on the set of previous unambiguous pi

1. A method of progressively stereo matching a first and a second digital image having pixels, comprising: determining a set of previous unambiguous matches between pixels of the first digital image and the second digital image; defining a search range based on the set of previous unambiguous pixel matches; generating an updated set of previous unambiguous pixel matches by determining current unambiguous pixel matches within the search range and appending them to the set of previous unambiguous pixel matches; iteratively redefining the search range and updating the set of previous unambiguous pixel matches until the first and second images have been suitable matched. 2. The method of claim 1, wherein determining the set of previous unambiguous pixel matches includes using at least one of: (a) a feature-based stereo matching technique; (b) user input; (c) unambiguous pixel matches found during previous iterations. 3. The method of claim 1, wherein defining a search range includes determining a size and an orientation of the search range. 4. The method of claim 3, wherein the search range is capable of being rotated based on the location of an epipolar line. 5. The method of claim 1, wherein determining current unambiguous pixel matches includes computing a correlation score between pixels within the search range. 6. The method of claim 5, wherein separate search ranges are defined for the first image and the second image. 7. The method of claim 6, wherein the separate search ranges are correlation windows that are capable of being rotated about respective epipolar lines of each image. 8. The method of claim 5, wherein a match label is assigned to a pixel based on the correlation score. 9. The method of claim 8, wherein the match label indicates whether the pixel is at least one of: (a) a matched pixel; (b) an unmatched pixel; (c) an unknown pixel. 10. The method of claim 1, wherein the search range is redefined based on the updated set of previous unambiguous pixel matches. 11. The method of claim 1 wherein the first and second images are suitably matched if at least one of the following occurs: (a) no further pixel matches can be found; (b) a desired number of iterations is attained. 12. A computer-readable medium having computer-executable instructions for performing the method recited in claim 1.