CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2004 vol.26 Issue No.06 - June
Issue No.06 - June (2004 vol.26)
Bogdan Georgescu , IEEE
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TPAMI.2004.2
<p><b>Abstract</b>—To solve the general point correspondence problem in which the underlying transformation between image patches is represented by a homography, a solution based on extensive use of first order differential techniques is proposed. We integrate in a single robust M-estimation framework the traditional optical flow method and matching of local color distributions. These distributions are computed with spatially oriented kernels in the 5D joint spatial/color space. The estimation process is initiated at the third level of a Gaussian pyramid, uses only local information, and the illumination changes between the two images are also taken into account. Subpixel matching accuracy is achieved under large projective distortions significantly exceeding the performance of any of the two components alone. As an application, the correspondence algorithm is employed in oriented tracking of objects.</p>
Correspondence problem, optical flow, color distribution matching, motion tracking, wide-baseline stereo.
Bogdan Georgescu, "Point Matching under Large Image Deformations and Illumination Changes", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.26, no. 6, pp. 674-688, June 2004, doi:10.1109/TPAMI.2004.2