Issue No. 02 - February (2012 vol. 34)
L. De-Maeztu , Dept. of Electr. & Electron. Eng., Public Univ. of Navarre, Pamplona, Spain
A. Villanueva , Dept. of Electr. & Electron. Eng., Public Univ. of Navarre, Pamplona, Spain
R. Cabeza , Dept. of Electr. & Electron. Eng., Public Univ. of Navarre, Pamplona, Spain
Adaptive-weight algorithms currently represent the state of the art in local stereo matching. However, due to their computational requirements, these types of solutions are not suitable for real-time implementation. Here, we present a novel aggregation method inspired by the anisotropic diffusion technique used in image filtering. The proposed aggregation algorithm produces results similar to adaptive-weight solutions while reducing the computational requirements. Moreover, near real-time performance is demonstrated with a GPU implementation of the algorithm.
stereo image processing, filtering theory, image matching, real-time systems, GPU implementation, real-time stereo matching, geodesic diffusion, adaptive weight algorithms, real-time implementation, anisotropic diffusion technique, image filtering, Anisotropic magnetoresistance, Image color analysis, Stereo vision, Algorithm design and analysis, Euclidean distance, Real time systems, Diffusion processes, Scene analysis, 3D/stereo scene analysis., Stereo
L. De-Maeztu, A. Villanueva, R. Cabeza, "Near Real-Time Stereo Matching Using Geodesic Diffusion", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 34, no. , pp. 410-416, February 2012, doi:10.1109/TPAMI.2011.192