Using disparity functional for stereo correspondence and surface reconstruction
Computer Vision, Graphics, and Image Processing
Surfaces from Stereo: Integrating Feature Matching, Disparity Estimation, and Contour Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Direct evidence for occlusion in stereo and motion
Image and Vision Computing - Special issue on the first ECCV 1990
Stereo image interpretation in the presence of narrow occluding objects
Stereo image interpretation in the presence of narrow occluding objects
International Journal of Computer Vision
Intrinsic Images for Dense Stereo Matching with Occlusions
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part I
Hi-index | 0.14 |
Most contemporary stereo correspondence algorithms impose global consistency among candidate match-points using Spatial Hierarchy Mechanism- (SHM) based techniques that rely on either the local support within a 2D neighborhood in the image plane and/or cooperative processes between multiple levels of a pixel-resolution or structural-description hierarchy. We analyze the stereo matching failures in SHM-based techniques in the presence of narrow occluding objects and propose the Dynamic Disparity Search (DDS) framework to reduce false-positive matches. Experiments with indoor and outdoor scenes demonstrate a significant reduction in the false-positive match rates of a DDS-based stereo algorithm as compared to those of two existing algorithms.