Multiple Plane Detection in Image Pairs Using J-Linkage

—We present a new method for the robust detection and matching of multiple planes in pairs of images. Such planes can serve as stable landmarks for vision-based urban navigation. Our approach starts from SIFT matches and generates multiple local homography hypotheses using the recent J-linkage technique by Toldo and Fusiello, a robust randomized multi-model estimation algorithm. These hypotheses are then globally merged, spatially analyzed, robustly fitted, and checked for stability. When tested on more than 30,000 image pairs taken from panoramic views of a college campus, our method yields no false positives and recovers 72% of the matchable building walls identified by a human, despite significant occlusions and viewpoint changes. Keywords-3D shape recovery; perceptual organization; stereo and motion.

• Type: Conference
• Year: 2010
• Where: ICPR
• Authors: David Ford Fouhey, Daniel Scharstein, Amy Briggs
• Keywords: Computer Vision, ICPR 2010, Local Homography Hypotheses, Randomized Multi-model Estimation, Vision-based Urban Navigation