Multiple Plane Detection in Image Pairs Using J-Linkage

David F. Fouhey, Daniel Scharstein, Amy J. BriggsICPR 2010 · OpenReview

Abstract

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.
BibTeX
@inproceedings{fouhey2010multiple,
  author = {David F. Fouhey and Daniel Scharstein and Amy J. Briggs},
  title = {{Multiple Plane Detection in Image Pairs Using J-Linkage}},
  booktitle = {ICPR},
  year = {2010},
  url = {https://openreview.net/forum?id=rqOxzEAyNU},
}

Loading related content...

Figure