Tree structural watershed for stereo matching
2012 (English)In: IVCNZ '12, Proceedings of the 27th Conference on Image and Vision Computing New Zealand, ACM Digital Library, 2012, 340-345 p.Conference paper (Other academic)Text
We present a new method for dense stereo matching based on a tree structural cost volume watershed (TSCVW) and a region combination (RC) process. Given a cost volume as the data cost and an initial segmentation result, the proposed TSCVW method reliably estimates the disparities in a segment by using energy optimization to control plane segmentation and plane fitting. Then the disparities in the incorrectly fitted and occluded regions are refined using our RC process. Experimental results show that our method is very robust to different initial segmentation results and the shape of a segment. The comparison between our algorithm and the current state-of-the-art algorithms on the Middlebury website shows that our algorithm is very competitive.
Place, publisher, year, edition, pages
ACM Digital Library, 2012. 340-345 p.
Watershed optimization, Region combination, Stereo, Disparity calculation
Medical Image Processing
IdentifiersURN: urn:nbn:se:liu:diva-125062DOI: 10.1145/2425836.2425903ISBN: 9781450314732OAI: oai:DiVA.org:liu-125062DiVA: diva2:902693
27th Image and Vision Computing New Zealand, IVCNZ'12, Dunedin, New Zealand, November 26-28th 2012