Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLI-B3, 91-97, 2016
http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLI-B3/91/2016/
doi:10.5194/isprs-archives-XLI-B3-91-2016
 
09 Jun 2016
FAST RADIOMETRY GUIDED FUSION OF DISPARITY IMAGES
Stephan Schmid1 and Dieter Fritsch2 1Daimler AG
2Institute for Photogrammetry, University of Stuttgart
Keywords: Disparity fusion, multi-view stereo, real-time stereo, machine vision, photo-consistency Abstract. Previous work on disparity map fusion has mostly focused on geometric or statistical properties of disparity maps. Since failure of stereo algorithms is often consistent in many frames of a scene, it cannot be detected by such methods. Instead, we propose to use radiometric information from the original camera images together with externally supplied camera pose information to detect mismatches. As radiometric information is local information, the computations in the proposed algorithm for disparity fusion can be decoupled and parallelized to a very large degree, which allows us to easily achieve real-time performance.
Conference paper (PDF, 6057 KB)


Citation: Schmid, S. and Fritsch, D.: FAST RADIOMETRY GUIDED FUSION OF DISPARITY IMAGES, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLI-B3, 91-97, doi:10.5194/isprs-archives-XLI-B3-91-2016, 2016.

BibTeX EndNote Reference Manager XML