2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) (2005)
San Diego, California
June 20, 2005 to June 26, 2005
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CVPR.2005.133
Dragomir Anguelov , Stanford University
Ben Taskar , University of California at Berkeley
Vassil Chatalbashev , Stanford University
Daphne Koller , Stanford University
Dinkar Gupta , Stanford University
Geremy Heitz , Stanford University
Andrew Ng , Stanford University
We address the problem of segmenting 3D scan data into objects or object classes. Our segmentation framework is based on a subclass of Markov Random Fields (MRFs) which support efficient graph-cut inference. The MRF models incorporate a large set of diverse features and enforce the preference that adjacent scan points have the same classification label. We use a recently proposed maximum-margin framework to discriminatively train the model from a set of labeled scans; as a result we automatically learn the relative importance of the features for the segmentation task. Performing graph-cut inference in the trained MRF can then be used to segment new scenes very efficiently. We test our approach on three large-scale datasets produced by different kinds of 3D sensors, showing its applicability to both outdoor and indoor environments containing diverse objects.
G. Heitz et al., "Discriminative Learning of Markov Random Fields for Segmentation of 3D Scan Data," 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)(CVPR), San Diego, CA, USA USA, 2005, pp. 169-176.