Discriminative Learning of Markov Random Fields for Segmentation of 3D Range Data

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 maximummargin 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. Authors: Drago Anguelov, Ben Taskar, Vasco Chatalbashev, Daphne Koller, Dinkar Gupta, Geremy Heitz, Andrew Y. Ng (2005)
AUTHORED BY
Drago Anguelov
Ben Taskar
Vasco Chatalbashev
Daphne Koller
Dinkar Gupta
Geremy Heitz
Andrew Y. Ng

Abstract

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 maximummargin 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.

Download PDF

Related Projects

Leave a Reply

You must be logged in to post a comment