Detecting, segmenting and tracking unknown objects using multi-label MRF inference
2014 (English)In: Computer Vision and Image Understanding, ISSN 1077-3142, E-ISSN 1090-235X, Vol. 118, 111-127 p.Article in journal (Refereed) Published
This article presents a unified framework for detecting, segmenting and tracking unknown objects in everyday scenes, allowing for inspection of object hypotheses during interaction over time. A heterogeneous scene representation is proposed, with background regions modeled as a combinations of planar surfaces and uniform clutter, and foreground objects as 3D ellipsoids. Recent energy minimization methods based on loopy belief propagation, tree-reweighted message passing and graph cuts are studied for the purpose of multi-object segmentation and benchmarked in terms of segmentation quality, as well as computational speed and how easily methods can be adapted for parallel processing. One conclusion is that the choice of energy minimization method is less important than the way scenes are modeled. Proximities are more valuable for segmentation than similarity in colors, while the benefit of 3D information is limited. It is also shown through practical experiments that, with implementations on GPUs, multi-object segmentation and tracking using state-of-art MRF inference methods is feasible, despite the computational costs typically associated with such methods.
Place, publisher, year, edition, pages
Elsevier, 2014. Vol. 118, 111-127 p.
Figure-ground segmentation, Active perception, MRF, Multi-object tracking, Object detection, GPU acceleration
Computer Vision and Robotics (Autonomous Systems)
IdentifiersURN: urn:nbn:se:kth:diva-133215DOI: 10.1016/j.cviu.2013.10.007ISI: 000328591500011ScopusID: 2-s2.0-84890998700OAI: oai:DiVA.org:kth-133215DiVA: diva2:659983
QC 20140122. Updated from accepted to published.2013-10-282013-10-282014-02-27Bibliographically approved