Title:
Occlusion-Aware Object Localization, Segmentation and Pose Estimation

Simple item page
dc.contributor.author Brahmbhatt, Samarth
dc.contributor.author Ben Amor, Heni
dc.contributor.author Christensen, Henrik I.
dc.contributor.corporatename Georgia Institute of Technology. College of Computing en_US
dc.contributor.corporatename Georgia Institute of Technology. Institute for Robotics and Intelligent Machines en_US
dc.date.accessioned 2016-04-29T14:59:09Z
dc.date.available 2016-04-29T14:59:09Z
dc.date.issued 2015-09
dc.description DOI: 10.5244/C.29.80
dc.description.abstract We present a learning approach for localization and segmentation of objects in an image in a manner that is robust to partial occlusion. Our algorithm produces a bounding box around the full extent of the object and labels pixels in the interior that belong to the object. Like existing segmentation aware detection approaches, we learn an appearance model of the object and consider regions that do not fit this model as potential occlusions. However, in addition to the established use of pairwise potentials for encouraging local consistency, we use higher order potentials which capture information at the level of image segments. We also propose an efficient loss function that targets both localization and segmentation performance. Our algorithm achieves 13.52% segmentation error and 0.81 area under the false-positive per image vs. recall curve on average over the challenging CMU Kitchen Occlusion Dataset. This is 42.44% less segmentation error and a 16.13% increase in localization performance compared to the state-of-the-art. Finally, we show that the visibility labeling produced by our algorithm can make full 3D pose estimation from a single image robust to occlusion. en_US
dc.description.uri https://dx.doi.org/10.5244/C.29.80
dc.embargo.terms null en_US
dc.identifier.citation Brahmbhatt, S.; Ben Amor, H., Christensen, H.; (2015), Occlusion Aware Object Localization, Segmentation and Pose Estimation, Proceedings of the 2015 British Machine Vision Conference (BMVC). en_US
dc.identifier.uri http://hdl.handle.net/1853/54761
dc.language.iso en_US en_US
dc.publisher Georgia Institute of Technology en_US
dc.subject Object detection en_US
dc.subject Pose estimation en_US
dc.title Occlusion-Aware Object Localization, Segmentation and Pose Estimation en_US
dc.type Text
dc.type.genre Proceedings
dspace.entity.type Publication
local.contributor.author Christensen, Henrik I.
relation.isAuthorOfPublication afdc727f-2705-4744-945f-e7d414f2212b
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
paper080(1).pdf
Size:
6.6 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
3.13 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Research Publications