Title:
Occlusion-Aware Object Localization, Segmentation and Pose Estimation
Occlusion-Aware Object Localization, Segmentation and Pose Estimation
Files
Authors
Brahmbhatt, Samarth
Ben Amor, Heni
Christensen, Henrik I.
Ben Amor, Heni
Christensen, Henrik I.
Authors
Person
Advisors
Advisors
Associated Organizations
Series
Collections
Supplementary to
Permanent Link
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.
Sponsor
Date Issued
2015-09
Extent
Resource Type
Text
Resource Subtype
Proceedings