Object Detection via Boundary Structure Segmentation

Loading...
Thumbnail Image
Penn collection
Departmental Papers (CIS)
Degree type
Discipline
Subject
Computer Sciences
Funder
Grant number
License
Copyright date
Distributor
Related resources
Author
Contributor
Abstract

We address the problem of object detection and segmentation using holistic properties of object shape. Global shape representations are highly susceptible to clutter inevitably present in realistic images, and can be robustly recognized only using a precise segmentation of the object.To this end, we propose a figure/ground segmentation method for extraction of image regions that resemble the global properties of a model boundary structure and are perceptually salient. Our shape representation, called the chordiogram, is based on geometric relationships of object boundary edges, while the perceptual saliency cues we use favor coherent regions distinct from the background. We formulate the segmentation problem as an integer quadratic program and use a semidefinite programming relaxation to solve it. Obtained solutions provide the segmentation of an object as well as a detection score used for object recognition. Our single-step approach improves over state of the art methods on several object detection and segmentation benchmarks.

Advisor
Date of presentation
2010-06-01
Conference name
Departmental Papers (CIS)
Conference dates
2023-05-17T07:09:42.000
Conference location
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
Object Detection via Boundary Structure Segmentation (http://www.cis.upenn.edu/%7Etaskar/pubs/segment_cvpr10.pdf), A. Toshev (http://www.seas.upenn.edu/%7Etoshev/), B. Taskar, and K. Daniilidis (http://www.seas.upenn.edu/%7Ekostas), IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (http://cvl.umiacs.umd.edu/conferences/cvpr2010/), San Francisco, CA, June 2010. ©2011 IEEE. Personal use of this material is permitted.Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Recommended citation
Collection