Skip to main navigation Skip to search Skip to main content

A learning algorithm for model based object detection

  • Guodong Chen*
  • , Zeyang Xia
  • , Rongchuan Sun
  • , Zhenhua Wang
  • , Zhiwu Ren
  • , Lining Sun
  • *Corresponding author for this work
  • Soochow University
  • Indiana University-Purdue University Indianapolis

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Detecting objects in images and videos is a difficult task that has challenged the field of computer vision. Most of the algorithms for object detection are sensitive to background clutter and occlusion, and cannot localize the edge of the object. An objects shape is typically the most discriminative cue for its recognition by humans. This paper introduces a model based object detection method which uses only shape-fragment features. The object shape model is learned from a very small set of training images. And the object model is composed of shape fragments. The model of the object is in multi-scales. The results presented in this paper are competitive with other state-of-the-art object detection methods. The major contributions of this paper are the application of learned shape fragments based model for object detection in complex environment and a novel two-stage object detection framework.

Original languageEnglish
Title of host publicationURAI 2011 - 2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence
Pages101-106
Number of pages6
DOIs
StatePublished - 2011
Externally publishedYes
Event2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2011 - Incheon, Korea, Republic of
Duration: 23 Nov 201126 Nov 2011

Publication series

NameURAI 2011 - 2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence

Conference

Conference2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2011
Country/TerritoryKorea, Republic of
CityIncheon
Period23/11/1126/11/11

Keywords

  • Object detection
  • image segmentation
  • shape fragment
  • shape matching

Fingerprint

Dive into the research topics of 'A learning algorithm for model based object detection'. Together they form a unique fingerprint.

Cite this