Object discovery on RGB-D data via salient object proposals

  • Wanyi Li
  • , Peng Wang
  • , Hong Qiao
  • , Naiji Fan
  • , Hai Zhou
  • , Feng Jing

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

Abstract

This paper presents an effective approach for object discovery in which both object proposals and saliency information are exploited. Our algorithm consists of three basic steps. Firstly, a set of object proposals are generated. Secondly, a saliency map is calculated and salient blobs are detected on the calculated saliency map. Finally, a saliency integrated objectness measure is proposed to rank object proposals thus objects are discovered. Experiments on a dataset of object discovery demonstrate the effectiveness of the proposed method.

Original languageEnglish
Title of host publicationProceedings - 2015 Chinese Automation Congress, CAC 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages737-739
Number of pages3
ISBN (Electronic)9781467371896
DOIs
StatePublished - 13 Jan 2016
Externally publishedYes
EventChinese Automation Congress, CAC 2015 - Wuhan, China
Duration: 27 Nov 201529 Nov 2015

Publication series

NameProceedings - 2015 Chinese Automation Congress, CAC 2015

Conference

ConferenceChinese Automation Congress, CAC 2015
Country/TerritoryChina
CityWuhan
Period27/11/1529/11/15

Keywords

  • Object discovery
  • RGBD data
  • object proposals
  • saliency

Fingerprint

Dive into the research topics of 'Object discovery on RGB-D data via salient object proposals'. Together they form a unique fingerprint.

Cite this