Computational stereo-vision model of proto-object based saliency in three-dimensional space

Elena Mancinelli, Ernst Niebur, Ralph Etienne-Cummings

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Our visual system deals with a three-dimensional space but most of the current saliency models do not include depth information. We extend a proto-object based model to show how stereoscopic depth perception changes the ability to predict saliency on natural scenes. Results show the ability to mark depth discontinuities and a promising statistical improvement.

Original languageEnglish (US)
Title of host publication2018 IEEE Biomedical Circuits and Systems Conference, BioCAS 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538636039
DOIs
StatePublished - Dec 20 2018
Event2018 IEEE Biomedical Circuits and Systems Conference, BioCAS 2018 - Cleveland, United States
Duration: Oct 17 2018Oct 19 2018

Other

Other2018 IEEE Biomedical Circuits and Systems Conference, BioCAS 2018
CountryUnited States
CityCleveland
Period10/17/1810/19/18

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Health Informatics
  • Instrumentation
  • Signal Processing
  • Biomedical Engineering

Fingerprint Dive into the research topics of 'Computational stereo-vision model of proto-object based saliency in three-dimensional space'. Together they form a unique fingerprint.

Cite this