Stereo vision head vergence using GPU cepstral filtering

Luis Almeida, Paulo Menezes, Jorge Dias

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

2 Scopus citations

Abstract

Vergence ability is an important visual behavior observed on living creatures when they use vision to interact with the environment. The notion of active observer is equally useful for robotic vision systems on tasks like object tracking, fixation and 3D environment structure recovery. Humanoid robotics are a potential playground for such behaviors. This paper describes the implementation of a real time binocular vergence behavior using cepstral filtering to estimate stereo disparities. By implementing the cepstral filter on a graphics processing unit (GPU) using Compute Unified Device Architecture (CUDA) we demonstrate that robust parallel algorithms that used to require dedicated hardware are now available on common computers. The cepstral filtering algorithm speed up is more than sixteen times than on a current CPU. The overall system is implemented in the binocular vision system IMPEP (IMPEP Integrated Multimodal Perception Experimental Platform) to illustrate the system performance experimentally.

Original languageBritish English
Title of host publicationVISAPP 2011 - Proceedings of the International Conference on Computer Vision Theory and Application
Pages665-670
Number of pages6
StatePublished - 2011
EventInternational Conference on Computer Vision Theory and Application, VISAPP 2011 - Vilamoura, Algarve, Portugal
Duration: 5 Mar 20117 Mar 2011

Publication series

NameVISAPP 2011 - Proceedings of the International Conference on Computer Vision Theory and Application

Conference

ConferenceInternational Conference on Computer Vision Theory and Application, VISAPP 2011
Country/TerritoryPortugal
CityVilamoura, Algarve
Period5/03/117/03/11

Keywords

  • Cepstrum
  • CUDA
  • GPU
  • Vergence

Fingerprint

Dive into the research topics of 'Stereo vision head vergence using GPU cepstral filtering'. Together they form a unique fingerprint.

Cite this