Multi-view face detection based on position estimation over multi-camera surveillance system

Ching-Chun Huang*, Jay Chou, Jia Hau Shiu, Sheng-Jyh Wang

*Corresponding author for this work

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

Abstract

In this paper, we propose a multi-view face detection system that locates head positions and indicates the direction of each face in 3-D space over a multi-camera surveillance system. To locate 3-D head positions, conventional methods relied on face detection in 2-D images and projected the face regions back to 3-D space for correspondence. However, the inevitable false face detection and rejection usually degrades the system performance. Instead, our system searches for the heads and face directions over the 3-D space using a sliding cube. Each searched 3-D cube is projected onto the 2-D camera views to determine the existence and direction of human faces. Moreover, a pre-process to estimate the locations of candidate targets is illustrated to speed-up the searching process over the 3-D space. In summary, our proposed method can efficiently fuse multi-camera information and suppress the ambiguity caused by detection errors. Our evaluation shows that the proposed approach can efficiently indicate the head position and face direction on real video sequences even under serious occlusion.

Original languageEnglish
Title of host publicationProceedings of SPIE-IS and T Electronic Imaging - Multimedia on Mobile Devices 2012; and Multimedia Content Access
Subtitle of host publicationAlgorithms and Systems VI
PublisherSPIE
ISBN (Print)9780819489517
DOIs
StatePublished - 11 May 2012
EventMultimedia on Mobile Devices 2012; and Multimedia Content Access: Algorithms and Systems VI - Burlingame, CA, United States
Duration: 23 Jan 201225 Jan 2012

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume8304
ISSN (Print)0277-786X

Conference

ConferenceMultimedia on Mobile Devices 2012; and Multimedia Content Access: Algorithms and Systems VI
CountryUnited States
CityBurlingame, CA
Period23/01/1225/01/12

Keywords

  • Face detection
  • Image information fusion
  • Multi-camera surveillance system
  • Multi-view face detection

Fingerprint Dive into the research topics of 'Multi-view face detection based on position estimation over multi-camera surveillance system'. Together they form a unique fingerprint.

Cite this