Conference Paper: Human face tracking system with multiple non-overlapping cameras
| Title | Human face tracking system with multiple non-overlapping cameras |
|---|---|
| Authors | He, XC1 Yuk, SC1 Luo, T1 Chow, KP1 Wong, KYK1 Chung, RHY1 |
| Issue Date | 2011 |
| Citation | Proceedings - 3Rd International Conference On Data Mining And Intelligent Information Technology Applications, Icmia 2011, 2011, p. 176-179 [How to Cite?] |
| Abstract | A novel human face tracking system with multiple cameras is proposed in this article. Unlike most surveillance approaches requiring overlapping field of views (FOVs) for tracking targets across multiple cameras, our proposed system utilizes face recognition as cue to build correspondence between cameras, and is therefore compatible with application with non-overlapping FOVs. Face recognition achieves great success in recent years, however it has an intrinsic limitation of low tolerance to face pose changes. In the proposed system, face reconstruction technology is adopted to transform non-frontal human face to a frontal one to substantially enhance the usability of face recognition, so that correspondence of humans across multiple trajectories can be reliably established. © 2011 AICIT. |
| ISBN | 978-898867848-0 |
| References | References in Scopus |
| dc.contributor.author | He, XC |
|---|---|
| dc.contributor.author | Yuk, SC |
| dc.contributor.author | Luo, T |
| dc.contributor.author | Chow, KP |
| dc.contributor.author | Wong, KYK |
| dc.contributor.author | Chung, RHY |
| dc.date.accessioned | 2012-06-26T06:32:39Z |
| dc.date.available | 2012-06-26T06:32:39Z |
| dc.date.issued | 2011 |
| dc.description.abstract | A novel human face tracking system with multiple cameras is proposed in this article. Unlike most surveillance approaches requiring overlapping field of views (FOVs) for tracking targets across multiple cameras, our proposed system utilizes face recognition as cue to build correspondence between cameras, and is therefore compatible with application with non-overlapping FOVs. Face recognition achieves great success in recent years, however it has an intrinsic limitation of low tolerance to face pose changes. In the proposed system, face reconstruction technology is adopted to transform non-frontal human face to a frontal one to substantially enhance the usability of face recognition, so that correspondence of humans across multiple trajectories can be reliably established. © 2011 AICIT. |
| dc.description.nature | Link_to_subscribed_fulltext |
| dc.identifier.citation | Proceedings - 3Rd International Conference On Data Mining And Intelligent Information Technology Applications, Icmia 2011, 2011, p. 176-179 [How to Cite?] |
| dc.identifier.epage | 179 |
| dc.identifier.isbn | 978-898867848-0 |
| dc.identifier.scopus | eid_2-s2.0-84863395052 |
| dc.identifier.spage | 176 |
| dc.identifier.uri | http://hdl.handle.net/10722/152030 |
| dc.language | eng |
| dc.relation.ispartof | Proceedings - 3rd International Conference on Data Mining and Intelligent Information Technology Applications, ICMIA 2011 |
| dc.relation.references | References in Scopus |
| dc.title | Human face tracking system with multiple non-overlapping cameras |
| dc.type | Conference_Paper |
Author Affiliations
- The University of Hong Kong