Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Robust Head Tracking with Particles Based on Multiple Cues Fusion
 

Summary: Robust Head Tracking with Particles Based on
Multiple Cues Fusion
Yuan Li1
, Haizhou Ai1
, Chang Huang1
, and Shihong Lao2
1
Department of Computer Science, Tsinghua University Beijing, China
2
Sensing and Control Technology Lab, OMRON Corporation, Kyoto, Japan
ahz@mail.tsinghua.edu.cn
Abstract. This paper presents a fully automatic and highly robust head
tracking algorithm based on the latest advances in real-time multi-view
face detection techniques and multiple cues fusion under particle fil-
ter framework. Visual cues designed for general object tracking prob-
lem hardly suffice for robust head tracking under diverse or even severe
circumstances, making it a necessity to utilize higher level information
which is object-specific. To this end we introduce a vector-boosted multi-
view face detector[2] as the "face cue" in addition to two other general
visual cues targeting the entire head, color spatiogram[3] and contour

  

Source: Ai, Haizhou - Department of Computer Science and Technology, Tsinghua University

 

Collections: Computer Technologies and Information Sciences