Tsinghua Face Detection and Tracking for CLEAR 2007 Evaluation

This paper presents the algorithm and evaluation results of a face detection and tracking system. A tree-structured multi-view face detector trained by Vector Boosting is used as the basic detection module. Once a new face are detected, a track is initialized and maintained by detection confidence and Lucas-Kanade features, which are fused by particle filter. Additionally, a post process is adopted to eliminate low confidence tracks and connect track fragments which are likely to belong to the same target. Evaluation results are given on video data of CLEAR 2007 test set. 1 Task Overview The objective of face detection and tracking task of CLEAR 2007 Evaluation is to output the bounding box (including in-plane rotation angle) of each face in the scene, and in addition, for tracking the identity of each face should be maintained, too. Test data are videos captured in six meeting rooms (CMU, EDI, IDI, NIST, TNO, VT), in different time and by cameras at different positions (Fig. 1). ...

• Type: Conference
• Year: 2007
• Where: CLEAR
• Authors: Yuan Li, Chang Huang, Haizhou Ai
• Keywords: Basic Detection Module, Biometrics, CLEAR 2007, Face Detection, Tree-structured Multi-view Face