A multiple face detection and tracking system based on TLD

Authors:
Weihua Cao;Guangzhu Xu;Bangjun Lei;Panlong Yin;Fangmin Dong
Affiliations:
Three Gorges University, Yichang;Three Gorges University, Yichang;Three Gorges University, Yichang;Three Gorges University, Yichang;Three Gorges University, Yichang
Venue:
Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service
Year:
2013

Citing 9
Cited 0

Performance of optical flow techniques

International Journal of Computer Vision
Neural network design

Neural network design
Mean Shift, Mode Seeking, and Clustering

IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust Real-Time Face Detection

International Journal of Computer Vision
Forward-Backward Error: Automatic Detection of Tracking Failures

ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition
Robust Object Tracking with Online Multiple Instance Learning

IEEE Transactions on Pattern Analysis and Machine Intelligence
Tracking-Learning-Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Struck: Structured output tracking with kernels

ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Real-time compressive tracking

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III

Quantified Score

Hi-index	0.00

Visualization

Abstract

With the rapid development of computer vision, automatic face detection and tracking has becoming more and more attractive and is applied extensively to human-computer interaction, biometrics, and video surveillance. In this paper, Viola-Jones object detector was adopted to find candidate faces in frames, and TLD (Tracking-Learning-Detection) tracking strategy was combined with it to realize robust longtime face tracking. At the same time. TLD was extended to track multiple faces in real time. Experimental results in real life scenarios show that the proposed system can efficiently detect multi-faces and track them for long time robustly.