Dynamic feature cascade for multiple object tracking with trackability analysis

Authors:
Zheng Li;Haifeng Gong;Song-Chun Zhu;Nong Sang
Affiliations:
Institute for Pattern Recognition and Artificial Intelligence, Huazhong University of Science and Technology, China and Lotus Hill Institute for Computer Vision and Information Science, China;Lotus Hill Institute for Computer Vision and Information Science, China and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China;Lotus Hill Institute for Computer Vision and Information Science, China and Departments of Statistics and Computer Science, University of California, Los Angeles;Institute for Pattern Recognition and Artificial Intelligence, Huazhong University of Science and Technology, China
Venue:
EMMCVPR'07 Proceedings of the 6th international conference on Energy minimization methods in computer vision and pattern recognition
Year:
2007

Citing 5
Cited 2

Learning Patterns of Activity Using Real-Time Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
Object Tracking with Bayesian Estimation of Dynamic Layer Representations

IEEE Transactions on Pattern Analysis and Machine Intelligence
Tracking Multiple Humans in Complex Situations

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Unified Framework for Tracking through Occlusions and across Sensor Gaps

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Multi-Object Tracking Through Simultaneous Long Occlusions and Split-Merge Conditions

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1

Semantic event representation and recognition using syntactic attribute graph grammar

Pattern Recognition Letters
Intrackability: Characterizing Video Statistics and Pursuing Video Representations

International Journal of Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

In multiple object tracking, the confusion caused by occlusion and similar appearances is an important issue to be solved. In this paper, trackability is proposed to measure how well given features can be used to find the correspondence of any given object in videos with multiple objects. Based on the analysis of trackability and computational complexity of the features under various occlusion conditions, a dynamic feature method cascade is presented to match the objects in consecutive frames. The cascade is composed of three tracking features: appearance, velocity and position. These features are enabled or disabled online to reduce computational complexity while obtaining similar trackability. Experiments are conducted on 27062 frame occlusion objects, in the cases of good trackability, our experiments can obtain high succussful tracking rate with low computation burden, and in the cases of poor trackability, our estimation of trackability and confusion matrix can explain why they can not be tracked well.