Target modeling for tracking and handoff in a camera network

Authors:
Adisorn Pasukmoon;Supavadee Aramvith;Thanarat H. Chalidabhongse;Supakorn Siddhichai
Affiliations:
Chulalongkorn University, Bangkok, Thailand;Chulalongkorn University, Bangkok, Thailand;Chulalongkorn University, Bangkok, Thailand;National Electronics and Computer Technology Center (NECTEC), Pathumthani, Thailand
Venue:
Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication
Year:
2013

Citing 4
Cited 0

Kernel-Based Object Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
A new approach to camera hand-off without camera calibration for the general scene with non-planar ground

Proceedings of the 4th ACM international workshop on Video surveillance and sensor networks
Multi-camera Control through Constraint Satisfaction for Persistent Surveillance

AVSS '08 Proceedings of the 2008 IEEE Fifth International Conference on Advanced Video and Signal Based Surveillance
Consistent labeling of tracked objects in multiple cameras with overlapping fields of view

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Tracking moving objects such as human has become a major topic in video surveillance applications. Camera handoff is an important problem when using multiple cameras which have overlapping or non-overlapping field of views. However, most handoff techniques rely on a robust tracker and some information from first camera assigned to tracked objects. In view-dependent appearance problem, a person might be seen simultaneously from different cameras but some variations such as differences in body posture, viewing angle, color characteristics, scale and lighting conditions may cause handoff failed from wrong object matching, multiple target models is needed. This paper presents a target modeling based on a CAMShift for moving object tracking. The target model process includes short-term and long-term memory. Experimental results have shown that our proposed algorithm can improve a person tracking among multiple PTZ cameras and especially solve the view-dependent appearance problem.