Paper Info
Title
Online learning of robust object detectors during unstable tracking
Abstract
This work investigates the problem of robust, longterm visual tracking of unknown objects in unconstrained environments. It therefore must cope with frame-cuts, fast camera movements and partial/total object occlusions/dissapearances. We propose a new approach, called Tracking-Modeling-Detection (TMD) that closely integrates adaptive tracking with online learning of the object-specific detector. Starting from a single click in the first frame, TMD tracks the selected object by an adaptive tracker. The trajectory is observed by two processes (growing and pruning event) that robustly model the appearance and build an object detector on the fly. Both events make errors, the stability of the system is achieved by their cancellation. The learnt detector enables re-initialization of the tracker whenever previously observed appearance reoccurs. We show the real-time learning and classification is achievable with random forests. The performance and the long-term stability of TMD is demonstrated and evaluated on a set of challenging video sequences with various objects such as cars, people and animals.
Year
DOI
Venue
2009
10.1109/ICCVW.2009.5457446
Computer Vision Workshops
Keywords
Field
DocType
image sensors,image sequences,learning (artificial intelligence),object detection,tracking,video signal processing,camera movements,object occlusions,object-specific detector,online learning,tracking-modeling-detection,unstable tracking,video sequences,visual tracking
Online learning,Computer vision,Object detection,Image sensor,Pattern recognition,Computer science,Robustness (computer science),Eye tracking,Artificial intelligence,Random forest,Detector,Trajectory
Conference
Volume
Issue
ISBN
2009
1
978-1-4244-4441-0
Citations 
PageRank 
References 
78
4.61
15
Authors
3
Name
Order
Citations
PageRank
Zdenek Kalal1102336.85
Jiri Matas24313234.68
Krystian Mikolajczyk3784.61