DocumentCode :
72882
Title :
A Protocol for Evaluating Video Trackers Under Real-World Conditions
Author :
Nawaz, Tasin ; Cavallaro, Andrea
Author_Institution :
Centre for Intell. Sensing, Queen Mary Univ. of London, London, UK
Volume :
22
Issue :
4
fYear :
2013
fDate :
Apr-13
Firstpage :
1354
Lastpage :
1361
Abstract :
The absence of a commonly adopted performance evaluation framework is hampering advances in the design of effective video trackers. In this paper, we present a single-score evaluation measure and a protocol to objectively compare trackers. The proposed measure evaluates tracking accuracy and failure, and combines them for both summative and formative performance assessment. The proposed protocol is composed of a set of trials that evaluate the robustness of trackers on a range of test scenarios representing several real-world conditions. The protocol is validated on a set of sequences with a diversity of targets (head, vehicle and person) and challenges (occlusions, background clutter, pose changes and scale changes) using six state-of-the-art trackers, highlighting their strengths and weaknesses on more than 187000 frames. The software implementing the protocol and the evaluation results are made available online and new results can be included, thus facilitating the comparison of trackers.
Keywords :
image sequences; protocols; target tracking; video signal processing; formative performance assessment; performance evaluation framework; real-world conditions; single-score evaluation measurement; software implementation; summative performance assessment; target diversity; trackers robustness; tracking accuracy; video tracker evaluation; Accuracy; Lighting; Protocols; Robustness; Standards; Target tracking; Vehicles; Evaluation measure; performance evaluation; protocol; trials; video trackers; Algorithms; Analysis of Variance; Automobiles; Databases, Factual; Head; Humans; Image Processing, Computer-Assisted; Models, Theoretical; Reproducibility of Results; Software; Video Recording;
fLanguage :
English
Journal_Title :
Image Processing, IEEE Transactions on
Publisher :
ieee
ISSN :
1057-7149
Type :
jour
DOI :
10.1109/TIP.2012.2228497
Filename :
6357282
Link To Document :
بازگشت