Paper Info
Title
Forward-Backward Error: Automatic Detection of Tracking Failures
Abstract
This paper proposes a novel method for tracking failure detection. The detection is based on the Forward-Backward error, i.e. the tracking is performed forward and backward in time and the discrepancies between these two trajectories are measured. We demonstrate that the proposed error enables reliable detection of tracking failures and selection of reliable trajectories in video sequences. We demonstrate that the approach is complementary to commonly used normalized cross-correlation (NCC). Based on the error, we propose a novel object tracker called Median Flow. State-of-the-art performance is achieved on challenging benchmark video sequences which include non-rigid objects.
Year
DOI
Venue
2010
10.1109/ICPR.2010.675
ICPR
Keywords
Field
DocType
forward-backward error,novel method,proposed error,tracking failures,reliable detection,median flow,reliable trajectory,automatic detection,benchmark video sequence,failure detection,novel object tracker,video sequence,reliability,normalized cross correlation,pixel,trajectory,measurement uncertainty
Cross-correlation,Computer vision,Normalization (statistics),Pattern recognition,Computer science,Measurement uncertainty,Tracking system,Pixel,Artificial intelligence,Trajectory
Conference
Citations 
PageRank 
References 
68
2.37
7
Authors
3
Name
Order
Citations
PageRank
Zdenek Kalal1102336.85
Krystian Mikolajczyk27280625.08
Jiri Matas333535.85