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 Kalal | 1 | 1023 | 36.85 |
Krystian Mikolajczyk | 2 | 7280 | 625.08 |
Jiri Matas | 3 | 335 | 35.85 |