Part-based Tracking by Sampling
This work addresses object tracking for video analysis, but it is incremental as it builds on existing part-based tracking approaches.
The paper tackles the problem of tracking arbitrary objects in challenging video sequences by proposing a part-based method that uses color distributions and patch placement, achieving higher performance than all other part-based trackers on VOT2018 and OTB100 benchmarks.
We propose a novel part-based method for tracking an arbitrary object in challenging video sequences. The colour distribution of tracked image patches on the target object are represented by pairs of RGB samples and counts of how many pixels in the patch are similar to them. Patches are placed by segmenting the object in the given bounding box and placing patches in homogeneous regions of the object. These are located in subsequent image frames by applying non-shearing affine transformations to the patches' previous locations, locally optimising the best of these, and evaluating their quality using a modified Bhattacharyya distance. In experiments carried out on VOT2018 and OTB100 benchmarks, the tracker achieves higher performance than all other part-based trackers. An ablation study is used to reveal the effectiveness of each tracking component, with largest performance gains found when using the patch placement scheme.