Abstract
Tracking-by-detection has proven to be the most successful strategy to address the task of tracking multiple targets in unconstrained scenarios [e.g. 40, 53, 55]. Traditionally, a set of sparse detections, generated in a preprocessing step, serves as input to a high-level tracker whose goal is to correctly associate these “dots” over time. An obvious shortcoming of this approach is that most information available in image sequences is simply ignored by thresholding weak detection responses and applying non-maximum suppression. We propose a multi-target tracker that exploits low level image information and associates every (super)-pixel to a specifific target or classififies it as background. As a result, we obtain a video segmentation in addition to the classical bounding-box representation in unconstrained, realworld videos. Our method shows encouraging results on many standard benchmark sequences and signifificantly outperforms state-of-the-art tracking-by-detection approaches in crowded scenes with long-term partial occlusions