Multiple object tracking with partial occlusion handling using salient feature points

• We propose a multiple object tracking method in the presence of partial occlusion.
• An object is represented by a bounding rectangle that encloses salient feature points.
• We track objects by the feature points instead of an object itself for effectiveness.
• The incorrectly tracked feature points due to occlusion are corrected by outlier analysis.
• The proposed method demonstrates high effectiveness in tracking multiple occluded objects.

Handling occlusion has been a challenging task in object tracking. In this paper, we propose a multiple object tracking method in the presence of partial occlusion using salient feature points. We first extract the prominent feature points from each target object, and then use a particle filter-based approach to track the feature points in image sequences based on various attributes such as location, velocity and other descriptors. We then detect and revise the feature points that have been tracked incorrectly. The main idea is that, even if some feature points are not successfully tracked due to occlusion or poor imaging condition, the other correctly tracked features can collectively perform the corrections on their behalf. Finally, we track the objects using the correctly tracked feature points through a Hough-like approach, and the object bounding boxes are updated using the relative locations of these feature points. Experimental results demonstrate that our method is proficient in providing accurate human tracking as well as appropriate occlusion handling, compared to the existing methods.