Multiple object tracking with occlusions using HOG descriptors and multi resolution images

We present an algorithm for tracking multiple objects through occlusions. Firstly, for each detected object we compute feature points using the FAST algorithm [1]. Secondly, for each feature point we build a descriptor based on the histogram of oriented gradients (HOG) [2]. Thirdly, we track feature points using these descriptors. Object tracking is possible even if objects are occluded. If few objects are merged and detected as a single one, we assign each newly detected feature point in such single object to one of these occluded objects. We apply probabilistic methods for this task, using information from the previous frames like object size and motion (speed and orientation). We use multi resolution images to decrease the processing time. Our approach is tested on the synthetic video sequence, the KTH dataset [3] and the CAVIAR dataset [4]. All tests confirm the effectiveness of our approach.