Attentive deep regression networks for real-time visual face tracking in video surveillance

Alver, Safa
Visual face tracking is one of the most important tasks in video surveillance systems. However, due to the variations in pose, scale, expression and illumination and the occlusions in cluttered scenes, it is considered to be a difficult task. To address these challenges, in this thesis, we propose an end-to-end tracker named Attentive Face Tracking Network (AFTN) that is build on top of the GOTURN tracker. Additionally, to overcome the scarce data problem in visual face tracking, we also provide bounding box annotations for the publicly available ChokePoint dataset and thus make it available for further studies in face tracking under surveillance conditions. Our test results show that our proposed tracker outperforms all the other trackers that are primitive versions of itself. Furthermore, it runs at speeds that are far beyond the requirements of real-time tracking.