Evaluation of Object Trackers in Distorted Surveillance Videos

Abstract

Object tracking in realistic scenarios is a difficult problem affected by various image factors such as occlusion, clutter, confusion, object shape, unstable speed, and zooming. While these conditions do affect tracking performance, there is no clear distinction between the scene dependent challenges like occlusion, clutter, etc., and the challenges imposed by traditional notions of impairments from capture, compression, processing, and transmission. This paper is concerned with the latter interpretation of quality as it affects video tracking performance. In this work we aim to evaluate two state-of-the-art trackers (STRUCK and TLD) systematically and experimentally in surveillance videos affected by in-capture distortions such as under-exposure and defocus. We evaluate these trackers with the area under curve (AUC) values of success plots and precision curves. In spite of the fact that STRUCK and TLD have ranked high in video tracking surveys. This study concludes that incapture distortions severely affect the performance of these trackers. For this reason, the design and construction of a robust tracker with respect to these distortions remains an open question that can be answered by creating algorithms that makes use of perceptual features to compensate the degradations provided by these distortions.