Video Object Tracking -VOT- in realistic scenarios is a difficult task. Image factors such as occlusion, clutter, confusion, object shape, and zooming, among others, have an impact on video tracker methods performance. While these conditions do affect trackers performance, there is not a clear distinction between the scene content challenges like occlusion and clutter, against challenges due to distortions generated by capture, compression, processing, and transmission of videos. This paper is concerned with the latter interpretation of quality as it affects VOT performance. The contribution of this paper is two-fold. We have constructed a database of 537 surveillance videos containing different levels of authentic distortions such as low exposure and out-of-focus. It is available at https://tinyurl.com/DSVD-Test. Based on this database, we assessed seven state-of-the-art trackers with the A-R plot performance measure. We demonstrate that in-capture distortions severely hamper VOT methods performance in a non intuitive way.

https://ieeexplore.ieee.org/document/8683625