Automatic Tracker Selection w.r.t Object Detection Performance
This work addresses video content variations in multi-object tracking, but it appears incremental as it builds on existing trackers with a selection mechanism.
The paper tackled the problem of multi-object tracking performance varying with video content by improving object detection with KLT feature tracking and selecting appropriate trackers based on online evaluation, resulting in better performance compared to recent state-of-the-art trackers on three public datasets.
The tracking algorithm performance depends on video content. This paper presents a new multi-object tracking approach which is able to cope with video content variations. First the object detection is improved using Kanade- Lucas-Tomasi (KLT) feature tracking. Second, for each mobile object, an appropriate tracker is selected among a KLT-based tracker and a discriminative appearance-based tracker. This selection is supported by an online tracking evaluation. The approach has been experimented on three public video datasets. The experimental results show a better performance of the proposed approach compared to recent state of the art trackers.