Siam R-CNN: Visual Tracking by Re-Detection

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, pp. 6577–6587

Abstract

We present Siam R-CNN, a Siamese re-detection architecture which unleashes the full power of two-stage object detection approaches for visual object tracking. We combine this with a novel tracklet-based dynamic programming algorithm, which takes advantage of re-detections of both the first-frame template and previous-frame predictions, to model the full history of both the object to be tracked and potential distractor objects. This enables our approach to make better tracking decisions, as well as to re-detect tracked objects after long occlusion. Finally, we propose a novel hard example mining strategy to improve Siam R-CNN's robustness to similar looking objects. Siam R-CNN achieves the current best performance on ten tracking benchmarks, with especially strong results for long-term tracking. We make our code and models available at www.vision.rwth-aachen.de/page/siamrcnn.

Authors 4

1. Paul Voigtlaender Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University

2. Jonathon Luiten Aachen

   University of Oxford · RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University

   University of Oxford

3. Philip H. S. Torr Aachen

   University of Oxford · RWTH Aachen University

   Affiliation as printed

   University of Oxford

   RWTH Aachen University

4. Bastian Leibe Aachen

   University of Oxford · RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University

   University of Oxford