Siam R-CNN: Visual Tracking by Re-Detection

Autor:	Voigtlaender, Paul, Luiten, Jonathon, Torr, Philip H. S., Leibe, Bastian
Rok vydání:	2019
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	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. Comment: CVPR 2020 camera-ready version
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1911.12836 Zobrazit plný text záznamu View this record from Arxiv