Siam R-CNN: Visual Tracking by Re-Detection
This work addresses the problem of robust visual tracking for computer vision applications, representing an incremental improvement by integrating existing detection methods with novel algorithmic components.
The paper tackles visual object tracking by introducing Siam R-CNN, a Siamese re-detection architecture that combines two-stage object detection with a tracklet-based dynamic programming algorithm to model object history and handle occlusions, achieving state-of-the-art performance on ten benchmarks with strong results in long-term tracking.
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.