Siam R-CNN: Visual Tracking by Re-Detection

11/28/2019
by   Paul Voigtlaender, et al.
0

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. The proposed tracker achieves the current best performance on ten tracking benchmarks, with especially strong results for long-term tracking.

READ FULL TEXT

page 1

page 3

page 19

research
11/24/2022

Multi-Template Temporal Siamese Network for Long-Term Object Tracking

Siamese Networks are one of most popular visual object tracking methods ...
research
12/13/2021

Tracking and Long-Term Identification Using Non-Visual Markers

Our objective is to track and identify mice in a cluttered home-cage env...
research
04/12/2018

Trajectory Factory: Tracklet Cleaving and Re-connection by Deep Siamese Bi-GRU for Multiple Object Tracking

Multi-Object Tracking (MOT) is a challenging task in the complex scene s...
research
08/13/2021

Non-imaging real-time detection and tracking of fast-moving objects

Real-time detection and tracking of fast-moving objects have achieved gr...
research
08/11/2022

Towards Sequence-Level Training for Visual Tracking

Despite the extensive adoption of machine learning on the task of visual...
research
06/20/2021

Learning to Track Object Position through Occlusion

Occlusion is one of the most significant challenges encountered by objec...

Please sign up or login with your details

Forgot password? Click here to reset