Fast Visual Object Tracking with Rotated Bounding Boxes

8 Jul 2019  ·  Bao Xin Chen, John K. Tsotsos ·

In this paper, we demonstrate a novel algorithm that uses ellipse fitting to estimate the bounding box rotation angle and size with the segmentation(mask) on the target for online and real-time visual object tracking. Our method, SiamMask_E, improves the bounding box fitting procedure of the state-of-the-art object tracking algorithm SiamMask and still retains a fast-tracking frame rate (80 fps) on a system equipped with GPU (GeForce GTX 1080 Ti or higher). We tested our approach on the visual object tracking datasets (VOT2016, VOT2018, and VOT2019) that were labeled with rotated bounding boxes. By comparing with the original SiamMask, we achieved an improved Accuracy of 0.652 and 0.309 EAO on VOT2019, which is 0.056 and 0.026 higher than the original SiamMask. The implementation is available on GitHub:

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Visual Object Tracking VOT2016 SiamMask_E Expected Average Overlap (EAO) 0.466 # 1
Visual Object Tracking VOT2017/18 SiamMask_E Expected Average Overlap (EAO) 0.446 # 1
Visual Object Tracking VOT2019 SiamMask_E Expected Average Overlap (EAO) 0.309 # 3


No methods listed for this paper. Add relevant methods here