Fast Visual Object Tracking with Rotated Bounding Boxes
This work addresses the need for more accurate rotated bounding box estimation in real-time object tracking for applications like robotics and surveillance, representing an incremental improvement over existing methods.
The paper tackles the problem of visual object tracking with rotated bounding boxes by improving the SiamMask algorithm using ellipse fitting, achieving an Accuracy of 0.652 and EAO of 0.309 on VOT2019, which are 0.056 and 0.026 higher than the original method while maintaining 80 fps.
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: https://github.com/baoxinchen/siammask_e.