Fast Visual Object Tracking with Rotated Bounding Boxes

TL;DR

This paper introduces SiamMask_E, an enhanced real-time visual object tracking algorithm that uses ellipse fitting for rotated bounding boxes, improving accuracy while maintaining high frame rates.

Contribution

SiamMask_E improves bounding box fitting in SiamMask by incorporating ellipse fitting for rotated boxes, achieving higher accuracy without sacrificing real-time performance.

Findings

Achieved 80 fps tracking speed on GPU.

Improved accuracy and EAO on VOT datasets.

Effective rotated bounding box estimation.

Abstract

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.