Motion Prediction in Visual Object Tracking

TL;DR

This paper emphasizes the importance of motion prediction in visual object tracking, demonstrating that combining standard methods like camera motion decouple and Kalman filter yields state-of-the-art results efficiently.

Contribution

It introduces a simple yet effective motion prediction approach that improves VOT performance without relying on computationally expensive feature extractors.

Findings

Achieved new state-of-the-art results on VOT-2016 and VOT-2018 datasets.

Improved EAO scores significantly over prior methods.

Demonstrated generalizability on video object segmentation tasks.

Abstract

Visual object tracking (VOT) is an essential component for many applications, such as autonomous driving or assistive robotics. However, recent works tend to develop accurate systems based on more computationally expensive feature extractors for better instance matching. In contrast, this work addresses the importance of motion prediction in VOT. We use an off-the-shelf object detector to obtain instance bounding boxes. Then, a combination of camera motion decouple and Kalman filter is used for state estimation. Although our baseline system is a straightforward combination of standard methods, we obtain state-of-the-art results. Our method establishes new state-of-the-art performance on VOT (VOT-2016 and VOT-2018). Our proposed method improves the EAO on VOT-2016 from 0.472 of prior art to 0.505, from 0.410 to 0.431 on VOT-2018. To show the generalizability, we also test our method on video object segmentation (VOS: DAVIS-2016 and DAVIS-2017) and observe consistent improvement.