Keyfilter-Aware Real-Time UAV Object Tracking

TL;DR

This paper introduces Keyfilter, a novel keyframe-based method for real-time UAV object tracking that effectively mitigates boundary effects and filter corruption, achieving superior accuracy and speed on challenging benchmarks.

Contribution

The paper proposes a new keyfilter approach that intermittently learns context via keyframes to improve tracking robustness and efficiency in UAV applications.

Findings

Outperforms state-of-the-art methods on challenging benchmarks.

Maintains real-time speed suitable for UAV deployment.

Effectively reduces boundary effect and filter corruption.

Abstract

Correlation filter-based tracking has been widely applied in unmanned aerial vehicle (UAV) with high efficiency. However, it has two imperfections, i.e., boundary effect and filter corruption. Several methods enlarging the search area can mitigate boundary effect, yet introducing undesired background distraction. Existing frame-by-frame context learning strategies for repressing background distraction nevertheless lower the tracking speed. Inspired by keyframe-based simultaneous localization and mapping, keyfilter is proposed in visual tracking for the first time, in order to handle the above issues efficiently and effectively. Keyfilters generated by periodically selected keyframes learn the context intermittently and are used to restrain the learning of filters, so that 1) context awareness can be transmitted to all the filters via keyfilter restriction, and 2) filter corruption can be repressed. Compared to the state-of-the-art results, our tracker performs better on two challenging benchmarks, with enough speed for UAV real-time applications.