Siamese Object Tracking for Vision-Based UAM Approaching with Pairwise Scale-Channel Attention

TL;DR

This paper introduces SiamSA, a novel Siamese network with pairwise scale-channel attention, designed for vision-based UAM approaching, effectively handling scale variations and validated on a new benchmark and real-world tests.

Contribution

The work proposes a new Siamese network architecture with scale-aware modules specifically for UAM approaching, addressing scale variation challenges in vision-based tracking.

Findings

SiamSA outperforms existing methods on UAMT100 benchmark.

The approach achieves real-time processing speed.

Experimental results confirm robustness in real-world scenarios.

Abstract

Although the manipulating of the unmanned aerial manipulator (UAM) has been widely studied, vision-based UAM approaching, which is crucial to the subsequent manipulating, generally lacks effective design. The key to the visual UAM approaching lies in object tracking, while current UAM tracking typically relies on costly model-based methods. Besides, UAM approaching often confronts more severe object scale variation issues, which makes it inappropriate to directly employ state-of-the-art model-free Siamese-based methods from the object tracking field. To address the above problems, this work proposes a novel Siamese network with pairwise scale-channel attention (SiamSA) for vision-based UAM approaching. Specifically, SiamSA consists of a pairwise scale-channel attention network (PSAN) and a scale-aware anchor proposal network (SA-APN). PSAN acquires valuable scale information for feature processing, while SA-APN mainly attaches scale awareness to anchor proposing. Moreover, a new tracking benchmark for UAM approaching, namely UAMT100, is recorded with 35K frames on a flying UAM platform for evaluation. Exhaustive experiments on the benchmarks and real-world tests validate the efficiency and practicality of SiamSA with a promising speed. Both the code and UAMT100 benchmark are now available at https://github.com/vision4robotics/SiamSA.