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

Although the manipulating of the unmanned aerial manipulator (UAM) has been widely studied, visionbased 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 Siamesebased 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 visionbased UAM approaching. Specifically, SiamSA consists of a pairwise scale-channel attention network (PSAN) and a scaleaware anchor proposal network (SA-APN). PSAN acquires valuable scale information for feature processing, while SAAPN 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.

Automated summary

This paper proposes a novel Siamese network for vision-based UAM approaching, addressing the issue of object tracking in the presence of scale variation. It introduces pairwise scale-channel attention and scale-aware anchor proposal to effectively deal with the challenges. A new UAM tracking benchmark, UAMT100, is also provided for evaluation.