Onboard Real-Time Aerial Tracking With Efficient Siamese Anchor Proposal Network

Object tracking approaches based on the Siamese network have demonstrated their huge potential in the remote sensing field recently. Nevertheless, due to the limited computing resource of aerial platforms and special challenges in aerial tracking, most existing Siamese-based methods can hardly meet the real-time and state-of-the-art performance simultaneously. Consequently, a novel Siamese-based method is proposed in this work for onboard real-time aerial tracking, i.e., SiamAPN. The proposed method is a no-prior two-stage method, i.e., Stage-1 for proposing adaptive anchors to enhance the ability of object perception and Stage-2 for fine-tuning the proposed anchors to obtain accurate results. Distinct from the traditional predefined anchors, the proposed anchors can adapt automatically to the tracking object. Besides, the internal information of adaptive anchors is utilized to feedback SiamAPN for enhancing the object perception. Attributing to the feature fusion network, different semantic information is integrated, enriching the information flow that is significant for robust aerial tracking. In the end, the regression and multiclassification operation refine the proposed anchors meticulously. Comprehensive evaluations on three well-known aerial tracking benchmarks have proven the superior performance of the presented approach. Moreover, to verify the practicability of the proposed method, SiamAPN is implemented onboard a typical embedded aerial tracking platform to conduct the real-world evaluations on specific aerial tracking scenarios, e.g., fast motion, long-term tracking, and low resolution. The results have demonstrated the efficiency and accuracy of the proposed approach, with a processing speed of over 30 frames/s. In addition, the image sequences in the real-world evaluations are collected and annotated as a new aerial tracking benchmark, i.e., UAVTrack112.

I. Introduction

Aerial object tracking is a fundamental task in the domain of remote sensing. Benefiting from the high mobility of aerial platforms, unmanned aerial vehicle (UAV)-based remote sensing has attracted worldwide attention recently. Given the object state in the first frame, the tracker aims to predict the object state in the following frames. Besides, aerial tracking has derived a wide range of applications, including, but not limited to, motion object analysis [2], [3], geographical survey [4], and surveillance [5]. Despite impressive achievements, designing an efficient and accurate tracker for aerial tracking remains a challenging task due to the special challenges aroused by flight processing, such as fast motion (FM), long-term tracking, and low resolution (LR). In addition, the requirement for real-time processing on the inherently limited computing resources of aerial platforms further constrains the applicability of trackers in onboard processors.