Siamese Anchor Proposal Network for High-Speed Aerial Tracking

Abstract

In the domain of visual tracking, most deep learning-based trackers highlight the accuracy but casting aside efficiency, thereby impeding their real-world deployment on mobile platforms like the unmanned aerial vehicle (UAV). In this work, a novel two-stage siamese network-based method is proposed for aerial tracking, i.e., stage-1 for high-quality anchor proposal generation, stage-2 for refining the anchor proposal. Different from anchor-based methods with numerous pre-defined fixed-sized anchors, our no-prior method can 1) make tracker robust and general to different objects with various sizes, especially to small, occluded, and fast-moving objects, under complex scenarios in light of the adaptive anchor generation, 2) make calculation feasible due to the substantial decrease of anchor numbers. In addition, compared to anchorfree methods, our framework has better performance owing to refinement at stage-2. Comprehensive experiments on three benchmarks have proven the state-of-the-art performance of our approach, with a speed of ∼200 frames/s.

MobileTrack: Siamese efficient mobile network for high‐speed UAV tracking

“…AutoTrack [1] is proposed to adaptively learn spatio-temporal regularisation terms with a speed of 60 FPS. SiamAPN [23] combines anchor-free policies and semantic information to track objects, which improves the tracking accuracy and speed but the regression of the bounding box becomes a problem. For the challenges such as the aerial target's small size, Liu et al [24] propose an adaptive tracker fusing multiscale features, which achieves a better tracking accuracy but speed is not ideal.…”