论文标题
用于高速航空跟踪的暹罗锚提案网络
Siamese Anchor Proposal Network for High-Speed Aerial Tracking
论文作者
论文摘要
在视觉跟踪的范围内，大多数基于学习的跟踪器都强调了准确性，但抛弃了效率。因此，他们在诸如无人驾驶汽车（UAV）之类的移动平台上的现实部署受到阻碍。在这项工作中，提出了一种新型的两阶段基于暹罗网络的方法，用于航空跟踪，\ textit {i.e。}，阶段1，用于高质量的锚定建议生成，第2阶段，用于完善锚点建议。不同于具有许多预定固定尺寸锚固锚的基于锚的方法，我们的NO-PRIOR方法可以1）在复杂的情况下，在适应性锚定的复杂情况下，增加了各种尺寸的不同物体的鲁棒性和概括性，尤其是对小型，遮挡和快速移动的对象，2）由于锚定数量的实质性减少而使计算可行。此外，与无锚方法相比，由于在阶段2处的完善，我们的框架具有更好的性能。三个基准测试的全面实验证明了我们方法的出色表现，速度约为200帧/s。
In the domain of visual tracking, most deep learning-based trackers highlight the accuracy but casting aside efficiency. Therefore, their real-world deployment on mobile platforms like the unmanned aerial vehicle (UAV) is impeded. In this work, a novel two-stage Siamese network-based method is proposed for aerial tracking, \textit{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) increase the robustness and generalization 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 anchor-free methods, our framework has better performance owing to refinement at stage-2. Comprehensive experiments on three benchmarks have proven the superior performance of our approach, with a speed of around 200 frames/s.
