论文标题
夜间航空跟踪的无监督域改编
Unsupervised Domain Adaptation for Nighttime Aerial Tracking
论文作者
论文摘要
先前在对象跟踪的进展主要报告在有利的照明情况下，同时忽略了夜间性能，这极大地阻碍了相关的空中机器人应用的发展。相反，这项工作为夜间航空跟踪（名为UDAT）开发了一个新颖的无监督域名适应框架。具体而言，提供了一种独特的对象发现方法，可以从原始的夜间跟踪视频中生成培训补丁。为了应对域差异，我们将基于变压器的桥接图层柱用于特征提取器，以使两个域的图像特征对齐。借助Transformer Day/Night功能歧视器，白天跟踪模型进行了对抗训练，可以在夜间进行跟踪。此外，我们为无监督的域名夜间跟踪构建了一个开创性的基准NAT2021，其中包括一组180个手动注释跟踪序列的测试集和一组超过276K未标记的夜间夜间跟踪框架。详尽的实验证明了夜间航空跟踪中提出的框架的鲁棒性和域的适应性。该代码和基准可以在https://github.com/vision4robotics/udat上获得。
Previous advances in object tracking mostly reported on favorable illumination circumstances while neglecting performance at nighttime, which significantly impeded the development of related aerial robot applications. This work instead develops a novel unsupervised domain adaptation framework for nighttime aerial tracking (named UDAT). Specifically, a unique object discovery approach is provided to generate training patches from raw nighttime tracking videos. To tackle the domain discrepancy, we employ a Transformer-based bridging layer post to the feature extractor to align image features from both domains. With a Transformer day/night feature discriminator, the daytime tracking model is adversarially trained to track at night. Moreover, we construct a pioneering benchmark namely NAT2021 for unsupervised domain adaptive nighttime tracking, which comprises a test set of 180 manually annotated tracking sequences and a train set of over 276k unlabelled nighttime tracking frames. Exhaustive experiments demonstrate the robustness and domain adaptability of the proposed framework in nighttime aerial tracking. The code and benchmark are available at https://github.com/vision4robotics/UDAT.
