Recent years have witnessed the fast evolution and promising performance of the convolutional neural network (CNN)-based trackers, which aim at imitating biological visual systems. However, current CNN-based trackers can hardly generalize well to low-light scenes that are commonly lacked in the existing training set. In indistinguishable night scenarios frequently encountered in unmanned aerial vehicle (UAV) tracking-based applications, the robustness of the state-of-the-art (SOTA) trackers drops significantly. To facilitate aerial tracking in the dark through a general fashion, this work proposes a low-light image enhancer namely DarkLighter, which dedicates to alleviate the impact of poor illumination and noise iteratively. A lightweight map estimation network, i.e., ME-Net, is trained to efficiently estimate illumination maps and noise maps jointly. Experiments are conducted with several SOTA trackers on numerous UAV dark tracking scenes. Exhaustive evaluations demonstrate the reliability and universality of DarkLighter, with high efficiency. Moreover, DarkLighter has further been implemented on a typical UAV system. Real-world tests at night scenes have verified its practicability and dependability.

中文翻译：

---

DarkLighter：照亮无人机跟踪的黑暗

近年来，我们见证了基于卷积神经网络 (CNN) 的跟踪器的快速发展和有希望的性能，其旨在模仿生物视觉系统。然而，当前基于 CNN 的跟踪器很难很好地泛化到现有训练集中通常缺乏的低光场景。在基于无人机 (UAV) 跟踪的应用中经常遇到的难以区分的夜间场景中，最先进 (SOTA) 跟踪器的鲁棒性显着下降。为了通过一般方式促进黑暗中的空中跟踪，这项工作提出了一种低光图像增强器，即 DarkLighter，它致力于迭代地减轻不良照明和噪声的影响。一个轻量级的地图估计网络，即 ME-Net，被训练以有效地联合估计光照图和噪声图。使用多个 SOTA 跟踪器在众多无人机黑暗跟踪场景中进行了实验。详尽的评估证明了 DarkLighter 的可靠性和通用性，以及高效性。此外，DarkLighter 已进一步在典型的无人机系统上实现。夜景实景测试验证了其实用性和可靠性。