Since targets are small in long-range infrared (IR) videos, it is challenging to accurately detect targets in those videos. In this paper, we propose a high-performance approach to detecting small targets in long-range and low-quality infrared videos. Our approach consists of a video resolution enhancement module, a proven small target detector based on local intensity and gradient (LIG), a connected component (CC) analysis module, and a track association module known as Simple Online and Real-time Tracking (SORT) to connect detections from multiple frames. Extensive experiments using actual mid-wave infrared (MWIR) videos in range between 3500 and 5000 m from a benchmark dataset clearly demonstrated the efficacy of the proposed approach. In the 5000 m case, the F1 score has been improved from 0.936 without SORT to 0.977 with SORT.

由于远程红外 (IR) 视频中的目标很小，因此在这些视频中准确检测目标具有挑战性。在本文中，我们提出了一种高性能方法来检测远程和低质量红外视频中的小目标。我们的方法包括视频分辨率增强模块、基于局部强度和梯度 (LIG) 的经过验证的小目标检测器、连接组件 (CC) 分析模块和称为简单在线和实时跟踪 (SORT) 的轨迹关联模块) 连接来自多个帧的检测。使用来自基准数据集的 3500 到 5000 m 范围内的实际中波红外 (MWIR) 视频进行的大量实验清楚地证明了所提出方法的有效性。在 5000 m 的情况下，F1 分数从没有 SORT 的 0.936 提高到有 SORT 的 0.977。