复杂背景下的低空无人机检测与跟踪算法  

Low-altitude UAV detection and tracking algorithms incomplex backgrounds

作　　者：汪建伟 游疆 万敏[1] 顾静良[1] Wang Jianwei;You Jiang;Wan Min;Gu Jingliang(Institute of Applied Electronics,CAEP,Mianyang 621900,China;Graduate School of China Academy of Engineering Physics,Beijing 100088,China)

机构地区：[1]中国工程物理研究院应用电子学研究所,四川绵阳621900 [2]中国工程物理研究院研究生院,北京100088

出　　处：《强激光与粒子束》2023年第7期154-165,共12页High Power Laser and Particle Beams

摘　　要：提出一种基于YOLOv5与CSRT算法优化的实时长跟踪方法,实现了对无人机在净空、城市、森林等场景的稳定跟踪。针对跟踪的不同阶段建立不同分辨率的两个捕获网络,分别对两个网络进行小目标检测优化和性能优化,并根据无人机数据集特点对其进行正负样本的添加以实现数据增强。然后,对CSRT算法使用GPU进行优化并结合特征点提取构建了低空无人机检测与跟踪模型。最后,将算法使用Tensorrt部署后在自建数据集上进行实验,实验结果表明,所提方法在RTX 2080Ti上实现了400FPS的跟踪性能,在NVIDIA Jetson NX上实现了70FPS的性能。在实际外场实验中也实现了稳定的长时间跟踪。With the frequent appearance of UAVs in several recent local wars and armed conflicts,the study ofUAV detection and tracking technology has become a research hotspot in imagery and other fields.Due to thecharacteristics of low altitude UAV targets such as large mobility,small size,low contrast and complex background,their capture and tracking is a major challenge in the field of photoelectric detection.To address these difficulties,thispaper proposes a real-time long tracking method based on YOLOv5 and CSRT algorithm optimization to achievestable tracking of UAVs in clear sky,urban and forest scenes.First,two capture networks with different resolutions areestablished for different stages of tracking,and the two networks are optimized for small target detection andperformance optimization respectively,and positive and negative samples are added to the UAV data set according toits characteristics to achieve data enhancement.Then,the CSRT algorithm is optimized using GPU and combined withfeature point extraction to construct a low-altitude UAV detection and tracking model.Finally,the algorithm isdeployed using Tensorrt and experimented on a self-built dataset.The experimental results show that the proposedmethod achieves a tracking performance of 400FPS on RTX 2080Ti and 70FPS on NVIDIA Jetson NX.Stable long-time tracking is also achieved in real field experiments.

关 键 词：无人机检测 实时跟踪 复杂背景 机动目标 无人机反制 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]