远距离监视激光雷达动目标快速检测  

Fast detection of moving targets in long range surveillance LiDAR

作　　者：冯杰 冯扬 刘翔 邓陈进 喻忠军 Feng Jie;Feng Yang;Liu Xiang;Deng Chenjin;Yu Zhongjun(Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100194,China;University of Chinese Academy of Sciences,Beijing 100049,China;School of Software Engineering,South China University of Technology,Guangzhou 510006,China;Key Laboratory of Quantum Optics,Shanghai Institute of Optics and Fine Mechanics,Chinese Academy of Sciences,Shanghai 201800,China)

机构地区：[1]中国科学院空天信息创新研究院,北京100194 [2]中国科学院大学,北京100049 [3]华南理工大学软件学院,广东广州510006 [4]中国科学院上海光学精密机械研究所量子光学重点实验室,上海201800

出　　处：《红外与激光工程》2023年第4期292-300,共9页Infrared and Laser Engineering

基　　金：国家自然科学基金(61971026)。

摘　　要：激光雷达具有全天候工作、探测精度高、有效探测距离远、易获得三维信息等特点,但工作在远距离模式时,目标点云比较稀疏。当前便携条件下,基于深度学习的算法在激光雷达点云数据直接目标识别时,实时性和成功率尚不能达到远程监视实际工程的要求。针对实际工程中利用激光雷达检测运动目标进而实时引导高分辨率相机的需求,采用基于变化的检测方法,对远距离条件下激光雷达的运动目标检测方法进行了研究,利用点云数据的距离信息,给出三维单高斯模型和三维高斯混合模型检测动目标的过程和方法,提出了利用杂波图恒虚警率检测法处理点云数据的方法。实验表明,与二维图像动目标检测方法相比,三维单高斯模型法会很大程度提高检测准确性,降低虚警率,但仍然存在较高虚警率。为适应复杂三维场景,采用基于三维高斯混合模型的方法进一步降低了虚警率,但也降低了检测速度;而杂波图CFAR的方法具有很高的实时性,同时也具有较好的检测性能。Objective Lidar is a kind of sensor using laser active imaging,with the advantages of high detection accuracy,all-weather working,easy access to high-precision three-dimensional information,far effective detection range,etc.It has been widely used in recent years,especially in the field of autonomous driving,as a three-dimensional environment perception device in the autonomous driving vehicles.When lidar is applied to perimeter surveillance and working in long-range mode,the target point cloud is relatively sparse which is different from microwave high-resolution imaging radar such as ISAR.The recognition speed of 3D point cloud data with the number of point clouds of 6000-7000/frame is lower than 12 frame/s when using training and real-time recognition of cooperative targets by deep learning method,while more missed alarms emerge.The rate of targets recognition needs to be improved.In order to guide the high-resolution infrared camera to carry out highresolution fine imaging of the detected target before recognition,the method of fast detection of moving targets is investigated.The processing method of complex scenes using 3D Gaussian method and clutter map CFAR to detect moving targets is provided.Methods The flow diagram of lidar moving target detection based on 3D point cloud data is given(Fig.2),including 3D point cloud mesh construction,noise filtering by 3D bilateral filtering,target and background segmentation.The principles of 3D single Gaussian method and 3D Gaussian mixture method for segmentation of target/background are given,and the method of using clutter map CFAR detection is proposed(Fig.1).Using 72 frames of data from actual equipment,the result of application of the Faster RCNN Resnet50 FPN deep-learning method,two-dimensional single Gaussian method,three-dimensional single Gaussian method,three-dimensional Gaussian mixture method,and clutter map CFAR method are compared.Results and Discussions Comparative experiments show that the average accuracy rate of using the Faster RCNN Resnet50 FPN de

关 键 词：动目标检测 杂波图CFAR 激光雷达 三维高斯混合模型 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]