3D laser scanning strategy based on cascaded deep neural network

作     者：Xiao-bin Xu Ming-hui Zhao Jian Yang Yi-yang Xiong Feng-lin Pang Zhi-ying Tan Min-zhou Luo Xiao-bin Xu;Ming-hui Zhao;Jian Yang;Yi-yang Xiong;Feng-lin Pang;Zhi-ying Tan;Min-zhou Luo

作者机构：College of Mechanical&Electrical EngineeringHohai UniversityChangzhou213022China Jiangsu Key Laboratory of Special Robot TechnologyHohai UniversityChangzhou213022China College of Mechanical EngineeringYangzhou UniversityYangzhou225127China 

出 版 物：《Defence Technology（防务技术）》 (Defence Technology)

年 卷 期：2022年第18卷第9期

页      面：1727-1739页

核心收录：

学科分类：080904[工学-电磁场与微波技术] 12[管理学] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 0810[工学-信息与通信工程] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 081105[工学-导航、制导与控制] 0835[工学-软件工程] 081001[工学-通信与信息系统] 081002[工学-信号与信息处理] 0825[工学-航空宇航科学与技术] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：funded by National Natural Science Foundation of China(Grant No. 51805146) the Fundamental Research Funds for the Central Universities (Grant No. B200202221) Jiangsu Key R&D Program (Grant Nos. BE2018004-1, BE2018004) College Students’ Innovative Entrepreneurial Training Plan Program (Grant No. 2020102941513) 

主　　题：Scanning strategy Cascaded deep neural network Improved cross entropy loss function Pitching range and speed model Integral separate speed PID 

摘      要：A 3D laser scanning strategy based on cascaded deep neural network is proposed for the scanning system converted from 2D Lidar with a pitching motion device. The strategy is aimed at moving target detection and monitoring. Combining the device characteristics, the strategy first proposes a cascaded deep neural network, which inputs 2D point cloud, color image and pitching angle. The outputs are target distance and speed classification. And the cross-entropy loss function of network is modified by using focal loss and uniform distribution to improve the recognition accuracy. Then a pitching range and speed model are proposed to determine pitching motion parameters. Finally, the adaptive scanning is realized by integral separate speed PID. The experimental results show that the accuracies of the improved network target detection box, distance and speed classification are 90.17%, 96.87% and 96.97%, respectively. The average speed error of the improved PID is 0.4239°/s, and the average strategy execution time is 0.1521 *** range and speed model can effectively reduce the collection of useless information and the deformation of the target point cloud. Conclusively, the experimental of overall scanning strategy show that it can improve target point cloud integrity and density while ensuring the capture of target.