基于嵌入式计算机的激光防御低慢小目标识别  

Low slow small target recognition of laser defense based on embedded computer

作　　者：郭敏 GUO Min(Hebei Open University,Shijiazhuang 050080,China)

机构地区：[1]河北开放大学,石家庄050080

出　　处：《激光杂志》2024年第1期205-210,共6页Laser Journal

基　　金：河北省自然科学基金项目(No.F2020202215);河北省人社厅资助项目(No.C20221159)。

摘　　要：针对现有激光防御低慢小目标识别准确率差的问题,提出基于嵌入式计算机的激光防御低慢小目标识别方法。本次研究先对激光雷达目标探测、识别原理进行分析,完成基于嵌入式计算机的激光防御系统架构设计,然后通过目标局部特征提取方法及目标识别检测方法完成激光防御低慢小目标的识别设计,最后开展仿真实验证明所提方法应用效果。实验结果表明,应用所提方法开展低小慢目标的识别准确率较高,均高于91.5%,而且其特征提取平均时间小于11.3 ms,均优于对比方法。Aiming at the problem of poor recognition accuracy of low slow small target in laser defense,a method of low slow small target recognition in laser defense based on embedded computer is proposed.This research first analyzes the principle of laser radar target detection and recognition,completes the architecture design of laser defense system based on embedded computer,and then completes the recognition design of low slow small targets for laser defense through target local feature extraction method and target recognition detection method.Finally,simulation experiments are carried out to prove the application effect of the proposed method.The experimental results show that the recognition accuracy of the proposed method for low,small and slow targets is higher than 91.5%,and the average feature extraction time is less than 11.3 ms,which is better than the comparison method.

关 键 词：嵌入式计算机 激光雷达 防御系统 局部形状特征 目标识别 

分 类 号：TN212[电子电信—物理电子学]