基于光电侦察的“低慢小”目标检测综述  

A Survey of LSS-Target Detection Based on Photoelectric Reconnaissance

作　　者：张鹏[1] 徐丹 ZHANG Peng;XU Dan(The 27th Institute of China Electronics Technology Group Corporation,Zhengzhou 450047,China;Henan Earthquake Agency,Zhengzhou 450016,China)

机构地区：[1]中国电子科技集团公司第二十七研究所,河南郑州450047 [2]河南省地震局,河南郑州450016

出　　处：《中国电子科学研究院学报》2022年第11期1042-1048,共7页Journal of China Academy of Electronics and Information Technology

摘　　要：目前关于小目标检测的研究、综述较多,但针对“低慢小”检测的相对较少。本文结合“低慢小”的目标特性,梳理了“低慢小”目标检测存在的技术难点,总结分析了近年基于光电侦察的传统图像处理检测方法、深度学习检测方法的基本流程、各自的优缺点以及主要研究进展,并着重对比分析了这些检测方法采用的数据集以及检测结果,对后续“低慢小”目标检测研究具有一定参考价值和推动作用。最后,指出了“低慢小”目标检测下一步亟待解决的问题。There is more research and survey on small target than LSS-Target(the Low altitude,Slow speed Small Target)currently.The paper firstly combining the target properties of LSS-Target analyze the difficulty to detect LSS-Target,Secondly,Summarize the base procedure,advantages and disadvantages,main achievements of detecting the LSS-Target which are based on conversational image processing method and on Deep Learning method in photoelectric reconnaissance area,and then analyze the data set and detecting result for these methods which are very import for the follow-up researchers to reference,certainly promote their researching progress.Finally,point out the problems of LSS-Target detecting which are urgently to be solved.

关 键 词：低慢小 无人机 目标检测 光电侦察 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]