大视场域的目标检测与识别算法综述  

Review on Object Detection and Recognition in Large Field of View

作　　者：李唐薇 童官军[1] 李宝清[1] 卢晓洋 Li Tangwei;Tong Guanjun;Li Baoqing;Lu Xiaoyang(Key Laboratory of Science and Technology on Micro-System,Shanghai Institute of Microsystem and Information Technology,Chinese Academy of Sciences,Shanghai 201800,China;University of Chinese Academy of Sciences,Beijing 100049,China)

机构地区：[1]中国科学院上海微系统与信息技术研究所微系统技术重点实验室,上海201800 [2]中国科学院大学,北京100049

出　　处：《激光与光电子学进展》2020年第12期15-29,共15页Laser & Optoelectronics Progress

基　　金：国家重点研发计划公共安全专项

摘　　要：目标精确感知与识别为信息化战争提供了一个重要的技术增长点,全景视觉传感设备因其拥有大视场(LFOV)范围优势而逐渐被应用于安防及军事领域中的目标检测与识别任务.首先从相机成像模型、图像成像质量以及目标物体的非对称性三个方面对存在的困难以及挑战进行阐述.基于是否进行畸变校正预处理,将近年来LFOV域的目标检测与识别算法分为基于畸变校正的目标检测与识别算法和基于原始LFOV图像的目标检测与识别算法两类,并针对这两类算法进行了全面梳理和总结,对当前LFOV域的目标检测与识别各类算法的统一性和差异性进行思考分析,探讨其未来发展趋势.Precise object detection and recognition plays an important role in information-based warfare.Due to panoramic vision sensors’large field of view(LFOV),they are gradually applied to security and military areas.In this paper,first,the difficulties and challenges in the development of object detection and recognition in LFOV are presented from three aspects:camera imaging model,image imaging quality,and asymmetry of object.Then,based on whether the distortion correction preprocessing is carried out or not,the object detection and recognition algorithms in LFOV are classified into two categories:distortion correction based algorithms and original LFOV image based algorithms.These two kinds of algorithms are comprehensively combed and summarized.Finally,the paper analyzes the unity and difference of various algorithms for object detection and recognition in LFOV and discusses their future development trend.

关 键 词：图像处理 目标检测与识别 大视场图像 畸变校正 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]