一种低照度图像目标识别方法  

A Method of Low Illumination Image Target Recognition

作　　者：张玲 张焱[1] 陈路路[1] ZHANG Ling;ZHANG Yan;CHEN Lulu(The 54th Research Institute of CETC,Shijiazhuang 050081,China)

机构地区：[1]中国电子科技集团公司第五十四研究所,河北石家庄050081

出　　处：《无线电工程》2020年第8期656-660,共5页Radio Engineering

基　　金：中国电子科技集团公司航天信息应用技术重点实验室开放基金资助项目(SXX18629T022)。

摘　　要：针对低照度条件下传感器图像目标分类精度低的问题,提出了一种基于方向梯度直方图(Histogram of Oriented Gradient,HOG)特征和支持向量机(Support Vector Machine,SVM)的传感器图像目标分类方法。通过图像目标特征的提取和分类器的设计,实现了目标的分类识别。验证结果表明,基于HOG特征的分类器可实现目标的高精度分类,且分类精度优于95%。For improving the accuracy of sensor image target classification under the condition of low illumination,a method of sensor image target classification based on the features of Histogram of Oriented Gradient(HOG) and Support Vector Machine(SVM) is proposed.By extracting the image target features and the design of classifier,the sensor image target classification and recognition are implemented.The experimental results show that the classifier based on HOG features can achieve high accuracy target classification,and the classification accuracy is better than 95%.

关 键 词：低照度 目标分类 HOG特征 支持向量机 

分 类 号：TN722.75[电子电信—电路与系统]