首页 | 官方网站   微博 | 高级检索  
     

基于增量学习的高光谱图像目标检测
引用本文:张宁,陈嘉杰,伍伟,沈霁,袁杰,朱新忠,谢凤英.基于增量学习的高光谱图像目标检测[J].上海航天,2019,36(5):44-49.
作者姓名:张宁  陈嘉杰  伍伟  沈霁  袁杰  朱新忠  谢凤英
作者单位:上海航天电子技术研究所;北京航空航天大学宇航学院
摘    要:高光谱图像目标检测是高光谱图像分析中的重要研究内容之一。本文从经典有效的约束能量最小化算法出发,提出了一种基于增量学习的高光谱目标检测方法。当获得新的样本时,不需要重新计算所有样本的自相关矩阵即可对检测器模型进行更新,减轻了星上有限计算资源的负担。实验结果表明:本文提出的目标检测算法在压制背景光谱的同时可以更好地适应目标光谱,提高了算法的检测性能。

关 键 词:高光谱图像    目标检测    增量学习    约束能量最小化    背景压制
收稿时间:2019/4/12 0:00:00
修稿时间:2019/6/21 0:00:00

Hyperspectral Target Detection Algorithm Based on Incremental Learning
ZHANG Ning,CHEN Jiajie,WU Wei,SHEN Ji,YUAN Jie,ZHU Xinzhong and XIE Fengying.Hyperspectral Target Detection Algorithm Based on Incremental Learning[J].Aerospace Shanghai,2019,36(5):44-49.
Authors:ZHANG Ning  CHEN Jiajie  WU Wei  SHEN Ji  YUAN Jie  ZHU Xinzhong and XIE Fengying
Affiliation:Shanghai Aerospace Electronic Technology Institute, Shanghai 201109, China,School of Astronautics, Beihang University, Beijing 100191, China,Shanghai Aerospace Electronic Technology Institute, Shanghai 201109, China,Shanghai Aerospace Electronic Technology Institute, Shanghai 201109, China,Shanghai Aerospace Electronic Technology Institute, Shanghai 201109, China,Shanghai Aerospace Electronic Technology Institute, Shanghai 201109, China and School of Astronautics, Beihang University, Beijing 100191, China
Abstract:Hyperspectral image target detection is one of the most important research directions in hyperspectral image analysis field. In this paper, an incremental learning based target detection method is proposed. We design the incremental form of the classical constrained energy minimization algorithm. When a new sample is obtained, the proposed method will update the model without recalculating the auto-correlation matrix of all samples, which reduces the burden of on-board calculations. Experiments show that the proposed method can adapt the target spectrum while suppressing the background spectrum, which improves the detection accuracy effectively.
Keywords:hyperspectral image  target detection  incremental learning  constrained energy minimization  background suppression
本文献已被 CNKI 等数据库收录!
点击此处可从《上海航天》浏览原始摘要信息
点击此处可从《上海航天》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号