首页 | 本学科首页   官方微博 | 高级检索  
     检索      

一种飞机目标的遥感识别方法
引用本文:殷文斌,王成波,袁翠,乔彦友.一种飞机目标的遥感识别方法[J].测绘通报,2017,0(3):34-37.
作者姓名:殷文斌  王成波  袁翠  乔彦友
作者单位:1. 中国科学院遥感与数字地球研究所, 北京 100094;2. 中国科学院大学, 北京 100049
摘    要:高空间分辨率遥感影像通常具有数据量大、背景复杂及地物占比较少等特点。如果直接将RCNN模型应用于高空间分辨率遥感影像目标识别,计算量大且效率低。级联AdaBoost算法识别率高、速度快,但又会产生较多的虚假目标。本文结合RCNN模型和级联AdaBoost算法,提出了一种由粗到精的飞机目标识别方法。首先使用基于HOG特征的级联AdaBoost算法快速提取飞机目标候选区域,然后利用基于卷积神经网络特征的SVM对飞机目标候选区域进行精细识别。试验表明,本文提出的方法在保证准确率的同时,还有效提高了计算效率。

关 键 词:AdaBoost  RCNN  飞机识别  高空间分辨率遥感影像  
收稿时间:2016-07-17
修稿时间:2017-01-17

A Method of Aircraft Recognition in Remote Sensing Images
YIN Wenbin,WANG Chengbo,YUAN Cui,QIAO Yanyou.A Method of Aircraft Recognition in Remote Sensing Images[J].Bulletin of Surveying and Mapping,2017,0(3):34-37.
Authors:YIN Wenbin  WANG Chengbo  YUAN Cui  QIAO Yanyou
Institution:1. Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China;2. University of Chinese Academy of Sciences, Beijing 100049, China
Abstract:High resolution remote sensing images often has the characteristics of huge data amount,complex background and low ground objects proportion.It is inefficient to use RCNN model for object recognition in high resolution remote sensing images directly.The cascade AdaBoost has the advantages of high recall rate and fast calculating speed,while it is likely to detect more false targets.In this article,a coarse to fine aircraft recognition method is proposed by combining RCNN model with cascade AdaBoost.Firstly,a HOG based cascade AdaBoost is applied to extract the candidate aircraft regions quickly.Then we classify the candidate regions with the support vector machine (SVM) classifier using features computed from convolutional neural networks.The results show that this method can ensure the accuracy and improve the computational efficiency.
Keywords:AdaBoost  RCNN  aircraft recognition  high resolution remote sensing images
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《测绘通报》浏览原始摘要信息
点击此处可从《测绘通报》下载免费的PDF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