Land Cover Classification of RADARSAT-2 SAR Data Using Convolutional Neural Network

来源 :Wuhan University Journal of Natural Sciences | 被引量 : 0次 | 上传用户:wudiscl
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
In this paper, we propose a convolutional neural network(CNN) based on deep learning method for land cover classification of synthetic aperture radar(SAR) images. The proposed method consists of convolutional layers, pooling layers, a full connection layer and an output layer. The method acquires high-level abstractions for SAR data by using a hierarchical architecture composed of multiple non-linear transformations such as convolutions and poolings. The feature maps produced by convolutional layers are subsampled by pooling layers and then are converted into a feature vector by the full connection layer. The feature vector is then used by the output layer with softmax regression to perform land cover classification. The multi-layer method replaces hand-engineered features with backpropagation(BP) neural network algorithm for supervised feature learning, hierarchical feature extraction and land cover classification of SAR images. RADARSAT-2 ultra-fine beam high resolution HH-SAR images acquired in the rural urban fringe of the Greater Toronto Area(GTA) are selected for this study. The experiment results show that the accuracy of our classification method is about 90% which is higher than that of nearest neighbor(NN). In this paper, we propose a convolutional neural network (CNN) based on deep learning method for land cover classification of synthetic aperture radar (SAR) images. The proposed method consists of convolutional layers, pooling layers, a full connection layer and an output layer The method acquires high-level abstractions for SAR data by using a hierarchical architecture composed of multiple non-linear transformations such as convolutions and poolings. The feature maps produced by convolutional layers are subsampled by pooling layers and then are converted into a feature vector by the full connection layer. The feature vector is then used by the output layer with softmax regression to perform land cover classification. The multi-layer method replaces hand-engineered features with backpropagation (BP) neural network algorithm for supervised feature learning, hierarchical feature extraction and land cover classification of SAR images. RADARSAT-2 ultra-fine beam high resolution HH-SAR images acquired in the rural urban fringe of the Greater Toronto Area (GTA) are selected for this study. The experiment results show that the accuracy of our classification method is about 90% which is higher than that of nearest neighbor (NN).
其他文献
1994年仲裁法的颁布标志着中国仲裁制度现代化进程正式起步,历经十几年的发展,选择仲裁解决商事争议已经获得越来越多商事主体的认同。在国际商事仲裁中,仲裁管辖权是一个首要的
对行行为是刑事司法实践中较为常见的犯罪行为模式,有其存在和研究的价值。我国刑法理论界引入对行犯这一概念后,并未对其进行适当的归位,使得我国刑法中对行行为的规定和具
近年来,内地与台湾地区的经济活动日趋频繁,随之产生的贸易摩擦而诉诸法律的纠纷也层出不穷。然而,因长期的政治对峙,两岸间的司法交流并不畅通,双方的判决或裁定在彼此间均存在不
在实践中,抵押权受到侵害的现象时有发生,抵押权受到侵害后,法律必须给予及时、充分、有效的救济。对抵押权的救济有多种方式,主要包括物权救济方式、侵权责任救济方式以及自力救
[目的]了解客家人新生儿哺乳卫生状况及其与新生儿腹泻发病的影响,为保护母婴健康提供参考依据。[方法]2011年11月至2012年1月,在梅县随机抽取99名客家产妇及其哺乳的新生儿(
本幅叶欣山水,水墨绢本,设色,八开册页,纵25厘米、横18厘米。此画写于顺治十四年(1657)八月。《山水册页》每画各取自然山水小景,或画峰峦楼阁,或写夏山茂林,极富意趣。第一
该文介绍了我国大地坐标系的概况 ,阐述了工程控制网坐标系的确定原则 ,以及工程控制网中央子午线和投影面选择和确定的方法。
前苏联建国时期卓越的心理学家维果茨基曾提出过这样一个观点:学生的学习是在教师有效指导下进步发展的过程,教学的本质特征不是行为主义者所认为的“刺激一反应”,而是激发学习
中央与地方立法权的配置是我国权力划分与国家治理无法回避的理论与实践问题。立法权是中央与地方关系的“晴雨表”,在中央与地方关系不断博弈、变化的背景下,对立法权纵向配置
某高层住宅楼基础施工中,发现土洞、岩溶发育.经查实,原施工挖孔桩基大部分未落到可靠的持力层上.采取钻孔充填灌浆处理土洞、次高压劈裂灌浆加固软弱接触带、高浓度水泥浆或