多偏移遥感图像的BP神经网络亚像元定位  

Sub-pixel mapping based on BP neural network with multiple shifted remote sensing images

作　　者：史文中[1] 赵元凌 王群明[3] 

机构地区：[1]香港理工大学武汉大学空间信息联合实验室,湖北武汉430079 [2]武汉大学遥感信息工程学院,湖北武汉430079 [3]香港理工大学土地测量与地理资讯学系,中国香港999077

出　　处：《红外与毫米波学报》2014年第5期527-532,共6页Journal of Infrared and Millimeter Waves

基　　金：香港研究资助局项目(PolyU 5249/12E);香港理工大学项目(G-YJ75);国家科技支撑计划(2012BAJ15B04);国家高技术研究发展计划(2012AA12A305);国家自然基金重点项目(41331175)~~

摘　　要：提出了一种借助多偏移遥感图像来改进基于BP神经网络(BPNN)的亚像元定位新方法.不同于原BPNN方法使用单幅低空间分辨率观测图像,新方法利用多幅带有亚像元偏移的低空间分辨图像来确定亚像元属于各类的概率,然后根据概率值和地物覆盖比例确定亚像元类别,以降低BPNN定位模型中的不确定性和误差.实验表明,提出方法在视觉和定量评价上,均能获得更高精度的亚像元定位结果,验证了提出方法的有效性.A new sub-pixel mapping method is presented in this paper, which makes use of multiple shifted remote sens- ing images to enhance the back-propagation neural network （BPNN）-based sub-pixel mapping method. Different from the original BPNN method that uses a single observed coarse spatial resolution image, the new method integrates multiple coarse spatial resolution images that are shifted from each other to determine the probability of a sub-pixel belonging to each class. The probabilities and land cover fractions are then used to allocate classes for sub-pixels. The proposed meth- od can decrease the uncertainty and errors in BPNN-based sub-pixel mapping. Experimental results show that with both visual and quantitative evaluation, the proposed method can obtain more accurate sub-pixel mapping results.

关 键 词：遥感图像 亚像元定位 BP神经网络(BPNN) 多偏移图像 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]