| 基于BP神经网络的高分辨率遥感影像分类 |
| |
| 引用本文： | 杨希,王鹏.基于BP神经网络的高分辨率遥感影像分类[J].四川测绘,2011(3):115-118. |
| |
| 作者姓名： | 杨希 王鹏 |
| |
| 作者单位： | 中铁第四勘察设计院集团有限公司; |
| |
| 摘 要： | 为了能有效地从高分辨率遥感影像中提取地物信息,本文通过影像的光谱和纹理特征,利用BP神经网络算法进行影像分类研究。首先提取分类所需的光谱和纹理特征源,然后根据影像和地物特征,建立BP神经网络,用于样本训练和分类处理,实现地物分类。为验证该方法的可靠性,以2006年11月获取的成都平原某区域的Quickbird影像为实验数据,进行高分辨率遥感影像的地物分类实验。实验结果表明,结合影像光谱和纹理特征的BP神经网络分类算法,不仅可以有效保证BP神经网络分类训练的稳定性和收敛速度,还能达到较高的分类精度。
|
| 关 键 词： | 影像分类 纹理特征 光谱特征 BP神经网络 |
Classification of High-resolution Image Based on Spectral and Textural Features by Back-propagation Neural Network |
| |
| YANG Xi WANG Peng.Classification of High-resolution Image Based on Spectral and Textural Features by Back-propagation Neural Network[J].Surveying and Mapping of Sichuan,2011(3):115-118. |
| |
| Authors: | YANG Xi WANG Peng |
| |
| Institution: | YANG Xi WANG Peng(China Railway Fourth Survey and Design Institute Group Co.,Ltd,Wuhan 430063,China) |
| |
| Abstract: | To extract the object-level information from the high-resolution satellite imagery,this paper presents a non-parametric classification approach termed back-propagation(BP) neural network.Both spectral and textural features extracted from high-resolution images are jointly used in the BP solution for the purpose of implementing classification.The experiments are performed using the multi-spectral(resolution 2.44 m) and panchromatic(resolution 0.61 m) images acquired by the satellite Quickbird in November of ... |
| |
| Keywords: | Classification Spectral features Textural features Back-propagation neural network |
| 本文献已被 CNKI 维普 等数据库收录！ |
|
