欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
为了提高多光谱遥感影像的分类精度,提出一种基于粒子群训练的人工神经网络的多光谱遥感影像的分类方法。该方法先建立一个针对多光谱遥感影像的神经网络分类模型,然后引入粒子群算法对神经网络进行网络权值与阈值的优化,再利用训练好的神经网络对多光谱遥感影像进行分类。该方法不仅利用了人工神经网络在解决多光谱遥感影像混合光谱的优势,而且克服了BP神经网络在训练时候收敛速度过慢、振荡的缺点。实验结果证明：基于粒子群训练的人工神经网络方法能够比较好地提高多光谱遥感影像的分类精度。
英文摘要：
In order to improve the classification accuracy of multi-spectral remote sensing images, a multi-spectral image classification using neural network based on PSO （particle swarm optimization） is presented. First a classification model of neural network is established, next the weights and threshold of the network are optimized through PSO algorithm, and then the trained network is utilized to classify the multi-spectral remote sensing images. This method makes use of the capability of artificial neural network mi~spectra recognition, and can speed up the convergence and eliminate the oscillation of backpropagation of neural network. The results have proved the method which based on PSO training of the artificial neural network can iruprove the classification accuracy of multi-spectral remote sensing images.
同期刊论文项目
同项目期刊论文
期刊信息
位置：