激光与光电子学进展, 2017, 54 (10): 102801, 网络出版: 2017-10-09
结合最小噪声分离变换和卷积神经网络的高分辨影像分类方法 下载: 539次
High Resolution Image Classification Method Combining with Minimum Noise Fraction Rotation and Convolution Neural Network
遥感 高分辨影像 卷积神经网络 最小噪声分离变换 影像分类 remote sensing high resolution image convolution neural network minimum noise fraction rotation image classification
摘要
针对传统浅层机器学习方法应用于高分辨影像分类时存在的问题, 提出了结合最小噪声分离变换和卷积神经网络的高分辨率影像分类方法。采用最小噪声分离分析非监督训练初始化卷积神经网络, 为提高训练速度, 使用线性修正函数作为神经网络的激活函数; 利用概率最大化采样原则减少池化过程中影像特征的缺失, 并将下采样后影像特征输入Softmax分类器进行分类。采用所提分类方法对典型地区的影像进行分类实验, 并与支持向量机和人工神经网络分类方法的分类结果进行对比。结果表明, 所提分类方法的分类精度明显高于另两种分类方法的分类精度, 并能充分挖掘高分辨遥感影像的空间信息。
Abstract
Aiming at the problems of traditional shallow machine learning methods applied to high resolution image classification, we propose a high resolution image classification method combining with minimum noise fraction (MNF) rotation and convolution neural networks (CNN). MNF is used to analyze the initial unsupervised pre-training CNN. Linear correction function is adopted as the activation function of the neural network to increase the training speed. In order to reduce the missing of image features in the process of the pool, the sampled image features are put into Softmax classifier under the principle of maximizing sampling probability. Experimental image of typical regions is selected and classified by using the proposed classification method, and the classification results are compared with those of support vector machines classification method and artificial neural network classification method. The results show that the classification accuracy of the proposed method is superior to the shallow machine learning classification methods, and can fully excavate the spatial information of high resolution remote sensing images.
陈洋, 范荣双, 王竞雪, 吴增林, 孙汝星. 结合最小噪声分离变换和卷积神经网络的高分辨影像分类方法[J]. 激光与光电子学进展, 2017, 54(10): 102801. Chen Yang, Fan Rongshuang, Wang Jingxue, Wu Zenglin, Sun Ruxing. High Resolution Image Classification Method Combining with Minimum Noise Fraction Rotation and Convolution Neural Network[J]. Laser & Optoelectronics Progress, 2017, 54(10): 102801.