| 高光谱影像分类的深度少样例学习方法 |
| |
| 引用本文： | 刘冰,左溪冰,谭熊,余岸竹,郭文月.高光谱影像分类的深度少样例学习方法[J].测绘学报,1957,49(10):1331-1342. |
| |
| 作者姓名： | 刘冰 左溪冰 谭熊 余岸竹 郭文月 |
| |
| 作者单位： | 信息工程大学, 河南 郑州 450001 |
| |
| 基金项目： | 国家自然科学基金（41801388） |
| |
| 摘 要： | 针对高光谱影像分类面临的小样本问题，提出了一种深度少样例学习算法，该算法在训练过程中通过模拟小样本分类的情况来训练深度三维卷积神经网络提取特征，其提取得到的特征具有较小类内间距和较大的类间间距，更适合小样本分类问题，且能用于不同的高光谱数据，具有更好的泛化能力。利用训练好的模型提取目标数据集的特征，然后结合最近邻分类器和支持向量机分类器进行监督分类。利用Pavia大学、Indian Pines和Salinas 3组高光谱影像数据进行分类试验，试验结果表明，该算法能够在训练样本较少的情况下（每类地物仅选取5个标记样本作为训练样本）取得优于传统半监督分类方法的分类精度。
|
| 关 键 词： | 高光谱影像分类 深度少样例学习 深度三维卷积网络 最近邻分类 |
| 收稿时间： | 2019-11-26 |
| 修稿时间： | 2020-05-11 |
A Deep few-shot learning algorithm for hyperspectral image classification |
| |
| LIU Bing,ZUO Xibing,TAN Xiong,YU Anzhu,GUO Wenyue.A Deep few-shot learning algorithm for hyperspectral image classification[J].Acta Geodaetica et Cartographica Sinica,1957,49(10):1331-1342. |
| |
| Authors: | LIU Bing ZUO Xibing TAN Xiong YU Anzhu GUO Wenyue |
| |
| Institution: | Information Engineering University, Zhengzhou 450001, China |
| |
| Abstract: | For hyperspectral image classification problem of small sample, this paper proposes a depth of less sample learning algorithm, this algorithm through the simulation of the small sample classification in the process of training is to train the depth 3D convolution neural network feature extraction, the extraction of characteristic with smaller class span and large spacing between classes, more suitable for small sample classification problem, and can be used for different hyperspectral data, has better generalization ability. The trained model is used to extract the features of the target data set, and then the nearest neighbor classifier and support vector machine classifier are combined for supervised classification. Three groups of hyperspectral image data of Pavia university, Indian Pines and Salinas were used in the classification experiment. The experimental results showed that the algorithm could achieve a better classification accuracy than the traditional semi-supervised classification method under the condition of fewer training samples (only 5 marked samples were selected for each type of feature as training samples). |
| |
| Keywords: | |
|
| 点击此处可从《测绘学报》浏览原始摘要信息 |
| 点击此处可从《测绘学报》下载免费的PDF全文 |
|
