| 高光谱图像混合像元多维卷积网络协同分解法 |
| |
| 引用本文： | 刘帅,邢光龙.高光谱图像混合像元多维卷积网络协同分解法[J].测绘学报,1957,49(12):1600-1608. |
| |
| 作者姓名： | 刘帅 邢光龙 |
| |
| 作者单位： | 1. 燕山大学信息科学与工程学院, 河北 秦皇岛 066004;2. 河北省信息传输与信号处理重点实验室, 河北 秦皇岛 066004 |
| |
| 基金项目： | 国家自然科学基金（61671401）；河北省高等学校科学技术研究项目（QN2017146） |
| |
| 摘 要： | 受成像光谱仪性能与复杂地物分布的影响，高光谱图像存在大量的混合像元。传统的基于学习的混合像元分解方法通常都是浅层模型，或缺少对空间、光谱信息的综合应用。本文提出一种多维卷积网络协同的混合像元分解深层模型，采用多种维度卷积网络能更充分利用多种维度语义信息，有利于估计小样本和高维的高光谱图像混合像元丰度。对训练数据进行增广处理，构建光谱维、空间维和立方体3种卷积神经网络；设计了融合层，协同3种卷积神经网络提取特征，“端到端”的估计混合像元丰度值；模型使用了批量归一化、池化和Dropout方法避免过拟合现象。试验结果表明，多维卷积网络协同方法的引入能更有效地提取空-谱特征信息，与其他的卷积网络解混模型相比，估计的混合像元丰度精度有显著提高。
|
| 关 键 词： | 高光谱解混 卷积神经网络 深度学习 丰度估计 |
| 收稿时间： | 2019-11-08 |
| 修稿时间： | 2020-07-24 |
Multi-dimensional convolutional network collaborative unmixing method for hyperspectral image mixed pixels |
| |
| LIU Shuai,XING Guanglong.Multi-dimensional convolutional network collaborative unmixing method for hyperspectral image mixed pixels[J].Acta Geodaetica et Cartographica Sinica,1957,49(12):1600-1608. |
| |
| Authors: | LIU Shuai XING Guanglong |
| |
| Institution: | 1. School of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, China;2. Hebei Key Laboratory of Information Transmission and Signal Processing, Qinhuangdao 066004, China |
| |
| Abstract: | Influenced by the performance of imaging spectrometer and the distribution of complex ground objects, hyperspectral images have a large number of mixed pixels. Traditional learning-based unmixing methods are shallow models, or lack of comprehensive use of spatial and spectral information. This paper proposes a collaborative deep model with multi-dimensional convolutional network. Using multi-dimensional convolutional network can make full use of multi-dimensional semantic information, which is better to estimate hyperspectral mixed pixel abundance with small samples. The method augments training data, constructs three kinds of convolutional neural networks: spectral dimension, spatial dimension and cube dimension; the method designs fusion layer to concatenate features with three kinds of convolutional neural networks, and to “end-to-end” estimate of mixed pixel abundance; the model uses batch normalization, pooling and dropout to avoid over fitting phenomenon. The experimental results indicate that the introduction of our proposed method can extract spatial-spectral feature information more effectively. Compared with other convolutional network unmixing models, the accuracy of the estimated mixed pixel abundance is significantly improved. |
| |
| 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 |
|
