高光谱成像
人工智能
模式识别(心理学)
计算机科学
卷积神经网络
特征提取
残余物
预处理器
特征(语言学)
降噪
保险丝(电气)
空间分析
深度学习
遥感
算法
地质学
工程类
哲学
电气工程
语言学
作者
Qiangqiang Yuan,Qiang Zhang,Jie Li,Michael K. Ng,Liangpei Zhang
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing
[Institute of Electrical and Electronics Engineers]
日期:2019-02-01
卷期号:57 (2): 1205-1218
被引量:98
标识
DOI:10.1109/tgrs.2018.2865197
摘要
Hyperspectral image (HSI) denoising is a crucial preprocessing procedure to improve the performance of the subsequent HSI interpretation and applications. In this paper, a novel deep learning-based method for this task is proposed, by learning a nonlinear end-to-end mapping between the noisy and clean HSIs with a combined spatial-spectral deep convolutional neural network (HSID-CNN). Both the spatial and spectral information are simultaneously assigned to the proposed network. In addition, multiscale feature extraction and multilevel feature representation are, respectively, employed to capture both the multiscale spatial-spectral feature and fuse different feature representations for the final restoration. The simulated and real-data experiments demonstrate that the proposed HSID-CNN outperforms many of the mainstream methods in both the quantitative evaluation indexes, visual effects, and HSI classification accuracy.
科研通智能强力驱动
Strongly Powered by AbleSci AI