Hyperspectral Remote Sensing Image Classification Based on Maximum Overlap Pooling Convolutional Neural Network

Hyperspectral Remote Sensing Image Classification Based on Maximum Overlap Pooling Convolutional Neural Network

In a traditional convolutional neural network structure, pooling layers generally use an average pooling method: a non-overlapping pooling. However, this condition results in similarities in the extracted image features, especially for the hyperspectral images of a continuous spectrum, which makes i...

Full description

Bibliographic Details
Main Authors: Chenming Li, Simon X. Yang, Yao Yang, Hongmin Gao, Jia Zhao, Xiaoyu Qu, Yongchang Wang, Dan Yao, Jianbing Gao
Format: Article
Language:English
Published: MDPI AG 2018-10-01
Series:Sensors
Subjects:
remote sensors
hyperspectral remote sensing image
image classification
convolution neural network
Online Access:http://www.mdpi.com/1424-8220/18/10/3587

Similar Items

Similar Items