An Object-Oriented CNN Model Based on Improved Superpixel Segmentation for High-Resolution Remote Sensing Image Classification

An Object-Oriented CNN Model Based on Improved Superpixel Segmentation for High-Resolution Remote Sensing Image Classification

Object-oriented convolutional neural network (CNN) has been proven to be an effective classification method for very fine spatial resolution remotely sensed imagery. It can obtain higher accuracy and well edge preservation results due to the combination of advantages of image segmentation and deep n...

Full description

Bibliographic Details
Main Authors: Zhiqing Li, Erzhu Li, Alim Samat, Tianyu Xu, Wei Liu, Yihu Zhu
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Convolutional neural network (CNN)
second-order pooling
superpixel segmentation
Online Access:https://ieeexplore.ieee.org/document/9794447/

Internet

https://ieeexplore.ieee.org/document/9794447/

Similar Items