An object-based supervised classification framework for very-high-resolution remote sensing images using convolutional neural networks

Zhang Xiaodong; Wang Qing; Chen Guanzhou; Dai Fan; Zhu Kun; Gong Yuanfu; Xie Yijuan

首页> 外文期刊>Remote sensing letters >An object-based supervised classification framework for very-high-resolution remote sensing images using convolutional neural networks

【24h】

An object-based supervised classification framework for very-high-resolution remote sensing images using convolutional neural networks

机译：基于卷积神经网络的超高分辨率遥感影像的基于对象的监督分类框架

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Object- based image classification ( OBIC) is presented to overcome the drawbacks of pixel- based image classification ( PBIC) when very- high- resolution ( VHR) imagery is classified. However, most of classification methods in OBIC are dealing with 1D hand- crafted features extracted from segmented image objects ( superpixels). To extract 2D deep features of superpixels, a new deep OBIC framework is introduced in this letter by using convolutional neural networks ( CNNs). We first analyze the different mask policies of superpixels and design two architectures of networks. Then, we determine the specific details of our framework before experiments. The results of comparison experiments show that our DiCNN- 4 ( Double- input CNN) model achieves higher overall accuracy,. coefficient and F- measure than conventional OBIC methods on our image dataset.

机译：提出了基于对象的图像分类（OBIC），以克服在对超高分辨率（VHR）图像进行分类时基于像素的图像分类（PBIC）的缺点。但是，OBIC中的大多数分类方法都是处理从分割图像对象（超像素）中提取的一维手工特征。为了提取超像素的2D深度特征，本文使用卷积神经网络（CNN）引入了新的深度OBIC框架。我们首先分析超像素的不同遮罩策略，然后设计两种网络架构。然后，我们在实验前确定框架的具体细节。比较实验结果表明，我们的DiCNN-4（双输入CNN）模型可实现更高的整体精度。系数和F-度量比我们的图像数据集上的传统OBIC方法要好。

著录项

来源
《Remote sensing letters》 |2018年第6期|373-382|共10页
作者
Zhang Xiaodong; Wang Qing; Chen Guanzhou; Dai Fan; Zhu Kun; Gong Yuanfu; Xie Yijuan;
展开▼
作者单位

Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan, Hubei, Peoples R China;

Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan, Hubei, Peoples R China;

Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan, Hubei, Peoples R China;

Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan, Hubei, Peoples R China;

Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan, Hubei, Peoples R China;

Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan, Hubei, Peoples R China;

Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan, Hubei, Peoples R China;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词

相似文献

外文文献
中文文献
专利

1. Exploring multiscale object-based convolutional neural network (multi-OCNN) for remote sensing image classification at high spatial resolution [J] . Martins Vitor S., Kaleita Amy L., Gelder Brian K., ISPRS Journal of Photogrammetry and Remote Sensing . 2020,第Octa期

机译：探索高空间分辨率遥感图像分类的多尺度对象卷积神经网络（多OCNN）
2. An object-based and heterogeneous segment filter convolutional neural network for high-resolution remote sensing image classification [J] . Pan Xin, Zhao Jian, Xu Jun International journal of remote sensing . 2019,第15a16期

机译：基于对象的异构段滤波卷积神经网络用于高分辨率遥感影像分类
3. An object-based and heterogeneous segment filter convolutional neural network for high-resolution remote sensing image classification [J] . Pan Xin, Zhao Jian, Xu Jun International journal of remote sensing . 2019,第15a16期

机译：用于高分辨率遥感图像分类的基于对象和异构段滤波器卷积神经网络
4. Object-based feature extraction and semi-supervised classification for urban change detection using high-resolution remote sensing images [C] . Bin Hou, Qingjie Liu, Yunhong Wang IEEE International Geoscience and Remote Sensing Symposium . 2015

机译：使用高分辨率遥感影像的基于对象的特征提取和半监督分类，用于城市变化检测
5. Classification of SAR images and retrieval of remotely sensed parameters using neural networks. [D] . Rawat, Vikram Kumar. 1994

机译：SAR图像分类和使用神经网络检索遥感参数。
6. Training Convolutional Neural Networks with Multi-Size Images and Triplet Loss for Remote Sensing Scene Classification [O] . Jianming Zhang, Chaoquan Lu, Jin Wang, 2020

机译：利用多尺寸图像和三重态损失训练卷积神经网络进行遥感场景分类
7. A supervised hierarchical segmentation of remote-sensing images using a committee of multi-scale convolutional neural networks [O] . Basaeed Essa, Bhaskar Harish, Hill Paul, 2016

机译：使用多尺度卷积神经网络委员会对遥感影像进行监督分层分割

An object-based supervised classification framework for very-high-resolution remote sensing images using convolutional neural networks

摘要

著录项

相似文献

相关主题

期刊订阅