一种融合多特征的面向对象变化检测方法

Translated title of the contribution: An Object-Oriented Change Detection Method Based on Multi-Feature Fusion

Wen Zhong Shi (Inventor), Liping Cai (Inventor)

Research output: Patents, agreements, assignments and companiesPatents granted

Abstract

本发明适用于遥感技术领域,提供了一种融合多特征的面向对象变化检测方法,包括S101、影像预处理;S102、纹理特征提取;S103、影像分割;S104、对象特征提取;S105、生成差分影像;S106、初始变化检测结果获取;S107、计算特征权重;S108、得到对象变化检测结果,通过加权模糊C均值法融合多维特征,将各个检测对象聚类为变与不变的两类。本发明实施例通过对两期图像进行上述步骤的处理,分析并确定各维特征的权重,并通过Relief算法提取各维特征的权重,将权重加入模糊C均值法中形成加权模糊C均值法,通过加权模糊C均值法融合多维特征,将各个检测对象聚类为变与不变的两类,有效地融合了不同特征进行面向对象的变化检测,提高了变化检测结果的精度。
Translated title of the contributionAn Object-Oriented Change Detection Method Based on Multi-Feature Fusion
Original languageChinese (Simplified)
Patent numberZL201710699957.3
IPC G06K9/54
Filing date16/08/17
Publication statusPublished - 24 Jan 2020

Fingerprint

Dive into the research topics of 'An Object-Oriented Change Detection Method Based on Multi-Feature Fusion'. Together they form a unique fingerprint.

Cite this