论文部分内容阅读
多时相遥感图像变化检测在国民经济和国防建设领域有着广泛的应用需求。通过分析同一地域不同时相的遥感图像,变化检测提供地物发生变化的信息,用于城市规划、资源和环境监测、战场态势分析以及打击效果评估等。迄今为止,众多学者己经提出了多种变化检测的方法,这些方法按照信息处理的层次可分为基于像素,基于特征和基于目标的变化检测。本文将针对城市变化检测的需要,利用SPOT5卫星数据主要研究了分析和测试了目前主要的变化检测方法在城市建筑和用地变化的应用,并试验了基于Mean-Shift图像分割的变化检测方法。试验证明这一方法是有效的。
Multi-temporal remote sensing image change detection in the national economy and national defense construction has a wide range of applications. By analyzing the remote sensing images of different phases in the same area, the change detection provides information on the change of the ground objects, which is used for urban planning, resource and environmental monitoring, battlefield situation analysis and impact evaluation. So far, many scholars have proposed a variety of detection methods, these methods can be divided into pixel-based, feature-based and target-based change detection according to the level of information processing. This paper will focus on the need of urban change detection, using SPOT5 satellite data to analyze and test the application of the main change detection methods in urban buildings and land use changes, and test the change detection method based on Mean-Shift image segmentation. Experiments prove that this method is effective.