Land cover changed object detection in remote sensing data with medium spatial resolution
Land cover changed object detection in remote sensing data with medium spatial resolution
复制标题
DOI：
10.1016/j.jag.2014.12.015
复制
发表时间：
2015-06
期刊：
影响因子：
--
通讯作者：
Xiaotong Yang;Huiping Liu;Xiaofeng Gao
中科院分区：
文献类型：
--
作者：
Xiaotong Yang;Huiping Liu;Xiaofeng Gao
土地覆被变化信息是分析环境和生态系统变化过程和变化规律的重要依据。最近的研究已经将基于对象的图像分析，其能力，以产生有意义的地理对象的变化检测的研究。在这项研究中，我们开发了一个系统的方法来实现多类型的土地覆盖变化的目标检测与中等空间分辨率的遥感图像在北京，中国。应用最优指标因子（OIF）确定最佳变化指标，并进行卡方变换确定4类变化对象的变化阈值。提出了在特征空间中对变化向量进行聚类的方法来区分变化类型。根据准确性评估，变化/不变对象检测的总体准确率约为93.9%，总体kappa值为0.824，变化类型区分的总体准确率也达到81.67%，表明所提出的方法的有效性。
Land cover change information is crucial to analyse the process and the change patterns of environments and ecological systems. Recent studies have incorporated object-based image analysis for its ability to generate meaningful geographical objects into studies of change detection. In this research, we developed a systematic methodology to realise multi-type land cover changed object detection with medium spatial resolution remote sensing images in Beijing, China. Optimum index factor (OIF) was applied to determine the best change indicators and the chi-square transformation was carried out to determine the change threshold of the 4 classes of changed object. The clustering change vectors in the feature space were proposed to discriminate the change types. According to the accuracy assessment, the overall accuracy of changed/unchanged object detection was approximately 93.9% with an overall kappa of 0.824, and the change type discrimination also achieved an overall accuracy of 81.67%, indicating the effectiveness of the proposed method.