摘要
Abstract
With the development of remote sensing technology,the demand for high-resolution image classification is increasing.This paper focuses on the remote sensing image classification method integrating OBIA and minimum distance classification algorithms,taking Ningxia Zhongwei images as the research area,and after a series of preprocessing,the FNEA algorithm is used to segment the images at multiple scales,and the optimal parameters are selected based on the"trial and error method".Then,the Eigenspace is constructed,the minimum distance algorithm is used to classify and the classification results are optimized through the context semantic relationship.The results show that the overall accuracy is improved from 90.65%to 92.99%,and the Kappa coefficient is increased from 0.88 to 0.91.However,due to the influence of image segmentation and sample selection,it is necessary to explore the optimization strategy of segmentation parameters and key features in the future,so as to promote the improvement of remote sensing image classification technology and serve the monitoring and management of resources in multiple fields.关键词
遥感影像分类/OBIA/最小距离分类算法/影像分割/特征空间Key words
remote sensing image classification/OBIA/minimum distance classification algorithm/image segmentation/eigen space分类
信息技术与安全科学
