基于ESP2的面向对象分类方法在高铁线路提取中的应用
Application of Object-Oriented Classification Based on ESP2 in High-Speed Railway Line Extraction
周秀芳 1龚循强 2李泽春 3邱万锦 3孙坤3
作者信息
- 1. 东华理工大学江西生态文明建设制度研究中心,江西南昌,330013
- 2. 东华理工大学自然资源部环鄱阳湖区域矿山环境监测与治理重点实验室,江西南昌,330013;东华理工大学测绘工程学院,江西南昌,330013
- 3. 东华理工大学测绘工程学院,江西南昌,330013
- 折叠
摘要
以高分二号影像为原始数据,采用eCognition软件中的ESP2工具预测影像最佳分割尺度参数,通过k近邻、分类与回归树、支持向量机3种面向对象分类方法提取高铁线路,并引入总体精度、Kappa系数、完整率、正确率和提取质量5个指标对提取的高铁线路进行精度评价.结果表明,3种方法的5个评定指标均在0.9以上,这表明面向对象分类方法在高铁线路提取中具有可行性.
Abstract
The ESP2 tool in eCognition software is used in combination with the GF-2 images as the original data to predict the optimal segmentation scale parameters of the image,and the high-speed railway lines are extracted through three object-ori-ented classification methods,i. e.,k-nearest neighbor,classi-fication and regression tree,and support vector machine. Five indicators of overall accuracy,Kappa coefficient,completion rate,correct rate and extraction quality are introduced to evaluate the accuracy of the extracted high-speed railway lines. The experimental results show that the five mentioned extraction indexes of the three methods are all above 0.9,which indicates that the object-oriented classification method is feasible in the field of high-speed railway line extraction.
关键词
面向对象分类/高铁线路提取/ESP2/影像分割/精度评定Key words
object-oriented classification/high-speed railway lines extraction/estimation of scale parameter 2/image segmentation/accuracy evaluation引用本文复制引用
基金项目
江西生态文明建设制度研究中心开放基金(JXST2104)
国家自然科学基金(42101457)
出版年
2024
NETL
NSTL
万方数据