期刊论文

Xiao, Yuelong

英文

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

1939-1404

2019

12

4

1120-1133

10.1109/JSTARS.2019.2903585

Manuscript received January 24, 2019; accepted March 4, 2019. Date of publication March 28, 2019; date of current version April 17, 2019. This work was supported in part by the National Natural Science Foundation of China (41701500, 41601440, and 41601354), in part by the Natural Science Foundation of Hunan Province (2018JJ3641), in part by the Hong Kong RGC (PolyU 152201/17E), and in part by the Early-Stage Research Start-up Grants funded by Central South University (502045001 and 506030101). (Corresponding author: Yuelong Xiao.) Z. Miao, Y. Xiao, L. Wu, and J. Li are with the School of Geoscience and Info-Physics, Central South University, Changsha 410083, Hunan, China, and also with the Key Laboratory of Metallogenic Prediction of Nonferrous Metals and Geological Environment Monitoring, Central South University, Ministry of Education, Changsha 410083, Hunan, China (e-mail:,zelang.miao@outlook.com; yuelong_xiao@csu.edu.cn; awulixin@263.net; 273300175@qq.com).

本校为其他机构

Supervised learning is vital to classify impervious surface from satellite images. Despite its effectiveness, the training samples need to be provided manually, which is time consuming and labor intensive, or even impractical when classifying satellite images at the regional/global scale. This study, therefore, sets out to automatically generate training samples from open data, based on the fact that cities and urban areas are nowadays full of individual geo-referenced data, such as social network data. The proposed method consists of automatic generation of training samples based on a filteri...