The content of this article comes from the "Surveying and Mapping Bulletin" No. 3 of 2024, drawing review number: GS Jing (2024) No. 0499
Extraction of typical natural resource elements based on multi-source high-resolution remote sensing images
Ma Jinshan1, Jia Guohuan1, Zhang Sai2, Zhang Jiong1
1. Xining Institute of Land Surveying and Planning Co., Ltd., Xining 810000, China; 2. Zhongke Beiwei (Beijing) Technology Co., Ltd., Beijing 100192
Keywords: high resolution, convolutional neural network, deep learning, remote sensing interpretation
Citation Format: MA Jinshan, JIA Guohuan, ZHANG Sai, et al. Extraction of Typical Natural Resources Elements Based on Multi-source High-resolution Remote Sensing Images[J]. Bulletin of Surveying and Mapping, 2024(3): 123-126. DOI: 10.13474/j.cnki.11-2246.2024.0321
Abstract:Taking advantage of the characteristics of high-resolution remote sensing data with high spatial resolution, this paper uses 0.3 and 1m multi-source high-resolution remote sensing images in Xining City, Qinghai Province as data sources, and extracts typical natural resource elements based on convolutional neural network deep learning algorithm. The results show that the accuracy rate of 0.3m remote sensing images extracting cultivated land and forest land is more than 85%, and the recall rate is more than 89%. The accuracy rate of 1m remote sensing image extraction of cultivated land and forest land is more than 90%, and the recall rate is more than 91%, and the research results can be used for intelligent extraction of typical elements of natural resources in Xining City.
About author:MA Jinshan (1992—), male, engineer, main research direction is satellite remote sensing image interpretation algorithm. E-mail:[email protected]
First trial: Ji Yinxiao review: Song Qifan
Final Judge: Jin Jun
information