DOI: 10.18178/wcse.2019.06.144
Environmental Monitoring of Electric Power Transmission Corridor Based on Satellite Remote Sensing
Abstract— With the rapid development of national economy, the current power industry and power
technology have made great progress in recent years. It is of vital importance to ensure the safety of electric
power transmission corridors and related facilities. At present, the inspection of electric power transmission
corridors mainly relies on manpower in China, which is not only of great labor intensity, high labor cost and
low efficiency. Therefore, this paper proposes a method of surveying typical environmental features of
electric power transmission corridor based on high-resolution remote sensing image. At first, the normalized
differential vegetation index (NDVI) and normalized difference water index (NDWI) time series were
constructed using multi-period remote sensing images in the research area. Then harmonic analysis is applied
to the indexes time series to obtain the harmonic characteristics. Finally, support vector machine (SVM) was
used to classify five typical environmental features including artificial active area, water, bare land, farmland
and forest, The overall classification accuracy is 90.29%, which is better than the result only using indexes
series for classification.
Index Terms— Electric Power Transmission Corridors; Ground object inspection; Remote sensing image;
Index time series; Harmonic analys
Yang zhi, Wei liguang, Fei xiangze, Li chuang, Zhao binbin, Ma xiao
State Grid Corporation of China, CHINA
Yang zhi, Ou wenhao, Fei xiangze, Li chuang, Zhao binbin, Ma xiao
China Electric Power Research Institute, CHINA
Wei liguang
Beijing Piesat Information Technology Co. Ltd, CHINA
Cite: Yang zhi, Ou wenhao, Wei liguang, Fei xiangze, Li chuang, Zhao binbin,Ma xiao, "Environmental Monitoring of Electric Power Transmission Corridor Based on Satellite Remote Sensing," Proceedings of 2019 the 9th International Workshop on Computer Science and Engineering, pp. 961-969, Hong Kong, 15-17 June, 2019.