How to monitor the coal mine in real time and efficiently,standardize the coal mine management and monitor the potential danger in coal mine has become a problem that the mining industry pays more and more attention to.This paper takes open-pit coal mines in Inner Mongolia Autonomous Region,Xinjiang Uygur Autonomous Region and Shanxi Province as research areas,uses high-resolution remote sensing satellite image data from China to build sample data sets of open-pit coal mines,and uses convolutional neural network to train and test the open-pit coal mine extraction model based on high-resolution remote sensing data from China,realizing automatic extraction of open-pit coal mines in the study area.