文献类型：期刊文献

英文题名：Mask R-CNN based automated identification and extraction of oil well sites

作者：He, Hongjie[1];Xu, Hongzhang[1];Zhang, Ying[2];Gao, Kyle[1];Li, Huxiong[3];Ma, Lingfei[4];Li, Jonathan[1,5]

机构：[1]Univ Waterloo, Dept Geog & Environm Management, Geospatial Sensing & Data Intelligence Lab, 200 Univ Ave West, Waterloo, ON N2L 3G1, Canada;[2]Nat Resources Canada, Canada Ctr Remote Sensing, 560 Rochester St, Ottawa, ON K1S 5H4, Canada;[3]Shaoxing Univ, Dept Comp Sci & Engn, Shaoxing 312000, Peoples R China;[4]Cent Univ Finance & Econ, Sch Stat & Math, Beijing 102206, Peoples R China;[5]Univ Waterloo, Dept Syst Design Engn, Waterloo, ON N2L 3G1, Canada

年份：2022

卷号：112

外文期刊名：INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION

收录：SCI-EXPANDED(收录号：WOS:000849817900002)、、Scopus(收录号：2-s2.0-85132894152)、WOS

基金：This study was partially funded by the Emerging Interdisciplinary Project of Central University of Finance and Economics, and also partially funded by the Remote Sensing for Cumulative Effects program of Canada Centre for Remote Sensing, National Resources Canada. The first author also acknowledges the China Scholarship Council for their support via a doctoral scholarship (No. 201906180088) . The group of the students at the Geospatial Sensing and Data Intelligence Laboratory, Faculty of Environment, University of Waterloo, including Siyu Li, Wenxuan Zhu, Yiqing Wu, Yuxiang Fang, Longxiang Xu, and Charlotte Pan are acknowledged for their contributions to labeling data. We also acknowledge the Planet Inc and the Maxar Technologies Inc for providing satellite images used in this work.

语种：英文

外文关键词：Land disturbance; Oil well sites; OWS Mask R -CNN; Multi sensors; RCAN

外文摘要：Fine-scale land disturbances due to mining development modify the land surface cover and have cumulative detrimental impacts on the environment. Understanding the distribution of fine-scale land disturbances related to mining activities, such as oil well sites, in mining regions is of vital importance to sustainable mining development. For efficient mapping, automated identification and extraction of the oil well sites using highresolution satellite images are required. In this work, we proposed the Oil Well Site extraction (OWS) Mask RCNN based on the original Mask R-CNN (Region-based Convolutional Neural Networks), to accurately extract well sites using multi-sensor remote sensing images. For improvement of mapping efficiency, two modifications were made to Mask R-CNN: (1) replacing the backbone of Mask R-CNN with D-LinkNet, and (2) adding a semantic segmentation branch to Mask R-CNN to force the whole network to focus on the relationship between line objects and oil well sites. As imagery data were from multiple sensors (RapidEye 2/3 and WorldView 3), a pretrained Residual Channel Attention Network (RCAN) was applied to super-resolve the images with different resolutions. Several key spatial features, such as nearby roads and area size, have also been used in the oil well site mapping process. The experimental results indicate that our OWS Mask R-CNN considerably improves the average precision (AP) and the F1 score of Mask R-CNN from 51.26% and 25.7% to 60.93% and 61.59%, respectively.