基于卷积神经网络的高分遥感影像露天采矿场识别
|
摘要
矿山环境监测常用遥感影像,研究卷积神经网络(convolutional neural network,CNN)对高分遥感影像露天采矿场识别有利于提高监测效率.针对因训练数据量小而导致CNN对露天采矿场识别精度不高的问题,采用了3种迁移学习方案对CNN的预训练模型进行训练与对比分析,发现冻结CNN预训练模型底层参数并微调高层参数的迁移学习方法训练效果最佳,在验证数据上的生产者精度与用户精度均超过87%.实验结果表明,本方法训练的CNN能提升高分遥感影像中露天采矿场的识别效率,可作为遥感解译露天采矿场中的辅助手段.
The application of remote sensing is a commonly used approach to environmental monitoring in mine areas. The research on convolutional neural network(CNN) for recognition of opencast mining area in high-resolution remote sensing image could help to improve monitoring efficiency.This paper focused on the problem of low classification accuracy of opencast mining area based on CNN due to insufficient trained datasets, the experiment is designed with three types of transfer learning methods and tested in different pre-trained CNN models. The analysis shows that by contrast, fixed lower layers' parameters in pre-trained CNN models and fine-tune higher layers' parameters is the optimal training method, it achieved over 87% in both producer's accuracy and user's accuracy. This experimental results indicate that opencast mining area could be effectively recognized in high-resolution imagery based on this training method, therefore, the CNN which trained by this method can be used as an aid in remote sensing interpretation of opencast mining area.
The application of remote sensing is a commonly used approach to environmental monitoring in mine areas. The research on convolutional neural network(CNN) for recognition of opencast mining area in high-resolution remote sensing image could help to improve monitoring efficiency.This paper focused on the problem of low classification accuracy of opencast mining area based on CNN due to insufficient trained datasets, the experiment is designed with three types of transfer learning methods and tested in different pre-trained CNN models. The analysis shows that by contrast, fixed lower layers' parameters in pre-trained CNN models and fine-tune higher layers' parameters is the optimal training method, it achieved over 87% in both producer's accuracy and user's accuracy. This experimental results indicate that opencast mining area could be effectively recognized in high-resolution imagery based on this training method, therefore, the CNN which trained by this method can be used as an aid in remote sensing interpretation of opencast mining area.
引文
Bengio,Y.,2012.Deep Learning of Representations for Unsupervised and Transfer Learning.Proceedings of Machine Learning Research,27:17-36.
Bengio,Y.,Bastien,F.,Bergeron,A.,et al.,2011.Deep Learners Benefit More from Out-of-Distribution Examples.Proceedings of Machine Learning Research,15:164-172.
Cao,L.L.,Li,H.T.,Han,Y.S.,et al.,2016.Application of Convolutional Neural Networks in Classification of High Resolution Remote Sensing Imagery.Science of Surveying and Mapping,41(9):170-175(in Chinese with English abstract).
Caruana,R., 1994.Learning Many Related Tasks at the Same Time with Backpropagation.Advances in Neural Information Processing Systems,7:657-664.
Chatfield,K.,Simonyan,K.,Vedaldi,A.,et al.,2014.Return of the Devil in the Details:Delving Deep into Convolutional Nets.Proceedings of the British Machine Vision Conference:Machine Leaning, Nottingham.
Demirel,N.,Emil,M.K.,Duzgun,H.S.,2011.Surface Coal Mine Area Monitoring Using Multi-Temporal High-Resolution SatelliteImagery.International Journal of Coal Geology,86(1):3-11.https://doi.org/10.1016/j.coal.2010.11.010
He,K.,Zhang,X.,Ren,S.,et al.,2015.Deep Residual Learning for Image Recognition.Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition,Las Vegas,770-778.
Hou,F.,Hu,Z.L.,2012.Remote Sensing Information Extraction of Typical Surface Objects in a Coal Mining Area Based on MultipleScale Segmentation.Bulletin of Surveying and Mapping,(1):22-25(in Chinese).
Jing,P.P.,Li,B.,Jia,Z.R.,et al.,2017.Research on Information Extraction Based on UAV Remote Sensing.Geomatics&Spatial Information Technology,40(12):77-80(in Chinese with English abstract).
Kang,R.F.,2017.Remote Sensing Monitoring and Evaluation of Mine Geological Environment in Ji'nan Open Pit Mining Area(Dissertation). Shandong Normal University,Jinan(in Chinese with English abstract).
Li,X.,2017.Open-Pit Mining Mine Geological Environment Treatment and Recovery.World Nonferrous Metals,(4):126-128(in Chinese with English abstract).
Pan,S.J.,Yang,Q.,2010.A Survey on Transfer Learning.IEEE Transactions on Knowledge and Data Engineering,22(10):1345-1359. https://doi.org/10.1109/tkde.2009.191
Qi,X.Y.,Yang,W.N.,Shao,H.Y.,et al.,2008.An Automatic Extraction Method of Mining Area Expanding Remote Sensing Image:A Study on Panzhihua Vanadium Titanium Magnetite Ore.Science of Surveying and Mapping,33(3):76-78(in Chinese with English abstract).
Razavian,A.S.,Azizpour,H.,Sullivan,J.,et al.,2014.CNN Features Offthe-Shelf:An Astounding Baseline for Recognition.Proceedings of2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops,Columbus,512-519.
Sun,M.,Yang,C.L.,2012.Geological Environment Problems and Countermeasures of Mining Areas in Hebi City. West-China Exploration Engineering,24(11):80-82(in Chinese).
Xu,S.H.,Mu,X.D.,Zhao,P.,et al.,2016.Scene Classification of Remote Sensing Image Based on Multi-scale Feature and Deep Neural Network.Acta Geodaetica et Cartographica Sinica,45(7):834-840(in Chinese with English abstract).
Yosinski,J.,Clune,J.,Bengio,Y.,et al.,2014.How Transferable are Features in Deep Neural Networks?Proceeding NIPS'14,2:33203-3328.
Zhu,X.X.,Tuia,D.,Mou,L.C.,et al.,2017.Deep Learning in Remote Sensing:A Comprehensive Review and List of Resources.IEEE Geoscience and Remote Sensing Magazine,5(4):836. https://doi.org/10.1109/mgrs.2017.2762307
Zhu,Z.J.,2010.Study on Mine Area Information Extraction Based on Object-Oriented High-Resolution Remote Sensing Image Classification and Its Application(Dissertation).China University of Geosciences,Beijing(in Chinese with English abstract).
曹林林,李海涛,韩颜顺,等,2016.卷积神经网络在高分遥感影像分类中的应用.测绘科学,41(9):170-175.
侯飞,胡召玲,2012.基于多尺度分割的煤矿区典型地物遥感信息提取.测绘通报,(1):22-25.
荆平平,李兵,贾宗仁,等,2017.基于无人机遥感的信息提取研究.测绘与空间地理信息,40(12):77-80.
康日斐,2017.济南市露天开采集中区矿山地质环境遥感监测与环境评价研究(硕士学位论文).济南:山东师范大学.
李夏,2017.露天采矿矿山地质环境治理与恢复研究.世界有色金属,(4):126-128.
漆小英,杨武年,邵怀勇,等,2008.矿山扩展遥感信息自动提取方法研究——以攀枝花钒钛磁铁矿为例.测绘科学,33(3):76-78.
孙淼,杨春丽,2012.鹤壁市矿山地质环境问题及防治对策.西部探矿工程,24(11):80-82.
许夙晖,慕晓冬,赵鹏,等,2016.利用多尺度特征与深度网络对遥感影像进行场景分类.测绘学报,45(7):834-840.
祝振江,2010.基于面向对象分类法的高分辨率遥感影像矿山信息提取应用研究(硕士学位论文).北京:中国地质大学.
Bengio,Y.,Bastien,F.,Bergeron,A.,et al.,2011.Deep Learners Benefit More from Out-of-Distribution Examples.Proceedings of Machine Learning Research,15:164-172.
Cao,L.L.,Li,H.T.,Han,Y.S.,et al.,2016.Application of Convolutional Neural Networks in Classification of High Resolution Remote Sensing Imagery.Science of Surveying and Mapping,41(9):170-175(in Chinese with English abstract).
Caruana,R., 1994.Learning Many Related Tasks at the Same Time with Backpropagation.Advances in Neural Information Processing Systems,7:657-664.
Chatfield,K.,Simonyan,K.,Vedaldi,A.,et al.,2014.Return of the Devil in the Details:Delving Deep into Convolutional Nets.Proceedings of the British Machine Vision Conference:Machine Leaning, Nottingham.
Demirel,N.,Emil,M.K.,Duzgun,H.S.,2011.Surface Coal Mine Area Monitoring Using Multi-Temporal High-Resolution SatelliteImagery.International Journal of Coal Geology,86(1):3-11.https://doi.org/10.1016/j.coal.2010.11.010
He,K.,Zhang,X.,Ren,S.,et al.,2015.Deep Residual Learning for Image Recognition.Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition,Las Vegas,770-778.
Hou,F.,Hu,Z.L.,2012.Remote Sensing Information Extraction of Typical Surface Objects in a Coal Mining Area Based on MultipleScale Segmentation.Bulletin of Surveying and Mapping,(1):22-25(in Chinese).
Jing,P.P.,Li,B.,Jia,Z.R.,et al.,2017.Research on Information Extraction Based on UAV Remote Sensing.Geomatics&Spatial Information Technology,40(12):77-80(in Chinese with English abstract).
Kang,R.F.,2017.Remote Sensing Monitoring and Evaluation of Mine Geological Environment in Ji'nan Open Pit Mining Area(Dissertation). Shandong Normal University,Jinan(in Chinese with English abstract).
Li,X.,2017.Open-Pit Mining Mine Geological Environment Treatment and Recovery.World Nonferrous Metals,(4):126-128(in Chinese with English abstract).
Pan,S.J.,Yang,Q.,2010.A Survey on Transfer Learning.IEEE Transactions on Knowledge and Data Engineering,22(10):1345-1359. https://doi.org/10.1109/tkde.2009.191
Qi,X.Y.,Yang,W.N.,Shao,H.Y.,et al.,2008.An Automatic Extraction Method of Mining Area Expanding Remote Sensing Image:A Study on Panzhihua Vanadium Titanium Magnetite Ore.Science of Surveying and Mapping,33(3):76-78(in Chinese with English abstract).
Razavian,A.S.,Azizpour,H.,Sullivan,J.,et al.,2014.CNN Features Offthe-Shelf:An Astounding Baseline for Recognition.Proceedings of2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops,Columbus,512-519.
Sun,M.,Yang,C.L.,2012.Geological Environment Problems and Countermeasures of Mining Areas in Hebi City. West-China Exploration Engineering,24(11):80-82(in Chinese).
Xu,S.H.,Mu,X.D.,Zhao,P.,et al.,2016.Scene Classification of Remote Sensing Image Based on Multi-scale Feature and Deep Neural Network.Acta Geodaetica et Cartographica Sinica,45(7):834-840(in Chinese with English abstract).
Yosinski,J.,Clune,J.,Bengio,Y.,et al.,2014.How Transferable are Features in Deep Neural Networks?Proceeding NIPS'14,2:33203-3328.
Zhu,X.X.,Tuia,D.,Mou,L.C.,et al.,2017.Deep Learning in Remote Sensing:A Comprehensive Review and List of Resources.IEEE Geoscience and Remote Sensing Magazine,5(4):836. https://doi.org/10.1109/mgrs.2017.2762307
Zhu,Z.J.,2010.Study on Mine Area Information Extraction Based on Object-Oriented High-Resolution Remote Sensing Image Classification and Its Application(Dissertation).China University of Geosciences,Beijing(in Chinese with English abstract).
曹林林,李海涛,韩颜顺,等,2016.卷积神经网络在高分遥感影像分类中的应用.测绘科学,41(9):170-175.
侯飞,胡召玲,2012.基于多尺度分割的煤矿区典型地物遥感信息提取.测绘通报,(1):22-25.
荆平平,李兵,贾宗仁,等,2017.基于无人机遥感的信息提取研究.测绘与空间地理信息,40(12):77-80.
康日斐,2017.济南市露天开采集中区矿山地质环境遥感监测与环境评价研究(硕士学位论文).济南:山东师范大学.
李夏,2017.露天采矿矿山地质环境治理与恢复研究.世界有色金属,(4):126-128.
漆小英,杨武年,邵怀勇,等,2008.矿山扩展遥感信息自动提取方法研究——以攀枝花钒钛磁铁矿为例.测绘科学,33(3):76-78.
孙淼,杨春丽,2012.鹤壁市矿山地质环境问题及防治对策.西部探矿工程,24(11):80-82.
许夙晖,慕晓冬,赵鹏,等,2016.利用多尺度特征与深度网络对遥感影像进行场景分类.测绘学报,45(7):834-840.
祝振江,2010.基于面向对象分类法的高分辨率遥感影像矿山信息提取应用研究(硕士学位论文).北京:中国地质大学.