Research on new construction land information extraction based on deep learning: Innovation exploration of the national project of land use monitoring via remote sensing
Haiping WU1, Shicun HUANG2
1. Institute of China Land Surveying and Planning, Beijing 100035, China 2. China Center for Resources Satellite Data and Application, Beijing 100094, China
The national project of land use monitoring via remote sensing has created millions of samples of new construction land. Based on these data, the authors conducted a preliminary research on applying the deep learning technology to automatically detect new constructions in comparison with the results generated by specialists. This study demonstrates that the deep learning technology has a great potential for completing the task of monitoring land use via remote sensing. It is believed that the efficiency of the project would be increased dramatically with minor manual assistance when a recall accuracy reaches 80%.
吴海平, 黄世存. 基于深度学习的新增建设用地信息提取试验研究——全国土地利用遥感监测工程创新探索[J]. 国土资源遥感, 2019, 31(4): 159-166.
Haiping WU, Shicun HUANG. Research on new construction land information extraction based on deep learning: Innovation exploration of the national project of land use monitoring via remote sensing. Remote Sensing for Land & Resources, 2019, 31(4): 159-166.
Hinton G E, Salakhutdinov R . Reducing the dimensionality of data with neural networks[J]. Science, 2006,313(5786):504-507.
[2]
Mnih V, Hinton G E. Learning to detect roads in high resolution aerial images [C]//Proc.of 2010 European Conf.Computer Vision(ECCV2010).Piscataway,NJ:IEEE, 2010: 210-223.
Zhang X L, Chen X W, Li F , et al. Change detection method for high resolution remote sensing images using deep learning[J]. Acta Geodaeticaet Cartographica Sinica, 2017,46(8):999-1008.
Kan X, Zhang Y H, Cao T , et al. Snow cover recognition for Qinghai-Tibetan Plateau using deep learning and multispectral remote sensing[J]. Acta Geodaeticaet Cartographica Sinica, 2016,45(10):1210-1221.
Chen Y, Fan R S, Wang J X , et al. Cloud detection of ZY-3 satellite remote sensing images based on deep learning[J]. Acta Optica Sinica, 2018,38(1):354-359.
Zhu Q F, Zhao J S, Chen L S , et al. Urban construction land extraction of the remote sensing image based on depth learning[J]. Software Guide, 2018,17(10):18-21.
Zhu S H, Wang S L, Shu B R . Classification of hyperspectral remote sensing image based on deep learning[J]Urban Geotechnical Investigation & Surveying, 2017(4):84-88.
Huang X , Multiscale Texture and Shape Feature Extraction and Object-oriented Classification for Very High Resolution Remotely Sensed Imagery[D]. Wuhan:Wuhan University, 2009: 71-76.
[15]
Hinton G . A practical guide to training restricted Boltzmann machines[J]. Momentum, 2010,9(1):926.
[16]
Larochelle H, Bengio Y, Louradour J , et al. Exploring strategies for training deep neural networks[J]. Journal of Machine Learning Research, 2009,10(1):1-40.