A Framework for Land Use Scenes Classification Based on Landscape Photos

doi:10.1109/JSTARS.2020.3028158

	A Framework for Land Use Scenes Classification Based on Landscape Photos
	Xu, Shiwu ; Zhang, Shihui ; Zeng, Jue 1,2; Li, Tingyu ; Guo, Qinghua3,4 ; Jin, Shichao 3,4,5
	2020
发表期刊	IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
ISSN	1939-1404
卷号	13 页码:6124-6141
摘要	Space-earth integrated stereoscopic mapping promotes the progress of earth observation technologies. The method which combined remote sensing images with zenith perspectives and ground-level landscape photos with slanted viewing angles improves the efficiency and accuracy of land surveys. Recently, numerous efforts have been devoted to combining deep learning and remote sensing images for the classification of land use scenes. However, improvement of classification accuracy has been limited because of the lack of sectional representation. Landscape photos can describe the cross-sections in detail. For this reason, this study constructed a land-use semantic photo dataset (LSPD) and proposed a land-use classification framework for photos (LUCFP) based on Inception-v4. LSPD was constructed through semantic planning, scene segmentation, supervised iteration transfer learning, and augmentation of photos. LSPD has 1.4 million photos collected from seven geographic regions of China, and covers 13 land-use categories and 44 semantic categories. LUCFP adapts scene segmentation based on depth of field, multisemantic block labeling, and weighting of semantic joint spatial ranges to determine the land use category. To validate LUCFP, nine semantic samples (9x3x2000 photos) were chosen from LSPD, obtaining an overall accuracy of 97.64%. The best photo cropping method was masking, which crops the boundary of the scene labeled by the photo, leading to an accuracy of 90.32%. The optimal pixel size that balances speed and accuracy is 675x675, with speed reaching 30 photos per second with an average accuracy of 93.80%. LUCFP has been successfully applied to the automatic verification of land surveys in China.
关键词	Semantics Remote sensing Image analysis Image segmentation Object recognition Machine learning Forestry Deep convolutional neural networks (DCNNs) landscape photos land survey land use scene classification
学科领域	Engineering, Electrical & Electronic ; Geography, Physical ; Remote Sensing ; Imaging Science & Photographic Technology
DOI	10.1109/JSTARS.2020.3028158
收录类别	SCI
语种	英语
WOS关键词	CONVOLUTIONAL NEURAL-NETWORKS ; SELECTION ; GRADIENT
WOS研究方向	Engineering ; Physical Geography ; Remote Sensing ; Imaging Science & Photographic Technology
WOS记录号	WOS:000579341600009
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
文献子类	Article
出版地	PISCATAWAY
EISSN	2151-1535
资助机构	China Institute of Land Surveying and Planning [2019114017]
作者邮箱	xushiwu1973@126.com ; 1284989128@qq.com ; 598722949@qq.com ; 493163208@qq.com ; qguo@ibcas.ac.cn ; jinshichao1993@gmail.com
引用统计	被引频次：7[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ibcas.ac.cn/handle/2S10CLM1/21554
专题	植被与环境变化国家重点实验室
作者单位	1.China Univ Geosci, Sch Geog & Informat Engn, Wuhan 430074, Hubei, Peoples R China 2.China Univ Geosci, Wuhan 430074, Hubei, Peoples R China 3.China Inst Land Surveying & Planning, Beijing 100035, Peoples R China 4.Chinese Acad Sci, Inst Bot, State Key Lab Vegetat & Environm Change, Beijing 100093, Peoples R China 5.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 6.Nanjing Agr Univ, Plant Phen Res Ctr, Nanjing 210095, Jiangsu, Peoples R China
推荐引用方式 GB/T 7714	Xu, Shiwu,Zhang, Shihui,Zeng, Jue,et al. A Framework for Land Use Scenes Classification Based on Landscape Photos[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,2020,13:6124-6141.
APA	Xu, Shiwu,Zhang, Shihui,Zeng, Jue,Li, Tingyu,Guo, Qinghua,&Jin, Shichao.(2020).A Framework for Land Use Scenes Classification Based on Landscape Photos.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,13,6124-6141.
MLA	Xu, Shiwu,et al."A Framework for Land Use Scenes Classification Based on Landscape Photos".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 13(2020):6124-6141.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Xu-2020-A Framework （6559KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览请求全文