Advanced Multi-Sensor Optical Remote Sensing for Urban Land Use and Land Cover Classification: Outcome of the 2018 IEEE GRSS Data Fusion Contest

被引：246

作者：

Xu, Yonghao ^{[1
]}

Du, Bo ^{[2
]}

Zhang, Liangpei ^{[1
]}

Cerra, Daniele ^{[3
]}

Pato, Miguel ^{[3
]}

Carmona, Emiliano ^{[3
]}

Prasad, Saurabh ^{[4
]}

Yokoya, Naoto ^{[5
]}

Hansch, Ronny ^{[6
]}

Le Saux, Bertrand ^{[7
]}

机构：

[1] Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan 430079, Hubei, Peoples R China

[2] Wuhan Univ, Sch Comp Sci, Wuhan 430072, Hubei, Peoples R China

[3] German Aerosp Ctr DLR, Remote Sensing Technol Inst MF PBA, D-82234 Wessling, Germany

[4] Univ Houston, Elect & Comp Engn Dept, Houston, TX 77004 USA

[5] RIKEN, Ctr Adv Intelligence Project, Tokyo 1030027, Japan

[6] Tech Univ Berlin, Comp Vis & Remote Sensing Dept, D-10587 Berlin, Germany

[7] Univ Paris Saclay, ONERA, DTIS, F-91123 Palaiseau, France

来源：

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING | 2019年 / 12卷 / 06期

基金：

中国国家自然科学基金;

关键词：

Convolutional neural networks (CNN); deep learning; hyperspectral (HS) imaging (HSI); image analysis and data fusion; multimodal; multiresolution; multisource; multispectral light detection and ranging (LiDAR); CONVOLUTIONAL NEURAL-NETWORKS; IMAGE CLASSIFICATION; HYPERSPECTRAL IMAGE; HIGH-RESOLUTION; DEEP; LIDAR; RGB;

D O I：

10.1109/JSTARS.2019.2911113

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This paper presents the scientific outcomes of the 2018 Data Fusion Contest organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society. The 2018 Contest addressed the problem of urban observation and monitoring with advanced multi-source optical remote sensing (multispectral LiDAR, hyperspectral imaging, and very high-resolution imagery). The competition was based on urban land use and land cover classification, aiming to distinguish between very diverse and detailed classes of urban objects, materials, and vegetation. Besides data fusion, it also quantified the respective assets of the novel sensors used to collect the data. Participants proposed elaborate approaches rooted in remote-sensing, and also in machine learning and computer vision, to make the most of the available data. Winning approaches combine convolutional neural networks with subtle earth-observation data scientist expertise.

引用

页码：1709 / 1724

页数：16

共 46 条

[1] Comparison of pansharpening algorithms: Outcome of the 2006 GRS-S data-fusion contest [J].

Alparone, Luciano ;

Wald, Lucien ;

Chanussot, Jocelyn ;

Thomas, Claire ;

Gamba, Paolo ;

Bruce, Lori Mann .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2007, 45 (10) :3012-3021

[2]

[Anonymous], 2018, ARXIV180306904

[3]

[Anonymous], 2014, ARXIV14120233

[4]

[Anonymous], 2016, ARXIV160803287

[5]

[Anonymous], 2015, PROC CVPR IEEE

[6]

[Anonymous], P LIV PLAN S PRAG CZ

[7] Beyond RGB: Very high resolution urban remote sensing with multimodal deep networks [J].

Audebert, Nicolas ;

Le Saux, Bertrand ;

Lefevre, Sebastien .

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2018, 140 :20-32

[8] Joint Learning from Earth Observation and OpenStreetMap Data to Get Faster Better Semantic Maps [J].

Audebert, Nicolas ;

Le Saux, Bertrand ;

Lefevre, Sebastien .

2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2017, :1552-1560

[9]

Ba LJ, 2014, ADV NEUR IN, V27

[10] Multisensor Earth Observation Image Classification Based on a Multimodal Latent Dirichlet Allocation Model [J].

Bahmanyar, Reza ;

Espinoza-Molina, Daniela ;

Datcu, Mihai .

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2018, 15 (03) :459-463

← 1 2 3 4 5 →