ADAPTIVE SPATIAL SAMPLING WITH ACTIVE RANDOM FOREST FOR OBJECT-ORIENTED LANDSLIDE MAPPING

被引：3

作者：

Stumpf, A. ^{[1
,3
]}

Lachiche, N. ^{[2
,4
]}

Kerle, N. ^{[3
]}

Malet, Jean-Philippe ^{[2
]}

Puissant, A. ^{[1
]}

机构：

[1] Univ Strasbourg, Lab Image, CNRS ERL 7230, 3 Rue Argonne, F-67083 Strasbourg, France

[2] Univ Strasbourg EOST, CNRS UMR 7516, Inst Phys Globe, F-67084 Strasbourg, France

[3] Univ Twente, ITC Fac Geo Informat Sci & Earth Observ, Dept Earth Syst Anal, NL-7500 AA Enschede, AA, Netherlands

[4] Univ Strasbourg, CNRS UMR 7005, Comp Sci & Remote Sensing Lab, Image Sci, F-67412 Illkirch Graffenstaden, France

来源：

2012 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS) | 2012年

基金：

欧盟第七框架计划;

关键词：

active learning; spatial sampling landslide inventory mapping; object-oriented image analysis;

D O I：

10.1109/IGARSS.2012.6351630

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：

Active learning (AL) is a powerful framework to reduce labeling costs in supervised classification. However, spatial constraints on the sampling design have not yet received much attention and still pose problems for the application of AL on remote sensing data. In this study such issues are addressed in the context of landslide inventory mapping and it is shown that region-based query functions that focus the labeling efforts on compact spatial batches may provide several advantages over point-wise queries.

引用

页码：87 / 90

页数：4

共 50 条

[1] Object-oriented mapping of urban trees using Random Forest classifiers
Puissant, Anne
Rougier, Simon
Stumpf, Andre
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2014, 26 : 235 - 245
[2] Object-Oriented Change Detection for Landslide Rapid Mapping
Lu, Ping
Stumpf, Andre
Kerle, Norman
Casagli, Nicola
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2011, 8 (04) : 701 - 705
[3] An object-oriented approach to urban forest mapping in Phoenix
Walker, Jason S.
Briggs, John M.
PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING, 2007, 73 (05): : 577 - 583
[4] Object-oriented mapping of landslides using Random Forests
Stumpf, Andre
Kerle, Norman
REMOTE SENSING OF ENVIRONMENT, 2011, 115 (10) : 2564 - 2577
[5] ARTOO: Adaptive Random Testing for Object-Oriented Software
Ciupa, Ilinca
Leitner, Andreas
Oriol, Manuel
Meyer, Bertrand
ICSE'08 PROCEEDINGS OF THE THIRTIETH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING, 2008, : 71 - 80
[6] Combining Random Forests and object-oriented analysis for landslide mapping from very high resolution imagery
Stumpf, Andre
Kerle, Norman
1ST CONFERENCE ON SPATIAL STATISTICS 2011 - MAPPING GLOBAL CHANGE, 2011, 3 : 123 - 129
[7] Object-Oriented Landslide Mapping Using ZY-3 Satellite Imagery, Random Forest and Mathematical Morphology, for the Three-Gorges Reservoir, China
Chen, Tao
Trinder, John C.
Niu, Ruiqing
REMOTE SENSING, 2017, 9 (04)
[8] Object-Oriented Mapping as a Tool for the Assessment of Landslide Hazard in Higly Urbanized Areas
Dramis, Francesco
Guida, Domenico
Valiante, Mario
FRONTIERS IN EARTH SCIENCE, 2022, 10
[9] The object-oriented design of KROSS: An object-oriented spatial database system
Kim, YH
Kim, MS
Kwon, SH
Jeong, CS
DATABASE AND EXPERT SYSTEMS APPLICATIONS, 1996, 1134 : 603 - 612
[10] Object-oriented classification of QuickBird data for mapping seagrass spatial structure
Urbanski, Jacek Andrzej
Mazur, Aleksandra
Janas, Urszula
OCEANOLOGICAL AND HYDROBIOLOGICAL STUDIES, 2009, 38 (01) : 27 - 43

← 1 2 3 4 5 →