Lake Ice-Water Classification of RADARSAT-2 Images by Integrating IRGS Segmentation with Pixel-Based Random Forest Labeling

被引:35
|
作者
Hoekstra, Marie [1 ]
Jiang, Mingzhe [2 ]
Clausi, David A. [2 ]
Duguay, Claude [1 ,3 ]
机构
[1] Univ Waterloo, Dept Geog & Environm Management, Waterloo, ON N2L3G1, Canada
[2] Univ Waterloo, Dept Syst Design Engn, Waterloo, ON N2L3G1, Canada
[3] H2O Geomat Inc, Waterloo, ON N2L1S7, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
classification; gray-level co-occurrence matrix (GLCM); iterative region growing using semantics (IRGS); RADARSAT-2; lake ice; random forest (RF); support vector machine (SVM); SAR; COVER;
D O I
10.3390/rs12091425
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Changes to ice cover on lakes throughout the northern landscape has been established as an indicator of climate change and variability, expected to have implications for both human and environmental systems. Monitoring lake ice cover is also required to enable more reliable weather forecasting across lake-rich northern latitudes. Currently, the Canadian Ice Service (CIS) monitors lakes using synthetic aperture radar (SAR) and optical imagery through visual interpretation, with total lake ice cover reported weekly as a fraction out of ten. An automated method of classification would allow for more detailed records to be delivered operationally. In this research, we present an automatic ice-mapping approach which integrates unsupervised segmentation from the Iterative Region Growing using Semantics (IRGS) algorithm with supervised random forest (RF) labeling. IRGS first locally segments homogeneous regions in an image, then merges similar regions into classes across the entire scene. Recently, these output regions were manually labeled by the user to generate ice maps, or were labeled using a Support Vector Machine (SVM) classifier. Here, three labeling methods (Manual, SVM, and RF) are applied after IRGS segmentation to perform ice-water classification on 36 RADARSAT-2 scenes of Great Bear Lake (Canada). SVM and RF classifiers are also tested without integration with IRGS. An accuracy assessment has been performed on the results, comparing outcomes with author-generated reference data, as well as the reported ice fraction from CIS. The IRGS-RF average classification accuracy for this dataset is 95.8%, demonstrating the potential of this automated method to provide detailed and reliable lake ice cover information operationally.
引用
收藏
页数:21
相关论文
共 9 条
  • [1] Operational algorithm for ice-water classification on dual-polarized RADARSAT-2 images
    Zakhvatkina, Natalia
    Korosov, Anton
    Muckenhuber, Stefan
    Sandven, Stein
    Babiker, Mohamed
    CRYOSPHERE, 2017, 11 (01): : 33 - 46
  • [2] Sea Ice-Water Classification of RADARSAT-2 Imagery Based on Residual Neural Networks (ResNet) with Regional Pooling
    Jiang, Mingzhe
    Xu, Linlin
    Clausi, David A.
    REMOTE SENSING, 2022, 14 (13)
  • [3] Pixel-based classification algorithm for mapping urban footprints from radar data: a case study for RADARSAT-2
    Taubenboeck, H.
    Felbier, A.
    Esch, T.
    Roth, A.
    Dech, S.
    CANADIAN JOURNAL OF REMOTE SENSING, 2012, 38 (03) : 211 - 222
  • [4] Antarctic Sea-Ice Classification Based on Conditional Random Fields From RADARSAT-2 Dual-Polarization Satellite Images
    Zhu, Tingting
    Li, Fei
    Heygster, Georg
    Zhang, Shengkai
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2016, 9 (06) : 2451 - 2467
  • [5] Pixel-based crop classification in Peru from Landsat 7 ETM+ images using a Random Forest model
    Tatsumi, Kenichi
    Yamashiki, Yosuke
    Morales Morante, Anggie Karolin
    Ramos Fernandez, Lia
    Apaclla Nalvarte, Ricardo
    JOURNAL OF AGRICULTURAL METEOROLOGY, 2016, 72 (01) : 1 - 11
  • [6] A Comparative Analysis of Object-Based and Pixel-Based Classification of RADARSAT-2 C-Band and Optical Satellite Data for Mapping Shoreline Types in the Canadian Arctic
    Demers, Anne-Marie
    Banks, Sarah N.
    Pasher, Jon
    Duffe, Jason
    Laforest, Sonia
    CANADIAN JOURNAL OF REMOTE SENSING, 2015, 41 (01) : 1 - 19
  • [7] Mapping irrigated, rainfed and paddy croplands from time-series Sentinel-2 images by integrating pixel-based classification and image segmentation on Google Earth Engine
    Xing, Huaqiao
    Chen, Bingyao
    Feng, Yongyu
    Ni, Yuanlong
    Hou, Dongyang
    Wang, Xue
    Kong, Yawei
    GEOCARTO INTERNATIONAL, 2022, 37 (26) : 13291 - 13310
  • [8] Consistent ice and open water classification combining historical synthetic aperture radar satellite images from ERS-1/2, Envisat ASAR, RADARSAT-2 and Sentinel-1A/B
    Johansson, A. Malin
    Malnes, Eirik
    Gerland, Sebastian
    Cristea, Anca
    Doulgeris, Anthony P.
    Divine, Dmitry, V
    Pavlova, Olga
    Lauknes, Tom Rune
    ANNALS OF GLACIOLOGY, 2020, 61 (82) : 40 - 50
  • [9] Identification and Counting of European Souslik Burrows from UAV Images by Pixel-Based Image Analysis and Random Forest Classification: A Simple, Semi-Automated, yet Accurate Method for Estimating Population Size
    Gedeon, Csongor, I
    Arvai, Matyas
    Szatmari, Gabor
    Brevik, Eric C.
    Takats, Tunde
    Kovacs, Zsofia A.
    Meszaros, Janos
    REMOTE SENSING, 2022, 14 (09)