Crop Classification Based on Temporal Information Using Sentinel-1 SAR Time-Series Data

被引:74
作者
Xu, Lu [1 ,2 ]
Zhang, Hong [1 ]
Wang, Chao [1 ,2 ]
Zhang, Bo [1 ]
Liu, Meng [1 ]
机构
[1] Chinese Acad Sci, Inst Remote Sensing & Digital Earth, Key Lab Digital Earth Sci, Beijing 100094, Peoples R China
[2] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
基金
中国国家自然科学基金;
关键词
Sentinel-1; Synthetic Aperture Radar (SAR); multitemporal; crop classification; temporal model; INTEGRATION; CORN;
D O I
10.3390/rs11010053
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
With the increasing temporal resolution of space-borne SAR, large amounts of intensity data are now available for continues land observations. Previous researches proved the effectiveness of multitemporal SAR in land classification, but the characterizations of temporal information were still inadequate. In this paper, we proposed a crop classification scheme, which made full use of multitemporal SAR backscattering responses. In this method, the temporal intensity models were established by the K-means clustering method. The intensity vectors were treated as input features, and the mean intensity vectors of cluster centers were regarded as the temporal models. The temporal models summarized the backscatter evolutions of crops and were utilized as the criterion for crop discrimination. The spectral similarity value (SSV) measure was introduced from hyperspectral image processing for temporal model matching. The unlabeled pixel was assigned to the class to which the temporal model with the highest similarity belonged. Two sets of Sentinel-1 SAR time-series data were used to illustrate the effectiveness of the proposed method. The comparison between SSV and other measures demonstrated the superiority of SSV in temporal model matching. Compared with the decision tree (DT) and naive Bayes (NB) classifiers, the proposed method achieved the best overall accuracies in both VH and VV bands. For most crops, it either obtained the best accuracies or achieved comparable accuracies to the best ones, which illustrated the effectiveness of the proposed method.
引用
收藏
页数:18
相关论文
共 21 条
[1]  
Arias M, 2018, INT GEOSCI REMOTE SE, P6623, DOI 10.1109/IGARSS.2018.8519005
[2]   Integration of Optical and Synthetic Aperture Radar Imagery for Improving Crop Mapping in Northwestern Benin, West Africa [J].
Forkuor, Gerald ;
Conrad, Christopher ;
Thiel, Michael ;
Ullmann, Tobias ;
Zoungrana, Evence .
REMOTE SENSING, 2014, 6 (07) :6472-6499
[3]   Mapping of Rice Varieties and Sowing Date Using X-Band SAR Data [J].
Hoa Phan ;
Thuy Le Toan ;
Bouvet, Alexandre ;
Lam Dao Nguyen ;
Tien Pham Duy ;
Zribi, Mehrez .
SENSORS, 2018, 18 (01)
[4]   Modified algorithm based on support vector machines for classification of hyperspectral images in a similarity space [J].
Hosseini, Reza Shah ;
Homayouni, Saeid ;
Safari, Reza .
JOURNAL OF APPLIED REMOTE SENSING, 2012, 6
[5]   Object-oriented crop mapping and monitoring using multi-temporal polarimetric RADARSAT-2 data [J].
Jiao, Xianfeng ;
Kovacs, John M. ;
Shang, Jiali ;
McNairn, Heather ;
Walters, Dan ;
Ma, Baoluo ;
Geng, Xiaoyuan .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2014, 96 :38-46
[6]   The sensitivity of RADARSAT-2 polarimetric SAR data to corn and soybean leaf area index [J].
Jiao, Xianfeng ;
McNairn, Heather ;
Shang, Jiali ;
Pattey, Elizabeth ;
Liu, Jiangui ;
Champagne, Catherine .
CANADIAN JOURNAL OF REMOTE SENSING, 2011, 37 (01) :69-81
[7]   Higher Order Dynamic Conditional Random Fields Ensemble for Crop Type Classification in Radar Images [J].
Kenduiywo, Benson Kipkemboi ;
Bargiel, Damian ;
Soergel, Uwe .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2017, 55 (08) :4638-4654
[8]   On the Added Value of Quad-Pol Data in a Multi-Temporal Crop Classification Framework Based on RADARSAT-2 Imagery [J].
Larranaga, Arantzazu ;
Alvarez-Mozos, Jesus .
REMOTE SENSING, 2016, 8 (04)
[9]   Early season monitoring of corn and soybeans with TerraSAR-X and RADARSAT-2 [J].
McNairn, H. ;
Kross, A. ;
Lapen, D. ;
Caves, R. ;
Shang, J. .
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2014, 28 :252-259
[10]   Integration of optical and Synthetic Aperture Radar (SAR) imagery for delivering operational annual crop inventories [J].
McNairn, Heather ;
Champagne, Catherine ;
Shang, Jiali ;
Holmstrom, Delmar ;
Reichert, Gordon .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2009, 64 (05) :434-449