Land Cover Information Extraction Based on Daily NDVI Time Series and Multiclassifier Combination

Mathematical Problems in Engineering - Tập 2017 Số 1 - 2017
Long Zhao1, Pan Zhang2, Xiaoyi Ma2, Zhuokun Pan3
1College of Mechanical and Electronic Engineering, Northwest A&F University, Yangling, Shaanxi Province 712100
2College of Water Resources and Architectural Engineering, Northwest A&F University, Yangling, Shaanxi Province 712100
3College of Natural Resources and Environment, South China Agricultural University, Guangzhou, Guangdong Province 510000

Tóm tắt

A timely and accurate understanding of land cover change has great significance in management of area resources. To explore the application of a daily normalized difference vegetation index (NDVI) time series in land cover classification, the present study used HJ‐1 data to derive a daily NDVI time series by pretreatment. Different classifiers were then applied to classify the daily NDVI time series. Finally, the daily NDVI time series were classified based on multiclassifier combination. The results indicate that support vector machine (SVM), spectral angle mapper, and classification and regression tree classifiers can be used to classify daily NDVI time series, with SVM providing the optimal classification. The classifiers of K‐means and Mahalanobis distance are not suited for classification because of their classification accuracy and mechanism, respectively. This study proposes a method of dimensionality reduction based on the statistical features of daily NDVI time series for classification. The method can be applied to land resource information extraction. In addition, an improved multiclassifier combination is proposed. The classification results indicate that the improved multiclassifier combination is superior to different single classifier combinations, particularly regarding subclassifiers with greater differences.

Từ khóa


Tài liệu tham khảo

10.2747/1548-1603.41.3.207

10.3390/ijgi2020302

10.1016/j.ecohyd.2014.01.002

10.21082/ijas.v11n1.2010.32-40

10.1080/01431160010007051

Prakasam C., 2010, Land use and land cover change detection through remote sensing approach: a case study of kodaikanal taluk, tamil nadu, International Journal of Geomatics & Geosciences, 150

10.3390/ijgi3010110

10.1016/j.measurement.2016.11.012

10.3390/ijgi5020015

10.1109/JSTARS.2012.2183118

XieZ. ShiR. ZhuL. PengS. andChenX. Comparison of pixel-based and object-oriented land cover change detection methods Proceedings of the 23rd International Archives of the Photogrammetry Remote Sensing and Spatial Information Sciences Congress (ISPRS ′16) July 2016 Prague Czech Republic 579–583 https://doi.org/10.5194/isprsarchives-XLI-B7-579-2016 2-s2.0-84979518023.

10.1080/2150704X.2015.1019015

10.3390/ijgi4031750

AhmedB.andNomanM. A. A. Land cover classification for satellite images based on normalization technique and Artificial Neural Network Proceedings of the 1st International Conference on Computer and Information Engineering (ICCIE ′15) November 2015 Rajshahi Bangladesh 138–141 https://doi.org/10.1109/CCIE.2015.7399300 2-s2.0-84966405110.

10.3390/ijgi5030031

GiacintoG.andRoliF. Ensembles of neural networks for soft classification of remote sensing images Proceedings of the European Symposium on Intelligent Techniques March 1997 Bari Italy 166–170.

Cao D., 2007, Multi-source remote sensing classification based on Mallat fusion and residual error feature selection, Journal of Digital Information Management, 5, 130

10.1007/s12524-016-0558-5

10.1016/j.rse.2016.10.001

10.1016/0034-4257(95)00142-5

10.1080/2150704X.2014.998793

10.1016/j.rse.2015.03.031

10.3390/rs61111518

10.1080/01431161.2014.999167

10.1016/j.jag.2014.08.011

10.1016/j.jag.2014.08.001

10.11834/jrs.20165173

10.3923/javaa.2012.3668.3676

Shi Y., 2013, Thoughts on irrigation in irrigation district of fufeng, China Science and Technology Review, 33, 497

10.1016/j.landusepol.2015.10.003

10.1016/j.ecolind.2014.06.044

10.1016/j.apgeog.2014.06.002

10.1007/s12665-016-6341-7

10.4028/www.scientific.net/AMM.519-520.1182

Yuan Z., 2015, Cross comparison of the vegetation indexes between landsat TM and HJ CCD, Remote Sensing for Land & Resources, 27, 87

10.3390/rs6087610

10.1080/10106049.2015.1132483

10.1016/j.jag.2015.08.004

10.3390/ijgi3020507

10.1080/2150704X.2016.1168945

10.1016/j.rse.2016.11.023

10.1021/ac50031a048

Loh W.-Y., 1997, Split selection methods for classification trees, Statistica Sinica, 7, 815

Tian J., 2014, Land cover classification in mongolian plateau based on decision tree method: a case study in tov province, mongolia, International Journal of Geographical Information Science, 16, 460

10.1063/1.44433

10.1016/j.compag.2016.01.012

10.1117/1.JRS.8.083636

MahmonN. A. Ya′AcobN. andYusofA. L. Differences of image classification techniques for land use and land cover classification Proceedings of the IEEE 11th International Colloquium on Signal Processing and Its Applications (CSPA ′15) March 2015 Kuala Lumpur Malaysia 90–94 https://doi.org/10.1109/CSPA.2015.7225624 2-s2.0-84957928433.

10.1016/j.rse.2012.05.001

10.3390/ijgi5110199

Sandya H. B., 2013, Fuzzy rule based feature extraction and classification of time series signal, International Journal of Soft Computing & Engineering, 3, 2231

RaudysŠ.andRoliF. The behavior knowledge space fusion method: analysis of generalization error and strategies for performance improvement 2709 Proceedings of the 4th International Workshop on Multiple Classifier Systems (MCS ′03) June 2003 Guildford UK Springer Berlin Heidelberg 55–64 Lecture Notes in Computer Science https://doi.org/10.1007/3-540-44938-8_6 Zbl1040.68734.

10.1016/j.isprsjprs.2015.02.010

10.1016/j.eswa.2016.07.037

10.3390/ijgi3020540

10.1016/0020-0255(92)90012-W

10.1016/S0924-0136(02)00587-3

10.1007/s12517-016-2791-1

OuzemouJ.-E. El HartiA. El MoujahidA. BouchN. El OuazzaniR. LhissouR. andBachaouiE. M. Mapping crop based on phenological characteristics using time-series NDVI of operational land imager data in Tadla irrigated perimeter Morocco 9637 Proceedings of the Remote Sensing for Agriculture Ecosystems and Hydrology XVII September 2015 Toulouse France SPIE Remote Sensing https://doi.org/10.1117/12.2194466 2-s2.0-84961838439.