Next Article in Journal
A Novel Hyperspectral Image Classification Pattern Using Random Patches Convolution and Local Covariance
Next Article in Special Issue
A Robust Rule-Based Ensemble Framework Using Mean-Shift Segmentation for Hyperspectral Image Classification
Previous Article in Journal
Remote Sensing of Environmental Changes in Cold Regions: Methods, Achievements and Challenges
Previous Article in Special Issue
Operational Large-Scale Segmentation of Imagery Based on Iterative Elimination
Open AccessArticle

Direct, ECOC, ND and END Frameworks—Which One Is the Best? An Empirical Study of Sentinel-2A MSIL1C Image Classification for Arid-Land Vegetation Mapping in the Ili River Delta, Kazakhstan

1
State Key Laboratory of Desert and Oasis Ecology, Xinjiang Institute of Ecology and Geography, CAS, Urumqi 830011, China
2
Research Center for Ecology and Environment of Central Asia, CAS, Urumqi 830011, China
3
University of Chinese Academy of Sciences, Beijing 100049, China
4
RIKEN Center for Advanced Intelligence Project, Tokyo 103-0027, Japan
5
Department of Geographical Information Science, Nanjing University, Nanjing 210093, China
6
College of Surveying and Geoinformatics, Tongji University, Shanghai 200092, China
7
Faculty of Geography and Environmental Sciences, Al-Farabi Kazakh National University, Almaty 050040, Kazakhstan
8
Research Center for Ecology and Environment of Central Asia (Almaty), CAS, Almaty 050060, Kazakhstan
9
U.U. Uspanov Kazakh Research Institute of Soil Science and Agrochemistry, Almaty 050060, Kazakhstan
*
Author to whom correspondence should be addressed.
Remote Sens. 2019, 11(16), 1953; https://doi.org/10.3390/rs11161953
Received: 30 July 2019 / Revised: 15 August 2019 / Accepted: 16 August 2019 / Published: 20 August 2019
(This article belongs to the Special Issue Image Segmentation for Environmental Monitoring)
To facilitate the advances in Sentinel-2A products for land cover from Moderate Resolution Imaging Spectroradiometer (MODIS) and Landsat imagery, Sentinel-2A MultiSpectral Instrument Level-1C (MSIL1C) images are investigated for large-scale vegetation mapping in an arid land environment that is located in the Ili River delta, Kazakhstan. For accurate classification purposes, multi-resolution segmentation (MRS) based extended object-guided morphological profiles (EOMPs) are proposed and then compared with conventional morphological profiles (MPs), MPs with partial reconstruction (MPPR), object-guided MPs (OMPs), OMPs with mean values (OMPsM), and object-oriented (OO)-based image classification techniques. Popular classifiers, such as C4.5, an extremely randomized decision tree (ERDT), random forest (RaF), rotation forest (RoF), classification via random forest regression (CVRFR), ExtraTrees, and radial basis function (RBF) kernel-based support vector machines (SVMs) are adopted to answer the question of whether nested dichotomies (ND) and ensembles of ND (END) are truly superior to direct and error-correcting output code (ECOC) multiclass classification frameworks. Finally, based on the results, the following conclusions are drawn: 1) the superior performance of OO-based techniques over MPs, MPPR, OMPs, and OMPsM is clear for Sentinel-2A MSIL1C image classification, while the best results are achieved by the proposed EOMPs; 2) the superior performance of ND, ND with class balancing (NDCB), ND with data balancing (NDDB), ND with random-pair selection (NDRPS), and ND with further centroid (NDFC) over direct and ECOC frameworks is not confirmed, especially in the cases of using weak classifiers for low-dimensional datasets; 3) from computationally efficient, high accuracy, redundant to data dimensionality and easy of implementations points of view, END, ENDCB, ENDDB, and ENDRPS are alternative choices to direct and ECOC frameworks; 4) surprisingly, because in the ensemble learning (EL) theorem, “weaker” classifiers (ERDT here) always have a better chance of reaching the trade-off between diversity and accuracy than “stronger” classifies (RaF, ExtraTrees, and SVM here), END with ERDT (END-ERDT) achieves the best performance with less than a 0.5% difference in the overall accuracy (OA) values, but is 100 to 10000 times faster than END with RaF and ExtraTrees, and ECOC with SVM while using different datasets with various dimensions; and, 5) Sentinel-2A MSIL1C is better choice than the land cover products from MODIS and Landsat imagery for vegetation species mapping in an arid land environment, where the vegetation species are critically important, but sparsely distributed. View Full-Text
Keywords: ND; END; ECOC; MRS; Extended object-guided morphological profiles; Multiclass classification; Arid-land vegetation mapping; Sentinel-2A MSIL1C; Central Asia ND; END; ECOC; MRS; Extended object-guided morphological profiles; Multiclass classification; Arid-land vegetation mapping; Sentinel-2A MSIL1C; Central Asia
Show Figures

Graphical abstract

MDPI and ACS Style

Samat, A.; Yokoya, N.; Du, P.; Liu, S.; Ma, L.; Ge, Y.; Issanova, G.; Saparov, A.; Abuduwaili, J.; Lin, C. Direct, ECOC, ND and END Frameworks—Which One Is the Best? An Empirical Study of Sentinel-2A MSIL1C Image Classification for Arid-Land Vegetation Mapping in the Ili River Delta, Kazakhstan. Remote Sens. 2019, 11, 1953.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop