TY - JOUR
T1 - A novel multi-parameter support vector machine for image classification
AU - Zhang, C.
AU - Wang, Tiejun
AU - Atkinson, P.M.
AU - Pan, X.
AU - Li, H.
PY - 2015
Y1 - 2015
N2 - The support vector machine (SVM) classification algorithm has received increasing attention in recent years in remote sensing for land-cover classification. However, it is well known that the performance of the SVM is sensitive to the choice of parameter settings. The traditional single optimized parameter SVM (SOP-SVM) attempts to identify globally optimized parameters for multi-class land-cover classification. In this article, a novel multi-parameter SVM (MP-SVM) algorithm is proposed for image classification. It divides the training set into several subsets, which are subsequently combined. Based on these combinations, sub-classifiers are constructed using their own optimum parameters, providing votes for each pixel with which to construct the final output. The SOP-SVM and MP-SVM were tested on three pilot study sites with very high, high, and low levels of landscape complexity within the Sanjiang Plain – a typical inland wetland and freshwater ecosystem in northeast China. A high overall accuracy of 82.19% with kappa coefficient (κ) of 0.80 was achieved by the MP-SVM in the very high-complexity landscape, statistically significantly different (z-value = 3.77) from the overall accuracy of 72.50% and κ of 0.69 produced by the traditional SOP-SVM. Besides, for the moderate-complexity landscape a significant increase in accuracy was achieved (z-value = 2.44), with overall accuracy of 84.03% and κ of 0.80 compared with an overall accuracy 76.05% and κ of 0.71 for the SOP-SVM. However, for the low-complexity landscape the MP-SVM was not significantly different from the SOP-SVM (z-value = 0.80). Thus, the results suggest that the MP-SVM method is promising for application to very high and high levels of landscape complexity, differentiating complex land-cover classes that are spectrally mixed, such as marsh, bare land, and meadow.
AB - The support vector machine (SVM) classification algorithm has received increasing attention in recent years in remote sensing for land-cover classification. However, it is well known that the performance of the SVM is sensitive to the choice of parameter settings. The traditional single optimized parameter SVM (SOP-SVM) attempts to identify globally optimized parameters for multi-class land-cover classification. In this article, a novel multi-parameter SVM (MP-SVM) algorithm is proposed for image classification. It divides the training set into several subsets, which are subsequently combined. Based on these combinations, sub-classifiers are constructed using their own optimum parameters, providing votes for each pixel with which to construct the final output. The SOP-SVM and MP-SVM were tested on three pilot study sites with very high, high, and low levels of landscape complexity within the Sanjiang Plain – a typical inland wetland and freshwater ecosystem in northeast China. A high overall accuracy of 82.19% with kappa coefficient (κ) of 0.80 was achieved by the MP-SVM in the very high-complexity landscape, statistically significantly different (z-value = 3.77) from the overall accuracy of 72.50% and κ of 0.69 produced by the traditional SOP-SVM. Besides, for the moderate-complexity landscape a significant increase in accuracy was achieved (z-value = 2.44), with overall accuracy of 84.03% and κ of 0.80 compared with an overall accuracy 76.05% and κ of 0.71 for the SOP-SVM. However, for the low-complexity landscape the MP-SVM was not significantly different from the SOP-SVM (z-value = 0.80). Thus, the results suggest that the MP-SVM method is promising for application to very high and high levels of landscape complexity, differentiating complex land-cover classes that are spectrally mixed, such as marsh, bare land, and meadow.
KW - ITC-ISI-JOURNAL-ARTICLE
UR - https://ezproxy2.utwente.nl/login?url=http://dx.doi.org/10.1080/01431161.2015.1029096
UR - https://ezproxy2.utwente.nl/login?url=https://webapps.itc.utwente.nl/library/2015/isi/wang_nov.pdf
U2 - 10.1080/01431161.2015.1029096
DO - 10.1080/01431161.2015.1029096
M3 - Article
VL - 36
SP - 1890
EP - 1906
JO - International journal of remote sensing
JF - International journal of remote sensing
SN - 0143-1161
IS - 7
ER -