TY - JOUR
T1 - Enhanced Super-Resolution Mapping of Urban Floods Based on the Fusion of Support Vector Machine and General Regression Neural Network
AU - Li, Linyi
AU - Chen, Yun
AU - Xu, Tingbao
AU - Shi, Kaifang
AU - Huang, Chang
AU - Liu, Rui
AU - Lu, Binbin
AU - Meng, Lingkui
N1 - Funding Information:
Manuscript received October 16, 2018; revised December 6, 2018; accepted January 14, 2019. Date of publication February 6, 2019; date of current version July 18, 2019. This work was supported by the National Key Research and Development Program of China under Grant 2018YFC0407804. (Corresponding author: Linyi Li.) L. Li, B. Lu, and L. Meng are with the School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China (e-mail: [email protected]; [email protected]; [email protected]).
Publisher Copyright:
© 2019-2012 IEEE.
PY - 2019/8
Y1 - 2019/8
N2 - Super-resolution mapping of urban flood (SMUF) is one of the hotspots in remote sensing and urban environment research. In this letter, a new SMUF method based on the fusion of support vector machine and general regression neural network (FSVMGRNN) was proposed to achieve enhanced performance. An SVM-SMUF algorithm was developed and a fusion criterion was formulated. Then, the FSVMGRNN-SMUF algorithm was developed. The results of FSVMGRNN-SMUF were evaluated using Landsat 8 OLI imagery of two representative cities in China. FSVMGRNN-SMUF yielded the most accurate SMUF results among the five SMUF methods according to visual comparisons and quantitative comparisons. The mapping accuracy of FSVMGRNN-SMUF related to the kernel functions was also analyzed and discussed. The results of this letter will help to boost practical applications of median-low resolution remote sensing images in urban flooding mapping, and to strengthen the means for monitoring and assessing urban flooding disasters.
AB - Super-resolution mapping of urban flood (SMUF) is one of the hotspots in remote sensing and urban environment research. In this letter, a new SMUF method based on the fusion of support vector machine and general regression neural network (FSVMGRNN) was proposed to achieve enhanced performance. An SVM-SMUF algorithm was developed and a fusion criterion was formulated. Then, the FSVMGRNN-SMUF algorithm was developed. The results of FSVMGRNN-SMUF were evaluated using Landsat 8 OLI imagery of two representative cities in China. FSVMGRNN-SMUF yielded the most accurate SMUF results among the five SMUF methods according to visual comparisons and quantitative comparisons. The mapping accuracy of FSVMGRNN-SMUF related to the kernel functions was also analyzed and discussed. The results of this letter will help to boost practical applications of median-low resolution remote sensing images in urban flooding mapping, and to strengthen the means for monitoring and assessing urban flooding disasters.
KW - Fusion algorithm
KW - general regression neural network (GRNN)
KW - super-resolution mapping
KW - support vector machine (SVM)
KW - urban floods
UR - https://www.scopus.com/pages/publications/85069509657
U2 - 10.1109/LGRS.2019.2894350
DO - 10.1109/LGRS.2019.2894350
M3 - Article
AN - SCOPUS:85069509657
SN - 1545-598X
VL - 16
SP - 1269
EP - 1273
JO - IEEE Geoscience and Remote Sensing Letters
JF - IEEE Geoscience and Remote Sensing Letters
IS - 8
M1 - 8636408
ER -