Target detection algorithm for rivers in SAR images based on multi-features and WSVM

被引：1

作者：

Wu, Yi-Quan ^{[1
,2
,3
,4
,5
]}

Li, Hai-Jie ^{[1
]}

Song, Yu ^{[1
]}

机构：

[1] College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing

[2] Key Laboratory of the Yellow River Sediment of the Ministry of Water Resource, Yellow River Institute of Hydraulic Research, Zhengzhou

[3] Engineering Technology Research Center of Wuhan Intelligent Basin, Changjiang River Scientific Research Institute, Changjiang Water Resources Commission of the Ministry of Water Resources, Wuhan

[4] Key Laboratory of Port, Waterway and Sedimentation Engineering of the Ministry of Transport, Nanjing Hydraulic Research Institute, Nanjing

[5] State Key Laboratory of Urban Water Resource and Environment, Harbin Institute of Technology, Harbin

来源：

Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics | 2015年 / 37卷 / 06期

关键词：

Gabor wavelet; Mean ratio; Multi-features; Regional connectivity; River target detection; Synthetic aperture radar (SAR) image; Wavelet support vector machine (WSVM);

D O I：

10.3969/j.issn.1001-506X.2015.06.10

中图分类号：

学科分类号：

摘要：

In order to further improve the accuracy of river target detection in synthetic aperture radar (SAR) images, a method of river target detection based on multi-features and wavelet support vector machine (WSVM) in SAR images is proposed. Firstly, gray features of pixel neighborhood are represented by the mean ratio. Texture features are extracted by Gabor wavelet. The training samples are constructed by fusion of the extracted gray features and texture features. Then, the normalized feature matrix is inputted into the WSVM for training. Each pixel in the images is classified by the trained WSVM. Finally, the similar regionals with ri-vers such as shadows, lakes are removed according to the regional connectivity, areas and shape features of ri-vers. A large number of experimental results show that compared with other methods of river target detection, the proposed method has more completely detection, error regions of classification are much less and edges of rivers are preserved better. ©, 2015, Chinese Institute of Electronics. All right reserved.

引用

页码：1288 / 1293

页数：5

共 15 条

[1]

Chen A.J., Wei X.Q., Zhu B., Fast extraction of river from satellite remote sensing images, Infrared and Laser Engineering, 35, z4, pp. 268-271, (2006)

[2]

Chen S.L., Li Y.R., Li T., Study on river detection based on SAR images, Computer Measurement & Control, 17, 7, pp. 1267-1269, (2009)

[3]

Sun J.P., Mao S.Y., River detection algorithm in SAR images based on edge extraction and ridge tracing techniques, International Journal of Remote Sensing, 32, 12, pp. 3485-3494, (2011)

[4]

Hu Z.L., Sun J.P., Yuan Y.N., Et al., River detection in SAR images based on edge extraction in wavelet domain and ridge tracking technique, Journal of Electronics & Information Technology, 29, 3, pp. 524-527, (2007)

[5]

Cheng H., Yu Q.Z., Liu J., Et al., SVM-based detection of bridge object over water, Journal of Astronautics, 26, 5, pp. 601-605, (2005)

[6]

Zhong W.Y., Sheng T., Multiple features and SVM combined SAR image segmentation, Application Research of Computers, 30, 9, pp. 2846-2851, (2013)

[7]

Klemenjak S., Waske B., Valero S., Et al., Automatic detection of rivers in high-resolution SAR data, IEEE Journal of Selec-ted Topics in Applied Earth Observations and Remote Sensing, 5, 5, pp. 1364-1372, (2012)

[8]

Shen L., Tang H., Wang S.D., Et al., River extraction from the high resolution remote sensing image based on spatially correlated pixels template and Adaboost algorithm, Acta Geodaetica et Cartographica Sinica, 42, 3, pp. 344-350, (2013)

[9]

Zhang L., Zhou W., Jiao L., Wavelet support vector machine, IEEE Trans. on Systems, Man, and Cybernetics, 34, 1, pp. 34-39, (2004)

[10]

Tan K., Du P.J., Wavelet support vector machines based on reproducing kernel Hilbert space for hyperspectral remote secsing image classification, Acta Geodaetica et Cartographica Sinica, 40, 2, pp. 142-147, (2011)

← 1 2 →