结合纹理特征的SVM海冰分类方法研究

张明; 吕晓琪; 张晓峰; 张婷; 吴凉; 王军凯; 张信雪

doi:10.3969/j.issn.0253-4193.2018.11.015

结合纹理特征的SVM海冰分类方法研究

doi: 10.3969/j.issn.0253-4193.2018.11.015

1.
内蒙古科技大学信息工程学院, 内蒙古自治区包头 014010
2.
内蒙古科技大学信息工程学院, 内蒙古自治区包头 014010;内蒙古工业大学, 内蒙古自治区呼和浩特 010051
3.
国家海洋局第一海洋研究所, 山东青岛 266061

基金项目: 国家重点研发计划（2018YFC1407203，2016YFA0600102）；国家自然科学基金（61771266）；内蒙古自治区高等学校科学研究项目（NJZY18150）；国家海洋局第一海洋研究所基本科研业务费专项资金项目（2014G31）

计量
- 文章访问数: 640
- HTML全文浏览量: 9
- PDF下载量: 264
- 被引次数: 0
出版历程
- 收稿日期: 2018-01-22
- 修回日期: 2018-04-11

Research on SVM sea ice classification based on texture features

1.
School of Information Engineering, Inner Mongolia University of Science and Technology, Baotou 014010, China
2.
School of Information Engineering, Inner Mongolia University of Science and Technology, Baotou 014010, China;Inner Mongolia University of Technology, Hohhot 010051, China
3.
The First Institute of Oceanography, State Oceanic Administration, Qingdao 266061, China

摘要

摘要: 海冰分类是遥感监测领域中的重要应用之一，海冰分类的准确性对于评估海冰冰情、保证航海安全和开辟北极航道具有重要的意义。针对海冰分类问题，本文选用Sentinel-1遥感数据，结合纹理特征分析，提出了一种改进的SAR海冰分类方法。该方法选用灰度共生矩阵提取特征值，通过实验得到适宜用于海冰分类的多特征组合，在此基础上利用支持向量机开展SAR海冰类型的分类研究。实验结果表明，该方法可以实现对海冰SAR图像中一年冰、多年冰和海水3种类型识别，与传统的海冰分类方法神经网络和最大似然法相比较，使用SVM分类方法，结合纹理特征开展海冰类型监测是可行的，同时也表明多特征组合有利于提高SAR图像的分类精度，从而验证了本方法的有效性，为海冰分类提供了一种新思路。
- 海冰分类 /
- 纹理特征 /
- 灰度共生矩阵 /
- 支持向量机
Abstract: The classification of sea ice is one of the most important applications in the field of remote sensing monitoring, and its accuracy is of great significance in assessing the ice conditions, ensuring the safety of navigation and opening up the Arctic channel. In order to solve the sea ice classification problems, this paper proposed an improved SAR sea ice classification method, which used Sentinel-1 data and texture feature analysis. In this method, the gray level co-occurrence matrix (GLCM) was used to extract the eigenvalue, and the suitable of texture features for sea ice classification was obtained, then we used support vector machine to carried out sea ice classification. The experimental results showed that the proposed method can recognize three types of ice, which are first year ice, multiyear ice and open water. Compared with the traditional methods of Neural Net and Maximum Likelihood, it is feasible to use SVM classification method and texture feature to monitor sea ice type. It also showed that multi-feature is helpful to improve the classification accuracy of SAR image, which verifies the effectiveness of this method and provides a new idea for sea ice classification.
- sea ice classification /
- texture characteristics /
- gray level co-occurrence matrix /
- support vector machine

HTML全文

参考文献(15)

Fraser A D. East Antarctic landfast sea ice distribution and variability, 2000-08[J]. Journal of Climate, 2012, 25(4):1137-1156.

Wilson K J, Falkingham J, Melling H, et al. Shipping in the Canadian Arctic:other possible climate change scenarios[C]//Proceedings of 2004 IEEE International Geoscience and Remote Sensing Symposium. Anchorage, AK, USA:IEEE, 2004:1853-1856.

Zhu Tingting, Li Fei, Heygster G, et al. Antarctic sea-ice classification based on conditional random fields from RADARSAT-2 dual-polarization satellite images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(6):2451-2467.

Holmes Q A, Nuesch D R, Shuchman R A. Textural analysis and real-time classification of sea-ice types using digital SAR data[J]. IEEE Transactions on Geoscience and Remote Sensing, 1984, GE-22(2):113-120.

Nystuen J A, Garcia F W. Sea ice classification using SAR backscatter statistics[J]. IEEE Transactions on Geoscience and Remote Sensing, 1992, 30(3):502-509.

Barber D G, Le Drew E F. SAR sea ice discrimination using texture statistics:a multivariate approach[J]. Photogrammetric Engineering and Remote Sensing, 1991, 57(4):385-395.

Haverkamp D, Tsatsoulis C. Information fusion for estimation of summer MIZ ice concentration from SAR imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 1999, 37(3):1278-1291.

Liu Huiying, Guo Huadong, Zhang Lu. SVM-based sea ice classification using textural features and concentration from RADARSAT-2 dual-pol ScanSAR data[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(4):1601-1613.

刘建强, 吴奎桥, 黄润恒. Radarsat卫星渤海海冰监测研究[J]. 海洋预报, 1999, 16(3):62-70. Liu Jianqiang, Wu Kuiqiao, Huang Runheng. The monitoring of sea ice in the Bohai Sea with Radarsat SAR[J]. Marine Forecasts, 1999, 16(3):62-70.

金亚秋, 陈轶, 张巍, 等. 雷达卫星SAR与防卫气象卫星SSM/I对渤海海冰的观测研究[J]. 地球物理学报, 2001, 44(2):163-170. Jin Yaqiu, Chen Yi, Zhang Wei, et al. Observations of radarsat SAR and DMSP SSM/I over sea ice of china's Bohai sea[J]. Chinese Journal of Geophysics, 2001, 44(2):163-170.

张晰, 张杰, 纪永刚. 基于纹理特征分析的辽东湾SAR影像海冰检测[J]. 海洋科学进展, 2008, 26(3):386-393. Zhang Xi, Zhang Jie, Ji Yonggang. Sea ice detection from SAR images of the Liaodong bay based on texture analysis[J]. Advances in Marine Science, 2008, 26(3):386-393.

沈杨, 郎文辉, 吴杰, 等. 结合MRF与ν-SVM的SAR海冰图像分类[J]. 遥感学报, 2015, 19(5):844-855. Shen Yang, Lang Wenhui, Wu Jie, et al. Combining MRF and ν-SVM for SAR sea ice image classification[J]. Journal of Remote Sensing, 2015, 19(5):844-855.

Zhang Yi, Zhang Ming, Ji Yonggang. Sea ice detection with sentinel-1A dual polarization SAR data[C]//Proceedings of Dragon 3 Final Results and Dragon 4 Kick-Off. Wuhan, China:ESA-SP, 2016.

高程程, 惠晓威. 基于灰度共生矩阵的纹理特征提取[J]. 计算机系统应用, 2010, 19(6):195-198. Gao Chengcheng, Hui Xiaowei. GLCM-based texture feature extraction[J]. Computer Systems & Applications, 2010, 19(6):195-198.

Su Hua, Wang Yunpeng, Xiao Jie, et al. Improving MODIS sea ice detectability using gray level co-occurrence matrix texture analysis method:a case study in the Bohai Sea[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2013, 85:13-20.

施引文献

资源附件(0)

访问统计