Back propagation neural network classification of sediment seabed acoustic sonar images based on particle swarm optimization algorithms
-
摘要: 利用粒子群优化算法(PSO)较强的鲁棒性和全局搜索能力等优点,将PSO算法与BP神经网络相结合,优化了BP神经网络分类时的初始权值和阈值。基于珠江河口三角洲的侧扫声呐图像数据,提取了海底声呐图像中砂、礁石、泥3类典型底质的6种主要特征向量,利用PSO-BP方法对海底底质进行分类识别。实验表明,3类底质分类精度均大于90%,高于BP神经网络70%左右的分类精度,表明PSO-BP方法可有效应用于海底底质的分类识别。
-
关键词:
- 基于粒子群优化算法的BP神经网络 /
- 特征向量 /
- 粒子群算法 /
- 底质分类
Abstract: By combining Particle Swarm Optimization (PSO) with BP neural network, the initial weights and thresholds of BP neural network classification are optimized by utilizing PSO with strong robustness and global searching ability. Extracting six main feature vectors of sandy, rocks and mud in the seabed sonar images based on the data of side scan sonar in the Zhujiang Estuary Delta, using the PSO-BP method to classify seabed sediment. The experiment shows that the accuracy of the sediments classification is more than 90%, higher than the accuracy about 70% which using BP neural network only. It proves that the PSO-BP method can be effectively applied to the identification and classification of sediment seabed. -
Leblanc L R, Mayer L, Rufino M, et al. Marine sediment classification using the chirp sonar[J]. Journal of the Acoustical Society of America, 1992, 91(1):107-115. Alexandrou D, Pantzartzis D. Seafloor classification with neural networks[J]. Oceans, 1990, 99(3):18-23. Chakraborty B, Kaustubha R, Hegde A, et al. Acoustic seafloor sediment classification using self-organizing feature maps[J]. IEEE Transactions on Geoscience & Remote Sensing, 2002, 39(12):2722-2725. Chakraborty B, Kodagali V, Baracho J. Sea-floor classification using multibeam echo-sounding angular backscatter data:a real-time approach employing hybrid neural network architecture[J]. IEEE Journal of Oceanic Engineering, 2003, 28(1):121-128. Marsh I, Brown C. Neural network classification of multibeam backscatter and bathymetry data from Stanton Bank (Area IV)[J]. Applied Acoustics, 2009, 70(10):1269-1276. 阳凡林, 刘经南, 赵建虎,等. 基于遗传算法的BP网络实现海底底质分类[J]. 测绘科学, 2006, 31(2):111-114. Yang Fanlin, Liu Jingnan, Zhao Jianhu, et al. Seabed classification using BP neural network basd on GA[J]. Science of Surveying and Mapping, 2006, 31(2):111-114. 唐秋华, 刘保华, 陈永奇, 等. 基于改进BP神经网络的海底底质分类[J]. 海洋测绘, 2009, 29(5):40-43. Tang Qiuhua, Liu Baohua, Chen Yongqi, et al. Seabed classification with improved BP neural network[J]. Hydrographic Surveying and Charting, 2009, 29(5):40-43. 唐秋华, 刘保华, 陈永奇,等. 结合遗传算法的LVQ神经网络在声学底质分类中的应用[J]. 地球物理学报, 2007, 50(1):313-319. Tang Qiuhua, Liu Baohua, Chen Yongqi, et al. Application of LVQ neural network combined with the genetic algorithm in acoustic seafloor classification[J]. Chinese Journal of Geophysics, 2007, 50(1):313-319. 唐秋华, 刘保华, 陈永奇,等. 基于自组织神经网络的声学底质分类研究[J]. 声学技术, 2007, 26(3):380-384. Tang Qiuhua, Liu Baohua, Chen Yongqi, et al. Acoustic seafloor classification using selforganizing map neural network[J]. Technical Acoustics, 2007, 26(3):380-384. Zhou Xinghua, Chen Yongqi. Seafloor classification of multibeam sonar data using neural network approach[J]. Marine Geodesy, 2005, 28(2):201-206. 郭军, 马金凤. 基于K-L变换的自组织竞争神经网络在海底底质分类中的应用[J]. 测绘工程, 2013, 22(1):51-54. Guo Jun, Ma Jinfeng. Self-organization competition neural network based on K-L transform in seafloor classification[J]. Engineering of Surveying and Mapping, 2013, 22(1):51-54 郭军, 马金凤. 基于粒子群优化算法的SVM神经网络在海底底质分类中的应用[J]. 测绘与空间地理信息, 2012, 35(12):66-68. Guo Jun, Ma Jinfeng. Support vector machine neural network based on particle swarm optimization in seafloor classification[J]. Geomatics &Spatial Information Technology, 2012, 35(12):66-68. 郭军. 基于主成分分析的自组织竞争神经网络实现海底底质分类[M]//中国地球物理(2012). 北京:中国科学技术大学出版社, 2012. Guo Jun. Self-organization competition neural network based on principle component analysis in seafloor classification[M]//The Chinese Geophysics(2012). Beijing:University of Science and Technology of China Press, 2012. 贺清碧. BP神经网络及应用研究[D]. 重庆:重庆交通大学, 2004. He Qingbi. BP neural network and application research[D]. Chongqing:Chongqing Jiaotong University, 2004. Kennedy J, Eberhart R C. Particle swarm optlmization[C]//Proceeding of IEEE International Conference on Neural Networks,1995,(4):1942-1948. 范娜, 云庆夏. 粒子群优化算法及其应用[J]. 信息技术, 2006, 30(1):53-56. Fan Na, Yun Qingxia. Particle swarm optimization algorithms and its applications[J]. Information Technology, 2006, 30(1):53-56. 李松, 刘力军, 翟曼. 改进粒子群算法优化BP神经网络的短时交通流预测[J]. 系统工程理论与实践, 2012, 32(9):2045-2049. Li Song, Liu Lijun, Zhai Man. Prediction for short-term traffic flow based on modified PSO optimized BP neural network[J]. System Engineering Theory &Practice, 2012, 32(9):2045-2049. 何怡刚, 祝文姬, 周炎涛,等. 基于粒子群算法的模拟电路故障诊断方法[J]. 电工技术学报, 2010(6):163-171. He Yigang, Zhu Wenji, Zhou Yantao, et al. An analog circuit diagnosis method based on particle swarm optimization algorithm[J]. Transactions of China Electrotechnical Society, 2010(6):163-171. 孙亚. 基于粒子群BP神经网络人脸识别算法[J]. 计算机仿真, 2008, 25(8):201-204. Sun Ya. Human face recognition based on PSO and BP neural network[J]. Computer Simulation, 2008, 25(8):201-204. Kloser R J. Seabed backscatter, data collection, and quality overview[J]. Ices Cooperative Research Report, 2007, 286:45-60. 唐秋华, 周兴华, 丁继胜,等. 多波束反向散射强度数据处理研究[J]. 海洋学报, 2006, 28(2):51-55. Tang Qiuhua, Zhou Xinhua, Ding Jisheng, et al. Study on processing of multibeam backscatter data[J]. Haiyang Xuebao, 2006, 28(2):51-55. 赵永祯, 唐劲松, 钟何平. 基于声呐图像纹理特征的海底底质分类方法研究[J]. 海洋测绘, 2015, 35(3):60-63. Zhao Yongzhen, Tang Jinsong, Zhong Heping. Seabed sediment classification based on texture feature of sonar imagery[J]. Hydrographic Surveying and Charting, 2015, 35(3):60-63. 王惠明, 史萍. 图像纹理特征的提取方法[J]. 中国传媒大学学报:自然科学版, 2006, 13(1):49-52. Wang Huiming, Shi Ping. Methods to extract images texture features[J]. Journal of Communication University of China Science and Techology, 2006, 13(1):49-52. Haralick R M, Shanmugam K, Dinstein I. Textural features for image classification[J]. Systems Man & Cybernetics IEEE Transactions on, 1973, SMC-3(6):610-621. 张铮, 王艳平, 薛桂香. 数字图像处理与机器视觉:Visual C++与Matlab实现[M]. 北京:人民邮电出版社, 2010. Zhang Zheng, Wang Yanping, Xue Guixiang. Digital Image Processing and Machine Vision:Visual C ++ and Matlab Realization[M]. Beijing:Posts & Telecom Press, 2010. 于成龙. 基于特征提取的特征选择研究[D]. 南京:南京邮电大学, 2011. Yu Chenglong. Research on feature selection based on feature extraction[D]. Nanjing:Nanjing University of Posts and Telecommunications, 2011.
点击查看大图
计量
- 文章访问数: 888
- HTML全文浏览量: 27
- PDF下载量: 674
- 被引次数: 0