节点文献

激光遥感探测海面溢油智能识别算法的研究

The Study of Intelligent Identification Algorithm for Detecting Littoral Oil-Spills by Laser Remote Sensing

【作者】 林彬

【导师】 安居白;

【作者基本信息】 大连海事大学 , 计算机应用技术, 2003, 硕士

【摘要】 海洋溢油污染是各种海洋污染中影响范围最广、危害时间最长、对生态环境破坏最大的一种。本论文根据对各种海洋遥感器的对比研究,总结出激光荧光遥感在此方面是最为有力的工具。 目前我国在激光遥感的硬件设备方面已经具备一定的条件,而软件的溢油信息智能处理方面仍存在空缺。由于ANN方法适合于处理非线性系统,具有自组织、自学习、自适应和联想能力,故通过对样本反复训练,能辨别各类样本特征差异,本论文的核心工作就是将人工神经网络(ANN)的方法应用于激光遥感光谱数据的智能分析。而在众多的人工神经网络模型中,本论文选择了三种模式识别应用最普遍效果相对较好的网络模型,即感知器、BP、SOM网络,提出了适用于海面溢油激光遥感光谱的智能分析与识别的神经网络理论模型。应用三种神经网络的理论模型设计光谱智能分析系统,以激光荧光光谱样本作为输入,训练神经网络系统,并对3种神经网络模型系统的推广能力进行比较实验分析。实验表明,SOM网络模型算法自身的特点决定了它在多光谱数据智能分析及海面溢油识别方面良好适用性,成为解决此类问题最好的算法。 本论文主要进行的是理论建模和分析工作,并且用计算机软件方法实现了神经网络系统的模式识别和分类功能。在论文的最后还提出了利用ANN方法解决溢油浓度算法的思路。ANN技术必将在海洋遥感领域里发挥它独特的功效。

【Abstract】 In this paper an artificial neural network (ANN) approach, which is based on flexible nonlinear models for a very broad class of transfer functions, is applied for multi-spectral data analysis and modeling of airborne laser fiuorosensor in order to differentiate between classes of oil on water surface. We use three types of algorithm: Perceptron Network, Back-Propagation (B-P) Network and Self-Organizing feature Maps (SOM) Network. Using the data in form of 64-channel spectra as inputs, the ANN presents the analysis and estimation results of the oil type on the basis of the type of background materials as outputs. The ANN is trained and tested using sample data set to the network. The results of the above 3 types of network are compared in this paper. SOM NN is the most effective and advanced one as classifier for littoral oil-spill in that SOM algorithm can extract the internal features of parameter by self-organizing. This paper has not only developed ANN models in theory but also completed software package for spectra intelligent analysis for the airborne detection of oil spills by laser-induced fluorescence.The ANN model would play a significant role in the ocean oil-spill identification in the future.

  • 【分类号】TN247
  • 【被引频次】2
  • 【下载频次】294
节点文献中: 

本文链接的文献网络图示:

本文的引文网络