论文部分内容阅读
遥感影像分类作为遥感技术的一个重要应用,对遥感技术的发展具有重要作用.针对遥感影像数据特点,在目前的非线性研究方法中主要用到的是BP神经网络模型.但是BP神经网络模型存在对初始权阈值敏感、易陷入局部极小值和收敛速度慢的问题.因此,为了提高模型遥感影像分类精度,提出采用MEA-BP模型进行遥感影像数据分类.首先采用思维进化算法代替BP神经网络算法进行初始寻优,再用改进BP算法对优化的网络模型权阈值进一步精确优化,随后建立基于思维进化算法的BP神经网络分类模型,并将其应用到遥感影像数据分类研究中.仿真结果表明,新模型有效提高了遥感影像分类准确性,为遥感影像分类提出了一种新的方法,具有广泛研究价值.
As an important application of remote sensing technology, remote sensing image classification plays an important role in the development of remote sensing technology.According to the characteristics of remote sensing image data, the BP neural network model is mainly used in the current nonlinear research methods.But the BP neural network model exists Therefore, in order to improve the classification accuracy of model remote sensing images, the MEA-BP model is proposed to classify the remote sensing image data.At first, the thought evolutionary algorithm is used to replace the BP neural network Algorithm, and then use the improved BP algorithm to further optimize the optimization threshold value of network model, and then establish the BP neural network classification model based on thought evolutionary algorithm and apply it to the remote sensing image data classification research.The simulation results show that The new model effectively improves the classification accuracy of remote sensing images and proposes a new method for remote sensing image classification with extensive research value.