遥感图像分类的实质是通过计算机对图像像元进行数值处理,达到自动识别地物的目的.在对国内外湿地遥感分类研究的基础上,用BP神经网络方法对湿地遥感分类进行了研究,并与最大似然法进行精度比较分析.结果表明:BP神经网络分类法是一种有效的湿地分类技术,能够提高分类精度. The essence of remote sensing image classification is to realize the automatic recognition of ground objects through the computer numerical processing of image pixels.On the basis of the remote sensing classification of wetlands at home and abroad, the method of BP neural network is used to study the remote sensing classification of wetlands And the maximum likelihood method to compare the accuracy.The results show that: BP neural network classification is an effective wetland classification technology, can improve the classification accuracy.