Lake Wetland Classification Based on an SVM-CNN Composite Classifier and High-resolution Images Using Wudalianchi as an Example

This paper constructs a composite classifier based on a convolutional neural network (CNN) and support vector machine (SVM) by using the decision fusion method to study the Wudalianchi Nature Reserve. It also conducts studies on the high-resolution remote sensing image classification of a lake wetland and makes a comparison between the pixel-based SVM method and the context-based CNN method. The experimental results show that the overall accuracy of the SVM-CNN classification method is higher than that of the SVM method, by 9% and 7.75% for the selected two study sites, and higher than the CNN method, by 5.23% and 2.39%. In particular, for the large-area lake wetland, the SVM-CNN classification method provides a higher boundary classification accuracy than the SVM and CNN methods. The research shows that the SVM-CNN composite classifier based on decision fusion theory provides a favorable means for the fine classification of lake wetland identification.