Remote sensing image classification based on object-oriented convolutional neural network

Remote sensing image classification is of great importance for urban development and planning. The need for higher classification accuracy has led to improvements in classification technology. In this research, Landsat 8 images are used as experimental data, and Wuhan, Chengde and Tongchuan are selected as research areas. The best neighborhood window size of the image patch and band combination method are selected based on two sets of comparison experiments. Then, an object-oriented convolutional neural network (OCNN) is used as a classifier. The experimental results show that the classification accuracy of the OCNN classifier is 6% higher than that of an SVM classifier and 5% higher than that of a convolutional neural network classifier. The graph of the classification results of the OCNN is more continuous than the plots obtained with the other two classifiers, and there are few fragmentations observed for most of the category. The OCNN successfully solves the salt and pepper problem and improves the classification accuracy to some extent, which verifies the effectiveness of the proposed object-oriented model.

Automated summary

Remote sensing image classification plays a crucial role in urban development and planning. This research proposes an object-oriented convolutional neural network (OCNN) method and compares it with SVM and convolutional neural network. The experimental results demonstrate that the OCNN method outperforms the others in terms of classification accuracy and image continuity.