| abstract |
The present invention relates to the field of land classification of high-resolution remote sensing images, and in particular to an object-oriented method for classifying land cover of coal-fired areas in high-resolution images of drones. The high-resolution color image is divided into homogeneous objects through the image multi-scale segmentation algorithm, and the expert knowledge base based on spectral features, shape features, texture features and height information is constructed. Accuracy classification, the classification accuracy is much higher than the traditional pixel-based classification method, and the invention meets the demand for accurate classification of land cover in complex coal fire areas. |