Technology Study in Division of Forest Resources Based on the High-spatial Resolution Remote Sensing Images

The main method of current forest resources sub-compartment division is adopted drawing division boundary according to the condition of opposite hillside in the field,which existence of human subjectivity and lacks of scientific objectivity in this approach.This paper brings forward the strategy of object-oriented multi-scale segmentation,which takes different segmentation scales according to the feature information of diferent scales.Based on this,the multi-scale segmentation network is established and the layered extraction of the feature information is realized.And then in sub-compartment division of forest resources,experimental results show that the method can greatly improve the accuracy of the sub-compartment division in image-based automatic interpretation.