Study On Extraction Method Of High-resolution Remote Sensing Image Based On Multi-algorithm Combination

Road is typical artificial object,which is a very important of city structure as the skeleton of the city.Road as an important national categories and basic geographic entities,road can accurately extract to build national and geographical spatial database related geographic information industry to lay a solid foundation.With the rapid development of science and technology,the resolution of remote sensing satellite image is in constant increase.Research on extracting trget featre information from high-resolution remote sensing image has become a hotshot in recent years.In this paper,the methods of road extraction from high-resolution remote sensing image are studied.On the basis of analyzing and summarizing the methods of existing image segmentation and road extraction,combined with high-resolution remote sensing image road feature,K-means clustering algorithm,fuzzy C-means clustering,P-value segmentation algorithm and support vector machine image segmentation algorithm are used to extract the remote sensing image road network.Based on the existing image segmentation and road extraction algorithm,this paper proposes three kinds of joint methods for the extraction of remote sensing image road,the K-means clustering method combined with SVM,and the fuzzy C-means clustering method combined with SVM and P-value segmentation combined with SVM.The results of experimental show that the three methods proposed in this paper can improve the accuracy of road extraction than the corresponding single method to improve the accuracy of roads by 11.88%,8.18%,8.02%.The research results can provide technical support for the future application of road extraction and algorithm research.