Abstarct: The purpose of route and road network extraction is to maintain or increase the accuracy and speed of data extraction compared to ground operations and the use of GPS. Remote sensing has wide applications in many scientific and research fields, including road engineering and transportation, the most important of which is road network extraction and road network schematic mapping. Extraction of road network from satellite images is a complementary technology for obtaining information, which simplifies the interpretation and analysis of the image and improves the quality, which is one of the most important goals of planners and officials. The main purpose of this study was to automatically extract the road network in the two study areas of Shahroud city and the Shahroud-Miami route so that the resulting road network map can be used as the input of the pavement management system (PMS). The proposed method in this study is baxsed on the technique of merging and combining images of Sentinel 1 and Sentinel 2 satellites with the majority voting method in order to make maximum use of spectral and spatial information of multiple images (detail enhancement) instead of single image using texture features. In order to perform the supervised classification, two non-parametric classifications of artificial neural network (ANN) and support vector machine (SVM) and a parametric classification of maximum likelihood similarity (ML) were used in two general classes of road and non-road. The results of this study showed that the integration of the results of the classifications with the majority voting method improves the accuracy of about 1/5% for the Sentinel 1 satellite and about 5% for the Sentinel 2 satellite in the urban area and the accuracy of about 3% for the Sentinel 1 satellite and about 4/5% has been created for Sentinel 2 satellite in non-urban area in identifying the route and road network.