A method and system for extracting road material from remote sensing images

Abstract

The invention discloses a method for extracting road materials from remote sensing images. The method utilizes the processing method of a double network structure to overcome some defects of using a single complex neural network structure, such as the potential overfitting and uncontrollability of the deep network structure to information learning. This improves the stability and reliability of the automatic road extraction model, and has better training characteristics, which can be applied in many fields.

Description

technical field [0001] The invention relates to the technical field of image extraction, in particular to a method and system for extracting road material from remote sensing images. Background technique [0002] The construction level of transportation infrastructure directly reflects the economic strength and development level of a country. As a developing country, my country has been vigorously promoting the construction of transportation infrastructure. The automatic extraction of traffic infrastructure, especially traffic roads, has always been one of the hot issues studied by scientific researchers. The identification and monitoring of road materials is of great significance to road construction and maintenance. In recent years, with the continuous development of remote sensing technology, information extraction technology based on remote sensing images has developed into an efficient scientific method, and related applications have also emerged, such as infrastructure...

AI Technical Summary

Problems solved by technology

However, in the actual application research, the vehicles driving on the road and the large buildings and green vegetation beside the road will block the road to a certain extent, resulting in an increase in information redundancy and a decrease in accuracy.

In addition, when identifying materials, since the current urban roads mainly use cement and asphalt surfaces, similar materials are also used for urban building roofs, parking lots, and embankments, which further increases the difficulty of road material identification.

Images