A low-grade road automatic extraction and change analysis method

Abstract

The invention discloses a low-grade road automatic extraction and change analysis method. According to the method, automatic extraction and change analysis of a road network can be realized, geometric, texture and spectral characteristics of road materials are subjected to sample selection through a high-resolution remote sensing image, a data set is generated to train a model, and the generated model is utilized to automatically extract a road.Road extraction is performed based on the data model to realize automatic registration of the image extraction result and the network data. Threshold values, confidence intervals and other modes are set for contrastive change analysis, and fusion is carried out to reduce generation work of a data set. According to the method, the generation work ofthe training data set can be greatly reduced, the image-based road extraction result is fused with the network road data, the accuracy of the fusion result road data is high, the new data set can be automatically generated according to the fusion result, and the generation work of the training data set is greatly reduced.

Description

Technical field [0001] The invention relates to the technical field of road image extraction and analysis, in particular to a low-grade road automatic extraction and change analysis method. Background technique [0002] Highways are an important part of the national infrastructure. As the "main artery" of transportation, they are closely related to local economic development. With the rapid development of my country's economy, the speed of urban construction has greatly increased, the road network is updated rapidly, and the delay of road network data update is a common problem faced by both developed and developing countries. The rapid and accurate road network update can provide assistance for regional economic development, as well as provide services for travel route planning, urban construction, disaster warning and even military strikes, laying a foundation for the development of smart cities and driverless technology. [0003] The traditional road network update method is ti...

AI Technical Summary

Problems solved by technology

[0004] At this stage, major map manufacturers use remote sensing data and mobile GPS data to update the traffic road network of large and medium-sized cities, but the update frequency of the road network at the county and town levels is slow, and the update frequency even reaches 3-5 years

Obtaining road trajectory data through GPS data requires massive basic data as support, but obtaining massive trajectory data in areas with low traffic density is usually time-consuming and expensive. High-level trajectory data often leads to large errors in trajectory data extraction, which cannot meet the needs of practical applications.

[0005] In the existing technology, although many adjustments have been made in the use characteristics and methods of the road network update technology, in essence, the road is extracted by manually giving the computer some knowledge of road color features, texture features, and shape features in advance. The extraction method is manual. The subjective initiative is relatively large, the road feature information is easy to understand, and the extraction effect can meet the needs of practical applications, but the extraction accuracy has reached the bottleneck period and it is difficult to improve it to a large extent

Images