Road intelligent extraction method and device, extraction model construction method and hybrid navigation system

Abstract

The invention provides a satellite image road intelligent extraction method and device base on deep learning. The method comprises the following steps: selecting a part of satellite image pictures, marking roads in the pictures with specific colors and constructing a mark database; carrying out autonomous learning through a convolutional neural network, constructing a learning model and utilizingthe learning model to carry out road extraction on newly-input satellite image pictures; judging the road extraction result, if the result is correct, carrying out road grid vectorization, or otherwise, returning to the mark database to carry out remarking and learning; and for extracted roads, traversing each road and carrying out road centerline extraction, and connecting central coordinates inseries to form a vector road line. The method carries out autonomous learning by providing a lot of mark data, then, carries out road extraction on the newly-input satellite image pictures and judgesthe extraction result, thereby correcting errors constantly and improving accuracy and recall rate of remote sensing image road extraction.

Description

technical field [0001] The present invention relates to the field of image recognition, in particular to a method and device for extracting roads from satellite images using a method based on deep learning. Background technique [0002] For road recognition in the prior art, a method based on image segmentation or a finite element method can be used. For the method based on image segmentation, according to certain algorithms, such as K-means clustering algorithm, fuzzy C-means clustering algorithm, etc., the image is divided into meaningful patches, and roads are identified according to the characteristics of the patches, and roads are extracted. Segment or road seed point. However, this method relies on high-resolution remote sensing images, which has a large amount of calculation and is difficult to automatically classify. The finite element method mostly focuses on the use of the geometric characteristics of the road, and is carried out in low (edge ​​detection and text...

AI Technical Summary

Problems solved by technology

However, this method relies on high-resolution remote sensing images, which is computationally intensive and difficult to automatically classify

The finite element method mostly focuses on the use of the geometric characteristics of the road, and is carried out in low (edge ​​detection and texture analysis), medium (analysis, selection and synthesis of low-level results), and some of the studies combine road models and road-related Knowledge and rules are carried out, but the overall effect is not obvious

[0003] The above algorithm is not universal, and there is a large extraction bias for remote sensing images of different resolutions or different seasons.

Images