Road center line and double-line extraction method based on convolutional neural network regression
A convolutional neural network and extraction method technology, which is applied in the field of automatic extraction of remote sensing image information, can solve the problems of lack of road network topology information, neglect of connectivity, and impact on road accuracy in segmentation results, and achieve good generalization ability and generalization ability. Strong, geometrically accurate effects
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0046] The specific embodiments and working principles of the present invention will be described in further detail below with reference to the accompanying drawings.
[0047] Such as figure 1 As shown, a road centerline and double-line extraction method based on convolutional neural network regression, the specific steps are as follows:
[0048] Step 1: Using the trained convolutional neural network, using multi-scale high-order semantic features and underlying features, to predict the distance between each pixel in the high-resolution remote sensing image to be extracted and the center line of the road and the road where the road pixel is located Width, predict the road centerline distance map and road width map of the high-resolution remote sensing image to be extracted;
[0049] Regarding the training process of the trained convolutional neural network:
[0050] Step A1: First, build a convolutional neural network to be trained. The entire network structure is as follows figure ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap