Remote sensing image building extraction and contour optimization method based on deep learning
A remote sensing image and deep learning technology, applied in neural learning methods, image enhancement, image analysis, etc., to reduce network size, overcome learning performance degradation and gradient explosion, and eliminate the semantic gap.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0083] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, now refer to the accompanying drawings in detail
[0084] Such as figure 1As shown, the deep learning-based remote sensing image building extraction and contour optimization method of the present invention, the specific steps are as follows:
[0085] S1, making semantic segmentation data set, data enhancement
[0086] S1.1. Make semantic segmentation dataset
[0087] Use the data labeling tool Arcmap to read several remote sensing image datasets, and manually frame the buildings on each remote sensing image with polygons to generate building vectors. The building vector labels are used to indicate the location and boundary of the building. The area not selected by the box is the background; the building vector is converted into raster data corresponding to the size of the remote sensing image, and the style is resampled to binary raster data, that is, the...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com