A Multi-granularity Computation Method for Airborne Laser Point Cloud Classification in Hybrid Scenes
An airborne laser and computing method technology, applied in computing, computer components, instruments, etc., to achieve the effects of suppressing misclassification, saving costs, and improving recognition accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0048] The present invention will now be described in further detail with reference to the accompanying drawings.
[0049] like figure 1 As shown, the inventive method mainly comprises the following steps:
[0050] Step 1: Randomly select a sampling point in the whole point cloud, and use the sampling point as the center to search for a set of square scene neighborhood points with a side length of 150 meters and a group of square classification neighbors with a side length of 50 meters. set of domain points, such as figure 2 shown.
[0051] Step 2: In the way of unsupervised learning, train the global feature extraction model of point cloud, and extract the spatial context information (scene knowledge) from the large-scale scene neighborhood point set, so as to realize the coarse-grained large-scale scene perception. like image 3 shown, including the following sub-steps:
[0052] (1) Collect a large number of square point clouds with a side length of 150 meters containi...
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