A method for segmenting the top surface of buildings based on airborne lidar point cloud
A building and point cloud technology, applied in image analysis, computer parts, image enhancement, etc., can solve the problems of different degrees of complexity of houses and inability to obtain stable and high-precision roof surface extraction results.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0124] see figure 1 and figure 2 , the present invention extracts the top surface of buildings efficiently and with high precision from the airborne LiDAR point cloud through the multi-scale L0 gradient minimization algorithm and the graph cut optimization algorithm.
[0125] Take the No. 1 survey area of the Vaihingen dataset of the ISPRS public dataset as an example.
[0126] Step 1: European clustering
[0127] First, we calculate the resolution of the point cloud by counting the average distance between all points and the nearest point. Set the minimum distance threshold for Euclidean clustering according to the point cloud resolution. Experiments have proved that three times the point cloud resolution can obtain a good segmentation effect of Euclidean clustering. The specific process of European clustering is as follows:
[0128] Kd-tree is established according to the minimum distance threshold, and the neighbor points of each point can be determined through Kd-tr...
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