RGB-D image variable metric super voxel segmentation method
A RGB-D, super-voxel technology, applied in image analysis, image data processing, instruments, etc., can solve problems such as increasing the amount of calculation, and achieve the effect of reducing the amount of calculation and multi-scale analysis
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0072] figure 1 It is a schematic diagram of the process of pre-segmentation and variable-scale segmentation of a frame of RGB-D image collected by a Kinect depth camera and the result of the present invention.
[0073] Use variable-scale super-voxel over-segmentation method of the present invention to segment a frame RGB-D image below, comprise the following steps:
[0074] Step 1. Selection of seed points. A frame of RGB-D image data is P, with a resolution of 480 rows and 640 columns. The information of each data point includes 3 color channels (r, g, b) and 1 depth channel (d ). Randomly pick a point p from P 0As the initial seed point, set the radius threshold R=20 as the minimum distance between the seed points to be generated, and use the Poisson disk sampling algorithm to sample in P to obtain the set of seed points. Specifically include the following steps:
[0075] Step 1-1. Randomly select a point p in P 0 As the initial seed point, the active sampling point qu...
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