Steel rail profile outlier detection and effective profile recognition method
A technology of outlier detection and contour, which is applied in the direction of measuring devices, optical devices, railway vehicle shape measuring devices, etc. Group segment and other problems, to achieve the effect of effective removal
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0033] Considering that each contour shape contains the characteristics of the rail head area, the rail jaw point and the inner line of the rail head area are used as the reference for contour registration. Compared with the traditional use of the rail waist area as the registration reference, the registration accuracy of the rail head area is lower. We call it coarse registration, and propose an outlier and effective profile detection algorithm based on rough contour registration. The specific testing process is as figure 2 Shown.
[0034] Step 1: Contour splitting to remove sparse outliers
[0035] The distribution of normal contour data points is dense, and the distance between adjacent points is small. Wherever there is a large jump in the dot pitch, there must be an abnormality. Based on this consideration, after we obtain the threshold of the distance between adjacent points on the normal contour curve, we first split the measured contour to obtain a lot of curve fragments...
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