A method for batch processing and visualization of high-density point cloud data of road surface based on Python

By using Python to process high-density point cloud data of asphalt pavement, and employing the 3σ rule to remove outliers, as well as meshing and normalization methods, this approach solves the problems of inconsistent outlier identification and weak visualization capabilities in existing point cloud data processing technologies, achieving high-precision and automated data processing and visualization.

CN122134905APending Publication Date: 2026-06-02CIVIL AVIATION UNIV OF CHINA
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
CIVIL AVIATION UNIV OF CHINA
Filing Date
2026-02-10
Publication Date
2026-06-02

AI Technical Summary

Technical Problem

Existing technologies for processing high-density 3D point cloud data of asphalt pavement suffer from inconsistent outlier identification, insufficient mesh reconstruction accuracy, and weak result visualization capabilities, making it difficult to achieve automated and high-precision processing of large-scale data.

Method used

Using a Python-based approach, outliers are removed by the 3σ rule, the data is meshed, missing height values ​​are filled using bilinear interpolation, and the mean is subtracted for normalization, enabling batch processing and visualization of point cloud data.

Benefits of technology

It improves the quality and continuity of point cloud data, enhances the accuracy and interpretability of texture feature analysis, and enables automated data processing and unified visualization.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122134905A_ABST
    Figure CN122134905A_ABST
Patent Text Reader

Abstract

A batch processing and visualization method for high-density point cloud data of road surfaces based on Python is disclosed. The method includes: acquiring raw 3D texture point cloud data of asphalt pavement and importing it into a Python environment; removing outliers from the raw 3D texture point cloud data using the 3σ rule to obtain 3D texture point cloud data; performing meshing processing on the 3D texture point cloud data to obtain a network matrix; using bilinear interpolation to complete the missing height values ​​in the network matrix; normalizing the height values ​​of all 3D texture point cloud data using a mean subtraction normalization method to obtain normalized new height values; outputting the 3D point cloud data; and automatically generating texture images after data processing using Python. The advantages of this invention are: a simple processing flow, high degree of automation, and ease of engineering implementation; a stable and reliable data processing method that effectively improves the quality of point cloud data; and intuitive visualization of texture height, which is beneficial for texture feature analysis and comparison.
Need to check novelty before this filing date? Find Prior Art