Ground target segmentation method based on fitting

Through the combination of vertical point filter and polar grid division, weighted mean filtering and linear interpolation method are used to solve the problem of insufficient adaptability and large data processing volume based on the fitting method in noise and complex environments, and improve the ground Accuracy and efficiency of target segmentation.

CN119206220AActive Publication Date: 2024-12-27ZHAOTONG POWER SUPPLYING BUREAU OF YUNNAN POWER GRID
View PDF 9 Cites 1 Cited by

Patent Information

Application Number
CN202411263151.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-10
Publication Date
2024-12-27
Estimated Expiration
2044-09-10

AI Technical Summary

Technical Problem

The existing fit-based ground target segmentation method is insufficiently adaptable in noise and complex environments, and has large data processing volume and low efficiency.

Method used

Vertical point filter and polar grid division are used, combined with weighted mean filtering and linear interpolation, iterative optimization and post-processing are carried out to improve segmentation accuracy and robustness and reduce data processing.

Benefits of technology

Effectively reduce the impact of noise data, improve the quality of seed point selection, enhance the algorithm's adaptability to noise and complex environments, improve overall efficiency, and ensure the integrity and accuracy of segmentation results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119206220A_ABST
    Figure CN119206220A_ABST
Patent Text Reader

Abstract

The invention discloses a ground target segmentation method based on fitting. The method comprises the following steps of preliminary screening, polar coordinate grid division, ground point classification, iterative optimization, post-processing of a preliminary classification result, noise point removal and misclassification point correction. According to the ground target segmentation method based on fitting, through a multi-step processing flow, the adaptive capacity of an algorithm to noise and a complex environment is enhanced; and through pre-filtering and grid-based processing, the data processing amount is greatly reduced, so that the overall efficiency of the algorithm is improved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Multiline laser radar-based 3D point cloud segmentation method

    CN106204705A

  • Ground point cloud segmentation method based on three-dimensional laser radar

    CN106530380A

  • Method and system for segmenting ground points based on key points, and readable medium

    CN114332414A

  • Laser point cloud ground filtering method and device

    CN116486268A

  • Obstacle detection method based on laser radar point cloud clustering

    CN116524219A

Cited By

  • Point cloud data-based ground identification method

    CN120766267A