Port local pit rapid detection method based on unmanned aerial vehicle laser point cloud data

A rapid detection method for localized craters in ports using UAV laser point cloud data, combined with semantic segmentation and geometric feature analysis, solves the problems of detection hazards during port damage and low efficiency of multi-source data fusion. This method achieves high-precision and efficient port damage detection, especially for the identification of small-scale craters and boundary areas.

CN122289273APending Publication Date: 2026-06-26NANJING UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
NANJING UNIV
Filing Date
2026-05-28
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Close-range measurement during port damage presents risks and low efficiency in multi-source data fusion processing, making it difficult to achieve high-precision and high-efficiency damage detection. In particular, in complex port environments, the detection of small-scale pits or boundary areas is prone to missed or false detections.

Method used

A rapid detection method for localized pits in ports based on UAV laser point cloud data is adopted. The method uses a 3D point cloud semantic segmentation network for preprocessing, combined with geometric feature analysis and sliding window block processing, to achieve accurate extraction of semantic point clouds on the dock surface and efficient processing of large-scale point cloud data.

Benefits of technology

It improves the accuracy and efficiency of port damage and crater detection, can simultaneously meet the detection needs of damage of different scales, reduces computational complexity, and provides accurate basic data support for port emergency repair and reopening plans.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122289273A_ABST
    Figure CN122289273A_ABST
Patent Text Reader

Abstract

This invention relates to the fields of lidar point cloud processing and computer vision, and discloses a rapid detection method for localized potholes in ports based on UAV lidar point cloud data. The method includes: outputting a semantic point cloud of the wharf surface using a port point cloud semantic segmentation model; filtering and fusing a reference plane point cloud and a point cloud below the reference plane to obtain a fused analysis point cloud; calculating the concavity depth and curvature features of the fused analysis point cloud; clustering the suspected damaged point cloud set according to the calculation results to extract a set of candidate damaged regions; and applying constraints such as point count, elevation difference, horizontal scale, and extension to the adjacent reference plane to each candidate damaged region to extract complete pothole damaged regions and output them one by one. This invention enables the rapid detection and location of damaged localized potholes in ports using UAV point cloud data, providing accurate basic data support for the formulation of subsequent port emergency repair and reopening plans.
Need to check novelty before this filing date? Find Prior Art