logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Refining point-cloud neighborhood construction for improved classification

delete2025-11-01
delete0
delete
OA
AI
M
Max Hess *
A
Aljoscha Rheinwalt
B
Bodo Bookhagen
DOI：10.1016/j.srs.2025.100325delete
deleteOriginal
deleteShare
deleteSave
View PDF
Abstract

Abstract

En 中文
• We propose a structure-aware neighborhood for 3D point cloud classification. • Region growing constrained by normal orientation and graph connectivity. • Enhanced extraction of geometric features by preserving semantic boundaries. • Improved classification across four diverse urban datasets. • We provide open-access source code and two new reference datasets.
Keywords:
Point cloud processing
Neighborhood construction
Geometric features
Urban classification
Lidar
AI Summary

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.

Journal

Science of Remote Sensing cover
Science of Remote Sensing
IF:
5.2
Papers:
471
Citations:
980

Organization

No organization information available