A dynamic and adaptive class-balanced data augmentation approach for 3D LiDAR point clouds.

3D LiDAR point clouds, obtained through scanning by LiDAR devices, contain rich information such as 3D coordinates (X, Y, Z), color, classification values, intensity values, and time. However, the original collected 3D LiDAR point clouds often exhibit significant disparities in instance counts, whic...

Full description

Saved in:
Bibliographic Details
Main Authors: Bo Liu, Xiao Qi
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0318888
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850265693750034432
author Bo Liu
Xiao Qi
author_facet Bo Liu
Xiao Qi
author_sort Bo Liu
collection DOAJ
description 3D LiDAR point clouds, obtained through scanning by LiDAR devices, contain rich information such as 3D coordinates (X, Y, Z), color, classification values, intensity values, and time. However, the original collected 3D LiDAR point clouds often exhibit significant disparities in instance counts, which can hinder the effectiveness of point cloud segmentation. PolarMix, a data augmentation algorithm for 3D LiDAR point cloud datasets, addresses this issue by rotating and pasting selected class instances around the Z axis multiple times to enrich the distribution of the point cloud. However, PolarMix does not adequately consider the substantial variations in instance counts within the original point clouds, leading to an imbalance in the dataset. To address this limitation, we propose a modified version of PolarMix's instance-level rotation and pasting method that dynamically adjusts the number of rotations and pastes based on the proportion of each instance's point cloud count relative to the total. This adaptive class-balancing approach ensures a more balanced distribution of instances across the entire dataset. We term our new algorithm Dynamic Adaptive Class-Balanced PolarMix (DACB-PolarMix). Experimental results demonstrate the effectiveness of DACB-PolarMix in balancing class distribution and enhancing model performance. The results on the SemanticKitti dataset are particularly significant. Under the MinkNet model, our method improved the mIoU from 65% to 67.9%, and under the SPVCNN model, our method increased the mIoU from 66.2% to 67.5%.
format Article
id doaj-art-5fb0812d1f20485893eeeb3033b07be6
institution OA Journals
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-5fb0812d1f20485893eeeb3033b07be62025-08-20T01:54:21ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01203e031888810.1371/journal.pone.0318888A dynamic and adaptive class-balanced data augmentation approach for 3D LiDAR point clouds.Bo LiuXiao Qi3D LiDAR point clouds, obtained through scanning by LiDAR devices, contain rich information such as 3D coordinates (X, Y, Z), color, classification values, intensity values, and time. However, the original collected 3D LiDAR point clouds often exhibit significant disparities in instance counts, which can hinder the effectiveness of point cloud segmentation. PolarMix, a data augmentation algorithm for 3D LiDAR point cloud datasets, addresses this issue by rotating and pasting selected class instances around the Z axis multiple times to enrich the distribution of the point cloud. However, PolarMix does not adequately consider the substantial variations in instance counts within the original point clouds, leading to an imbalance in the dataset. To address this limitation, we propose a modified version of PolarMix's instance-level rotation and pasting method that dynamically adjusts the number of rotations and pastes based on the proportion of each instance's point cloud count relative to the total. This adaptive class-balancing approach ensures a more balanced distribution of instances across the entire dataset. We term our new algorithm Dynamic Adaptive Class-Balanced PolarMix (DACB-PolarMix). Experimental results demonstrate the effectiveness of DACB-PolarMix in balancing class distribution and enhancing model performance. The results on the SemanticKitti dataset are particularly significant. Under the MinkNet model, our method improved the mIoU from 65% to 67.9%, and under the SPVCNN model, our method increased the mIoU from 66.2% to 67.5%.https://doi.org/10.1371/journal.pone.0318888
spellingShingle Bo Liu
Xiao Qi
A dynamic and adaptive class-balanced data augmentation approach for 3D LiDAR point clouds.
PLoS ONE
title A dynamic and adaptive class-balanced data augmentation approach for 3D LiDAR point clouds.
title_full A dynamic and adaptive class-balanced data augmentation approach for 3D LiDAR point clouds.
title_fullStr A dynamic and adaptive class-balanced data augmentation approach for 3D LiDAR point clouds.
title_full_unstemmed A dynamic and adaptive class-balanced data augmentation approach for 3D LiDAR point clouds.
title_short A dynamic and adaptive class-balanced data augmentation approach for 3D LiDAR point clouds.
title_sort dynamic and adaptive class balanced data augmentation approach for 3d lidar point clouds
url https://doi.org/10.1371/journal.pone.0318888
work_keys_str_mv AT boliu adynamicandadaptiveclassbalanceddataaugmentationapproachfor3dlidarpointclouds
AT xiaoqi adynamicandadaptiveclassbalanceddataaugmentationapproachfor3dlidarpointclouds
AT boliu dynamicandadaptiveclassbalanceddataaugmentationapproachfor3dlidarpointclouds
AT xiaoqi dynamicandadaptiveclassbalanceddataaugmentationapproachfor3dlidarpointclouds