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

## TL;DR

This paper introduces a new data augmentation method for 3D LiDAR point clouds that balances class distribution and improves model performance.

## Contribution

The novel DACB-PolarMix algorithm dynamically adjusts data augmentation based on class imbalance in LiDAR point clouds.

## Key findings

- DACB-PolarMix improves mIoU by 2.9% under the MinkNet model on the SemanticKitti dataset.
- The method increases mIoU by 1.3% under the SPVCNN model on the same dataset.

## Abstract

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%.