Intensity Harmonization for Airborne LiDAR

TL;DR

This paper introduces a deep learning-based method for harmonizing intensity values in airborne LiDAR point clouds, improving consistency across scans from different sources and conditions, which is crucial for large-scale geographic data analysis.

Contribution

The paper presents a novel neural network approach for LiDAR intensity harmonization, outperforming traditional methods in diverse intensity distribution scenarios.

Findings

Outperforms baseline methods in areas with differing intensity distributions

Achieves comparable results to best methods in similar intensity regions

Provides publicly available source code for reproducibility

Abstract

Constructing a point cloud for a large geographic region, such as a state or country, can require multiple years of effort. Often several vendors will be used to acquire LiDAR data, and a single region may be captured by multiple LiDAR scans. A key challenge is maintaining consistency between these scans, which includes point density, number of returns, and intensity. Intensity in particular can be very different between scans, even in areas that are overlapping. Harmonizing the intensity between scans to remove these discrepancies is expensive and time consuming. In this paper, we propose a novel method for point cloud harmonization based on deep neural networks. We evaluate our method quantitatively and qualitatively using a high quality real world LiDAR dataset. We compare our method to several baselines, including standard interpolation methods as well as histogram matching. We show that our method performs as well as the best baseline in areas with similar intensity distributions, and outperforms all baselines in areas with different intensity distributions. Source code is available at https://github.com/mvrl/lidar-harmonization .