Riverine Land Cover Mapping through Semantic Segmentation of Multispectral Point Clouds

TL;DR

This paper presents a transformer-based deep learning approach for semantic segmentation of multispectral LiDAR point clouds to accurately classify land cover types in riverine environments, improving generalization with multi-dataset training.

Contribution

It introduces the use of Point Transformer v2 for land cover mapping in riverine multispectral point clouds and demonstrates enhanced performance and generalization through multi-dataset training.

Findings

Full-feature configuration achieved a mean IoU of 0.950.

Intensity and reflectance features are crucial for accurate classification.

Multi-dataset training improves model generalization across different river environments.

Abstract

Accurate land cover mapping in riverine environments is essential for effective river management, ecological understanding, and geomorphic change monitoring. This study explores the use of Point Transformer v2 (PTv2), an advanced deep neural network architecture designed for point cloud data, for land cover mapping through semantic segmentation of multispectral LiDAR data in real-world riverine environments. We utilize the geometric and spectral information from the 3-channel LiDAR point cloud to map land cover classes, including sand, gravel, low vegetation, high vegetation, forest floor, and water. The PTv2 model was trained and evaluated on point cloud data from the Oulanka river in northern Finland using both geometry and spectral features. To improve the model's generalization in new riverine environments, we additionally investigate multi-dataset training that adds sparsely annotated data from an additional river dataset. Results demonstrated that using the full-feature configuration resulted in performance with a mean Intersection over Union (mIoU) of 0.950, significantly outperforming the geometry baseline. Other ablation studies revealed that intensity and reflectance features were the key for accurate land cover mapping. The multi-dataset training experiment showed improved generalization performance, suggesting potential for developing more robust models despite limited high-quality annotated data. Our work demonstrates the potential of applying transformer-based architectures to multispectral point clouds in riverine environments. The approach offers new capabilities for monitoring sediment transport and other river management applications.