TS40K: a 3D Point Cloud Dataset of Rural Terrain and Electrical Transmission System

2024-05-22

arXiv.org

AI Summary

Existing public 3D point cloud datasets severely lack rural terrain and power transmission infrastructure scenes, hindering research on intelligent power line inspection. Method: We introduce TS40K—the first large-scale, semantically annotated 3D point cloud dataset specifically designed for rural power transmission systems—covering over 40,000 km of rural overhead lines across Europe, with fine-grained annotations for 22 classes. We establish the first rural 3D point cloud benchmark for power grid inspection, characterized by high point density, low occlusion, and long-range sparse linear structures, and formulate the novel challenge of non-native label migration. Contribution/Results: We provide LiDAR-derived ground-truth annotations, evaluation frameworks for 3D semantic segmentation and object detection, and a cross-domain label adaptation analysis method. Comprehensive benchmarking reveals significant performance bottlenecks in state-of-the-art models for sparse linear structure recognition and effective utilization of non-standard labels.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Application Domains: Internet of Things, Sensor Networks & Smart Cities
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Security and Privacy: Large-scale security measurements

Abstract

Research on supervised learning algorithms in 3D scene understanding has risen in prominence and witness great increases in performance across several datasets. The leading force of this research is the problem of autonomous driving followed by indoor scene segmentation. However, openly available 3D data on these tasks mainly focuses on urban scenarios. In this paper, we propose TS40K, a 3D point cloud dataset that encompasses more than 40,000 Km on electrical transmission systems situated in European rural terrain. This is not only a novel problem for the research community that can aid in the high-risk mission of power-grid inspection, but it also offers 3D point clouds with distinct characteristics from those in self-driving and indoor 3D data, such as high point-density and no occlusion. In our dataset, each 3D point is labeled with 1 out of 22 annotated classes. We evaluate the performance of state-of-the-art methods on our dataset concerning 3D semantic segmentation and 3D object detection. Finally, we provide a comprehensive analysis of the results along with key challenges such as using labels that were not originally intended for learning tasks.

Problem

• Introduces TS40K, a 3D rural terrain dataset.
• Focuses on electrical transmission system inspection.
• Evaluates 3D semantic segmentation and object detection.

Innovation

• TS40K dataset creation
• 3D semantic segmentation evaluation
• high-density rural point clouds