Abstract
Repeat-visit airborne lidar is a powerful tool for change detection in urban and rural environments. In this work, we present a learning-based approach that addresses one of the key challenges in comparing point cloud scans of the same region: handling geometric differences caused by varying sensor position. Our approach is to perform shape modeling through ray casting with a point cloud neural network. Recent work on learning-based shape modeling has been based on the assumption that an explicit surface representation is available, which is not the case for airborne lidar datasets. Our key insight is that by using a ray casting approach we can perform shape modeling directly with lidar measurements. We evaluate our method both quantitatively and qualitatively on learned surface accuracy and show that our method correctly predicts surface intersection even in sparse regions of the input cloud.
| Original language | English |
|---|---|
| Title of host publication | 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings |
| Pages | 1110-1113 |
| Number of pages | 4 |
| ISBN (Electronic) | 9781728163741 |
| DOIs | |
| State | Published - Sep 26 2020 |
| Event | 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Virtual, Waikoloa, United States Duration: Sep 26 2020 → Oct 2 2020 |
Publication series
| Name | International Geoscience and Remote Sensing Symposium (IGARSS) |
|---|
Conference
| Conference | 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 |
|---|---|
| Country/Territory | United States |
| City | Virtual, Waikoloa |
| Period | 9/26/20 → 10/2/20 |
Bibliographical note
Funding Information:We presented a method for implicit surface modeling of airborne lidar through direct point cloud ray casting. Our method allows for accurate and simple to generate surface predictions. Because it depends only on easily obtainable samples for training, it can be applied to real-world data. When applied to real airborne lidar data, we show that our approach is able to accurately sample new points even in areas where the input cloud is extremely sparse. We believe our method is useful for lidar point cloud change detection, and hope to evaluate it for this task in future work. Acknowledgements We gratefully acknowledge the support of the National Science Foundation (IIS-1553116).
Publisher Copyright:
© 2020 IEEE.
Keywords
- lidar
- machine learning
- point cloud synthesis
- ray casting
ASJC Scopus subject areas
- Computer Science Applications
- Earth and Planetary Sciences (all)