3D Modeling Drones Lidar Surveying

Semantic Labeling for Drone Lidar Applications

graphic of Semantic Labeling
Semantic Labeling

Small Unmanned Aerial Vehicle (UAV) platforms equipped with compact laser scanners provides a low-cost option for many applications, including surveillance, mapping, and reconnaissance. For these applications, semantic segmentation or semantic labeling of each point in the lidar point cloud, is important for scene-understanding.

In this work, we evaluate methods for semantic segmentation of three-dimensional (3D) point clouds of outdoor scenes measured with a laser scanner mounted on a small UAV. We compare the performance of four different semantic segmentation methods, which are all applied in a scan-by-scan fashion, on semi-sparse laser data.

The best method achieves 95.3% on the three classes ground, vegetation, and vehicle in terms of mean intersection over union (mIoU) on a previously unseen scene from a different geographical area. The results demonstrate that it is possible to achieve good performance on the semantic segmentation task on data measured using a combination of a small UAV and a compact laser scanner.

From a research paper by Maria Axelsson, et al.

The technical development of Unmanned Aerial Vehicles (UAV) and a drive for miniaturization of advanced sensor technologies enables new sensing approaches. For example, a small UAV can be equipped with a scanning lidar and be used for short-range applications in surveillance, mapping, and reconnaissance. UAVs with scanning lidars are well suited for mapping three-dimensional (3D) environments and can provide accurate 3D measurements during both day and night conditions.

Scene-understanding is an important step in the data analysis of point clouds from scanning lidar. This paper addresses the problem of labeling each point in a 3D point cloud with the correct class in data from a scanning lidar mounted on a UAV. This labeling problem is denoted semantic segmentation and is well studied for lidar point clouds in computer vision applications like autonomous cars, where the annotated public dataset SemanticKITTI [1] is available. However, semantic segmentation is not well studied in the context of scanning lidar data from UAVs. Applications of point cloud semantic segmentation are also found in robotics and remote sensing.

For the complete paper CLICK HERE.

Note – If you liked this post click here to stay informed of all of the 3D laser scanning, geomatics, UAS, autonomous vehicle, Lidar News and more. If you have an informative 3D video that you would like us to promote, please forward to editor@lidarnews.com and if you would like to join the Younger Geospatial Professional movement click here.



  • How would one detect lidar if you were on the receiving end of it what type of camera would pick it up?

Leave a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.

%d bloggers like this: