Abstract
Abstract. Functional classification of the road is important to the construction of sustainable transport systems and proper design of facilities. Mobile laser scanning (MLS) point clouds provide accurate and dense 3D measurements of road scenes, while their massive data volume and lack of structure also bring difficulties in processing. 3D point cloud understanding through deep neural networks achieves breakthroughs since PointNet and arouses wide attention in recent years. In this paper, we study the automatic road type classification of MLS point clouds by employing a point-wise neural network, RandLA-Net, which is designed for consuming large-scale point clouds. An effective local feature aggregation (LFA) module in RandLA-Net preserves the local geometry in point clouds by formulating an enhanced geometric feature vector and learning different point weights in a local neighborhood. Based on this method, we also investigate possible feature combinations to calculate neighboring weights. We train on a colorized point cloud from the city of Hannover, Germany, and classify road points into 7 classes that reveal detailed functions, i.e., sidewalk, cycling path, rail track, parking area, motorway, green area, and island without traffic. Also, three feature combinations inside the LFA module are examined, including the geometric feature vector only, the geometric feature vector combined with additional features (e.g., color), and the geometric feature vector combined with local differences of additional features. We achieve the best overall accuracy (86.23%) and mean IoU (69.41%) by adopting the second and third combinations respectively, with additional features including Red, Green, Blue, and intensity. The evaluation results demonstrate the effectiveness of our method, but we also observe that different road types benefit the most from different feature settings.
Highlights
Automation of road information extraction is of great significance to economic and social development
This study investigates the capability of a deep neural network, i.e., RandLA-Net, for classifying 3D point clouds into different road types and evaluates the performance of different feature combinations in the local feature aggregation module
We compare three feature combinations to calculate neighboring weights in the local feature aggregation module of RandLA-Net, which refer to the choice of fik in g(fik, W ): 1. rki : Geometric feature vector only. 2. rki ⊕ fik: Geometric feature vector rik concatenated with additional features fik, which is the original implementation of RandLA-Net. 3. rki ⊕: Geometric feature vector rik concatenated with relative additional features
Summary
Automation of road information extraction is of great significance to economic and social development. Point cloud processing benefits from the rapid development of deep learning techniques (Liu et al, 2019). It is still challenging to interpret 3D point clouds using neural networks due to their irregular data structure. Determining the type of each road point is consistent with the aim of point cloud semantic segmentation. Recent studies on semantic segmentation of point clouds using deep learning mainly consist of two kinds of methods, i.e., projection-based and point-based methods. Through achieving a regularly aligned data format, 2D or 3D convolutional neural networks (CNN) can be applied. These methods address the problem of unorganized point clouds indirectly, some spatial information is lost and additional computational resources are needed during pre-processing
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
