Abstract
Abstract. This work proposes an approach for semantic classification of an outdoor-scene point cloud acquired with a high precision Mobile Mapping System (MMS), with major goal to contribute to the automatic creation of High Definition (HD) Maps. The automatic point labeling is achieved by utilizing the combination of a feature-based approach for semantic classification of point clouds and a deep learning approach for semantic segmentation of images. Both, point cloud data, as well as the data from a multi-camera system are used for gaining spatial information in an urban scene. Two types of classification applied for this task are: 1) Feature-based approach, in which the point cloud is organized into a supervoxel structure for capturing geometric characteristics of points. Several geometric features are then extracted for appropriate representation of the local geometry, followed by removing the effect of local tendency for each supervoxel to enhance the distinction between similar structures. And lastly, the Random Forests (RF) algorithm is applied in the classification phase, for assigning labels to supervoxels and therefore to points within them. 2) The deep learning approach is employed for semantic segmentation of MMS images of the same scene. To achieve this, an implementation of Pyramid Scene Parsing Network is used. Resulting segmented images with each pixel containing a class label are then projected onto the point cloud, enabling label assignment for each point. At the end, experiment results are presented from a complex urban scene and the performance of this method is evaluated on a manually labeled dataset, for the deep learning and feature-based classification individually, as well as for the result of the labels fusion. The achieved overall accuracy with fusioned output is 0.87 on the final test set, which significantly outperforms the results of individual methods on the same point cloud. The labeled data is published on the TUM-PF Semantic-Labeling-Benchmark.
Highlights
1.1 MotivationIncreasing need for fast and accurate 3D spatial data has led to rapid development of Mobile Mapping Systems (MMS) in terms of accuracy and scanning density, which further enabled extensive research in the topic of 3D scene semantic classification
Our work offers a solution for semantic classification of outdoor-scene point clouds by utilizing combination of feature-based approach for semantic segmentation of point clouds with deep learning approach for semantic segmentation of images
Two types of classification are performed upon data collected with an MMS (Figure 1): 1) Feature-based approach is applied as in (Sun et al, 2018, Xu et al, 2018): firstly, point cloud is organized into a supervoxel structure for capturing geometric characteristics of points, followed by defining local context for each supervoxel for gaining contextual information
Summary
Increasing need for fast and accurate 3D spatial data (e.g. for designing HD maps for autonomous driving) has led to rapid development of Mobile Mapping Systems (MMS) in terms of accuracy and scanning density, which further enabled extensive research in the topic of 3D scene semantic classification. The major goal is an output with enhanced classification accuracy, compared to the outputs of individual methods applied for the same task. For these purposes, two types of classification are performed upon data collected with an MMS (Figure 1): 1) Feature-based approach is applied as in (Sun et al, 2018, Xu et al, 2018): firstly, point cloud is organized into a supervoxel structure for capturing geometric characteristics of points, followed by defining local context for each supervoxel for gaining contextual information. Pyramid Scene Parsing Network (Zhao et al, 2017) is used Fusion of the point clouds from the same urban scene, classified with these two methods is presented as experiment result and the performance of our method evaluated on a manually labeled dataset
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
