An Efficient Class-Constrained DBSCAN Approach for Large-Scale Point Cloud Clustering
Zhang Hua, Zhenwei Duan, Nanshan Zheng, Yong Li, Yu Zeng, Wenzhong Shi
Abstract
To better interpret the scene and facilitate the subsequent processing of large-scale point cloud, clustering is often implemented in the preprocessing stage. However, when the original density-based spatial clustering of application with noise (DBSCAN) approach is used for point cloud clustering, it is easy to categorize closely spaced vegetation points and non-vegetation points into the same cluster by mistake. Aiming at the above problem, this paper presents an improved DBSCAN by embedding a strategy of class constraint, which is called CC-DBSCAN. Specially, based on the RGB and label information of each point in the training samples, by using the logistic regression model, the logistic regression color index (LRCI) is calculated for each point in the clustering samples. Then, points to be clustered are classified as vegetation points and non-vegetation points through the LRCI. Furtherly, the class information of point is introduced as a constraint for ensuring the core point and its directly density-reachable points belong to the same class, thus, solving the problem that confusion cluster of the adjacent vegetation points and non-vegetation points. We evaluate our approach on the benchmark SensatUrban data set, where Cambridge_28 scene data set is taken as the training set, Cambridge_18 scene data set is as the data set to be clustered. Experimental results show that our method achieved 97.20% purity of point cluster, which outperforms the other DBSCAN methods. At the same time, it takes only 24.25s for clustering 2 million points, which indicates that CC-DBSCAN has high computational efficiency and good practicability.