Semantic Classification of 3D Point Clouds with Multiscale Spherical Neighborhoods
This work addresses the challenge of consistent feature extraction for 3D point cloud classification, which is important for applications like autonomous driving and robotics, though it is incremental in improving existing methods.
The paper tackled the problem of semantic classification of 3D point clouds by introducing a new multiscale neighborhood definition based on spherical neighborhoods and proportional subsampling, which outperformed state-of-the-art features and competed with deep learning methods in classification tasks.
This paper introduces a new definition of multiscale neighborhoods in 3D point clouds. This definition, based on spherical neighborhoods and proportional subsampling, allows the computation of features with a consistent geometrical meaning, which is not the case when using k-nearest neighbors. With an appropriate learning strategy, the proposed features can be used in a random forest to classify 3D points. In this semantic classification task, we show that our multiscale features outperform state-of-the-art features using the same experimental conditions. Furthermore, their classification power competes with more elaborate classification approaches including Deep Learning methods.