.png){kind=icon}
.png){kind=icon}
Return
Exploring Semantic Information Extraction From Different Data Forms in 3D Point Cloud Semantic Segmentation
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2023.3287940.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
As a critical step in 3D scene understanding, semantic segmentation of point clouds has broad application scenarios, including intelligent driving, augmented reality, smart factories, etc. Point cloud data is complex and irregular, and traditional machine learning methods are difficult to achieve ideal segmentation results. Deep learning techniques have yielded remarkable outcomes for researchers, leading to a surge in interest in investigating the semantic segmentation of point clouds. This article begins by examining the difficulties involved in segmenting point clouds by analyzing the inherent structural characteristics of point clouds. Then, commonly used datasets for point cloud semantic segmentation and evaluation metrics for assessing segmentation performance were introduced. Subsequently, an exploration was carried out on extracting semantic information from different data forms in point cloud semantic segmentation. Based on these findings, the experimental results of these methods on publicly available datasets are compared quantitatively. Lastly, several outlooks are presented regarding the future development of semantic segmentation techniques for 3D point clouds. The point cloud semantic segmentation techniques summarized in this paper are mainly from the state-of-the-art methods presented at top international conferences. The goal is to provide a comprehensive overview of this field's state of the art and can be used as a reference for researchers and beginners.
Keywords:
3D point cloud
deep learning
public datasets
semantic segmentation