Multigranularity Semantic Labeling of Point Clouds for the Measurement of the Rail Tanker Component With Structure Modeling

• Published in: IEEE transactions on instrumentation and measurement Vol. 70; pp. 1 - 12
• Main Authors: Qi, Chao, Yin, Jianqin
• Format: Journal Article
• Language: English
• Published: New York IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Feature extraction; Graph neural network; Graph neural networks; Image edge detection; Image segmentation; Labeling; Modelling; multigranularity semantic labeling; Neural networks; point cloud; rail tanker; Rails; Semantic segmentation; Semantics; structure modeling; Tank cars; Three dimensional models; Three-dimensional displays; Transportation safety
• ISSN: 0018-9456; 1557-9662
• DOI: 10.1109/TIM.2020.3027406

It is important to ensure every component of the rail tanker with standard dimensions for guaranteeing transportation safety. Point clouds are widely used in the dimension measurement, and the key of the measurement is to segment the point cloud into different components. Currently, the segmentation is realized manually, which is labor-intensive and has high uncertainty. Different from this, we model this problem as semantic segmentation based on point clouds and present an automatic and accurate method for solving it. Previous semantic segmentation methods cannot capture characteristics of inherent geometric structures well, which leads to unexpected segmentation results. Therefore, we explore the inherent geometric structures hidden in the point cloud and propose a new two-stage framework to achieve automatic and accurate segmentation. Especially, the framework consists of structure modeling and semantic labeling. First, we model the inherent geometric structures of the tanker. To this end, the point cloud is partitioned into a few geometrically homogeneous regions, and each region contains points with semantic consistency and geometric continuity. An edge-informative graph is introduced to describe the characteristics of regions and the adjacency relationships between regions. Second, we design a new graph neural network to process the graph with modeling information for component segmentation. The network extracts the deep features for each region and models the interaction between regions. Besides, it obtains the final segmentation by labeling points at different granularity levels. We evaluate our method on the point clouds of different types of tankers. The results show that the overall accuracy of our method can reach 97.53%, and our method shows better performance compared with other baseline methods in almost all metrics.