FGCN: Image-Fused Point Cloud Semantic Segmentation with Fusion Graph Convolutional Network
Author:
Zhang Kun1, Chen Rui1, Peng Zidong2, Zhu Yawei1, Wang Xiaohong1
Affiliation:
1. College of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang 050018, China 2. College of International Education, Guangxi University of Science and Technology, Liuzhou 545006, China
Abstract
In interpreting a scene for numerous applications, including autonomous driving and robotic navigation, semantic segmentation is crucial. Compared to single-modal data, multi-modal data allow us to extract a richer set of features, which is the benefit of improving segmentation accuracy and effect. We propose a point cloud semantic segmentation method, and a fusion graph convolutional network (FGCN) which extracts the semantic information of each point involved in the two-modal data of images and point clouds. The two-channel k-nearest neighbors (KNN) module of the FGCN was created to address the issue of the feature extraction’s poor efficiency by utilizing picture data. Notably, the FGCN utilizes the spatial attention mechanism to better distinguish more important features and fuses multi-scale features to enhance the generalization capability of the network and increase the accuracy of the semantic segmentation. In the experiment, a self-made semantic segmentation KITTI (SSKIT) dataset was made for the fusion effect. The mean intersection over union (MIoU) of the SSKIT can reach 88.06%. As well as the public datasets, the S3DIS showed that our method can enhance data features and outperform other methods: the MIoU of the S3DIS can reach up to 78.55%. The segmentation accuracy is significantly improved compared with the existing methods, which verifies the effectiveness of the improved algorithms.
Funder
Department of Education of Hebei Province Hebei Science and Technology Department
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference47 articles.
1. Cui, W., Yao, M., Hao, Y., Wang, Z., He, X., Wu, W., Li, J., Zhao, H., Xia, C., and Wang, J. (2021). Knowledge and geo-object based graph convolutional network for remote sensing semantic segmentation. Sensors, 21. 2. Dong, S., and Chen, Z. (2021). A multi-level feature fusion network for remote sensing image segmentation. Sensors, 21. 3. Li, J., Wang, H., Zhang, A., and Liu, Y. (2022). Semantic segmentation of hyperspectral remote sensing images based on PSE-UNet model. Sensors, 22. 4. Teixeira, M.A.S., Nogueira, R.d.C.M., Dalmedico, N., Santos, H.B., Arruda, L.V.R.d., Neves-Jr, F., Pipa, D.R., Ramos, J.E., and Oliveira, A.S.d. (2019). Intelligent 3D perception system for semantic description and dynamic interaction. Sensors, 19. 5. Li, D., Li, C., Chen, C., and Zhao, Z. (2020). Semantic segmentation of a printed circuit board for component recognition based on depth images. Sensors, 20.
|
|