MeshNet-SP: A Semantic Urban 3D Mesh Segmentation Network with Sparse Prior
-
Published:2023-11-11
Issue:22
Volume:15
Page:5324
-
ISSN:2072-4292
-
Container-title:Remote Sensing
-
language:en
-
Short-container-title:Remote Sensing
Author:
Zhang Guangyun1ORCID, Zhang Rongting1ORCID
Affiliation:
1. School of Geomatics Science and Technology, Nanjing Tech University, Nanjing 211800, China
Abstract
A textured urban 3D mesh is an important part of 3D real scene technology. Semantically segmenting an urban 3D mesh is a key task in the photogrammetry and remote sensing field. However, due to the irregular structure of a 3D mesh and redundant texture information, it is a challenging issue to obtain high and robust semantic segmentation results for an urban 3D mesh. To address this issue, we propose a semantic urban 3D mesh segmentation network (MeshNet) with sparse prior (SP), named MeshNet-SP. MeshNet-SP consists of a differentiable sparse coding (DSC) subnetwork and a semantic feature extraction (SFE) subnetwork. The DSC subnetwork learns low-intrinsic-dimensional features from raw texture information, which increases the effectiveness and robustness of semantic urban 3D mesh segmentation. The SFE subnetwork produces high-level semantic features from the combination of features containing the geometric features of a mesh and the low-intrinsic-dimensional features of texture information. The proposed method is evaluated on the SUM dataset. The results of ablation experiments demonstrate that the low-intrinsic-dimensional feature is the key to achieving high and robust semantic segmentation results. The comparison results show that the proposed method can achieve competitive accuracies, and the maximum increase can reach 34.5%, 35.4%, and 31.8% in mR, mF1, and mIoU, respectively.
Funder
Natural Science Foundation of Jiangsu Province National Natural Science Foundation of China the Key Laboratory Independent Research Foundation
Subject
General Earth and Planetary Sciences
Reference56 articles.
1. Skondras, A., Karachaliou, E., Tavantzis, I., Tokas, N., Valari, E., Skalidi, I., Bouvet, G.A., and Stylianidis, E. (2022). UAV Mapping and 3D Modeling as a Tool for Promotion and Management of the Urban Space. Drones, 6. 2. Urban form simulation in 3D based on cellular automata and building objects generation;Chen;Build. Environ.,2022 3. Gong, Y., Zhang, F., Jia, X., Huang, X., Li, D., and Mao, Z. (2021). Deep Neural Networks for Quantitative Damage Evaluation of Building Losses Using Aerial Oblique Images: Case Study on the Great Wall (China). Remote Sens., 13. 4. Hong, Z., Yang, Y., Liu, J., Jiang, S., Pan, H., Zhou, R., Zhang, Y., Han, Y., Wang, J., and Yang, S. (2022). Enhancing 3D reconstruction model by deep learning and its application in building damage assessment after earthquake. Appl. Sci., 12. 5. Zhang, Y., Dai, Z., Wang, W., Li, X., Chen, S., and Chen, L. (2021). Estimation of the Potential Achievable Solar Energy of the Buildings Using Photogrammetric Mesh Models. Remote Sens., 13.
|
|