Details
Original language | English |
---|---|
Pages (from-to) | 331-350 |
Number of pages | 20 |
Journal | ISPRS Journal of Photogrammetry and Remote Sensing |
Volume | 215 |
Early online date | 23 Jul 2024 |
Publication status | Published - Sept 2024 |
Abstract
Recent advances in mobile mapping systems have greatly enhanced the efficiency and convenience of acquiring urban 3D data. These systems utilize LiDAR sensors mounted on vehicles to capture vast cityscapes. However, a significant challenge arises due to occlusions caused by roadside parked vehicles, leading to the loss of scene information, particularly on the roads, sidewalks, curbs, and the lower sections of buildings. In this study, we present a novel approach that leverages deep neural networks to learn a model capable of filling gaps in urban scenes that are obscured by vehicle occlusion. We have developed an innovative technique where we place virtual vehicle models along road boundaries in the gap-free scene and utilize a ray-casting algorithm to create a new scene with occluded gaps. This allows us to generate diverse and realistic urban point cloud scenes with and without vehicle occlusion, surpassing the limitations of real-world training data collection and annotation. Furthermore, we introduce the Scene Gap Completion Network (SGC-Net), an end-to-end model that can generate well-defined shape boundaries and smooth surfaces within occluded gaps. The experiment results reveal that 97.66% of the filled points fall within a range of 5 centimeters relative to the high-density ground truth point cloud scene. These findings underscore the efficacy of our proposed model in gap completion and reconstructing urban scenes affected by vehicle occlusions.
Keywords
- 3D scene completion, LiDAR mobile mapping, Point cloud processing
ASJC Scopus subject areas
- Physics and Astronomy(all)
- Atomic and Molecular Physics, and Optics
- Engineering(all)
- Engineering (miscellaneous)
- Computer Science(all)
- Computer Science Applications
- Earth and Planetary Sciences(all)
- Computers in Earth Sciences
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 215, 09.2024, p. 331-350.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Gap completion in point cloud scene occluded by vehicles using SGC-Net
AU - Feng, Yu
AU - Xu, Yiming
AU - Xia, Yan
AU - Brenner, Claus
AU - Sester, Monika
N1 - Publisher Copyright: © 2024 The Author(s)
PY - 2024/9
Y1 - 2024/9
N2 - Recent advances in mobile mapping systems have greatly enhanced the efficiency and convenience of acquiring urban 3D data. These systems utilize LiDAR sensors mounted on vehicles to capture vast cityscapes. However, a significant challenge arises due to occlusions caused by roadside parked vehicles, leading to the loss of scene information, particularly on the roads, sidewalks, curbs, and the lower sections of buildings. In this study, we present a novel approach that leverages deep neural networks to learn a model capable of filling gaps in urban scenes that are obscured by vehicle occlusion. We have developed an innovative technique where we place virtual vehicle models along road boundaries in the gap-free scene and utilize a ray-casting algorithm to create a new scene with occluded gaps. This allows us to generate diverse and realistic urban point cloud scenes with and without vehicle occlusion, surpassing the limitations of real-world training data collection and annotation. Furthermore, we introduce the Scene Gap Completion Network (SGC-Net), an end-to-end model that can generate well-defined shape boundaries and smooth surfaces within occluded gaps. The experiment results reveal that 97.66% of the filled points fall within a range of 5 centimeters relative to the high-density ground truth point cloud scene. These findings underscore the efficacy of our proposed model in gap completion and reconstructing urban scenes affected by vehicle occlusions.
AB - Recent advances in mobile mapping systems have greatly enhanced the efficiency and convenience of acquiring urban 3D data. These systems utilize LiDAR sensors mounted on vehicles to capture vast cityscapes. However, a significant challenge arises due to occlusions caused by roadside parked vehicles, leading to the loss of scene information, particularly on the roads, sidewalks, curbs, and the lower sections of buildings. In this study, we present a novel approach that leverages deep neural networks to learn a model capable of filling gaps in urban scenes that are obscured by vehicle occlusion. We have developed an innovative technique where we place virtual vehicle models along road boundaries in the gap-free scene and utilize a ray-casting algorithm to create a new scene with occluded gaps. This allows us to generate diverse and realistic urban point cloud scenes with and without vehicle occlusion, surpassing the limitations of real-world training data collection and annotation. Furthermore, we introduce the Scene Gap Completion Network (SGC-Net), an end-to-end model that can generate well-defined shape boundaries and smooth surfaces within occluded gaps. The experiment results reveal that 97.66% of the filled points fall within a range of 5 centimeters relative to the high-density ground truth point cloud scene. These findings underscore the efficacy of our proposed model in gap completion and reconstructing urban scenes affected by vehicle occlusions.
KW - 3D scene completion
KW - LiDAR mobile mapping
KW - Point cloud processing
UR - http://www.scopus.com/inward/record.url?scp=85199285161&partnerID=8YFLogxK
U2 - 10.1016/j.isprsjprs.2024.07.009
DO - 10.1016/j.isprsjprs.2024.07.009
M3 - Article
AN - SCOPUS:85199285161
VL - 215
SP - 331
EP - 350
JO - ISPRS Journal of Photogrammetry and Remote Sensing
JF - ISPRS Journal of Photogrammetry and Remote Sensing
SN - 0924-2716
ER -