Plane Segmentation in Outdoor Imagery DOI Open Access
Haolin Liang, Shawn Newsam

Published: Nov. 13, 2023

Plane segmentation in monocular images plays an important role understanding the geometry of a 3D environment. However, most previous plane work focuses mostly on indoor environments since it is hard to create precise planar annotations outdoor for training. In this work, we proposed framework automatically generate synthetic data any given building model, that can be used and tasks. We also conduct experiments evaluate applicability real-world scenarios. show models trained understand geometry.

Language: Английский

Improving facade parsing with vision transformers and line integration DOI
Bowen Wang, Jiaxin Zhang, Ran Zhang

et al.

Advanced Engineering Informatics, Journal Year: 2024, Volume and Issue: 60, P. 102463 - 102463

Published: March 3, 2024

Language: Английский

Citations

15
Generating Synthetic Images for Construction Machinery Data Augmentation Utilizing Context-Aware Object Placement DOI Creative Commons
Yujie Lu, Bo Liu, Wei We

et al.

Developments in the Built Environment, Journal Year: 2025, Volume and Issue: unknown, P. 100610 - 100610

Published: Jan. 1, 2025

Language: Английский

Citations

0
Addressing Data Scarcity in Crack Detection via CrackModel: A Novel Dataset Synthesis Approach DOI Creative Commons
Jian Ma, Yuan Meng, Weidong Yan

et al.

Buildings, Journal Year: 2025, Volume and Issue: 15(7), P. 1053 - 1053

Published: March 25, 2025

The application of deep learning in crack detection has become a research hotspot Structural Health Monitoring (SHM). However, the potential models is often limited due to lack large-scale training data, and this issue particularly prominent ancient wooden buildings China. To address challenge, “CrackModel”, an innovative dataset construction model, proposed paper. This model capable extracting storing information from hundreds images structures with cracks synthesizing data intact generate high-fidelity for algorithms. evaluate effectiveness synthetic systematic experiments were conducted using YOLO-based on both real data. results demonstrate that can effectively simulate providing support subsequent tasks. Additionally, these findings validate efficacy CrackModel generating CrackModel, supported by baseline constructing datasets across various scenarios simulating future damage, showcasing its broad field structural engineering.

Language: Английский

Citations

0
Enhancing intrusion detection using wireless sensor networks: A novel ahp-madm aggregated multiple type 3 fuzzy logic-based k-barriers prediction system DOI
Anirban Tarafdar,

Azharuddin Sheikh,

Pinki Majumder

et al.

Peer-to-Peer Networking and Applications, Journal Year: 2024, Volume and Issue: 17(3), P. 1732 - 1749

Published: March 26, 2024

Language: Английский

Citations

3
A perception-powered urban digital twin to support human-centered urban planning and sustainable city development DOI
Junjie Luo, Pengyuan Liu,

Wenhui Xu

et al.

Cities, Journal Year: 2024, Volume and Issue: 156, P. 105473 - 105473

Published: Oct. 21, 2024

Language: Английский

Citations

3
A systematic review and evaluation of synthetic simulated data generation strategies for deep learning applications in construction DOI
Li-Qun Xu, Hexu Liu, Bo Xiao

et al.

Advanced Engineering Informatics, Journal Year: 2024, Volume and Issue: 62, P. 102699 - 102699

Published: July 11, 2024

Language: Английский

Citations

2
Automatic identification of bottlenecks for ambulance passage on urban streets: A deep learning-based approach DOI

Shuo Pan,

Zhuo Liu, Hai Yan

et al.

Advanced Engineering Informatics, Journal Year: 2024, Volume and Issue: 62, P. 102931 - 102931

Published: Oct. 1, 2024

Language: Английский

Citations

2
Evaluation of the urban heat island effect based on 3D modeling and planning indicators for urban planning proposals DOI Creative Commons
Yanwen Luo, Jiang He

Journal of Asian Architecture and Building Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 23

Published: Oct. 6, 2024

Urban planning plays an important role in the formation of urban space and microclimate. As a middle-level Chinese system, regulatory has direct impact on shaping 3D can maximize operability planning. However, is not considered present preparation plans, which leads to misunderstanding possibly formed landscapes microclimatic effects after plan implementation. To support visualization quantitative analysis heat island effect (UHI) for planning, this study proposes rule-based modeling method efficiently generate models. The main elements models (terrain, building, road, vegetation, land parcel) their content were determined analyzing characteristics plan. process was constructed combined with UHI evaluation model through CGA programming. An index called potential (HIP) used as be quantified using correlation equations between indicators HIP. proposed planners proposal, simultaneously analyze spatial UHI.

Language: Английский

Citations

0
Plane Segmentation in Outdoor Imagery DOI Open Access
Haolin Liang, Shawn Newsam

Published: Nov. 13, 2023

Plane segmentation in monocular images plays an important role understanding the geometry of a 3D environment. However, most previous plane work focuses mostly on indoor environments since it is hard to create precise planar annotations outdoor for training. In this work, we proposed framework automatically generate synthetic data any given building model, that can be used and tasks. We also conduct experiments evaluate applicability real-world scenarios. show models trained understand geometry.

Language: Английский

Citations

0