Abstracts – Browse Results
Click on the titles below to expand the information about each abstract.
Viewing 17 results ...
Abdelkader, E M, Moselhi, O, Marzouk, M and Zayed, T (2021) Integrative Evolutionary-Based Method for Modeling and Optimizing Budget Assignment of Bridge Maintenance Priorities. Journal of Construction Engineering and Management, 147(09).
Ahmed, A, Mohammed, H A, Gambatese, J and Hurwitz, D (2021) Effects of Flashing Blue Lights Mounted on Paving Equipment on Vehicle Speed Behavior in Work Zones. Journal of Construction Engineering and Management, 147(09).
Cai, Q, Hu, Q and Ma, G (2021) Improved Hybrid Reasoning Approach to Safety Risk Perception under Uncertainty for Mountain Tunnel Construction. Journal of Construction Engineering and Management, 147(09).
Chen, B, Yu, X, Dong, F, Zheng, C, Ding, G and Wu, W (2021) Compaction Quality Evaluation of Asphalt Pavement Based on Intelligent Compaction Technology. Journal of Construction Engineering and Management, 147(09).
Hajj, C E, Jawad, D and Montes, G M (2021) Analysis of a Construction Innovative Solution from the Perspective of an Information System Theory. Journal of Construction Engineering and Management, 147(09).
Hasan, A, Rameezdeen, R, Baroudi, B and Ahn, S (2021) Mobile ICT–Induced Informal Work in the Construction Industry: Boundary Management Approaches and Consequences. Journal of Construction Engineering and Management, 147(09).
Hassan, F u, Le, T and Lv, X (2021) Addressing Legal and Contractual Matters in Construction Using Natural Language Processing: A Critical Review. Journal of Construction Engineering and Management, 147(09).
Huang, H, Zhang, C and Hammad, A (2021) Effective Scanning Range Estimation for Using TLS in Construction Projects. Journal of Construction Engineering and Management, 147(09).
Jiang, Y and Bai, Y (2021) Low–High Orthoimage Pairs-Based 3D Reconstruction for Elevation Determination Using Drone. Journal of Construction Engineering and Management, 147(09).
Johannes, K, Theodorus Voordijk, J, Marias Adriaanse, A and Aranda-Mena, G (2021) Identifying Maturity Dimensions for Smart Maintenance Management of Constructed Assets: A Multiple Case Study. Journal of Construction Engineering and Management, 147(09).
Kar, S and Jha, K N (2021) Exploring the Critical Barriers to and Enablers of Sustainable Material Management Practices in the Construction Industry. Journal of Construction Engineering and Management, 147(09).
Noghabaei, M, Han, K and Albert, A (2021) Feasibility Study to Identify Brain Activity and Eye-Tracking Features for Assessing Hazard Recognition Using Consumer-Grade Wearables in an Immersive Virtual Environment. Journal of Construction Engineering and Management, 147(09).
Perez-Perez, Y, Golparvar-Fard, M and El-Rayes, K (2021) Scan2BIM-NET: Deep Learning Method for Segmentation of Point Clouds for Scan-to-BIM. Journal of Construction Engineering and Management, 147(09).
Raoufi, M and Fayek, A R (2021) How to Improve Crew Motivation and Performance on Construction Sites. Journal of Construction Engineering and Management, 147(09).
Taghizadeh, K, Alizadeh, M and Yavari Roushan, T (2021) Cooperative Game Theory Solution to Design Liability Assignment Issues in BIM Projects. Journal of Construction Engineering and Management, 147(09).
Votto, R, Lee Ho, L and Berssaneti, F (2021) Earned Duration Management Control Charts: Role of Control Limit Width Definition for Construction Project Duration Monitoring. Journal of Construction Engineering and Management, 147(09).
Xu, Y, Shen, X, Lim, S and Li, X (2021) Three-Dimensional Object Detection with Deep Neural Networks for Automatic As-Built Reconstruction. Journal of Construction Engineering and Management, 147(09).
- Type: Journal Article
- Keywords: As-built modeling; Volumetric reconstruction; Three-dimensional (3D) object detection; Deep learning; Point clouds; Building information model (BIM);
- ISBN/ISSN: 0733-9364
- URL: https://doi.org/10.1061/(ASCE)CO.1943-7862.0002003
- Abstract:
Automatic three-dimensional (3D) as-built reconstruction for non-Manhattan structures and multiroom buildings remains an industrywide challenge due to complex building environments and high demands for generating volumetric and object-level models. Conventional approaches are based on multiple separate steps extracting geometric and semantic features independently that cannot fully exploit object-level features. This paper aims to develop an end-to-end, fully automatic, and object-level reconstruction approach to converting point clouds of non-Manhattan and multiroom buildings into 3D models. A two-stage 3D object-detection method is proposed using region-based convolutional neural networks (R-CNN). Feature fusion between sparse 3D and two-dimensional (2D) bird’s eye view (BEV) feature maps is investigated to improve the generality and efficiency of modeling building primitives. In order to address the difficulties of training label generation caused by largely overlapped building objects, a dual-channel network is developed with one channel detecting walls and the other channel detecting remaining categories. The experimental results achieved an overall detection accuracy of 85.79% and localization accuracy of 79.03%, which have increased by 12.75% and 5.71% over the latest benchmarks, respectively. It took an average of 4.75 s to reconstruct a single-story building with a mean footprint of