Grant: Alliance Grants
Université Laval
$41,554.00
Quality control and progress monitoring from large-scale 3D point clouds
EF 2024-25
Résumé
The advent of new 3D sensors clearly marks a revolution for the infrastructure and construction industry, but they also come with their own set of issues. One of the simplest ways to summarize most of these is by stressing the important distinction between gathering and using data. The main problem faced by construction and infrastructure companies has shifted from data acquisition to data interpretation. One example of such a transition is the as-built vs. as-design comparison. The mere task of aligning these 3D modalities (CAD models and high density point clouds) is challenging because of the incompleteness, noise, discrepancies, and occlusions that inevitably occur in any real-world 3D capture. In addition, there may exist structural differences between the CAD model and the point cloud (that is the point of comparing them), which further complicates their alignment.
The main goal of this project is to provide tools to engineers, architects, designers, inspectors, surveyors, and other professionals to assist them in tedious and time-consuming tasks related to the exploitation of those new sensors and techniques. By designing systems able to intelligently clean, pre-process and interpret a 3D representation embedded in a raw point cloud within specific professional contexts, to point out potential problematic situations before they even occur, and to produce helpful abstractions to better assess a situation, it will be possible to reduce the workload and improve the efficiency of the professionals overseeing construction sites. In turn, this will lead to cost reductions and new possibilities such as more frequent surveys, increasing the chances of early error catching and reducing the risk of cost and time overruns. This could also have an impact on the safety and security of workers.
Programme
Alliance Grants
Bénéficiaire
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
580274-2022
Name nom
Lalonde, Jean-François JF
Department département
Génie électrique et génie informatique
Organization id
51
Institution établissement
Université Laval
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2022
Award amount
41554
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
1001
Area of application group en
Northern development
Area of application group fr
Développement du nord
Area of application en
Construction, transportation and communications
Area of application fr
Construction, transports et communications
Research subject code
2605
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Pattern analysis and machine intelligence
Research subject fr
Analyse de formes et intelligence artificielle
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Quality control and progress monitoring from large-scale 3D point clouds
Keywords
3d data processing; 3d point clouds; 3d registration; deep learning; denoising; semantic segmentation
Application summary
The advent of new 3D sensors clearly marks a revolution for the infrastructure and construction industry, but they also come with their own set of issues. One of the simplest ways to summarize most of these is by stressing the important distinction between gathering and using data. The main problem faced by construction and infrastructure companies has shifted from data acquisition to data interpretation. One example of such a transition is the as-built vs. as-design comparison. The mere task of aligning these 3D modalities (CAD models and high density point clouds) is challenging because of the incompleteness, noise, discrepancies, and occlusions that inevitably occur in any real-world 3D capture. In addition, there may exist structural differences between the CAD model and the point cloud (that is the point of comparing them), which further complicates their alignment.
The main goal of this project is to provide tools to engineers, architects, designers, inspectors, surveyors, and other professionals to assist them in tedious and time-consuming tasks related to the exploitation of those new sensors and techniques. By designing systems able to intelligently clean, pre-process and interpret a 3D representation embedded in a raw point cloud within specific professional contexts, to point out potential problematic situations before they even occur, and to produce helpful abstractions to better assess a situation, it will be possible to reduce the workload and improve the efficiency of the professionals overseeing construction sites. In turn, this will lead to cost reductions and new possibilities such as more frequent surveys, increasing the chances of early error catching and reducing the risk of cost and time overruns. This could also have an impact on the safety and security of workers.