.png){kind=icon}
.png){kind=icon}
Return
Box-Loc: Box-aware module localization using point cloud and deep learning in modular integrated construction
.png){kind=icon}
PRE
AI
DOI：10.1016/j.aei.2025.104100.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A box-aware module localization (Box-Loc) model is developed using point cloud and deep learning. • A synthetic dataset is created combining both pseudo-lidar and real-life point clouds. • Module localization is achieved via a 3D bounding box with center coordinates and a rotation angle. • Box-Loc advances accuracy from tens of centimeters to a minimum average error of 8.46 cm. • Box-Loc increases module localization efficiency by reducing the time from minutes to 55.7 ms.
Journal
IF:
9.9
Papers:
4.0K
Citations:
1.7W
Organization
No organization information available