| spelling |
oapen-20.500.12657-890432024-04-03T02:22:47Z Chapter Indoor Trajectory Reconstruction Using Building Information Modeling and Graph Neural Networks Li, Mingkai Wong, Peter Kok-Yiu Huang, Cong Cheng, Jack C. P. Indoor trajectory reconstruction Graph neural network Building information modeling Camera-based tracking Spatial graph Pedestrian simulation thema EDItEUR::U Computing and Information Technology::UT Computer networking and communications::UTV Virtualization Trajectory reconstruction of pedestrian is of paramount importance to understand crowd dynamics and human movement pattern, which will provide insights to improve building design, facility management and route planning. Camera-based tracking methods have been widely explored with the rapid development of deep learning techniques. When moving to indoor environment, many challenges occur, including occlusions, complex environments and limited camera placement and coverage. Therefore, we propose a novel indoor trajectory reconstruction method using building information modeling (BIM) and graph neural network (GNN). A spatial graph representation is proposed for indoor environment to capture the spatial relationships of indoor areas and monitoring points. Closed circuit television (CCTV) system is integrated with BIM model through camera registration. Pedestrian simulation is conducted based on the BIM model to simulate the pedestrian movement in the considered indoor environment. The simulation results are embedded into the spatial graph for training of GNN. The indoor trajectory reconstruction is implemented as GNN conducts edge classification on the spatial graph 2024-04-02T15:44:38Z 2024-04-02T15:44:38Z 2023 chapter ONIX_20240402_9791221502893_12 2704-5846 9791221502893 https://library.oapen.org/handle/20.500.12657/89043 eng Proceedings e report application/pdf n/a 9791221502893_89.pdf https://books.fupress.com/doi/capitoli/979-12-215-0289-3_89 Firenze University Press 10.36253/979-12-215-0289-3.89 10.36253/979-12-215-0289-3.89 bf65d21a-78e5-4ba2-983a-dbfa90962870 9791221502893 137 12 Florence open access
|
| description |
Trajectory reconstruction of pedestrian is of paramount importance to understand crowd dynamics and human movement pattern, which will provide insights to improve building design, facility management and route planning. Camera-based tracking methods have been widely explored with the rapid development of deep learning techniques. When moving to indoor environment, many challenges occur, including occlusions, complex environments and limited camera placement and coverage. Therefore, we propose a novel indoor trajectory reconstruction method using building information modeling (BIM) and graph neural network (GNN). A spatial graph representation is proposed for indoor environment to capture the spatial relationships of indoor areas and monitoring points. Closed circuit television (CCTV) system is integrated with BIM model through camera registration. Pedestrian simulation is conducted based on the BIM model to simulate the pedestrian movement in the considered indoor environment. The simulation results are embedded into the spatial graph for training of GNN. The indoor trajectory reconstruction is implemented as GNN conducts edge classification on the spatial graph
|
