Point Cloud Based 3d Models for Agent Based Simulations in Social Distancing and Evacuation

Nikoohemat, S.; Godoy, Pablo; Valkhoff, N.; Leeuwen, M. Wouters van; Voûte, R.; Lehtola, Ville V.

doi:10.5194/isprs-annals-v-4-2021-113-2021

Cited by 2 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From the processed point clouds, we separate wall, floor, and ceiling classes to reconstruct planar geometries as polyhedrons using Polyfit [Nan and Wonka, 2017], a polygonal surface reconstruction tool [Nikoohemat et al, 2021]. Then the identified safety-related assets are added to the obtained mesh to construct the final 3D-geometry model.…”

Section: Post-processing and 3d-geometry Modelsmentioning

confidence: 99%

Needle in a Haystack: Feasibility of Identifying Small Safety Assets From Point Clouds Using Deep Learning

Anjanappa,

Nikoohemat,

Oude Elberink

et al. 2023

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Asset management systems are beneficial for maintaining building infrastructure and can be used to keep up-to-date records of relevant safety assets, such as smoke detectors, exit signs, and fire extinguishers. Existing methods for locating and identifying these assets in buildings primarily rely on surveys and images, which only provide 2D locations and can be tedious for large-scale structures. Indoor point clouds, which can be captured quickly for buildings using mobile scanning techniques, can provide us with 3D asset locations. In this paper, we study the feasibility of using 3D point clouds of buildings combined with deep learning techniques to identify safety-related assets, particularly small-sized assets like fire switches and exit signs. We adopt the state-of-the-art Deep Learning network, Kernel Point-Fully Convolutional Network (KP-FCNN), to identify these assets through semantic segmentation. Using the obtained results, we create a 3D-geometry model of the building with assets pinpointed, providing scene semantics and delivering more value. Our method is tested using three different point cloud datasets obtained from a depth camera, a mobile laser scanner, and an iPhone lidar sensor.

show abstract

Section: Post-processing and 3d-geometry Modelsmentioning

confidence: 99%

Needle in a Haystack: Feasibility of Identifying Small Safety Assets From Point Clouds Using Deep Learning

Anjanappa,

Nikoohemat,

Oude Elberink

et al. 2023

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Cuevas presents an agent-based model for COVID-19 transmission with a focus on agent interactions [41]. Nikoohemat et al focus on building realistic point-cloud models for simulation [42], while Kramer and Wang did a study on the adverse effects of social distancing on pedestrian movement [43]. Last but not least, Mayr and Köster propose an "optimal steps model", with focus on keeping distances [10].…”

Section: Related Workmentioning

confidence: 99%

Agent-Based Simulation for Infectious Disease Modelling over a Period of Multiple Days, with Application to an Airport Scenario

Harweg

Wagner

Weichert

2022

IJERPH

View full text Add to dashboard Cite

With the COVID-19 pandemic, the role of infectious disease spreading in public places has been brought into focus more than ever. Places that are of particular interest regarding the spread of infectious diseases are international airport terminals, not only for the protection of staff and ground crew members but also to help minimize the risk of the spread of infectious entities such as COVID-19 around the globe. Computational modelling and simulation can help in understanding and predicting the spreading of infectious diseases in any such scenario. In this paper, we propose a model, which combines a simulation of high geometric detail regarding virus spreading with an account of the temporal progress of infection dynamics. We, thus, introduce an agent-based social force model for tracking the spread of infectious diseases by modelling aerosol traces and concentration of virus load in the air. We complement this agent-based model to have consistency over a period of several days. We then apply this model to investigate simulations in a realistic airport setting with multiple virus variants of varying contagiousness. According to our experiments, a virus variant has to be at least twelve times more contagious than the respective control to result in a level of infection of more than 30%. Combinations of agent-based models with temporal components can be valuable tools in an attempt to assess the risk of infection attributable to a particular virus and its variants.

show abstract

Point Cloud Based 3d Models for Agent Based Simulations in Social Distancing and Evacuation

Cited by 2 publications

References 32 publications

Needle in a Haystack: Feasibility of Identifying Small Safety Assets From Point Clouds Using Deep Learning

Needle in a Haystack: Feasibility of Identifying Small Safety Assets From Point Clouds Using Deep Learning

Agent-Based Simulation for Infectious Disease Modelling over a Period of Multiple Days, with Application to an Airport Scenario

Contact Info

Product

Resources

About