This paper presents a methodology to simulate and visualize crowds. Our goal is to represent the ... more This paper presents a methodology to simulate and visualize crowds. Our goal is to represent the most realistic possible scenarios in a city. Due to the high demand of resources a GPU Cluster is used. We use real data from which we identify the behavior of the masses applying statistical and artificial intelligence techniques. In order to take advantge of the processing power of the GPU cluster we use the following programming models during the characters simulation: MPI, OmpSs and CUDA. We developed different visualization schemes: a) In situ, b) Streaming, c) Web. The web scheme is the most flexible, allowing to interact in real time with the simulation through a web browser. For this scheme we use WebGL and Cesium.
Large scale crowd simulation and visualization combine computer graphics, artificial intelligence... more Large scale crowd simulation and visualization combine computer graphics, artificial intelligence and high performance computing among other areas. Crowd sourced location data is used to compute spatio-temporal people and vehicle flows, while map and geometric data describe specific real places. With all this data, we can visualize both real trajectories and data driven on-line crowd simulation. We have some initial results using vehicle trajectory data.
Human stampedes caused by panic and overcrowding occur frequently as a result of abnormal events ... more Human stampedes caused by panic and overcrowding occur frequently as a result of abnormal events (e.g., a fire or explosion) produced in collective events (e.g., religious pilgrimages, music concerts and sportive events). These events provoke panic and when people are agglomerated they try to escape pushing each other without realizing that others are being crushed. Since crowds can consist of individuals with diverse physical and social characteristics determined by cultural diversity, it is difficult to configure the space in advance and find solutions in real-time to save people and reduce catastrophe. This paper proposes an approach to explore the impact of anthropometry and cultural diversity in the behaviour of crowds in panic situations. Our approach includes techniques for reproducing and simulating the behaviour of the crowd to generate models that can help decision making to control such situations. The main contribution of our work is to use computational science, data processing and visualization techniques to perform our simulation and study, for eventually supporting critical decision making.
We present a set of algorithms for simulating and visualizing real-time crowds in GPU (Graphics P... more We present a set of algorithms for simulating and visualizing real-time crowds in GPU (Graphics Processing Units) clusters. First we present crowd simulation and rendering techniques that take advantage of single GPU machines. Then, using as an example a wandering crowd behavior simulation algorithm, we explain how this kind of algorithms can be extended for their use in GPU cluster environments. We also present a visualization architecture that renders the simulation results using detailed 3D virtual characters. This architecture is adaptable in order to support the Barcelona Supercomputing Center (BSC) infrastructure. The results show that our algorithms are scalable in different hardware platforms including embedded systems, desktop GPUs, and GPU clusters, in particular, the BSC's Minotauro cluster.
We present a set of algorithms for simulating and visualizing real-time crowds in GPU (Graphics P... more We present a set of algorithms for simulating and visualizing real-time crowds in GPU (Graphics Processing Units) clusters. First we present crowd simulation and rendering techniques that take advantage of single GPU machines. Then, using as an example a wandering crowd behavior simulation algorithm, we explain how this kind of algorithms can be extended for their use in GPU cluster environments. We also present a visualization architecture that renders the simulation results using detailed 3D virtual characters. This architecture is adaptable in order to support the Barcelona Supercomputing Center (BSC) infrastructure. The results show that our algorithms are scalable in different hardware platforms including embedded systems, desktop GPUs, and GPU clusters, in particular, the BSC's Minotauro cluster.
Large scale crowd simulation and visualization combine computer graphics, artificial intelligence... more Large scale crowd simulation and visualization combine computer graphics, artificial intelligence and high performance computing among other areas. Crowd sourced location data is used to compute spatio-temporal people and vehicle flows, while map and geometric data describe specific real places. With all this data, we can visualize both real trajectories and data driven on-line crowd simulation. We have some initial results using vehicle trajectory data.
Human stampedes occur frequently because of abnormal events (e.g., a fire or explosion) produced ... more Human stampedes occur frequently because of abnormal events (e.g., a fire or explosion) produced in collective events (e.g., religious pilgrimages, music concerts and sportive events). These events provoke panic and when people are agglomerated they try to escape pushing each other without realizing that others are being crushed. Since crowds can consist of individuals with diverse physical and social characteristics determined by cultural diversity, it is difficult to configure the space in advance and find solutions in real-time to save people and reduce catastrophe. This paper proposes an approach to explore the impact of anthropometry and cultural diversity in the behaviour of crowds in panic situations. Our approach includes techniques for reproducing and simulating the behaviour of the crowd to generate models that can help decision making to control such situations. The main contribution of our work is to use computational science, data processing and visualization techniques to perform our simulation and study, for eventually supporting critical decision making.
This paper presents a methodology to simulate and visualize crowds. Our goal is to represent the ... more This paper presents a methodology to simulate and visualize crowds. Our goal is to represent the most realistic possible scenarios in a city. Due to the high demand of resources a GPU Cluster is used. We use real data from which we identify the behavior of the masses applying statistical and artificial intelligence techniques. In order to take advantge of the processing power of the GPU cluster we use the following programming models during the characters simulation: MPI, OmpSs and CUDA. We developed different visualization schemes: a) In situ, b) Streaming, c) Web. The web scheme is the most flexible, allowing to interact in real time with the simulation through a web browser. For this scheme we use WebGL and Cesium.
Large scale crowd simulation and visualization combine computer graphics, artificial intelligence... more Large scale crowd simulation and visualization combine computer graphics, artificial intelligence and high performance computing among other areas. Crowd sourced location data is used to compute spatio-temporal people and vehicle flows, while map and geometric data describe specific real places. With all this data, we can visualize both real trajectories and data driven on-line crowd simulation. We have some initial results using vehicle trajectory data.
Human stampedes caused by panic and overcrowding occur frequently as a result of abnormal events ... more Human stampedes caused by panic and overcrowding occur frequently as a result of abnormal events (e.g., a fire or explosion) produced in collective events (e.g., religious pilgrimages, music concerts and sportive events). These events provoke panic and when people are agglomerated they try to escape pushing each other without realizing that others are being crushed. Since crowds can consist of individuals with diverse physical and social characteristics determined by cultural diversity, it is difficult to configure the space in advance and find solutions in real-time to save people and reduce catastrophe. This paper proposes an approach to explore the impact of anthropometry and cultural diversity in the behaviour of crowds in panic situations. Our approach includes techniques for reproducing and simulating the behaviour of the crowd to generate models that can help decision making to control such situations. The main contribution of our work is to use computational science, data processing and visualization techniques to perform our simulation and study, for eventually supporting critical decision making.
We present a set of algorithms for simulating and visualizing real-time crowds in GPU (Graphics P... more We present a set of algorithms for simulating and visualizing real-time crowds in GPU (Graphics Processing Units) clusters. First we present crowd simulation and rendering techniques that take advantage of single GPU machines. Then, using as an example a wandering crowd behavior simulation algorithm, we explain how this kind of algorithms can be extended for their use in GPU cluster environments. We also present a visualization architecture that renders the simulation results using detailed 3D virtual characters. This architecture is adaptable in order to support the Barcelona Supercomputing Center (BSC) infrastructure. The results show that our algorithms are scalable in different hardware platforms including embedded systems, desktop GPUs, and GPU clusters, in particular, the BSC's Minotauro cluster.
We present a set of algorithms for simulating and visualizing real-time crowds in GPU (Graphics P... more We present a set of algorithms for simulating and visualizing real-time crowds in GPU (Graphics Processing Units) clusters. First we present crowd simulation and rendering techniques that take advantage of single GPU machines. Then, using as an example a wandering crowd behavior simulation algorithm, we explain how this kind of algorithms can be extended for their use in GPU cluster environments. We also present a visualization architecture that renders the simulation results using detailed 3D virtual characters. This architecture is adaptable in order to support the Barcelona Supercomputing Center (BSC) infrastructure. The results show that our algorithms are scalable in different hardware platforms including embedded systems, desktop GPUs, and GPU clusters, in particular, the BSC's Minotauro cluster.
Large scale crowd simulation and visualization combine computer graphics, artificial intelligence... more Large scale crowd simulation and visualization combine computer graphics, artificial intelligence and high performance computing among other areas. Crowd sourced location data is used to compute spatio-temporal people and vehicle flows, while map and geometric data describe specific real places. With all this data, we can visualize both real trajectories and data driven on-line crowd simulation. We have some initial results using vehicle trajectory data.
Human stampedes occur frequently because of abnormal events (e.g., a fire or explosion) produced ... more Human stampedes occur frequently because of abnormal events (e.g., a fire or explosion) produced in collective events (e.g., religious pilgrimages, music concerts and sportive events). These events provoke panic and when people are agglomerated they try to escape pushing each other without realizing that others are being crushed. Since crowds can consist of individuals with diverse physical and social characteristics determined by cultural diversity, it is difficult to configure the space in advance and find solutions in real-time to save people and reduce catastrophe. This paper proposes an approach to explore the impact of anthropometry and cultural diversity in the behaviour of crowds in panic situations. Our approach includes techniques for reproducing and simulating the behaviour of the crowd to generate models that can help decision making to control such situations. The main contribution of our work is to use computational science, data processing and visualization techniques to perform our simulation and study, for eventually supporting critical decision making.
Uploads
Papers by Hugo Perez