• The Journal of the Korea institute of electronic communication sciences
• /
• v.2 no.2
• /
• pp.106-112
• /
• 2007

Recently the crowd environment in the department of the animation is necessary to the digital industry. The goal of researching a proper crowd animation is to design character animation that is defined by the reality of scenes, performance of system and interaction with users to show the crowd vividly and effectively in cyber underwater. It is important to set up the crowd behavior patterns to represent for moving crowd naturally in cyber space. In the paper, we expressed the behavior patterns for flocks of fish in cyber underwater, and compared with the number of mesh, the number of fish, the number of frame, elapsed time, and resolution and analyzed them with the fish behavior simulating system.

• Journal of Korea Multimedia Society
• /
• v.24 no.5
• /
• pp.629-641
• /
• 2021

Crowd behavior simulations have been studied to further accelerated and refined by parallelism by inducing agent-interacting forces into the image field representing the forces of attraction and repulsion. However, it was difficult to consider rapidly changing environments such as fire situations in buildings because texture images must be generated in advance simulation starts and simulations can only be performed in 2D spaces. In this paper, we propose a crowd agent behavior simulation method based on agent's 3D affordance field for flexible agent behavior in variable geomorphological environments in 3D space. The proposed method generates 3D affordance field related to agents and sensors in 3D space and defines the agent behavior in 3D space for the crowd behavior simulation based on an image-inducing field to a 3D space. Experimental results verified that our method enables the development of large-scale crowd behavior simulations that are flexible to various fire evacuation situations in 3D virtual spaces.

• Journal of Korea Multimedia Society
• /
• v.10 no.6
• /
• pp.770-778
• /
• 2007

Fish schooling or group moving in cyber underwater is a part of beautiful and familiar ecosystem. It is not so easy to present the behavior of fish crowd naturally as a computer animation. Thanks to development of computer graphics in entertainment industry, the numbers of digital films and animations is increased and the scenes of numerous crowd are shown to us. Though there are many studies on the techniques to process the behavior of crowd effectively and the developments of crowd behavioral systems, there is not enough study on the development for an efficient crowd behavioral simulator. In this' paper, we smartly present the types offish behavior in cyber underwater and make up for the weak points of time and cost. We develop the fish schooling behavior simulator for the contents of cyber underwater, automating fish behavioral types realistically and efficiently.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.2 no.1
• /
• pp.25-33
• /
• 2007

Crowd behaviors on cyber underwater environment are often produced in entertainment contents, such as films and games. It is easy for us to come in contact with the scenes appearing a lot of characters as digital films and animation works are increased gradually, owing to developing of computer graphics. Though the processing a scene of crowd and the behavior system of crowd, related to the processing techniques of crowd behavior in cyber space, have been implemented so far, the research for developing the natural crowd behavior simulator can not be still satisfying. In this paper, we designed a realistic and efficient Fish Schooling Behavior Simulator for the contents production of cyber underwater environment, which showed each type of fish behavior in cyber underwater smartly, and which generated the animating the behavior automatically, reducing the time and cost.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.1 no.1
• /
• pp.27-35
• /
• 2006

Crowd behaviors on cyber underwater environment are often produced in entertainment contents, such as films and games. It is easy for us to come in contact with the scenes appearing a lot of characters as digital films and animation works are increased gradually, owing to developing of computer graphics. Though the processing a scene of crowd and the behavior system of crowd, related to the processing techniques of crowd behavior in cyber space, have been implemented so far, the research for developing the natural crowd behavior simulator can not be still satisfying. In this paper, we designed a realistic and efficient Fish Schooling Behavior Simulator for the contents production of cyber underwater environment, which showed each type of fish behavior in cyber underwater smartly, and which generated the animating the behavior automatically, reducing the time and cost.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.9
• /
• pp.2170-2190
• /
• 2012

There are nowadays strong demands for intelligent surveillance systems, which can infer or understand more complex behavior. The application of crowd density estimation methods could lead to a better understanding of crowd behavior, improved design of the built environment, and increased pedestrian safety. In this paper, we propose a new crowd density estimation method, which aims at estimating not only a moving crowd, but also a stationary crowd, using images captured from surveillance cameras situated in various public locations. The crowd density of the moving people is measured, based on the moving area during a specified time period. The moving area is defined as the area where the magnitude of the accumulated optical flow exceeds a predefined threshold. In contrast, the stationary crowd density is estimated from the coarseness of textures, under the assumption that each person can be regarded as a textural unit. A multilayer neural network is designed, to classify crowd density levels into 5 classes. Finally, the proposed method is experimented with PETS 2009 and the platform of Gangnam subway station image sequences.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.3769-3789
• /
• 2018

Social pedestrian groups are the basic elements that constitute a crowd; therefore, detection of such groups is scientifically important for modeling social behavior, as well as practically useful for crowd video understanding. A social group refers to a cluster of members who tend to keep similar motion state for a sustained period of time. One of the main challenges of social group detection arises from the complex dynamic variations of crowd patterns. Therefore, most works model dynamic groups to analysis the crowd behavior, ignoring the existence of stationary groups in crowd scene. However, in this paper, we propose a novel unified framework for detecting social pedestrian groups in crowd videos, including dynamic and stationary pedestrian groups, based on spatiotemporal-oriented energy measurements. Dynamic pedestrian groups are hierarchically clustered based on energy flow similarities and trajectory motion correlations between the atomic groups extracted from principal spatiotemporal-oriented energies. Furthermore, the probability distribution of static spatiotemporal-oriented energies is modeled to detect stationary pedestrian groups. Extensive experiments on challenging datasets demonstrate that our method can achieve superior results for social pedestrian group detection and crowd video classification.

• Journal of Korean Society of Steel Construction
• /
• v.24 no.1
• /
• pp.1-11
• /
• 2012

To overcome the limitations of current evaluation procedures for floor vibration under crowd loading, two kinds of uncertainties associated with individual time lag differences and the complex behavior of crowd should be taken into account. The complex behavior of crowds has yet to be fully described, even though individual differences can be dealt with statistically. This paper proposes time lag considered (TLC) crowd model based on a probabilistic approach. The load reduction factor, which reflects the effect of a general degree of synchronization among crowd, is proposed. Extensive Monte Carlo simulations were carried out to determine various crowd behaviors by using the TLC crowd model proposed. The TLC crowd model can rationally treat the energy loss of various crowd patterns. This indicates that it may be used as a theoretical basis in refining dynamic load factor of crowd loading.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.2 no.3
• /
• pp.157-162
• /
• 2007

The goal of researching a proper crowd animation is to design system that is satisfied with the reality of scenes, performance of system, and interaction with users to show the crowd vividly and effectively in virtual underwater world. In this paper, we smartly expressed the behavior patterns for flocks of fish in virtual underwater and we made up for the weak points in spending time and cost to produce crowd animation. We compared with the number of mesh, the number of fish, the number of frame, elapsed time, and resolution and analyzes them with the fish behavior simulating system. We developed a virtual underwater simulator using this system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.912-928
• /
• 2019

Crowd behavior analysis research has revealed a central role in helping people to find safety hazards or crime optimistic forecast. Thus, it is significant in the future video surveillance systems. Recently, the growing demand for safety monitoring has changed the awareness of video surveillance studies from analysis of individuals behavior to group behavior. Group detection is the process before crowd behavior analysis, which separates scene of individuals in a crowd into respective groups by understanding their complex relations. Most existing studies on group detection are scene-specific. Crowds with various densities, structures, and occlusion of each other are the challenges for group detection in diverse crowded scenes. Therefore, we propose a group detection approach called Collective Interaction Filtering to discover people motion interaction from trajectories. This approach is able to deduce people interaction with the Expectation-Maximization algorithm. The Collective Interaction Filtering approach accurately identifies groups by clustering trajectories in crowds with various densities, structures and occlusion of each other. It also tackles grouping consistency between frames. Experiments on the CUHK Crowd Dataset demonstrate that approach used in this study achieves better than previous methods which leads to latest results.