Security is an important topic in our contemporary world, and the ability to automate the detection of any events of interest that can take place in a crowd is of great interest to a population. We hypothesize that the detection of events in videos is correlated with significant changes in pedestrian behaviors. In this paper, we examine three different scenarios of crowd behavior, containing both the cases where an event triggers a change in the behavior of the crowd and two video sequences where the crowd and its motion remain mostly unchanged. With both the videos and the tracking of the individual pedestrians (performed in a pre-processed phase), we use Geomind, a software we developed to extract significant data about the scene, in particular, the geometrical features, personalities, and emotions of each person. We then examine the output, seeking a significant change in the way each person acts as a function of the time, that could be used as a basis to identify events or to model realistic crowd actions. When applied to the games area, our method can use the detected events to find some sort of pattern to be then used in agent simulation. Results indicate that our hypothesis seems valid in the sense that the visually observed events could be automatically detected using GeoMind.

翻译：安全是当代社会的重要议题，实现人群中有意义事件的自动化检测具有重大社会价值。我们假设视频中事件的检测与行人行为的显著变化相关。本文研究了三种不同的人群行为场景，包含事件触发行为变化的案例，以及两段人群运动基本保持不变的视频序列。基于视频和预处理阶段完成的单个行人追踪，我们使用自主研发的GeoMind软件提取场景关键数据，包括每个行人的几何特征、个性特征和情绪状态。随后通过分析输出结果，探究个体行为随时间变化的显著波动——这种波动可作为事件识别或真实人群行为建模的基础。在游戏领域应用时，该方法可利用检测到的事件寻找行为模式，进而用于智能体仿真。实验结果表明，我们的假设具有可行性：通过GeoMind可以自动检测到视觉上可观察到的事件。