Abstract: On the background of the national improvement of public safety governance, this paper proposes a comprehensive framework for modeling and optimizing pedestrian emergency evacuation in public spaces based on video data. The framework utilizes real video data from specific public place and scenarios to construct pedestrian evacuation simulation models, comprising both route decision models and microscopic movement models. By establishing a pedestrian evacuation simulation system and developing optimization algorithms focused on rapid evacuation, the framework determines optimal configurations for various facility elements. In the case study, extensive surveillance video data from the Huazhong Agricultural University library during an earthquake was collected and analyzed. Using the proposed framework, pedestrian evacuation models and simulation systems were developed for this specific scenario. Considering multiple situations including different number of pedestrians, elevator availability, and power outage with low visibility conditions, the simulation optimization algorithms is used to analyze the simulation results, and the conclusions on how to open the stairs, elevators, gate machines and how to set the entrances and exits of the reading room in different situations are obtained. The main contribution of this paper lies in proposing a universally applicable and comprehensive solution for optimizing public place elements to facilitate rapid pedestrian evacuation. By integrating video data analysis, pedestrian movement modeling, and simulation optimization, this framework provides a scientific basis for decision-making in public safety management.

Key words: public place, pedestrian safety, evacuation, video data, simulation optimization