2017/07/09 by Rob Dupre, Dupre, Rob, Vasileios Argyriou +1
Computer Science · Engineering · #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #Evacuation and Crowd Dynamics #FOS: Computer and information sciences #Traffic control and management #Video Surveillance and Tracking Methods
paper · pdf · doi:10.48550/arxiv.1707.02655
openalex publication_date 2017/07/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this work we present the modular Crowd Simulation Evaluation through\nComposition framework (CSEC) which provides a quantitative comparison between\ndifferent pedestrian and crowd simulation approaches. Evaluation is made based\non the comparison of source footage against synthetic video created through\nnovel composition techniques. The proposed framework seeks to reduce the\ncomplexity of simulation evaluation and provide a platform from which the\ncomparison of differing simulation algorithms as well as parametric tuning can\nbe conducted to improve simulation accuracy or providing measures of similarity\nbetween crowd simulation algorithms and source data. Through the use of\nfeatures designed to mimic the Human Visual System (HVS), specific simulation\nproperties can be evaluated relative to sample footage. Validation was\nperformed on a number of popular crowd datasets and through comparisons of\nmultiple pedestrian and crowd simulation algorithms.\n