Development of a Realistic Crowd Simulation Environment for Fine-grained Validation of People Tracking Methods
This work addresses the need for efficient and realistic synthetic data generation for people-tracking research, though it is incremental as it extends existing simulation tools.
The authors developed CrowdSim2, a realistic crowd simulation environment using Unity 3D, to generate scenario-specific datasets for validating people-tracking algorithms, and tested it with three tracking methods (IOU-Tracker, Deep-Sort, Deep-TAMA).
Generally, crowd datasets can be collected or generated from real or synthetic sources. Real data is generated by using infrastructure-based sensors (such as static cameras or other sensors). The use of simulation tools can significantly reduce the time required to generate scenario-specific crowd datasets, facilitate data-driven research, and next build functional machine learning models. The main goal of this work was to develop an extension of crowd simulation (named CrowdSim2) and prove its usability in the application of people-tracking algorithms. The simulator is developed using the very popular Unity 3D engine with particular emphasis on the aspects of realism in the environment, weather conditions, traffic, and the movement and models of individual agents. Finally, three methods of tracking were used to validate generated dataset: IOU-Tracker, Deep-Sort, and Deep-TAMA.