Video Driven Crowd Synthesis

Jordan Stadler
Faisal Z. Qureshi (


We present a framework for video-driven crowd synthesis. The proposed framework employs motion analysis techniques to extract inter-frame motion vectors from the exem- plar crowd videos. Motion vectors collected over the duration of the video are processed to compute global motion paths. These paths encode the dominant motions observed during the course of the video. These paths are then fed into a behavior-based crowd sim- ulation framework, which is responsible for synthesizing crowd animations that respect the motion patterns observed in the video. Our system synthesizes 3D virtual crowds by animating virtual humans along the trajectories returned by the crowd simulation framework. We also propose a new metric for comparing the “visual similarity” between the synthesized crowd and exemplar crowd. We demonstrate the proposed approach on crowd videos collected under different settings and the initial results appear promising.