September 24, 2014
Speaker: Jordan Stadler, UOIT
Title: A Framework for Video-Driven Crowd Analysis
Abstract: We present a framework for video-driven crowd synthesis. The proposed framework employs motion analysis techniques to extract inter-frame motion vectors from the exemplar crowd video. 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 behaviour-based crowd simulation 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.