Detection of Salient Regions in Crowded Scenes
This addresses the need for proactive surveillance in crowded scenes with many cameras, though it is incremental as it builds on existing flow field and stability theory methods.
The paper tackles the problem of automatically detecting salient regions in crowded surveillance videos by analyzing temporal variations in flow fields as a dynamic system, achieving effective detection of unstable flow, occlusions, bottlenecks, entries, and exits without prior scene knowledge or training.
The increasing number of cameras and a handful of human operators to monitor the video inputs from hundreds of cameras leave the system ill equipped to fulfil the task of detecting anomalies. Thus, there is a dire need to automatically detect regions that require immediate attention for a more effective and proactive surveillance. We propose a framework that utilises the temporal variations in the flow field of a crowd scene to automatically detect salient regions, while eliminating the need to have prior knowledge of the scene or training. We deem the flow fields to be a dynamic system and adopt the stability theory of dynamical systems, to determine the motion dynamics within a given area. In the context of this work, salient regions refer to areas with high motion dynamics, where points in a particular region are unstable. Experimental results on public, crowd scenes have shown the effectiveness of the proposed method in detecting salient regions which correspond to unstable flow, occlusions, bottlenecks, entries and exits.