Analysis of crowd movements and densities in built-up environments using image processing

Real-time monitoring of site usage in public areas subject to major crowd movements relies on human observers with limited attention span and varying reliability. It is essential to investigate techniques to acquire crowd data and features automatically first, as part of the data gathering process, to develop realistic models for planning and designing pedestrian facilities in urban areas and, secondly, as online systems to detect problems in crowd movement before or shortly after they occur, using existing CCTV systems wherever possible. Such studies could lead to improved site designs, management procedures, public safety and reduced operating costs. Image processing techniques applicable to the measurement of density and motion in crowded scenes have therefore been presented. These give results comparable to human observers with potential for real-time implementation. Detailed studies of site usage and real-time operation then become feasible