A neural-based crowd estimation by hybrid global learning algorithm

A neural-based crowd estimation system for surveillance in complex scenes a t underground station platform is presented. Estimation is carried out by e xtracting a set of significant features from sequences of images. Those fea ture indexes are modeled by a neural network to estimate the crowd density. The learning phase is based on our proposed hybrid of the least-squares an d global search algorithms which are capable of providing the global search characteristic and fast convergence speed. Promising experimental results are obtained in terms of accuracy and real-time response capability to aler t operators automatically.