Crowd and people counting aims to estimate the number of people in crowded images or videos from surveillance cameras. Accurately estimating the number or density of crowds is an increasingly important application for purposes of crowd control and public safety. In overcrowding scenarios, people counting offers an essential piece of information which can be used as an accident avoidance and congestion control mechanism.
Existing methods of people counting can be divided into detection-based and regression-based. Recently, Deep Convolutional Neural Networks have been shown to be accurate, robust and effective in crowd counting. These networks extract scale-relevant features to estimate effectively the crowd density.