Crowd detection and analysis for surveillance videos using deep learning

Abstract

Due to the reduced costs, the availability of surveillance systems has increased many folds. Surveillance videos have proved to be very important for crime investigation. The recent technological advancements have made it possible to analyze the video to extract valuable information from it. Mass or crowd gatherings can be seen at a lot of places like airports, sports stadiums, various religious, educational, and entertainment-related events, etc. Video surveillance at such crowded places can prove to be very helpful in crowd management. It is very important to identify the presence of a crowd and detect the number of people in the gathering. This can prove very useful for the detection of sudden troupe build-up, to avoid riots. Moreover, it can also be very useful in the Covid-19 pandemic situation to avoid people gathering at a place. In this paper a framework for crowd detection is presented. Presence of crowd is found by counting unique people and then performing crowd analysis. Crowd analysis is performed by detecting the gender and age of people in the crowd.