Crowd Density Estimation Using Image Processing: A Survey

摘要

People counting is a crucial subject in video surveillance application. Factors such as severe occlusions, scene perspective distortions in real time application make this task a bit more challenging. The use of Infra Red (IR) sensors and Channel State Information (CSI) of the WIFI network, which are the classical methods, give the count but have their own range constraints and its limited applicability to controlled environment. Video-surveillance systems are one of the advanced technologies used to estimate the density of people in a place for security reasons and to obtain the human statistics. The vision based techniques works well when people are in motion and when a high resolution image with clear background are available. This paper presents the state of the art of such image processing algorithms which are used for crowd estimation and their related applications.