Curve analysis for real-time crowd estimation system

Abstract

The crowd monitoring system has been widely used in many areas such as transportation control and safety management. The aim of a crowd monitoring system is to count the number of people in a confined area. There are different kinds of crowd monitoring systems in the market with their principles of operation different from each other. Some may use sensors as the principle of the operation. In this paper, the principle of operation of the crowd monitoring system is based on image processing techniques where information extracted from the image is based on its color density. The information in the number represented by the image will be rearranged and changed in an appropriate way. Then, by analyzing the pattern and format of these numbers, a computer can obtain the information from the image like a human being. In addition, this paper presents a new people counting system to count the number of people in a certain image in real-time. The proposed system employs a Curve Analysis (CA) method for the crowd monitoring system where evaluation on its performance provides promising results.