Crowd Density Estimation System for Al-Masjid Al-Haram
International journal of computing, communication and instrumentation engineering · 2017
Estimating crowd occupancy is an important element in crowd management and safety.Crowding is greatly manifested in the two holy mosques of Mecca and Medina which makes them a constant source of study and concern.As a solution to this problem we developed a prototype of Al-Haram Crowd Guide System; a client-server crowd density estimation system which uses texture based methods to assist in the guiding and management of crowds in Al-Masjid Al-Haram.This is achieved through a visual representation of the crowd occupancy presented to the users in the form of a heat-map.The main contribution of our paper is two-fold: first we explore the features of the system and its main design aspects and phases.Second, we provide a brief comparison between two texture-based techniques used to estimate crowd density; Grey Level Co-occurrence Matrices and Local Binary Patterns.To classify the images, they were coupled with a Self-Organizing Map and a Support Vector Machine respectively.Finally, we show examples of our system in operation tested on sample data gathered from the Saie area in Al-Masjid Al-Haram.We conclude with a summary of our results and some future considerations for the continuation of our work.