Hajj pilgrimage video analytics using CNN

This paper advances video analytics with a focus on crowd analysis for Hajj and Umrah pilgrimages. In recent years, there has been an increased interest in the advancement of visible surveillance to improve safety security pilgrims during their stay Makkah. It is mainly because entirely special event that involve hundreds thousands people being clustered small area. proposed convolutional neural network (CNN) system performing multitude analysis, particular counting. addition, it also proposes new algorithm applications Umrah. We create dataset based pilgrimage scenario order address this challenge. The outperforms state-of-the-art approach significant reduction mean absolute error (MAE) result: 240.0 (177.5 improvement) square (MSE) 260.5 (280.1 when used latest (HAJJ-Crowd dataset). present density map prediction traditional our novel HAJJ-crowd purpose evaluation method.