Abstract
A novel method has been proposed to classify the motion of pilgrims with respect to congestion level in the holy mosque of Makkah. Millions of Muslims visit this mosque during Hajj and Umrah every year. A large number of security personnel is required to maintain the smooth flow of pilgrims in order to avert any catastrophe. Therefore, it is inevitable to design a computer aided system to reduce human effort. The proposed system pre-processes input images to segregate the moving shadows and pilgrims in order to nullify the false motion due to moving shadows. A hybrid method consisting of block matching and optical flow techniques has been used for the computation of motion vectors. Decision tree classifier is used on the number of motion vectors having non-zero magnitude. Experiments show that the proposed system has promising results yielding an accuracy of 90.58% for the congestion classification of pilgrims.
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call