Realization of multiple human head detection and direction movement using Raspberry Pi

People gather in huge crowds during festive seasons and the streets get overcrowded during peak hours of traffic. Managing the crowd requires an intelligent monitoring technology. In this paper, we propose a method to manage the crowd by counting multiple humans in the scene by head detection. In our study, we develop a system using Raspberry Pi 3 board that detects the human heads and provide a count of humans in the region using OpenCV-Python. A Haar cascade classifier is trained for human head detection. The direction of movement is determined from the pixel values in consecutive frames. The results of the analysis will be helpful in managing the crowd in any area with high density of crowds.