Realization of multiple human head detection and direction movement using Raspberry Pi
Authors:
- 1 March 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1160-1164
Abstract
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.Keywords
This publication has 12 references indexed in Scilit:
- Multiple object detection using OpenCV on an embedded platform2014
- Automatic Detection and Tracking of Pedestrians in Videos with Various Crowd Densities2013
- Multi-human Tracking in Crowds Based on Head Detection and Energy OptimizationInformation Technology Journal, 2013
- Robust Local Optical Flow for Feature TrackingIEEE Transactions on Circuits and Systems for Video Technology, 2012
- Density-aware person detection and tracking in crowds2011
- Online Multiperson Tracking-by-Detection from a Single, Uncalibrated CameraIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Rapid object detection using a boosted cascade of simple features2005
- Tracking multiple humans in complex situationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- A real-time face tracker2002
- A general framework for object detection2002