Crowd estimation in images

• Main Author: Ng, Zi Yang.
• Other Authors: Cham Tat Jen
• Format: Final Year Project
• Language: English
• Published: 2010
• Subjects: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
• Online Access: http://hdl.handle.net/10356/36259
• Institution: Nanyang Technological University

The crowd monitoring system has been widely used in many areas such as transportation control and safety management. The purpose of a crowd estimating system is to count the number of people in an area so as to facilitate its management. There are many different kinds of crowd estimating systems in the market. Some of them use sensors as the principle of the operation. There are still significant problems in the planning, design and management of public facilities subject to dense pedestrian traffic. The automation of data collection and analysis of crowd behavior is increasingly desirable in design of facilities and long-term site management using image processing techniques with existing closed- circuit television systems. In this project, the principle of operation of the crowd estimating system is based on image processing techniques where information extracted from the image is based on its color density. Estimation is also carried out by extracting a set of significant features from the sequences of images and matching them to the other areas of the images. Parameters such as hue, saturation and intensity (HSI) are used for the matching. The matching will determine if that is the features we are looking for. The crowd density will then be determined. Some images with background or other redundant objects that are similar to the part being chosen to compare may posed problems to the crowd estimation. An area remove method has been introduced to the system, which can eliminate area of the image which are redundant and caused problem to the system. The system is developed using Microsoft Visual C++ and OpenCV library. At the end of the project, the system is able to count the number of people in an image. In future, as security become a more and more important aspect in our society, development of similar system is inevitable.