Aerial Based Traffic Monitoring And Vehicle Count Detection Using Background Subtraction

Increasing population in an area of the world increasingly increases the density of the area. This happened by an increase in vehicle volume resulting in congestion. This project uses Python as its programming language and OpenCV as an open-source library for programming, and Raspberry Pi. The objec...

Full description

Saved in:
Bibliographic Details
Main Author: Muhamad, Muhamad Zulhilmi
Format: Monograph
Language:English
Published: Universiti Sains Malaysia 2021
Subjects:
Online Access:http://eprints.usm.my/54547/1/Aerial%20Based%20Traffic%20Monitoring%20And%20Vehicle%20Count%20Detection%20Using%20Background%20Subtraction.pdf
http://eprints.usm.my/54547/
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Increasing population in an area of the world increasingly increases the density of the area. This happened by an increase in vehicle volume resulting in congestion. This project uses Python as its programming language and OpenCV as an open-source library for programming, and Raspberry Pi. The objective of this study was to develop a vision-based system for road vehicle counting and tracking. The system will be able to achieve counting with very good accuracy even in difficult scenarios related to occlusions or the presence of shadows. The principle of the system is to install a camera on the pedestrian bridges and track the vehicular traffic congestion by incorporating a unique ID. Moving objects were tracked using simple background subtraction and moving object monitoring was conducted using the MOSSE (Minimum Output Sum of Squared Error) tracker. The video processing model is combined with a motion detection procedure, which correctly allows the positioning of moving vehicles depending on the space and time when the experiment was conducted. More trials need to be carried out comprising of peak periods and different vehicle types, and occlusions need to be observed between close moving vehicles and between cars and heavy vehicles. Using the proposed method, the identification of severe shadows based on solidity can be calculated through the nature of the shape and this classification allows its accuracy to be estimated.