Moving Object Detection and Tracking Using Dynamic Background and Foreground Separation for the Purpose of Traffic Analysis on Mobile Device

Anton Prokopov
This work describes an automatic background-foreground detection for the purpose of further analysing of traffic. The aim of this project was to investigate and implement the background removal algorithm that uses Gaussian Mixture Model to perform robust background subtraction in real time. This kind of a system can recognize the moving objects in the video sequence using only camera. It finds its application in traffic analysis. The implementation has been done firstly on a computer using C++ OpenCV library followed by translating the code for being executable on Android device.
Graduation Thesis language
Graduation Thesis type
Bachelor - Computer Science
Assoc. Prof. Gholamreza Anbarjafari, Priit Salumaa, MSc
Defence year
PDF Extras