Vision-based vehicle detection and tracking in intelligent transportation system

Loading...
Thumbnail Image

URL

Journal Title

Journal ISSN

Volume Title

Insinööritieteiden korkeakoulu | Master's thesis

Date

2019-06-17

Department

Major/Subject

Mcode

Degree programme

Master's Programme in Mechanical Engineering (MEC)

Language

en

Pages

64+13

Series

Abstract

This thesis aims to realize vision-based vehicle detection and tracking in the Intelligent Transportation System. First, it introduces the methods for vehicle detection and tracking. Next, it establishes the sensor fusion framework of the system, including dynamic model and sensor model. Then, it simulates the traffic scene at a crossroad by a driving simulator, where the research target is one single car, and the traffic scene is ideal. YOLO Neural Network is applied to the image sequence for vehicle detection. Kalman filter method, extended Kalman filter method, and particle filter method are utilized and compared for vehicle tracking. The Following part is the practical experiment where there are multiple vehicles at the same time, and the traffic scene is in real life with various interference factors. YOLO Neural Network combined with OpenCV is adopted to realize real-time vehicle detection. Kalman filter and extended Kalman filter are applied for vehicle tracking; an identification algorithm is proposed to solve the occlusion of the vehicles. The effects of process noise as well as measurement noise are analysed using variable-controlling approach. Additionally, perspective transformation is illustrated and implemented to transfer the coordinates from the image plane to the ground plane. If the vision-based vehicle detection and tracking can be realized and popularized in daily lives, vehicle information can be shared among infrastructures, vehicles, and users, so as to build interactions inside the Intelligent Transportation System.

Description

Supervisor

Tammi, Kari

Thesis advisor

Tammi, Kari

Keywords

intelligent transportation system, computer vision, vehicle detection, vehicle tracking, YOLO neural network, sensor fusion

Other note

Citation