کنفرانس مهندسی برق ایران

صفحه اصلی / سی و چهارمین کنفرانس بین المللی مهندسی برق

An Intelligent Multi-Camera Vision-Based Parking System with Vehicle Detection and Tracking

نویسندگان :

Javad Pourrafi Arabani¹ Negar Shenavar² Dorsa Khalafi³ Saeed Ebadollahi⁴

1- دانشگاه علم و صنعت ایران 2- دانشگاه علم و صنعت ایران 3- دانشگاه علم و صنعت ایران 4- دانشگاه علم و صنعت ایران

کلمات کلیدی :

Smart Parking،Computer Vision،Perspective Mapping،Multi-Camera Tracking،Vehicle Tracking

چکیده :

Considering the growing need for urban communities to utilize parking resources efficiently, intelligent parking monitoring and management systems have become essential. Traditional management systems contribute to further traffic congestion and consequently, environmental pollution. In this paper, we design and implement an experimental vision-based parking system for an open-space parking area at Iran University of Science and Technology. Using multiple cameras, the system detects vehicles through object detection and applies perspective mapping to generate a top-down view of the parking area. This approach allows the system to accurately determine parking spot occupancy. Vehicle tracking is achieved through a custom approach that fuses Kalman filtering and re-identification techniques. The proposed framework offers an efficient solution for intelligent parking management in large open-space environments.