Video Based Car Parking Management and Monitoring Using Computer Vision and Machine Learning

Each day, countless individuals around the globe are affected by the extensive and complex problem of traffic congestion. This raising challenge is becoming increasingly substantial across the country, driven by factors such as rising population numbers, speedy urban development, insufficient infrastructure, and changing socioeconomic requirements. This paper depicts a novel global video-based parking approach designed to boost the supervising and management of parking spaces using real-time aerial statistics. Utilizing advanced image processing and computer vision procedures, the system essentially detects and examines the occupancy position of parking slots. In our realization, we assessed a total of 48 parking spaces, positively identifying 7 as unused while 41 were occupied. The application of Python, OpenCV, and machine learning assisted real-time monitoring, allowing precise counting and expose of parking availability. The procedure contained critical procedures, including Gaussian blur filtering to minimize noise and improve edge detection, followed by binary thresholding to describe vehicles and parking spots from the background. Furthermore, a median filter was utilized to boost the clarity of vehicle contours. These image enhancement methods significantly expanded detection accuracy and facilitated precise recognition of the Region of Interest (ROI). The results show the system's ability to provide reliable, real-time data for dynamic parking administration, thereby focusing the challenges of urban parking.