GitHub: https://github.com/nripesh-k/Automated-Parking-System
The Automated Parking System is a computer-vision-based project developed to automate the parking management process, especially in urban areas The system uses computer vision algorithms to track the availability of parking spots, facilitate the entry and exit of vehicles, and calculate ticket prices. The main aim of this project is to provide an efficient and hassle-free parking experience for customers and parking management staff, reducing the time and effort required for management, improving overall efficiency and productivity, and ultimately leading to better customer satisfaction.
OpenCV is used as it is a free, open-source computer vision and machine learning software library, and a CNN model was trained using Keras and the available datasets from the internet and our instructor. Multiple filters such as Gaussian blur, Otsu-thresholding, etc. along with algorithms like connected components were applied to the video feed for the task of number-plate localization which was fed into the CNN for the number-plate prediction.
Similarly, the parking lot monitoring was done through the usage of masks and various computer vision techniques like blurring, thresholding, dilating, and using the simple idea of counting the non-zero pixels in the spots. The use of computer vision applications like this can help automate open parking areas and decrease human effort in managing those areas.