Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{178048,
        author = {R Sudha and S Devapriyan and N Dheepak Prasath and G Manohar Kumar and K Nalin Kumar},
        title = {Vision based parking occupation detecting with embedded and AI},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {7738-7745},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178048},
        abstract = {This paper presents a vision-based smart parking system that utilizes embedded systems and artificial intelligence (AI) to detect and monitor parking space occupancy in real-time. The proposed solution leverages camera-based input, computer vision algorithms, and deep learning models to classify parking spots as either occupied or vacant. By automating the monitoring of parking lots, this system reduces manual supervision and improves overall traffic management. It addresses challenges in urban mobility, such as time wastage, fuel consumption, and congestion caused by the inefficient search for parking spaces. Designed to be both cost-effective and scalable, the system integrates affordable hardware such as Raspberry Pi, along with open-source software libraries including OpenCV for image processing. A lightweight convolutional neural network (CNN), optimized for embedded deployment, performs real-time inference on images to detect vehicles in designated parking zones. The model was trained on a custom dataset that includes diverse environmental conditions such as varying lighting, weather, and angles, ensuring robustness in real-world scenarios. Experimental results demonstrate high classification accuracy, low power consumption, and minimal latency, confirming the viability of deploying AI-driven parking systems in smart city infrastructure. Additionally, the system offers potential for integration with IoT platforms, enabling remote access, data analytics, and predictive modeling for traffic optimization and space utilization.},
        keywords = {Smart Parking, Computer Vision, Embedded System, Nodemcu, Artificial Intelligence (AI), Deep Learning, Occupancy Detection, Convolutional Neural Networks (CNN), Edge Computing, Internet of Things (IoT), OpenCV, Real-Time Image Processing, Parking Space Optimization, Smart City Infrastructure.},
        month = {May},
        }