PARKNEST: A LIGHTWEIGHT COMPUTER VISION FRAMEWORK FOR REAL-TIME PARKING SPACE DETECTION AND VISUALIZATION

This paper presented an efficient, software-based smart parking framework designed for real-time occupancy detection. The proposed system integrates manual coordinate mapping, an adaptive OpenCV thresholding pipeline, and a Flask-based API into a single operational architecture. Experimental testing shows that by prioritizing basic architectural pixel density over heavy neural network classification, the framework achieves high detection accuracy while maintaining extermely low latency. The study highlight how clever applications of fundamental computer vision techniques can solve complex urban infrastructure problems cheaply, allowing scalable smart-city deployment without the massive hardware costs.

[1]R. S. Pressman, Software Engineering: A Practitioner’s Approach, 2020. [2]S.Russell and P.Norvig, Aritificial Intelligence: A Modern Approach, 2021. [3]J.Redmon etal., “You Only Look Once: Unified, Real-Time Object Detection,”Proceedings of CVPR, 779-788, 2016. [4]N.Dalal and B.Triggs,”Histograms of Oriented Gradients for Human Detection,”Proceedings of the IEEE Conference on Computer Vision and Pattern Recognitions (CVPR), 886-893, 2005. [5]G.Jocher et al., “Ultralystics YOLOv8 Documentation and Architecture,” Ultralytics Technical Documentation, 2023. [6]OpenCV Development Team, “OpenCV Documentation, “2024. Available: https://opencv.org/ [7]G.Amato, F.Carrara, F. Falchi, C.Gennaro, C.Meghini, and C.Vairo, “Deep learning for decentralized parking lot occupancy detection, “ Expert Systems with Applications, vol. 72, pp.327- 334,2017. [8]T. Lin, H.Chu, and Z.Chen, “A vision-based parking lot management system,” Ieee International Conference on systems, Man and Cybernetics, pp.2897-2902,2006. [9]N.True,”Vacant parking space detection in static images,” University of California, San Diego, 2007. [10]M. Grinberg, Flask Web Development: Developing Web Applications with Python, 2nd ed., O’Reilly Media, 2018.