EUVIMEDEUVIMED entdecken
Crossref

Intelligent Multi-Level Parking Management using Computer Vision, Edge Inference, and Reinforcement Learning for Slot Assignment

Saravanan O, Harikarthick G

International Journal of Engineering & Extended Technologies Research · 28.03.2026 · 08 (02)

DOI: 10.15662/ijeetr.2026.0802384 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Engineering & Extended Technologies Research, online erschienen am 28.03.2026. Verfasst von Saravanan O und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid expansion of urban transportation systems has intensified the demand for efficient and intelligent parking management solutions. Conventional parking approaches, which primarily depend on manual supervision or static sensor-based mechanisms, often fail to address the dynamic and complex nature of multi-level parking environments. These limitations result in inefficient space utilization, increased vehicle search time, and elevated congestion levels. To overcome these challenges, this study presents a comprehensive intelligent multi-level parking management framework that integrates computer vision, edge computing, and reinforcement learning for real-time parking optimization. The system employs deep learning-based visual analysis to accurately detect parking slot occupancy, while edge-based inference ensures low-latency processing and reduced dependency on centralized infrastructure. A reinforcement learning-driven decision model is incorporated to dynamically allocate parking slots based on real-time occupancy status, traffic density, and vehicle movement patterns. In addition, predictive analytics techniques are utilized to estimate short-term parking availability by analyzing historical usage trends and temporal variations. This enables proactive decision-making and improved resource planning. The proposed framework is evaluated using key performance metrics such as detection accuracy, inference latency, slot utilization efficiency, congestion reduction rate, and average vehicle search time. Experimental results demonstrate significant improvements over traditional parking systems, including enhanced detection precision, reduced latency, and optimized traffic flow within parking facilities. The findings indicate that the integration of intelligent perception, distributed computing, and adaptive learning mechanisms provides a scalable and effective solution for modern smart city parking infrastructures

Zitieren

APA

O, S., & G, H. (2026). Intelligent Multi-Level Parking Management using Computer Vision, Edge Inference, and Reinforcement Learning for Slot Assignment. International Journal of Engineering & Extended Technologies Research, 08(02). https://doi.org/10.15662/ijeetr.2026.0802384

Vancouver

O S, G H. Intelligent Multi-Level Parking Management using Computer Vision, Edge Inference, and Reinforcement Learning for Slot Assignment. International Journal of Engineering & Extended Technologies Research. 2026;08(02). doi:10.15662/ijeetr.2026.0802384

BibTeX
@article{O2026,
  author = {O, Saravanan and G, Harikarthick},
  title = {Intelligent Multi-Level Parking Management using Computer Vision, Edge Inference, and Reinforcement Learning for Slot Assignment},
  journal = {International Journal of Engineering & Extended Technologies Research},
  year = {2026},
  volume = {08},
  number = {02},
  doi = {10.15662/ijeetr.2026.0802384}
}
Kostenlos starten →