Data Driven Traffic Density Monitoring: A UAV and ResNet50 Deep Learning Framework
Rubab S. Dahri F.H. Mustafa Abro G.E. Tahir N.M. Javed M.
2025Institute of Electrical and Electronics Engineers Inc.
Proceedings of the International Colloquium on Signal Processing and Its Applications, CSPA
2025Issue 202522 - 26 pp.
Urban traffic congestion necessitates innovative monitoring and control solutions. This study leverages UAV footage and deep learning techniques to classify and analyze traffic density levels autonomously. By employing a pre-trained ResN et50 model enhanced with additional layers, the research optimizes traffic density classification using UAV-captured data. A custom dataset of traffic scenarios in Dammam, Saudi Arabia, was developed, incorporating diverse conditions through advanced normalization and data augmentation techniques to improve resilience and robustness. The modified ResN et50 model demonstrated high classification accuracy across varied traffic scenarios, validating its reliability and scalability for real-world applications. Key findings include the superior adaptability of UAV-based monitoring for real-time urban traffic assessment and the enhanced classification precision achieved through model optimization. This research underscores the potential of integrating UAV technology with deep learning to advance urban traffic management and foster more efficient urban planning strategies.
Deep Learning Algorithms , ResNet50 Model , Traffic Density Classification , UAV Imagery , Urban Traffic
Text of the article Перейти на текст статьи
University of Sharjah, College of Computing and Informatics, Department of Computer Engineering, Sharjah, 27272, United Arab Emirates
Southeast University, School of Computer Science and Engineering, Nanjing, China
King Fahd University of Petroleum and Minerals (KFUPM), Interdisciplinary Research Centre for Aviation and Space Exploration, Saudi Arabia
College of Engineering, Universiti Teknologi Mara, School of Electrical Engineering, Selangor, Shah Alam, Malaysia
International Information Technology University, Department of Cybersecurity, Alamty, Kazakhstan
Donghua University, College of Computer Science, Department of Computer Science and Technology, Shanghai, 200022, China
University of Sharjah
Southeast University
King Fahd University of Petroleum and Minerals (KFUPM)
College of Engineering
International Information Technology University
Donghua University
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026