Finding Stolen Vehicles Using Traffic Cameras

Abstract

A modern tracking system based on traffic cameras will be detailed in this document to improve vehicle theft recovery rates particularly during plate obscuring or removal situations. The standard stolen vehicle detection system experiencing difficulties with license plate recognition relies primarily on Automatic License Plate Recognition (ALPR). The proposed system connects ALPR technology with contemporary machine learning and computer vision features to enable detections of vehicles by model-specific attributes like vehicle shape and color type. l??t ??ng c? y?u t? dissipation from a wide network of traffic cameras enables the system to provide instant location updates to law enforcement agencies. The system generates instantaneous alerts about located stolen vehicles which contain specific information regarding position data and travel direction and timestamp. Swift emergency responses become possible through this technology which increases the odds of stolen vehicle recovery and criminal capture. The system implements two machine learning models (Convolutional Neural Networks and YOLO) which detect and categorize vehicles under any lighting circumstances or when obscured by other objects. The connection of current traffic cameras to these technologies permits efficient and scalable tracking services in real-time. The paper shows how machine learning tools with computer vision technology integrated with traffic cameras create an efficient solution to detect stolen vehicles which delivers practical data to police services that boosts public protection rates.

Introduction

The growing issue of stolen vehicles poses significant challenges for law enforcement globally, as traditional license plate recognition (LPR) methods often fail when plates are obscured or altered. To overcome these limitations, the research proposes a novel system leveraging traffic camera feeds combined with machine learning (ML) and computer vision (CV) techniques. This system identifies stolen vehicles by analyzing features such as make, model, color, and shape, enabling detection even without visible license plates.

Key components include Automatic License Plate Recognition (ALPR), Convolutional Neural Networks (CNNs), and the YOLO object detection model to detect and classify vehicles in real-time. The system uses Kalman Filters and Re-identification (Re-ID) for continuous tracking across multiple cameras. Upon detection, real-time alerts with vehicle details and location are sent to law enforcement to enable rapid response.

The system integrates existing traffic infrastructure with advanced AI technologies, supported by a centralized SQL database for storing detection and tracking data. This approach aims to improve stolen vehicle recovery rates, reduce response times, and enhance public safety by providing a scalable, automated solution to the shortcomings of current detection methods.

Conclusion

The proposed system enhances the capabilities of traditional stolen vehicle detection systems by using a combination of traffic cameras, ALPR, machine learning, and real-time tracking. By overcoming the challenges posed by obscured or missing license plates, the system improves the accuracy and reliability of stolen vehicle detection and tracking, contributing to the overall safety of the community.

References

[1] Shjarback, J. A., & Sarkos, J. A. (2025). An Evaluation of a Major Expansion in Automated License Plate Reader (ALPR) Technology. Justice Evaluation Journal, 1-18. [2] Kumawat, K., Jain, A., & Tiwari, N. (2024). Relevance of automatic number plate recognition systems in vehicle theft detection. Engineering Proceedings, 59(1), 185. [3] Kang, L., Lu, Z., Meng, L., & Gao, Z. (2024). YOLO-FA: Type-1 fuzzy attention based YOLO detector for vehicle detection. Expert Systems with Applications, 237, 121209. [4] Kanishkha, L. D., & Poojah, G. (2022). Stolen car detection using image processing and Machine Learning. International Journal of Signal Processing, 7. [5] Li, Y., Zhang, M., Zhang, C., Liang, H., Li, P., & Zhang, W. (2024). YOLO-CCS: Vehicle detection algorithm based on coordinate attention mechanism. Digital Signal Processing, 153, 104632. [6] Pan, H., Guan, S., & Zhao, X. (2024). LVD-YOLO: An efficient lightweight vehicle detection model for intelligent transportation systems. Image and Vision Computing, 151, 105276. [7] Shafi, S., Reddy, T. P. S. K., Silla, R., & Yasmeen, M. (2023, June). Deep learning based real-time stolen vehicle detection model with improved precision and reduced look up time. In 2023 3rd International Conference on Intelligent Technologies (CONIT) (pp. 1-6). IEEE. [8] Al-lQubaydhi, N., Alenezi, A., Alanazi, T., Senyor, A., Alanezi, N., Alotaibi, B., ... & Hariri, S. (2024). Deep learning for unmanned aerial vehicles detection: A review. Computer Science Review, 51, 100614. [9] Vishwakarma, P. K., & Jain, N. (2024). Design and augmentation of a deep learning based vehicle detection model for low light intensity conditions. SN Computer Science, 5(5), 605. [10] Sivasubramanian, K., Balasundaram Sathiya Devi, V., MS, B. M., & Rajagopal, M. K. (2023, December). Leveraging Deep Learning for Improving Real Time Stolen Vehicle Tracking in Smart Cities. In Proceedings of the 2023 11th International Conference on Information Technology: IoT and Smart City (pp. 206-210). [11] Ramzan, S. R. S., Iqbal, M. J. I. M. J., Arslan, F. A. F., Nawaz, S. N. S., Chauhdary, N. J. C. N. J., & Ramzan, M. R. M. (2024). Smart and Secure Vehicle Parking System to Avoid Theft Using Deep Image Recognition. Journal of Innovative Computing and Emerging Technologies, 4(1). [12] Mustafa, T., & Karabatak, M. (2024). Real time car model and plate detection system by using deep learning architectures. IEEE Access. [13] Alotaibi, A., Chatwin, C., & Birch, P. (2025). AI-driven UAV system for autonomous vehicle tracking and license plate recognition. Open Engineering, 15(1), 20240101. [14] Zohaib, M., Asim, M., & ELAffendi, M. (2024). Enhancing emergency vehicle detection: a deep learning approach with multimodal fusion. Mathematics, 12(10), 1514. [15] Vikram, A., Jothi, A., Ahmad, S., Rubini, L. J., Kadry, S., & Kim, J. (2024). Deep Learning Based Vehicle Detection and Counting System for Intelligent Transportation. Comput. Syst. Sci. Eng., 48(1), 115-130. [16] Ma, C., & Xue, F. (2024). A review of vehicle detection methods based on computer vision. Journal of Intelligent and Connected Vehicles, 7(1), 1-18. [17] Chughtai, B. R., & Jalal, A. (2024, February). Traffic surveillance system: robust multiclass vehicle detection and classification. In 2024 5th International conference on advancements in computational sciences (ICACS) (pp. 1-8). IEEE. [18] Alif, M. A. R. (2024). Yolov11 for vehicle detection: Advancements, performance, and applications in intelligent transportation systems. arXiv preprint arXiv:2410.22898. [19] Bakirci, M. (2024). Enhancing vehicle detection in intelligent transportation systems via autonomous UAV platform and YOLOv8 integration. Applied Soft Computing, 164, 112015. [20] Sundaresan Geetha, A., Alif, M. A. R., Hussain, M., & Allen, P. (2024). Comparative Analysis of YOLOv8 and YOLOv10 in Vehicle Detection: Performance Metrics and Model Efficacy. Vehicles, 6(3), 1364-1382.

Copyright

Copyright © 2025 Karthikeyan R, Karthikeyan P, Muthamizh Selvan M, Mrs. Babisha A, Dr. Suma Christal Mary S, Mrs. Swagatha J. P. This 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.