Vehicle Tracking and Tint Violation Detection System using RFID and AI-Based ANPR

Vehicle Tracking and Tint Violation Detection System using RFID and AI-Based ANPR

Dr Brindha S

Head of the Department, Computer Networking, PSG Polytechnic College, Coimbatore

Ms. Divya M

Lecturer, Computer Networking, PSG Polytechnic College, Coimbatore Mr. Harish R, Mr. Ashwin S

Ms. Harshitha V, Mr. Sreeharan M, Mr. Sriram partha sarathi S

Students, Computer Networking, PSG Polytechnic College, Coimbatore

Abstract- With the rapid increase in the number of vehicles, effective vehicle tracking and enforcement of traffic regulations have become major challenges for modern transportation systems. Conventional monitoring techniques are often limited in accurately detecting vehicle movement, tint violations, stolen vehicles, and unauthorized access, and they rely heavily on manual intervention. To overcome these limitations, this paper presents a Vehicle Tracking and Tint Violation Detection System using Radio Frequency Identification (RFID) and Artificial Intelligence (AI)-based Automatic Number Plate Recognition (ANPR).The proposed system integrates AI-based image processing for real-time license plate recognition with RFID technology for secure and reliable vehicle identification and tracking. Illegal window tint detection is carried out using computer vision techniques by analyzing captured vehicle images. The recognized vehicle number and RFID data are cross-verified with a centralized database to identify stolen, blacklisted, or rule-violating vehicles. The system enables automatic traffic monitoring, violation detection, toll collection, and parking management.This integrated approach enhances traffic surveillance accuracy, reduces human effort, and improves road safety. The proposed system is well-suited for smart city applications by providing real-time monitoring, better law enforcement, and improved transportation security.

1. INTRODUCTION

   The rapid growth of urbanization and the significant increase in the number of vehicles have placed a heavy burden on traffic management systems. Ensuring vehicle security, monitoring traffic violations, and maintaining road safety have become critical challenges for traffic authorities. Traditional traffic monitoring systems mainly depend on manual inspection and limited automated tools, which are inefficient for real-time monitoring and large-scale deployment. These systems often fail to accurately track vehicles, detect illegal window tinting, and identify unauthorized or stolen vehicles.

   Illegal window tinting is a serious traffic violation as it reduces visibility, contributes to criminal activities, and violates government regulations. At the same time, vehicle

   theft and unauthorized vehicle movement continue to be major security concerns. Conventional enforcement methods require human intervention, which is time-consuming, costly, and prone to errors.

   To address these challenges, this paper proposes a Vehicle Tracking and Tint Violation Detection System using RFID and AI-based Automatic Number Plate Recognition (ANPR). The system integrates RFID-based vehicle identification with AI-driven computer vision techniques for license plate recognition and window tint detection. By combining these technologies, the proposed system provides accurate real-time vehicle tracking, automatic violation detection, and improved traffic law enforcement. The system is designed to support smart city infrastructure by enabling intelligent and automated transportation monitoring.

2. RELATED WORKS

   1. RFID-Based Vehicle Tracking Systems

      RFID technology has been widely used for automatic vehicle identification and tracking due to its fast response, low cost, and reliability. Several researchers have proposed RFID-based vehicle monitoring systems for traffic management and security applications. Shaikh et al. developed an RFID-based traffic monitoring system for automatic toll collection and stolen vehicle detection. The system improved identification speed but lacked visual verification of vehicles. Patil et al. proposed an RFID-based vehicle authorization system for parking management to prevent unauthorized access. Although the system was efficient for access control, it did not support real-time law enforcement or violation detection. These studies show that RFID is effective for vehicle identification but requires integration with vision-based systems for comprehensive monitoring.

   2. AI-Based Automatic Number Plate Recognition (ANPR)

      Automatic Number Plate Recognition (ANPR) plays a crucial role in intelligent transportation systems. Du et al. presented a detailed review of ANPR systems using image processing and deep learning techniques such as convolutional neural networks (CNNs). Their work demonstrated high recognition accuracy under controlled conditions but suffered performance degradation in poor lighting and weather conditions. Silva and Jung proposed a real-time ANPR system using the YOLO deep learning model for faster detection. While their system achieved good speed and accuracy, it required high computational resources. These studies highlight the importance of AI in achieving accurate and real-time number plate recognition.

   3. Computer Vision-Based Traffic Violation Detection

      Computer vision has been widely adop

      ted for automatic traffic violation detection. Kumar et al. developed a system for detecting red-light and lane violations using surveillance cameras and ANPR. The system successfully reduced manual monitoring, but it focused only on signal violations. Another study proposed a speed violation detection system using video analytics and deep learning. Although these systems were effective for specific violations, they did not include vehicle identification using RFID or window tint analysis. Hence, existing vision-based systems are limited to selected types of traffic violations.

   4. Window Tint Detection Techniques

      Research on automatic window tint detection is comparatively limited. Chen et al. proposed a vision-based tint detection system using image brightness and visible light transmission (VLT) estimation. The systems performance depended heavily on sunlight intensity and camera angle. Some studies used infrared imaging and light sensors to measure tint levels more accurately, but such systems increased overall system cost and complexity. Most existing tint detection techniques suffer from low accuracy in real- time outdoor traffic environments, showing the need for improved AI-based solutions.

   5. Integrated Smart Traffic Monitoring Systems

      Only a few studies have attempted to integrate multiple technologies for smart traffic monitoring. Sharma et al. proposed an IoT-based vehicle monitoring system that integrated RFID and ANPR for real-time tracking. The system improved surveillance efficiency but did not include automated tint violation detection. Cloud-based traffic monitoring systems have also been proposed to store and analyze vehicle data in real time, primarily focusing on

      congestion control and route optimization. However, limited work has been done on integrating RFID, AI-based ANPR, and tint violation detection into a single unified platform.

3. SYSTEM ARCHITECTURE OVERVIEW

   The proposed Vehicle Tracking and Tint Violation Detection System is designed as an intelligent and automated traffic monitoring framework that integrates RFID technology, AI-based image processin, and a centralized database system. The architecture ensures real-time vehicle identification, number plate recognition, and detection of window tint violations with minimum human intervention.

   The overall system architecture consists of four main layers:

   • Data Acquisition Layer

   • Processing and Analysis Layer

   • Communication Layer

   • Application and Storage Layer

   1. Data Acquisition Layer

      This layer is responsible for collecting real-time data from vehicles. It includes: RFID Tags installed on vehicles, storing unique vehicle identification details. RFID Reader placed at checkpoints or traffic signals to scan vehicle tags.High-Resolution Camera used to capture images of passing vehicles for number plate recognition and tint analysis.When a vehicle passes through the monitoring zone, the RFID reader scans the tag while the camera simultaneously captures the vehicle image.

   2. Processing and Analysis Layer

      This layer performs all intelligent operations using embedded processing units such as Raspberry Pi or a microcontroller.The RFID Processing Module verifies the vehicle identity using tag data.The AI-Based ANPR Module processes the captured image, localizes the number plate, segments characters, and recognizes the vehicle number using deep learning models.The Tint Detection Module extracts the window region from the vehicle image and analyzes light intensity and transparency to estimate the window tint percentage.A Decision-Making Module compares the detected tint value with legal limits and verifies whether the vehicle is authorized.If a mismatch or violation is detected, the system immediately flags the vehicle.

   3. Communication Layer

      The communication layer ensures secure data transmission between the local processing unit and the remote server. It uses:Wi-Fi / Ethernet / GSM modules for real-time network communication.Secure communication protocols to transfer RFID data, recognized number plates, vehicle

      images, and violation status.This layer enables continuous monitoring and remote access by traffic authorities.

   4. Application and Storage Layer

      A Centralized Database Server that stores vehicle details, RFID records, ANPR results, images, and violation reports.A Web-Based Monitoring Dashboard used by traffic authorities to view vehicle movement, track violations, and generate reports.

   5. Working Principle of the Architecture

      The vehicle enters the monitoring zone..The RFID reader scans the vehicles RFID tag..The camera captures the real-time image of the vehicle..The ANPR system extracts and recognizes the number plate..The tint detection module evaluates window transparency..The processing unit verifies the vehicle and checks for violations.Data is transmitted to the central server.If a violation is detected, an alert is generated for authorities.

   6. Key Features of the Architecture

      Real-time automated vehicle Identification AI- based number plate. Recognition Automatic detection of illegal window tint Centralized data storage and monitoring Reduced human effort and improved accuracy Scalable and suitable for smart city deployment

      such as toll gates, traffic signals, or checkpoints.The RFID reader reads the tag wirelessly.The tag ID is sent to the processing unit (Raspberry Pi/Arduino).The system verifies the tag ID with the registered database.If the tag is valid, the vehicle is marked as authorized; otherwise, it is flagged as suspicious.This step ensures fast and contactless vehicle identification.

      1. Image Acquisition Using Camera Module

         A high-resolution camera module is installed beside the RFID reader to capture real-time images of moving vehicles. The camera continuously streams video frames to the processing unit.Relevant frames are selected based on vehicle motion detection.The captured image is forwarded to the ANPR and tint detection modules for further processing.Images are stored temporarily for evidence and verification.

      2. AI-Based Automatic Number Plate Recognition (ANPR) Implementation

         The ANPR module is implemented using Python and OpenCV with a deep learning model.Steps involved Number Plate Detection Character Segmentation Text Output Generation.

      3. Tint Violation Detection Implementation

         The window tint detection module is implemented using image processing techniques.The vehicle window

         region is extracted from the captured image.Pixel intensity and brightness values are analyzed.The Visible Light Transmission (VLT) percentage is estimated.The detected tint value is compared with the legal permissible limit.If the tint exceeds the legal threshold, the vehicle is marked as a tint violation case.This method enables real-time automated

         Fig 1: Block diagram

         detection of illegal tinted windows without manual inspection.

      4. Data Communication and Database Implementation

4. IMPLEMENTATION

   The implementation of the proposed Vehicle Tracking and Tint Violation Detection System is carried out by integrating hardware components with AI-based software modules. The complete system is implemented in four main stages: RFID-based vehicle identification, image acquisition, AI-based number plate recognition, and tint violation detection, followed by data storage and alert generation.

   1. RFID-Based Vehicle Identification Implementation

      Each vehicle is equipped with a unique RFID tag that stores the vehicle identification number and registration details. An RFID reader is installed at the monitoring point

      Once the RFID data, number plate number, and tint status are obtained:The data is transmitted to the central server using Wi-Fi/Ethernet/GSM.

      A MySQL database stores:

      Vehicle ID RFID tag number Vehicle number plateTimestampn Tint violation status Image evidence This allows long-term storage and future analysis of traffic data.

      1. Alert Generation and Monitoring Dashboard

         A web-based monitoring dashboard is developed using Flask/PHP/HTML-CSS.Traffic authorities can log in to the system.Real-time vehicle movement is displayed.If a tint

         violation or unauthorized vehicle is detected:An instant alert notification is generated.Violation details and captured image are displayed.Violation reports can be downloaded for legal documentation.

      2. Hardware and Software Integration

         The hardware and software modules are synchronized using serial and network communication.RFID reader communicates with the controller via UART.Camera transfers image data via USB/CSI interface.AI algorithms run on the processing unit.Data is pushed to the cloud or local server.The complete system operates in real time with high reliability and minimal human intervention.

      3. EM4100/4001 Module

         The EM4100 / EM4001 RFID module is a 125 kHz passive RFID system used for vehicle identification in the proposed system. Each vehicle carries an RFID tag with a unique ID, which is automatically read when it comes within range of the RFID reader.The obtained RFID data is matched with the vehicle database and combined with AI-based ANPR results for accurate vehicle tracking and tint violation detection. This dual verification improves reliability and reduces false identification.The module offers fast, contactless operation, low power consumption, and reliable performance, making it suitable for real-time traffic monitoring and security applications.

         Fig 2 :EM4100/4001 Module

      4. Fow of the Implemented System

      Vehicle enters monitoring zone.RFID reader scans the vehicle tag.Camera captures the vehicle image.ANPR system recognizes the number plate.Tint

      detection module analyzes window transparency.Data is verified with the database.Violation status is determined.Alert and record are generated on the monitoring dashboard.

5. RESULTS AND ANALYSIS

   The proposed Vehicle Tracking and Tint Violation Detection System using RFID and AI-Based ANPR was implemented and tested under real-time conditions to evaluate its performance in terms of accuracy, speed, reliability, and effectiveness. Multiple test vehicles with different lighting conditions, number plate styles, and window tint levels were used for experimental validation.

   1. RFID-Based Vehicle Identification Results

      The RFID module successfully identified vehicles in real time with a high detection rate. During testing:All registered RFID tags were read correctly within the readers range.The average tag detection time was less than 1 second.Unauthorized or unregistered vehicles were effectively detected and flagged.This confirms that RFID provides fast, contactless, and reliable vehicle identification.

   2. System Performance Results

      The AI-based ANPR system was evaluated using captured images under.Daylight conditions Night conditions Partial occlusion and different angles.

      The system achieved:

      High number plate detection and recognition accuracy Successful recognition of both private and commercial vehicle plates Minor errors only in cases of poor lighting and blurred images The use of deep learning significantly improved recognition performance compared to traditional image processing methods.

   3. Tint Violation Detection Results

      The window tint detection module was tested using vehicles with No tint Legal permissible tint Excessive/illegal tint.

      Results showed that:

      The system accurately estimated the Visible Light Transmission (VLT) value.Vehicles with tint exceeding the legal limit were correctly identified as violators.Performance slightly reduced under extreme sunlight and heavy shadows, but overall detection remained reliable.This confirms that the proposed system can automatically detect illegal tinted windows in real time.

   4. Integrated System Performance Analysis

      When all modules (RFID, ANPR, and Tint Detection) were integrated.The system successfully tracked vehicles in real time.RFID identification and ANPR results were properly matched.All detected violations were correctly stored in the central database.Real-time alerts were generated on the monitoring dashboard without delay.The total processing time for one vehicle (from detection to alert) was found to be within a few seconds, making the system suitable for real-time traffic monitoring.

   5. Comparative Analysis with Existing Systems

      Compared with traditional traffic monitoring systems, the proposed system offers.Automated identification instead of manual checking Dual verification using RFID + ANPR Automatic detection of tint violations, which is not commonly available in many existing systems Reduced manpower requirement Improved accuracy and faster response time.

   6. Discussion

      The experimental results clearly demonstrate that the integration of RFID and AI-based ANPR with tint detection significantly improves traffic surveillance and law enforcement efficiency. The system minimizes human error, enhances security, and ensures better compliance with traffic regulations. The results also indicate that environmental factors such as poor lighting and extreme weather slightly affect performance, which can be further improved using advanced cameras and improved AI models.

   7. Summary of Results

      High accuracy in RFID-based vehicle identification Effective AI-based number plate recognition Reliable detection of illegal tinted windows Real-time data transmission and alert generation Successful integration of all system modules.

      Fig 3: Tint detection 1

      Fig 4: Tint detection 2

      Fig 5: ANPR cam

      Fig 6: RFID

6. CONCLUSION

   This research presented a Vehicle Tracking and Tint Violation Detection System using RFID and AI-Based Automatic Number Plate Recognition (ANPR) to provide an efficient and automated solution for modern traffic monitoring and law enforcement. The proposed system successfully integrates RFID-based vehicle identification, AI-driven number plate recognition, and automatic window tint violation detection into a single unified platform.

   The experimental results demonstrate that the system is capable of accurately identifying vehicles in real time, recognizing number plates with high reliability, and detecting illegal tinted windows effectively. The use of RFID

   ensures fast and contactless authentication, while the AI- based ANPR module provides visual verification and enhances overall system accuracy. Automatic tint detection further strengthens traffic regulation enforcement by eliminating the need for manual inspection.

   The integrated architecture significantly reduces human intervention, minimizes errors, and improves operational efficiency for traffic authorities. The centralized database and real-time alert system enable effective monitoring, quick response to violations, and long-term data analysis. Hence, the proposed system is well suited for smart city applications, intelligent transportation systems, and real- time traffic surveillance.

   Overall, the implemented system proves to be a reliable, scalable, and cost-effective solution for automated vehicle tracking and tint violation detection, contributing to improved road safety and enhanced public security.

7. ACKNOWLEDGEMENT

   The authors would like to express their sincere gratitude to all those who contributed to the successful completion of this research work titled Vehicle Tracking and Tint Violation Detection System Using RFID and AI-Based ANPR. We are deeply thankful to our project guide for their continuous support, valuable guidance, and constructive suggestions throughout the course of this work.

   We also extend our heartfelt thanks to the Head of the Department and the faculty members of our institution for providing the necessary infrastructure, technical support, and encouragement. Our sincere appreciation is extended to our classmates and laboratory staff for their cooperation and assistance during the implementation and testing phases of the project.

   Finally, we would like to thank our parents and well- wishers for their constant motivation, support, and encouragement throughout this research work.

8. REFERENCES

1. S. Du, M. Ibrahim, M. Shehata, and W. Badawy, Automatic License Plate Recognition (ALPR): A State-of-the-Art Review, IEEE Transactions on Circuits and Systems for Video Technology, vol. 23, no. 2, pp. 311325, 2013.

2. K. Finkenzeller, RFID Handbook: Fundamentals and Applications in Contactless Smart Cards and Identification, 3rd ed., Wiley, 2010.

3. C.-N. E. Anagnostopoulos, I. E. Anagnostopoulos, V. Loumos, and E. Kayafas, A License Plate-Recognition Algorithm for Intelligent Transportation System Applications, IEEE Transactions on Intelligent Transportation Systems, vol. 7, no. 3, pp. 377392, 2006.

4. R. Silva and C. Jung, Real-Time Brazilian License Plate Detection and Recognition Using Deep Convolutional Neural Networks, IEEE International Conference on Graphics, Patterns and Images, pp. 5562, 2017.

5. A. Kumar, R. Khera, and S. Gupta, Automated Traffic Violation Detection Using Image Processing, International Journal of Computer Applications, vol. 144, no. 4, pp. 16, 2016.

6. Y. Chen, J. Sun, and Z. Li, Vision-Based Vehicle Window Tint Detection Using Light Transmission Analysis, International Journal of Computer Vision and Signal Processing, vol. 8, no. 2, pp. 4551, 2018.

7. P. Patil and V. Bansode, RFID Based Vehicle Authentication System for Parking Area, International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, vol. 5, no. 4,

   pp. 24202424, 2016.

8. S. Sharma, R. Singh, and P. Verma, IoT Based Smart Traffic Monitoring System Using RFID and ANPR, International Journal of Engineering and Technology, vol. 7, no. 4, pp. 236241, 2018.

9. N. Dalal and B. Triggs, Histograms of Oriented Gradients for Human Detection, IEEE Conference on Computer Vision and Pattern Recognition, pp. 886893, 2005.

10. T. Rajeshwari and S. Punithavalli, Automatic Number Plate Recognition Using OpenCV and Machine Learning, International Journal of Scientific Research in Computer Science, vol. 6, no. 3, pp. 120125, 2019.