Computer-vision based automatic rider helmet violation detection and vehicle identification in Indian smart city scenarios using NVIDIA TAO toolkit and YOLOv8
Two-wheeler traffic offenses are a well-known fact about the Indian Road scenario. In addition to endangering the offenders, these offenses also endanger other commuters. Two-wheeler traffic violations can take many different forms, such as overloading, triple riding, and helmetless riding. Effectiv...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-07-01
|
| Series: | Frontiers in Artificial Intelligence |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frai.2025.1582257/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839622334030282752 |
|---|---|
| author | Uttam U. Deshpande Goh Kah Ong Michael Sufola Das Chagas Silva Araujo Vaidehi Deshpande Rudragoud Patil Ramchandra Alias Ameet Chate Varun R. Tandur Supreet S. Goudar Shreya Ingale Vaishnavi Charantimath |
| author_facet | Uttam U. Deshpande Goh Kah Ong Michael Sufola Das Chagas Silva Araujo Vaidehi Deshpande Rudragoud Patil Ramchandra Alias Ameet Chate Varun R. Tandur Supreet S. Goudar Shreya Ingale Vaishnavi Charantimath |
| author_sort | Uttam U. Deshpande |
| collection | DOAJ |
| description | Two-wheeler traffic offenses are a well-known fact about the Indian Road scenario. In addition to endangering the offenders, these offenses also endanger other commuters. Two-wheeler traffic violations can take many different forms, such as overloading, triple riding, and helmetless riding. Effective identification and enforcement strategies are necessary for these offenses since they pose a serious risk to public safety. Due to the inadequacy of traditional traffic monitoring and enforcement techniques, advanced technology-based solutions are now required. Deep learning-based systems have demonstrated significant promise in identifying and stopping such infractions in recent years. We propose a two-step deep learning approach that leverages the strengths of pre-trained object detection models to detect two-wheeler riders and specialized helmet classifiers to identify helmet wear status as well as detect number plates. In the first stage, we utilized a highly efficient, robust, and accurate object identification DetectNet (Model 1) framework developed by NVIDIA, and it uses the ResNet18 Convolutional Neural Network (CNN) architecture as part of the Transfer Learning Toolkit known as TAO (Train, Adapt, Optimize). The second stage demands accurate detection of a helmet on the identified rider and extracting numbers from the violator’s license plates using the OCR module in real time. We employed YOLOv8 (Model 2), a deep learning-based architecture that has proven effective in several applications involving object detection in real time. It predicts bounding boxes and class probabilities for objects within an image using a single neural network, making it a perfect choice for real-time applications like rider helmet violations detections and number plate processing. Due to a lack of publicly available traffic datasets, we created a custom dataset containing motorcycle rider images captured under complex scenarios for training and validating our models. Experimental analysis shows that our proposed two-step model achieved a promising helmet detection accuracy of 98.56% and a 97.6% number plate detection accuracy of persons not wearing helmets. The major objective of our proposed study is to enforce stringent traffic laws in real-time to decrease rider helmet violations. |
| format | Article |
| id | doaj-art-23df6b51bfce406a8c0a705d00f25a39 |
| institution | Matheson Library |
| issn | 2624-8212 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Artificial Intelligence |
| spelling | doaj-art-23df6b51bfce406a8c0a705d00f25a392025-07-22T05:29:51ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122025-07-01810.3389/frai.2025.15822571582257Computer-vision based automatic rider helmet violation detection and vehicle identification in Indian smart city scenarios using NVIDIA TAO toolkit and YOLOv8Uttam U. Deshpande0Goh Kah Ong Michael1Sufola Das Chagas Silva Araujo2Vaidehi Deshpande3Rudragoud Patil4Ramchandra Alias Ameet Chate5Varun R. Tandur6Supreet S. Goudar7Shreya Ingale8Vaishnavi Charantimath9Department of Electronics and Communication Engineering, KLS Gogte Institute of Technology, Karnataka, IndiaCenter for Image and Vision Computing, COE for Artificial Intelligence, Faculty of Information Science and Technology (FIST), Multimedia University Jalan Ayer, Keroh Lama, 75450, Bukit Beruang, Melaka, MalaysiaDepartment of Computer Science and Engineering, Padre Conceição College of Engineering, Goa, IndiaDepartment of Electronics and Communication Engineering, KLS Gogte Institute of Technology, Karnataka, IndiaDepartment of Computer Science and Engineering, KLS Gogte Institute of Technology, Karnataka, IndiaDepartment of MBA, KLS Gogte Institute of Technology, Karnataka, IndiaDepartment of Electronics and Communication Engineering, KLS Gogte Institute of Technology, Karnataka, IndiaDepartment of Electronics and Communication Engineering, KLS Gogte Institute of Technology, Karnataka, IndiaDepartment of Electronics and Communication Engineering, KLS Gogte Institute of Technology, Karnataka, IndiaDepartment of Electronics and Communication Engineering, KLS Gogte Institute of Technology, Karnataka, IndiaTwo-wheeler traffic offenses are a well-known fact about the Indian Road scenario. In addition to endangering the offenders, these offenses also endanger other commuters. Two-wheeler traffic violations can take many different forms, such as overloading, triple riding, and helmetless riding. Effective identification and enforcement strategies are necessary for these offenses since they pose a serious risk to public safety. Due to the inadequacy of traditional traffic monitoring and enforcement techniques, advanced technology-based solutions are now required. Deep learning-based systems have demonstrated significant promise in identifying and stopping such infractions in recent years. We propose a two-step deep learning approach that leverages the strengths of pre-trained object detection models to detect two-wheeler riders and specialized helmet classifiers to identify helmet wear status as well as detect number plates. In the first stage, we utilized a highly efficient, robust, and accurate object identification DetectNet (Model 1) framework developed by NVIDIA, and it uses the ResNet18 Convolutional Neural Network (CNN) architecture as part of the Transfer Learning Toolkit known as TAO (Train, Adapt, Optimize). The second stage demands accurate detection of a helmet on the identified rider and extracting numbers from the violator’s license plates using the OCR module in real time. We employed YOLOv8 (Model 2), a deep learning-based architecture that has proven effective in several applications involving object detection in real time. It predicts bounding boxes and class probabilities for objects within an image using a single neural network, making it a perfect choice for real-time applications like rider helmet violations detections and number plate processing. Due to a lack of publicly available traffic datasets, we created a custom dataset containing motorcycle rider images captured under complex scenarios for training and validating our models. Experimental analysis shows that our proposed two-step model achieved a promising helmet detection accuracy of 98.56% and a 97.6% number plate detection accuracy of persons not wearing helmets. The major objective of our proposed study is to enforce stringent traffic laws in real-time to decrease rider helmet violations.https://www.frontiersin.org/articles/10.3389/frai.2025.1582257/fulltraffic violationsdeep learningDetectNetResnet18NVIDIA TAOYOLOv8 |
| spellingShingle | Uttam U. Deshpande Goh Kah Ong Michael Sufola Das Chagas Silva Araujo Vaidehi Deshpande Rudragoud Patil Ramchandra Alias Ameet Chate Varun R. Tandur Supreet S. Goudar Shreya Ingale Vaishnavi Charantimath Computer-vision based automatic rider helmet violation detection and vehicle identification in Indian smart city scenarios using NVIDIA TAO toolkit and YOLOv8 Frontiers in Artificial Intelligence traffic violations deep learning DetectNet Resnet18 NVIDIA TAO YOLOv8 |
| title | Computer-vision based automatic rider helmet violation detection and vehicle identification in Indian smart city scenarios using NVIDIA TAO toolkit and YOLOv8 |
| title_full | Computer-vision based automatic rider helmet violation detection and vehicle identification in Indian smart city scenarios using NVIDIA TAO toolkit and YOLOv8 |
| title_fullStr | Computer-vision based automatic rider helmet violation detection and vehicle identification in Indian smart city scenarios using NVIDIA TAO toolkit and YOLOv8 |
| title_full_unstemmed | Computer-vision based automatic rider helmet violation detection and vehicle identification in Indian smart city scenarios using NVIDIA TAO toolkit and YOLOv8 |
| title_short | Computer-vision based automatic rider helmet violation detection and vehicle identification in Indian smart city scenarios using NVIDIA TAO toolkit and YOLOv8 |
| title_sort | computer vision based automatic rider helmet violation detection and vehicle identification in indian smart city scenarios using nvidia tao toolkit and yolov8 |
| topic | traffic violations deep learning DetectNet Resnet18 NVIDIA TAO YOLOv8 |
| url | https://www.frontiersin.org/articles/10.3389/frai.2025.1582257/full |
| work_keys_str_mv | AT uttamudeshpande computervisionbasedautomaticriderhelmetviolationdetectionandvehicleidentificationinindiansmartcityscenariosusingnvidiataotoolkitandyolov8 AT gohkahongmichael computervisionbasedautomaticriderhelmetviolationdetectionandvehicleidentificationinindiansmartcityscenariosusingnvidiataotoolkitandyolov8 AT sufoladaschagassilvaaraujo computervisionbasedautomaticriderhelmetviolationdetectionandvehicleidentificationinindiansmartcityscenariosusingnvidiataotoolkitandyolov8 AT vaidehideshpande computervisionbasedautomaticriderhelmetviolationdetectionandvehicleidentificationinindiansmartcityscenariosusingnvidiataotoolkitandyolov8 AT rudragoudpatil computervisionbasedautomaticriderhelmetviolationdetectionandvehicleidentificationinindiansmartcityscenariosusingnvidiataotoolkitandyolov8 AT ramchandraaliasameetchate computervisionbasedautomaticriderhelmetviolationdetectionandvehicleidentificationinindiansmartcityscenariosusingnvidiataotoolkitandyolov8 AT varunrtandur computervisionbasedautomaticriderhelmetviolationdetectionandvehicleidentificationinindiansmartcityscenariosusingnvidiataotoolkitandyolov8 AT supreetsgoudar computervisionbasedautomaticriderhelmetviolationdetectionandvehicleidentificationinindiansmartcityscenariosusingnvidiataotoolkitandyolov8 AT shreyaingale computervisionbasedautomaticriderhelmetviolationdetectionandvehicleidentificationinindiansmartcityscenariosusingnvidiataotoolkitandyolov8 AT vaishnavicharantimath computervisionbasedautomaticriderhelmetviolationdetectionandvehicleidentificationinindiansmartcityscenariosusingnvidiataotoolkitandyolov8 |