{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T22:19:19Z","timestamp":1793830759047,"version":"4.6.1"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T00:00:00Z","timestamp":1753142400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>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\u2019s 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.<\/jats:p>","DOI":"10.3389\/frai.2025.1582257","type":"journal-article","created":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T05:31:31Z","timestamp":1753162291000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Computer-vision based automatic rider helmet violation detection and vehicle identification in Indian smart city scenarios using NVIDIA TAO toolkit and YOLOv8"],"prefix":"10.3389","volume":"8","author":[{"given":"Uttam U.","family":"Deshpande","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Goh Kah Ong","family":"Michael","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sufola Das Chagas Silva","family":"Araujo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vaidehi","family":"Deshpande","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rudragoud","family":"Patil","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramchandra Alias Ameet","family":"Chate","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Varun R.","family":"Tandur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Supreet S.","family":"Goudar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shreya","family":"Ingale","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vaishnavi","family":"Charantimath","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,7,22]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1061\/JTEPBS.TEENG-7312","article-title":"Driver maneuver detection and analysis using time series segmentation and classification","volume":"149","author":"Aboah","year":"2023","journal-title":"J. Transport. Eng. A Syst."},{"key":"ref2","first-page":"252","article-title":"Automatic helmet violation detection of motorcyclists from surveillance videos using deep learning approaches of computer vision","volume-title":"Proceedings of the 2021 international conference on artificial intelligence (ICAI)","author":"Afzal","year":"2021"},{"key":"ref3","article-title":"Real-time helmet violation detection using YOLOv5 and ensemble learning","author":"Agorku","year":"2023"},{"key":"ref4","article-title":"Ai-based framework for understanding car following behaviors of drivers in a naturalistic driving environment","author":"Armstrong Aboah","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"14819","DOI":"10.1109\/ACCESS.2022.3148036","article-title":"CNN-based object recognition and tracking system to assist visually impaired people","volume":"10","author":"Ashiq","year":"2022","journal-title":"IEEE Access"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1049\/iet-cvi.2008.0089","article-title":"Urban road user detection and classification using 3D wire frame models","volume":"4","author":"Buch","year":"2010","journal-title":"IET Comput. Vis."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"920","DOI":"10.1109\/TITS.2011.2119372","article-title":"A review of computer vision techniques for the analysis of urban traffic","volume":"12","author":"Buch","year":"2011","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1049\/iet-its.2011.0138","article-title":"Helmet presence classification with motorcycle detection and tracking","volume":"6","author":"Chiverton","year":"2012","journal-title":"IET Intell. Transp. Syst."},{"key":"ref9","first-page":"1","article-title":"Automated helmet detection for multiple motorcycle riders using CNN","volume-title":"Proceedings of the 2019 IEEE conference on information and communication technology","author":"Dasgupta","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1535775","DOI":"10.3389\/fcomp.2025.1535775","article-title":"Computer vision and AI-based cell phone usage detection in restricted zones of manufacturing industries","volume":"7","author":"Deshpande","year":"2025","journal-title":"Front. Comput. Sci."},{"key":"ref001","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/s44163-025-00263-3","article-title":"Automatic two-wheeler rider identification and triple-riding detection in surveillance systems using deep-learning models","volume":"5","author":"Deshpande","year":"2025","journal-title":"Discov Artif Intell"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"144","DOI":"10.4103\/2249-4863.104987","article-title":"A public health perspective of road traffic accidents","volume":"1","author":"Gopalakrishnan","year":"2012","journal-title":"J. Family Med. Prim. Care"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1136\/ip.2006.012112","article-title":"Bicycle helmet prevalence two years after the introduction of mandatory use legislation for under 18-year-olds in Alberta, Canada","volume":"12","author":"Hagel","year":"2011","journal-title":"Inj. Prev."},{"key":"ref13","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1007\/978-981-19-0840-8_14","article-title":"Traffic rule violation detection system: deep learning approach","volume-title":"Advanced machine intelligence and signal processing","author":"Kathane","year":"2022"},{"key":"ref14","first-page":"1","article-title":"Deep-learning based helmet violation detection system","volume-title":"Proceedings of the 2021 international conference on artificial intelligence and machine vision (AIMV)","author":"Kharade","year":"2021"},{"key":"ref15","volume-title":"Labelimg: the ultimate tool for efficient data annotation","year":"2025"},{"key":"ref16","first-page":"1","article-title":"An automatic detection of helmeted and non-helmeted motorcyclist with license plate extraction using convolutional neural network","volume-title":"Proceedings of the 2017 seventh international conference on image processing: eory, tools and applications (IPTA)","author":"Mistry","year":"2017"},{"key":"ref17","volume-title":"Object detection using TAO DetectNet_v2","year":"2025"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/IWAIT.2018.8369734","article-title":"Helmet violation processing using deep learning","volume-title":"Proceedings of the 2018 international workshop on advanced image technology (IWAIT)","author":"Raj","year":"2018"},{"key":"ref19","first-page":"286","article-title":"Traffic violation invigilation using transfer learning","volume-title":"Proceedings of the 2022 international conference on electronic systems and intelligent computing (ICESIC)","author":"Rajalakshmi","year":"2022"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1109\/IVCNZ.2013.6726989","article-title":"Machine vision techniques for motorcycle safety helmet detection","volume-title":"2013 28th International Conference on Image and Vision Computing New Zealand (IVCNZ 2013)","author":"Rattapoom Waranusast","year":"2013"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1177\/0971097320130415","article-title":"Patterns of head injuries in road traffic accidents involving two wheelers: an autopsy study","volume":"35","author":"Ravikumar","year":"2013","journal-title":"J. Indian Acad. Forensic Med."},{"key":"ref22","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1109\/CVPR.2016.91","article-title":"You only look once: unified, real-time object detection","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Redmon","year":"2016"},{"key":"ref23","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"105319","DOI":"10.1016\/j.aap.2019.105319","article-title":"Detecting motorcycle helmet use with deep learning","volume":"134","author":"Siebert","year":"2020","journal-title":"Accid. Anal. Prev."},{"key":"ref25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/CLEI.2013.6670613","article-title":"Automatic detection of motorcyclists without helmet","volume-title":"Proceedings of the 2013 XXXIX Latin American computing conference (CLEI)","author":"Silva","year":"2013"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1109\/SIBGRAPI.2014.28","article-title":"Helmet detection on motorcyclists using image descriptors and classifiers","volume-title":"Proceedings of the 2014 27th SIBGRAPI conference on graphics, patterns and images","author":"Silva","year":"2014"},{"key":"ref27","volume-title":"Model benchmarking with Ultralytics YOLO","year":"2025"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"3694","DOI":"10.1109\/TVT.2010.2058134","article-title":"An enhanced background estimation algorithm for vehicle detection in urban traffic scenes","volume":"59","author":"Vargas","year":"2010","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref29","doi-asserted-by":"crossref","first-page":"3036","DOI":"10.1109\/IJCNN.2017.7966233","article-title":"Detection of motorcyclists without helmet in videos using convolutional neural network","volume-title":"Proceedings of the 2017 international joint conference on neural networks (IJCNN)","author":"Vishnu","year":"2017"},{"key":"ref30","first-page":"35","article-title":"Machine vision techniques for motorcycle safety helmet detection","volume-title":"Proceedings of the 2013 28th international conference on image and vision computing New Zealand (IVCNZ 2013)","author":"Waranusast","year":"2013"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2022\/8246776","article-title":"CNN-based automatic helmet violation detection of motorcyclists for an intelligent transportation system","volume":"2022","author":"Waris","year":"2022","journal-title":"Math. Probl. Eng., Hindawi"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.cd004607.pub3","article-title":"Speed cameras for the prevention of road traffic injuries and deaths","volume":"6","author":"Wilson","year":"2010","journal-title":"Cochrane Database Syst. Rev."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"147","DOI":"10.47852\/bonviewJCCE20514","article-title":"Research on vehicle automatic driving target perception technology based on improved MSRPN algorithm","volume":"1","author":"Yang","year":"2022","journal-title":"J. Comput. Cogn. Eng."},{"key":"ref34","year":"2025"},{"key":"ref35","volume-title":"A brief history of YOLO object detection models from YOLOv1 to YOLOv5","year":"2025"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1582257\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T05:31:34Z","timestamp":1753162294000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1582257\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,22]]},"references-count":36,"alternative-id":["10.3389\/frai.2025.1582257"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1582257","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,22]]},"article-number":"1582257"}}