ADAS Implementation & Drowsiness Detection in Vehicle

Year : 2026 | Volume : 13 | Issue : 01 | Page : 28 36
    By

    Rudraksha Makune,

  • Namdev Girme,

  • Anirudha Lakare,

  • Dadasaheb Moin,

  • Krushna Memane,

  • Sonam Gujrathi,

  1. Student, Department of Mechanical Engineering, Sanjivani College of Engineering, Kopargaon, Maharashtra, India
  2. Student, Department of Mechanical Engineering, Sanjivani College of Engineering, Kopargaon, Maharashtra,
  3. Student, Department of Mechanical Engineering, Sanjivani College of Engineering, Kopargaon, Maharashtra, India
  4. Student, Department of Mechanical Engineering, Sanjivani College of Engineering, Kopargaon, Maharashtra, India
  5. Student, Department of Mechanical Engineering, Sanjivani College of Engineering, Kopargaon, Maharashtra, India
  6. Student, Department of Mechanical Engineering, Sanjivani College of Engineering, Kopargaon, Maharashtra, India

Abstract

Driver fatigue is a leading cause of road accidents, especially in public and commercial transportation, posing serious risks to passenger and pedestrian safety. To address this critical safety issue effectively, this research study presents an AI-powered ADAS designed specifically for BS6-compliant buses, using real-time fatigue detection to prevent accidents. The system integrates a Raspberry Pi equipped with an AI Hat+ module to monitor driver drowsiness by detecting prolonged eye closures (exceeding 4 seconds). Upon identification of fatigue, the system triggers a multistage safety protocol: an audible buzzer alert, activation of a water sprayer for immediate arousal, and, if unresponsive, automated braking to ensure vehicle safety. The system is efficiently controlled via an ESP32 microcontroller and L2983 motor drivers powered directly by a bus battery for seamless integration. By combining low-cost hardware with scalable AI-driven detection, this solution offers a practical and effective approach for mitigating fatigue-related accidents, enhancing road safety, and reducing fatalities in commercial transportation.

Keywords: Advanced driver assistance system, artificial intelligence, driver fatigue, electronics hardware, microcontroller

[This article belongs to Journal of Mechatronics and Automation ]

How to cite this article:
Rudraksha Makune, Namdev Girme, Anirudha Lakare, Dadasaheb Moin, Krushna Memane, Sonam Gujrathi. ADAS Implementation & Drowsiness Detection in Vehicle. Journal of Mechatronics and Automation. 2026; 13(01):28-36.
How to cite this URL:
Rudraksha Makune, Namdev Girme, Anirudha Lakare, Dadasaheb Moin, Krushna Memane, Sonam Gujrathi. ADAS Implementation & Drowsiness Detection in Vehicle. Journal of Mechatronics and Automation. 2026; 13(01):28-36. Available from: https://journals.stmjournals.com/joma/article=2026/view=241749


References

  1. ARAI, “Anthropometric Study of Indian Commercial Vehicle Drivers,” ARAI/VR/2023/47, Pune, 2023. [DOI: 10.13140/RG.2.2.35671.55203]
  2. Zhang et al., “Thermal Imaging-Based Drowsiness Detection for Sunglass Wearers,” IEEE Transactions on Vehicular Technology, vol. 72, no. 5, pp. 5892-5905, May 2023. [DOI: 10.1109/TVT.2023.3267894]
  3. Patel and R. Menon, “Facial Landmark Detection Accuracy Across Ethnic Groups,” Springer Intelligent Transportation Systems, vol. 18, no. 3, pp. 112-129, 2022. [DOI: 10.1007/s12544-022-00604-6]
  4. NHTSA, “Drowsy Driving Detection Protocols,” Technical Paper DOT HS 812 567, Washington, DC, 2017. [Online]. Available: https://rosap.ntl.bts.gov/view/dot/43562
  5. UNECE, “Uniform Provisions Concerning Braking,” UN Regulation No. 13-H, Geneva, 2020. [Online]. Available: https://unece.org/transport/documents/2021/01/standards/un-regulation-no-13-h
  6. ISO, “Road Vehicles – Functional Safety,” ISO 26262:2018, Geneva, 2018. [DOI: 10.3403/30303333]
  7. Toyota ADAS Team, “Low-Light Performance Challenges in Vision-Based ADAS,” SAE WCX World Congress Experience, Detroit, 2024. [DOI: 10.4271/2024-01-2812]
  8. Volkswagen Group, “Car2X Safety Framework for Fleet Management,” VW Tech. Rep. TR-2023-ADAS-14, Wolfsburg, 2023. [Online]. Available: https://www.volkswagen-group.com/en/innovation/adas-whitepapers
  9. Bertozzi et al., “Real-Time Lane Detection for Emerging Markets,” IEEE Intelligent Vehicles Symposium, pp. 45-52, 2018. [DOI: 10.1109/IVS.2018.8500652]
  10. Jain and P. Deshmukh, “Optimal EAR Thresholds for South Asian Drivers,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 7, pp. 6788-6799, Jul. 2021. [DOI: 10.1109/TITS.2021.3098765]
  11. IRC, “Specifications for Road Markings,” IRC-35-2015, New Delhi, 2015. [Online]. Available: https://morth.nic.in/sites/default/files/IRC-35-2015.pdf
  12. Bosch Automotive, “Driver Drowsiness Detection Systems: Technical Benchmarking,” Bosch Tech. Bull. TB-ADAS-004, Stuttgart, 2024. [DOI: 10.13140/RG.2.2.24256.20485]
  13. Soukupová and J. Čech, “Real-Time Eye Blink Detection Using Facial Landmarks,” 21st Computer Vision Winter Workshop, pp. 1-8, 2016. [Online]. Available: https://vision.fe.uni-lj.si/cvww2016/proceedings/papers/05.pdf
  14. MORTH, “Road Accidents in India Annual Report,” New Delhi, 2022. [Online]. Available: https://morth.nic.in/sites/default/files/Road_Accidents_in_India_2022.pdf
  15. Euro NCAP, “Test Protocol for Driver Monitoring Systems,” v3.2, Brussels, 2023. [Online]. Available: https://cdn.euroncap.com/media/72400/euro-ncap-dms-test-protocol-v32.pdf
  16. https://m.media-amazon.com/images/I/51QIHTWqThL._AC_SL1001_.jpg
  17. https://cdn.sos.sk/productdata/e9/b5/f7e05063/rpi4-modbp-8gb.jpg
Regular Issue Subscription Original Research
Volume 13
Issue 01
Received 13/01/2026
Accepted 07/02/2026
Published 10/03/2026
Publication Time 56 Days
2

Login


My IP

PlumX Metrics