Skip to main content
SpringerLink
Log in

Hybrid Architecture for Traffic Light Recognition Using Deep CNN and Ensemble Machine Learning Model

  • Conference paper
  • First Online:
Proceedings of Third Emerging Trends and Technologies on Intelligent Systems (ETTIS 2023)

Part of the book series: Lecture Notes in Networks and Systems ((LNNS,volume 730))

  • 164 Accesses

Abstract

Traffic light recognition is an essential basic technology for automated driving in metropolitan areas. Traffic light recognition plays a significant part in the field of autonomous vehicles for safe driving. It has been proven that using intelligent vehicles will be the norm in the next years. However, numbers of challenges are currently existent in traffic light recognition, such as the appearance of traffic light, illumination, and the bad weather, etc. More and more cars on the road means more and more collisions, especially at intersections where lights change. To enhance the driving safety at traffic lights, this research provides an intelligent traffic light system based on the combination of deep learning and machine learning from visual image processing. The recognition performance of the suggested technique was tested experimentally to see if it is adequate for automated driving. The verification experiments demonstrate that the performance of the proposed method meets the necessary standards at junctions in automated driving.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 149.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 199.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Lee E, Kim D (2019) Accurate traffic light detection using deep neural network with focal regression loss. Image Vision Comput 87. https://doi.org/10.1016/j.imavis.2019.04.003

  2. Wang X, Jiang T, Xie Y (2018) A method of traffic light status recognition based on deep learning. RCAE 2018

    Google Scholar 

  3. Kim J, Cho H, Hwangbo M, Choi J, Canny J, Kwon YJ (2018) Deep traffic light detection for self-driving cars from a large-scale dataset, pp 280–285. https://doi.org/10.1109/ITSC.2018.8569575

  4. Loh SH, Sim JJ, Ong CS, Yeap KH, The PC, Tshai KH (2021) Development of smart traffic light controller system with deep learning capability in image processing, applications of modelling and simulation

    Google Scholar 

  5. Nine J, Mathavan R (2021) Traffic Light And Back-Light Recognition Using Deep Learning And Image Processing with Raspberry Pi. Embed Selforganising Syst 8:15–19. https://doi.org/10.14464/ess.v8i2.490

  6. Possatti LC et al (2019) Traffic light recognition using deep learning and prior maps for autonomous cars. In: 2019 International joint conference on neural networks (IJCNN), pp 1–8. https://doi.org/10.1109/IJCNN.2019.8851927

  7. Yeh T-W, Lin H-Y (2020) Detection and recognition of arrow traffic signals using a two-stage neural network structure, pp 322–330. https://doi.org/10.5220/0009345203220330

  8. Kim H, Park J, Jung H-Y (2018) An efficient color space for deep-learning based traffic light recognition. J Adv Transp 2018:1–12. https://doi.org/10.1155/2018/2365414

  9. Acoba A, De Los Trinos M, Cunanan C, Guerrero N, Casuat C (2021) A deep neural inferencing approach of assistive Philippine traffic light recognition: an augmented transfer learning approach, pp 307–310. https://doi.org/10.1109/ICCIKE51210.2021.9410683

  10. Sun X, Shi W, Cheng Q, Liu W, Wang Z, Zhang J (2021) An LED detection and recognition method based on deep learning in vehicle optical camera communication. IEEE Access 1–1. https://doi.org/10.1109/ACCESS.2021.3085117

  11. Yeh T-W, Lin H-Y, Chang C-C (2021) Traffic light and arrow signal recognition based on a unified network. Appl Sci 11:8066. https://doi.org/10.3390/app11178066

    Article  Google Scholar 

  12. Chen X, Zhang C (2019) Traffic light recognition based on spectral residual model and multi-feature fusion. In: 2019 2nd International conference on safety produce informatization (IICSPI), pp 119–123. https://doi.org/10.1109/IICSPI48186.2019.9096010

  13. Zeng Y, Xie K, Yang M, Wu J (2019) Traffic light recognition and ranging system based on machine vision. In: 2019 International conference on high performance big data and intelligent systems (HPBD&IS), pp 204–208.https://doi.org/10.1109/HPBDIS.2019.8735440

  14. Almeida T, Macedo H, Matos L, Vasconcelos N (2018) Prototyping a traffic light recognition device with expert knowledge. Information 9:278. https://doi.org/10.3390/info9110278

    Article  Google Scholar 

  15. John V, Yoneda K, Qi B, Liu Z, Mita S (2014) Traffic light recognition in varying illumination using deep learning and saliency map. In: 17th International IEEE conference on intelligent transportation systems (ITSC), pp 2286–2291. https://doi.org/10.1109/ITSC.2014.6958056

  16. Scavone JM, Ferreira JL, Barea ERA, Junior GB, Neto A (2020) Optimizing CNN’s using cumulative learning with auxiliary networks for traffic light recognition, pp 273–278. https://doi.org/10.1109/IWSSIP48289.2020.9145056

  17. Li Z, Zeng Q, Liu Y-C, Liu J, Li L (2021) An improved traffic lights recognition algorithm for autonomous driving in complex scenarios. Int J Distrib Sens Netw 17:155014772110183. https://doi.org/10.1177/15501477211018374

    Article  Google Scholar 

  18. Bao C, Chen C, Kui H, Wang X (2019) Safe driving at traffic lights: an image recognition based approach, pp 112–117. https://doi.org/10.1109/MDM.2019.00-67

  19. Sharma M, Bansal A, Kashyap V, Goyal P, Sheakh T (2021) Intelligent traffic light control system based on traffic environment using deep learning. IOP Conf Ser Mater Sci Eng 1022:012122. https://doi.org/10.1088/1757-899X/1022/1/012122

    Article  Google Scholar 

  20. Kim HK, Yoo KY, Park JH, Jung HY (2019) Traffic light recognition based on binary semantic segmentation network. Sensors (Basel) 19(7):1700. PMID: 30974735; PMCID: PMC6479298. https://doi.org/10.3390/s19071700

  21. Yoneda K, Kuramoto A, Suganuma N, Asaka T, Aldibaja M, Yanase R (2020) Robust traffic light and arrow detection using digital map with spatial prior information for automated driving. Sensors (Basel, Switzerland) 20

    Google Scholar 

  22. Catalin P, Stavarache I, Stoica T, Ciurea M (2020) GeSi nanocrystals photo-sensors for optical detection of slippery road conditions combining two classification algorithms. Sensors 20:6395. https://doi.org/10.3390/s20216395

    Article  Google Scholar 

  23. Wang Q, Zhang Q, Liang X, Wang Y, Zhou C, Mikulovich VI (2021) Traffic lights detection and recognition method based on the improved YOLOv4 algorithm. Sensors (Basel) 22(1):200. PMID: 35009743; PMCID: PMC8749665. https://doi.org/10.3390/s22010200

  24. Rao SS, Desai SR (2021) Machine learning based traffic light detection and IR sensor based proximity sensing for autonomous cars (July 10, 2021). Proceedings of the International conference on IoT based control networks & intelligent systems (ICICNIS 2021). Available at SSRN: https://ssrn.com/abstract=3883931 or https://doi.org/10.2139/ssrn.3883931

  25. Wang JG, Zhou LB (2019) Traffic light recognition with high dynamic range imaging and deep learning. IEEE Trans Intell Transp Syst 20(4):1341–1352. https://doi.org/10.1109/TITS.2018.2849505

    Article  Google Scholar 

  26. https://hci.iwr.uni-heidelberg.de/content/bosch-small-traffic-lights-dataset

  27. https://www.kaggle.com/datasets/mbornoe/lisa-traffic-light-dataset

Download references

Author information

Authors and Affiliations

  1. Department of Electronics and Telecommunication Engineering, PRMIT & R Badnera, Amravati, Maharashtra, India

    Akshay Utane & S. W. Mohod

Authors
  1. Akshay Utane
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. S. W. Mohod
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Akshay Utane .

Editor information

Editors and Affiliations

  1. Education & Training, CDAC, Noida, India

    Arti Noor

  2. Education & Training, CDAC, Noida, Uttar Pradesh, India

    Kriti Saroha

  3. Automatic Control, Computers and Electronics Department, Petroleum-Gas University of Ploiesti, Ploiesti, Romania

    Emil Pricop

  4. Computing Science and Information Technology, Kwantlen Polytechnic University, Surrey, BC, Canada

    Abhijit Sen

  5. EEE Department, IIT Guwahati, Guwahati, India

    Gaurav Trivedi

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Utane, A., Mohod, S.W. (2023). Hybrid Architecture for Traffic Light Recognition Using Deep CNN and Ensemble Machine Learning Model. In: Noor, A., Saroha, K., Pricop, E., Sen, A., Trivedi, G. (eds) Proceedings of Third Emerging Trends and Technologies on Intelligent Systems. ETTIS 2023. Lecture Notes in Networks and Systems, vol 730. Springer, Singapore. https://doi.org/10.1007/978-981-99-3963-3_10

Download citation

Publish with us

Policies and ethics

Search

Navigation