Single-level Discrete Two Dimensional Wavelet Transform Based Multiscale Deep Learning Framework for Two-Wheeler Helmet Detection

Authors

DOI:

https://doi.org/10.4108/eetinis.v12i2.7612

Keywords:

Multi Scale CNN, Long Short-Term Memory, Discrete Wavelet Transform, Helmet Detection

Abstract

INTRODUCTION: A robust method is proposed in this paper to detect helmet usage in two-wheeler riders to enhance road safety.

OBJECTIVES: This involves a custom made dataset that contains 1000 images captured under diverse real-world scenarios, including variations in helmet size, colour, and lighting conditions. This dataset has two classes namely with helmet and without helmet.

METHODS: The proposed helmet classification approach utilizes the Multi-Scale Deep Convolutional Neural Network (CNN) framework cascaded with Long Short-Term Memory (LSTM) network. Initially the Multi-Scale Deep CNN extracts modes by applying Single-level Discrete 2D Wavelet Transform (dwt2) to decompose the original images. In particular, four different modes are used for segmenting a single image namely approximation, horizontal detail, vertical detail and diagonal detail. After feeding the segmented images into a Multi-Scale Deep CNN model, it is cascaded with an LSTM network.

RESULTS: The proposed model achieved accuracies of 99.20% and 95.99% using both 5-Fold Cross-Validation (CV) and Hold-out CV methods, respectively.

CONCLUSION: This result was better than the CNN-LSTM, dwt2-LSTM and a tailor made CNN model.

Downloads

References

[1] A. Afzal, H. Umer, Z. Khan, and M. U. Khan, “Automatic Helmet Violation Detection of Motorcyclists from Surveillance Videos using Deep Learning Approaches of Computer Vision,” Apr. 2021, pp. 252–257. doi: 10.1109/ICAI52203.2021.9445206. DOI: https://doi.org/10.1109/ICAI52203.2021.9445206

[2] D. M. Trupthi, “Helmet Detection Based on Convolutional Neural Networks,” vol. 09, no. 06, 2022.

[3] A. Soni and A. Singh, “Automatic Motorcyclist Helmet Rule Violation Detection using Tensorflow & Keras in OpenCV,” Feb. 2020, pp. 1–5. doi: 10.1109/SCEECS48394.2020.55. DOI: https://doi.org/10.1109/SCEECS48394.2020.55

[4] T. Waris et al., “CNN-Based Automatic Helmet Violation Detection of Motorcyclists for an Intelligent Transportation System,” Math. Probl. Eng., vol. 2022, pp. 1–11, Oct. 2022, doi: 10.1155/2022/8246776. DOI: https://doi.org/10.1155/2022/8246776

[5] J. Mercado Reyna et al., “Detection of Helmet Use in Motorcycle Drivers Using Convolutional Neural Network,” Appl. Sci., vol. 13, no. 10, Art. no. 10, Jan. 2023, doi: 10.3390/app13105882. DOI: https://doi.org/10.3390/app13105882

[6] N. Boonsirisumpun, W. Puarungroj, and P. Wairotchanaphuttha, “Automatic Detector for Bikers with no Helmet using Deep Learning,” in 2018 22nd International Computer Science and Engineering Conference (ICSEC), Nov. 2018, pp. 1–4. doi: 10.1109/ICSEC.2018.8712778. DOI: https://doi.org/10.1109/ICSEC.2018.8712778

[7] M. Dasgupta, O. Bandyopadhyay, and S. Chatterji, “Automated Helmet Detection for Multiple Motorcycle Riders using CNN,” in 2019 IEEE Conference on Information and Communication Technology, Dec. 2019, pp. 1–4. doi: 10.1109/CICT48419.2019.9066191. DOI: https://doi.org/10.1109/CICT48419.2019.9066191

[8] A. Singh, D. Singh, J. Singh, P. Singh, and D. A. Kaur, “Helmet & Number Plate Detection Using Deep Learning and Its Comparative Analysis.” Rochester, NY, Jun. 29, 2022. doi: 10.2139/ssrn.4149145. DOI: https://doi.org/10.2139/ssrn.4149145

[9] L. Shine and J. C. V., “Automated detection of helmet on motorcyclists from traffic surveillance videos: a comparative analysis using hand-crafted features and CNN,” Multimed. Tools Appl., vol. 79, no. 19–20, pp. 14179–14199, May 2020, doi: 10.1007/s11042-020-08627-w. DOI: https://doi.org/10.1007/s11042-020-08627-w

[10] H. Lin, J. D. Deng, D. Albers, and F. W. Siebert, “Helmet use detection of tracked motorcycles using CNN-based multi-task learning.,” IEEE Access, vol. 8, Sep. 2020, doi: 10.1109/access.2020.3021357. DOI: https://doi.org/10.1109/ACCESS.2020.3021357

[11] C. A. Rohith, S. A. Nair, P. S. Nair, S. Alphonsa, and N. P. John, “An Efficient Helmet Detection for MVD using Deep learning,” in 2019 3rd International Conference on Trends in Electronics and Informatics (ICOEI), Apr. 2019, pp. 282–286. doi: 10.1109/ICOEI.2019.8862543. DOI: https://doi.org/10.1109/ICOEI.2019.8862543

[12] R. Cheng, X. He, Z. Zheng, and Z. Wang, “Multi-Scale Safety Helmet Detection Based on SAS-YOLOv3-Tiny,” Appl. Sci., vol. 11, no. 8, Art. no. 8, Jan. 2021, doi: 10.3390/app11083652. DOI: https://doi.org/10.3390/app11083652

[13] S. Kanakaraj, “Real-time Motorcyclists Helmet Detection and Vehicle License Plate Extraction using Deep Learning Techniques”.

[14] S. Chen, J. Lan, H. Liu, C. Chen, and X. Wang, “Helmet Wearing Detection of Motorcycle Drivers Using Deep Learning Network with Residual Transformer-Spatial Attention,” Drones, vol. 6, no. 12, Art. no. 12, Dec. 2022, doi: 10.3390/drones6120415. DOI: https://doi.org/10.3390/drones6120415

[15] F. W. Siebert and H. Lin, “Detecting motorcycle helmet use with deep learning,” Accid. Anal. Prev., vol. 134, p. 105319, Jan. 2020, doi: 10.1016/j.aap.2019.105319. DOI: https://doi.org/10.1016/j.aap.2019.105319

Downloads

Published

11-03-2025

How to Cite

Annadurai, A., Ranjan Prusty, M., Pandey, T. N., & Rani Patra, S. (2025). Single-level Discrete Two Dimensional Wavelet Transform Based Multiscale Deep Learning Framework for Two-Wheeler Helmet Detection. EAI Endorsed Transactions on Industrial Networks and Intelligent Systems, 12(2). https://doi.org/10.4108/eetinis.v12i2.7612