Single-level Discrete Two Dimensional Wavelet Transform Based Multiscale Deep Learning Framework for Two-Wheeler Helmet Detection
DOI:
https://doi.org/10.4108/eetinis.v12i2.7612Keywords:
Multi Scale CNN, Long Short-Term Memory, Discrete Wavelet Transform, Helmet DetectionAbstract
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
How to Cite
Issue
Section
License
Copyright (c) 2024 Amrutha Annadurai, Manas Ranjan Prusty, Trilok Nath Pandey, Subhra Rani Patra
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 3.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
