DPPNet: A Deformable-Perspective-Perception network for Safety Helmet Violation Detection
Received: 16 November 2023 | Revised: 5 December 2023 | Accepted: 7 December 2023 | Online: 11 December 2023
Corresponding author: Yahia Said
Abstract
The issue of worker safety at construction sites has become increasingly prominent within the construction industry. Safety helmet usage has been shown to reduce accidents among construction workers. However, there are instances when safety helmets are not consistently worn, which may be attributed to a variety of factors. Therefore, an automated system based on computer vision needs to be established to track protective gear appropriate usage. While there have been studies on helmet detection systems, there is a limited amount of research specifically addressing helmet detection. Also, various challenges need to be addressed such as small object miss-detection and occluded helmet detection. To fix these issues, a Deformable Perspective Perception Network (DPPNet) is proposed in this paper. Two modules make up the proposed DPPNet: Background/Image Spatial Fusion (BISF) and Grayscale Background Subtraction (GBS). While the BISF module utilizes channel attention to blend feature maps from a current frame and the background, the GBS submodule in particular incorporates background spatial information into a current frame. Additionally, the DPPNet facilitates occluded and small helmet detection. Excessive training and testing experiments have been performed using the Safety Helmet Wearing Detection (SHWD) Dataset. Experimental results demonstrate the effectiveness of the proposed DPPNet network. The obtained findings exhibit that the suggested module significantly enhances the detection capabilities of small objects. Effective mean average precision results have been obtained on the SHWD dataset coming up to 97.4% of mAP.
Keywords:
construction sites, traffic accidents, violation detection, deep learning, DPPNet, safety helmetDownloads
References
K. Dahiya, D. Singh, and C. K. Mohan, "Automatic detection of bike-riders without helmet using surveillance videos in real-time," in International Joint Conference on Neural Networks, Vancouver, BC, Canada, Jul. 2016, pp. 3046–3051.
"CDC Works 24/7," Centers for Disease Control and Prevention, Dec. 06, 2023. https://www.cdc.gov/index.htm.
M. Aftf, R. Ayachi, Y. Said, E. Pissaloux, and M. Atri, "Indoor Object C1assification for Autonomous Navigation Assistance Based on Deep CNN Model," in International Symposium on Measurements & Networking, Catania, Italy, Jul. 2019, pp. 1–4.
M. Afif, R. ayachi, Y. Said, E. Pissaloux, and M. Atri, "Recognizing signs and doors for Indoor Wayfinding for Blind and Visually Impaired Persons," in 5th International Conference on Advanced Technologies for Signal and Image Processing, Sousse, Tunisia, Sep. 2020, pp. 1–4.
M. Afif, R. Ayachi, S. Yahia, and M. Atri, "COVID-19 Disease Detection Using Deep Learning Techniques in CT Scan Images," in Advanced AI and Internet of Health Things for Combating Pandemics, M. Lahby, V. Pilloni, J. S. Banerjee, and M. Mahmud, Eds. New York, NY, USA: Springer, 2023, pp. 177–191.
R. Ayachi, M. Afif, Y. Said, and A. B. Abdelaali, "pedestrian detection for advanced driving assisting system: a transfer learning approach," in 5th International Conference on Advanced Technologies for Signal and Image Processing, Sousse, Tunisia, Sep. 2020, pp. 1–5.
R. Ayachi, M. Afif, Y. Said, and A. B. Abdelali, "Real-Time Implementation of Traffic Signs Detection and Identification Application on Graphics Processing Units," International Journal of Pattern Recognition and Artificial Intelligence, vol. 35, no. 7, Jun. 2021, Art. no. 2150024.
R. Ayachi, M. Afif, Y. Said, and A. B. Abdelali, "An Embedded Implementation of a Traffic Light Detection System for Advanced Driver Assistance Systems," in Industrial Transformation, Boca Raton, FL, USA: CRC Press, 2022, pp. 237–250.
Y. Said, M. Barr, and H. E. Ahmed, "Design of a Face Recognition System based on Convolutional Neural Network (CNN)," Engineering, Technology & Applied Science Research, vol. 10, no. 3, pp. 5608–5612, Jun. 2020.
D. Contractorr, K. Pathak, S. Sharma, S. Bhagat, and T. Sharma, "Cascade Classifier based Helmet Detection using OpenCV in Image Processing," in National Conference on Recent Trends in Computer and Communication Technology, May. 2016, pp. 195–200.
L. Shine and C. V. Jiji, "Automated detection of helmet on motorcyclists from traffic surveillance videos: a comparative analysis using hand-crafted features and CNN," Multimedia Tools and Applications, vol. 79, no. 19, pp. 14179–14199, May 2020.
V. H. Duong, Q. H. Tran, H. S. P. Nguyen, D. Q. Nguyen, and T. C. Nguyen, "Helmet Rule Violation Detection for Motorcyclists Using a Custom Tracking Framework and Advanced Object Detection Techniques," in Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada, Jun. 2023, pp. 5381–5390.
D. N.-N. Tran et al., "Robust Automatic Motorcycle Helmet Violation Detection for an Intelligent Transportation System," in Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada, Jun. 2023, pp. 5341–5349.
L. Wang et al., "Investigation Into Recognition Algorithm of Helmet Violation Based on YOLOv5-CBAM-DCN," IEEE Access, vol. 10, pp. 60622–60632, 2022.
N. Kharade, S. Mane, J. Raghav, N. Alle, A. Khatavkar, and G. Navale, "Deep-learning based helmet violation detection system," in International Conference on Artificial Intelligence and Machine Vision, Gandhinagar, India, Sep. 2021, pp. 1–4.
P. Sridhar, M. Jagadeeswari, S. H. Sri, N. Akshaya, and J. Haritha, "Helmet Violation Detection using YOLO v2 Deep Learning Framework," in 6th International Conference on Trends in Electronics and Informatics, Tirunelveli, India, Apr. 2022, pp. 1207–1212.
G. Agorku et al., "Real-Time Helmet Violation Detection Using YOLOv5 and Ensemble Learning." arXiv, Apr. 14, 2023.
A. Aboah, B. Wang, U. Bagci, and Y. Adu-Gyamfi, "Real-Time Multi-Class Helmet Violation Detection Using Few-Shot Data Sampling Technique and YOLOv8," in Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada, Jun. 2023, pp. 5350–5358.
A. Goyal, D. Agarwal, A. Subramanian, C. V. Jawahar, R. K. Sarvadevabhatla, and R. Saluja, "Detecting, Tracking and Counting Motorcycle Rider Traffic Violations on Unconstrained Roads," in Conference on Computer Vision and Pattern Recognition, Jun. 2022, pp. 4303–4312.
njvisionpower, "Safety-Helmet-Wearing-Dataset." github.com, Dec. 08, 2023, [Online]. Available: https://github.com/njvisionpower/Safety-Helmet-Wearing-Dataset.
S. T. Mpinda Ataky, J. de Matos, A. de S. Britto, L. E. S. Oliveira, and A. L. Koerich, "Data Augmentation for Histopathological Images Based on Gaussian-Laplacian Pyramid Blending," in International Joint Conference on Neural Networks, Glasgow, UK, Jul. 2020, pp. 1–8.
S. Bell, C. L. Zitnick, K. Bala, and R. Girshick, "Inside-Outside Net: Detecting Objects in Context With Skip Pooling and Recurrent Neural Networks," in Conference on Computer Vision and Pattern Recognition, Jun. 2016, pp. 2874–2883.
X. Tang, D. K. Du, Z. He, and J. Liu, "PyramidBox: A Context-assisted Single Shot Face Detector," in European Conference on Computer Vision, Munich, Germany, Sep. 2018, pp. 797–813.
S. Ioffe and C. Szegedy, "Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift," in 32nd International Conference on Machine Learning, Lile, France, Jul. 2015, pp. 448–456.
BT.601-5 - Studio encoding parameters of digital television for standard 4:3 and wide-screen 16:9 aspect ratios. ITU, 2011.
S. Woo, J. Park, J.-Y. Lee, and I. S. Kweon, "CBAM: Convolutional Block Attention Module," in 15th European Conference on Computer Vision, Munich, Germany, Sep. 2018, pp. 3–19.
J. Hu, L. Shen, and G. Sun, "Squeeze-and-Excitation Networks," in Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, Jun. 2018, pp. 7132–7141.
Q. Wang, B. Wu, P. Zhu, P. Li, W. Zuo, and Q. Hu, "ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks," in Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, Jun. 2020, pp. 11534–11542.
H. Rezatofighi, N. Tsoi, J. Gwak, A. Sadeghian, I. Reid, and S. Savarese, "Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression," in Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, Jun. 2019, pp. 658–666.
H. Zhang et al., "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection." arXiv, Jul. 11, 2022.
M. Karthi, V. Muthulakshmi, R. Priscilla, P. Praveen, and K. Vanisri, "Evolution of YOLO-V5 Algorithm for Object Detection: Automated Detection of Library Books and Performace validation of Dataset," in International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, Chennai, India, Sep. 2021, pp. 1–6.
Z. Ge, S. Liu, F. Wang, Z. Li, and J. Sun, "YOLOX: Exceeding YOLO Series in 2021." arXiv, Aug. 05, 2021.
M. Touahmia, "Identification of Risk Factors Influencing Road Traffic Accidents," Engineering, Technology & Applied Science Research, vol. 8, no. 1, pp. 2417–2421, Feb. 2018
F. Siddiqui, M. A. Akhund, A. H. Memon, A. R. Khoso, and H. U. Imad, "Health and Safety Issues of Industry Workmen," Engineering, Technology & Applied Science Research, vol. 8, no. 4, pp. 3184–3188, Aug. 2018.
X. Chen and Q. Xie, "Safety Helmet-Wearing Detection System for Manufacturing Workshop Based on Improved YOLOv7," Journal of Sensors, vol. 2023, May 2023, Art. no. e7230463.
J. Li, Y. Li, J. F. Villaverde, X. Chen, and X. Zhang, "A safety wearing helmet detection method using deep leaning approach," Journal of Optics, Jul. 2023.
Y. Qian and B. Wang, "A new method for safety helmet detection based on convolutional neural network," PLOS ONE, vol. 18, no. 10, Sep. 2023, Art. no. e0292970.
Downloads
How to Cite
License
Copyright (c) 2023 Yahya Alassaf, Yahia Said
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
