Abstract
To evade falling objects, debris, impacts with other objects, rain, and electric shock, workers at industrial or construction sites usually don hard hats or safety helmets to safeguard themselves. As a result, detecting the use of safety helmets can safeguard workers from these types of mishaps. Installing the detection system in checkpoints is efficient because manual screening is time-consuming and ineffective. This procedure may be divided into two stages. First, cameras will be installed at the department’s entry points. This lowers the requirement for manual checking by humans and, alternatively, simply requires someone to be notified if a helmet violation is identified. The next stage is to use this facility to constantly monitor if employees are still wearing the required PPE and are in regulated areas of the worksite. A helmet wearing detection system based on YOLOv7 is proposed here. Mean average precision of 0.98 was obtained for a dataset consisting of a single head classes, and a precision of 0.96 was obtained for a dataset consisting of head and helmet classes. The results indicate the effectiveness and practicality of the model, making it a dependable and suitable option for safety helmet detection.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
LNCS homepage. https://www.bls.gov/iag/tgs/iag23.htm. Accessed 24 Dec 2022
Redmon J, Divvala S, Girshick R, Farhadi A (2015) You only look once: unified, real-time object detection. https://arxiv.org/abs/1506.02640
Wang C, Bochkovskiy A, Liao H (2022) YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. https://arxiv.org/abs/2207.02696
Li N, Lyu X, Xu S, Wang Y, Wang Y, Gu Y (2021) Incorporate online hard example mining and multi-part combination into automatic safety helmet wearing detection. IEEE Access 9:139536–139543
Jin M, Lu B, Zhang J, Wang Q, Chen X, Nie G, Huang T, Fu J, Guo Z, Wang X (2021) Video streaming helmet detection algorithm based on feature map fusion and faster RCNN. In: 2021 international conference on electronic information engineering and computer science (EIECS), pp 470–474
Chen S, Tang W, Ji T, Zhu H, Ouyang Y, Wang W (2020) Detection of safety helmet wearing based on improved faster R-CNN. In: 2020 international joint conference on neural networks (IJCNN), pp 1–7
Li Y, Wei H, Han Z, Huang J, Wang W (Sep 2020) Deep learning-based safety helmet detection in engineering management based on convolutional neural networks. Adv Civ Eng 2020:1–10
Shanti M, Cho C, Byon Y, Yeun C, Kim T, Kim S, Altunaiji A (2021) A novel implementation of an AI-based smart construction safety inspection protocol in the UAE. IEEE Access 9:166603–166616
Zhao B, Lan H, Niu Z, Zhu H, Qian T, Tang W (2021) Detection and location of safety protective wear in power substation operation using wear-enhanced YOLOv3 algorithm. IEEE Access 6:125540–125549
Liu L, Han R, Huang X, Jiang X, Hong Q, Gao S (2021) Safety helmet detection based on YOLOV3N. In: 2021 14th international congress on image and signal processing, biomedical engineering and informatics (CISP-BMEI), pp 1–4
Kumar S, Gupta H, Yadav D, Ansari I, Verma O (Jul 2022) YOLOv4 algorithm for the real-time detection of fire and personal protective equipments at construction sites. Multimed Tools Appl 81
Benyang D, Xiaochun L, Miao Y (2020) Safety helmet detection method based on YOLO v4. In: 2020 16th international conference on computational intelligence and security (CIS), pp 155–158
Gao S, Ruan Y, Wang Y, Xu W, Zheng M (2022) Safety helmet detection based on YOLOV4-M. In: 2022 IEEE international conference on artificial intelligence and computer applications (ICAICA), pp 179–181
Zhou F, Zhao H, Nie Z (2021) Safety helmet detection based on YOLOv5. In: 2021 IEEE international conference on power electronics, computer applications (ICPECA), pp 6–11
Zhou M, Zhu J, Li X (2022) Safety helmet detection system of smart construction site based on YOLOv5S. In: 2022 7th international conference on intelligent computing and signal processing (ICSP), pp 1223–1228
Han K, Zeng X (2022) Deep learning-based workers safety helmet wearing detection on construction sites using multi-scale features. IEEE Access 10:718–729
Wang L, Cao Y, Wang S, Song X, Zhang S, Zhang J, Niu J (2022) Investigation into recognition algorithm of helmet violation based on YOLOv5-CBAM-DCN. IEEE Access 10:60622–60632
Hayat A, Morgado-Dias F (Aug 2022) Deep learning-based automatic safety helmet detection system for construction safety. Appl Sci 12:8268
Wang C, Yeh I, Liao H (2021) You only learn one representation: unified network for multiple tasks. https://arxiv.org/abs/2105.04206
Wu D, Jiang S, Zhao E, Liu Y, Zhu H, Wang W, Wang R (2022) Detection of camellia oleifera fruit in complex scenes by using YOLOv7 and data augmentation. Appl Sci 12. https://www.mdpi.com/2076-3417/12/22/11318
YOLOv7-a breakdown of how it works. https://blog.roboflow.com/yolov7-breakdown. Accessed 25 Dec 2022
HardHatW32:online. https://universe.roboflow.com/joseph-nelson/hard-hat-workers. Accessed 25 Dec 2022
Wang X, Song J (2021) ICIoU: improved loss based on complete intersection over union for bounding box regression. IEEE Access 9:105686–105695
Liang H, Seo S (2022) Automatic detection of construction workers & RSQUO; helmet wear based on lightweight deep learning. Appl Sci 12. https://www.mdpi.com/2076-3417/12/20/10369
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Athidhi, B.P., Smitha Vas, P. (2023). YOLOv7-Based Model for Detecting Safety Helmet Wear on Construction Sites. In: Raj, J.S., Perikos, I., Balas, V.E. (eds) Intelligent Sustainable Systems. ICoISS 2023. Lecture Notes in Networks and Systems, vol 665. Springer, Singapore. https://doi.org/10.1007/978-981-99-1726-6_29
Download citation
DOI: https://doi.org/10.1007/978-981-99-1726-6_29
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1725-9
Online ISBN: 978-981-99-1726-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)