Research on YOLOv7-tiny Improved Algorithm for Compli-ance Detection of Production Personnel Wearing
Pages 320 - 326
Abstract
Proposed is an improved production personnel wearing target detection algorithm based on YOLOv7, aiming to address the issues of false positives and false negatives caused by occlusion and detection of small to medium-sized objects in complex backgrounds. The algorithm introduces a Transformer module into the Backbone to better capture global feature information of images. The spatial pyramid pooling layer (SPPCSP) is enhanced to improve the model's detection speed. Additionally, the detection head of the model is replaced with the decoupled YOLOX detection head to enhance detection accuracy. Experiments were conducted on the publicly available safety helmet dataset SHWD, with the addition of two classes of targets: reflective clothing and people wearing reflective clothing. The experimental results demonstrate that the improved algorithm achieves a detection accuracy of 89.6% on this dataset, which is an improvement of 1.5 percentage points compared to the original algorithm. The detection speed reaches 85 FPS, showing good accuracy and real-time performance. Furthermore, compared with some mainstream target detection algorithms, the proposed improved algorithm also exhibits certain advantages.
References
[1]
Yaling L., Jie Y. 2022. Research on Human Attire Recognition Based on Support Vector Machine. Automation and Instrumentation, 272(06):47-51.
[2]
Cong L., Jinlei H., Junhuang Z., Wanfei K. 2019. Image Recognition Algorithm of Substation Operation Personnel's Attire Based on SRBFNN. Guangdong Electric Power, 32(09): 124-130. https://kns.cnki.net/kcms2/article/abstract?v=3uoqIhG8C44YLTlOAiTRKibYlV5Vjs7iLik5jEcCI09uHa3oBxtWoAEUY1ivYDH mUlejbuxFWsK2YFcIXDM109SZvX_0KggA&uniplatform=NZKPT&src=copy.
[3]
JIAO L., ZHANG F., LIU F., 2019. A survey of deep learning-based object detection.
[4]
Girshick R., Dnoahue J., Darrell T., 2014. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington, D.C. 580-587.
[5]
Girshick R. Fast R-CNN. 2015. Rich Feature Hierarchies for Accurate Object Detection and Se-mantic Segmentation. In Proceedings of the IEEE Conference on Com-puter Vision and Pattern Recognition (CVPR). Boston. 1440-1448.
[6]
Shaoqing R., 2017. Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6): 1137-1149.
[7]
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C., Berg, A. C. 2016. SSD: Single Shot Multibox Detector. In European Conference on Computer Vision (ECCV). Amsterdam. 21-37.
[8]
Redmon, J., Divvala, S., Girshick, R., Farhadi, A. 2016. You Only Look Once: Unified, Real-Time Object Detection. In Proceed-ings of the IEEE Conference on Computer Vision and Pattern Recogni-tion(CVPR). Las Vegas. 779-788.
[9]
Redmon J, Farhadi A. YOLO9000: Better, Faster, Stronger. 2017. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Hawaii. 7263-7271.
[10]
REDMON J, FARHADI A, 2019 YOLOv3: An incremental improvement. https://arxiv.org/abs/1804.02767v1.
[11]
Alexey B., CHIENYAO W., HONGYUAN M. L, 2019. Yolov4: optimal speed and accuracy of object detection
[12]
CHU L., LULU L., HONGLIANG J., 2022. YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications.
[13]
CHIENYAO W., Alexey B., HONGYUAN M. L, 2022. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors.
[14]
Xinyi L., Baofeng Z. Ye F., 2020. Normative Detection of Attire for Operators in Polluted Workplaces Based on Deep Learning.Journal of Safety Science and Technology, 16(7):169-175. https://kns.cnki.net/kcms2/article/abstract?v=3uoqIhG8C44YLTlOAiTRKibYlV5Vjs7i8oRR1PAr7RxjuAJk4dHXor395rYBFHm 6DIwupPj4SsnZoCQKfHRF94hLgiWJnHYb&uniplatform=NZKPT&src=copy.
[15]
Zejia H., Qinkun X., Liqi Z. 2021. Improved SSD-based Algorithm for Safety Helmet and Reflective Clothing Detection.Automation and Instrumentation, 2021,36(9):63-68.
[16]
Wu F., JIN G., GAO M., 2019. Helmet Detection Based on Improved YOLOv3 deep model. In International Conference on Networking,Sensing and Control(ICNSC). Salvador. 363-368.
[17]
Dosovitskiy A., Beyer L., Kolesnikov A., Weissenborn D., Zhai X., Unterthiner T., 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. International Conference on Learning Representations (ICLR). Vienna. 1534-1543.
[18]
Zheng G., Songtao L., Feng W., Zeming L., Jian S, 2021, YOLOX: Exceeding YOLO Series.
Index Terms
- Research on YOLOv7-tiny Improved Algorithm for Compli-ance Detection of Production Personnel Wearing
Index terms have been assigned to the content through auto-classification.
Recommendations
An Efficient Helmet Wearing Detection Method Based On YOLOv7-Tiny
MLMI '23: Proceedings of the 6th International Conference on Machine Learning and Machine IntelligenceIn high-risk construction environments, ensuring safety is paramount. Accidents, often resulting in casualties, underscore the importance of wearing helmets correctly. To tackle the challenges posed by small, traditional targets and the complexity of ...
Helmet detection algorithm based on improved yolov7
CSAI '23: Proceedings of the 2023 7th International Conference on Computer Science and Artificial IntelligenceIn order to solve the problems of low detection accuracy, wrong detection and missed detection in the traditional target detection algorithm in the safety helmet detection task, a safety helmet detection algorithm based on improved YOLOv7 is proposed. ...
Improved Helmet Wearing Detection Method Based on YOLOv3
Artificial Intelligence and SecurityAbstractIn order to monitor the wearing of safety helmet in dangerous workplace in real-time and ensure the safety of production, this paper proposes a method based on the yolov3 algorithm to detect the wearing of safety helmet. Firstly, K-means algorithm ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
October 2023
446 pages
ISBN:9798400716683
DOI:10.1145/3640912
Copyright © 2023 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 22 February 2024
Check for updates
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
CNML 2023
CNML 2023: 2023 International Conference on Communication Network and Machine Learning
October 27 - 28, 2023
Zhengzhou, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 24Total Downloads
- Downloads (Last 12 months)24
- Downloads (Last 6 weeks)6
Reflects downloads up to 12 Dec 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format