ABSTRACT
Two situations are necessary to improve the safety and health conditions of people in industries: A proper use of Personal Protective Equipment by workers who develop their jobs into industrial areas and a continuous inspection promoted by employers. In this paper, we review the best known object detectors for prediction tasks, evaluating the features that are needed for a real-time surveillance system that can provide reliable predictions in a safety and health context. We present a tool based on Computer Vision which make predictions about if people are using their respective High Visibility Vest and Hard Hat. Additionally, the same model predicts if a person is wearing a face cover or there is an absence of this protector on the person's face. Our dataset was built by collecting images from available online datasets and we added own images. It has six classes which were defined by the combination of four instances. For detection task, we explored and evaluated different versions of You-only-look-once (YOLO). The best performance for a real time surveillance was reached by YOLO v5-nano, 125.3 FPS. On the other hand, the most important outcomes in terms of average precision were achieved by YOLO v4 and YOLO v5-small with 0.892 and 0.916 respectively.
- U. S. B. of L. Statistics, “About the construction sector,.” https://www.bls.gov/iag/tgs/iag23.htm (accessed Nov. 22, 2021).Google Scholar
- N. D. Nath and A. H. Behzadan, “Deep Learning Detection of Personal Protective Equipment to Maintain Safety Compliance on Construction Sites,” Constr. Res. Congr. 2020 Comput. Appl. - Sel. Pap. from Constr. Res. Congr. 2020, pp. 181–190, 2020, doi: 10.1061/9780784482865.020.Google ScholarCross Ref
- E. Badillo and C. Acevedo, “Actitud de los trabajadores ante el uso de Equipo de Proteccion Personal,” CuidArte, vol. 8, no. 15, pp. 56–66, 2019, doi: http://dx.doi.org/10.22201/fesi.23958979e.2019.8.15.69157.Google ScholarCross Ref
- N. D. Nath, A. H. Behzadan, and S. G. Paal, “Deep learning for site safety: Real-time detection of personal protective equipment,” Autom. Constr., vol. 112, no. July 2019, p. 103085, 2020, doi: 10.1016/j.autcon.2020.103085.Google ScholarCross Ref
- N. Filatov, N. Maltseva, and A. Bakhshiev, “Development of Hard Hat Wearing Monitoring System Using Deep Neural Networks with High Inference Speed,” in 2020 International Russian Automation Conference (RusAutoCon), Sep. 2020, pp. 459–463, doi: 10.1109/RusAutoCon49822.2020.9208155.Google ScholarCross Ref
- S. Khosravipour, E. Taghvaei, and N. M. Charkari, “COVID-19 personal protective equipment detection using real-time deep learning methods,” 2021, [Online]. Available: http://arxiv.org/abs/2103.14878.Google Scholar
- P. Soviany and R. T. Ionescu, “Optimizing the trade-off between single-stage and two-stage deep object detectors using image difficulty prediction,” Proc. - 2018 20th Int. Symp. Symb. Numer. Algorithms Sci. Comput. SYNASC 2018, pp. 209–214, 2018, doi: 10.1109/SYNASC.2018.00041.Google ScholarCross Ref
- M. Carranza-García, J. Torres-Mateo, P. Lara-Benítez, and J. García-Gutiérrez, “On the performance of one-stage and two-stage object detectors in autonomous vehicles using camera data,” Remote Sens., vol. 13, no. 1, pp. 1–23, 2021, doi: 10.3390/rs13010089.Google Scholar
- J. Redmon and A. Farhadi, “YOLO v3: An Incremental Improvement,” Tech Rep., pp. 1–6, 2018, [Online]. Available: https://pjreddie.com/media/files/papers/YOLOv3.pdf.Google Scholar
- A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” 2020, [Online]. Available: http://arxiv.org/abs/2004.10934.Google Scholar
- Z. Wang, Y. Wu, L. Yang, A. Thirunavukarasu, C. Evison, and Y. Zhao, “Fast Personal Protective Equipment Detection for Real Construction Construction Sites Using Deep Learning Approaches,” pp. 1–22, 2021.Google Scholar
- G. Jocher , “Ultralytics/yolov5: v3.1 - Bug Fixes and Performance Improvements,” Oct. 29, 2020. https://zenodo.org/record/4154370 (accessed Oct. 21, 2021).Google Scholar
- Z. Tian, C. Shen, H. Chen, and T. He, “FCOS: Fully convolutional one-stage object detection,” Proc. IEEE Int. Conf. Comput. Vis., vol. 2019-Octob, pp. 9626–9635, 2019, doi: 10.1109/ICCV.2019.00972.Google ScholarCross Ref
- Y. Zhang, C. Wang, X. Wang, W. Zeng, and W. Liu, “FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking,” pp. 1–13, 2020, doi: 10.1007/s11263-021-01513-4.Google ScholarDigital Library
- X. Zhou, D. Wang, and P. Krähenbühl, “Objects as Points,” 2019, [Online]. Available: http://arxiv.org/abs/1904.07850.Google Scholar
- H. M. Hung, L. T. Lan, and H. S. Hong, “a Deep Learning-Based Method for Real-Time Personal Protective Equipment Detection,” J. Sci. Tech. Le Quy Don Tech. Univ., vol. 199, no. 199, pp. 23–34, 2019.Google Scholar
- L. Biewald, “Experiment tracking with weights and biases,” 2020. https://www.wandb.com/.Google Scholar
- M. D. Bloice, P. M. Roth, and A. Holzinger, “Biomedical image augmentation using Augmentor,” Bioinformatics, vol. 35, no. 21, pp. 4522–4524, 2019, doi: 10.1093/bioinformatics/btz259.Google ScholarCross Ref
Index Terms
- Personal Protective Equipment use inspection, real time surveillance with YOLO
Recommendations
Detection of Personal Protective Equipment in Factories: A Survey and Benchmark Dataset
Intelligent Computing MethodologiesAbstractThere are many accidents in chemical plants and laboratories caused by workers not wearing the required personal protective equipment (PPE). Yet, manually ensuring that workers wear their PPE all the time is often infeasible. Object detection ...
OSDDY: embedded system-based object surveillance detection system with small drone using deep YOLO
AbstractComputer vision is an interdisciplinary domain for object detection. Object detection relay is a vital part in assisting surveillance, vehicle detection and pose estimation. In this work, we proposed a novel deep you only look once (deep YOLO V3) ...
Real-time background subtraction based on GPGPU for high-resolution video surveillance
IMCOM '17: Proceedings of the 11th International Conference on Ubiquitous Information Management and CommunicationDemand for intelligent surveillance has been increasing, to automatically detect and prevent dangerous situations with surveillance cameras. Image analysis, the most essential element in intelligent surveillance system, has continuously developed and ...
Comments