Automatic Detection of Personal Protective Equipment in Construction Sites Using Metaheuristic Optimized YOLOv5
Arabian Journal for Science and Engineering, ISSN: 2191-4281, Vol: 49, Issue: 10, Page: 13519-13537
2024
- 2Citations
- 15Captures
Metric Options: Counts1 Year3 YearSelecting the 1-year or 3-year option will change the metrics count to percentiles, illustrating how an article or review compares to other articles or reviews within the selected time period in the same journal. Selecting the 1-year option compares the metrics against other articles/reviews that were also published in the same calendar year. Selecting the 3-year option compares the metrics against other articles/reviews that were also published in the same calendar year plus the two years prior.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Article Description
Personal protective equipment (PPE) plays a crucial role in safeguarding the well-being of workers on construction sites by mitigating the risk of accidents and incidents. Nevertheless, incidents stemming from a lack of awareness regarding PPE usage persist. To enhance the oversight of construction laborers for accident prevention, most current approaches involve overseeing the availability and correct utilization of PPE using intricate data processing techniques. However, these methods encounter challenges related to their applicability and capacity for universal implementation. This study presents the hybridization of seahorse optimization (SHO) algorithm with the YOLOv5 model to ultimate detection accuracy. First, an improved YOLO network is constructed through scale and loss function enhancement. Second, the SHO is utilized to tune the parameters of the improved YOLOv5. A data set with 4535 construction work images was collected for training, validation and testing the hybrid SHO-YOLOv5 model. Experimental results supported by statistical tests show that the SHO-YOLOv5 is a capable method for detecting automatically the PPE with a precision value of 0.74, recall value of 0.65 and F1 score of 0.68. The SHO-YOLOv5 surpasses the benchmarked models like YOLOv8, YOLOv5, Faster-R-CNN MobilenetV3, and Faster-R-CNN Resnet50. Therefore, the proposed hybrid approach is a promising tool to support the project managers in the task of safety inspection.
Bibliographic Details
Springer Science and Business Media LLC
Provide Feedback
Have ideas for a new metric? Would you like to see something else here?Let us know