Personal protective equipment(PPE)donning detection for medical staff is a key link of medical operation safety guarantee and is of great significance to combat COVID-19.However,the lack of dedicated datasets makes th...Personal protective equipment(PPE)donning detection for medical staff is a key link of medical operation safety guarantee and is of great significance to combat COVID-19.However,the lack of dedicated datasets makes the scarce research on intelligence monitoring of workers’PPE use in the field of healthcare.In this paper,we construct a dress codes dataset for medical staff under the epidemic.And based on this,we propose a PPE donning automatic detection approach using deep learning.With the participation of health care personnel,we organize 6 volunteers dressed in different combinations of PPE to simulate more dress situations in the preset structured environment,and an effective and robust dataset is constructed with a total of 5233 preprocessed images.Starting from the task’s dual requirements for speed and accuracy,we use the YOLOv4 convolutional neural network as our learning model to judge whether the donning of different PPE classes corresponds to the body parts of the medical staff meets the dress codes to ensure their self-protection safety.Experimental results show that compared with three typical deeplearning-based detection models,our method achieves a relatively optimal balance while ensuring high detection accuracy(84.14%),with faster processing time(42.02 ms)after the average analysis of 17 classes of PPE donning situation.Overall,this research focuses on the automatic detection of worker safety protection for the first time in healthcare,which will help to improve its technical level of risk management and the ability to respond to potentially hazardous events.展开更多
The construction industry has always remained the economic and social backbone of any country in the world where occupational health and safety(OHS)is of prime importance.Like in other developing countries,this indust...The construction industry has always remained the economic and social backbone of any country in the world where occupational health and safety(OHS)is of prime importance.Like in other developing countries,this industry pays very little,rather negligible attention to OHS practices in Pakistan,resulting in the occurrence of a wide variety of accidents,mishaps,and near-misses every year.One of the major causes of such mishaps is the non-wearing of safety helmets(hard hats)at construction sites where falling objects from a height are unavoid-able.In most cases,this leads to serious brain injuries in people present at the site in general and the workers in particular.It is one of the leading causes of human fatalities at construction sites.In the United States,the Occupational Safety and Health Administration(OSHA)requires construction companies through safety laws to ensure the use of well-defined personal protective equipment(PPE).It has long been a problem to ensure the use of PPE because round-the-clock human monitoring is not possible.However,such monitoring through technological aids or automated tools is very much possible.The present study describes a systema-tic strategy based on deep learning(DL)models built on the You-Only-Look-Once(YOLOV5)architecture that could be used for monitoring workers’hard hats in real-time.It can indicate whether a worker is wearing a hat or not.The proposed system usesfive different models of the YOLOV5,namely YOLOV5n,YOLOv5s,YOLOv5 m,YOLOv5l,and YOLOv5x for object detection with the support of PyTorch,involving 7063 images.The results of the study show that among the DL models,the YOLOV5x has a high performance of 95.8%in terms of the mAP,while the YOLOV5n has the fastest detection speed of 70.4 frames per second(FPS).The proposed model can be successfully used in practice to recognize the hard hat worn by a worker.展开更多
为缓解YOLOv7在检测个人防护用品时面临标签重写、标签分配不平衡和特征耦合等问题,提出一种基于改进YOLOv7的检测方法.首先去除YOLOv7的大尺度和中尺度输出层,以降低标签重写率,且保证输出层得到充分训练;其次将输出层的定位和分类解耦...为缓解YOLOv7在检测个人防护用品时面临标签重写、标签分配不平衡和特征耦合等问题,提出一种基于改进YOLOv7的检测方法.首先去除YOLOv7的大尺度和中尺度输出层,以降低标签重写率,且保证输出层得到充分训练;其次将输出层的定位和分类解耦,避免不同任务的特征表示互相影响,并选择在边界框级别检测防护服,在关键点级别检测防护帽和防护手套;最后引入部分卷积,实现实时检测.为验证该方法的有效性,使用实验人员穿戴防护用品的图像数据对所提方法进行验证.结果表明,相比YOLOv7,该方法的精确率和召回率分别提高了4.1和4.5个百分点,FPS(Frames Per Second)提升了1.3帧,可满足实验室场景下的个人防护用品穿戴检测需求.展开更多
基金supported by the grants from the Natural Science Foundation of China(No.72161034).
文摘Personal protective equipment(PPE)donning detection for medical staff is a key link of medical operation safety guarantee and is of great significance to combat COVID-19.However,the lack of dedicated datasets makes the scarce research on intelligence monitoring of workers’PPE use in the field of healthcare.In this paper,we construct a dress codes dataset for medical staff under the epidemic.And based on this,we propose a PPE donning automatic detection approach using deep learning.With the participation of health care personnel,we organize 6 volunteers dressed in different combinations of PPE to simulate more dress situations in the preset structured environment,and an effective and robust dataset is constructed with a total of 5233 preprocessed images.Starting from the task’s dual requirements for speed and accuracy,we use the YOLOv4 convolutional neural network as our learning model to judge whether the donning of different PPE classes corresponds to the body parts of the medical staff meets the dress codes to ensure their self-protection safety.Experimental results show that compared with three typical deeplearning-based detection models,our method achieves a relatively optimal balance while ensuring high detection accuracy(84.14%),with faster processing time(42.02 ms)after the average analysis of 17 classes of PPE donning situation.Overall,this research focuses on the automatic detection of worker safety protection for the first time in healthcare,which will help to improve its technical level of risk management and the ability to respond to potentially hazardous events.
文摘The construction industry has always remained the economic and social backbone of any country in the world where occupational health and safety(OHS)is of prime importance.Like in other developing countries,this industry pays very little,rather negligible attention to OHS practices in Pakistan,resulting in the occurrence of a wide variety of accidents,mishaps,and near-misses every year.One of the major causes of such mishaps is the non-wearing of safety helmets(hard hats)at construction sites where falling objects from a height are unavoid-able.In most cases,this leads to serious brain injuries in people present at the site in general and the workers in particular.It is one of the leading causes of human fatalities at construction sites.In the United States,the Occupational Safety and Health Administration(OSHA)requires construction companies through safety laws to ensure the use of well-defined personal protective equipment(PPE).It has long been a problem to ensure the use of PPE because round-the-clock human monitoring is not possible.However,such monitoring through technological aids or automated tools is very much possible.The present study describes a systema-tic strategy based on deep learning(DL)models built on the You-Only-Look-Once(YOLOV5)architecture that could be used for monitoring workers’hard hats in real-time.It can indicate whether a worker is wearing a hat or not.The proposed system usesfive different models of the YOLOV5,namely YOLOV5n,YOLOv5s,YOLOv5 m,YOLOv5l,and YOLOv5x for object detection with the support of PyTorch,involving 7063 images.The results of the study show that among the DL models,the YOLOV5x has a high performance of 95.8%in terms of the mAP,while the YOLOV5n has the fastest detection speed of 70.4 frames per second(FPS).The proposed model can be successfully used in practice to recognize the hard hat worn by a worker.
文摘为缓解YOLOv7在检测个人防护用品时面临标签重写、标签分配不平衡和特征耦合等问题,提出一种基于改进YOLOv7的检测方法.首先去除YOLOv7的大尺度和中尺度输出层,以降低标签重写率,且保证输出层得到充分训练;其次将输出层的定位和分类解耦,避免不同任务的特征表示互相影响,并选择在边界框级别检测防护服,在关键点级别检测防护帽和防护手套;最后引入部分卷积,实现实时检测.为验证该方法的有效性,使用实验人员穿戴防护用品的图像数据对所提方法进行验证.结果表明,相比YOLOv7,该方法的精确率和召回率分别提高了4.1和4.5个百分点,FPS(Frames Per Second)提升了1.3帧,可满足实验室场景下的个人防护用品穿戴检测需求.
