• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2023년도 봄 학술논문 발표대회
• /
• pp.173-174
• /
• 2023

In this paper, we introduce a model for detecting Personal Protective Equipment (PPE) using YOLO (You Only Look Once), an object detection neural network. PPE is used to maintain a safe working environment, and proper use of PPE protects workers' safety and health. However, failure to wear PPE or wearing it improperly can cause serious safety issues. Therefore, a PPE detection system is crucial in industrial settings.

• 한국지역사회생활과학회지
• /
• 제28권3호
• /
• pp.391-401
• /
• 2017

This study was conducted to evaluate the relationships between exposure level to pyrethroid pesticide and wearing of protective equipment in 194 Chung-nam orchard male farmers. The urinary metabolites of pyrethroid pesticides, including Cis, Trans, DBCA, and 3-PBA, were analyzed by GC/MSD. As a result of this study, the detection rate and exposure level of 3-PBA was the highest among pyrethroid metabolites discovered by orchard farmers. As a result of analyzing the actual conditions of wearing protective equipment by the subjects of this study, the rate of agricultural farmers who wore four pieces of protective equipment compared to agricultural farmers wearing a single piece of protective clothing was as high as 35.1%. Pyrethroid exposure levels were low when farmers wore more personal protective equipment (PPE). In conclusion, training with regards to pesticide hazards and protective equipment for farmers who spray pesticides will help reduce pesticide exposure levels.

• International Journal of Advanced Culture Technology
• /
• 제10권1호
• /
• pp.302-309
• /
• 2022

Occupational safety accidents are caused by various factors, and it is difficult to predict when and why they occur, and it is directly related to the lives of workers, so the interest in safety accidents is increasing every year. Therefore, in order to reduce safety accidents at industrial fields, workers are required to wear personal protective equipment. In this paper, we proposes a method to automatically check whether workers are wearing safety helmets among the protective equipment in the industrial field. It detects whether or not the helmet is worn using YOLOv5, a computer vision-based deep learning object detection algorithm. We transfer learning the s model among Yolov5 models with different learning rates and epochs, evaluate the performance, and select the optimal model. The selected model showed a performance of 0.959 mAP.

• 한국재난정보학회 논문집
• /
• 제18권2호
• /
• pp.269-279
• /
• 2022

연구목적: 본 연구의 목적은 건설현장의 재해 예방을 위해 딥러닝기반의 개인보호구 검출 모델을 개발하고, 실제 건설현장에 적용하여 분석하는 것이다. 연구방법: 본 연구의 수행 방법은 실제 환경의 데이터를 구축하고, 개발된 개인보호구 검출 모델을 적용하였다. 개인보호구 검출 모델은 크게 근로자 검출 및 개인보호구 착용 분류 모델로 구성되어 있다. 근로자 검출 모델은 딥러닝 기반의 알고리즘을 실제 현장에서 획득한 데이터셋을 구축하여 학습 및 근로자를 검출하였고, 개인보호구 착용 분류 모델은 앞단에서 추출된 근로자 검출영역에서 학습된 개인보호구 검출 알고리즘을 적용하였다. 구축된 모델의 검증을 위해 건설현장 3곳에서 획득된 데이터를 통해 실험결과를 도출하였다. 연구결과: 데이터베이스 12,000장을 구축하여 정상검출 9,460장(78.8%), 오검출 1,468(12.2%), 미검출 1,072장(8.9%)으로 나타났으며 주요 원인은 영상에서의 객체 크기, 객체간 중첩(Occulusion), 객체 잘림, 그림자에 의한 오검출로 분류되었다. 결론: 개인보호구 검출모델은 현장 상황마다 다른 검출률을 확인할 수 있었고, 본 연구의 결과가 차후 현장적용을 위한 연구에 활용될 수 있을 것으로 여겨진다.

• 한국건축시공학회지
• /
• 제23권1호
• /
• pp.81-92
• /
• 2023

According to the 2020 industrial accident reports of the Ministry of Employment and Labor, the number of fatal accidents in the construction industry over the past 5 years has been higher than in other industries. Of these more than 50% of fatal accidents are initially caused by fall accidents. The central government is intensively managing falling/jamming protection device and the use of personal protective equipment to eradicate the inappropriate factors disrupting safety at construction sites. In addition, although efforts have been made to prevent safety accidents with the proposal of the Special Act on Construction Safety, fatalities on construction sites are constantly occurring. Therefore, this study developed a model that automatically detects the wearing state of the worker's safety helmet and belt using computer vision technology. In considerations of conditions occurring at construction sites, we suggest an optimization method, which has been verified in terms of the accuracy and operation speed of the proposed model. As a result, it is possible to improve the efficiency of inspection and patrol by construction site managers, which is expected to contribute to reinforcing competency of safety management.

• 국제학술발표논문집
• /
• The 6th International Conference on Construction Engineering and Project Management
• /
• pp.313-316
• /
• 2015

Construction is one of the most dangerous job sectors, which reports tens of thousands of time-loss injuries and deaths every year. These disasters incur delays and additional costs to the projects. The safety management needs to be on the top primary tasks throughout the construction to avoid fatal accidents and to foster safe working environments. One of the safety regulations that are frequently violated is the wearing of personal protection equipment (PPE). In order to facilitate monitoring of the compliance of the PPE wearing regulations, this paper proposes a vision based method that automatically identifies whether workers wear hard hats and safety vests. The method involves three modules - human body detection, identification of safety vest wearing, and hard hat detection. First, human bodies are detected in the video frames captured by real-time on-site construction cameras. The detected human bodies are classified into with/without wearing safety vests based on the color features of their upper parts. Finally, hard hats are detected on the nearby regions of the detected human bodies and the locations of the detected hard hats and human bodies are correlated to reveal their corresponding matches. In this way, the proposed method provides any appearance of the workers without wearing hard hats or safety vests. The method has been tested on onsite videos and the results signify its potential to facilitate site safety monitoring.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.721-727
• /
• 2022

Construction safety remains an ongoing concern, and project managers have been increasingly forced to cope with myriad uncertainties related to human operations on construction sites and the lack of a skilled workforce in hazardous circumstances. Various construction fatality monitoring systems have been widely proposed as alternatives to overcome these difficulties and to improve safety management performance. In this study, we propose an intelligent, automatic control system that can proactively protect workers using both the analysis of big data of past safety accidents, as well as the real-time detection of worker non-compliance in using personal protective equipment (PPE) on a construction site. These data are obtained using computer vision technology and data analytics, which are integrated and reinforced by lessons learned from the analysis of big data of safety accidents that occurred in the last 10 years. The system offers data-informed recommendations for high-risk workers, and proactively eliminates the possibility of safety accidents. As an illustrative case, we selected a pilot project and applied the proposed system to workers in uncontrolled environments. Decreases in workers PPE non-compliance rates, improvements in variable compliance rates, reductions in severe fatalities through guidelines that are customized according to the worker, and accelerations in safety performance achievements are expected.

• 농약과학회지
• /
• 제20권2호
• /
• pp.172-180
• /
• 2016

본 연구는 국내 일부 농업인을 대상으로 유기인계 농약 노출수준과 농약살포 특성의 관련성을 규명하기 위하여 수행되었다. 소변시료를 채취하여 GC/MSD와 GC/MS/MS를 이용하여 분석하였으며, 소변 중 DMP, DMTP, DEP, DETP를 대상으로 검출률 및 노출수준을 평가 하였다. 검출률은 DMP, DMTP에서 캡이 없는 SS살포기가 캡이 있는 SS살포기보다 높았고, 보호구 착용률이 낮을수록 높았다. 노출수준은 동력 분무기가 가장 높았고, 캡이 있는 SS살포기에서 낮게 나타났다. 또한, 착용 보호구 개수가 증가할수록 노출수준이 낮아짐을 확인할 수 있었다. 검출률은 카이제곱, 노출수준 비교는 연령 및 살포방법을 보정한 GLM을 이용하여 분석하였다.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2020년도 하계학술대회
• /
• pp.650-651
• /
• 2020

본 논문은 YOLO v4 알고리즘을 이용하여 산업 현장에서 근로자의 개인 보호장비를 검출하는 방법을 제시한다. 학습데이터 주석은 사람 영역, 안전모, 안전 조끼 혹은 벨트 영역을 검출하도록 처리하였으며, 학습데이터 2,198개, 검증데이터 275개를 학습하는 데 이용하였다. 실험 결과 학습 반복 수 10,000번을 기준으로 81.81%의 mAP가 나옴을 확인하였다. 추후 정확도 개선을 위해 학습데이터 구축 및 전·후처리 알고리즘 관련 연구를 수행할 예정이다.

• Safety and Health at Work
• /
• 제11권4호
• /
• pp.537-542
• /
• 2020

Background: Personal protective equipment (PPE) has been designed in such a way to reduce accident rates. Unfortunately, existing PPE is rather ineffective as it is not able to provide warning signals when hazard is around. The integration of intelligent systems is envisaged to increase the efficiency of existing PPE. Methods: This project designed a safety vest incorporated with metal detectors which can provide immediate warning to the field workers when there is metal hazard around. This product has greater freedom of design via smart manufacturing as it involves the assembly of few commercially available parts into a single entity. Briefly, the metal detector is a do it yourself (DIY) kit, and the safety vest is purchasable from any local market. The DIY kit was connected to a copper coil and being sewed into the safety vest. Results: The metal detector induces beeping sound when there is metal hazard around. A total of 121 engineering students were introduced to the prototype before being requested to answer a survey associated with the design. Respondents have rated >3.00/5.00 for the design simplicity, ease of usage, and light weight. Meanwhile, respondents suggested that the design should be further improved by increasing the metal detection range. Conclusion: It is envisaged that the introduction of this smart safety vest will allow the workers to carry out their duties securely by reducing the accident rates. Particularly, such design is expected to reduce workplace accident especially during night time at construction sites where the visibility is low.