2026· International Journal of Innovative Research in Engineering & Management· Vol 13, pp. 11-16· 0 citations
TL;DR
Results indicate the vision model achieves 92% PPE detection accuracy and practical implications highlight the need for robust encryption user training and continuous model retraining, and future research should examine long-term behavioral impacts and cross-plant scalability.
Abstract
This study investigates the deployment of AI-powered computer vision systems for automated safety compliance monitoring and personal protective equipment (PPE) detection in automobile manufacturing. Four objectives guide the research evaluating detection accuracy measuring incident reporting speed improvements assessing worker acceptance and identifying data security challenges. A mixed-method approach combined with system performance logs with responses from a 100-person survey. Hypothesis tests include one-sample t-tests for accuracy benchmarks paired t-tests for reporting times one-sample t-tests for acceptance scores and chi-square tests for security challenge reports. Results indicate the vision model achieves 92% PPE detection accuracy (t(99)=6.5p<0.001) reduces reporting time by an average of 3.2 minutes (t(99)=7.8p<0.001) yields high acceptance (mean=4.1 t(99)=8.2p<0.001) but reveals moderate security concerns (χ²(1)=12.4p<0.001). Practical implications highlight the need for robust encryption user training and continuous model retraining. Future research should examine long-term behavioral impacts and cross-plant scalability.
Suggestions for ensuring safe person detection using AI in industrial environments are offered, including suggestions for ensuring safe person detection using AI in industrial environments.
Iwo Kurzidem, Andrea Matic-Flierl, Poulami Sinhamahapatra et al.· 0 citations
This study quantitatively evaluates the performance of a YOLO-based computer vision system
for real-time hazard detection across construction, manufacturing, and healthcare environments
in New York State. The analysis compares YOLO-based detection with traditional manual
inspection using key performance metrics, including mean average precision (mAP), recall,
precision, time-to-detection, and personal protective equipment (PPE) compliance rates. Results
indicate that YOLO-based systems significantly outperform manual inspection across all metrics,
demonstrating higher detection accuracy, faster response times, and improved compliance
monitoring. The findings provide empirical evidence supporting the effectiveness of artificial
intelligence–enabled safety systems in enhancing hazard detection performance and advancing
proactive safety management practices.
Dr. Robb Shawe· International journal of adv...· 0 citations
This paper presents an artificial intelligence (AI)-powered automated access control system that aims to reduce delays and improve safety. The primary problem addressed is effective monitoring of compliance with personal protective equipment (PPE) and secure access control for personnel entering sites. This study represents the design and development of an access control system that includes accurate detection of essential PPE items (e.g., safety helmets, gloves, goggles, and gas detectors), integration of facial recognition for identity verification, real-time monitoring of video feeds, and an intuitive user interface for security personnel to manage access and compliance efficiently. The software part uses you only look once (YOLO) version 8 for real-time object detection, classification, and drawing the bounding boxes around the detected object in a single forward pass. The hardware platform consists of NVIDIA Jetson AGX Orin 64 GB as an edge computing device. The developed AI-based embedded system is tested and validated with real-world scenarios and achieved a mean average precision (mAP) of 98.4% for PPE detection and 99.38% accuracy for face recognition.
Mariam Mesfer, Aoosh Matar, Reem Saif et al.· IAES International Journal o...· 0 citations
This survey categorizes AI-based vision systems by their functional objectives rather than algorithmic classification, and organizes prior work by functional roles and practical deployment considerations, rather than algorithm-centric evaluations, to provide practitioners with actionable insights for industrial adoption.
Minjung Kim, Hwan-Sik Yoon· AI for Engineering· 0 citations
Restricted-area security requires detection systems that can identify human intrusion rapidly and accurately while reducing false alarms caused by non-human objects. Conventional single-sensor security systems may be limited in distinguishing humans from inanimate objects crossing a monitored boundary, particularly when the system relies only on perimeter interruption or motion detection. This study aims to design and evaluate an ESP32-based area violation detection system that integrates a Beam Sensor, Passive Infrared (PIR) sensor, and HC-SR04 ultrasonic sensor using a Finite State Machine (FSM) decision model. The Beam Sensor functions as the initial perimeter trigger, the PIR sensor verifies human presence based on body infrared radiation, and the ultrasonic sensor provides supporting distance information for spatial monitoring. Sensor readings are processed through sequential FSM states to determine whether an alarm condition should be activated. The prototype was tested in 30 trials involving human and inanimate objects at distances ranging from 1 m to 5 m. The experimental results show that the proposed system achieved an accuracy of 83.33%, precision of 85.71%, recall of 80.00%, and F1-score of approximately 82.76%. The HC-SR04 ultrasonic sensor also produced an average measurement error of 1.68% within the tested range of 50–300 cm. These findings indicate that the integration of multi-sensor inputs with FSM-based validation provides a structured and selective approach for area violation detection. Although the system is designed to address limitations commonly found in single-sensor configurations, further comparative testing against beam-only, PIR-only, and ultrasonic-only systems is required to empirically confirm its relative performance advantage.
Muhammad Aji Ramadhan, A. Handayani, Suroso Suroso· bit-Tech· 0 citations
The application of computer vision technology in automation systems plays a crucial role in improving the efficiency of occupational safety monitoring in industrial environments. This study developed a YOLOv8-based visual detection application in ONNX format to identify safety helmet violations in real-time. The system was developed using Python with a Tkinter-based user interface and integrated with a Flask web dashboard that displays violation log data. The application can accept video input from various sources, including webcams, USB cameras, and IP cameras, to classify the type of helmet being used. Only orange and white safety helmets are considered valid. Detecting a new helmet, a motorcycle helmet, or a helmet with an inappropriate colour will trigger an alarm and store the image as evidence of the violation. The YOLOv8 model was trained on a six-class dataset and demonstrated good performance, with a precision of 0.921, a recall of 0.859, an mAP50 value of 0.919, and an mAP50-95 value of 0.619. System evaluation demonstrated the application's stability and accuracy in computer vision-based automated surveillance.
S. Syufrijal, Heri Firmansyah, Christophorus Mrc Yuda et al.· EPJ Web of Conferences· 0 citations