Related Experiment Videos
A Vision-Based Sensing Framework for PPE Detection and Safety Harness Compliance Recognition in High-Formwork
Gang Yao1,2, Lang Liu1,2, Yang Yang1,2
1School of Civil Engineering, Chongqing University, Chongqing 400045, China.
Sensors (Basel, Switzerland)
|July 15, 2026
Summary
This study introduces YOLO-ILB, a vision system for construction site safety, accurately detecting personal protective equipment (PPE) compliance and harness anchoring. It overcomes challenges like occlusions and scale variation for improved worker safety.
Area of Science:
- Computer Vision
- Construction Safety Engineering
Background:
- Construction sites present unique challenges for automated safety monitoring, including extreme scale variations, occlusions from scaffolding, and small safety hook targets.
- Existing systems lack the ability to assess the regulatory compliance of safety harness anchoring, focusing only on presence detection.
Purpose of the Study:
- To develop an automated vision-based sensing system, YOLO-ILB, for detecting personal protective equipment (PPE) compliance and assessing safety harness anchoring in high-formwork support system (HFSS) environments.
- To improve upon existing object detection models for enhanced accuracy and efficiency in complex construction settings.
Main Methods:
- Proposed YOLO-ILB, a lightweight object detector based on YOLO11n, featuring C3k2_IDWC modules for multi-scale feature discrimination, SPPF_LSKA modules for global context awareness, and a BiFPN neck for cross-scale feature fusion.
- Constructed a novel UAV-based sensing dataset with 2700 annotated images from 17 construction sites, capturing varied conditions.
- Developed a geometry-based algorithm to classify harness anchoring states.
Main Results:
- YOLO-ILB achieved a mean Average Precision (mAP50) of 0.939 with 1.923 M parameters and 5.7 G FLOPs, running at 262.3 FPS, outperforming eight YOLO baselines.
- The geometry-based compliance algorithm attained 90.82% accuracy in classifying three distinct harness anchoring states (correct, incorrect, unclipped).
- The system demonstrated deployability on resource-constrained edge computing nodes.
Conclusions:
- YOLO-ILB effectively addresses the challenges of PPE compliance detection in HFSS environments, offering high accuracy and efficiency.
- The integrated geometry-based algorithm successfully extends the system's capability from simple presence detection to regulatory compliance assessment.
- This research provides a robust, deployable solution for enhancing construction worker safety and regulatory adherence through advanced computer vision techniques.
Related Concept Videos
01:24Vision
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
01:20Personal Protective Equipment
Personal protective equipment (PPE) is unique clothing or equipment worn by an employee to minimize or prevent exposure to infectious agents. PPE creates a barrier between the employee and the infectious materials. PPE must be readily available in the patient care area. PPE includes gloves, gowns and aprons, masks and respirators, goggles, face shields, shoes, and headcovers:
02:16Light Acquisition
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.