yolo26s-construction-ppe
construction site personal protective equipment detector
2 min read
This model is designed to automatically detect people, safety helmets, high-visibility vests, and safety violations (such as missing helmets or vests) in construction site photos. It is built on the YOLO architecture (a popular real-time computer vision library) and is available in PyTorch and ONNX formats with various optimization levels (FP32, FP16, INT8). This development will be useful for occupational health and safety engineers, video monitoring system developers, and automation specialists for construction site monitoring.
Key features
- Accurately detects helmets, vests, and people in images.
- Supports fast ONNX FP16 inference with response times down to 6.3 ms on an NVIDIA Tesla T4 GPU.
- An INT8 quantized version weighing only 11 MB is available for running on CPUs and edge devices.
- Rigorous dataset verification was performed to prevent data leakage between training and test splits.
What you can do
- Integrate the model into a construction site video surveillance system to automatically detect workers without helmets.
- Set up a photo analysis script for safety inspectors' mobile devices.
- Run the optimized ONNX version on resource-constrained edge boxes with limited CPU resources.
Example
from ultralytics import YOLO
model = YOLO("best-int8.onnx")
for r in model.predict("site.jpg", conf=0.35):
for xyxy, cls, conf in zip(r.boxes.xyxy.tolist(), r.boxes.cls.tolist(), r.boxes.conf.tolist()):
print(r.names[int(cls)], round(conf, 2), [round(v) for v in xyxy])
Read more
DetailsMetrics on the test split (119 images): overall mAP50 is 0.900, mAP50-95 is 0.509.
Hardware requirements: GPU execution is supported (FP16 recommended) along with CPU via ONNX Runtime.
Limitations: rare classes like no-helmet have few examples in the test set, requiring validation on live security cameras.
License: weights inherit from Ultralytics YOLO and require compliance with AGPL-3.0 for commercial use.










Comments