FactoryVision AI PPE detection: YOLO11n object detection for safety equipment

Educational prototype | Object detection for factory and construction imagery | Human review required

Model overview

Model	Task	Framework	Weights
FactoryVision AI PPE YOLO11n	Object detection	Ultralytics YOLO11n	`model.pt`

Held-out test results

Metric	Reported result
Precision (bounding boxes)	0.8400
Recall (bounding boxes)	0.6398
mAP@50	0.7053
mAP@50:95	0.3927

These values are reported in ppe_test_metrics.json, not independently reproduced. The reported test split has 82 images; a class-specific breakdown is not included in this package. Do not confuse the separate pretrained YOLO COCO person baseline with this PPE result.

Purpose and safety

Educational object detection for people and PPE-related objects in factory and construction images. This is not a certified industrial safety system. Detected PPE status is only a suggested alert requiring human review; it cannot establish a worker's actual PPE compliance or substitute for a trained safety inspector. Missed detections mean unsafe situations may go unflagged.

Safety limitation: Object detections alone do not perform the project's person-to-helmet association. The original application implements an additional alert logic layer; consult its source and use human review.

Model details

Fine-tuned Ultralytics YOLO11n; original starting checkpoint yolo11n.pt
Packaged weights: model.pt (archive path checkpoints/ppe_yolo.pt)
10 classes: see labels.json
Training configuration: 30 epochs, 640px image size, batch size 16; the training script uses a held-out PPE test split

Training data

Construction Site Safety Image Dataset, attributed to Snehil Sanyal / Roboflow Universe and referenced by the source project: Kaggle dataset. The source project lists CC BY 4.0 for this dataset; verify provenance and attribution requirements before public release. Dataset images are not included in this model package.

Example inference

from ultralytics import YOLO
model = YOLO('model.pt')
results = model.predict('your_image.jpg', conf=0.25)
for result in results:
    print(result.boxes)

Licensing and redistribution

Ultralytics YOLO11 and its fine-tuned checkpoints have AGPL-3.0 obligations by default, or require a suitable enterprise licence for uses incompatible with AGPL-3.0. See Ultralytics licensing.
The source repository's MIT licence does not automatically license this trained checkpoint, pretrained weights, or source datasets.
The original developer has reportedly authorised publication; the publisher must still confirm the specific publication terms and applicable third-party rights.
Do not assign an MIT/Apache model licence or switch to public visibility until licensing has been checked and recorded.

Known limitations

Domain shift, lighting, small objects, occlusion, crowded scenes, cameras and inference thresholds may reduce performance. False negatives are especially concerning for PPE alerting.

Credits and attribution

Role	Contributor
Original Developer & Model Author	Theivanth Rajamohan
Technical Reviewer, Code Contributor & Publication Support	Swapin Vidya
Project Contributor	Rajah Shanmugasundaram
Publishing Organisation	TechSphere Consultancy Services Private Limited

Project provenance: FactoryVision AI was originally developed by Theivanth Rajamohan. Swapin Vidya contributed technical review, detection-metrics improvements, testing, model publication preparation and documentation. The models are being prepared for publication under TechSphere Consultancy Services Private Limited's Hugging Face namespace, with the original developer's permission.

Downloads last month: 59