Personal Protective Equipment (PPE) Detection
This model analyzes construction site imagery to automatically detect and identify personal protective equipment (PPE) being used.
40 credits (with a subscription)
80 credits (without a subscription)
Version 1.2
Free Trial available!
Powerful Computer Vision
This machine learning model uses object detection to detect and classify personal protective equipment (PPE) from construction site images.
Use Case
Ideal for integration with a construction site camera for advanced analytics, this model produces results that can help optimize safety training and respond to safety audits.
Fast Analysis
The model is currently trained to detect people along with the following types of PPE:
- Anchorage Point
- Boots
- Fall Limiter
- Full Body Harness
- Head Gear (Type 1 and Type 2)
- Gloves
- Safety Vests (Class 2 and Class 3)
- Self-Retracting Lifelines
Required Inputs
- PNG, JPG, or JPEG files
Note: Oblique to level camera angles are required.
Expected Outputs
- Annotated images
- A summary report in XLSX format
Identifying unsafe behavior among construction workers is critical for enhancing site safety. This model provides key insights to owners, contractors, and construction site managers, allowing them to prioritize safety and conduct regular job site safety training.
Note: Current mAP (Mean Average Precision) score is 52.3%. Results will continue to be refined as the model is trained on more data.