AI Precision Manual

For the system to reliably detect objects, camera optics and installation are critical. These general rules should be followed to optimise the field of view and the accuracy of the AI engine:

• • Mounting Height:

• A standard height of 3 metres above ground level is recommended to balance viewing angle and coverage.

• • Tilt Angle:

• The angle between the lens and the horizontal should be between 0° and 45°. Exceeding this angle increases "blind spots" and distorts workers' silhouettes, reducing the effectiveness of the pose model.

• • Occlusions and Line of Sight:

• The system requires a clear, direct line of sight to the target.

  • · Occlusions (objects blocking the view, such as columns, heavy machinery or shelving) can prevent the AI from detecting a person or their protective equipment.

  • · If a worker is partially hidden, the model's confidence drops; cameras should therefore be positioned to minimise physical obstructions in the highest-risk areas.

• • Environmental Conditions:

• The scene background should not be excessively complex or have constantly moving elements that are not the detection target. Adequate lighting and high contrast between PPE (such as high-visibility vests) and the background will dramatically improve the confidence rate.

Given the variety of supported manufacturers, we recommend and use camera simulators integrated with the installation floor plans. This pre-production phase allows you to:

• • Verify Pixel Density:

• Confirm whether the required thresholds are met (e.g. 125 px/m for recognition) in critical zones.

• • Optimise Field of View (FoV):

• Avoid blind spots by virtually positioning cameras on the floor plan.

• • Optics Selection:

• Confirm whether the chosen camera and lens model is suitable for the required detection distance before physical installation.

Detecting personal protective equipment (helmets, vests, gloves) requires a specific information density for the YOLO engine to distinguish elements with high confidence. Below are example pixel densities by equipment type:

• • Helmets:

• Require a size of between 30–50 pixels.

• • Reflective Vests:

• Being more visible, they are detected with high accuracy from 50–100 pixels. High-visibility colours (fluorescent yellow/orange) dramatically improve the model's detection rate.

• • Gloves and Goggles:

• Due to their small size, the system requires between 20–30 pixels. Using longer focal length (zoom) optics is recommended for these applications. Uniform lighting that avoids harsh shadows on the equipment is essential.

For technical questions about hardware compatibility or custom quotes, contact us at:

• • Technical Support: support@safe.ai

• • Sales: commercial@safe.ai