The requirements for cameras when you work with theVisionLabs equipment detectormodule are given in the following table.
Camera
The resolution is at least 640x360 pixels. We also don't recommend using a resolution higher than 1920×1080 since a higher resolution doesn't increase the detection quality but significantly increases the consumption of resources. The optimal resolution for solving typical tasks is 1920х1080.
The frame rate per second in the video stream from a camera is at least 13 for solving typical tasks.
Detector-based analytics works only with color images
We don't guarantee the correct operation of the detector when you use a fish-eye lens.
Lighting
Lighting in the scene is at least 200 lux. The detector is applicable in conditions of artificiallight.In conditions of insufficient or excessive lighting (night or light-striking), stable analytics operation isn't guaranteed.
There are no abrupt changes in lighting
Scene and camera angle
Moving objects are visually separable from each other.
The background is mostly static and doesn't change abruptly.
There are no products made of rods in the detection area.
Moving objects are minimally obscured by static objects in the scene (columns, manufactured goods, and so on).
Avoid large obstacles in the camera's FOV (columns, tower cranes, stacked materials, etc.). They obscure detected objects and cause track breaks. If obstacles cannot be avoided, we don't recommend centering them in the frame.
The analyzed scene must not have reflective surfaces. If present, they must be masked.
The analyzed scene must not have strong camera glare (spotlights, active welding zones).
Camera shake must not result in image offsets greater than 1% of the frame size.
Camera angle is without strong camera tilt.
To improve video quality, the camera lens must be kept clean. We don't recommend placing cameras above unloading areas or near ventilation shafts
Object images
The detected object (PPE) must be clearly distinguishable by the human eye.
The image is in color, isn't noisy, and isn't distorted by artifacts of the compression algorithm.
The dimensions of the equipment must not exceed 65% of the frame size.
The duration of the object's visibility is at least 10-13 frames. The minimum number of frames depends on the task.
There must be no visible physical barriers between the camera lens and the analyzed object.
A person and/or PPE can be obscured by an obstacle and/or another person or cropped by frame boundaries by at least 25%.
The minimum height of equipment on body parts in pixels is observed:
Vest is at least 50 pixels
Helmet/Hood is at least 20 pixels
PPE must be of a standard design and shape and come in the following colors:
Vest: light green (green), yellow, orange
Helmet/Hood: white, yellow, orange, red, blue, green
The minimum value of pixel density per meter is observed:
Image resolution
Minimum pixel density per meter (ratio of object height in pixels to object height in meters)