Requirements for the operation of the Queue detector are given in the tableThe following table contains the requirements for the cameras used by the queue detection tool:
720 х 576 360 х 288 - 360х288 (CIF1) is also allowed
|
to use- . Increasing the resolution above CIF4
|
does not operating quality - performance of the recognition algorithm
|
.Frames per second: 6 or more. color or greyscale.- analytics works with both gray and color images
- No camera
|
jitter is allowed.Illumination | Best recognition results are |
Lighting | - The best performance of the detection tool is achieved under moderate
|
illumination. If the scene is under- or over-illuminated, the recognition accuracy may drop down.- lighting. In conditions of insufficient (night) or excessive (light-striking) lighting, the algorithm performance can decrease
- Abrupt changes in lighting can lead to short-term incorrect operation of analytics
|
Sharp changes in illumination may lead to improper operation of analytics.Vertically downward of is the best for the purpose. The closer to vertical- looking down at the scene. The better this requirement is met, the more accurate the
|
estimation.Camera FOV dimensions- estimate is
- Dimensions of the camera FOV: minimum 3x3 m (6x6
|
humans- people), optimal 4x4 m (8x8
|
humans- people), maximum 8x8 m (16x16
|
humans. should be primarily static and should not undergo sudden changes.- is mostly static and doesn’t change abruptly
- Analytics can work incorrectly on reflective surfaces, and if there are sharp
|
Reflective surfaces and harsh - shadows from moving objects
|
can affect the quality of analytics. may not correctly - incorrectly if there are periodic movements of
|
the - background objects in the camera FOV (
|
leafage screens, etc.).Images of objects | Image quality: the image should be clear, with no visible compression artifacts.Dimensions of a human in scene: bounding rectangle has to occupy from 0,25% to 10% of the frame area.
