The following table contains the requirements for cameras used by the queue Queue detection tool:
Resolution- resolution: 360 х 288 (CIF1) to 720 х 576 (CIF4) pixels; lager images are scaled down to CIF4
|
.Frames - frames per second: 6 or more;
|
Color- color: color or greyscale
|
.No - no camera jitter is allowed.
|
Illumination: |
Best - best recognition results are achieved under moderate illumination. If the scene is under- or over-illuminated, the recognition accuracy may drop down
|
.Sharp - sharp changes in illumination may lead to improper operation of analytics.
|
Scene and viewing angle: |
Vertically - vertically downward position is the best for the purpose.
|
- The closer to vertical, the more accurate counting
|
.Camera - camera FOV dimensions: min. 3 x 3m (6 x 6 humans), optimal 4 x 4m (8 x 8x humans), max. 8 x 8m (16 x 16 humans)
|
.The - the background must be primarily static and not undergo sudden changes
|
.Reflective - reflective surfaces and harsh shadows from moving objects can affect the quality of analytics
|
.Leafage- leafage, TV screens or any periodic object movement in the background may cause analytics glitches.
|
Images of objects within the scene: |
Image - image quality: the image must be clear and sharp with no visible compression artifacts
|
.Dimensions - dimensions of a human in scene: bounding rectangle has to occupy 0.25 to 10 percent of the frame area.
|
