Page History

To operate the The neural tracker , a camera must match operation imposes the following requirements:

1. To the video stream from the camera:
   1. The
   Minimum
   1. resolution is at least
   640х360 pixels.

2. Frame rate must be no less than 8 FPS. To detect fast moving objects (running individuals, vehicles), you must set frame rate at 18 FPS or above.

3. Objects must be visually separated from the background as well as from each other.
4. Camera is mounted in no less than 3 meters above the ground, or on the ceiling, or pointed strictly downwards (for counting visitors with a line crossing detection tool).
5. 1. 640x360 pixels. It is also not recommended to use a resolution higher than 1920×1080, since higher resolution does not increase the detection quality, but significantly increases the consumption of resources. The optimal resolution for solving typical tasks is 1280x720 (see Examples of configuring neural tracker for solving typical tasks).
   2. The frame rate per second in the video stream from the camera is at least 8 for solving typical tasks.
   3. Both colorless (gray) and color images.
6. To lighting:
   1. Lighting in the scene is at least 50 lux per square meter. In conditions of insufficient or excessive lighting (night or light-striking), stable operation of the video analytics is not guaranteed.
   2. There are no abrupt changes in lighting.
7. To the scene and camera angle:
   1. Moving objects are visually separable from each other.
   2. The background is mostly static and does not change abruptly.
   3. Moving objects are minimally obscured by static objects in the scene (columns, trees, etc.).
   4. The analyzed scene does not have reflective surfaces and sharp shadows from moving objects. If present, they should be masked.
   5. Camera shake does not result in image offsets greater than 1% of the frame size
   An object must occupy no less than 5% of the FoV width / height
   1. .