The requirements for cameras that will when you work with the the Neurocounter module are shown given in the following table.
Video stream from camera | - The resolution is at least 640x360 pixels. It is also not recommended to use We also don't recommend using a resolution higher than 1920×1080, since higher resolution does not doesn't increase the detection quality , but significantly increases the consumption of resources. The optimal resolution for solving typical tasks is 1280x720 (seeExample of configuring Neurocounter neurocounter for solving typical tasktasks).
- The frame rate per second in the video stream from the a camera is must be at least 8 eight for solving typical tasktasks.
- Both colorless Colorless (gray) and color images
|
| Lighting | - Lighting in the scene is at least 50 lux per square meter. In conditions of insufficient or excessive lighting (night or light-striking), the stable operation of the video analytics is not 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 does not doesn't change abruptly.
- Moving objects are minimally obscured by static objects in the scene (columns, trees, and so on).
- The analyzed scene does must not have reflective surfaces and sharp shadows from moving objects. If present, they should must be masked.
- Camera shake does must not result in image offsets greater than 1% of the frame size
|
Object images | Objects Detected object image requirements for Neurocounterneurocounter |
| Note |
|---|
|
Correct We don't guarantee the correct operation of the neurocounter is not guaranteed if you use a the fisheye lens. Correct We don't guarantee the correct operation of the neurocounter isn't guaranteed if you use a the video stream or frames that were masked before they got into into Axxon PSIM by an the IP camera or similar means and methods. |
