Documentation for DetectorPack PSIM 2.0.

Previous page Next page

The requirements for cameras when you work with the Neurocounter module are given in the following table.

Video stream from camera

  • The resolution is at least 640x360 pixels. We also don't recommend using a resolution higher than 1920×1080, since higher resolution doesn't increase the detection quality but significantly increases the consumption of resources. The optimal resolution for solving typical tasks is 1280x720 (see Example of configuring neurocounter for solving typical tasks).
  • The frame rate per second in the video stream from a camera must be at least eight for solving typical tasks.
  • Colorless (gray) and color images
Lighting
  • Lighting in the scene is at least 50 lux. In conditions of insufficient or excessive lighting (night or light-striking), the 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.
  • Moving objects are minimally obscured by static objects in the scene (columns, trees, and so on).
  • The analyzed scene must not have reflective surfaces and sharp shadows from moving objects. If present, they must be masked.
  • Camera shake must not result in image offsets greater than 1% of the frame size

Object images

Detected object image requirements for neurocounter

Attention!

We don't guarantee the correct operation of the neurocounter if you use the fisheye lens.

We don't guarantee the correct operation of the neurocounter if you use the video stream or frames that were masked before they got into Axxon PSIM by the IP camera or similar means and methods.

Requirements for hardware platform for neural analytics operation


  • No labels