Documentation for Axxon One 1.0.

Previous page Setting up common parameters for pose detection tools  Video stream and scene requirements for pose detection tool Next page

To ensure the correct recognition of a person's posture, the following image requirements should be met:

  1. The object to be detected is clearly distinguishable by the human eye.
  2. The detected object is completely within the frame.
  3. The image is not noisy and not distorted by compression algorithm artifacts.
  4. The duration of the object's visibility is at least 2 frames.

  5. The minimum value of pixel density per meter is observed:

    Image resolution

    		Object type

    Minimum pixel density per meter (ratio of the object width in pixels to the object width in meters)

    		Minimum object size in pixels, width x height
    For pose detection tools
    1920x1080Human170~102x309
    1280x720Human128~77x233
    640x360Human80~48x145
    For classical sub-detectors* pose detection tools
    1920x1080Human100~45x187
    1280x720Human68~31x134
    640x360Human35~15x65

Video stream and scene requirements for pose detection tool

* see information about classical sub-detectors here: Functions of Scene Analytics

  • No labels