Versions Compared

Old Version 5

changes.mady.by.user Gleb Matskevich

Saved on

compared with

New Version Current

changes.mady.by.user Alena Kniazeva

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.
Tip

Image requirements for the Human pose detector and its sub-detectors

Hardware requirements for neural analytics operation

Requirements for the operation of the Pose Detection Human pose detector and its sub-tools detectors are given in the table:

Camera
  • Resolution must be 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
  • The frame rate per second in the video stream from the camera is at least 8
  • Color image only
Note
titleAttention!
  • Correct
operation of the Pose Detection tools isn't guaranteed when using
  • operation of the detector isn't guaranteed if you use frames that were masked before they got into Axxon One by an IP camera or similar methods.
  • Correct operation of the Human pose detector sub-detectors isn't guaranteed if you use fisheye cameras and other cameras with strong image distortion.
  • The camera tilt angle from top to bottom on a person must not exceed 30°. Otherwise, the
detection tool
  • detector won't operate correctly.
    The following diagrams show the examples of:
    • The acceptable tilt angle:
      Image Modified
    • The unacceptable tilt angle:
      Image Modified


Lighting
  • 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 analytics isn't guaranteed
  • 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 doesn't have reflective surfaces and sharp shadows from moving objects. If present, they must be masked
  • Camera shake doesn't result in image offsets greater than 1% of the frame size
Object images
  • The detected object must be clearly distinguishable by the human eye
  • The detected object must be completely within the frame
  • The image isn't noisy and not distorted by the artifacts of compression algorithm
  • The duration of the object visibility is at least two frames
    • For the correct operation of the Sitting person detector and Person down detector sub-detectors, the area of interest must be covered from at least two perpendicular angles (a and b are the directional beams from the cameras and the point of their intersection is the area of interest):
      Image Added
      The algorithms have a limitation and can work incorrectly if:
      • a person falls down or sits down with their head or face towards the camera,
      • a person falls down with their feet towards the camera (for the Person down detector sub-detector)
    The minimum value of pixel density per meter is observed:
    Image resolutionObject typeMinimum pixel density per meter (ratio of the object width in pixels to the object width in meters)Minimum object size in pixels, width x heightFor Pose Detection sub-tools1920x1080Human170~102x3091280x720Human128~77x233640x360Human80~48x145For common sub-tools1920x1080Human100~45x1871280x720Human68~31x134640x360Human35~15x65