Versions Compared

Old Version 3

changes.mady.by.user Alena Kniazeva

Saved on

compared with

New Version Current

changes.mady.by.user Bahdan Tsiulkou

Saved on

Key

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

Image requirements for the Neural tracker and its sub-detectors

Hardware requirements for neural analytics operation

Requirements for the operation of Neurotracker the Neural tracker and its sub-tools detectors are given in the table:

Camera
Resolution must be at least 640x360 pixels
  • The optimal resolution for solving typical tasks is 1280x720. We
also
  • don't recommend using a resolution higher than 1920×1080, since a higher resolution doesn't increase the detection quality
,
  • but significantly increases the consumption of resources. The
optimal resolution for solving typical tasks is 1280x720
  • minimum resolutions for each neural network are listed in the table:
    Name of the neural networkNeural network (Detector Pack 3.16)Neural network (Detector Pack 3.15)Minimum resolution
    VehicleGeneralNMCar_v1.0_onnxGeneralNMCar_v1.0CPU_IR10_FP16300x300
    GeneralNMCar_v1.0GPU_onnx
    PersonGeneralNMHuman_v1.0_onnxGeneralNMHuman_v1.0_IR10_FP16
    GeneralNMHuman_v1.0GPU_onnx
    Person (top-down view)GeneralNMHumanTopView_Nano_v1.0_onnxGeneralNMHumanTopView_v0.8CPU_IR10_FP16
    GeneralNMHumanTopView_v0.8GPU_onnx
    Person (top-down view Nano)
    		GeneralNMHumanTopView_Nano_v1.0_onnxGeneralNMHumanTopView_Nano_v1.0_CPU_IR10_FP16576x320
    GeneralNMHumanTopView_Nano_v1.0_GPU_onnx
    Person (top-down view Medium)GeneralNMHumanTopView_Medium_v1.0_onnxGeneralNMHumanTopView_Medium_v1.0_CPU_IR10_FP16
    GeneralNMHumanTopView_Medium_v1.0_GPU_onnx
    Person (top-down view Large)
    		GeneralNMHumanTopView_Large_v1.0_onnxGeneralNMHumanTopView_Large_v1.0_CPU_IR10_FP16
    GeneralNMHumanTopView_Large_v1.0_GPU_onnx
    Person and vehicle (Nano)GeneralNMHumanAndVehicle_Nano_v1.0_onnxGeneralNMHumanAndVehicle_Nano_v1.0_CPU_IR10_FP161152x640
    GeneralNMHumanAndVehicle_Nano_v1.0_GPU_onnx
    Person and vehicle (Medium)GeneralNMHumanAndVehicle_Medium_v1.0_onnxGeneralNMHumanAndVehicle_Medium_v1.0_CPU_IR10_FP16
    GeneralNMHumanAndVehicle_Medium_v1.0_GPU_onnx
    Person and vehicle (Large)GeneralNMHumanAndVehicle_Large_v1.0_onnxGeneralNMHumanAndVehicle_Large_v1.0_CPU_IR10_FP16
    GeneralNMHumanAndVehicle_Large_v1.0_GPU_onnx

  • The frame rate per second in the video stream from the camera is at least 8 for solving typical tasks
Neurotracker
  • Neural tracker-based analytics works with both colorless (gray) and color images. When you use a
neurofilter
  • neural filter, we recommend using color cameras. When you use black-and-white cameras, the recognition quality can be noticeably worse
Note
titleAttention!
  • Correct 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 Neurotracker
  • of the Neural tracker isn't guaranteed
when using
  • if you use a fisheye camera.
Lighting
  • Lighting in the scene is at least 50 lux. 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 sizeObject images
  • The detected object must be clearly distinguishable by the human eye
    • Width and height of objects in the image must not exceed 75%
    • of the frame size
  • When you use a neurofilter, the minimum width or height of an object must be at least 5% of the width/height of 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 six frames
  • Between two frames, an object must move in the direction of a distance not exceeding its size. This condition is necessary for the correct calculation of object track
    • 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 heightRatio of the object width to the frame width as a percentage1920x1080Human55~25x105~3%1280x720Human35~17x70~3%640x360Human17~10x42~3%1920x1080Light vehicle (2 axles)55~354x300~20%1280x720Light vehicle (2 axles)35~240x205~20%640x360Light vehicle (2 axles)17~132x112~20%