Versions Compared

Old Version 32

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.
Section
Column
width50%
Panel
borderColor#CCCCCC
bgColor#FFFFFF
titleBGColor#F0F0F0
borderStylesolid
titleOn the page:

Table of Contents

Column


Tip

Video stream and scene requirements for the Neurotracker Neural tracker and its sub-toolsdetectors

Image requirements for the Neurotracker Neural tracker and its sub-toolsdetectors

Hardware requirements for neural analytics operation

Data collection requirements for neural network training

Optimizing the operation of neural analytics on GPU in Windows OS

Optimizing the operation of neural analytics on GPU in Linux OS

Configuring the

...

detector

To configure Neurotrackerconfigure the Neural tracker, do the following:

  1. Go to
    2. the Detection Tools tab
  2. the Detectors tab.

  3. Below the required camera,

    4. click 

  4. click Create… → Category: Trackers →

    5. Neurotracker

  5. Neural tracker.

By default, the detection tool detector is enabled and set to detect moving people.

If necessary, you can change the detection tool detector parameters. The list of parameters is given in the table:

ParameterValueDescription
Object features
Record objects trackingYes

By default, metadata are recorded into the database. To disable metadata recording, select the No value

Note
titleAttention!

To obtain metadata, video is decompressed and analyzed, which places a heavy load on the server and limits the number of cameras used on it.

No
Video streamMain streamIf the camera supports multistreaming,
 select
 select the stream for which detection is needed
Other
EnableYesBy default, the
detection tool
detector is enabled. To disable, select the No
 value
 value
No
Name
Neurotracker
Neural trackerEnter the
detection tool
detector name or leave the default name
Decoder modeAutoSelect a processing resource for decoding video streams. When you select a GPU, a stand-alone graphics card takes priority (when decoding with Nvidia NVDEC chips). If there is no appropriate GPU, the decoding will use the Intel Quick Sync Video technology. Otherwise, CPU resources
will be
are used for decoding


CPU
GPU
HuaweiNPU
Neurofilter modeCPUSelect a processing resource for neural network operation (see Hardware requirements for neural analytics operation, Selecting Nvidia GPU when configuring detection tools)
Number of frames processed per second6

Specify the number of frames for the neural network to process per second. The higher the value, the more accurate the tracking, but the load on the CPU is also higher. The value must be in the range [0.016, 100]

Note
titleAttention!

We recommend

using the GPU. It may take several minutes to launch the algorithm on Nvidia GPU after you apply the settings. You can use caching to speed up future launches (see Optimizing the operation of neural analytics on GPU in Windows OS).
  • Starting with Detector Pack 3.11, Intel HDDL and Intel NCS aren’t supported.
  • Starting with Detector Pack 3.12, the parameter is removed from the detection tool settings, and Neurofilter runs on the same processor as Neurotracker. If before Detector Pack update, you select a different processor in the Neurofilter mode parameter, after the update, the detection tool works without Neurofilter.

    • the value of at least 6 FPS. For fast-moving objects (running individuals, vehicles), you must set the frame rate at 12 FPS or above.

    TypeNeural trackerName of the detector type (non-editable field)
    Advanced settings
    Camera position
         		Wall To sort out false events from the detector when using a fisheye camera, select the correct device location. For other devices, this parameter is irrelevant
    Ceiling
    Hide moving objects
         		Yes

    By default, the parameter is disabled. If you don't need to detect moving objects, select the Yes value. An object is considered static if it doesn't change its position more than 10% of its width or height during its track lifetime

    Note
    titleAttention!

    If a static object starts moving, the detector creates a track, and the object is no longer considered static.

    No
    Hide static objects
         		Yes

    Starting with Detector Pack 3.14, the parameter is disabled by default. If you need to hide static objects, select the Yes value.

    This parameter lowers the number of false events from the detector when detecting moving objects. An object is considered static if it hasn't moved more than 10% of its width or height during the whole time of its track existence

    Note
    titleAttention!
    • If a static object starts moving, the detector creates a track, and the object is no longer considered static.
    • Disabling the parameter reduces the load on the CPU.
    No
    Minimum number of detection triggers6Specify the Minimum number of detection triggers for the Neural tracker to display the object's track. The higher the value, the longer the time interval between the detection of an object and the display of its track on the screen. Low values of this parameter can lead to false events from the detector. The value must be in the range [2, 100]
    Model quantization

    		Yes

    By default, the parameter is disabled. The parameter is applicable only to standard neural networks for Nvidia GPUs. It allows you to reduce the consumption of computation power. The neural network is selected automatically, depending on the value selected in the Detection neural network parameter. To quantize the model, select the Yes value

    Note
    titleAttention!

    AxxonSoft conducted a study in which a neural network model was trained to identify the characteristics of the detected object with quantization. The following results of the study were obtained: model quantization can lead to both an increase in the percentage of recognition and a decrease. This is due to the generalization of the mathematical model. The difference in detection ranges within ±1.5%, and the difference in object identification ranges within ±2%.

    • The first launch of a detector with the Model quantization parameter enabled can take longer than a standard launch.
    • If GPU caching is used, next time the detector with quantization runs without delay.


    No
    Neural network file 

    If you use a custom neural network, select the corresponding file. 

    Note
    titleAttention!
    • To train your neural network, contact AxxonSoft (see Data collection requirements for neural network training).
    • A trained neural network for a particular scene allows you to detect only objects of a certain type (for example, a person, a cyclist, a motorcyclist, and so on).
    • If you don't specify the neural network file, the default file is used that is selected automatically, depending on the selected value in the Detection neural network parameter and the selected processor for the neural network operation in the Decoder mode parameter. If you use a custom neural network, enter a path to the file. The selected detection neural network is ignored when you use a custom neural network.
    • You cannot specify the network file in Windows OS. You must place the neural network file locally, that is, on the same server where you install Axxon One.
    • For correct neural network operation on Linux OS, place the corresponding file locally in the /opt/AxxonSoft/DetectorPack/NeuroSDK directory or in the network folder with the corresponding access rights.
    Scanning mode

    		YesBy default, the parameter is disabled. To enable the scanning mode, select the Yes value (see Configuring the scanning mode)
    No
    Scanning window height0The height and width of the scanning window are determined according to the actual size of the frame and the required number of windows. For example, the real frame size is 1920×1080 pixels. To divide the frame into four equal windows, set the width of the scanning window to 960 pixels and the height to 540 pixels
    Scanning window step height0

    The scanning step determines the relative offset of the windows. If the step is equal to the height and width of the scanning window, respectively, the segments are lined up one after another. Reducing the height or width of the scanning step increases the number of windows due to their overlapping each other with an offset. This increases the detection accuracy but can also increase the load on the CPU

    Note
    titleAttention!

    The height and width of the scanning step mustn't be greater than the height and width of the scanning window, since the detector doesn't operate with such settings.

    Scanning window width0The height and width of the scanning window are determined according to the actual size of the frame and the required number of windows. For example, the real frame size is 1920×1080 pixels. To divide the frame into four equal windows, set the width of the scanning window to 960 pixels and the height to 540 pixels
    Scanning window step width0

    The scanning step determines the relative offset of the windows. If the step is equal to the height and width of the scanning window, respectively, the segments are lined up one after another. Reducing the height or width of the scanning step increases the number of windows due to their overlapping each other with an offset. This increases the detection accuracy but can also increase the load on the CPU

    Note
    titleAttention!

    The height and width of the scanning step mustn't be greater than the height and width of the scanning window, since the detector doesn't operate with such settings.

    Selected object classes
    Nvidia GPU 0Nvidia GPU 1Nvidia GPU 2Nvidia GPU 3Intel NCS (not supported)Intel HDDL (not supported)Intel GPUHuawei NPUNumber of frames processed per second6

    Specify the number of frames for the neural network to process per second. The higher the value, the more accurate the tracking, but the load on the CPU is also higher. The value must be in the range [0.016, 100].

    Note
    titleAttention!

    We recommend the value of at least 6 FPS. For fast moving objects (running individuals, vehicles), you must set the frame rate at 12 FPS or above.

    TypeNeurotrackerName of the detection tool type (non-editable field)Advanced settings
    Camera position
    Wall To sort out false events from the detection tool when using a fisheye camera, select the correct device location. For other devices, this parameter is irrelevant
    CeilingHide moving objects
    Yes

    By default, the parameter is disabled. If you don't need to detect moving objects, select the Yes value. An object is considered static if it doesn't change its position more than 10% of its width or height during its track lifetime

    Note
    titleAttention!

    If a static object starts moving, the detection tool will create a track, and the object will no longer be considered static.

    NoHide static objects
    Yes

    By default, the parameter is disabled. If you don't need to detect static objects, select the Yes value. This parameter lowers the number false events from the detection tool when detecting moving objects. An object is considered static if it has not moved more than 10% of its width or height during the whole time of its track existence.

    Note
    titleAttention!

    If a static object starts moving, the detection tool will create a track, and the object will no longer be considered static.

    NoMinimum number of detection triggers6Specify the Minimum number of detection triggers for the Neurotracker to display the object's track. The higher the value, the longer the time interval between the detection of an object and the display of its track on the screen. Low values of this parameter can lead to false events from the detection tool. The value must be in the range [2, 100]Model quantization
    Yes

    By default, the parameter is disabled. The parameter is applicable only to standard neural networks for Nvidia GPU. It allows you to reduce the consumption of computation power. The neural network is selected automatically depending on the value selected in the Object type parameter. To quantize the model, select the Yes value

    Note
    titleAttention!

    AxxonSoft conducted a study in which a neural network model was trained to identify the characteristics of the detected object with quantization. The following results of the study were obtained: model quantization can lead to both an increase in the percentage of recognition and a decrease. This is due to the generalization of the mathematical model. The difference in detection ranges within ±1.5%, and the difference in object identification ranges within ±2%.

    • The first launch of a detection tool with the Model quantization parameter enabled can take longer than a standard launch.
    • If GPU caching is used, next time the detection tool with quantization will run without delay.
    NoNeural network file 

    If you use a custom neural network, select the corresponding file

    Note
    titleAttention!
    • To train your neural network, contact AxxonSoft (see Data collection requirements for neural network training).
    • A trained neural network for a particular scene allows you to detect only objects of a certain type (for example, a person, a cyclist, a motorcyclist, and so on).
    • If the neural network file is not specified, the default file will be used, which is selected automatically depending on the selected object type (Object type) and the selected processor for the neural network operation (Decoder mode). If you use a custom neural network, enter a path to the file. The selected object type is ignored when you use a custom neural network.
    • To ensure the correct operation of the neural network on Linux OS, the corresponding file must be located in the /opt/AxxonSoft/DetectorPack/NeuroSDK directory. 
    Scanning window
    YesBy default, the parameter is disabled. To enable the scanning mode, select the Yes value (see Configuring the scanning mode)
    NoScanning window height0

    The height and width of the scanning window are determined according to the actual size of the frame and the required number of windows. For example, the real frame size is 1920×1080 pixels. To divide the frame into four equal windows, set the width of the scanning window to 960 pixels and the height to 540 pixels

    Scanning window step height0

    The scanning step determines the relative offset of the windows. If the step is equal to the height and width of the scanning window respectively, the segments will line up one after another. Reducing the height or width of the scanning step will increase the number of windows due to their overlapping each other with an offset. This will increase the detection accuracy, but will also increase the CPU load.

    Note
    titleAttention!

    The height and width of the scanning step must not be greater than the height and width of the scanning window—the detection tool will not operate with such settings.

    Scanning window step width0Scanning window width0The height and width of the scanning window are determined according to the actual size of the frame and the required number of windows. For example, the real frame size is 1920×1080 pixels. To divide the frame into four equal windows, set the width of the scanning window to 960 pixels and the height to 540 pixelsSelected object class
     

    If necessary, specify the class of the detected object.

     If

     If you want to display tracks of several classes, specify them separated by a comma with a space. For example, 1, 10

    .


    The numerical values of classes for the embedded neural networks: 1—Human/Human (top-down view), 10—Vehicle

    .

      1. If you leave the field blank, the tracks of all available classes from the neural network
    will be
      1. are displayed (
    Object type
      1. Detection neural network, Neural network file)
    .
      2. If you specify a class/classes from the neural network, the tracks of the specified class/classes
    will be
      1. are displayed (
    Object type
      1. Detection neural network, Neural network file)
    .
      2. If you specify a class/classes from the neural network and a class/classes missing from the neural network, the tracks of a class/classes from the neural network
    will be
      1. are displayed (
    Object type
      1. Detection neural network, Neural network file)
    .

      2. If you specify a class/classes missing from the neural network, the tracks of all available classes from the neural network

    will be

      1. are displayed (

    Object type

      1. Detection neural network, Neural network file)

        Info
        titleNote

        Starting

    with 

      1. with Detector Pack 3.10.2, if you specify a class/classes missing from the neural network, the tracks

    won’t be

      1. aren't displayed (

    Object type

      1. Detection neural network, Neural network file).

    Similitude search
    Yes
    Sensitivity of excluding static objects (starting with Detector Pack 3.14) 25Specify the level of sensitivity of excluding static objects. The higher the value, the less sensitive to motion the algorithm becomes. The value must be in the range [0, 100]
    Similitude search

    		Yes

    By default, the

    By default, the

    parameter is disabled. To enable the search for similar persons, select

    the Yes 

    the Yes value. If you

    enabled processor load.

    enable the parameter, it increases the

     

    load on the CPU


    Note
    titleAttention!
    The 

    The Similitude search

     works

     works only on tracks of people.

    No
    Time of processing similitude track (sec)0Specify the time in seconds for the algorithm to process the track to search for similar persons. The value must be in the range [0, 3600]
    Time period of excluding static objects0Specify the time in seconds after which the track of the static object is hidden. If the value of the parameter is 0, the track of the static object isn't hidden. The value must be in the range
     
    [0, 86 400]
    Track lifespan (starting with Detector Pack 3.14)

    		YesBy default, the parameter is disabled. If you want to display the track lifespan for an object in seconds, select the Yes value

    No
    Track retention time0.7Specify the time in seconds after which the object track is considered lost. This helps if objects in the scene temporarily overlap each other. For example, when a larger vehicle completely blocks the smaller one from view. The value must be in the range
     
    [0.3, 1000]
    Basic settings
    Detection threshold30Specify the Detection threshold for objects in percent. If the recognition probability falls below the specified value, the data will be ignored. The higher the value, the higher the detection quality, but some events from the
    detection tool
    detector may not be considered. The value must be in the range [0.05, 100]
    Neurotracker
    Neural tracker mode













    		CPU

    Select the processor for the neural network operation (see Hardware requirements for neural analytics operation, Selecting Nvidia GPU when configuring

    detection tools

    detectors)

    .


    Note
    titleAttention!
    • We recommend using the GPU. It
    may
    neurotracker
    • the neural tracker is running on the GPU, object tracks can
    be lagging
    • lag behind the objects in the
    Surveillance
    • Surveillance window. If this happens, set the camera buffer size to 1000 milliseconds (see
    The
    object
    • ).
    • Starting with Detector Pack 3.11, Intel HDDL and Intel NCS aren’t supported.
    Nvidia GPU 0
    • Starting with Detector Pack 3.14, Intel Multi-GPU and Intel GPU 0-3 are supported.













    Nvidia GPU 0
    Nvidia GPU 1
    Nvidia GPU 2
    Nvidia GPU 3
    Intel NCS (not supported)
    Intel HDDL (not supported)
    Intel GPU
    Intel Multi-GPU
    Intel GPU 0
    Intel GPU 1
    Intel GPU 2
    Intel GPU 3
    Huawei NPU
    Object type
    Detection neural network








    		PersonSelect
    the recognition object.
  • Nano—low accuracy, low processor load.
  • Medium—medium accuracy, medium processor load.
    • Large—high accuracy, high processor load.
    the detection neural network from the list. By default, the Person detection neural network is selected. Neural networks are named taking into account the objects they detect. The names can include the size of the neural network (Nano, Medium, Large), which indicates the amount of consumed resources. The larger the neural network, the higher the accuracy of object recognition









    Person (top-down view)
    Person (top-down view Nano)
    Person (top-down view Medium)
    Person (top-down view Large)
    Vehicle
    Person and vehicle (Nano)
    Person and vehicle (Medium)
    Person and vehicle (Large)
    Neural network filter
    Neurofilter
    Neural filter

    		Yes

    By default, the parameter is disabled. To sort out parts of tracks, select the Yes value.

    For example:

    Neurotracker

    The Neural tracker detects all freight trucks, and the

    neurofilter

    Neural filter sorts out only the tracks that contain trucks with cargo

    door

    doors open

    No
    Neurofilter
    Neural filter file 

    Select a neural network file

    Note
    titleAttention!
    Starting with Detector Pack 3.12, the neural network file of the Neurofilter must match the processor type specified in the Neurotracker mode parameter

    . You must place the neural network file locally, that is, on the same server where you install Axxon One. You cannot specify the network file in Windows OS

    Note
    titleAttention!
    • Starting with Detector Pack 3.12, the neural network file of the neural filter must match the processor type specified in the Neural tracker mode parameter.
    • If you use a standard neural network (training wasn't performed in operating conditions), we guarantee an overall accuracy of 80-95% and a percentage of false positives of 5-20%. The standard neural networks are located in the C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroSDK directory.

    Starting with Detector Pack 3.14, you can add the DISABLE_CALC_HSV system variable to determine the object's color (see Appendix 9. Creating system variable). You can set the following values for the variable:

    • 0—color detection is enabled. The system will collect data about the object's color. This data is necessary for further search in the archive by color.
    • 1—color detection is disabled. Disabling color determination reduces the load on the CPU, including when the detector runs on GPU.

    By default, the entire frame is a detection area. If necessary, in the preview window, you can set detection areas with the help of anchor points Image Removed  (see Configuring a detection area).

    Info
    titleNote
    • For convenience of configuration, you can "freeze" the frame. Click the
    Image Removed
    • Image Added button. To cancel the action, click this button again.
    • The detection area is displayed by default. To hide it, click the
    Image Removed
    • Image Added button. To cancel the action, click this button again.

    To save the parameters of the detection tooldetector, click the Apply Image RemovedImage Added button. To cancel the changes, click the Cancel Image Removed button. Image Added button.

    Configuring the Neural tracker is complete. If necessary, you can create and configure the necessary detection sub-tools detectors on the basis of Neurotracker the neural tracker (see Standard detection sub-toolsdetectors).

    Note
    titleAttention!

    To trigger get an event from the Motion In Area detection tool in area sub-detector on the basis of Neurotrackerthe Neural tracker, an object must be displaced by at least 25% of its width or height in the frame.

    Example of configuring

    ...

    Neural tracker for solving typical tasks

    ParameterTask: detection of moving peopleTask: detection of moving vehicles
    Other
    Number of frames processed per second612
    Neural network filter
    NeurofilterNeural filterNoNo
    Basic settings
    Detection threshold3030
    Advanced settings
    Minimum number of detection triggers66
    Camera positionWallWall
    Hide static objectsYesYes
    Neural network file

    Path to the *.ann neural network file. You can also select the Object type valuevalue in the Detection neural network parameter. In this case, this field must be left blank

    		Path to the *.ann neural network file. You can also select the Object type valuevalue in the Detection neural network parameter. In this case, this field must be left blank