Versions Compared

Old Version 2

changes.mady.by.user Alena Kniazeva

Saved on

compared with

New Version 3

changes.mady.by.user Bahdan Tsiulkou

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 Neural tracker and its sub-detectors

Image requirements for the Neural tracker and its sub-detectors

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 the Neural tracker, do the following:

  1. Go to the Detectors tab.

  2. Below the required camera, click Create… → Category: Trackers → Neural tracker.

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

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

Camera position
Hide moving objects
Model quantization
If you use a custom neural network, select the corresponding fileScanning window
will line will increase will increase , will CPU load.
ParameterValueDescription
Object features
Record objects trackingYes

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

No
Video streamMain stream

If the camera supports multistreaming, select the stream for which detection is needed

Other
EnableYesBy default, the detector is enabled. To disable, select the No value
No
NameNeural trackerEnter the detector name or leave the default name
Decoder modeAuto

Select 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 uses the Intel Quick Sync Video technology. Otherwise, CPU resources will be are used for decoding

CPU
GPU
HuaweiNPU
Neural filter modeCPU

Select a processing resource for neural network operation (see Hardware requirements for neural analytics operation, Selecting Nvidia GPU when configuring detectors)

Note
titleAttention!
  • We recommend using the GPU. It can take several minutes to launch the algorithm on an 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, Optimizing the operation of neural analytics on GPU in Linux 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 detector settings, and the Neural filter runs on the same processor as Neural tracker. If before Detector Pack update, you select a different processor in the Neural filter mode parameter, after the update, the detector works without Neural filter.
Nvidia GPU 0
Nvidia GPU 1
Nvidia GPU 2
Nvidia GPU 3
Intel NCS (not supported)
Intel HDDL (not supported)
Intel GPU
Huawei NPU
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 range [0.016, 100].

Note
titleAttention!

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

TypeNeural trackerName of the detector type (non-editable field)
Advanced settings
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
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 will create a track, and the object will no longer be considered static.

Color detection (starting with Detector Pack 3.14 version)Yes

By default, color detection is enabled. This parameter collects the data about the object's color. These data are necessary for further search in the archive by color.
If you set the No value, color detection is unavailable when searching in the archive. Disabling color detection reduces the load on the CPU, especially during detector operation on the GPU.

No
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
Scanning mode
No
Hide static objects

YesBy default, the parameter is enabled. If you need to detect static objectsdisabled. To use the Scanning mode, select the Yes value. (see Configuring the scanning mode)
No
Hide moving objects

Yes

By default, the parameter is disabled. If you don't need to detect moving objects, select the Yes value. No value. This parameter lowers the number false events from the detector when detecting moving objects. An object is considered static if it has not moved doesn't change its position more than 10% of its width or height during the whole time of its track existence.lifetime

Note
titleAttention!

If a static object starts moving, the detector

will create

creates a track, and the object

will

is no longer

be

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]
    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 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 will run without delay.
    No
    Hide static objects

    		Yes

    By default, the parameter is enabled. If you need to detect static objects, select the No 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

    No
    Neural network 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 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.
    • 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. 
    • If you use standard neural network (training wasn't performed in operating conditions), we guarantee the overall accuracy of 80-95% and the percentage of false positives of 5-20%. The standard neural networks are located in the C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroSDK directory.
    YesBy default, the parameter is disabled. To enable the scanning mode, select the Yes value (see Configuring the scanning mode)
    No

    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 is within ±1.5%, and the difference in object identification ranges is 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 

    When using a custom neural network, select the corresponding file. Select a neural network file. 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!
    • To train your neural network, contact AxxonSoft (see Data collection requirements for neural network training).

    • Using a trained neural network for a particular scene allows detecting 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.
    • 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 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 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 widthScanning 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 heightwidth0

    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

    Note
    titleAttention!

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

    Scanning window step width0

    load on the CPU.

    Note
    titleAttention!
    Scanning window width0

    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

    step mustn't be greater than the height and width of the scanning window

    to 960 pixels and the height to 540 pixels

    since the detector doesn't operate with such settings.

     

    Selected object classes 

    If necessary, specify the class of the detected object. 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
      2. will be
      1. are displayed (Detection neural network, Neural network file).
      2. If you specify a class/classes from the neural network, the tracks of the specified class/classes
      3. will be
      1. are displayed (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
      4. will be
      1. are displayed (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

      5. will be

      1. are displayed (Detection neural network, Neural network file)

        Info
        titleNote

        Starting with Detector Pack

      6.  3

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

      7. won’t be

      1. isn't displayed (Detection neural network, Neural network file).

    Sensitivity of excluding static objects (starting with Detector Pack 3.14)

    25

    Specify the level ofsensitivity 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 parameter is disabled. To enable the search for similar persons, select the Yes value. If you enabled enable the parameter, it increases the processor loadthe load on the CPU.

    Note
    titleAttention!

    The Similitude search works only on tracks of people.

    NoTime of processing similitude track (sec)0

    Specify 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
    NoTrack 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 range [0.3, 1000]Basic settings
    Detection threshold30

    Specify the Detection threshold for objects in percent.

    If

    The system ignores the data 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 detector may not be considered. The value must be in the range [0.05, 100]

    Neural tracker mode








    CPU

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

    .

    Note
    titleAttention!
    be lagging
    • lag behind the objects in the Surveillance window. If this happens, set the camera buffer size to 1000 milliseconds (
    see 
    • see Camera).
    • Starting with Detector Pack 3.11, Intel HDDL and Intel NCS aren’t supported.
    • Starting with Detector Pack 3.11, Intel Multi-GPU and Intel GPU 0-3 are supported.









    Nvidia GPU 0Nvidia GPU 1Nvidia GPU 2Nvidia GPU 3Intel NCS (not supported)Intel HDDL (not supported)not supported)Intel GPUIntel Multi-GPUIntel GPU 0Intel GPU 1Intel GPU 2Intel GPU 3Huawei NPUDetection neural network





    Person

    Select 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)VehiclePerson and vehicle (Nano)Person and vehicle (Medium)Person and vehicle (Large)Neural network filter
    Neural filterYes

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

    For example:

    The Neural tracker detects all freight trucks, and the Neural filter sorts out only the tracks that contain trucks with cargo door doors open

    NoNeural filter file 

    Select a neural network filenetwork file. 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
    • neural filter must match the processor type specified in the Neural tracker mode parameter.

    • When using a standard neural network (training isn'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 folder.

    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 Modified button. To cancel the action, click this button again.

    The detection area is displayed by default. To hide it, click the Image Modified button. To cancel the action, click this button again.

    To save the parameters of the detector, click the Apply Image Modified button. To cancel the changes, click the Cancel Image Modified button.

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

    Note
    titleAttention!

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

    Example of configuring the 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
    Neural 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 value 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 value in the Detection neural network parameter. In this case, this field must be left blank