Versions Compared

Old Version 4

changes.mady.by.user Alina Luchkina

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

Video stream and scene requirements for the Object Tracker tracker and its sub-toolsdetectors

Image requirements for the Object Tracker tracker and its sub-toolsdetectors

Hardware requirements for neural analytics operation

To configure the Object Tracker detection tooltracker detector, do the following:

  1. Go to the Detection ToolsDetectors tab.

  2. Below the required camera, click Create… → Category: Trackers → Object Trackertracker.

By default, the detection tool detector is enabled and set to detect moving objects in the frame, on the basis of which their tracks are created.

Some parameters are set for all sub-tools detectors of the Object Trackertracker simultaneously (see Recommendations for configuring the Object Tracker tracker and its sub-toolsdetectors).

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

other will carry the will be the detection tool may on NVIDIA GPU
ParameterValueDescription
Object features
Record objects trackingYes

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

Note
titleAttention!

To obtain metadata, the video is decompressed and analyzed, which results in a heavy load on the Server server and limits the number of video cameras that can be used on it.

No
Video streamMain stream

If the camera supports multistreaming, select the stream for which detection is needed. Selecting a low-quality video stream allows you to reduce the Server server load.

Note
titleAttention!

To ensure the correct display of streams on a multi-stream camera, all video streams must have the same frame aspect ratio.

Other
EnableYesBy default, the parameter is enabled. To disable, select the No value
No
NameObject TrackertrackerEnter the detection tool 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 the Intel Quick Sync Video technology. Otherwise, CPU resources will be are used for decoding

CPU
GPU
HuaweiNPU
TypeObject TrackertrackerName of the detection tool detector type (non-editable field)
Neural network filter
Enable filter

Yes

By default, the neural network filter is disabled. To enable a neural network filter to filter out parts of tracks, set the value to Yes (see Hardware requirements for neural analytics operation). For example, a neural network filter can process the results of the tracker and filter out false positives on a complex video image (foliage, glare, etc.and so on).

Note
titleAttention!

A You can use a neural network filter can be used either only for the analysis of moving objects , or only for the analysis of abandoned objects. You cannot use two neural network filters simultaneously.

No
Moving object filter mode
 
 
 
 
 
 






CPU

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

Note
titleAttention!
  • If you specify
  • another processing resource than the CPU, this device
  • carries most of the computing load. However, the CPU
  • is also
  • used to run
  • the detector.
  • It
  • can 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 3.14, 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 Multi-GPU
Intel GPU 0
Intel GPU 1
Intel GPU 2
Intel GPU 3
Huawei NPU
Abandoned object filter mode
 
 
 
 
 
 






CPU
Nvidia GPU 0
Nvidia GPU 1
Nvidia GPU 2
Nvidia GPU 3
Intel NCS (not supported)
Intel HDDL (not supported)
Intel Multi-GPU
Intel GPU 0
Intel GPU 1
Intel GPU 2
Intel GPU 3
Huawei NPU
Moving object filter file
 

Select the required neural network. To obtain a neural network, contact AxxonSoft technical support. If the neural network file

is not

isn't selected or selected incorrectly, the filter

will not work

doesn't work

Note
titleAttention!
  • 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.
Abandoned object filter file 
Basic settings
Long-time abandoned object detection

Yes

By default, the parameter is disabled. To enable, select theYesvalue.

Info
titleNote

If you enable this and the Enable filter parameter, it can reduce the number of false positives during detection.

No
Abandoned object detection

Yes

By default, the parameter is disabled. To enable, select theYesvalue.

Info
titleNote

Objects abandoned for 10 seconds or longer will be are detected.

No
Max. object height
100

Set the maximum height and width of the detected object as a percentage of the frame size. The value must be in the range [0.05, 100].

Note
titleAttention!

If the Object calibration parameter is enabled in the tracker settings, then the maximum height and width of objects is set in decimeters , and not as a percentage of the frame size.

Max. object width100
Alarm on object's max. idle time in area60

Specify the time in seconds—if seconds exceeding which the object remains idle for the time longer than the specified, it will be is detected. This value must be in the range [15, 1800].

Info
titleNote

This parameter is used only for the Long-time abandoned object detection. It is recommended to select We recommend selecting the parameter value starting from 15.

Min. object height2

Set the minimum height and width of the detected object as a percentage of the height/width of the frame size. The value must be in the range [0.05, 100].

Note
titleAttention!

If the Object calibration parameter is enabled in the tracker settings, then the minimum height and width of objects is set in decimeters , and not as a percentage of the frame size.

Min. object width2
Motion detection sensitivity
25

Set the sensitivity of the motion detection sub-tools detectors in percentage. The higher the sensitivity, the more subtle change fewer changes in the frame will be are detected. The value must be in the range [0, 100]

Abandoned object detection sensitivity9

Set the sensitivity for abandoned object detection and long-time abandoned object detection as a percentage.
The value must be in the range [10, 100].

Info
titleNote

This parameter The Abandoned object detection sensitivity parameter depends on the lighting conditions and must be chosen is selected empirically. It is recommended to select We recommend selecting the parameter value starting from 20.

Advanced settings
Auto sensitivity
Yes

By default, the parameter the Auto sensitivity is enabled. To disable automatic adjustment of the sensitivity of the the Object tracker sub-toolsdetectors, select theNovalue.

Info
titleNote

It is recommended to enable We recommend enabling this parameter if the lighting changes significantly in during the video camera field of view operation (for example, if the camera operates in outdoors).

No
Track lifespan (starting with Detector Pack 3.14)
Yes

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

No
Leveling rod height
20
Set the height of the calibration object in decimeters. The value must be in the range [1, 100]
Frame size change
1280

By default, during the analysis, the frame is compressed to the specified size (by default, 1280 pixels on the larger side). The following algorithm is used:

  • If the original resolution on the larger side of the frame is greater than the resolution specified in the Frame size change parameter, then it is divided in half.
  • If the resulting resolution becomes less than the specified one, then the algorithm stops and the resulting resolution will be is used.
  • If the resulting resolution is still greater than the specified one, then it is divided in half again until it becomes less than the resolution specified in the Frame size change parametersmaller.
Info
titleNote

For example, the original video resolution is 2048x1536, the specified value is 1000. In this case, the original resolution will be is divided in half (512x384) twice , because after the first division, the value on the larger side of the frame will be is greater than the specified value (1024 > 1000).
If detection errors occur when using a higher resolution stream is used for detection, and there are detection errors, it is recommended to reduce , we recommend reducing compression.

Object calibration
Yes
By default, the parameter is disabled (see see Configuring perspective). To estimate the real size of an object based on a simplified calibration system, select theYesvalue
No
Camera position
Wall
If you use a fish-eye camera, choose To filter out false events when using a fisheye camera, select the correct location of the device to filter out false events. The default value is is Wall. This parameter is not isn't relevant for all other devices
Ceiling
Antishaker
Yes
By default, the parameter is disabled. To reduce camera shake, select theYesvalue. It is recommended to use We recommend using this parameter only when there is significant camera shake
No

In the preview windowBy default, specify the entire frame is a detection area in which objects will be detected. The area is configured by moving the anchor points Image Removed .If necessary, in the preview window, set:

...

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 Image Added button.

The Configuring the Object tracker detection tool detector is configuredcomplete. General parameters will be are set for all its sub-toolsdetectors. If necessary, you can create and configure the necessary sub-tools detectors on the basis of the Object Trackertracker (see Abandoned Object detectionobject, Standard sub-detectors).