Requirements and recommendations for the Tracking module๐Ÿ”—

Module operation modes๐Ÿ”—

Objects being tracked (setting in Configurator)

Only those in motion

Filter by categories

Additional setting in the Configurator

Using neural networks

Available in version 4.3

โˆš

โ€”

โˆš

Available in version 4.4

โ€”

โ€”

โˆš

Neural networks are used to detect objects

โˆš

โˆš

โˆš

Neural networks are used to make a trajectory

โ€”

โˆš

โˆš

Can operate efficiently without a graphics card (GPU)

โˆš

โˆš

โ€”

It is possible to run the module on a high-performance graphics card (see hardware resource requirements)

โ€”

โˆš

โˆš

Relative accuracy of trajectories

Middle

Average or above average in certain conditions

High

Operating systems

Available on all operating systems used by the Eocortex software

The list of supported operating systems depends on the :ref:` used neural network package <tracking-requirements-os>`

What objects are tracked

All moving objects detected by software motion detector.

Objects of the following categories:

  • People

  • Animals

  • Vehicles by type: Passenger cars, Buses, Trucks, Motorcycles.

Warning

To run the module in the Filter by categories mode, the neural-networks package must be installed.

Warning

It is not recommended to run the module on the central processing unit (CPU) in Filter by categories mode, as in this case the module performance is extremely low.

Note

Using Only those in motion mode with neural networks at resolutions starting from 2 MP allows (compared to the same cameras in the mode without neural networks) to run more cameras with the module on the same server even if there is no video card.

At the same time, it is possible that the accuracy of the module in Only those in motion mode using neural networks will drop (and a warning about it will appear) if the following conditions are met simultaneously:

  • low resolution of video streams (less than 1 MP) on a large number of cameras with the module enabled;

  • there is no video card that supports neural networks.

Hardware and software๐Ÿ”—

Minimum hardware and software requirements are caused by the following factors:

  • If neural networks are used in the module's operation.

  • If neural networks are used in the module's operation, whether they run on a central processing unit (CPU) or a graphics card (GPU).

Hardware resources๐Ÿ”—

Tip

To calculate the parameters of the server and client hardware on which you plan to run Eocortex software, use our Calculator.

Using neural networks on the CPU๐Ÿ”—

  • The module using neural networks that will run on a central processing unit (CPU) requires an Intel CORE I3-10100 or higher processor with AVX support.

Using neural networks on the graphics card๐Ÿ”—

  • The module using neural networks that will run on a high-performance graphics card (GPU), it is necessary to follow the requirements below:

    • A processor that supports AVX instructions.

    • An NVIDIA video card (GPU) with the computation capacity index of at least 6.5 and with at least 4 GB of memory; the parameters and performance of the video card must be similar or better than those of NVIDIA GeForce GTX 1650 Ti model.

    • Version of the video card driver at least 460.

    • Swap file at least half of the total RAM size.

    Warning

    NVIDIA RTX 50 series video cards cannot be used to run Eocortex neural networks.

    If the package will be installed on a virtual machine, it may additionally be required to:

    • Enable support for AVX instructions in the guest machine settings.

    • Use GRID drivers for GPU virtualization.

    Warning

    Eocortex must use video cards selected for running neural networks in monopoly mode. It is not allowed to use such card for other applications or tasks that consume GPU resources, including for displaying video. Simultaneous use of a video card for several tasks may lead to incorrect system operation: from analytics performance degradation to server instability.

    Warning

    When using a video card, the stable operation of the module is guaranteed on operating systems Windows 10, Windows Server 2016, Ubuntu 20.04, as well as on the newer versions of these operating systems.

    Warning

    On other operating systems (Windows versions 7 and 8, Windows Server versions 2008 and 2012, Debian), issues may arise when trying to use NVIDIA graphics cards. On Windows 8, this is due to the cessation of support for NVIDIA graphics card drivers. On Debian, the problem is due to the high complexity of installing workable versions of video card drivers.

    Warning

    When upgrading Eocortex to another version, it is necessary to also upgrade the neural networks package to the corresponding version.

Neural networks๐Ÿ”—

Note

If you are having trouble choosing which network package to install, check out this Usage of neural networks article. This article provides an overview and comparison of neural-network packages.

Operating systems๐Ÿ”—

  • The Only those in motion mode without the use of neural networks will work on all operating systems available to run the Eocortex software.

  • When using the Eocortex Neural Networks Standard package, the following operating systems are available:

    • Windows 10, 11

    • Windows Server 2016, 2019, 2022

    • Ubuntu 20.04, 22.04

    • Debian 11

  • When using the Eocortex Neural Networks Special package, the following operating systems are available:

    • Windows 10, 11

    • Windows Server 2016, 2019, 2022

    • Ubuntu 20.04, 22.04

    • Debian 11

Video stream๐Ÿ”—

  • Frame frequency: no lower than 3 frames per second;

  • Image resolution: no lower than HD (1280x720). Increasing the resolution will not detect more objects or smaller objects.

  • Frame aspect ratio 16:9.

Note

The accuracy of object recognition may be reduced if the frame aspect ratio is different.

Image๐Ÿ”—

  • Lighting in the frame should be uniform and constant.

  • If the camera is installed in front of a bright light source (the sun behind an entrance door, etc.), it is required to adjust the exposure (or brightness) to ensure that the objects in the frame have a natural color (not overexposed or darkened). In this case, it is permissible for the background to be overexposed.

  • The image must be in color.

  • Image quality should be at least average. There should be no significant compression artifacts.

  • White balance must be adjusted correctly.

Scene and camera position๐Ÿ”—

Error

The Tracking module must not be used on PTZ cameras.

  • The object should be seen from a suitable angle so that it is positively distinguishable from the background and clearly visible to the human eye.

  • The frame must not contain reflective surfaces: glass, mirrors, etc. If there are such surfaces in the frame, it is necessary to exclude them from the detection area in the module settings.

For the modes using neural networks:

  • It is permitted to place the camera overhead. In this case, the angle of inclination of the camera in relation to the horizontal must not exceed 35ยฐ.

  • Objects must be fully visible in the frame.

  • The camera must be fixed securely, do not allow the camera to jiggle or wobble.

For the Only those in motion mode without using neural networks:

  • It is permitted to place the camera overhead. In this case, the angle of inclination of the camera in relation to the horizontal must not exceed 45ยฐ.

Object size๐Ÿ”—

  • To successfully detect objects in a frame, their size must be at least 80 pixels in height.

  • People must occupy at least 2% of the width and 8% height.

  • Animals โ€” at least 4% of the width and 6% height.

  • Passenger cars โ€” at least 4% of the width and 4% of the height.

  • Trucks โ€” at least 7% width and 9% height.

  • Buses โ€” at least 5% of width and 7% height.

  • Motorcycles โ€” at least 3% width and 7% height.

Recognition of vehicles๐Ÿ”—

Minimum requirements to ensure the identification of vehicles are as follows:

  • Detection of vehicles must be performed during daylight hours in good weather.

  • Exposure and contrast on the camera must be set so that the color of the object can be unambiguously detected by the human eye.

  • The body of a vehicle must not be light-struck by headlights or other light sources. There must not be any bright glare on the body.

  • The angle of view must provide correct identification of the type of vehicle (e.g., it is sometimes difficult to distinguish a bus from a truck when viewed from behind).

  • Installing the camera at an angle to the axis of movement of vehicles provides the most favorable perspective.

Examples๐Ÿ”—

Below are the examples of angles for determining the mode of transport.

Correct

Incorrect

/analytics/search/img/example-vehicle-ok-1.png

/analytics/search/img/example-vehicle-failure-1.png

/analytics/search/img/example-vehicle-ok-2.png

/analytics/search/img/example-vehicle-failure-2.png

/analytics/search/img/example-vehicle-ok-3.png

/analytics/search/img/example-vehicle-failure-3.png