Requirements and recommendations for the Emergency Vehicle Detection module🔗

Important

If multiple video analytics modules are used on a single camera, it should be installed and configured to meet the requirements of all modules.

For example, module A and module B are used on the camera with the following requirements:

  • Module A: Camera tilt angle to the plane is at least 10°; resolution is at least 1024×768; frame rate is at least 20 frames per second.

  • Module B: Camera tilt angle to the plane is no more than 20°; resolution is no less than 1920×1080; frame rate is no less than 6 frames per second.

In this case, the camera must be installed and configured in order to comply with the following conditions:

  • Camera tilt angle to the plane is from 10° to 20°; resolution is at least 1920×1080; frame rate is at least 20 frames per second.

Hardware and software🔗

Tip

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

Warning

Before using the neural network capabilities of the module, it is necessary to install the neural networks package.

The following is required to use this neural network module:

  • 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.

Hint

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

The neural network works with the 64-bit version of Eocortex only.

Warning

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

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.

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.

Video stream🔗

For the modes using neural networks:

  • 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.

    Tip

    Increasing the resolution above HD will not lead to detecting smaller objects or a greater number of objects compared to HD.

  • Frame aspect ratio 16:9.

    Note

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

Image🔗

  • 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 position🔗

  • Emergency vehicle must be fully in the frame;

  • The camera angle must be adequate to correctly identify the type of emergency vehicle;

  • Emergency vehicle must not be covered by other objects;

  • Emergency vehicle must be clearly distinguishable from the background;

  • Vehicle should not be overexposed.

  • 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 35°.

  • Objects must be fully visible in the frame.

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

Warning

It is not recommended to use PTZ cameras.

Object size🔗

For successful detection, objects must be at least 80 pixels tall in the frame. In addition, the objects must meet the following parameters relative to the frame size:

  • Passenger cars must occupy at least 4% of the width and 4% of the height of the frame.

  • Trucks — at least 7% of the width and 9% of the height of the frame.

  • Buses — at least 5% of the width and 7% of the height of the frame.

Warning

The above requirements for object sizes as a percentage of frame size are the minimum necessary to ensure the best recognition quality under optimal conditions. If the relative sizes of objects are reduced from the required values, the module's performance for such objects will decrease.