Requirements and recommendations for the Object Classification and Counting 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🔗

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.

Video stream🔗

Frame frequency: no lower than 10 frames per second;

Classification of objects🔗

The object should be clearly visible on the frame, not overlapped by other objects and not blend into the background.
The object should not be blurred.
Frame resolution should not be lower than HD (1280×720 px).

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:

People must occupy at least 2% of the width and 8% of the height of the frame.
Passenger cars — at least 4% of the width and 4% of the height of the frame.
Trucks — at least 9% of the width and 13% of the height of the frame.
Motorcycles — at least 4% of the width and 10% of the height of the frame.
Buses — at least 8% of the width and 11% of the height of the frame.
Animals — at least 11% of the frame width and 15% of the height of the frame.

Counting by line crossing:

The greatest side of the object should not exceed 25% of the frame size.
The movement speed of the object should be such that in 0.1 seconds the object moves no more than 0.25 of its size.

Note

Specifics of vehicle type recognition:

Pickup trucks are recognized as Passenger cars. However, in some cases they may be recognized as Trucks.
Minibuses and minivans are recognized as Buses. However, in some cases they may be recognized as Passenger cars.

Examples🔗

The following are examples of camera angles for the proper module operation.

Correct	Incorrect