Unique Visitor Counting🔗

The Unique Visitor Counting module is designed for building reports on counting unique visitors. It is possible to exclude from counting the persons present in the face database and included in the specified groups of this database. This may be required when you want to exclude your own employees from counting.

Capabilities of the module🔗

  • Counting people wearing glasses, hats, etc.

  • Counting people in masks

  • The number of employees in the base is not limited

  • Determination of gender and age

  • Emotion Recognition

  • Reports

  • Using a high-performance graphics card (GPU)

  • Using multiple graphics cards (GPU)

Details🔗

In a situation when the number of cameras with enabled recognition modules exceeds the number of video cards in use, cameras will be distributed to video cards evenly, without taking into account the characteristics of video streams from cameras and video card performance (i.e., an equal number of cameras will be attached to each video card, if possible).

The module uses the recognized face access control technology, in which the uniqueness of a face is determined based on a set of features called an index. In this case, the module does not operate on individual points of the face when determining the index; instead, the entire 100x100 pixel image is analyzed.

The Unique Visitor Counting module can identify masked faces of employees with a fairly high accuracy; provided that the database contains samples of unmasked faces of these employees. Also, this plugin can identify turned faces; even if the database contains only images of these faces looking directly into the camera.

The face database can be located either on the same server where the recognition is performed or on another server of a single multi-server video surveillance system.

Each record in the face database contains:

  • one or more images (screenshots and/or photos) of the person's face;

  • surname, first name, patronymic (full name), which is entered manually and is an optional parameter;

  • additional information (optional text field);

  • group membership (optional parameter);

  • the uniqueness of the records of the person database is determined by the person index. Thus, the database may contain several records with matching full name (including those with empty full name value).

You can work with the face database either from the Eocortex Client application or using the API.

Using multiple video cards🔗

The Unique Visitor Counting module uses all video cards installed on the server and matching the requirements. In this case, each camera with the module running is matched to one of the video cards.

In a video surveillance system that has many cameras, using multiple video cards on the server allows distributing the load on all video cards. In order to distribute the load on the video cards installed on the same server evenly when working with recognition modules, it is recommended to observe the following conditions:

  • The number of cameras with modules using video cards bound to the server is a multiple of the number of video cards.

  • The number of cameras with modules using video cards bound to the server is greater than or equal to the number of video cards.

  • All video cards on the server must be equal or comparable in performance.

Warning

If the video cards have different performance, the load will not be evenly distributed between them.

Warning

The video card specifications must comply with the requirements listed in the module requirements.

Note

When the number of cameras with the recognition modules enabled exceeds the quantity of video cards used, the cameras will be uniformly distributed among the video cards, as applicable, without considering the characteristics of the video streams coming from the cameras and the performance of the video cards (i.e. an equal number of cameras will be assigned to each video card, wherever possible).

Compatibility with other modules🔗

Requires Eocortex motion detector

Neural Networks

Compatible with modules

Incompatible with modules

Standard

Special

√

√

√

  • Abandoned object detection module

  • Auto Zoom

  • Counting People in Queue

  • Crowd Monitoring

  • Emergency Vehicle Detection

  • Face detection

  • Face Mask Detection

  • Face Recognition (Complete)

  • Fire and Smoke Detection

  • Frame Area Blurring

  • Loud sound detection

  • People Counting

  • Personnel Activity Monitoring

  • Sabotage Detection

  • Search for Objects

  • Shelf Fullness Check

  • Traffic density heat map

  • Tracking

  • Uniform Detection

  • Face Recognition (Light)

  • Fisheye dewarping module

  • License Plate Recognition (Complete)

  • License Plate Recognition (Light)

  • Object Classification and Counting

√

supported and required for the module to work

+

supported and provides additional features of the module

–

not supported or not required for the module to work

⚠

not recommended for use with the current module

Usage🔗

Using the module in the Eocortex Client application.

Related references

  • /additional-instructions/analytics-module-troubleshooting