VCloud.ai Hard Hat Detection Module

From vCloud.ai Documentation
Revision as of 19:33, 13 November 2023 by Vcloudai (talk | contribs) (→‎Product Description)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

Main functionality

  • Recognition and notification of employees of production facilities, workshops or factories, construction sites in the workplace without a hardhat.
  • Data storage and transmission on violations of hardhats wearing regime.
  • Monitoring the level of security at construction or industrial facilities.

Product Description

The Hard Hat Detection module is designed for rapid response to cases of non-compliance with safety regulations.

Hard Hat module can be used for:

  • Prevent injuries in production or construction;
  • Monitoring the compliance with safety rules in places where equipment is used and installation works are performed;
  • Control of discipline on the construction site or at the places of loading/unloading of raw materials.

System Requirements

It is necessary to have the minimum system requirements for one video stream for Hard Hat Detection module installation on GPU as in the table below.  For information on a bigger quantity of video streams address the official distributor of the VEZHA products.  

PARAMETER RECOMMENDED VALUE
CPU Intel Core i5-5575 or higher
RAM 2 GB RAM
GPU NVIDIA 1030
Places for archive up to 3GB per day (~4.5k detections)
Operating system Ubuntu 20.04

Analytics

To open the Hard Hat Detection analytics, select Hard Hat Detection in the left menu and pass to the Analytics section.

K90.png

In the Analytics section, you can customize analytics. The page displays a list of analytics with the status and the ability to add, edit, view, or delete analytics.

There is a search field at the top of the page. Here you can filter analytics by the following parameters:

Field name Description
Camera               Analytics name or part of a name can be entered in this field
Status                 Select the Analytics status from the drop-down list - All, Active, or Stopped

To start the search click on the Search button. To clear the fields click on the Reset button.

K91.png

Analytics Adding

In order to add a new Hard Hat Detection analytics, press Add Analytics in the upper right corner of the page.

K93.png

The Hard Hat Detection analytics setup process consists of 3 Steps.

Step 1 - General

K94.png

First of all, it is necessary to select a video stream. Click on the Video field and select the camera name from a list.

K95.png

You can also enter the part of the camera name in the Search field to find the necessary video stream faster.

K96.png

On the right side of the window, you can see the video stream preview and information about Camera name and Address, Time Zone, Resolution, Codec, and Type.

K97.png

When the video stream is selected press the Set Video Stream button.

By pressing the Update Video Frame button you can see a frame in real-time in the field of frame addition.

It is possible if a video stream was selected

To add analytics it is necessary to set up the following parameters:

Field name Description
The interval between alerts, sec The frequency with which the system will check for the notification. The possible range is from 0.5 to 300 s. The recommended value is 0.5 s
Check interval, sec The frequency with which the system will check for the presence of a hardhat. The possible range is from 0.04 to 30 s. The recommended value is 0.04 s

To pass to the next step, click on the Next button in the upper right corner of the page.

K99.png

Step 2 - Hardware

K100.png

Now it is time to customize Hardware options. System users can change the following parameters:

Parameter Description
Hardware Select one of the technologies - CPU or GPU acceleration
Decoding Select the hardware decoder from the drop-down list - CPU, Intel, Nvidia
Optimization Select the optimization parameter from the drop-down list (for CPU - CPU (no optimization), Open VINO; for GPU - CUDA (no optimization), cuDNN Half (FP16), Tensor RT)
FPS Enter the desired number of frames per second in the field for detection. The recommended value is 25

When all necessary parameters are selected, go forward to the last step by clicking on the Next button in the upper right corner of the page.

Step 3 – Notifications

Finally, it is possible to customize Notifications.

K102.png

For this purpose check the box next to Send events to Event Manager. The system will send all notifications to the Event Manager and then to external resources.

K103.png

Then it is necessary to fill in the following fields:

Field name Description
Events Select the event for which notifications will be sent from the drop-down list.
Extra Options If necessary, it is possible to add additional parameters for further use when event creating. Fill in the parameter and value fields.

To add more parameters, click on the Add Options button.

K105.png

To remove parameters, click on the Delete icon.

K106.png


If you want to make changes to previous steps, click on the Back button in the upper right corner of the page.

K107.png

When the analytics setup is complete, click on the Save button in the upper right corner of the page to save changes and create the analytics.

K108.png

Analytics Editing

To open the Hard Hat Detection analytics editing window, click the Edit button on the right side of the analytics record.

K109.png


It is possible to edit the analytics if it is not running.

If the analytics is active at the moment, it is necessary to disable it by clicking on the Stop Analytics button in the upper right corner of the editor page.

K110.png

When you click on the Stop Analytics button, the Confirmation window opens. Click Yes to confirm the analytics disable or click No to cancel the action.

K111.png


Now when the analytics is disabled it is possible to make changes to it.

There are 3 tabs of parameters at the top of the page, similar to the steps in creating analytics - General, Hardware, and Notifications. The General tab opens first by default.

The current tab is always highlighted. You can switch among them by clicking on their names.


General Tab

At the General tab it is possible to edit the following parameters:

Field name Description
The interval between alerts, sec The frequency with which the system will check for the notification. The possible range is from 0.5 to 300 s. The recommended value is 0.5 s
Check interval, sec The frequency with which the system will check for the presence of a hardhat. The possible range is from 0.04 to 30 s. The recommended value is 0.04 s


Hardware Tab

At the Hardware tab it is possible to edit the following parameters:

PARAMETER DESCRIPTION
Hardware Select one of the technologies - CPU or GPU acceleration
Decoding Select the hardware decoder from the drop-down list - CPU, Intel, Nvidia
Optimization       Select the optimization parameter from the drop-down list (for CPU - CPU (no optimization), Open VINO; for GPU - CUDA (no optimization), cuDNN Half (FP16), Tensor RT)
FPS Enter the desired number of frames per second in the field for detection. The recommended value is 25
K120.png

Notifications Tab

At the Notifications tab it is possible to edit values in the following fields:

        FIELD NAME DESCRIPTION
Events Select the event for which notifications will be sent from the drop-down list.
Extra Options If necessary, it is possible to add additional parameters for further use when event creating. Fill in the parameter and value fields.


To add parameters, click on the Add Options button.

K121.png

To remove parameters, click on the Delete icon.

K122.png

When the analytics editing is complete, click on the Save button in the right upper corner of the editor page to save changes.

K125.png

Analytics Viewing

To view a Hard Hat Detection analytics, press the View icon on the right side of the video stream field.

It is possible to view only Active video streams.

In the opened window, you can view the video from the camera in real-time.

K126.png

There are violation records in the table below, which includes Camera, and Violation Time columns.

COLUMN NAME         DESCRIPTION
Camera Here you can look at the camera location and a frame of violations of the hardhats wearing regime
Violation Time     The time the camera detects a violation of hardhats wearing regime


Press on the Frame icon to look closer at the detected violation of the hardhats wearing regime.

K127.png

To download an image of the violation of the hardhats wearing regime, press Save image.

K128.png

Analytics Start and Stop

To start analytics, press the Start button on the right side of the analytics field. To stop analytics, press the Stop button.

K129.png

When you click on the Stop button, the confirmation window opens. Click Yes to confirm or click No to cancel the action.

K130.png

Analytics Deletion

To delete analytics, press the Delete icon on the right side of the analytics field.

K131.png

In opened window press Yes to confirm the deletion or No to cancel the deletion.

K132.png

Events

To view the history of security violations, select Hard Hat Detection in the left menu and pass into the Events section.

K133.png

Events Search

There is an event search field at the top of the page.

Search field Parameters
        Time Frame Press on the field and select the desired time period.
        Camera Press on the field and select the camera you want to receive notifications for from the drop-down list

Press Search to display the search results. Press Reset to clear the input fields.

To view the location and direction of the camera, press the Location icon.

K134.png

Events View

To go to the list view format, press the corresponding icon in the upper-right corner.

K135.png

To return to the grid format, press the corresponding icon in the upper-right corner again.

K140.png

Frame View

To enlarge a frame with a hardhat wearing regime violation, press the enlargement icon on the photo of interest.

K141.png


Press "+" to Zoom in or "-" to Zoom out the frame. Press "~" to return the frame to the default size.

K143.png

If desired, it is possible to save the image by pressing the Save Image button.