Page History

Configuration of the Equipment detection (PPE) module includes: general settings of the detector, selection of the area of interest, and configuration of the neural networks. 

The Equipment detection (PPE) module is configured on the settings panel of the Equipment detection (PPE) object created on the basis of the Camera object on the Hardware tab of the System System settings dialog window window.

The Equipment detection (PPE)module is configured as follows:

...

General settings of the detector

General configuration of the detector is performed on the Detection settings tab on the settings panel of the Equipment detection (PPE) object

...

.
Image Modified

1. In the Recognition threshold [0, 100] field (1), enter the detection tool sensitivity - an integer value from 0 to 100.

   Info
   title Note
   The detector sensitivity is determined experimentally. The lower the sensitivity, the greater the probability of false positives. The higher the sensitivity, the less chance of false alarms, however, some useful tracks may be skipped.

   In the Min person height, % (2) and  and Min person width, % (3) fields fields, enter the minimum height and width of a person in the frame as a percentage of the frame height/width. Objects smaller than the specified size will not be detected.
2. In the Frames processed per second second [0,.016, 100] field (4), set the number of frames per second that will be processed by the detection tooldetector.

3. In the Number of frames for analysis and output field (5)[2, 20] field, enter the minimum number of frames on which a violation should must be detected in order to generate a triggeran event. The value should must be in the range [2; 20].

4. In the Track retention time (sec) field, enter the time in seconds in the range from 0.3 to 1000 after which the object track is considered lost. You can use this parameter in situations when one object in the frame temporarily overlaps another.

5. By default,  the detection triggering is generated the One event per equipment element checkbox is set, and the detector generates an event once for each equipment element violation . If it is necessary to generate a trigger once for each equipment item violation within a whole person's track, then uncheck One event per equipment element checkbox (6)within an object (track). If you want the detector to generate an event each time an equipment violation occurs, clear the checkbox.

   Info
   title Note
   Example. A person appeared in the frame without a helmet, then put it on and then took it off again. If the One event per equipment element checkbox is set, then there will be is one triggerevent, if not — twonot—two events.

6. Set the Show objects in on image checkbox (7) if it is necessary to highlight outline the detected object with a border on the image in the Monitor interface object window.

7. Set the Save tracks to show in archive checkbox to save the object (track) to the archive.
   

   Info
   title Note
   The frame on the image of the detected object is saved in the Monitor

   interface

   object

   window

   archive.

8. From the Working mode drop-down list (8) , select the device on which the neural network will operate: CPU, one of NVIDIA GPUs, or one of Intel GPUs. The default value is CPU. Depending on the device that you select, the neural networks will be selected.
   

   Note
   title Attention!
   It can take several minutes to launch the algorithm on NVIDIA GPU after you apply the settings. You can use caching to speed up future launches (see Optimizing the operation of neural analytics on GPU in Windows OS). If you specify another processing resource than the CPU, this device will carry most of the computing load. However, the CPU will also be used to run the detector.

    
9. Set the PPE detection checkbox to detect the presence of personal protective equipment (PPE). By default, the checkbox is clear.

Selecting the area of interest

1. Click the Settings button. The Detection settings window opensClick the Setup button (9). The Detector settings window will open.
   

2. Click the Start Stop video button (1) to pause playback and capture a frame of the video image.
3. Click the Surveillance territory button (2). Area of interest button to specify the area of detection. The button is highlighted in blue.
   Image Added
4. On the captured video frame, sequentially set the nodal anchor points of the area in which the objects will be detected by left-clicking the mouse button (3).
5. Click OK (4).
button. The rest of the frame will be faded. If you don't specify the area of interest, the entire frame is analyzed.


Info
title Note
You can add only one area. If you try to add a second area, the first area is deleted. To delete the area, click the Image Added button to the right of the Area of interest button.

There can be only one area of interest.
6. Click the OK button to close the Detection settings window and return to the settings panel of the detector.

Configuring neural networks

1. Go to the Network settings tab on the settings panel of the detector.
   Image Added
2. By default, the standard (default) segmenting neural network is initialized according to the device selected in the Working mode drop-down list. The standard neural networks for different processor types are selected automatically. If you use a custom segmenting neural network, click the Image Added button (1) to the right of the Segmenting network file field, and in the standard Windows Explorer window, specify the path to the file.
3. By default, two standard classification neural networks are initialized: classification neural network (PPE on the head) and classification neural network (PPE on the body) according to the selected processing device in the Working mode drop-down list
4. Go to the Network settings tab (10).
   Image Removed
5. Select the segmenting neural network file (11).
6. Select one or several files of the classification neural network (12). Each classification neural network detects equipment on a specific body segment.. The standard classification neural networks for different processor types are selected automatically. If you want to detect only one item of equipment, click the Image Added button to the right of the Classification network file field (2), and in the standard Windows Explorer window, specify the path to the custom neural network file. If there are several custom neural network files, specify the path to each.
7. Click the Apply button to save the settingsClick the Apply button (13) to save the changes.

The Equipment detection (PPE)module is now configured.