Configuring the Area occupancy detector

Video stream and scene requirements for the Area occupancy detector

To configure the Area occupancy detector, do the following:

Go to the Detectors tab.
Below the required camera, click Create… → Category: Retail → Area occupancy detector.

By default, the detector is enabled.

If necessary, you can change the settings of the detector parameters given in the table:

Parameter	Value	Description
Object features
Record mask to archive	Yes	By default, the recording of the current occupancy readings to the archive is enabled (see Displaying information from a detector (mask)). To disable the parameter, select the No value
Record mask to archive	No
Video stream	Main stream	If the camera supports multistreaming, select the stream for which detection is needed. Selecting a low-quality video stream reduces the load on the server
Other
Enable	Yes	By default, the detector is enabled. To disable it, select the No value
Enable	No
Name	Area occupancy detector	Enter the detector name or leave the default name
Decoder mode	Auto	Select a processing resource for decoding video streams. When you select a GPU, a stand-alone graphics card takes priority (when decoding with NVIDIA NVDEC chips). If there is no appropriate GPU, the decoding will use the Intel Quick Sync Video technology. Otherwise, CPU resources are used for decoding
	CPU
	GPU
	HuaweiNPU
Number of frames processed per second	1	Specify the number of frames for the detector to process per second. The value must be in the range [0.016, 100]
Type	Area occupancy detector	Name of the detector type (non-editable field)
Advanced settings
Delayed start	Yes	By default, the delayed start of the detector after receiving the first frame is enabled. The delay is applied randomly, ranging from 0 to the value specified in the Event sending period (min) parameter. By default, the value of the Event sending period (min) parameter is 1 minute. It means that the detector startup after receiving the first frame is delayed for the time in the range from 0 to 60 seconds. The optimal delay value depends on the configuration and number of detectors. We recommend specifying the delay value in such a way so that the number of seconds isn't less than the number of detectors. To disable delayed start, select the No value
Delayed start	No
Detected objects	Yes	By default, detected objects are displayed. To disable the display of detected objects, select the No value
Detected objects	No
Frame averaging	Yes	By default, frame averaging is enabled. To disable it, select the No value
Frame averaging	No
Frame comparison	Yes	By default, the parameter is disabled. To enable frame comparison, select the Yes value
Frame comparison	No
Minimum number of detection triggers	5	Specify the minimum number of detection triggers to generate an event. The value must be in the range [1, 20]
Segmentation neural network file		Select the segmentation neural network file. Standard neural networks for different types of processors are located in the C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroSDK directory. You don't need to select standard neural networks in this field, the system automatically selects the necessary one. When you use a custom neural network, you must specify the path to the file. Attention! You cannot specify the network file in Windows OS. You must place the neural network file locally, that is, on the same server where you install Axxon One. For correct neural network operation on Linux OS, place the corresponding file locally in the /opt/AxxonSoft/DetectorPack/NeuroSDK directory or in the network folder with the corresponding access rights. If you use a standard neural network (training wasn't performed in operating conditions), we guarantee the overall accuracy of 80-95% and the percentage of false positives of 5-20% (see Data collection requirements for neural network training).
Basic settings
Event sending period (min)	1	Specify the time period in minutes between sending events. The default value is 1 minute. The value must be in the range [0, 1440] Attention! The value must not be less than the period specified by the parameter Number of frames processed per second.
Segmentation neural network mode	CPU	Select a processor for the operation of the segmentation neural network (see Hardware requirements for neural analytics operation, Selecting Nvidia GPU when configuring detectors) 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, Optimizing the operation of neural analytics on GPU in Linux OS). If you specify another processing resource than the CPU, this device will carry most of the computing load. However, the CPU is also used to run the detector.
	Nvidia GPU 0
	Nvidia GPU 1
	Nvidia GPU 2
	Nvidia GPU 3
Classification settings
Classification network file		By default, the classification neural network is initialized according to the processing device selected in the Classification neural network mode parameter. To initialize, select the required classification neural network file. Standard neural networks for different types of processors are located in the C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroSDK directory. You don't need to select standard neural networks in this field, the system automatically selects the necessary one. When you use a custom neural network, you must specify the path to the file Attention! You cannot specify the network file in Windows OS. You must place the neural network file locally, that is, on the same server where you install Axxon One. For correct neural network operation on Linux OS, place the corresponding file locally in the /opt/AxxonSoft/DetectorPack/NeuroSDK directory or in the network folder with the corresponding access rights. If you use a standard neural network (training wasn't performed in operating conditions), we guarantee the overall accuracy of 80-95% and the percentage of false positives of 5-20% (see Data collection requirements for neural network training).
Classification neural network filter	Yes	By default, the parameter is disabled. To enable the classification filter, select the Yes value
Classification neural network filter	No
Event reporting settings
Current occupancy	Yes	By default, the parameter is disabled. If it is necessary to send an event about the current occupancy level, select the Yes value. Events are sent each time frames are analyzed
Current occupancy	No
Max object size (%)	100	Specify the maximum object size as a percentage of the area. The value must be in the range [0, 100]
Min object size (%)	0	Specify the minimum object size as a percentage of the area. The value must be in the range [0, 100]
Occupancy threshold, %	10	Specify the occupancy threshold as a percentage above which events are generated. The value must be in the range [0, 100]

To generate events, you must specify a detection area. To do this, do the following:

Click in the preview window.
Select Detection area.
Specify the detection area using the anchor points . We recommend specifying an area with a simple shape for more correct operation of the detector. You can create multiple detection areas.

Note

For convenience of configuration, you can "freeze" the frame. Click the button. To cancel the action, click this button again.
To hide a detection area, click the button. To cancel the action, click this button again.
To delete a selected area, click the button.

To save the parameters of the detector, click the Apply button. To cancel the changes, click the Cancel button.

Configuring the Area occupancy detector is complete.

Page tree

Documentation for Axxon One 2.0. Documentation for other versions of Axxon One is available too.