Documentation for Axxonsoft Platform Calculator. Documentation for other products available here.
Previous page Next page
The following detection tools are available for Axxon Next platform calculation:
Name | Calculation on GPU | Description | Hardware requirements and features of calculation |
Video Content Analytic (VCA) | - | Object trajectories detection tool. | - |
Motion Detection | - | NOT a smart video detection tool in Axxon Next (Motion detection). | - |
Motion Detection (decode key frames) | - | NOT a smart video detection tool in Axxon Next (Motion detection) with key frames decoding enabled. | - |
License Plate Recognition | - | License plate recognition detection tool in Axxon Next version 4.0 and newer. | - |
Face Search | - | Face search detection tool in Axxon Next version 4.0 and newer. | - |
Fire Detection (CPU) | - | Fire detection based on neural network in Axxon Next version 4.1 and newer. | In order to enhance quality of operation and reduce CPU usage, it is recommended to use the detection tool with calculation on GPU. |
Fire Detection (GPU) | Yes | Video card requirements:
The detection tool uses 500 MB of video memory regardless of number of channels. Example: for 4 channels of fire detection tool, a video card with no less than 500 MB of memory is required. Several video cards can be in use in one system. | |
Smoke Detection (CPU) | - | Smoke detection based on neural network in Axxon Next version 4.1 and newer. | In order to enhance quality of operation and reduce CPU usage, it is recommended to use the detection tool with calculation on GPU. |
Smoke Detection (GPU) | Yes | Video card requirements:
The detection tool uses 500 MB of video memory regardless of number of channels. Example: for 4 channels of smoke detection tool, a video card with no less than 500 MB of memory is required. Several video cards can be in use in one system. | |
VCA with neural filter (GPU) | Yes | Object trajectories detection tool (VMDA) based on neural network in Axxon Next and Intellect. | Video card requirements:
For each track, one image per second is sent to neural network for classification.
Several video cards can be in use in one system. For example, if you need to track 9 persons per second on 10 cameras, GeForce GTX 1070 or similar video card is suitable. Up to two Intel Neural Compute Stick can be in use in one system. |
IntelliVision VCA | - | A smart video detection tool in Axxon Next | - |
Service detection (key frames) | - | Axxon Next detection tools:
| - |
VCA (Axis ACAP) | - | For Axis IP-devices only. This is an AxxonSoft Video Content Analytic (VCA) detection tool built into Axis device. See also AxxonSoft tracking in Axis devices (Intellect) or AxxonSoft tracking in Axis devices (Axxon Next). | The detection tool performs calculations using camera resources, and therefore has low hardware requirements. |
Note.
* - The results are given for Core i5-3570 (3400 MHz) CPU and may vary depending on the CPU installed. For example, the Xeon Gold 6140 (2300 MHz) CPU allows 95 classifications** per second.
** -1 classification per second is 1 object detected on video. For example, if average of 9 moving objects are simultaneously present on video from one camera, and there are 5 cameras in the system, use video card allowing 45 classifications per second.
*** - The results are given for the Core i7-8700 (3200 MHz) CPU and may vary depending on the CPU installed.
**** - 360 classifications per second were achieved in test utility on the 2x Intel Xeon Gold 6140 platform. In Axxon Next, up to 122 classifications per second were possible with 90% CPU utilization.
***** - The results are given for the Core i7-3770 (3400 MHz) CPU and may vary depending on the CPU installed.