Page History
The following Axxon Next x64 detection tools grouped by tabs are available for Axxon Next platform calculation:
...
selection.
Base tab
Name | Description | Features of calculation |
|---|
Motion Detection (CPU, 20fps) |
Base motion detection tool The frame rate specified during the detection tool configuration (the Frames processed per second parameter) is indicated in brackets. This is the number of fps processed by the module; the frame rate of the incoming video stream is usually higher. | - | |
| Motion Detection (GPU, 20fps) | Base motion detection tool when using the GPU resources The frame rate specified during the detection tool configuration (the Frames processed per second parameter) is indicated in brackets. |
This is the number of fps processed by the module; the frame rate of the incoming video stream is usually higher. | 1 NVidia Quadro RTX 4000 card, regardless of the codec (H.264, H.265), processes up to 238 channels of 640x360 video with 25 fps; in case of 1920x1080 video with 25 fps, the number of channels depends on the codec: up to 55 channels for H.264, and up to 90 channels for H.265. For details, see GPU performance for Axxon Next detection tools Multiple NVidia Quadro RTX 4000 cards can be used on the server. |
Motion Detection (key frames) |
Base motion detection tool |
with the Decode key frames |
option enabled | The detection tool is applicable only for H.264, H.265 codecs. The platform is calculated for decoding by key frames if the GOP=25 (every 25th frame is the key frame) |
| Service Detection (key frames) |
Service detection tools: |
|
|
|
| The platform is calculated for one service detection tool (any of the listed) |
The detection tool is applicable only for H.264, H.265 codecs. The platform is calculated for decoding by key frames if the GOP=25 (every 25th frame is the key frame) |
Tracker tab
Name | Description | Features of calculation |
|---|
| Tracker VMDA |
Object trajectories detection tool.
Scene analytics detection tools (VMDA) based on object tracker | The results are given for the object tracker with 1 active sub detection tool Motion in area |
| AI tracker with neural filter (GPU) |
Scene analytics detection |
tools (VMDA) based on |
object tracker with use of a neural filter and GPU resources | For each track, one image per second is sent to neural network for classification.
|
|
|
|
|
|
|
The
|
|
|
|
|
| |
| Neural tracker (CPU, 6fps) | Scene |
analytics detection tools based on neural |
tracker with use of CPU resources The frame rate |
specified during the Neurotracker |
object configuration (the Frames processed per second parameter) is indicated in brackets. This is the number of |
fps processed by the module |
; the frame rate of the incoming video stream is usually higher. | The results are given for a standard size neural network5 |
| Neural tracker (VPU, 6fps) | Scene |
analytics detection tools based on neural tracker with use of VPU resources The frame rate specified during the Neurotracker object configuration (the Frames processed per second parameter) is indicated in brackets. This is the number of fps processed by the module; the frame rate of the incoming video stream is usually higher. | 1 Mustang-V100-MX8 (Intel HDDL) card processes up to 60 |
video channels regardless of video resolution. Multiple Mustang-V100-MX8 (Intel HDDL) cards can be used on the server. The |
results are given for a standard size neural network5 | ||
| Neural tracker (GPU, 6fps) | Scene analytics detection tools based on neural tracker with use of GPU resources The frame rate specified during the Neurotracker object configuration (the Frames processed per second parameter) is indicated in brackets. This is the number of fps processed by the module; the frame rate of the incoming video stream is usually higher. | 1 NVidia Quadro RTX 4000 card, regardless of the codec (H.264, H.265), processes up to 73 channels of 640x360 video with 25 fps; in case of 1920x1080 video with 25 fps, the number of channels depends on the codec: up to 52 channels for H.264, and up to 73 channels for H.265. For details, see GPU performance for Axxon Next detection tools Multiple NVidia Quadro RTX 4000 cards can be used on the server. The results are given for a standard size neural network5 The results are given for a neural tracker with 1 active sub detection tool Motion in area |
| Neural tracker, increased accuracy (GPU, 6fps) | Scene analytics detection tools based on neural tracker with use of GPU resources and high-precision neural network The frame rate specified during the Neurotracker object configuration (the Frames processed per second parameter) is indicated in brackets. This is the number of fps processed by the module; the frame rate of the incoming video stream is usually higher. | 1 NVidia Quadro RTX 4000 card, regardless of the codec (H.264, H.265), processes up to 61 channels of 640x360 video with 25 fps; in case of 1920x1080 video with 25 fps, the number of channels depends on the codec: up to 52 channels for H.264, and up to 61 channels for H.265. For details, see GPU performance for Axxon Next detection tools Multiple NVidia Quadro RTX 4000 cards can be used on the server. The results are given for a standard size neural network5 The results are given for a neural tracker with 1 active sub detection tool Motion in area |
LPR&Traffic tab
Name |
|---|
| Description | Features of calculation | |
|---|---|---|
| License plate recognition (VT) | License plate recognition (VT) detection tool | - |
Face tab
Name | Description | Features of calculation |
|---|---|---|
| Face |
| detection tool | Face |
detection tool | - |
Fire&Smoke tab
Name | Description | Features of calculation |
|---|---|---|
Fire detection tool (CPU, 0.1fps) Smoke detection tool (CPU, 0.1fps |
) | Fire and smoke detection tools based on neural |
500 MB of video memory per detection type is required regardless of the number of channels. For example, for any number of smoke detection channels, 500 MB is required, and if the server has any number of both smoke and fire detector channels at the same time, a video card with at least 1 GB of memory should be in use.
Several video cards can be in use in one system.
If the Time between processed frames in seconds parameter is set to the default value (10 seconds), any NVIDIA graphics card compatible with the detection tool will be suitable (see the requirements in the Axxon Next User Guide).
network with use of CPU resources The frame rate specified during the detection tool configuration (the Frames processed per second parameter) is indicated in brackets. This is the number of fps processed by the module; the frame rate of the incoming video stream is usually higher. | - |
Behavior analytics tab
Name | Description | Features of calculation |
|---|
| Pose detection (CPU, 3fps) | Pose detection tools based on neural |
network with use of CPU resources The frame rate specified during the detection tool configuration (the Frames processed per second parameter) is indicated in brackets. This is the number of fps processed by the module; the frame rate of the incoming video stream is usually higher. | The number of specific pose detection tools created under the head Pose detection object |
does not affect the calculation results (except for the Close-standing people detection |
The platform is calculated for Frame processed per second value of 3 fps which is different from the default value.
; to calculate the result with this detection tool, please contact the AxxonSoft support). | |
| Pose detection (VPU, 3fps) | Pose detection tools based on neural |
network with use of VPU resources The frame rate specified during the detection tool configuration (the Frames processed per second parameter) is indicated in brackets. This is the number of fps processed by the module; the frame rate of the incoming video stream is usually higher. | The number of specific pose detection tools created under the head Pose detection object |
does not affect the calculation results (except for the Close-standing people detection |
; to |
The platform is calculated for Frame processed per second value of 3 fps which is different from the default value.
If decoding is performed on CPU, 2x Intel Xeon Gold 6130T or 1х Intel core i7-8700 process up to 28 channels******
calculate the result with this detection tool, please contact the AxxonSoft support). 1 Mustang-V100-MX8 (Intel HDDL) card processes up to 28 channels regardless of video resolution Multiple Mustang-V100-MX8 (Intel HDDL) cards can be used on the server. The results are given for the standard neural network included in the Axxon Next distribution | ||
Equipment detection (CPU, 1fps) | Personal protection equipment (PPE) detection tools based on neural network with use of CPU resources The frame rate specified during the detection tool configuration (the Frames processed per second parameter) is indicated in brackets. This is the number of fps processed by the module; the frame rate of the incoming video stream is usually higher. | The results are given for a detection tool with 5 classification nets operating simultaneously when determining equipment on each body part (head, torso, hands, legs, feet) in a gateway: at the entrance to the area in which the equipment is required, an employee lingers for 5-10 seconds during which the detection tool determines the presence of the necessary equipment. |
| Equipment detection (VPU, 1fps) | Personal protection equipment (PPE) detection |
tools based on neural network with use of VPU resources The frame rate specified during the detection tool configuration (the Frames processed per second parameter) is indicated in brackets. This is the number of fps processed by the module; the frame rate of the incoming video stream is usually higher. | The results are given for a detection tool with 5 classification nets operating simultaneously when determining equipment on each body part (head, torso, hands, legs, feet) in a gateway: at the entrance to the area in which the equipment is required, an employee lingers for 5-10 seconds during which the detection tool determines the presence of the necessary equipment. 1 Mustang-V100-MX8 (Intel HDDL) card processes up to 40 channels regardless of video resolution. Multiple Mustang-V100-MX8 (Intel HDDL) cards can be used on the server. If you use Mustang-V100-MX8 (Intel HDDL), please note that due to the peculiarities of the device, only the segmentation neural network will be processed on it, and the CPU will be involved in the operation of the classification neural networks. |
| Info | ||
|---|---|---|
| ||
* 1 – The results are given for the 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** 2 per second. ** 2 – 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, then you need to use a video card allowing 45 classifications per second. *** 3 – 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. ***** – 4 – The results are given for the Core i7-3770 (3400 MHz) CPU and may vary depending on the CPU installed. ****** 5 – The results are given for a standard neural network capable of detecting an object sized at least 5% of the frame width/height. The results may differ for a neural network capable of detecting smaller objects (since more resources are required). |
...