Page History
The
...
following Axxon PSIM x64 and vertical solutions detection tools grouped by tabs are available for
...
selection.
Base detection tools
Name | Description | |
|---|---|---|
- Optimal resolution of 704*288 OR 640*360 and fps = 25. At a higher resolution the module will not be able to process all frames reducing quality of operation.
- Main channel has the same resources consumption as subordinate channel.
- Optimal resolution of 704*288 OR 640*360 and fps = 25. At a higher resolution the module will not be able to process all frames reducing quality of operation.
- Main channel has the same resources consumption as subordinate channel.
Object trajectories detection tool.
Face-Intellect face detection tool based on the Cognitec recognition module.
Face-Intellect face detection tool based on the Huawei recognition module.
| Motion detection (CPU) | Base detection tool (activated when the camera is armed) for decoding by all frames when using the CPU resources. The results are given with the registry key DetectionFps = 25. Changing the value of the DetectionFps key does not significantly affect the load | |
Motion detection (CPU, key frames) | Base detection tool (activated when the camera is armed) for decoding by key frames when using the CPU resources. Changing the frame rate in the settings of the detection tool (the Frames processed per second parameter) does not significantly affect the load | |
| Service detection (CPU, key frames) | Service detection tools for decoding by key frames when using the СPU resources:
The platform is calculated for one service detection tool (any of the listed). The results are given for decoding by key frames with GOP=25 (every 25th frame is the key frame). The detection tool is applicable only for H.264, H.265 codecs | |
Tracker
Name | Description | |
|---|---|---|
| Tracker VMDA (CPU) | VMDA detection tools based on object trajectory tracker when using the СPU resources | |
| Neurotracker (CPU, 6 FPS) | The scene analytics detection tools based on the Neurotracker when using the CPU resources and resource-intensive neural networks for detection of people or vehicles. You can select the type of recognition object for the detection tool: Person, Person (top-down view), Vehicle. Relative accuracy: medium, relative resource intensity: low. These neural networks are embedded in the product and can be trained on demand to detect different objects. In brackets is the frame rate that you can specify when configuring the Neurotracker object (the Number of frames processed per second parameter). This is the number of frames per second processed by the module; the frame rate of the incoming video stream is usually higher. The results are given for the Neurotracker with one working detection sub-tool Motion In Area | |
LPR&Traffic
Name | Description | |
|---|---|---|
| License plate recognition VT (CPU) | License plate recognition module VIT as part of Auto Axxon PSIM when using the СPU resources | |
| License plate recognition IV (CPU) | License plate recognition module LPR IntelliVision as part of Auto Axxon PSIM when using the СPU resources | |
| Vehicle detection IV (CPU) | Subsystem of traffic flow data collection based on IntelliVision vehicle detection as part of Auto PSIM when using the СPU resources | |
| License plate recognition RR (CPU) | License plate recognition module RR as part of Auto Axxon PSIM software package when using the СPU resources | |
Face
Name | Description | |
|---|---|---|
| Face recognition VA (CPU) | Face detection tool based on the VA recognition module as part of Face PSIM when using the СPU resources. When calculating the platform using this detection tool, only the resources for face detection and their | |
Face-Intellect face detection tool based on the Tevian recognition module.
vectorization are taken into account. The load from comparing faces with |
the reference database is not taken into account, because usually a separate server is provided to perform this function |
Railway
Name | Description | |
|---|---|---|
| Wagon number recognition ITB, passenger (CPU) | Recognizer of railway passenger carriage numbers based on the IntLab module as part of Auto PSIM when using the СPU resources.
| |
| Wagon number recognition ITB, freight (CPU) | Recognizer of railway freight carriage numbers based on the IntLab module as part of Auto PSIM when using the СPU resources.
| |
Behavior analytics
Name | Description | |
|---|---|---|
People counter (CPU) | ||
LPR VT
Auto-Intellect, VIT license plate recognition module.
People counter detection tool that is a part of | ||
Axxon PSIM Detector Pack when using the СPU resources. Optimal parameters for this detection tool are resolution of 800x600 / 640x360 / 640x480 / 320x240 and FPS |
in range from 24 to 30. If |
specified parameters of the video stream do not meet these conditions, then when you select this detection tool the resolution is set to 320x240 and FPS |
=24 |
Virtual Loop
Auto-Intellect, Vehicle detector module and Vehicle processor module that are the part of the information-gathering subsystem.
| Heat map (CPU) | Heat map detection tool (detection of "cold/hot" areas of a store) | |
| that is a part of |
| Axxon PSIM Detector Pack when using the СPU resources. The results are given when frame rate in the detector settings (the Frames processed per second parameter) is 25 | ||
| Queue length (CPU) | Queue length detection tool that is a part of Axxon PSIM Detector Pack when using the СPU resources. The results are given when frame rate in the settings of the detection tool (the Frames processed per second parameter) is 25 | |
Fire&Smoke
* - 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.
...
Name | Description | |
|---|---|---|
Fire detection tool (CPU, 0.1fps) Smoke detection tool (CPU, 0.1fps) | Fire and smoke detection tools based on neural network as part of Axxon PSIM Detector Pack when using the CPU resources. The frame rate specified during the detection tool configuration (the Number of frames for analysis and output parameter) is indicated in brackets. This is the number of FPS | |
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 in seconds between processed frames 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 documentation for the Detector Pack subsystem).
Object trajectories detection tool (VMDA) based on neural network and using the GPU resources
For each track, one image per second is sent to neural network for classification.
- The NVIDIA GeForce GT 730 video card is capable of processing about 70* classifications** per second.
- The NVIDIA GeForce GTX 1070 video card is capable of processing about 220*** classifications per second.
- The NVIDIA Tesla P40 video card is capable of processing about 122**** classifications per second.
The Intel Neural Compute Stick 1 (movidius I) is capable of processing about 58***** classifications per second.
The Intel Neural Compute Stick 2 (movidius II) is capable of processing about 200***** classifications per second.
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.
Intellect detection tools:
- focusing detection tool;
- video signal stability detection tool;
- background change detection tool;
- camera blinding detection tool;
- camera covering detection tool.
processed by the module; the frame rate of the incoming video stream is usually higher |
...
| title | Note. |
|---|