Page History

To configure NeuralcounterNeurocounter, do the following:

1. To record mask (highlighting of recognized objects) to the archive, select Yes for the corresponding parameter (1).
   Image Added
2. If the If a camera supports multistreaming, select the stream to apply the detection tool to (1for which detection is needed (2). 
   Image Modified
3. Select a processing resource for decoding video streams (23). When you select a GPU, a stand-alone graphics card takes priority (when decoding with NVidia NVIDIA NVDEC chips). If there 's is no appropriate GPU, the decoding will use the Intel Quick Sync Video technology. Otherwise, CPU resources will be used for decoding.
4. If you need to outline the recognized objects in the preview window, select Yes in for the Detected Objectsobjects parameter (34).
5. Set the recognition threshold for objects in percent (45). If the recognition probability falls below the specified value, the data will be ignored. The higher the value, the higher the accuracy — for the cost of sensitivityrecognition accuracy, but some triggers may not be considered.

6. Set the

   interval between the analyzed frames in seconds (5). The

   frame rate value for the detection tool to process per second (6). This value should be

   within

   in the range

   of 0,05 – 30.Set the minimum number of frames with excessive numbers of objects for Neuralcounter to trigger (9). The value should be within the range of 2 – 20

   [0,016; 100].

   Info
   title Note
   The default values (3 output frames and 1 secondFPS) indicate that Neuralcounter Neurocounter will analyze one frame every second. If Neuralcounter Neurocounter detects more objects than the specified threshold value number of objects (or more) on 3 frames, then it triggers.

   
   

7. Select the processor for the neural network - – CPU, one of NVIDIA GPUs , or one of Intel NCSGPUs (67, see Hardware requirements for neural analytics operation, General Information on Configuring Detection). 

   Note
   title Attention!
   If you specify other processing resource than the CPU, this device will carry the most of computing load. However, the CPU will also be used to run Neurocounter.

   
   

   Note
   title Attention!
   It may take several minutes to launch the algorithm on an NVIDIA GPU NVIDIA GPU after you apply the settings. You can use caching to speed up future launches (see Configuring the acceleration of GPU-based neuroanalytics).

   
   

8. In the Object type field (11), select the object type for counting, or in the Neural network file field (8), select the neural network file.

   Note
   title Attention!
   If you specify other processing resource than the CPU, this device will carry the most of computing load. However, the detection tool will consume CPU as well.

   Select the neural network file

   To train your neural network, contact AxxonSoft (see Data collection requirements for neural network training). A trained neural network for a particular scene allows you to detect only objects of a certain type (e.g. person, cyclist, motorcyclist, etc.).  If the neural network file is not specified, the default file will be used, which is selected depending on the selected object type (11) and the selected processor for the neural network operation (7).

   
   

   Info
   title Note
   For correct neural network operation under on Linux, place the corresponding file in the /opt/AxxonSoft/AxxonNextDetectorPack/NeuroSDK directory.

   
   

9. Set the triggering condition for the neural counterNeurocounter:

   1. In the Number of alarm objects field field (9), set the threshold value for the number of objects in FoV (8)FOV. 

   2. In the Trigger upon count field (12), select the condition polarity: whether triggering should occur on exceeding the threshold, or dropping below it (10). when you want to generate the trigger − when the number of objects in the detection area is greater or less than the threshold value. 

10. Set the minimum number of frames on which Neurocounter should detect objects in order to trigger (10). The value should be in the range [2; 20].

11. In the preview window, you can set the detection zones areas with the help of anchor points much like privacy masks in Scene Analytics detection tools (see Setting General Zones for Scene Analyticsanalytics detection tools). By default, the entire FoV FOV is a detection zonearea.
    
12. Click the Apply button.

After the neural tracker is created, the layout can It is possible to display the sensor icon with and the number of objects within in the controlled area in the video surveillance window on the layout. To configure this option, please follow do the steps belowfollowing:

1. Proceed Switch to the Layout Editing mode (see Switching to layout editing mode).
2. Place the sensor anywhere in FoVFOV.
   Image Modified
3. Customize the font. To do this, press click the Image Added button Image Removed.
4. Save the layout (see Exiting layout editing mode). As a result, the sensor and the number of objects will be displayed in the selected place:
   Image Modified