Page History

Some parameters can be configured for Scene Analytics detection tools simultaneously. To configure them, do as follows: 

1. Select the Object tracker object.

   

2. By default, video stream metadata are recorded to the database. You can disable the recording by selecting No in the Record objects tracking list (1).

   Note
   title Attention!
   Video decompression and analysis are used to obtain metadata, which causes high Server load and limits the number of video cameras that can be used on it.

   
   

3. If the video camera supports multistreaming, select the stream for which detection is needed (2). Selecting a low-quality video stream allows reducing the load on the Server.

   Note
   title Attention!
   To display the object tracks properly, make sure that all video streams from multistreaming camera have the same aspect ratio settings.

   
   

4. If you need to automatically adjust the sensitivity of the scene analytics detection tools, select Yes in the Auto sensitivity list (3).

   Info
   title Note
   It is recommended to enable this option if the lighting fluctuates significantly in the course of the video camera operation (for example, in outdoor conditions).

   
   

5. To reduce the number of false positives from a fish-eye camera, you have to position it properly (4). For other devices, this parameter is not valid.

6. Select a processing resource for decoding video streams (5). 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 will be used for decoding.
7. In the Motion detection sensitivity field (6), set the sensitivity of the scene analytics detection tools to motion in the range [1, 100].
8. To smooth camera shake, set Yes for the Antishaker parameter (7). This parameter is recommended to use only when the camera shake is evident.

9. Analyzed framed are scaled down to a specified resolution (8, 1280 pixels on the longer side). This is how it works:

   1. If the longer side of the source image exceeds the value specified in the Frame size change field, it is divided by two.

   2. If the resulting resolution falls below the specified value, it is used further.

   3. If the resulting resolution still exceeds the specified limit, it is divided by two, etc.

      Info
      title Note
      For example, the source image resolution is 2048*1536, and the specified value is set to 1000. In this case, the source resolution will be halved two times (512*384), as after the first division, the number of pixels on the longer side exceeds the limit (1024 > 1000).

      
      

      Info
      title Note
      If detection is performed on a higher resolution stream and detection errors occur, it is recommended to reduce the compression.

      
      

10. Enter the time interval in seconds, during which object properties will be stored in the Time of object in DB field (9). If the object leaves and enters the FOV within the specified time, it will be identified as one and the same object (same ID).  

11. If necessary, configure the neural network filter (see Hardware requirements for neural analytics operation). The neural network filter processes the results of the tracker and filters out false positives on complex video images (foliage, glare, etc.).

    Note
    title Attention!
    A neural network filter can be used either for analyzing moving objects, or for analyzing abandoned objects only. You cannot operate two neural networks simultaneously.

    1. Enable the filter by selecting Yes (1).
       

    2. Select the processor for the neural network—CPU, one of NVIDIA GPUs, or one of Intel GPUs (2, 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 the detection tool. It may 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). Starting with Detector Pack 3.11, Intel HDDL and Intel NCS aren’t supported.

       
       

       Tip
       Camera requirements for neural filter operation

       
       

    3. Select a neural network (3). To access a neural network, contact Grundig technical support. If no neural network file is specified, or the settings are incorrect, the filter will not operate.

    
    

12. Click the Apply button.

The general parameters of the Scene Analytics detection tools are now set.