Skip to end of metadata
Go to start of metadata

1 Main purpose

Offload-video analytics is an offloading technology that allows you to delegate computing operations demanding resources from one machine to another by transferring data over a local network.

2 Work principle

NVRs receive a stream from video cameras. An encoded video stream or key frames of this video stream are sent to the computing server, depending on the detector. After that, processing and analytics take place, then the results are returned to the source server.

For offload detectors, video analytics works as follows:

  1. The data is sent to the machine;
  2. Operations related to neural networks and/or using GPUs are transferred to a remote machine with suitable hardware;
  3. The results of the detector operation are returned to the data source machine.

This makes it possible to efficiently use the available hardware resources.

That is, in fact, offload video analytics is remote video analytics: the ability to transfer calculations to another server.

2.1 Example

Let's say there are already several cameras connected to MiniNVR video recorders, the image from which we can view in the TRASSIR Client. We want to connect a neural network queue detector.  However, the MiniNVR series recorders do not support local neuro analytics. But you can connect a NVR from the NeuroStation series to MiniNVR, and transfer the video stream from MiniNVR to it.  If necessary, you can connect the cameras directly to the NVR with analytics.

After analyzing the video, the analytics server returns the data with detections to the source server from which the offload was performed. Thus, we can use the results of neural network analytics, regardless of the fact that the video stream is recorded on the MiniNVR recorder, which is simple in functionality.

3 Interface and Settings

  • First, you need to enable analytics over the network. In the client settings for the required user, check the "Enable remote analytics".

  • The connection to the analytics server is made in the same way as to a regular TRASSIR server.

    A new NeuroStation server is being added in the "Network" section

  • Then on the NeuroStation server in the Modules settings > Analytics you can configure possible detectors to process them on the GPU.

  • To activate the module, it is necessary to select the desired detector item and specify Server for offload video analytics in the Channel Settings in the Software Detectors area.

   The status of the offload video analytics for each detector is also displayed here. This state can also be seen in the detector Settings.

4 Requirements

4.1 Network bandwidth 

  • Vehicle number recognition (AutoTRASSIR-30) - at least 512 kb/s
  • Vehicle number recognition (AutoTRASSIR-200) - at least 2 mb/s
  • Zone Crossing Detector (Neuro Counter) - at least 1 mb/s
  • Direction Detector - at least 1 mb/s
  • For other modules (for example, a helmet detector, people, objects), the network bandwidth must be at least 128 kb/s

In the case of tracing objects (tracking movement, crossing lines), the entire video stream is transmitted to the computing server. And if the detection occurs every few seconds, then only the key frames are used.

The capabilities of the recorders to work video analytics without displaying video on the monitor (provided that one module is running on the recorder) in the Offload mode are indicated in paragraph 1 in the Analytics Reference

5 Operations performed

The sequence of operations performed is shown in the diagram below:

In the case of face recognition, after selecting the found faces and sending the data back to the source server, the received faces are compared with the database of faces that is specified on the source server, and after that the recognition occurs.

6 Licensing

With offload analytics, the detector license is spent on the server that directly performs analytics, and not on the video source server

7 Advantages of offload in system design

  • Offload analytics allows you to upgrade the video surveillance system to the neural network level and get access to all the capabilities of neuroanalytics with one NVR - instead of replacing the entire fleet with dozens of video recorders with analytics technology. Hence, it is possible to reduce the cost of purchasing equipment and increase the convenience of maintenance.
  • In the presence of a large-scale video surveillance system with the need for video analytics of several channels located in disparate corners of the object, Offload analytics is an excellent solution, since a neural network recorder can be located anywhere, connecting to the network via the Internet.
  • Offload allows you to read more channels than it is physically possible to connect to the NVR. That is, you can connect many video recorders of the system and analyze all incoming video streams. Previously, a complex and expensive system was used for these purposes: several cameras on the same territory were connected to a powerful NVR that conducted all video analytics. If there were more objects, each required the installation of a separate device for data processing.

Alexander Savkin