Skip to content

Calculating resources for analytics

Our face and license plate recognition modules are based on neural networks. We have created a separate neural network for each type of recognition consuming custom amount of video memory (VRAM) for GPU analytics or RAM for CPU. The analytics module memory consumption depends on the type of recognition you are going to to use.

Calculating video memory for analytics on GPU

You can use the following figures in your calculations of VRAM for analytics on GPU:

  • License plate recognition consumes 1.7 GB of video memory per server and about 150 MB per each camera
  • License plate recognition with detection of vehicles without license plates consumes 4.4 GB of video memory per server and about 150 MB per each camera
  • Emergency vehicle detection consumes 4.4 GB of video memory per server and about 150 MB per each camera
  • Face recognition consumes 2.5 GB of video memory per server and about 200 MB per each camera

It is also recommended to make a memory margin of about 1 GB for each neural network.

VRAM for one type of recognition = Video memory per neural network + Number of cameras × Video memory per camera + 1 GB

Please refer to this page for other system requirements for analytics on GPU.

Example:

Let's consider the situation when Watcher controls access to some facility. For that, there are 5 checkpoints each having one camera recognizing license plates to open the barriers, and 10 checkpoints each having one camera for face recognition to open the doors. Assume that we connect all these cameras to one streamer which will perform both license plate recognition and face recognition.

VRAM required for license plate recognition: 1,7 GB + 5 × 150 MM + 1 GB ≈ 3,4 GB

VRAM required for face recognition: 2,5 GB + 10 × 200 MB + 1 GB ≈ 5,4 GB

Total VRAM: 3,4 GB + 5,4 GB = 8,8 GB

Knowing this number and versions of Compute Capability supported by Watcher (6.1, 7.5 and 8.6) you can choose your video card(s) on the Nvidia website

Calculating RAM for analytics on CPU

You can use the following figures in your calculations of RAM for analytics on CPU:

  • License plate recognition consumes 450 MB of RAM per server and about 25 MB per each camera
  • Face recognition consumes 250 MB of RAM per server and about 30 MB per each camera

We also recommend about 30% margin in RAM to avoid system overload.

RAM for one type of recognition = RAM per neural network + Number of cameras × RAM per camera + 30%

Please refer to this page for other system requirements for analytics on CPU.

Example.

Let's calculate for the same example as above: 5 cameras with LPR and 10 for face recognition.

RAM required for license plate recognition: 450 MB + 5 × 25 MB + 30% = 757,5 MB

RAM required for face recognition: 250 MB + 10 × 30 MB + 30% = 715 MB

Total RAM: 757,5 MB + 715 MB = 1472,5 MB ≈ 1,4 GB