System requirements
Hardware
| Task | CPU with AVX support | RAM | VRAM | GPU power |
|---|---|---|---|---|
| Video decoding | 0.3 cores | – | – | – |
| Face identification | 1.1 cores | 1.0 GB +3 GB per 1M faces in the database | 0.3 GB | 0.9 TFLOP |
| Face identification (CPU only) | 2.0 cores | 3.5 GB +3 GB per 1M faces in the database | – | – |
| Body detection and skeleton joint tracking | 1.3 cores | 1 GB | 0.5 GB | 1.0 TFLOP |
| Behavioral analytics (added to body detector consumption) | 0.2 cores | 0.6 GB | 0.5 GB | 5.5 TFLOP |
| UAD – new objects (700×700) | 1.9 cores | 1.9 GB | 1.8 GB | 3.8 TFLOP |
| Object detection (phones, cigarettes, etc.) | 1.0 core | 1.4 GB | 0.5 GB | 1.0 TFLOP |
| Driver state monitoring (DSM) | 1.0 core | 1.0 GB | 1.4 GB | 3.1 TFLOP |
note
Values are specified per video stream. Additionally, 0.1 CPU core and 0.4 GB RAM are required to maintain OMNI Agent. All CPU values refer to threads with hyper-threading (not physical cores). Calculate your server needs with the server capacity calculator.
Software
Supported OS: Windows 10+ (x86_64), Ubuntu 14+ (x86_64).
caution
For stable operation of OMNI Agent, hardware resources should not be loaded above 80%.
caution
If the database exceeds 50K persons, the agent’s working directory must be located on an SSD drive.
GPU requirements
System requirements
Linux / Windows:
GPU Driver >= 441.22
CUDA Toolkit 11.8
cuDNN v8.8.0 for CUDA 11.x
TensorRT 8.6 (optional)
Hardware requirements
- GPU with CUDA support (from NVIDIA GTX 1050 Ti up to RTX 4090 inclusive, Compute Capability 3.5–9.0).