Test results
Performance testing
For performance testing, we took a video of a corridor with a flow of people moving at a speed of 5-10 people/sec (FPS=25). The volume of the database for identification is 249 persons.
Metrics
Metric name | Description |
Maximum | Maximum value of parameters (CPU load, GPU load, amount of RAM, amount of VRAM) for the entire test time |
95th percentile |
|
Median |
|
FPS | Number of frames processed per second |
Number of tracks | Number of tracks created during the test |
Number of tracks with biometric templates | Number of tracks that contain the generated biometric face template |
Number of matches with the face database | Number of matches of faces from videos with faces from the database |
Test 1
Test machine specification
CPU | RAM | Graphics Card |
AMD Ryzen 9 5950X @ 3.4 GHz: 16 cores (32 threads) | 118GB DDR4 | NVIDIA GeForce GTX 1080 Ti |
Test Results
Number of video streams | 1 | 5 | 8 | 10 | |
Maximum | Number of CPU cores | 1 | 8 | 12 | 16 |
GPU load | 82% | 96% | 95% | 94% | |
Amount of RAM | 2.34 GB | 4.2 GB | 5.31 GB | 6.18 GB | |
Amount of VRAM | 1.56 GB | 1.89 GB | 1.81 GB | 1.82 GB | |
95th percentile | Number of CPU cores | 1 | 8 | 12 | 16 |
GPU load | 19% | 78% | 84% | 82% | |
Amount of RAM | 2.34 GB | 4.08 GB | 5.19 GB | 6.05 GB | |
Amount of VRAM | 1.56 GB | 1.89 GB | 1.81 GB | 1.82 GB | |
Median | Number of CPU cores | 1 | 8 | 12 | 15 |
GPU load | 10% | 49% | 50% | 46% | |
Amount of RAM | 2.22 GB | 3.95 GB | 4.94 GB | 5.93 GB | |
Amount of VRAM | 1.56 GB | 1.89 GB | 1.81 GB | 1.82 GB | |
Number of tracks | 563 | 570 | 497 | 451 | |
FPS | 24.8 | 24.6 | 24.5 | 24.5 | |
Number of tracks with biometric templates | 563 | 570 | 497 | 451 | |
Number of matches with the face database | 233 | 236 | 233 | 230 |
Conclusion
1.5 cores per video stream when using GPU in the most high-load case "Safe City".