AI Glossary
The complete dictionary of Artificial Intelligence
FPS (Frames Per Second)
Key metric measuring the number of frames processed per second by a detection system, determining its ability to operate in real-time.
Detection Latency
Delay in milliseconds between image acquisition and the production of detection results, crucial for interactive applications.
NMS (Non-Maximum Suppression)
Post-processing algorithm that eliminates redundant detections by keeping only the boxes with the highest confidence scores.
Model Quantization
Optimization technique that reduces the numerical precision of model weights (e.g., 32-bit to 8-bit) to accelerate inference.
Inference Pipeline
Optimized sequence of processing steps from video input to detection output, including pre/post-processing.
OpenVINO
Intel toolkit for optimized deployment of AI models on various hardware architectures (CPU, GPU, VPU).