Loading…
Loading…
13 production-ready AI models with self-learning intelligence and hardware-adaptive inference. Enable face recognition, person tracking, ANPR, intrusion detection, line crossing, and more on any stream with per-stream configuration granularity. Integrated with Radha AI Copilot for natural language control.
Each model is optimized for video analytics use cases with configurable parameters, threshold tuning, and per-stream activation.
High-accuracy face detection, embedding extraction, and 1:N matching against enrolled galleries. Supports liveness detection and multi-angle recognition in challenging lighting conditions.
Track individuals across multiple cameras and timeframes using appearance-based feature vectors. Maintains identity consistency without requiring face visibility.
Automatic Number Plate Recognition supporting 100+ country formats. High-speed capture at up to 200 km/h with infrared and visible-light camera support.
General-purpose object detection identifying 80+ object classes including vehicles, animals, luggage, and personal items. Real-time bounding box output with confidence scoring.
Density-based crowd estimation and occupancy counting without individual tracking. Configurable thresholds trigger alerts when defined capacity limits are exceeded.
Specialized human body detection optimized for surveillance scenarios. Higher accuracy than general object detection for person-specific use cases including partially occluded individuals.
Define restricted zones on any camera view. Alerts trigger when persons or objects enter, exit, or dwell within configured polygonal boundaries.
Directional line crossing detection for counting, flow analysis, and perimeter monitoring. Supports multiple lines per camera with per-direction triggering rules.
Identifies individuals who remain in a defined area beyond a configurable time threshold. Combines person detection with temporal analysis for accurate dwell-time measurement.
Detects presence or absence of personal protective equipment including hard hats, safety vests, gloves, and goggles. Designed for industrial and construction site compliance monitoring.
Visylix automatically selects the optimal inference runtime based on available hardware. Deploy with or without GPUs.
Optimized inference on GPUs with FP16 and INT8 quantization. Batch processing across multiple streams maximizes GPU utilization and throughput.
Efficient CPU inference using hardware-accelerated optimization. Enables AI analytics on servers without dedicated GPU hardware, reducing deployment cost for smaller installations.
Enable, disable, and tune individual AI models on each video stream independently.
Enable face recognition on entrance cameras, ANPR on parking streams, and crowd detection in lobbies. Each stream runs only the models it needs.
Adjust confidence thresholds, minimum object sizes, and detection intervals per model per stream. Fine-tune sensitivity for each camera's field of view.
Define polygonal regions of interest within each camera view. AI models only process objects within configured zones, reducing false positives and compute load.
Configure where AI events are sent: WebSocket subscribers, webhook endpoints, recording triggers, or third-party integrations. Each model's events route independently.
Set per-stream FPS targets for AI processing. The engine balances inference load across available hardware to meet quality-of-service requirements.
New AI models under active development to expand Visylix's analytical capabilities.
Early-warning fire and smoke detection using thermal and visual analysis for critical infrastructure and industrial environments.
Classify vehicle make, model, year, and color for parking management, toll collection, and law enforcement applications.
Unsupervised anomaly detection that learns normal scene patterns and alerts on deviations without predefined rules.
Detect objects left unattended in public spaces. Distinguishes between placed objects and temporarily stationary items.
Visylix AI does not just detect. It learns your environment and continuously improves without manual retraining. No competitor offers this level of on-premise self-learning.
Motion detection and intrusion detection continuously learn what 'normal' looks like in your environment: shift patterns, traffic flow, peak hours, regular visitors. False positive rates drop by 60 to 80% in the first week of operation.
As recognized faces are seen from different angles and lighting conditions, embeddings auto-update with the highest quality captures. Face recognition accuracy improves by 15 to 25% over 30 days with zero manual retraining.
Person tracking Re-ID models learn the unique appearance characteristics of your environment. Handoff accuracy between cameras improves from approximately 70% on day one to approximately 90% after two weeks of operation.
All improvement happens automatically without manual retraining. Every acknowledged alert teaches the system what is important and what is noise. ANPR builds a plate database that grows more accurate with repeated observations.
AI learns which alert types are most actionable for your team. Noise alerts are automatically suppressed while critical alerts like unknown faces at restricted areas are prioritized higher over time.
All self-learning happens on your hardware. Video data never leaves your building. No cloud dependency for model improvement. Fully on-premise continuous learning that works in air-gapped environments.
Draw custom polygons and virtual lines on any camera view. Assign AI models per zone, filter events by region, and count directional crossings with speed estimation.
Hardware-adaptive inference automatically selects GPU or CPU based on available hardware. Scale from small test deployments to enterprise production environments.
Optimized NVIDIA CUDA inference for maximum throughput. Recommended for production deployments requiring real-time AI processing at scale.
Efficient CPU-only inference for testing environments and small deployments. No dedicated GPU hardware required, reducing deployment cost.
Automatic GPU detection and configuration. The engine automatically selects GPU or CPU inference based on available hardware.
See how Visylix AI integrates with the VMS Core Engine and multi-protocol streaming to deliver actionable intelligence.