Skip links

Vision & PerceptionLab

A lab specialized in AI-powered visual understanding, transforming images, videos, documents, and multimodal content into actionable information that enables intelligent automation, operational monitoring, and business decision-making.

Where Images BecomeIntelligence

The Vision Lab develops advanced technologies for visual perception and multimodal AI, helping organizations extract value from visual data and transform it into scalable operational knowledge. Combining computer vision, image processing, document understanding, and generative AI, the lab delivers reliable solutions that support inspection, monitoring, automation, and information access across complex enterprise environments.

Distinctive Approach

Deep Visual Understanding

A detail-oriented approach that preserves the contextual, structural, and semantic richness of visual information, from video streams to complex document layouts.

Operations Ready

Technologies shaped by real-world deployments, ensuring robustness, scalability, and measurable business value in production environments.

Flexibility

A modular architecture enabling adaptation across industries, data sources, and deployment scenarios while supporting continuous integration and evolution.

Reliability

Solutions designed for enterprise-grade reliability, delivering traceable, verifiable, and auditable outputs that support critical operational processes.

Focus Areas

Traffic, Infrastructure & Mobility Analytics
Development of computer vision solutions for monitoring intersections, assets, vehicles, infrastructure, and critical events across urban and extra-urban roadways, enabling safer mobility, improved traffic management, and more efficient infrastructure operations.
01
Document AI & Layout Understanding
Advanced document understanding technologies that transform complex files, scans, and visual documents into structured, actionable enterprise knowledge.
02
Multimodal Foundation Models
Research and development of multimodal AI systems, including contributions to Velvet, combining visual and language understanding to enable more natural interaction with enterprise information and intelligent automation.
03
Occupational Health & Safety
Development of AI-powered visual monitoring solutions that support workplace safety by identifying hazardous conditions, detecting unsafe behaviors, monitoring compliance with safety procedures, and enabling proactive risk prevention across industrial and operational environments.
04