All Foundries

Isometric blue-and-white model of an energy and logistics network with a docked cargo ship, solar panels, factories, office buildings, pipes, trucks, workers, and stacked materials.

Commodity Management & Trading

Transforming trading ecosystems through data-driven insights and secure, agile platforms that empower global commerce.

Isometric illustration of a bright modern office with glass meeting rooms, people working at desks, large data dashboards, presentation screens, plants, and studio lights.

Customer & Marketing Strategy

Reimagining customer engagement with personalized, connected experiences that build trust and long-term value.

Isometric 3D smart city model with white-blue buildings, cranes, power grids, map pins, and people using tablets around connected infrastructure platforms.

Digital Engineering

Turning ideas into scalable digital solutions—accelerating transformation through design, technology, and engineering excellence.

Isometric 3D model of a white-and-blue EV charging station with canopy, office buildings, small cars, delivery van, chargers, planters, and tiny people.

Station Studio

Redefining mobility hubs with digital innovation to create smarter, sustainable experiences for people and businesses on the move.

Isometric 3D logistics campus with white modern warehouses, blue-green accents, workers, delivery vans, a loading dock, and stacked shipping containers.

Supply Chain & Industry 5.0

Building resilient, intelligent supply networks that anticipate change and deliver efficiency with purpose.

White-and-blue sustainable campus with solar panels, a wind turbine, EV charging stations, loading dock trucks, trees, and small groups of people.

Sustainability

Driving responsible innovation to help organizations achieve net-zero goals and create a positive impact for future generations.

Isometric smart factory scene with white buildings, robotic arms on assembly lines, drones, autonomous carts, workers, control screens, and a fenced power substation connected by blue paths.

Physical AI

Physical AI gives machines, robots and physical operations the ability to perceive their environment, decide what matters and act in real time. Factories, plants, stores and infrastructure become systems able to sense conditions, learn from them and improve on their own, closing the gap between the physical and the digital world.

Isometric 3D smart infrastructure scene with white roads and buildings, blue data lines linking control rooms, vans, a rail crossing, drone, workers, and trees.

Next-Gen Infrastructure

From networks as infrastructure to connected platforms that enable critical, autonomous and intelligent operations.

Testudo: Security and Resilience through Advanced Robotics

Critical infrastructure has to detect and answer threats without putting people in harm's way. Testudo, a European-financed project, develops autonomous robotic solutions for monitoring, detection and response in sensitive environments. NTT DATA contributes robotic intelligence and automation, backed by its expertise in AI, computer vision and robotics.

Testudo: Security and Resilience through Advanced Robotics

Improving workplace safety with machine vision

On a warehouse floor, forklifts and people share the same aisles all day. A leading energy technology company needed safety monitoring able to scale, without the integration and maintenance costs of its legacy tools. NTT DATA built a modular, vendor-independent platform which combines real-time indoor positioning with computer vision to monitor people, machines and assets and alert the team as risks appear.

Improving workplace safety with machine vision

Contact

AI-Powered Video Situational Awareness Platform with Explainable Alerts

Most video analytics spot objects and stop there, and operators spend hours checking what each alert means. NTT DATA built a situational awareness platform on vision language models (VLMs) for clients in industry, public safety, corrections and energy and utilities. Users write monitoring rules in plain English, and every alert explains why the system raised the flag.

Operations specialists review explainable video alerts across industrial, public safety, corrections and energy environments.

Rule creation: Plain English

Users define monitoring logic without writing code.

Alerts: Explainable

Each alert describes the conditions behind the trigger.

New use cases: No retraining

New scenarios need new rules, not a new model.

Sectors: 4

Industrial, public safety, corrections, and energy and utilities.

AI-Powered Video Situational Awareness Platform with Explainable Alerts

Video monitoring with context

Objectives

Interpret video streams in context, adapt monitoring to different scenarios and give operators alerts they trust.

Opportunity

VLMs read scenes, objects, actions and interactions, so monitoring logic moves out of code and into everyday language.

Detection without context

Organizations across sectors watch complex environments in real time and need to respond fast when something critical happens. Traditional video analytics detect objects but miss behaviors and interactions. Teams close the gap by reviewing footage by hand.

Key Challenges

1: False positives. Alerts based on object detection alone fire without enough context.

2: Manual review. Operators confirm each alert by watching the footage.

3: Rigid rules. Defining or changing monitoring logic requires development work.

4: One scenario at a time. Each new use case calls for another model or more training.

Solution

A VLM platform driven by natural language rules

NTT DATA developed an AI-powered platform, built with Python and NVIDIA technology, to understand video streams in context and generate actionable, explainable alerts from rules written in natural language.

Natural language rules

Users describe what to watch in plain English, and the platform turns each description into detection logic.

Context-aware video understanding

The VLM interprets scenes, objects, actions and interactions within every stream. NTT DATA selects the model per site and task, with no lock-in to one AI vendor.

Explainable alerts

An alert fires only when its conditions are met and arrives with a short explanation of what the model saw.

Region and context customization

Rules apply to specific areas of the frame, and users add context wherever a scenario needs more detail.

Impact

Alerts operators believe and act on

Context understanding detects critical events more accurately, from fire and smoke at industrial sites to anomalous behavior in public spaces and violence in corrections facilities. Operators spend less time on manual monitoring, safety and risk mitigation improve across sites, and the platform scales to new use cases without retraining. Explainable alerting keeps the AI transparent, and the operator decides each response with the reason in front of them.

Drag