Apply now
Master'sData, AI, Simulation & Analytics Applications open

Master’s in Multimodality (Video, IMU, Radar, Technical Text)

Online master's programme of 1,900 hours in multimodal AI for engineering: fusion and cross-learning from video, IMU, radar and technical text. 12 modules covering multimodal data, computer vision, inertial sensors, radar and point clouds, technical text processing, multisensor calibration, sensor fusion, multimodal foundation models, edge deployment, reliability and regulation, and industrial applications, with an assigned technical tutor.

Duration12–14 months
ModeOnline
LanguageEnglish
Start datesSet by the faculty
AwardSEIUM Institute diploma
Enrol now View syllabus Ask an advisor
Virtual lab · try it before you enrol

Take the controls.

Run a real engineering trade-off from this field. Move the sliders, watch the model react in real time and beat the challenge.

SIM · LIVE ●
Learning outcomes

What you will be able to do

01

Characterise video, IMU, radar and technical text data.

02

Develop computer vision models.

03

Process inertial and radar signals.

04

Apply language models to technical documentation.

05

Calibrate, synchronise and fuse sensors.

06

Adapt multimodal foundation models.

07

Deploy reliable systems that comply with regulation.

Profile

Who it's for

  • Multimodal AI engineers.
  • Perception engineers in automotive and robotics.
  • Sensor fusion specialists.
  • Industrial data scientists working with heterogeneous data.
  • Computer vision engineers moving into multisensor systems.
  • Embedded AI engineers.
  • Engineering or science graduates looking to enter the automotive sector.
Standards & tools

What you'll work with

  • ISO 26262 (road vehicle functional safety)
  • ISO 21448 (safety of the intended functionality, SOTIF)
  • IEEE 1588 (Precision Time Protocol)
  • ISO/IEC 22989 (AI concepts and terminology)
  • ISO/IEC 23053 (framework for AI systems using machine learning)
  • ISO/IEC 42001 (AI management systems)
  • Regulation (EU) 2024/1689 (Artificial Intelligence Act)
  • ISO 8855 (vehicle dynamics and coordinate systems)
  • PyTorch
  • ROS 2
  • OpenCV
  • Hugging Face Transformers
  • MATLAB Sensor Fusion and Tracking Toolbox
Syllabus

12 modules

  1. 1.1The concept of multimodality
  2. 1.2Video, IMU, radar and text
  3. 1.3Applications in vehicles and robotics
  4. 1.4Multimodal industrial inspection
  5. 1.5Maintenance with heterogeneous data
  6. 1.6Technical documentation as a source
  7. 1.7Alignment and scale challenges
  8. 1.8State of the art
  9. 1.9AI ethics and regulation
  10. 1.10Case study: infrastructure inspection with multiple sensors
  1. 2.1Image formation and cameras
  2. 2.2Intrinsic and extrinsic calibration
  3. 2.3Convolutional networks
  4. 2.4Object detection
  5. 2.5Semantic segmentation
  6. 2.6Video tracking
  7. 2.7Vision transformers
  8. 2.8Optical flow and motion
  9. 2.9Data augmentation
  10. 2.10Lab: defect detector with PyTorch
  1. 3.1MEMS accelerometers and gyroscopes
  2. 3.2IMU error models
  3. 3.3IMU calibration
  4. 3.4Integration and drift
  5. 3.5Orientation estimation
  6. 3.6Activity recognition
  7. 3.7Visual-inertial odometry
  8. 3.8Vibration and diagnostics
  9. 3.9Networks for time series
  10. 3.10Practical exercise: orientation estimation with a complementary filter
  1. 4.1FMCW radar principles
  2. 4.2Range, velocity and angle processing
  3. 4.3Radar point clouds
  4. 4.44D imaging radar
  5. 4.5LiDAR and comparison with radar
  6. 4.6Networks for point clouds
  7. 4.7Detection in adverse conditions
  8. 4.8Micro-Doppler
  9. 4.9Public datasets
  10. 4.10Lab: processing data from an FMCW radar
  1. 5.1Text representations
  2. 5.2Language models
  3. 5.3Information extraction from manuals
  4. 5.4Technical named entity recognition
  5. 5.5Classification of incident reports
  6. 5.6Semantic search
  7. 5.7Retrieval-augmented generation
  8. 5.8Technical ontologies
  9. 5.9Evaluation of language models
  10. 5.10Practical exercise: semantic search engine for technical documentation
  1. 6.1Time synchronisation
  2. 6.2Precision Time Protocol
  3. 6.3Camera-radar calibration
  4. 6.4Camera-IMU calibration
  5. 6.5Coordinate systems
  6. 6.6Multisensor data logging
  7. 6.7Formats and storage
  8. 6.8Labelling tools
  9. 6.9Dataset quality
  10. 6.10Lab: camera-radar calibration
  1. 7.1Early, intermediate and late fusion
  2. 7.2Kalman filters
  3. 7.3Probabilistic fusion
  4. 7.4Fusion with neural networks
  5. 7.5Cross-attention mechanisms
  6. 7.6Unified bird's-eye view
  7. 7.7Handling degraded sensors
  8. 7.8Uncertainty in fusion
  9. 7.9Performance evaluation
  10. 7.10Practical exercise: camera-radar fusion for detection
  1. 8.1Contrastive learning
  2. 8.2Vision-language models
  3. 8.3Models for time series
  4. 8.4Adaptation to technical domains
  5. 8.5Efficient fine-tuning
  6. 8.6Few-shot learning
  7. 8.7Generating technical descriptions
  8. 8.8Multimodal agents
  9. 8.9Limitations and hallucinations
  10. 8.10Lab: fine-tuning a vision-language model
  1. 9.1Embedded hardware for AI
  2. 9.2Quantisation and pruning
  3. 9.3Accelerated inference
  4. 9.4Pipelines in ROS 2
  5. 9.5Latency and determinism
  6. 9.6Energy consumption
  7. 9.7Model updates
  8. 9.8Monitoring in operation
  9. 9.9Robustness testing
  10. 9.10Practical exercise: deployment on an embedded board
  1. 10.1Functional safety and perception
  2. 10.2Safety of the intended functionality
  3. 10.3Robustness against adversarial attacks
  4. 10.4Multimodal explainability
  5. 10.5Handling personal data in video
  6. 10.6European AI Act
  7. 10.7AI management systems
  8. 10.8Model and data documentation
  9. 10.9Auditing and traceability
  10. 10.10Case study: risk analysis of a perception system
  1. 11.1Autonomous vehicles
  2. 11.2Mobile robotics
  3. 11.3Infrastructure inspection with drones
  4. 11.4Predictive maintenance
  5. 11.5Occupational safety with vision
  6. 11.6Technical assistants for maintenance
  7. 11.7Railways and track monitoring
  8. 11.8Precision agriculture
  9. 11.9AI project management
  10. 11.10Case study: multimodal assistant for field technicians
  1. 12.1Problem definition
  2. 12.2State of the art
  3. 12.3Data acquisition
  4. 12.4Calibration and synchronisation
  5. 12.5Model architecture
  6. 12.6Training and evaluation
  7. 12.7Deployment and robustness
  8. 12.8Conclusions
  9. 12.9Thesis report
  10. 12.10Master's Thesis: defence before a panel
Methodology, software & labs

How you'll learn

The programme is delivered 100% online on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. There are no fixed timetables: you progress at your own pace within each intake, so it fits around your job.

Each module combines theory, guided reading of the original standard and applied exercises. The working software is PyTorch, ROS 2, OpenCV, Hugging Face Transformers and MATLAB Sensor Fusion and Tracking Toolbox, in free, academic or evaluation versions. Exercises are based on real procedures: multisensor calibration and synchronisation, camera-radar fusion for detection and model deployment on embedded hardware. Assessment is continuous by module, plus the final Master's Thesis.

Standards covered: ISO 26262, ISO 21448, IEEE 1588, ISO/IEC 22989, ISO/IEC 23053, ISO/IEC 42001, Regulation (EU) 2024/1689, ISO 8855.

Assigned technical tutor:every module ends with a deliverable that your tutor marks individually.
Standards-based learning:guided reading of ISO 26262, ISO 21448 and IEEE 1588 applied to real cases, not as a theoretical annex.
Industry software:PyTorch, ROS 2, OpenCV, Hugging Face Transformers and MATLAB Sensor Fusion and Tracking Toolbox, in free, academic or evaluation versions.
Master's Thesis with defence:a complete multimodal perception system, from data acquisition and calibration to robust deployment, defended before a panel.
Flexible format:100% online, no fixed timetables, compatible with full-time work.
Capstone project

Build it end to end

Your final project follows the real engineering workflow, step by step, reviewed by your tutor.

Vision defect detector
Train a defect detection model with PyTorch.
Camera-radar calibration
Calibrate and synchronise a camera-radar rig.
Sensor fusion for detection
Fuse camera and radar data to improve object detection.
Edge deployment
Deploy the model on an embedded board and test its robustness.
Master's Thesis
Develop a complete multimodal system from acquisition to deployment, defended before a panel.
Career opportunities

Where this takes you

Multimodal AI engineerPerception engineerSensor fusion specialistIndustrial data scientistComputer vision engineerEmbedded AI engineer
Admissions & scholarships

Requirements

  • University degree in engineering, science or architecture, or equivalent demonstrable professional experience.
  • Internet connection and a computer capable of running the programme software.
  • English sufficient to read technical standards.

Ready to start?

Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.

Apply now Scholarships
FAQ

Frequently asked questions

The programme totals 1,900 hours over 12–14 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.

You work with PyTorch, ROS 2, OpenCV, Hugging Face Transformers and MATLAB Sensor Fusion and Tracking Toolbox, using free, academic or evaluation versions. Your tutor indicates the free alternative wherever one exists.

A SEIUM Institute diploma, awarded on passing the continuous assessment and the Master's Thesis. It is SEIUM's own qualification, not an official state degree; its recognition depends on the programme completed and the regulations of each country.

Yes. Modules passed in a course or postgraduate diploma in the same area are recognised in the higher programme. Ask about the recognition policy when you enrol.

A university degree in engineering, science or architecture (or equivalent professional experience), a suitable computer and English sufficient to read technical standards.

Start dates are set by SEIUM's faculty for each intake. Our admissions team will confirm the next available date when you apply.

Keep exploring

Related programmes

See all in Data, AI, Simulation & Analytics
Master's8,850 $

Master’s in Time Series, Signals and Anomaly Detection

Online master's programme of 1,900 hours in time series, signals and anomaly detection: sensors, spectra, forecasting and root cause analysis. 12 modules covering digital signal processing,…

12–14 monthsOnlineData, AI, Simulation & Analytics
Master's11,090 $

Master’s in Model Verification, Validation and UQ Engineering

Online master's programme of 1,900 hours in model verification, validation and uncertainty quantification (UQ) engineering. 12 modules covering model credibility, code and solution verification, uncertainty propagation,…

1900 hOnlineData, AI, Simulation & Analytics
Master's9,970 $

Master’s in Factory and Supply Chain Digital Twins Engineering — Discrete-Event Simulation, WIP/OEE and What-If

Online master's programme of 1,900 hours in factory and supply chain digital twin engineering, with discrete-event simulation, WIP/OEE and what-if analysis. 12 modules covering discrete-event simulation,…

1900 hOnlineData, AI, Simulation & Analytics
Master’s in Multimodality (Video, IMU, Radar, Technical Text)Enrol
Related programmes

More in Data, AI, Simulation & Analytics

Master’s in Time Series, Signals and Edge AI EngineeringView programme →Master’s in Optimisation, Operations Research and Decision EngineeringView programme →Master’s in Graph ML Engineering for Networks and SystemsView programme →Master’s in Simulation, Co-Simulation and HPC EngineeringView programme →Master’s in Data Products and Visualisation EngineeringView programme →Master’s in Causality and Experimentation EngineeringView programme →

All Data, AI, Simulation & Analytics programmes → · How to apply · Fees & financing · Scholarships

Scroll to Top
SEIUM – Institute of Advanced Engineering
Powered by  GDPR Cookie Compliance
Privacy Overview

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.