Postgraduate Diploma in Multimodal Fusion and Cross-Calibration
Online 800-hour Postgraduate Diploma in Multimodal Fusion and Cross-Calibration. 8 modules covering ISO 26262:2018, ISO 21448:2022 (SOTIF) and ROS 2. Assigned tutor and open enrolment.
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.
What you will be able to do
Design sensor fusion architectures suited to the use case.
Extrinsically calibrate camera, LiDAR and radar.
Apply probabilistic fusion techniques.
Implement deep learning-based fusion models.
Manage temporal synchronisation between sensors.
Evaluate fusion systems using metrics and ablation studies.
Deploy fusion with functional safety criteria.
Who it's for
- Sensor fusion engineer looking to specialise in Multimodal Fusion and Cross-Calibration.
- Calibration engineer looking to specialise in Multimodal Fusion and Cross-Calibration.
- Perception engineer looking to specialise in Multimodal Fusion and Cross-Calibration.
- ADAS systems architect looking to specialise in Multimodal Fusion and Cross-Calibration.
- Researcher in multimodal learning looking to specialise in Multimodal Fusion and Cross-Calibration.
- Validation engineer looking to specialise in Multimodal Fusion and Cross-Calibration.
- Graduates in engineering or science seeking to enter the automotive sector.
What you'll work with
- ISO 26262:2018
- ISO 21448:2022 (SOTIF)
- ISO 23150:2023
- IEEE 802.1AS-2020
- IEEE 1588-2019
- ISO/PAS 8800:2024
- ISO 34502:2022
8 modules · 800 h
1.1Early, intermediate and late fusion1.2Centralised and distributed fusion1.3Complementarity of camera, radar and LiDAR1.4Measurement models and noise per sensor1.5Coordinate systems and transformations1.6Temporal synchronisation and timestamps1.7Latency requirements of fusion1.8Industry reference architectures1.9Standardised interfaces between sensor and fusion1.10Case study: architecture of an L2+ ADAS
2.1Camera–LiDAR calibration using targets2.2Target-less edge-based calibration2.3Radar–camera calibration2.4LiDAR–LiDAR calibration2.5Calibration with IMU and odometry2.6Propagation of calibration errors2.7Multisensor calibration graphs2.8Open-source calibration tools2.9Visual verification by reprojection2.10Laboratory: camera–LiDAR calibration with Autoware
3.1Multisensor Kalman filter3.2Track fusion and covariance intersection3.3Bayesian occupancy grids3.4Dempster–Shafer theory3.5Out-of-sequence measurements3.6Association between sensors3.7Object fusion under uncertainty3.8Filter consistency with NEES3.9Classification and existence fusion3.10Practical: fusion of radar and camera tracks
4.1Projection of LiDAR onto image4.2Bird's-eye view fusion: BEVFusion4.3TransFusion and cross-attention4.4Camera–radar fusion in BEV4.53D occupancy representations4.6Feature alignment across modalities4.7Robustness to loss of a sensor4.8Training with multimodal data4.9Temporal fusion across multiple frames4.10Laboratory: BEVFusion on nuScenes
5.1Clocks and PTP in the vehicle5.2IEEE 802.1AS and gPTP5.3Camera triggering synchronised with LiDAR5.4Latency compensation5.5State interpolation and extrapolation5.6Data logging with timestamps5.7Desynchronisation diagnostics5.8Impact on fusion accuracy5.9GNSS synchronisation as reference5.10Practical: analysis of time offsets
6.1Detection and tracking metrics6.2Per-sensor and joint evaluation6.3Modality ablation6.4Critical scenarios and edge cases6.5Sensitivity to calibration errors6.6Computational cost and memory6.7Simulation-based evaluation6.8Reference multimodal datasets6.9Error analysis by distance6.10Case study: evaluation report of a fusion system
7.1ISO 26262 requirements for fusion7.2SOTIF limitations due to discrepancies7.3Cross-sensor plausibility7.4In-service recalibration7.5Deployment on automotive SoC7.6Quantisation and optimisation7.7Traceability of calibration versions7.8Fleet validation7.9Sensor degradation management7.10Workshop: designing a plausibility monitor
8.1Sensor and dataset selection8.2Extrinsic calibration of the set8.3Synchronisation and temporal alignment8.4Proposed fusion architecture8.5Implementation and training8.6Evaluation and ablations8.7Robustness analysis8.8Safety considerations8.9Report and presentation8.10Final review with the tutor
How you'll learn
> 100% online training on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. No fixed timetables: students progress at their own pace within the intake, which makes it possible to combine study with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is ROS 2, Autoware, PyTorch, MMDetection3D, MATLAB Sensor Fusion and Tracking Toolbox, in free, academic or evaluation versions. Studies are based on real extrinsic camera–LiDAR calibration procedures, BEV fusion on nuScenes, and desynchronisation analysis on an instrumented vehicle. Assessment is continuous per module plus the final integrating project.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Design sensor fusion architectures suited to the use case.
Extrinsically calibrate camera, LiDAR and radar.
Apply probabilistic fusion techniques.
Implement deep learning-based fusion models.
Manage temporal synchronisation between sensors.
Where this takes you
Requirements
- Prior technical training or professional experience in the sector. A university degree is not required.
- Internet connection and a computer capable of running the programme's software.
- Sufficient level of Spanish to follow technical standards documentation.
Ready to start?
Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.
Frequently asked questions
The programme comprises 800 hours in total, spread over 6 to 8 months. That is between 10 and 15 hours per week on average, compatible with a full-time job.
The programme uses ROS 2, Autoware, PyTorch, MMDetection3D, MATLAB Sensor Fusion and Tracking Toolbox. Free, academic or evaluation versions are used, and the tutor indicates the free alternative where one exists.
An SEIUM Institute diploma of its own upon passing the continuous assessment and the integrating project. It is in-house training, not an official title issued by the Ministry.
Yes. Modules passed in a course or postgraduate diploma in the same area can be recognised towards the advanced programme. Check the recognition policy when enrolling.
Related programmes
Postgraduate Diploma in Edge Analytics for Predictive Maintenance
Online 800-hour Postgraduate Diploma in Edge Analytics for Predictive Maintenance. 8 modules with ISO 13374-1, ISO 17359:2018 and Eclipse Kuksa. Assigned tutor and open enrolment.
Postgraduate Diploma in Traffic Behaviour and Social Interaction Models
800-hour online Postgraduate Diploma in Traffic Behaviour and Social Interaction Models. 8 modules covering SAE J3016:2021, ISO 21448:2022 (SOTIF) and SUMO. Personal tutor assigned and enrolment…
Postgraduate Diploma in HRI for Remote Assistance and Regulatory Frameworks
Online 800-hour Postgraduate Diploma in HRI for Remote Assistance and Regulatory Frameworks. 8 modules covering Regulation (EU) 2022/1426, Regulation (EU) 2024/1689 and Figma. Assigned tutor and…
More in Autonomous, ADAS & Software-Defined Vehicle
All Autonomous, ADAS & Software-Defined Vehicle programmes → · How to apply · Fees & financing · Scholarships