Apply now
Master'sAutonomous, ADAS & Software-Defined Vehicle Applications open

Master’s in Perception & Sensors Engineering

Online master's programme of 1,900 hours in perception and sensors engineering. 12 modules covering perception for automated vehicles, cameras and computer vision, automotive radar, LiDAR, ultrasonic and proximity sensors, sensor fusion, deep learning perception, hardware and processing, perception safety, validation and regulation, with an assigned technical tutor.

Duration1900 h
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

Analyse the sensor technologies used in automated vehicles.

02

Apply computer vision techniques to driving.

03

Process radar and LiDAR data for object detection.

04

Design sensor fusion architectures.

05

Train and deploy deep learning perception models.

06

Assess perception safety in line with ISO 26262 and SOTIF.

07

Develop a complete perception system.

Profile

Who it's for

  • Perception engineers.
  • Sensor fusion engineers.
  • Computer vision engineers.
  • ADAS validation engineers.
  • Deep learning engineers applying their work to driving.
  • Sensor systems architects.
  • Engineering or science graduates seeking to enter the automotive sector.
Standards & tools

What you'll work with

  • SAE J3016 (levels of driving automation)
  • ISO 26262 (road vehicle functional safety)
  • ISO 21448 (SOTIF, safety of the intended functionality)
  • Regulation (EU) 2019/2144 (General Safety Regulation)
  • UN ECE R152 (advanced emergency braking systems)
  • UN ECE R157 (automated lane keeping systems)
  • IEC 60825-1 (laser product safety)
  • ISO 34502 (scenario-based safety evaluation)
  • ROS 2
  • PyTorch
  • OpenCV
  • Point Cloud Library
  • NVIDIA DriveWorks
Syllabus

12 modules · 1900 h

  1. 1.1Levels of automation under SAE J3016
  2. 1.2The perception, prediction and planning chain
  3. 1.3Perception requirements by ADAS function
  4. 1.4Centralised and distributed architectures
  5. 1.5Sensors in production vehicles
  6. 1.6Environment representation and world model
  7. 1.7Perception performance metrics
  8. 1.8Open challenges in perception
  9. 1.9Documented failure cases
  10. 1.10Case study: analysis of a commercial sensor suite
  1. 2.1CMOS sensors and HDR dynamic range
  2. 2.2Optics, distortion and field of view
  3. 2.3ISP image processing
  4. 2.4Lane and traffic sign detection
  5. 2.5Object detection with CNNs
  6. 2.6Semantic and instance segmentation
  7. 2.7Monocular depth estimation
  8. 2.8Stereo vision and disparity
  9. 2.9Surround-view cameras and bird's-eye view
  10. 2.10Lab: YOLO detector on a driving dataset
  1. 3.1FMCW principle and 77 GHz bands
  2. 3.2Range and velocity resolution
  3. 3.3MIMO arrays and angular resolution
  4. 3.44D imaging radar
  5. 3.5Processing the detection point cloud
  6. 3.6Object classification with radar
  7. 3.7Interference between radars
  8. 3.8Integration behind the bumper
  9. 3.9Advantages in rain and fog
  10. 3.10Practical exercise: radar data processing in Python
  1. 4.1Time-of-flight principle
  2. 4.2Mechanical, MEMS and flash LiDAR
  3. 4.3Coherent FMCW LiDAR
  4. 4.4905 and 1550 nm wavelengths
  5. 4.5Point clouds and density
  6. 4.6Object detection in point clouds
  7. 4.7Eye safety to IEC 60825
  8. 4.8Cost and integration in production
  9. 4.9Limitations in rain and dust
  10. 4.10Workshop: point cloud segmentation with PCL
  1. 5.1Ultrasonic parking sensors
  2. 5.2Echolocation and range
  3. 5.3Fusion for automated parking
  4. 5.4Interior occupancy sensors
  5. 5.5Short-range radar
  6. 5.6Blind-spot detection
  7. 5.7Cross-traffic alert
  8. 5.8Limitations of near-field sensors
  9. 5.9Calibration of parking sensors
  10. 5.10Practical exercise: parking assistant logic
  1. 6.1Early, intermediate and late fusion
  2. 6.2The Kalman filter and its variants
  3. 6.3Multi-object tracking in the environment
  4. 6.4Data association and JPDA
  5. 6.5Occupancy grids
  6. 6.6Bird's-eye-view (BEV) fusion
  7. 6.7Fusion with neural networks
  8. 6.8Uncertainty management
  9. 6.9Sensor time synchronisation
  10. 6.10Lab: tracking with an extended Kalman filter
  1. 7.1CNN and transformer architectures
  2. 7.23D detection with PointPillars
  3. 7.3BEVFormer and BEVFusion models
  4. 7.43D occupancy networks
  5. 7.5KITTI, nuScenes and Waymo datasets
  6. 7.6Data labelling and annotation
  7. 7.7Data augmentation
  8. 7.8Quantisation for deployment
  9. 7.9mAP and NDS metrics
  10. 7.10Practical exercise: training a 3D detector
  1. 8.1Automotive SoCs for perception
  2. 8.2GPUs and neural accelerators
  3. 8.3Latency requirements
  4. 8.4Sensor bandwidth
  5. 8.5GMSL and automotive Ethernet interfaces
  6. 8.6Power consumption and thermal management
  7. 8.7Optimisation with TensorRT
  8. 8.8AEC-Q100 component qualification
  9. 8.9Zonal compute architecture
  10. 8.10Workshop: inference optimisation on Jetson
  1. 9.1ISO 26262 functional safety in sensors
  2. 9.2SOTIF and perception insufficiencies
  3. 9.3Triggering conditions and failure conditions
  4. 9.4Sensor redundancy and diversity
  5. 9.5Plausibility monitoring
  6. 9.6Robustness against adversarial attacks
  7. 9.7Sensor cybersecurity
  8. 9.8Degradation and safe states
  9. 9.9Safety argumentation
  10. 9.10Case study: SOTIF analysis of a front camera
  1. 10.1Ground truth and reference
  2. 10.2Metrics by class and distance
  3. 10.3On-road validation
  4. 10.4Validation in simulation
  5. 10.5Re-injection of recorded data
  6. 10.6Scenario coverage
  7. 10.7Track testing
  8. 10.8False positive analysis
  9. 10.9Validation reports
  10. 10.10Lab: evaluation with nuScenes metrics
  1. 11.1General Safety Regulation 2019/2144
  2. 11.2Emergency braking (R152)
  3. 11.3Lane keeping system (R79)
  4. 11.4ALKS under R157
  5. 11.5Euro NCAP protocols
  6. 11.6NHTSA requirements
  7. 11.7The ISO 34502 standard
  8. 11.8Type approval of perception systems
  9. 11.9Regulatory trends in perception
  10. 11.10Practical exercise: AEB requirements matrix
  1. 12.1Defining the function and ODD
  2. 12.2Selecting the sensor suite
  3. 12.3Designing the fusion architecture
  4. 12.4Developing detection models
  5. 12.5Integration on the compute platform
  6. 12.6Safety analysis
  7. 12.7Validation plan
  8. 12.8Results and conclusions
  9. 12.9Master's Thesis report
  10. 12.10Master's Thesis: defence before a panel
Methodology, software & labs

How you'll learn

Training is 100% online on the SEIUM campus, with downloadable materials, 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 ROS 2, PyTorch, OpenCV, Point Cloud Library and NVIDIA DriveWorks, in free, academic or evaluation versions. Testing is studied through real procedures for evaluating detectors on public datasets, track validation of ADAS functions and re-injection of recorded data. Assessment is continuous by module, plus the final Master's Thesis.

Standards covered: SAE J3016, ISO 26262, ISO 21448, Regulation (EU) 2019/2144, UN ECE R152, UN ECE R157, IEC 60825-1, ISO 34502.

Assigned technical tutor:every module ends with a deliverable that your tutor marks individually.
Standards-based learning:guided reading of SAE J3016, ISO 26262 and ISO 21448 applied to real cases, not as a theoretical annex.
Industry software:ROS 2, PyTorch, OpenCV, Point Cloud Library, NVIDIA DriveWorks, in free, academic or evaluation versions.
Master's Thesis with defence:A complete perception system project covering sensor suite selection, fusion architecture, detection models, compute integration, safety analysis and validation plan, 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.

Function and sensor suite
Define the function and ODD and select the sensor suite.
Fusion architecture
Design the sensor fusion and tracking architecture.
Detection models
Develop and train the detection models and integrate them on the compute platform.
Safety and validation
Carry out the safety analysis and prepare the validation plan.
Master's Thesis
A complete perception system with results and conclusions, defended before a panel.
Career opportunities

Where this takes you

Perception engineerSensor fusion engineerComputer vision engineerADAS validation engineerDeep learning engineerSensor systems architect
Admissions & scholarships

Requirements

  • A university degree in engineering, science or architecture, or equivalent demonstrable professional experience.
  • An internet connection and a computer capable of running the programme's 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 ROS 2, PyTorch, OpenCV, Point Cloud Library, NVIDIA DriveWorks, 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 degree in engineering, science or architecture (or equivalent professional experience), a computer able to run the software, 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 Autonomous, ADAS & Software-Defined Vehicle
Master's11,090 $

Master’s in Autonomous Urban Buses and Shuttles Engineering

Online master's programme of 1,900 hours in urban autonomous bus and shuttle engineering: 12 modules covering vehicle platforms, urban perception and localisation, bus planning and control,…

1900 hOnlineAutonomous, ADAS & Software-Defined Vehicle
Master's6,610 $

Master’s in Traffic and Proving Ground Digital Twins Engineering

Online master's programme of 1,900 hours in traffic and test track digital twin engineering, structured in 12 modules covering environment reconstruction, microscopic and real-time traffic modelling,…

1900 hOnlineAutonomous, ADAS & Software-Defined Vehicle
Master's9,970 $

Master’s in Functional Safety, Cyber and Compliance Engineering

Online master's programme of 1,900 hours in functional safety, cybersecurity and compliance engineering, structured in 12 modules covering ISO 26262, SOTIF under ISO 21448, cybersecurity under…

1900 hOnlineAutonomous, ADAS & Software-Defined Vehicle
Master’s in Perception & Sensors EngineeringEnrol
Related programmes

More in Autonomous, ADAS & Software-Defined Vehicle

Master’s in Autonomous Last-Mile Logistics EngineeringView programme →Master’s in Product, Regulation & Business EngineeringView programme →Master’s in RTOS and Hypervisor Engineering in Automotive — Partitioning, Isolation and Mixed CriticalityView programme →Master’s in Specific Verticals and ODDs EngineeringView programme →Master’s in Human Factors & HMI EngineeringView programme →Master’s in AUTOSAR Adaptive, ROS 2 and DDS Engineering — Middleware Design, QoS and DiscoveryView programme →

All Autonomous, ADAS & Software-Defined Vehicle 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.