Postgraduate Diploma in Validation of Attention Systems with Computer Vision
800-hour online Postgraduate Diploma in validation of Attention Systems with Computer Vision. 8 modules with Delegated Regulation (EU) 2023/2590, Delegated Regulation (EU) 2021/1341 and OpenCV. Assigned tutor and open enrolment.
Postgraduate Diploma in Validation of Attention Systems with Computer Vision — studying from New Zealand
Autonomy and advanced driver assistance work in New Zealand is mostly applied rather than manufacturing-led, with significant interest in autonomous systems for agriculture, forestry, mining and port logistics. Research groups at the University of Auckland and the University of Canterbury contribute to robotics, perception and control, and firms in these regions develop software for driverless and remote-operated machinery. Engineers in this area often collaborate with government transport agencies on the regulatory frameworks that will govern automated vehicles on public roads.
Fees for New Zealand: NZ$2,160 (New Zealand dollar), with instalments and employer sponsorship available.
Relevant bodies in New Zealand
Typical roles
Questions from New Zealand
Which New Zealand bodies oversee autonomous and ADAS vehicle work, and how is engineering registration handled?
Engineering registration in New Zealand is handled by Engineering New Zealand, which offers Chartered Professional Engineer status. Land transport rules, including those affecting vehicle technology, are administered by NZ Transport Agency Waka Kotahi. SEIUM is a private institute and its qualifications are not state degrees or accredited by a national body, so recognition is ultimately a matter for employers or the relevant body.
Who employs autonomous vehicle and ADAS engineers in New Zealand?
Demand comes mainly from vehicle importers and fleet operators exploring driver assistance, software suppliers, research organisations and firms developing mobility or automation systems. Employers typically look for software, sensing and systems skills backed by project evidence. A private online qualification may help show your learning, but it does not guarantee a role or any particular salary.
Is this programme workable online from New Zealand with a full-time job?
Yes. The programmes are 100% online and taught in English, so you can study from New Zealand without needing a student visa. You will have an assigned technical tutor and complete a final project. Specialist courses run 300 hours, diplomas 800 hours and master's programmes 1,900 hours. Fees can be paid in instalments, and your employer may be willing to sponsor you.
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
Define measurable requirements for vision-based attention systems.
Build reliable ground truth for gaze and drowsiness.
Design diverse, privacy-compliant validation datasets.
Calculate metrics with confidence intervals and by subgroup.
Assess robustness against edge cases.
Run regulatory and consumer tests.
Maintain validation after model updates.
Who it's for
- Computer vision validation engineer who wants to specialise in Validation of Attention Systems with Computer Vision.
- DMS engineer who wants to specialise in Validation of Attention Systems with Computer Vision.
- Vision data scientist who wants to specialise in Validation of Attention Systems with Computer Vision.
- Annotation and ground truth specialist who wants to specialise in Validation of Attention Systems with Computer Vision.
- Type-approval engineer who wants to specialise in Validation of Attention Systems with Computer Vision.
- Algorithmic fairness analyst who wants to specialise in Validation of Attention Systems with Computer Vision.
- Engineering or science graduates looking to join car manufacturers.
What you'll work with
- Reglamento Delegado (UE) 2023/2590
- Reglamento Delegado (UE) 2021/1341
- ISO 15007
- ISO/IEC 19795-1
- Euro NCAP Safety Assist
- ISO/PAS 8800:2024
- IEC 62471
- Reglamento (UE) 2016/679
8 modules · 800 h
1.1Processing chain: capture, detection and estimation1.2Geometric models and appearance-based gaze models1.3Convolutional networks and transformers in the cabin1.4Operational definition of attention and distraction1.5Gaze zones and regions of interest1.6Required latency and frame rate1.7Sources of error in real environments1.8Functional requirements derived from regulation1.9System validation architecture1.10Case study: measurable requirements for a distraction detector
2.1Eye-tracking reference systems2.2Manual annotation of gaze zones according to ISO 150072.3Inter-annotator agreement and Cohen's kappa2.4Video and reference signal synchronisation2.5Drowsiness annotation with KSS and observers2.6Video annotation tools2.7Annotation quality control2.8Systematic reference errors2.9Annotation costs and scaling2.10Lab: gaze zone annotation with CVAT
3.1Participant sample design3.2Diversity of age, sex, ethnicity and physiognomy3.3Glasses, sunglasses and facial accessories3.4Lighting conditions: day, night and backlight3.5Vehicles, camera positions and seats3.6Public datasets: DMD and Drive&Act3.7Synthetic face data and its validity3.8Biometric data protection3.9Dataset management and versioning3.10Practice: participant sampling plan for a DMS
4.1Gaze accuracy in degrees4.2Confusion matrices by zone4.3False positive and false negative rates4.4ROC curves and threshold selection4.5Event detection latency4.6Event-level versus frame-level metrics4.7ISO/IEC 19795-1 methodology for biometrics4.8Confidence intervals and sample size4.9Subgroup metrics and fairness4.10Workshop: calculating per-event metrics with Python
5.1Infrared lighting variations5.2Partial facial occlusions5.3Extreme head movements5.4Vibration and blur5.5Driver changes during the journey5.6Out-of-distribution detection5.7Stress tests with synthetic perturbations5.8Controlled degradation and unavailable state5.9Robustness reports5.10Practice: robustness test battery with perturbations
6.1ADDW test procedures6.2DDAW test procedures6.3Euro NCAP distraction protocols6.4Standardised distraction scenarios6.5Track tests with real drivers6.6Driving simulator tests6.7Preparing type-approval documentation6.8Repeatability across laboratories6.9Experience from recent assessments6.10Case study: running a Euro NCAP distraction protocol
7.1Validation of new model versions7.2Automated regression tests7.3Field monitoring with privacy7.4Analysis of reported false alarms7.5ISO/PAS 8800 requirements for AI models7.6Change management after OTA updates7.7Fleet quality indicators7.8Periodic fairness audits7.9Dataset improvement7.10Lab: gaze model regression pipeline
8.1Defining measurable requirements8.2Ground truth plan8.3Validation set design8.4Metric selection8.5Robustness testing8.6Simulated regulatory test8.7Fairness analysis8.8Validation report8.9Thesis and presentation8.10Final review with the tutor
How you'll learn
Fully 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, making it possible to combine with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is OpenCV, PyTorch, CVAT, Tobii Pro Lab, Python with scikit-learn, in free, academic or evaluation versions. Tests are studied using real validation procedures for gaze estimation against reference, robustness tests with image perturbations, and distraction tests in simulator and on track. Assessment is continuous per module plus the final integrative project.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Define measurable requirements for vision-based attention systems.
Build reliable ground truth for gaze and drowsiness.
Design diverse, privacy-compliant validation datasets.
Calculate metrics with confidence intervals and by subgroup.
Assess robustness against edge cases.
Where this takes you
Requirements
- Prior technical training or professional experience in the sector. No university degree is required.
- Internet connection and a computer capable of running the programme's software.
- Sufficient English to follow technical regulatory texts.
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 consists of 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 course works with OpenCV, PyTorch, CVAT, Tobii Pro Lab, Python with scikit-learn. Free, academic or evaluation versions are used, and the tutor indicates the free alternative where one exists.
An own diploma from SEIUM upon passing the continuous assessment and the integrative project. It is in-house training, not an official Ministry qualification.
Yes. Modules passed in a course or diploma in the same area are credited towards the higher programme. Check the credit recognition policy when enrolling.
Related programmes
Postgraduate Diploma in HD Map Production/QA and Change Detection
Online 800-hour Postgraduate Diploma in HD Map Production/QA and Change Detection. 8 modules covering ASAM OpenDRIVE 1.8, ISO 19157-1:2023 and QGIS. Dedicated tutor and open enrolment.
Postgraduate Diploma in Perception in Unstructured Environments
Online 800 h Postgraduate Diploma in Perception in Unstructured Environments. 8 modules covering ISO 17757:2019, ISO 18497 and ROS 2. Assigned tutor and open enrolment.
Postgraduate Diploma in UDS/OBD Diagnostics, Health Monitoring and FOTA
Online 800-hour Postgraduate Diploma in UDS/OBD diagnostics, Health Monitoring and FOTA. 8 modules covering ISO 14229-1:2020, ISO 15765-2:2024 and Vector CANoe. Assigned tutor and open enrolment.
More in Autonomous, ADAS & Software-Defined Vehicle
All Autonomous, ADAS & Software-Defined Vehicle programmes → · How to apply · Fees & financing · Scholarships