UAV Visual Navigation Course
Online course of 300 hours in visual navigation for UAVs: 6 modules covering computer vision for navigation, visual odometry, visual SLAM, perception for guidance, and integration and validation, with an assigned technical tutor.
UAV Visual Navigation Course — studying from South Africa
South Africa has a long-standing aerospace base, anchored by the Western Cape cluster around Cape Town and the Gauteng aerospace corridor near Johannesburg. Companies such as Denel Aerospace Systems, Aerosud and Airbus-linked suppliers in the Western Cape draw on local engineering talent. The South African Civil Aviation Authority oversees airworthiness and drone regulation, while the South African National Space Agency coordinates national space activity. Demand for skills in aircraft systems, unmanned aerial systems and satellite engineering continues to grow across both regions.
Fees for South Africa: R 14 900 (South African rand), with instalments and employer sponsorship available.
Relevant bodies in South Africa
Typical roles
Questions from South Africa
Will a SEIUM qualification be recognised by the South African Council for Aeronautical and Engineering Professions or ECSA?
SEIUM is a private online institute and its qualifications are not official state degrees or accredited by a national body. In South Africa, professional registration is handled by bodies such as ECSA (Engineering Council of South Africa) and SACAP for built environment roles, and aviation licensing by the SACAA. Recognition of a private qualification is decided by the employer or the relevant body, so check directly with them before enrolling.
Would this qualification help me get work with aerospace or drone employers in South Africa?
Employers in South Africa's aerospace and drone sector, such as aircraft maintenance organisations, defence contractors and drone operators, usually weigh experience, licensing and university credentials heavily. A private online qualification can support your CV and show specialist knowledge, but it does not guarantee hiring or a particular role. Ask prospective employers whether they value the programme before you commit.
Can I manage the workload while working full time, and do I need to be fluent in English?
The programme is 100% online and taught in English, so you need solid working English. Study is fully remote, so no student visa is needed to study from home. Master's programmes total 1,900 hours, postgraduate diplomas 800 hours and specialist courses 300 hours, with an assigned technical tutor. Plan your weekly hours realistically, and ask whether employer sponsorship or instalment payment could help with fees.
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
Calibrate cameras and camera-IMU systems.
Implement visual and inertial odometry algorithms.
Apply visual SLAM techniques in GNSS-denied environments.
Develop perception functions for guidance and landing.
Integrate visual estimators with commercial autopilots.
Assess accuracy using trajectory metrics.
Analyse the limitations and certification of vision-based systems.
Who it's for
- Computer vision engineers.
- SLAM developers.
- Robotic perception engineers.
- Autonomous navigation researchers.
- Embedded systems integrators working on on-board computing.
- Autonomy test engineers.
- Engineering or science graduates seeking to enter robotics.
What you'll work with
- Delegated Regulation (EU) 2019/945 (UAS product requirements)
- Implementing Regulation (EU) 2019/947 (rules and procedures for UAS operations)
- EASA Concept Paper for Level 1 & 2 Machine Learning Applications (EASA guidance for machine learning in aviation)
- ISO/PAS 21448 (SOTIF) (safety of the intended functionality)
- ASTM F3269 (run-time assurance of complex functions in UAS)
- RTCA DO-178C (software considerations in airborne systems)
- OpenCV
- ROS 2
- ORB-SLAM3
- Kalibr
- Gazebo
6 modules
1.1Pinhole camera model1.2Intrinsic calibration and distortion1.3Camera-IMU calibration1.4Epipolar geometry1.5Feature detectors: FAST, ORB and SIFT1.6Matching and RANSAC1.7Lucas-Kanade optical flow1.8Stereo cameras and depth1.9Event cameras1.10Lab: camera calibration with Kalibr
2.1Motion estimation between frames2.2Direct and feature-based methods2.3Stereo and monocular visual odometry2.4The scale problem2.5Visual-inertial odometry2.6IMU measurement preintegration2.7MSCKF filters2.8Sliding-window optimisation2.9VINS-Mono and OpenVINS algorithms2.10Practical exercise: visual-inertial odometry with EuRoC datasets
3.1Formulation of the SLAM problem3.2Point maps and dense maps3.3ORB-SLAM33.4Loop closure and relocalisation3.5Pose graph optimisation3.6Occupancy maps and OctoMap3.7LiDAR and camera SLAM3.8Indoor navigation without GNSS3.9Drift errors and their correction3.10Workshop: running ORB-SLAM3 in ROS 2
4.1Marker-based landing4.2Visual target tracking4.3Obstacle detection with stereo4.4Semantic segmentation for landing zones4.5Neural networks on board4.6Navigation based on georeferenced maps4.7Image correlation with orthophotos4.8Visual servo control4.9Latency and performance evaluation4.10Lab: visual servo control in Gazebo
5.1On-board computers and GPU acceleration5.2Integration with PX4 via external vision5.3ROS 2 and uXRCE-DDS interfaces5.4Hardware sensor synchronisation5.5ATE and RPE metrics5.6Indoor tests with motion capture5.7Adverse conditions: low light and poor textures5.8Functional safety of perception5.9Certification of learning-based systems5.10Case study: autonomous inspection inside a tank
6.1Defining a GNSS-denied scenario6.2Sensor selection6.3System calibration6.4Estimator implementation6.5Integration with the autopilot6.6Simulation tests6.7Accuracy evaluation6.8Failure analysis6.9Report and presentation6.10Final project: final review with your tutor
How you'll learn
Training is 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 the intake, making it compatible with work.
Each module combines theory, guided reading of the original standards and applied exercises. The working software is OpenCV, ROS 2, ORB-SLAM3, Kalibr and Gazebo, in free, academic or evaluation versions. Exercises are based on real procedures for evaluating odometry with public datasets, indoor flights with motion capture and vision-based landing tests. Assessment is continuous by module, plus the final capstone project.
Standards covered: Delegated Regulation (EU) 2019/945, Implementing Regulation (EU) 2019/947, EASA Concept Paper for Level 1 & 2 Machine Learning Applications, ISO/PAS 21448 (SOTIF), ASTM F3269, RTCA DO-178C.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Where this takes you
Requirements
- No prior qualification is required.
- An 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.
Frequently asked questions
The programme totals 300 hours over 3 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.
You work with OpenCV, ROS 2, ORB-SLAM3, Kalibr and Gazebo, using free, academic or evaluation versions. Your tutor indicates the free alternative wherever one exists.
A SEIUM Institute certificate, awarded on passing the continuous assessment and the final project. 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 are recognised in a higher programme in the same area (postgraduate diploma or master's). Ask about the recognition policy when you enrol.
No prior qualification is required; you need an internet connection, a computer able to run the programme 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.
Related programmes
Preventive maintenance course for helicopters
Online course of 300 hours in helicopter preventive maintenance. 6 modules covering the maintenance regulatory framework, scheduled inspections, transmission and dynamic systems, condition monitoring and HUMS,…
Synthetic data generation course
Online course of 300 hours in synthetic data generation. 6 modules covering synthetic data in aerospace engineering, physics-based simulation, generative models, data quality and validation, and…
Course in the Future of Aerospace Simulation
Online course of 300 hours in the future of aerospace simulation, with 6 modules covering the state of the art, digital twins, surrogate models and machine…
More in Aerospace, UAM, Drones & Space
All Aerospace, UAM, Drones & Space programmes → · How to apply · Fees & financing · Scholarships