Computer Vision
The planned outline of 20 modules. Lessons are written, run and reviewed before they are published.
Before this track
Planned outline
- Module 1
Start here: images, pixels and the CV toolbox
Coming soon - Module 2
How images are made: light, sensors and colour
Coming soon - Module 3
Filtering, edges and the frequency domain
Coming soon - Module 4
Thresholds, morphology, contours and classic segmentation
Coming soon - Module 5
Keypoints, descriptors and matching
Coming soon - Module 6
Geometric transforms, homographies and stitching
Coming soon - Module 7
Camera models, calibration and pose
Coming soon - Module 8
Two-view geometry, stereo and structure from motion
Coming soon - Module 9
Deep learning for images: CNNs and classification
Coming soon - Module 10
Vision transformers, self-supervised learning and foundation models
Coming soon - Module 11
Object detection
Coming soon - Module 12
Segmentation with deep learning
Coming soon - Module 13
Data, licences and responsible vision
Coming soon - Module 14
Video, motion and tracking
Coming soon - Module 15
Faces, people and pose, with privacy built in
Coming soon - Module 16
Text, documents and codes
Coming soon - Module 17
Restoration, generative models and synthetic media
Coming soon - Module 18
Optimising and deploying vision models
Coming soon - Module 19
Specialised imaging: satellites, medicine and industry
Coming soon - Module 20
End-to-end case studies
Coming soon
Official documentation
- onnxruntime.ai/docs (onnxruntime.ai)
- developers.google.com/edge/mediapipe/solutions/guide (developers.google.com)
- docs.pytorch.org/vision/stable/index.html (docs.pytorch.org)
More in AI and machine learning
- Machine Learning (scikit-learn) (coming soon)
- AI Literacy & Prompting (coming soon)
- Building LLM Applications (coming soon)
- Artificial Intelligence (classical AI and soft computing) (coming soon)
- All AI & ML tracks
- How we make lessons