CTU-AI321.AU1
Computer Vision: Algorithms and Applications
- Practice in 30 Hands-On Labs — nothing to install
- 8 Interactive Lessons and 78 topics mapped to the official exam objectives
Intermediate Self-paced · 1 year access
30 Hands-On LiveLabs
Practice real IT tasks in guided environments.
- Real environments
- Auto-graded
- No installation
8Interactive Lessons
78Topics
30LiveLab
7Videos
92Flashcards
92Glossary of terms
01 / Lessons & labs
See exactly what you will learn and practice
Lessons
8 Interactive Lessons · 78 topics01 Foundations of Computer Vision 11 topics · 4 LiveLab +
- What is computer vision?
- A brief history
- Geometric primitives and transformations
- Photometric image formation
- The digital camera
- Point operators
- Linear filtering
- More neighborhood operators
- Fourier transforms
- Pyramids and wavelets
- Geometric transformations
4 LiveLab in this lesson — see the labs panel →
02 Visual Recognition Models 16 topics · 12 LiveLab +
- Supervised learning
- Unsupervised learning
- Deep neural networks
- Convolutional neural networks
- More complex models
- Instance recognition
- Image classification
- Object detection
- Semantic segmentation
- Video understanding
- Vision and language
- Points and patches
- Edges and contours
- Contour tracking
- Lines and vanishing points
- Segmentation
12 LiveLab in this lesson — see the labs panel →
03 Machine Learning for Vision Tasks 13 topics · 3 LiveLab +
- Shape from X
- 3D scanning
- Surface representations
- Point-based representations
- Volumetric representations
- Model-based reconstruction
- Recovering texture maps and albedos
- View interpolation
- Layered depth images
- Light fields and Lumigraphs
- Environment mattes
- Video-based rendering
- Neural rendering
3 LiveLab in this lesson — see the labs panel →
04 Optimization Strategies for Vision Models 11 topics · 6 LiveLab +
- Scattered data interpolation
- Variational methods and regularization
- Markov random fields
- Epipolar geometry
- Sparse correspondence
- Dense correspondence
- Local methods
- Global optimization
- Deep neural networks
- Multi-view stereo
- Monocular depth estimation
6 LiveLab in this lesson — see the labs panel →
05 Deployment and Real-Time Performance 13 topics · 5 LiveLab +
- Pairwise alignment
- Image stitching
- Global alignment
- Compositing
- Translational alignment
- Parametric motion
- Optical flow
- Layered motion
- Geometric intrinsic calibration
- Pose estimation
- Two-frame structure from motion
- Multi-frame structure from motion
- Simultaneous localization and mapping (SLAM)
5 LiveLab in this lesson — see the labs panel →
06 Appendix A: Linear algebra and numerical techniques 5 topics +
- A1 Matrix decompositions
- A2 Linear least squares
- A3 Non-linear least squares
- A4 Direct sparse matrix techniques
- A5 Iterative techniques
07 Appendix B: Bayesian modeling and inference 6 topics +
- B1 Estimation theory
- B2 Maximum likelihood estimation and least squares
- B3 Robust statistics
- B4 Prior models and Bayesian inference
- B5 Markov random fields
- B6 Uncertainty estimation (error analysis)
08 Appendix C: Supplementary material 3 topics +
- C1 Datasets and benchmarks
- C2 Software
- C3 Slides and lectures
Hands-On Labs Our edge
30 LiveLabs- Understanding Computer Vision
- Exploring Image Processing Using OpenCV
- Evaluating Camera-Based Perception for Autonomous Hospital Robots
- Understanding Image Processing
- Recognizing Handwritten Digits Using TensorFlow
- Developing an Image Classification Application Using TensorFlow
- Classifying Images Using Convolutional Neural Networks
- Classifying Images Using TensorFlow
- Classifying Images Using PyTorch
- Detecting Objects Using OpenCV and YOLOv8
- Performing Semantic Segmentation Using Deep Learning
- Recognition in Computer Vision
- Detecting Edges and Contours Using OpenCV
- Exploring Machine Learning and Deep Learning for Computer Vision
- Understanding Image Features
- Segmenting Images Using OpenCV
- Enhancing Images Through Noise Reduction Techniques
- Reconstructing 3D Shape and Appearance
- Exploring Image-Based Rendering for Immersive Media
- Augmenting Images for Improving Model Accuracy
- Optimizing CNN Performance Through Hyperparameter Tuning
- Applying Transfer Learning Using TensorFlow
- Comparing Deep Learning Models Using TensorFlow and PyTorch
- Reconstructing Visual Data
- Estimating Scene Depth Using Stereo Vision Techniques
- Stitching Images into Panoramic Views
- Aligning Images Using Geometric Image Registration
- Detecting Faces Using OpenCV
- Structure from Motion and SLAM
- Estimating Motion in Video Using Classical and Learning-Based Techniques
Labs run in your browser — nothing to install.
02 / FAQs
Questions before you start
Keep going
You might also like
Prepare for Computer Vision: Algorithms and Applications
One-time payment. Full access for 1 year. Start with a free trial if you want to look around first.
- 1 year of full access
- 30 LiveLab included
- Certificate of completion