Course information

This class is a general introduction to computer vision methods relevant in geoscience. It teaches classical computer vision methods and machine learning based techniques. It was taught at UNAM in 2021.

You can open all notebooks in binder .

Instructors

Sébastien Valade (UNAM) and Manuel Wöllhaf (TUB)

Schedule

Introduction

• Introduction (slides)

Week 1

• Lecture: Python (slides)
• Tutorial: Python (notebook)
• Tutorial: Jupyter (notebook)

Week 2

• Lecture: Images (slides)
• Tutorial: Numpy (notebook)
• Exercises: notebook

Week 3

• Lecture: Filtering (slides)
• Exercises: notebook

Week 4

• Lecture: Morphology & Segmentation (slides)
• Exercises: notebook

Week 5

• Lecture: Homography (slides)
• Exercises: notebook

Week 6

• Lecture: Features & Motion Estimation (slides part 1, slides part 2)
• Exercises: notebook

Week 7

• Lecture: Machine Learning I (slides)
• Exercises: notebook

Week 8

• Lecture: Machine Learning II (slides)
• Exercises: notebook

Week 9

• Lecture: Machine Learning III (slides)
• Exercises: notebook

Week 10

• Lecture: Deep Learning I (slides)
• Exercises: slides, notebook

Week 11

• Lecture: Deep Learning II (slides)
• Exercises: slides, notebook

Week 12

• Lecture: Deep Learning III (slides)
• Exercises: slides

Recommended Literature

• Szeliski, R. (2021). Computer Vision: Algorithms and Applications, second edition
• Gareth, J., Witten, D., Hastie, T., Tibshirani, R. (2013). An Introduction to Statistical Learning : with Applications in R. New York, Springer
• Chollet, F. (2017). Deep learning with Python. Manning Publications.
• Géron, A. (2019). Hands-on machine learning with Scikit-Learn, Keras and TensorFlow: concepts, tools, and techniques to build intelligent systems (2nd ed.). O’Reilly.