Photogrammetry I & II Course (2021/22)

Course Overview

• Taught by Cyrill Stachniss at the University of Bonn.
• Covers Photogrammetry I and II for the BSc program in Geodesy and Geoinformation.

Course Links

• Photogrammetry I Slides
• Photogrammetry II Slides

Resources

PDF Resources for Photogrammetry I

• Introductory Notes
• Camera Basics
• Image Histograms
• Binary Images
• Local Operators

PDF Resources for Photogrammetry II

• Introductory Notes
• Fundamental Matrix
• RANSAC
• SLAM Introduction

Weekly Breakdown

Photogrammetry I

Week 1: Introduction

• Introductory lecture series covering course structure and expectations.
• External resource: Python Crash Course.

Week 2: Python Basics

• Coverage of Python basics, Jupyter Notebooks, NumPy, and Matplotlib.

Week 3: Camera and Light

• What cameras measure.
• Basics of camera propagation of light.

Week 4: Image Histograms

• Understanding histograms and point operators.
• Histogram transformations and noise variance equalization.

Week 5: Binary Images

• Common operations: connected components, distance transform, and morphological operators.

Week 6: Convolutions

• Local operators for smoothing and gradient filters.

Week 7: Image Matching

• Cross correlation for image matching and computing keypoints.

Week 8: Visual Features

• SIFT and binary features explained.
• Introduction to feature descriptors.

Week 9: Classification

• Introduction to classification and ensemble methods.

Week 10: Neural Networks

• Basics and learning in neural networks.
• Coverage of gradient descent and backpropagation.

Week 11: Convolutional Neural Networks

• Introduction to CNNs and their applications.

Week 12: Camera Calibration

• Intrinsic/extrinsic parameters and DLT for calibration.

Week 13: Camera Calibration Methods

• Zhang's method and P3P algorithm explained.

Photogrammetry II

Week 1: Welcome

• Introduction to Photogrammetry II course.

Week 2: Epipolar Geometry

• Basics of epipolar geometry and 8-point algorithm.

Week 3: Relative Orientation

• Iterative solutions for estimating relative orientation.

Week 4: RANSAC

• Introduction to RANSAC and its applications.

Week 5: Triangulation

• Triangulation techniques for image pairs.

Week 6: Absolute Orientation

• Solving absolute orientation problems.

Week 7: Bundle Adjustment

• Basics and numerics involved in bundle adjustment.

Week 8: Orthophotos

• Understanding orthophotos and their uses.

Week 9: Clustering and Visual Words

• Introduction to k-means clustering and bag of visual words.

Week 10: Bayesian and Kalman Filters

• Introduction to Bayes filter and Kalman filter techniques.

Week 11: SLAM

• Introduction to SLAM and EKF-SLAM methods.

Conclusion

• Course wrap-up and final words from Cyrill Stachniss.