Photogrammetry I & II Course (2021/22) StachnissLab

Course Overview

• Institution: University of Bonn
• Instructor: Cyrill Stachniss
• Course Structure: Consists of two modules: Photogrammetry I and II

Slides Links

Photogrammetry I

• PDF-00: Notes
• PDF-01: Introduction
• PDF-02: Camera Basics
• ... (more links)

Photogrammetry II

• PDF-01: Introduction
• PDF-02: Fundamental Matrix
• ... (more links)

1st Term: Photogrammetry I

Week 1

• Introduction to Photogrammetry: Overview and course details provided.
• Python Crash Course: External video resource introduced.

Week 2

• Continued Python Crash Course, including:
  • Jupyter Notebook Lab Tutorial
  • Python NumPy Basics
  • Matplotlib Basics (Creating first plots)

Week 3

• Camera Basics: Propagation of light explained.
  • Slides

Week 4

• Image Histograms: Explained in two parts.
  • Part 1: Histograms and Point Operators
  • Part 2: Transformations and Equalizations

Week 5

• Binary Images: Common operations such as connected components and morphological operators discussed.

Week 6

• Local Operators: Part 1 & 2 covering smoothing and gradient filters.

Week 7

• Image Matching: Using Cross Correlation.
• Visual Feature Part 1: Computing Keypoints.

Week 8

• Visual Features: SIFT, Binary Features, and Feature Descriptors.
• Image Segmentation: Using Mean Shift Algorithm.

Week 9

• Introduction to Classification and Ensemble Methods.

Week 10

• Neural Networks: Basics, Gradient Descent, and Backpropagation explained.

Week 11

• Convolutional Neural Networks: Concepts and applications discussed.

Week 12

• Camera Parameters: Intrinsics and extrinsics explained.
• Direct Linear Transform: Camera calibration and localization.

Week 13

• Camera Calibration: Using Zhang's method.
• Projective 3-Point Algorithm: Explained using Grunert's method.

2nd Term: Photogrammetry II

Week 1

• Fundamental and Essential Matrices: Introduced.

Week 2

• Epipolar Geometry Basics and 8-Point Algorithm.

Week 3

• Iterative Solutions: For estimating relative orientation.

Week 4

• RANSAC: Explained with applications.

Week 5

• Triangulation: Techniques for 3D points based on image pairs.

Week 6

• Absolute Orientation Problem: Solutions discussed.

Week 7

• Bundle Adjustment: Explained and its basics covered.

Week 8

• Orthophotos: Concepts and applications.

Week 9

• k-means Clustering and Bag of Visual Words: Explained with applications.

Week 10

• Bayes Filter: Derivation of the equation discussed.

Week 11

• Kalman Filter and EKF: Concepts presented.

Week 12

• SLAM: Introduction from a photogrammetric perspective.

Week 13

• EKF-SLAM: Landmark-based SLAM discussed.

Conclusion

• The course provided comprehensive coverage of both theoretical and practical aspects of photogrammetry and its applications.