Photogrammetry I & II Course (2021/22)

 

1st Term:

Photogrammetry I

Week 1

Introduction


Introduction to Photogrammetry (Cyrill Stachniss)

Introductory Lecture for the Photogrammetry Module consisting of the courses Photogrammetry I and & at the University of Bonn.
Slides: Link


Photogrammetry Course – Lecture & Tutorial Information for Students Enrolled at the University of Bonn

Notes about lectures, tutorials, homework assignments, and formal aspects for the Photogrammetry I & II Course, taught in the BSc programme Geodesy and Geoinformation at the University of Bonn for the summer term 2021 and winter term 2021/2022.


Python Crash Course (external video)

Python Crash Course For Beginners


Week 2

Python Crash Course (cont.)


Python Crash Course (external video)

Jupyter Notebook Lab Tutorial


Python Crash Course (external video)

Python NumPy for Beginners


Python Crash Course (external video)

Matplotlib (Part 1): Creating and Customizing Our First Plots


Week 3

Technical Content on Photogrammetry Starts


What Cameras Measure – 5 Minutes with Cyrill

What do cameras actually measure explained in 5 minutes
Series: 5 Minutes with Cyrill


Camera Basics and Propagation of Light (Cyrill Stachniss)

Camera Basics and Propagation of Light
Slides: Link


Week 4


Image Histograms – 5 Minutes with Cyrill

Image histograms explained in 5 minutes
Series: 5 Minutes with Cyrill


Image Histograms – Part1: Histograms and Point Operators (Cyrill Stachniss)

Image Histograms Part 1: Image Histograms and Simple Point Operators
Slides: Link


Image Histograms – Part2: Histograms Transformations (Cyrill Stachniss)

Image Histograms – Part 2: Histograms Transformations, Histogram Equalizations and Noise Variance Equalizations
Slides: Link


Week 5


Binary Images (Cyrill Stachniss)

Binary Images and Commonly used Operations: Connected Components, Distance Transform, Morphological Operators
Slides: Link


Local Operators Through Convolutions – Part 1: Smoothing (Cyrill Stachniss)

Local operators defines in the framework of convolutions looking into two smoothing kernels, namely the box filter and binomial filter.
Slides: Link


Week 6


Local Operators Through Convolutions – Part 2: Gradient Filters (Cyrill Stachniss)

Local operators defines in the framework of convolutions looking into gradient kernels such as Sobel, Scharr, or Laplace. The video basically explains how to compute a derivative of an image.
Slides: Link


Geometric Transformation of Images (Cyrill Stachniss)

Geometric Transformation of Images
Slides: Link


Week 7


Image Matching using Cross Correlation (Cyrill Stachniss)

Image Matching using Cross Correlation
Slides: Link


Visual Feature Part 1: Computing Keypoints (Cyrill Stachniss)

Visual Feature Part 1: Computing Keypoints
Slides: Link


Week 8


SIFT – 5 Minutes with Cyrill

SIFT features explained in 5 minutes
Series: 5 Minutes with Cyrill


Binary Features – 5 Minutes with Cyrill

Binary features explained in 5 minutes
Series: 5 Minutes with Cyrill


Visual Features Part 2: Features Descriptors (Cyrill Stachniss)

Visual Features Part 2: Features Descriptors
Slides: Link


Image Segmentation using Mean Shift (Cyrill Stachniss)

Image Segmentation using the Mean Shift Algorithm
Slides: Link


Week 9


Introduction to Classification (Nived Chebrolu)

Introduction to Classification
Slides: Link


Classification – Ensemble Methods (Nived Chebrolu)

Classification – Ensemble Methods
Slides: Link

Week 10


Neural Networks – 5 Minutes with Cyrill

Neural networks explained in 5 minutes
Series: 5 Minutes with Cyrill


Introduction to Neural Networks – Part 1: The Basics (Cyrill Stachniss)

Lecture on Introduction to Neural Networks – What are neural networks and how do they work covering MLPs, weights, biases, and activations and examples how the hidden layers of a network look like.
Slides: Link


Gradient Descent – 5 Minutes with Cyrill

Gradient descent explained in 5 minutes
Series: 5 Minutes with Cyrill


Backpropagation – 5 Minutes with Cyrill

Backpropagation explained in 5 minutes
Series: 5 Minutes with Cyrill


Introduction to Neural Networks – Part 2: Learning (Cyrill Stachniss)

Lecture on Introduction to Neural Networks – Part 2: Learning (Parameter Learning, Stochastic Gradient Descent, Backprop)
Slides: Link

Errata in the video (corrected in the pdf file of the slides):
* At 55:23 the value of dL\df is not specified and only indicated as “…”. This is suboptimal for the example as this value has to be multiplied with dL\da and dL\db. Thus, the example might be a bit misleading.
* At 59:37 the derivative of “z^2” is “2z” and not “z”, thus the last dimension of the gradient in the example must be multiplied with 2.


Week 11


Convolutional Neural Networks – 5 Minutes with Cyrill

Convolution Neural Networks (CNNs) explained in 5 minutes
Series: 5 Minutes with Cyrill


Introduction to Neural Networks – Part 3: CNNs (Cyrill Stachniss)

Lecture on Introduction to Neural Networks – Part 3: Convolutional Neural Networks
Slides: Link


Some Math Basics often used in Photogrammetry (Cyrill Stachniss)

An brief, informal, and incomplete collection of math basics and tools that are often used in Photogrammetry
Slides: Link
Cyrill Stachniss, 2021


Homogeneous Coordinates – 5 Minutes with Cyrill

Homogeneous coordinates explained in 5 minutes
Series: 5 Minutes with Cyrill


Homogeneous Coordinates (Cyrill Stachniss)

Lecture on Homogeneous Coordinates
Slides: Link


Week 12


Camera Intrinsics and Extrinsics – 5 Minutes with Cyrill

Intrinsic and extrinsic parameters of a camera explained in 5 minutes
Series: 5 Minutes with Cyrill


Mapping the 3D World to an Image – 5 Minutes with Cyrill

Mapping 3D points to 2D pixel locations explained in 5 minutes
Series: 5 Minutes with Cyrill


Camera Parameters – Extrinsics and Intrinsics (Cyrill Stachniss)

Camera Parameters – Extrinsic and Intrinsic Parameters
Slides: Link


Direct Linear Transform – 5 Minutes with Cyrill

The Direct Linear Transform or short DLT explained in 5 minutes
Series: 5 Minutes with Cyrill


Direct Linear Transform for Camera Calibration and Localization (Cyrill Stachniss)

Direct Linear Transform – Joint Camera Calibration and Localization
Slides: Link


Week 13


Intrinsic Camera Calibration – 5 Minutes with Cyrill

Intrinsic camera calibration explained in 5 minutes
Series: 5 Minutes with Cyrill


Camera Calibration using Zhang’s Method (Cyrill Stachniss)

Camera Calibration using Zhang’s Method
Slides: Link


Projective 3 Point Algorithm – 5 Minutes with Cyrill

Projective 3 Point (P3P) algorithm explained in 5 minutes
Series: 5 Minutes with Cyrill


Projective 3-Point Algorithm using Grunert’s Method (Cyrill Stachniss)

Projective 3-Point Algorithm, also called Spatial Resectioning, using Grunert’s Method of 1841
Slides: Link


Photogrammetry I Course – Thank you for your Attention

 

2nd Term:

Photogrammetry II

Week 1


Photogrammetry II Course – Welcome (Cyrill Stachniss)

Welcome to the Photogrammetry II Course
Slides: PDF-01


Fundamental and Essential Matrix – 5 Minutes with Cyrill

Fundamental and essential matrix explained in 5 minutes
Series: 5 Minutes with Cyrill


Relative Orientation, Fundamental and Essential Matrix (Cyrill Stachniss)

Relative Orientation of the Image Pair, Fundamental and Essential Matrix
Slides: PDF-02

Week 2


Epipolar Geometry Basics (Cyrill Stachniss)

Epipolar Geometry Basics
Slides: PDF-03


8 Point Algorithm – 5 Minutes with Cyrill

8 point algorithm explained in 5 minutes
Series: 5 Minutes with Cyrill


Direct Solution for Estimating the Fundamental and Essential Matrix (Cyrill Stachniss)

Direct Solution for Estimating the Fundamental and Essential Matrix from Corresponding Points (“8-Point Algorithm”)
Slides: PDF-04

Week 3


Iterative Solution for Estimating the Relative Orientation (Cyrill Stachniss)

Iterative Solution for Estimating the Relative Orientation
Slides: PDF-05

Week 4


RANSAC – 5 Minutes with Cyrill

RANSAC – Random Sample Consensus explained in 5 minutes
Series: 5 Minutes with Cyrill


RANSAC – Random Sample Consensus (Cyrill Stachniss)

RANSAC – Random Sample Consensus
Slides: PDF-06

Week 5


Stereo Normal Case – 5 Minutes with Cyrill

Stereo normal case, a special configuration of a stereo camera, explained in 5 minutes
Series: 5 Minutes with Cyrill


Triangulation for Image Pairs (Cyrill Stachniss)

Triangulation of 3D Points based on Pairs of Camera Images
Slides: PDF-07

Week 6


Absolute Orientation Problem – 5 Minutes with Cyrill

Absolute orientation problem explained in 5 minutes
Series: 5 Minutes with Cyrill


Absolute Orientation Problem: Similarity Transformations Between Point Sets (Cyrill Stachniss)

Direct solution to the absolute orientation problem
Slides: PDF-08

Week 7


Bundle Adjustment – 5 Minutes with Cyrill

Bundle Adjustment explained in 5 minutes
Series: 5 Minutes with Cyrill


The Basics about Bundle Adjustment (Cyrill Stachniss)

The Basics about Bundle Adjustment
Slides: PDF-09

Week 8


The Numerics of Bundle Adjustment (Cyrill Stachniss)

The Numerics of Bundle Adjustment
Slides: PDF-10

Week 9


Orthophoto – 5 Minutes with Cyrill

Orthophoto explained in 5 minutes
Series: 5 Minutes with Cyrill


Orthophotos (Cyrill Stachniss)

Orthophotos
Slides: PDF-11

Week 10


Bag of Visual Words – 5 Minutes with Cyrill

Bag of visual words explained in 5 minutes
Series: 5 Minutes with Cyrill


Bag of Visual Words (Cyrill Stachniss)

Lecture on Bag of Visual Words for Finding Similar Images
Slides: PDF-12
Olga’s notebook on BoW: Link

Week 11


OPTIONAL VIDEO (Probability Primer)

A Short Probability Primer


Bayes Filter – 5 Minutes with Cyrill

Bayes Filter explained in 5 minutes
Series: 5 Minutes with Cyrill


Bayes Filter (Cyrill Stachniss)

Derivation of the Bayes filter equation
Slides: PDF-13

Week 12


Kalman Filter – 5 Minutes with Cyrill

The Kalman filter explained in 5 minutes
Series: 5 Minutes with Cyrill

Further reading: Link


Kalman Filter & EKF (Cyrill Stachniss)

Kalman Filter and Extended Kalman Filter (EKF)
Slides: PDF-14

Week 13


SLAM – 5 Minutes with Cyrill

SLAM explained in 5 minutes
Series: 5 Minutes with Cyrill

There is also a set of more detailed lectures on SLAM available:
Link, Link, Link, Link


Introduction to SLAM from a Photogrammetric Perspective (Cyrill Stachniss)

A Brief Introduction to SLAM from a Photogrammetric Perspective
Slides: PDF-15

Week 14


EKF-SLAM (Cyrill Stachniss)

EKF-SLAM: Landmark-based SLAM using the Extended Klaman Filter
Slides: PDF-16


Photogrammetry II Course – Thank You for Your Attention (Cyrill Stachniss)

A few final words on the Photogrammetry II Course
Cyrill Stachniss