Difference between revisions of "Applied Computer Vision Lecture Schedule"

From David Vernon's Wiki
Jump to: navigation, search
 
(7 intermediate revisions by the same user not shown)
Line 5: Line 5:
 
<small>
 
<small>
 
{| class="wikitable"
 
{| class="wikitable"
−
! scope="col" style="width: 7%;" | Date
+
! scope="col" style="width: 7%;" | Date                           <!-- 7% -->
−
! scope="col" style="width: 3%;" | Lecture
+
! scope="col" style="width: 3%;" | Lecture                     <!-- 3% -->
−
! scope="col" style="width: 14%;" | Topic
+
! scope="col" style="width: 20%;" | Topic                         <!-- 14% -->
−
! scope="col" style="width: 50%;" | Material covered
+
! scope="col" style="width: 30%;" | Material covered     <!-- 50% -->
−
! scope="col" style="width: 13%;" | Reading
+
! scope="col" style="width: 20%;" | Reading                   <!-- 13% -->
−
! scope="col" style="width: 13%;" | Assignments
+
! scope="col" style="width: 20%;" | Assignments           <!-- 13% -->
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Mon. 28 Aug.
+
| Tue. 29 Aug.
 
| 1
 
| 1
−
| Overview of human and computer vision  
+
| Overview
−
|
+
| Human and computer vision  
−
|[http://www.vernon.eu/ACV/ACV_01.pdf Lecture 1 Slides]. Szeliski 2010, Chapter 1. ]
+
|[http://www.vernon.eu/ACV/ACV_01.pdf Lecture 1 Slides]. Szeliski 2010, Sections 1.1 and 1.2. Kragic and Vincze, 2010.  <!-- [http://www.cs.ubc.ca/~lowe/vision.html David Lowe's website of industrial vision systems]. -->
 
|
 
|
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Wed. 30 Aug.
+
| Thur. 31 Aug.
 
| 2  
 
| 2  
−
| Formalisms for Representing Algorithms
+
| Software tools
−
| Definition of an algorithm. Modelling software. Relational modelling. State modelling. Practical representations. Pseudo code. Flow charts. Finite state machines. UML. Predicate logic. Analysis.
+
| OpenCV, Software development tools for course work 
−
| [http://www.vernon.eu/04-630/04-630_Lecture_02_Formalisms_for_Representing_Algorithms.pdf Lecture 2 Slides]. Harel 2004, Chapters 1 and 2.
+
| [http://www.vernon.eu/ACV/ACV_02.pdf Lecture 2 Slides].  
−
| [http://www.vernon.eu/04-630/04-630_Assignment_1.pdf Assignment 1]
+
|
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Mon. 4 Sept.
+
| Tue. 5 Sept.
 
| 3
 
| 3
−
| Analysis of Complexity I
+
| Optics, sensors, and image formation
−
| Performance of algorithms, time and space tradeoff, worst case and average case performance. Big O notation. Recurrence relationships. Analysis of complexity of iterative and recursive algorithms. Recursive vs. iterative algorithms: runtime memory implications.
+
| Illumination, projections, lenses, Gauss lens equation, field of view, depth of field, CMOS and CCD sensors, colour sensors, noise, resolution.
−
| [http://www.vernon.eu/04-630/04-630_Lecture_03_Analysis_of_Complexity_I.pdf Lecture 3 Slides]. Aho et al. 1983, Chapter 1.
+
|
 
|  
 
|  
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Wed. 6 Sept.
+
| Thur. 7 Sept.
 
| 4
 
| 4
−
| Analysis of Complexity II
+
| Image acquisition and image representation
−
| Complexity theory: tractable vs intractable algorithmic complexity. Example intractable problems: travelling salesman problem, Hamiltonian circuit, 3-colour problem, SAT, cliques. Determinism and non-determinism. P, NP, and NP-Complete classes of algorithm.
+
| Sampling and quantization, Shannon's sampling theorem, Nyquist frequency, Nyquist sampling rate, aliasing, resolution, space-variant sampling, log-polar images, dynamic range, colour spaces: HIS, HLS, HSV
−
| [http://www.vernon.eu/04-630/04-630_Lecture_04_Analysis_of_Complexity_II.pdf Lecture 4 Slides]. Aho et al. 1983, Chapter 1.
+
|
−
| [http://www.vernon.eu/04-630/04-630_Assignment_2.pdf Assignment 2]
+
|  
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Mon. 11 Sept.
+
| Tue. 12 Sept.
 
| 5
 
| 5
−
| Searching and Sorting Algorithms I
+
| Image processing
−
| Linear and binary search (iterative and recursive). In-place sorts: bubblesort (efficient and inefficient), selection sort, insertion sort.
+
| Point & neighbourhood operations, image filtering, convolution, Fourier transform 
−
| [http://www.vernon.eu/04-630/04-630_Lecture_05_Searching_and_Sorting_Algorithms_I.pdf Lecture 5 Slides]. Aho et al. 1983, Chapter 8.
+
|  
 
|  
 
|  
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Wed. 13 Sept.
+
| Thur. 14 Sept.
 
| 6
 
| 6
−
| Searching and Sorting Algorithms I
+
| Image processing
−
| Not-in-place sorts: Quicksort, merge sort. Complexity analysis. Characteristics of a good sort. Speed, consistency, keys, memory usage, length & code complexity, stability. Other sorts ordered by complexity.
+
| Morphological operations
−
|[http://www.vernon.eu/04-630/04-630_Lecture_06_Searching_and_Sorting_Algorithms_II.pdf Lecture 6 Slides]. Aho et al. 1983, Chapter 8.
+
|  
 
|  
 
|  
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Mon. 18 Sept.
+
| Tue. 19 Sept.
 
| 7
 
| 7
−
| Abstract Data Types (ADT)
+
| Image processing
−
| <!-- Vector example exercise. History of abstraction. --> Abstract Data Types (ADT). Information hiding. Types and typing. <!-- Encapsulation. Efficiency. --> Design Goals. Design practices.
+
| Geometric operations
−
| [http://www.vernon.eu/04-630/04-630_Lecture_07_Abstract_Data_Types.pdf Lecture 7 Slides].
+
|
 
|
 
|
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Wed. 20 Sept.
+
| Thur. 21 Sept.
 
| 8
 
| 8
−
| Containers, Dictionaries, and Lists I
+
|Segmentation
−
| Container and dictionaries: mechanisms for accessing data in a list.  List ADT.  Implementation with arrays.
+
|Region-based approaches, binary thresholding, connected component analysis 
−
|  [http://www.vernon.eu/04-630/04-630_Lecture_08_Containers,_Dictionaries,_and_Lists_I.pdf Lecture 8 Slides].
+
|
−
| [http://www.vernon.eu/04-630/04-630_Assignment_3.pdf Assignment 3] <!-- <BR> [[Assignment 3 Status]] -->
+
|
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Mon. 25 Sept.
+
| Tue. 26 Sept.
 
| 9
 
| 9
−
| Containers, Dictionaries, and Lists II
+
| Segmentation
−
| List ADT.  Implementation with linked lists. Doubly linked lists and circular lists. Performance considerations.
+
| Edge detection
−
|   [http://www.vernon.eu/04-630/04-630_Lecture_09_Containers,_Dictionaries,_and_Lists_II.pdf Lecture 9 Slides].
+
|  
 
|  
 
|  
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Wed. 27 Feb.
+
| Thur. 28 Feb.
 
| 10
 
| 10
−
| Stacks
+
| Segmentation
−
| Stack (LIFO) ADT. Implementation using List ADT (array and linked-list). Comparison of order of complexity. Stack applications, including token matching, evaluation of postfix expressions, and conversion of infix expressions to postfix.
+
| Colour-based approaches; k-means clustering  
−
| [http://www.vernon.eu/04-630/04-630_Lecture_10_Stacks.pdf Lecture 10 Slides].
+
|
 
|  
 
|  
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Mon. 2 Oct.
+
| Tue. 3 Oct.
 
| 11
 
| 11
−
|  
+
| Image features 
−
| Queue (FIFO ADT). Implementation using List ADT (array and linked-list).  Comparison of order of complexity.  Dedicated ADT. Circular queues.  Queue applications.
+
| Harris and Difference of Gaussian interest point operators
−
|  [http://www.vernon.eu/04-630/04-630_Lecture_11_Queues.pdf Lecture 11 Slides]. [http://www.vernon.eu/04-630/poisson.pdf  On the Simulation of Random Events].
+
|   
 
|  
 
|  
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Wed. 4 Oct.
+
| Thur. 5 Oct.
 
| 12
 
| 12
 +
|  Image features
 +
|  SIFT feature descriptor
 
|   
 
|   
−
| Concepts and terminology: level, height, external and internal nodes, skinny, fat, complete, left-complete, perfect, multi-way, d-ary. Types of tree: binary, binary search, B-tree, 2-3 tree, AVL, Red-Black
 
−
|  [http://www.vernon.eu/04-630/04-630_Lecture_12_Trees_I.pdf Lecture 12 Slides].
 
 
|  
 
|  
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Mon. 9 Oct.
+
| Tue. 10 Oct.
 
| 13
 
| 13
−
|
+
| Object recognition
 +
| Template matching; normalized cross-correlation; chamfer matching 
 +
| 
 
|  
 
|  
−
|  [http://www.vernon.eu/04-630/04-630_Lecture_13_Trees_II.pdf Lecture 13 Slides].
 
−
| [http://www.vernon.eu/04-630/04-630_Lab_Exercise_1.pdf Lab Exercise 1]
 
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Wed. 11 Oct.
+
| Thur. 12 Oct.
 
| 14
 
| 14
−
|
+
| Object recognition
−
|
+
| 2D shape features; statistical pattern recognition 
 
|  
 
|  
 
|   
 
|   
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Mon. 16 Oct.
+
| Tue. 17 Oct.
 
| 15
 
| 15
−
|   
+
|  Object recognition
−
|  
+
| Hough transform for parametric curves: lines, circles, and ellipses 
 
|  
 
|  
 
|   
 
|   
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Wed. 18 Oct.
+
| Thur. 19 Oct.
 
| 16
 
| 16
−
|   
+
|  Object recognition
−
|  
+
| Generalized Hough transform; extension to codeword features 
 
|   
 
|   
 
|  
 
|  
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Mon. 23 Oct.
+
| Tue. 24 Oct.
 
| 17
 
| 17
−
|
+
| Object recognition
−
|  
+
| Colour histogram matching and back-projection
 
|   
 
|   
 
|   
 
|   
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Wed. 25 Oct.
+
| Thur. 26 Oct.
 
| 18
 
| 18
−
|  
+
| Object recognition
−
|  
+
| Haar features and boosted classifiers 
 
|   
 
|   
 
|  
 
|  
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Mon. 30 Oct.
+
| Tue. 31 Oct.
 
| 19
 
| 19
−
|   
+
|  Object recognition
−
|  
+
| Histogram of Oriented Gradients (HOG) feature descriptor 
 
|  
 
|  
 
|   
 
|   
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Wed. 1 Nov.
+
| Thur. 2 Nov.
 
| 20
 
| 20
−
|   
+
|  Video image processing
−
|   
+
| Background subtraction and object tracking  
 
|     
 
|     
 
|  
 
|  
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Mon. 6 Nov.
+
| Tue. 7 Nov.
 
| 21
 
| 21
−
|   
+
|  3D vision
−
|  
+
| Homogeneous transformations. Perspective transformation. Camera model and inverse perspective transformation 
 
|  
 
|  
 
|   
 
|   
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Wed. 8 Nov.
+
| Thur. 9 Nov.
 
| 22
 
| 22
−
|
+
| Stereo vision.
−
|   
+
| Stereo correspondence, Epipolar geometry  
 
|   
 
|   
 
|   
 
|   
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Mon. 13 Nov.
+
| Tue. 14 Nov.
 
| 23
 
| 23
−
|   
+
| Optical flow  
 
|   
 
|   
 
|   
 
|   
 
|  
 
|  
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Wed. 15 Nov.
+
| Thur. 16 Nov.
 
| 24
 
| 24
−
|   
+
|  Visual attention
−
|   
+
| Saliency, Bottom-up and top-down attention  
 
|   
 
|   
 
|   
 
|   
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Mon. 20 Nov.
+
| Tue. 21 Nov.
 
| 25
 
| 25
−
|   
+
|  Clustering, grouping, and segmentation
−
|  
+
| Gestalt principles. Clustering algorithms 
 
|   
 
|   
 
|   
 
|   
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Wed. 22 Nov.
+
| Thur. 23 Nov.
 
| 26
 
| 26
−
|   
+
|  Object recognition in 3D
−
|  
+
| Object detection, object recognition, object categorisation 
 
|   
 
|   
 
|  
 
|  
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Mon. 27 Nov.
+
| Tue. 28 Nov.
 
| 27
 
| 27
−
|   
+
| Affordances  
 
|   
 
|   
 
|  
 
|  
 
|   
 
|   
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Wed. 29 Nov.
+
| Thur. 30 Nov.
 
| 28
 
| 28
−
|   
+
| Computer vision and machine learning  
 
|   
 
|   
 
|  
 
|  
 
|   
 
|   
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Mon. 4 Dec.
+
| Tue. 5 Dec.
 
| 29
 
| 29
−
|   
+
| Computer vision and machine learning  
 
|   
 
|   
 
|  
 
|  
 
|
 
|
 
|- style="vertical-align: top;"
 
|- style="vertical-align: top;"
−
| Wed. 6 Dec.
+
| Thur. 7 Dec.
 
| 30
 
| 30
−
|   
+
| Computer vision and machine learning  
 
|   
 
|   
 
|  
 
|  

Latest revision as of 12:52, 22 August 2017

|CARNEGIE MELLON UNIVERSITY AFRICA|

Date Lecture Topic Material covered Reading Assignments
Tue. 29 Aug. 1 Overview Human and computer vision Lecture 1 Slides. Szeliski 2010, Sections 1.1 and 1.2. Kragic and Vincze, 2010.
Thur. 31 Aug. 2 Software tools OpenCV, Software development tools for course work Lecture 2 Slides.
Tue. 5 Sept. 3 Optics, sensors, and image formation Illumination, projections, lenses, Gauss lens equation, field of view, depth of field, CMOS and CCD sensors, colour sensors, noise, resolution.
Thur. 7 Sept. 4 Image acquisition and image representation Sampling and quantization, Shannon's sampling theorem, Nyquist frequency, Nyquist sampling rate, aliasing, resolution, space-variant sampling, log-polar images, dynamic range, colour spaces: HIS, HLS, HSV
Tue. 12 Sept. 5 Image processing Point & neighbourhood operations, image filtering, convolution, Fourier transform
Thur. 14 Sept. 6 Image processing Morphological operations
Tue. 19 Sept. 7 Image processing Geometric operations
Thur. 21 Sept. 8 Segmentation Region-based approaches, binary thresholding, connected component analysis
Tue. 26 Sept. 9 Segmentation Edge detection
Thur. 28 Feb. 10 Segmentation Colour-based approaches; k-means clustering
Tue. 3 Oct. 11 Image features Harris and Difference of Gaussian interest point operators
Thur. 5 Oct. 12 Image features SIFT feature descriptor
Tue. 10 Oct. 13 Object recognition Template matching; normalized cross-correlation; chamfer matching
Thur. 12 Oct. 14 Object recognition 2D shape features; statistical pattern recognition
Tue. 17 Oct. 15 Object recognition Hough transform for parametric curves: lines, circles, and ellipses
Thur. 19 Oct. 16 Object recognition Generalized Hough transform; extension to codeword features
Tue. 24 Oct. 17 Object recognition Colour histogram matching and back-projection
Thur. 26 Oct. 18 Object recognition Haar features and boosted classifiers
Tue. 31 Oct. 19 Object recognition Histogram of Oriented Gradients (HOG) feature descriptor
Thur. 2 Nov. 20 Video image processing Background subtraction and object tracking
Tue. 7 Nov. 21 3D vision Homogeneous transformations. Perspective transformation. Camera model and inverse perspective transformation
Thur. 9 Nov. 22 Stereo vision. Stereo correspondence, Epipolar geometry
Tue. 14 Nov. 23 Optical flow
Thur. 16 Nov. 24 Visual attention Saliency, Bottom-up and top-down attention
Tue. 21 Nov. 25 Clustering, grouping, and segmentation Gestalt principles. Clustering algorithms
Thur. 23 Nov. 26 Object recognition in 3D Object detection, object recognition, object categorisation
Tue. 28 Nov. 27 Affordances
Thur. 30 Nov. 28 Computer vision and machine learning
Tue. 5 Dec. 29 Computer vision and machine learning
Thur. 7 Dec. 30 Computer vision and machine learning


Back to Applied Computer Vision

Retrieved from "http://www.vernon.eu/w/index.php?title=Applied_Computer_Vision_Lecture_Schedule&oldid=1508"