Machine Vision

Module Details

Title: Machine Vision DRAFT

Long Title: Machine Vision

Module Code: n/a Duration: 1 Semester

Credits: 5

NFQ Level: Expert

Field of Study: Computer Science

Valid From: Semester 2 - 2019/20 ( January 2020 )

Module Delivered no programmes

In

Module Donna OShea

Coordinator:

Module Author: Christian Beder

Module The module will provide a comprehensive overview of the application and implementation
Description: of computer vision techniques, which are the foundation of many AI and machine learning
applications. The module will focus on three specific areas: the first part will look at basic
image capturing and image processing techniques. The second part will focus on the
extraction of relevant content from images and videos, while the third part will look into
image geometry and estimation techniques for scene reconstruction from image and video data.

Learning Outcomes
On successful completion of this module the learner will be able to:
LO1 Apply computer vision methodologies to facilitate capturing, filtering and pre-processing of
image and video data.
LO2 Select and apply appropriate computer vision algorithms to solve real-world problems involving
image and video data.
LO3 Implement computer vision algorithms to extract and track relevant features from image and
video data.
LO4 Apply projective modelling techniques to implement parameter estimation algorithms for inferring
and measuring scene geometry from image and video data.
LO5 Analyse and evaluate the performance of computer vision and photogrammetry algorithms.

Pre-requisite learning
Module Recommendations
This is prior learning (or a practical skill) that is strongly recommended before enrolment in this module.
You may enrol in this module if you have not acquired the recommended learning but you will have
considerable difficulty in passing (i.e. achieving the learning outcomes of) the module. While the prior
learning is expressed as named CIT module(s) it also allows for learning (in another module or modules)
which is equivalent to the learning specified in the named module(s).
No recommendations listed
Incompatible Modules
These are modules which have learning outcomes that are too similar to the learning outcomes of this
module. You may not earn additional credit for the same learning and therefore you may not enrol in this
module if you have successfully completed any modules in the incompatible list.
No incompatible modules listed
Co-requisite Modules
No Co-requisite modules listed
Requirements
This is prior learning (or a practical skill) that is mandatory before enrolment in this module is allowed. You
may not enrol on this module if you have not acquired the learning specified in this section.

Page 1 of 6
No requirements listed
Co-Requisites
No Co Requisites listed

Page 2 of 6
 Machine Vision

Module Content & Assessment

Indicative Content
Image processing
Introduction to image capturing methodologies, such as sampling of raster images, colour representation
and histogram operations. Image processing algorithms for binary images and morphological operations
for image segmentation. Theory of linear filters and the application of convolution filters using Fourier
transformation. Application of linear low-pass filtering to smoothing and image pyramid computation.
Theory of sampling and its relation to local frequency and aliasing effects with application to
super/sub-sampling and anti-aliasing. Application of linear high-pass filtering to edge detection, the
computation of image gradients and methods for feature extraction based on local gradients.
Content extraction
Introduction to algorithms for extracting local descriptors of feature points, such as scale-invariant feature
transformation (SIFT) and SURF. Algorithms for image segmentation based on mathematical
representations such as level-sets and Markov-random-fields. Optimisation techniques for solving image
segmentation problems. Photometric stereo algorithms for extracting 3d information from single images,
such as shape-from-shading. Image sequence analysis using optical flow algorithms. Feature tracking
algorithms for image sequences, such as KLT, to facilitate multi-view scene reconstruction and automatic
camera calibration.
Parameter estimation
Theory of statistical parameter estimation. Maximum Likelihood and iterative Least-Squares estimation
techniques, such as Gauss-Helmert- and Gauss-Markov-models as well as online estimation methods
such as Kalman filters. Robust estimation techniques to cope with outliers in data including robust cost
functions and random sampling consensus (RANSAC). Performance analysis techniques like the
estimation of empirical parameter accuracy and variance components.
Projective geometry
Introduction to the projective geometry of 2d and 3d space. Geometric modelling of the imaging process
using linear projective camera models and forward/backward projection of image point and image line
features. Estimation of planar homographies and their application to plane-to-plane image mapping, image
registration and stitching of panoramic views from multiple images. Epipolar geometry of two and three
projective images. Estimation of the fundamental matrix and the trifocal tensor to describe the
un-calibrated multi-view geometry. Application of un-calibrated multi-view geometry to projective 3d scene
reconstruction from multiple images. Algorithms and techniques for camera calibration. Estimation of the
essential matrix to describe calibrated two-view geometry with applications to metric 3d scene
reconstruction. Simultaneous localisation and mapping (SLAM) algorithms using bundle adjustment to
recover camera and scene geometry from image sequences. Auto-calibration techniques for recovering
metric information from video sequences of un-calibrated images.

Assessment Breakdown %
Course Work 100.00%

Course Work
Assessment Assessment Description Outcome % Assessment
Type addressed of Date
total
Project For a given case-study apply computer vision 1,2,3 50.0 Week 8
methodologies and implement algorithms to capture,
process, and extract relevant information from image or
video data.
Project For a given case-study implement algorithms to extract 3,4,5 50.0 Sem End
and measure features from image or video data, estimate
scene geometry parameters, and evaluate the accuracy
of the results.

No End of Module Formal Examination

Reassessment Requirement
Coursework Only
This module is reassessed solely on the basis of re-submitted coursework. There is no repeat written
examination.

The institute reserves the right to alter the nature and timings of assessment

Page 3 of 6
 Machine Vision

Module Workload

Workload: Full Time

WorkLoad Type WorkLoad Description Hours Frequency Average
Weekly
Learner
Workload
Lecture Presentation of theory 2.0 Every 2.00
Week
Lab Lab supporting lectures 2.0 Every 2.00
Week
Independent Learning Student reads recommended materials and 3.0 Every 3.00
practices implementation Week
Total Hours 7.00
Total Weekly Learner Workload 7.00
Total Weekly Contact Hours 4.00

Workload: Part Time

WorkLoad Type WorkLoad Description Hours Frequency Average
Weekly
Learner
Workload
Lecture Presentation of theory 2.0 Every 2.00
Week
Lab Lab supporting lectures 2.0 Every 2.00
Week
Independent Learning Student reads recommended materials and 3.0 Every 3.00
practices implementation Week
Total Hours 7.00
Total Weekly Learner Workload 7.00
Total Weekly Contact Hours 4.00

Page 4 of 6
Module Resources

Recommended Book Resources

McGlone, J. C., Mikhail, E. M., Bethel, J. S., Mullen, R., & American Society for Photogrammetry
and Remote Sensing 2004, Manual of photogrammetry, 5th edition Ed., American Society for
Photogrammetry and Remote Sensing [ISBN: 1570830711]

Supplementary Book Resources

Nikos Paragios, Yunmei Chen, and Olivier Faugeras 2005, Handbook of Mathematical Models in
Computer Vision, Springer [ISBN: 1441938850]
Berthold Klaus Paul Horn 1986, Robot Vision, MIT Press [ISBN: 0262081598]
Richard Hartley and Andrew Zisserman 2004, Multiple View Geometry in Computer Vision, 2nd
edition Ed., Cambridge University Press [ISBN: 0521540518]
Rafael C. Gonzalez and Richard E. Woods 2017, Digital Image Processing, 4th edition Ed., Pearson
[ISBN: 1292223049]
Olivier Faugeras, Quang-Tuan Luong, and T. Papadopoulou 2001, The Geometry of Multiple
Images: The Laws that Govern the Formation of Images of a Scene and some of their Applications,
MIT Press [ISBN: 0262562049]
Olivier Faugeras 1993, Three-Dimensional Computer Vision: A Geometric Viewpoint, MIT Press
[ISBN: 0262061589]
Gerhard Winkler 2012, Image Analysis, Random Fields and Dynamic Monte Carlo Methods: A
Mathematical Introduction, 2nd edition Ed., Springer [ISBN: 3642629113]

This module does not have any article/paper resources

Other Resources

Website: CVOnline
http://homepages.inf.ed.ac.uk/rbf/CVonli ne/
Website: OpenCV library
https://opencv.org/

Page 5 of 6
Page 6 of 6