COMPUTER VISION AND PATTERN RECOGNITION - 2023/4
Module code: EEE3032
Expected prior learning: Module EEE2041 – Computer Vision & Graphics, or equivalent learning about the geometric interpretation of Linear Algebra (e.g. homogeneous coordinates and matrices for point transformation e.g. rotation, translation, scaling).
Module purpose: The module delivers a grounding in Computer Vision, suitable for students with a grounding in linear algebra similar to that provided by EEE2041 – Computer Vision & Graphics) and will help with modules such EEEM071 Advanced Topics in Computer Vision and Deep Learning. Content is presented as an application-focused tour of Computer Vision from the low-level (image processing), through to high level model fitting and object recognition.
Computer Science and Electronic Eng
BOBER Miroslaw (Elec Elec En)
Number of Credits: 15
ECTS Credits: 7.5
Framework: FHEQ Level 6
JACs code: I100
Module cap (Maximum number of students): 100
Overall student workload
Independent Learning Hours: 88
Lecture Hours: 11
Tutorial Hours: 11
Laboratory Hours: 10
Guided Learning: 10
Captured Content: 20
Prerequisites / Co-requisites
The module first introduces low-level image processing, discussing how edges may be detected, and how regions of interest may be identified using simple colour classifiers. Mid-level scene representation is then discussed in the context of global shape descriptors and local feature descriptors. These descriptors are combined with knowledge of machine learning; simple classifiers to explore supervised classification problems (shape and object recognition) and applications of unsupervised clustering (e.g. codebook based image retrieval). The latter is explored more deeply through coursework assignments. Dynamical models are then presented in the content of object tracking, with examples of classical and contemporary tracking algorithms. High-level scene description is briefly explored using statistical models of shape. Finally, models of camera geometry and image formation are presented, and their applications to 3D reconstruction are explored. Taught material is reinforced through formative lab-based exercises in MATLAB.
Introduction to Computer Vision and its Applications.
Image Processing: Convolution and Linear filters. Edge detection. Image Interpolation.
Pattern classification: Supervised clustering; K-NN; Thresholding and decision boundaries; Eigenmodels and Mahalanobis distance; PCA
Features and Matching: Image Descriptors (EHD, SIFT). Concept of a feature space. Unsupervised clustering (K-Means). Visual codebooks. Bag of Visual Words framework. Applications to object classification and visual search.
Shape Description: Shape Factors, Image Moments, Fourier descriptors, Chain Code, Hough Transform.
Tracking: Templates and cross-correlation. Blob trackers. Kalman filter. Bayes Law. Particle filters. Markov Processes.
Contour models: Piecewise cubic splines, Active contours; PDMs; ASMs. .
Multiview Geometry: Linear Perspective, Homography, RANSAC and Mosaicing. Epipolar Geometry; Fundamental and Essential Matrix; Estimating scene geometry; Stereo matching and triangulation; Visual Hull.
|Assessment type||Unit of assessment||Weighting|
|Examination Online||ONLINE (OPEN BOOK) EXAM IN A 4-HOUR WINDOW||80|
The assessment strategy for this module is designed to provide students with the opportunity to demonstrate the following.
The examination assesses all learning outcomes through use of broad range of questions covering worked calculations and problem solving “scenario” based questions that require recommendation of appropriate algorithms and solutions. All taught material is covered in the examination covering low- mid- and high- level vision so following the lecture plan. The coursework focuses on the design, implementation and evaluation of a Computer Vision system e.g. a visual search system being one of the topics covered in the early lectures. This particularly focuses upon the first 3 learning outcomes, on the selection of appropriate vision techniques, and their implementation and their evaluation.
Thus, the summative assessment for this module consists of the following.
· Coursework assignment in MATLAB (20% weighting).
· Examination (80% weighting).
Any deadline given here is indicative. For confirmation of exact date and time, please check the Departmental assessment calendar issued to you.
Formative assessment and feedback
For the module, students will receive formative assessment/feedback in the following ways.
· During lectures by question and answer sessions
· By means of unassessed lab problem sheets
· During supervised computer laboratory sessions
· Via feedback comments on assessed coursework
- The module teaches the mathematical principles and concepts of computer vision alongside its practical applications. The module aims to provide a first course in computer vision, encompassing: image formation and low-level image processing; mid-level scene representation; model-based description and tracking.
- The module also aims to provide opportunities for students to learn about the Surrey Pillars listed below.
|001||Identify and implement appropriate solutions to low, mid and high level Computer Vision problems.||C||C1|
|002||Represent problems as a mathematical models and apply appropriate machine learning and optimization techniques to solve those problems.||KCPT||C3,C4|
|003||Apply digital image processing operations and explain their operation in terms of the spatial and frequency domain.||KC||C2|
|004||Recommend appropriate statistical representations of static and dynamic objects and apply these to solve detection, classification and/or tracking problems.||KCPT||C5. C6|
|005||Evaluate the performance of visual classification, tracking and retrieval systems and draw conclusions on their efficacy.||KCPT||C13, C16, C17|
C - Cognitive/analytical
K - Subject knowledge
T - Transferable skills
P - Professional/Practical skills
Methods of Teaching / Learning
The learning and teaching strategy is designed to achieve the following aims:
The strategy is to deliver core theory in lectures and use the lab sheets in the supported computer labs to enable practical application of that theory. The latter also provides an opportunity for formative feedback.
The coursework exposes students to the full development cycle of a vision system – design, implementation, evaluation and reporting of a computer vision system. Both summative and formative feedback are delivered via the coursework.
Learning and teaching methods include the following:
Supervised computer labs
Work in mini-groups of 2-3 students (organised ad-hoc, so student mix changes, likely to be multi-cultural) solving mini-problems and presenting solutions during the lectures. This helps student to engage, work across-cultures and build networks and supportive relationships and also teaches students to respond quickly to unexpected challenges and be confident to present their thinking. Assess responses of other students (critical thinking, work across cultures).
Indicated Lecture Hours (which may also include seminars, tutorials, workshops and other contact time) are approximate and may include in-class tests where one or more of these are an assessment on the module. In-class tests are scheduled/organised separately to taught content and will be published on to student personal timetables, where they apply to taken modules, as soon as they are finalised by central administration. This will usually be after the initial publication of the teaching timetable for the relevant semester.
Upon accessing the reading list, please search for the module using the module code: EEE3032
This module will enhance employability skills by developing customer-driven approach to practical problem solving during labs and the project assignment. Digital capabilities and employability are further strengthened by providing a fundamental grounding in computer programming and problem modelling and prototyping in MATLAB, which is commonly used in industry and academia. Students solve technical challenges during the lectures and labs working with peers in mini-groups (formed in an ad-hoc fashion, and often multi-cultural), which helps them to master cultural intelligence and develop team-working skills. Resourcefulness and resilience is promoted by encouraging students to reach their full potential via planning and optimal use of resources offered, including teaching staff, demonstrators, and fellow students
This module has a capped number and may not be available to exchange students. Please check with the International Engagement Office email: firstname.lastname@example.org
Programmes this module appears in
|Computer Vision, Robotics and Machine Learning MSc||1||Optional||A weighted aggregate mark of 40% is required to pass the module|
|Electronic Engineering MSc||1||Optional||A weighted aggregate mark of 40% is required to pass the module|
|Electronic Engineering with Professional Postgraduate Year MSc||1||Optional||A weighted aggregate mark of 40% is required to pass the module|
|Electronic Engineering MEng||1||Optional||A weighted aggregate mark of 40% is required to pass the module|
|Electronic Engineering with Computer Systems MEng||1||Optional||A weighted aggregate mark of 40% is required to pass the module|
|Computer and Internet Engineering MEng||1||Optional||A weighted aggregate mark of 40% is required to pass the module|
|Computer and Internet Engineering BEng (Hons)||1||Optional||A weighted aggregate mark of 40% is required to pass the module|
|Electronic Engineering BEng (Hons)||1||Optional||A weighted aggregate mark of 40% is required to pass the module|
|Electronic Engineering with Computer Systems BEng (Hons)||1||Optional||A weighted aggregate mark of 40% is required to pass the module|
|Artificial Intelligence MSc||1||Optional||A weighted aggregate mark of 50% is required to pass the module|
Please note that the information detailed within this record is accurate at the time of publishing and may be subject to change. This record contains information for the most up to date version of the programme / module for the 2023/4 academic year.