Registry
Module Specifications
Archived Version 2017 - 2018
| |||||||||||||||||||||||||||||||||||||||||
|
Description Computer vision applications have significantly expanded over the last decade and this core skill set is always in high demand by employers. This module will build on the basic concepts with a view to delving deeper into core computer vision, machine learning and deep learning topics. As well as examining traditional computer vision concepts (i.e. feature extraction and machine learning) a key focus of the module will be on deep learning as applied to computer vision. We will examine the core concepts behind deep learning for computer vision with a specific focus on Convolutional Neural Networks (CNN). Students will learn how to design and tune such networks in a range of practical applications and assignments. In addition we will examine a range of deep learning architectures ranging from AlexNet upto the current state of the art in this ever expanding field. Deep learning based computer vision forms the core of many of the recent developments in this field and has been widely adopted as a core AI tool by all the key industrial players such as Google, Facebook, IBM, Apple, Baidu ... as well as a wide range of highly innovative startups. All computer vision and deep learning concepts will be reinforced by guided practical work and case studies. This module is primarily aimed at those who aim to undertake research in computer vision or require a deeper understanding of the subject to address commercial computer vision development. Computer vision applications span a wide range of disciplines including industrial/machine vision, video data processing, biomedical engineering, healthcare, astronomy, imaging science, sensor technology, multimedia and enhanced reality systems. Please refer to the modules summary syllabus for a breakdown of the course content. This module will require basic programming skills. See the EE544 module website (http://www.eeng.dcu.ie/~whelanp/ee544/) for details on the computer vision & deep learning development environment. | |||||||||||||||||||||||||||||||||||||||||
|
Learning Outcomes 1. Recall, review and analyse the advanced theories, algorithms, methodologies and techniques involved in computer vision. 2. Illustrate their ability to comprehend and interpret issues relating to the design of advanced computer vision. 3. Synthesize and evaluate the relevant merits of competing advanced computer vision techniques. 4. Apply computer vision techniques in a range of application scenarios. 5. Develop an deep understanding of the issues involved in the evaluating computer vision research. 6. Demonstrate the ability to implement a computer vision pipeline. | |||||||||||||||||||||||||||||||||||||||||
All module information is indicative and subject to change. For further information,students are advised to refer to the University's Marks and Standards and Programme Specific Regulations at: http://www.dcu.ie/registry/examinations/index.shtml |
|||||||||||||||||||||||||||||||||||||||||
|
Indicative Content and
Learning Activities Shape, Colour & TextureIntroduction to Python / scikit-image, Basic Morphology, Conditional Dilation, Geodesic Transformations, Reconstruction by Dilation, Applications, Double [Hysteresis] Threshold, Skeleton Influence By Zones, Watershed, Marker Controlled Segmentation, H-Extrema, Regional Maxima/Minima, Minima Imposition Technique, Opening/Closing by Reconstruction - Colour Spaces (CIE-Lab, CIE-Luv, Spatial SCIE-Lab), Colour Image Processing, Decorrelation Stretching, Computational Colour Constancy, Colour Segmentation (Feature-Based, Area Based, Physics Based), Integration of Colour-Texture Descriptors, Example Applications - Texture Spectrum Method, Local Binary Patterns (LBP), Rotation Invariance, Gabor Filtering, Multi-Channel Filtering, GIST, Texture based deep learning - Example applications and case studies.Interest Point Detection & Feature ExtractionInterest Points Review, Moravec Corner Detector, Harris/Plessey Corner Detector, Scale Invariant Harris Corner Detector, SIFT – Scale Invariant Feature Transform, SIFT Matching, SIFT Variants, SIFT Applications - Histogram of Oriented Gradients (HOG), RHOG + SIFT, HOG + SVM, Deformable Part Models, Face Detection (Viola Jones), Boosting, Classifier Cascade, Bag of Visual Words - Example applications and case studies.Classification & Machine LearningIntroduction to scikit-learn, Statistics Review, Principal Component Analysis (First Principals to Practical Applications), PCA Applied to Images: Eigenvalues and Eigenvectors, Training and Testing, Automated Selection of Eigenvalues - Metrics, Feature Normalisation, VC Dimension, Hughes Phenomenon, Feature Selection, Supervised & Unsupervised Classification, Hierarchical Clustering / Non-Hierarchical Clustering, KMeans Classification, Randomized Decision Forests, Evaluation of Classifier Performance, Parametric vs Non-Parametric Classifiers, Decision Trees, Gaussian Mixture Models, Expectation Maximization - Shallow vs Deep Learning, Support Vector Machines (SVM), SVM Classification, Kernels, SVM Multi-Class Classification, SVM Implementation - Example applications and case studies.Deep Learning for Computer VisionIntroduction to Keras/Tensorflow, Feature vs Data Driven Approaches, Artificial Neural Networks (ANN), Logistic (Linear) Classifier, softmax, Stochastic Gradient Descent, Multi-Layer Perceptron, Gradient Decent, Backpropagation Learning Algorithm, Overfitting / Regularization, From ANN to Deep Learning, Sparse Coding, Supervised Deep Learning (DL), Convolution Neural Networks (CNN – Convnets), Network Architectures, Transfer Learning, DL APIs, DL Network Architectures (Alexnet to current SOA), Fully Convolutional Networks, Classification + Localization, R-CNN, RNN, Unsupervised Learning, Autoencoders, Style Transfer Network, Generative Adversarial Networks, DL Visualization - Example applications and case studies.Systems EngineeringComputer Vision Design Factors, Video Standards and Techniques, Optical Terminology, Lenses, Lighting Design, Optical Material Characteristics, Typical Machine Vision Lamps, Lighting Techniques, Reliability, Solid State (Digital) Sensors, Sensor Characteristics, Colour Cameras, Pixel Level Effects, Monochrome Aberrations, Chromatic Aberrations, Vignetting, Extended Focus - Example applications and case studies.3D Imaging (Spatial & Temporal)Passive Stereoscopic Methods, Camera Calibration/Rectification, Epipolar Geometry, Shape from Stereo, Fundamental Matrix, Rectification Procedure, Stereo Feature Constraints & Matching, Depth Estimation Techniques (Window-based techniques, Dynamic programming, Deep Learning), Colour Stereo Vision, Multiple View Stereo Vision, Active Stereoscopic Methods, Structure (3D) from Motion (SfM), Depth From Focus, Laser Ranging Systems, Time of Flight Measurement, Structured Light, Moiré, Infrared Scanning, Shape from X, RGBD, Industry/Consumer Applications - Motion Tracking, Motion Field & Optical Flow, Optical Flow: 2D, Optical Flow: Local Approach, Histogram of Optical Flow (HOF), Feature Matching (Motion Correspondence), Kanade Lucas Tomasi Tracking. | |||||||||||||||||||||||||||||||||||||||||
| |||||||||||||||||||||||||||||||||||||||||
Indicative Reading List
| |||||||||||||||||||||||||||||||||||||||||
|
Other Resources 27166, Module Website, Paul F Whelan, 2017, EE544, http://www.eeng.dcu.ie/~whelanp/ee544/ee544_notes.html, 27162, Lecturer Website, Paul F Whelan, 2017, http://paulwhelan.eu/, http://paulwhelan.eu/, | |||||||||||||||||||||||||||||||||||||||||
| Programme or List of Programmes | |||||||||||||||||||||||||||||||||||||||||
| Archives: |
| ||||||||||||||||||||||||||||||||||||||||