Intelligent Transportation Systems
Contents
Students get an overview of the principles of modern, intelligent traffic, logistic and driver assistant systems. Further, the basic aspects of modelling simulation and data acquisition are taught. Besides of software based simulations also practical laboratories and projects are carried out.Lectures with courses [VK]
Courses and labs[KU]
Research Seminar and Project
Guest Lectures
Lectures with courses [VK]
[700.350] Transportation Telematics I
Semester |
Winter semester |
Allocation in the Curriculum |
Master Curriculum, Information Technology
|
Recommended Semester |
|
Teacher |
Prof. Kyandoghere Kyamakya, Transportation Informatics Group, Institute of Smart Systems Technologies Email: kyandoghere.kyamakya@aau.at |
Type of lecture and number of credits |
VK (lecture with integrated course, project, exercises or mini-seminar) 2 SWS, 4 ECTS |
Description |
A general presentation of core systems components of intelligent transportation systems: a) traffic theory; b) traffic control, c) traffic sensors; d) selected systems and services |
Topics |
1. Course Plan, Organization and Evaluation Policy 2. Definitions, Overall Context and Motivation 3. Introduction to Transportation Systems 4. Overview of ITS (Intelligent Transportation Systems) 5. Positioning, Navigation Principles, and Location-based Services 6. Basics of Road Traffic Theory
7. Principles of Traffic Information Sensing + Sensor
8. Basics of Road Traffic Control 9. Toll Collection: Principles and Systems 10. Road Safety: issues, technologies, modelling, assessment 11. Students Short Seminar on Selected Topics |
Keywords |
Road traffic theory, traffic management, traffic sensing, road safety, driver assistance, mobility systems |
Prior knowledge |
none |
Learning objective |
Acquire advanced and deep knowledge on core components of intelligent transportation systems |
Recommended Literature |
|
Language |
English |
Related Lectures |
|
Recommended Lectures |
|
[700.310] Transportation Telematics II
Semester |
Winter semester |
Allocation in the Curriculum |
Master Curriculum, Information Technology
|
Recommended Semester |
|
Teacher |
Prof. Kyandoghere Kyamakya, Transportation Informatics Group, Institute of Smart Systems Technologies Email: kyandoghere.kyamakya@aau.at |
Type of lecture and number of credits |
VK (lecture with integrated course, project, exercises or mini-seminar) 2 SWS, 4 ECTS |
Description |
A general presentation of core systems components of intelligent transportation systems: a) traffic theory; b) traffic control, c) traffic sensors; d) selected systems and services |
Topics |
1. Introduction to Transportation 2. Basics of "Road Traffic Theory 3. Traffic Control Principles 4. Principles of Traffic Information Sensing + Sensor technologies 5. Advanced Traveller Information Systems 6. Data Fusion at the Traffic Management Center 7. Toll Collection: Principles and Systems 8. Transportation Risk and Safety Assessment + Road safety basics 9. Urban Mobility Transportation System 10. Students Seminar on Selected Topics |
Keywords |
Road traffic theory, traffic management, traffic sensing, road safety, driver assistance, mobility systems |
Prior knowledge |
|
Learning objective |
Acquire advanced and deep knowledge on core components of intelligent transportation systems |
Recommended Literature |
|
Language |
English |
Related Lectures |
|
Recommended Lectures |
|
[700.320] Telecommunication Systems
Semester |
Winter semester |
Allocation in the Curriculum |
Master Curriculum, Information Technology
|
Recommended Semester |
|
Teacher |
Prof. Kyandoghere Kyamakya, Transportation Informatics Group, Institute of Smart Systems Technologies Email: kyandoghere.kyamakya@aau.at |
Type of lecture and number of credits |
VK (lecture with integrated course, project, exercises or mini-seminar) 2 SWS, 4 ECTS |
Description |
|
Topics |
1. Introduction to Telecommunications 2. Mathematical Basics -1: GRAPH THEORY 3. Mathematical Basics -2: TRAFFIC THEORY 4. Network Reliability & Availability basics 5. The OSI Model 6. Standards and regulation issues 7. Convergence of Telecommunication Systems 8. Billing issues in Telecommunication Systems 9. Value added Services in Telecommunications 10. Telecommunication Systems for Intelligent Transportation Systems 11. Students' short seminar on selected Telecom. Systems |
Keywords |
|
Prior knowledge |
|
Learning objective |
|
Recommended Literature |
|
Language |
English |
Related Lectures |
|
Recommended Lectures |
[700.300] Logistics Systems Analysis and Engineering
Semester |
Winter semester |
Allocation in the Curriculum |
Master Curriculum, Information Technology
|
Recommended Semester |
|
Teacher |
Prof. Kyandoghere Kyamakya, Transportation Informatics Group, Institute of Smart Systems Technologies Email: kyandoghere.kyamakya@aau.at |
Type of lecture and number of credits |
VK (lecture with integrated course, project, exercises or mini-seminar) 2 SWS, 4 ECTS |
Description |
|
Topics |
1. Introduction to Logistics Systems 2. Shared Solutions to Common Challenges 3. Freight Transportation: An Overview 4. Understanding Supply Chain Networks 5. Supply Chain Network Processes and performance measurements 6. Modelling and Managing Supply Chain Networks 7. Information Technology in Supply Chain Management & Logistics 8. Forecasting Logistics Requirements 9. Designing the Logistics Networks 10. Solving Inventory Management Problems 11. Designing and Operating a Warehouse |
Keywords |
|
Prior knowledge |
|
Learning objective |
|
Recommended Literature |
|
Language |
English |
Related Lectures |
|
Recommended Lectures |
[700.395] Data Mining in Intelligent Transportation and Logistics
Semester |
Winter semester |
Allocation in the Curriculum |
Master Curriculum, Information Technology
|
Recommended Semester |
|
Teacher |
Prof. Kyandoghere Kyamakya, Transportation Informatics Group, Institute of Smart Systems Technologies Email: kyandoghere.kyamakya@aau.at |
Type of lecture and number of credits |
VK 2 SWS, 4 ECTS |
Description |
The goal of this course is to give the students the algorithmic methods at the heart of successful data mining-including tried and true techniques. Finally, some concrete applications of practical interest will be provided. |
Topics |
1. Introduction to MATLAB 2. Mathematical basics 3. Data selection and preparation 4. Bayesian classifier 5. Linear models 6. Non linear models 7. Prediction 8. Time Series Analysis 9. Collaborative filtering 10. Optimization metrics 11. Evaluation Metrics |
Keywords |
Optimization, Classification, Prediction, Optimization |
Prior knowledge |
Basics of linear algebra and basics in programming |
Learning objective |
|
Recommended Literature |
|
Language |
English |
Related Lectures |
|
Recommended Lectures |
Fundamentals of Image Processing Seminar on Pattern Recognition and Data Mining in Intelligent Vehicle Technologies |
[700.304] Fundamentals of Image Processing
Semester |
Winter semester |
Allocation in the Curriculum |
Master Curriculum, Information Technology
Bachelor Curriculum, Informationstechnik
|
Recommended Semester |
1. Semester Information Technology (Master) 4. Semester Information Technology (Bakk.) |
Teacher |
Prof. Kyandoghere Kyamakya, Transportation Informatics Group, Institute of Smart Systems Technologies Email: kyandoghere.kyamakya@aau.at |
Type of lecture and number of credits |
VK 2 SWS, 3 ECTS |
Description |
It is an introductory course to the fundamentals of digital image processing. It emphasizes general principles of image processing, rather than specific applications. |
Topics |
1. Introduction (color systems & image formats) 2. Thresholding Techniques 3. Edge Detection 4. Binary Shape Analysis 5. Boundary Pattern Analysis 6. Mathematical Morphology 7. Hough Transformation 8. Fourier transformation 9. Polygon and Corner Detection 10. Image Filtering 11. Image interpolation 12. Epipolar Geometry 13. Camera Calibration |
Keywords |
Computer Vision, Filtering, Image transformation |
Prior knowledge |
none |
Learning objective |
|
Recommended Literature |
|
Language |
English |
Related Lectures |
|
Recommended Lectures |
|
[700.340] Machine Vision in Intelligent Transportation
Semester |
Winter semester |
Allocation in the Curriculum |
Master Curriculum, Information Technology
|
Recommended Semester |
1. Semester Information Technology (Master) 4. Semester Information Technology (Bakk.) |
Teacher |
Prof. Kyandoghere Kyamakya, Transportation Informatics Group, Institute of Smart Systems Technologies Email: kyandoghere.kyamakya@aau.at |
Type of lecture and number of credits |
VK 2 SWS, 4 ECTS |
Description |
|
Topics |
1. Dynamic Vision based Intelligence 2. Autonomous landing of airplanes by dynamic machine vision 3. Visual servoing based on dynamic vision 4. Adaptive Deformable Models for Graphics and Vision 5. Introduction to Predictive Filters with some application example in computer vision 6. Robust pedestrian detectio 7. Cellular neural networks for motion estimation and obstacle detection 8. An Adaptive Architecture for Hierarchical Vision Systems 9. Vision Guided Landing of an Autonomous Helicopter in Hazardous Terrain 10. Feature tracking using vision on an autonomous airplane 11. Implementation of a CNN-based perceptual framework on a roving robot 12. Traffic sign detection for driver support systems 13. Stereo vision: principles + CNN (cellular neural networks) based approach 14. Principles of scene analysis and image understanding |
Keywords |
|
Prior knowledge |
|
Learning objective |
|
Recommended Literature |
|
Language |
English |
Related Lectures |
|
Recommended Lectures |
[700.730] Seminar on Pattern Recognition in Intelligent Vehicle Technologies
Semester |
Summer semester |
Allocation in the Curriculum |
Master Curriculum, Information Technology
Bachelor Curriculum, Informationstechnik
|
Recommended Semester |
|
Teacher |
Prof. Kyandoghere Kyamakya, Transportation Informatics Group, Institute of Smart Systems Technologies Email: kyandoghere.kyamakya@aau.at |
Type of lecture and number of credits |
SE 2 SWS, 4 ECTS |
Description |
In the lecture we deal with various aspects of pattern recognition and their applications in Image processing for INTELLIGENT VEHICLES
TECHNOLOGIES and ROBOTICS. Different classification methods for both statistical and stochastical approaches will be presented.
|
Topics |
1. Introduction/Overview to Pattern Recognition 2. Introduction, k-nearest-neighbor 3. k-means, Gaussian distributions, Gaussian classifier 4. Principal components analysis 5. linear regression, pseudo-inverse 6. Fisher linear discriminants 7. Perceptron, Perceptron learning algorithm 8. Multi-layered neural networks, backpropagation 9. Support Vector Machine 10. Applications in Image processing / machine Vision 11. Introduction to ROBOTICS 12. Introduction to Advanced Driver assistance Systems (ADAS) |
Keywords |
|
Prior knowledge |
|
Learning objective |
|
Recommended Literature |
|
Language |
English |
Related Lectures |
|
Recommended Lectures |
Courses and Labs [KU]
[700.371] Nonlinear Dynamics - Modeling, Simulation and Neuro-Computing
Semester |
Summer semester |
Allocation in the Curriculum |
Master Curriculum, Information Technology
|
Recommended Semester |
|
Teacher |
Ass.Prof. Jean Chamberlain Chedjou , Prof. Kyandoghere Kyamakya Transportation Informatics Group, Institute of Smart Systems Technologies |
Type of lecture and number of credits |
KU 2 SWS, 3 ECTS |
Description |
The first part of this lecture provides in-depth information concerning the modelling process with specific applications in transportation. The second part considers several mathematical models (e.g. ODEs and/or PDEs) and, some classical analysis methods are used to derive approximate analytical solutions. The theory of stability is considered with application to some concrete mathematical models. The third part is concerned with the investigation of several mathematical models using both numerical and experimental methods. A comparison is performed between the analytical, numerical and experimental results. The fourth part of the lecture is focused on Neuro-computing. Some basics of Neuro-computing are provided and some applications are considered in transportation (e.g. solving ODEs, PDEs, etc.). The optimization concept is considered together with some specific applications of practical interest in transportation. |
Topics |
1. Fundamentals of dynamical systems 2. Analysis methods for nonlinear dynamical systems 3. Applications of the analysis methods to concrete mathematical models 4. Numerical solution of Nonlinear Ordinary differential Equations 5. Numerical solution of Partial differential Equations 6. Background of the Oscillatory theory 7. Bifurcation analysis and applications to concrete mathematical models 8. Application of the oscillator theory in image processing 9. Fundamentals of Neuro-computing 10. Background of Optimization and related applications in transportation 11. Application of the CNN paradigm |
Keywords |
Modelling, ODEs, PDES, Stability, Analytical methods, Numerical methods, Oscillatory theory, Bifurcation, Image processing based on nonlinear oscillators, Experimental methods, Neuro-computing, ANN, CNN, Optimization in Transportation. |
Prior knowledge |
Good basics in System-theory, Mathematics and Programming |
Learning objective |
|
Recommended Literature |
|
Language |
English |
Related Lectures |
|
Recommended Lectures |
[700.301] GIS (Geographic Information Systems) - Expert Systems in Transportation
Semester |
Winter semester |
Allocation in the Curriculum |
Master Curriculum, Information Technology
|
Recommended Semester |
|
Teacher |
Prof. Kyandoghere Kyamakya Transportation Informatics Group, Institute of Smart Systems Technologies Email: kyandoghere.kyamakya@aau.at |
Type of lecture and number of credits |
KU 3 SWS, 3 ECTS |
Description |
The goal of this lecture is to help the students to develop fundamental GIS skills in a variety of areas such as data conversion, map
symbology, and projections.
|
Topics |
1. Fundamentals of GIS 2. Terrestrial data structures, representing the real world 3. GIS Data Structures representing the world in a computer 4. Data Quality An essential ingredient 5. Data Input: preparation, integration, and editing (Image processing basics, Satellites, GPS, Remote sensing) 6. Data analysis and modelling 7. Fundamentals of expert systems 8. First order logic 9. Resource Description Framework 10. Ontology Web Language 11. Semantic Web Rule Language 12. GIS application examples |
Keywords |
Expert Systems, Modelling, Ontology, Logic, |
Prior knowledge |
Basic programming skills |
Learning objective |
|
Recommended Literature |
|
Language |
English |
Related Lectures |
|
Recommended Lectures |
[700.302] Lab Fundamentals of Image Processing
Semester |
Winter semester |
Allocation in the Curriculum |
Master Curriculum, Information Technology
|
Recommended Semester |
|
Teacher |
n.n Transportation Informatics Group, Institute of Smart Systems Technologies Email: |
Type of lecture and number of credits |
KU 2 SWS, 3 ECTS |
Description |
In this Lab. we are focusing on the fundamental concepts of image processing and machine vision. Different topics such as Image enhancement, blob analysis, transformations, grouping and fitting, geometric vision, Hough transform, recognition and basic of Artificial Neural Network have been considered. Student can practice how to implement image processing algorithms in Matlab and OpenCV with C++. |
Topics |
1. Machine Vision Introduction and Image formation 2. Grouping and fitting 3. Geometric vision 4. Recognition 5. Artificial Neural Network |
Keywords |
Image processing, machine vision, image enhancement, MATLAB, recognition, matching, ANN, blob analysis, Hough transform. |
Prior knowledge |
Basics in Mathematic, Familiar with Matlab programming. |
Learning objective |
They can solve simple image processing and machine vision problems with MATLAB. |
Recommended Literature |
|
Language |
English |
Related Lectures |
|
Recommended Lectures |
[700.303] Methods of Transportation Informatics and Logistics
Semester |
Winter semester |
Allocation in the Curriculum |
Master Curriculum, Information Technology
|
Recommended Semester |
|
Teacher |
Ass.Prof. Jean Chamberlain Chedjou Transportation Informatics Group, Institute of Smart Systems Technologies Email: Jean.Chedjou@aau.at |
Type of lecture and number of credits |
KU 2 SWS, 3 ECTS |
Description |
|
Topics |
1. General Introduction; Systems Theory; Principles of modeling Dynamic Systems. 2. Basics of MATLAB + SIMULINK 3. Analog Computing - 1 (Basics) 4. Analog Computing - 2 (CNN) 5. Basics of Artificial Neural Networks (ANN) 6. Basics of Graph Theory 7. Queuing-1 8. Queuing-2 + Examples in MATLAB 9. Basics of the theory of traffic flow: Mathematical models for microscopic and macroscopic flows- simulation concepts. 10. Traffic- control based on the concept of "Nonlinear Dynamics" 11. Modeling of "Optimization problems" and solutions based on the CNN- paradigm 12. Statistical Analysis of Stochastic Scenarios/Phenomena 13. Scheduling - Basics + Examples 14. Operations Research - Basics 15. Small project on one of the themes addressed |
Keywords |
|
Prior knowledge |
|
Learning objective |
|
Recommended Literature |
|
Language |
English |
Related Lectures |
|
Recommended Lectures |
[700.372] Simulation Lab for Transportation and Logistics
Semester |
Winter semester |
Allocation in the Curriculum |
Master Curriculum, Information Technology
|
Recommended Semester |
|
Teacher |
Ass.Prof. Jean Chamberlain Chedjou Transportation Informatics Group, Institute of Smart Systems Technologies Email: Jean.Chedjou@aau.at |
Type of lecture and number of credits |
KU 2 SWS, 3 ECTS |
Description |
|
Topics |
1. Introduction to Traffic Simulation, Management and control. 2. Overview of the traffic Simulation models 3. Overview of the traffic Management, Control and Optimization Systems/tools (Synchro7, Cube5, Vissim, Visum, Spot, Utopia, Transyt, Sidra, SCOOT, SCAT, etc.) 4. Simulation of Traffic scenarios using "SYNCHRO-7" 5. Simulation of Traffic scenarios using "CUBE-5" 6. Traffic Control using the "CNN- paradigm" 7. Analysis of "Optimization problems" in Transportation using the "CNN- paradigm" 8. Simulation of "Graphs & Queuing" in Transportation Using the CNN- paradigm. 9. Modeling and Simulation of Logistic scenarios using "VENSIM". 10. Modeling and Simulation of Logistic scenarios using "STELLA". 11. Small project on one of the themes addressed |
Keywords |
|
Prior knowledge |
|
Learning objective |
|
Recommended Literature |
|
Language |
English |
Related Lectures |
|
Recommended Lectures |
[700.373] Lab: Machine Vision and Smart Sensors for Intelligent Vehicles
Semester |
Winter semester |
Allocation in the Curriculum |
Master Curriculum, Information Technology
|
Recommended Semester |
|
Teacher |
Ahmad Haj Mosa Transportation Informatics Group, Institute of Smart Systems Technologies Email: Ahmad.HajMosa@aau.at |
Type of lecture and number of credits |
KU 2 SWS, 3 ECTS |
Description |
This Lab delivers an overview of machine vision and image processing. Our focus will be in some basic and advanced methods such us Image
enhancement, Houch transform , Edge detection, face detection. Handwriting recognition, Active apprience modeling, 3D reconstruction. and
image enhancement.
|
Topics |
1. Introduction to Machine Vision 2. Object Representation and Description 3. Spatial Processing 4. Frequency Domain Processing 5. Image Restoration 6. Advanced Filtering Techniques (Diffusion filtering). 7. Segmentation 8. Advanced Segmentation Methods (Mean shift, Active contours, Watersheds) 9. Camera vision (2D&3D) 10. Image Stitching (Panorama) 11. Motion Estimation and Object tracking(Kalman Tracking, Optical Flow) 12. Visual Pattern Recognition (PCA, LDA, SVM) 13. Statistical Shape Modeling (AAM,ASM) 14. Some Medical Imaging Examples |
Keywords |
|
Prior knowledge |
Basics in Mathematic, Familiar with Matlab programming or .NET |
Learning objective |
Build smart vision systems using Matlab or C# |
Recommended Literature |
|
Language |
English |
Related Lectures |
|
Recommended Lectures |
Research Seminar and Project
[700.398] Research Seminar on Transportation Informatics
Semester |
Summer semester |
Allocation in the Curriculum |
Master Curriculum, Information Technology
|
Recommended Semester |
|
Teacher |
Prof. Kyandoghere Kyamakya, Transportation Informatics Group, Institute of Smart Systems Technologies Email: kyandoghere.kyamakya@aau.at |
Type of lecture and number of credits |
SE 2 SWS, 6 ECTS |
Description |
In this research seminar topical subjects in the area of Intelligent Transportation Systems will be regarded. Based on topical scientific publications on a particular subject participants develop a powerpoint presentation and a paper on the selected topic, and finally give a talk for their fellow students and their supervisor. NOTE: The seminar will be held in blocks. Topics will be presented and assigned in the first meeting. Also the semester's schedule will be presented in the first meeting. |
Topics |
|
Keywords |
|
Prior knowledge |
|
Learning objective |
|
Recommended Literature |
Scientific Publications |
Language |
English |
Related Lectures |
|
Recommended Lectures |
[700.396] Research Project on Transportation Informatics
Semester |
Summer semester |
Allocation in the Curriculum |
Master Curriculum, Information Technology
|
Recommended Semester |
|
Teacher |
Prof. Kyandoghere Kyamakya, Transportation Informatics Group, Institute of Smart Systems Technologies Email: kyandoghere.kyamakya@aau.at |
Type of lecture and number of credits |
KU 8 SWS, 12 ECTS |
Description |
Students work independently on a research oriented project. |
Topics |
|
Keywords |
|
Prior knowledge |
|
Learning objective |
|
Recommended Literature |
|
Language |
English |
Guest Lectures
[621.010] Diskrete Steuerungen 1
Semester |
Winter semester |
Allocation in the Curriculum |
Master Curriculum, Information Technology
|
Recommended Semester |
|
Teacher |
Prof. Dr.-Ing. habil. Wolfram Büttner, Institute of Applied Informatics Email: Wolfram.Buettner@aau.at |
Type of lecture and number of credits |
VK 2 SWS, 3 ECTS |
Description |
The control of such diverse processes as railroading or manufacturing, chemical processes in a steel mill or information processing on a chip follows a common principle: The control algorithm (controller) owns an image or abstraction of the dynamics of the process consisting of sequences of states. If the process is in a certain state and the controller receives some input, i.e. a command or some feedback from the process, then the controller will compute a suitable control action (output). This action will influence the dynamics of the process in such a way that the "new" image of the process equals a "next" state which the controller also computes. In short, the process is controlled by a sequence of suitable control actions which ensure that the process achieves its objective. A discrete controller has only finitely many states, inputs and outputs. The lecture will teach fundamental techniques for specifying, synthesizing and verifying discrete controllers. Representative tasks as arising in the design of discrete controllers will demonstrate how to apply those techniques. |
Topics |
Motivation
|
Keywords |
Controllers; discrete controllers; Boolean algebra; finite automata; specification, programming, synthesis and verification of discrete controllers |
Prior knowledge |
No particular prior knowledge required |
Learning objective |
Mastering the basic techniques required for designing hardware and software implementations of discrete controllers |
Recommended Literature |
|
Language |
German |
Related Lectures |
|
Recommended Lectures |
Having heard the lecture "Design of digital systems" is useful but not mandatory |
Curricula
Curriculum Master
official german version
inofficial english translation
Curriculum Bachelor
official german version
inofficial english translation
Contact
Dr.-Ing. Kyandoghere Kyamakya
Contact
Students Representatives
Website
Research Groups
Control and Measurement Systems
Embedded Systems and Signal Processing