Progettazione di Sistemi Embedded
Design of Embedded Systems Claudio Turchetti
Programmable digital systems,basic electronics,digital signal processing.
KNOWLEDGE AND UNDERSTANDING:
The course aims to provide the necessary hardware and software knowledge for designing embedded system in general and computer vision systems in particular. To this end the fundamental ARM architectures, the programming languages for embedded systems will be studied.CAPACITY TO APPLY KNOWLEDGE AND UNDERSTANDING:
The course is intended to train the students so that they acquire the capability of applying the knowledge to the design specifications of an embedded system, to the selection of devices to obtain the desired performance, to the definition and implementation of algorithms for computer vision.TRANSVERSAL SKILLS:
The course provides a multidisciplinary background on emebedded microcontrollers and microprocessors, computer vision techniques, which can be spent in the fields of biomedical engineering, telecommunications, automatic control and information technology in general.
ARM Embedded Systems ARM Architecture; The RISC design philosophy; Instruction Set for Embedded Systems; Embedded System Hardware; ARM Bus Technology; AMBA Bus Protocol; ARM Processor Fundamentals Registers; Banked Registers; Exceptions, Interrupts, and the Vector Table; Introduction to the ARM Instruction Set; Introduction to the Thumb Instruction Set; ARM Assembler Structure of assembly language modules; Directives; Processors STM32F4(Cortex-M4/ARMv7_M); Raspberry PI(ARM1176JzF-S/ArMv6); MC1322x (ARM7TDMI-S, ARMv4T); Introduction to C programming of ARM processors.
Embedded system for monitoring of physiological signals: ECG, PPG, EMG.
Embedded Systems for Navigation in Mobile Robots Localization; Dynamics and Control.
Embedded Systems for Computer Vision in Mobile Robots: Image Processing; Matrix theory results; Random signals; Stationary processes; Estimation theory; Mean Square Estimation; Orthogonality Principle; Image Transforms; Outer Product Expansion and Singular Value Decomposition; Image Filtering and Restoration; Image formation models; Inverse Filter; Wiener Filter; Filtering using image transform; Bayesian Signal Processing; Recursive filtering; Single-stage Wiener-Kalman Filter; Multi-stage Wiener Kalman Filter; Non-linear Bayesian tracking; Grid-based method; Particle Filters; Sequential Important Sampling (SIS) Algorithm; Digital Image Processing with MATLAB; Video Tracking; The basic equations of motion field; Estimating the motion field from image sequences; An optical flow algorithm; Feature tracking; Simultaneous Localization and Mapping (SLAM).
Embedded Systems for Machine Learning Introduction to statistical learning
Development of the examination
LEARNING EVALUATION METHODS
LEARNING EVALUATION CRITERIA
To pass the exam the student will show to know all the metodologies and techniques for designing an embedded system
LEARNING MEASUREMENT CRITERIA
A score in the range 18-30 will be given as a final grade
FINAL MARK ALLOCATION CRITERIA
The oral examination will be focused on questions concerning the course topics and the discussion of a specific design with refernece to the approach used and the results obtained
A.N.Sloss,D.Symes,C.Wright, ARM System Developers Guide, Elsevier, 2004;
P.Coke,Robotics, Vision and Control, Springer,2013.
K.Jain, Fundamentals of Digital Image Processing, Prentice Hall;
J.V.Candy, Bayesian Siganl Processing,Wiley,2009.
Appunti del docente.
- Ingegneria Elettronica (Corso di Laurea Magistrale (DM 270/04))