93668 - ANALISI DI IMMAGINI 3D E SISTEMI DI COMPUTER VISION

Course Unit Page

  • Teacher Alessandro Bevilacqua

  • Credits 6

  • SSD ING-INF/05

  • Language Italian

  • Campus of Cesena

  • Degree Programme Second cycle degree programme (LM) in Computer Science and Engineering (cod. 8614)

SDGs

This teaching activity contributes to the achievement of the Sustainable Development Goals of the UN 2030 Agenda.

Good health and well-being Industry, innovation and infrastructure

Academic Year 2020/2021

Learning outcomes

The objective of this Course is to form an engineer able to design computer vision systems working in the real world, even in real time, for industrial, scientific and play purposes. The systems exploit automatic analysis of 3D image sequences in a number of application fields including machine vision, automotive, automatic quality control, zero-defect analysis, predictive maintenance, security, medical and biomedical imaging, aerospace imaging, precision agriculture, cultural heritage. At the end of the Course, students are able to apply the acquired skills:

  • To apply computer vision in critical multidisciplinary fields, including medical imaging
  • To use cameras to perform high-accuracy 3D measurements
  • To realize augmented and mixed reality applications
  • To use vision sensors in IoT applications
  • To perform 3D scene reconstruction from moving aerial or terrestrial vehicle
  • To perform 3D scanning, also for 3D printing
  • To perform 3D defect analysis in industry
  • To design real time computer vision systems on parallel/distributed architectures

Course contents

- Computer vision: examples of systems and applications

- From sensor to image: basics of optics

- Real time image sequence and video analysis

- Semantic extraction of multi-dimensional features

- Perspective: a 2D projection of the real world

- From perspective to 3D: camera calibration, stereoscopy, triangulation

- From motion to 3D: the cloud points

- Cloud points and 3D geometric object representation

- Principles of real time processing (high throughput)

- Effective GPU programming

Case studies: the ongoing projects

Readings/Bibliography

  • R. I. Hartley, A. Zisserman: “Multiple View Geometry in Computer Vision”, Second Edition, Cambridge University Press, 2004
  • Richard O. Duda, Peter E. Hart, David G. Stork: “Pattern Classification”, Second Edition, Wiley Interscience, New York, 2001

Teaching methods

Classroom lessons and practice in lab. Each topic will be treated jointly with significant case studies developed in lab to highlight its meaningful applications. In order to make the students aware of the different topics, many homework exercises will be proposed and publicly corrected afterwards in lab.

Assessment methods

The students will be evaluated on the basis of homework assigned at the end of the main lectures (12/30), a computer vision project (15/30), developed either alone or in a small team, and an oral examination (6/30) regarding the most theoretical aspects of the topics presented. Honours will be marked when proving to use effectively the computer vision theory on a practical problem

Teaching tools

In the teaching material section all the slides shown in class are available for download as well as the software tools for practice in lab

Links to further information

https://cvg.deis.unibo.it

Office hours

See the website of Alessandro Bevilacqua