Filippo Bergamasco
PhD
Assistant Professor
Department of Environmental Sciences, Informatics and Statistics (DAIS)
Universtà Ca' Foscari of Venice
Via Torino, 155
Venezia Mestre 30172 - ITALY
Phone: +39 041 234 8418
Mail: filippo.bergamasco AT unive.it

Computer Vision 2016/2017

Official course page

http://www.unive.it/data/course/218005

Moodle page (requires course enrollment)

https://moodle.unive.it/course/view.php?id=962

Referral texts

- R. Szeliski. Computer Vision Algorithms and Applications. Springer - R. C. Gonzalez e R.E. Woods. Digital Image Processing (3rd edition). Pretience Hall



Final Project:

Download the package with all the information needed to develop your final project for the exam. Follow the instructions inside.

NOTE: Submission of the final project must be performed via moodle


Assignments:


Course slides:

  1. Introduction
  2. Image Formation Process
  3. Intensity transformations
  4. Color Vision
  5. Spatial Filtering
  6. Filtering in Frequency Domain
  7. Edge Features
  8. Morphological Image processing
  9. Finding Curves
  10. Point Features
  11. Geometric Primitives and Transformations
  12. The Pinhole Camera Model

Other materials:

Last Lesson:

> March 27st

Lab Session #4: The final project


Past Lessons:

> March 21st

The Pinhole camera model

  • Camera obscura
  • Cameras and Lenses
  • Radial distortion
  • The pinhole model
  • Intrinsic and Extrinsic parameters


> March 20th

Lab session #3

  • Geometric primitives
  • The 2D Projective space
  • Homogeneous coordinates
  • Projectivities
  • Image warping and interpolation


> March 14th

Point Features (part 2)

  • Scale-invariant Feature Transform (SIFT)


> March 13th

Point Features (part 1)

  • Harris corner detector


> March 7th

Finding curves

  • Finding lines
  • The RANSAC algorithm
  • The Hough transform for lines
  • The Hough transform for circles and other curves


> March 6th

Lab session #2: Morphological image processing

  • Dilation and Erosion
  • Opening and closing
  • Boundary following


> February 28th

Edge features

  • Features in computer vision
  • Edge models
  • Image gradient
  • Derivatives and noise
  • Marr-Hildreth edge detector
  • Canny edge detector

> February 27th

Filtering in the frequency domain

  • Continuous Fourier transform
  • DFT
  • Spectrum / Phase angle
  • 2D Convolution theorem
  • Low-pass, High-pass filters
  • Notch filters
  • Deconvolution


> February 21st

Spatial Filtering

  • Linear filter
  • Correlation and Convolution
  • Template matching
  • Smoothing
  • Order-statistic filter
  • Sharpening


> February 20th

Lab session #1


> February 14th

Color vision

  • Color fundamentals
  • Human vision
  • Color matching
  • Color models
  • Color cameras
  • Transformations
  • Chroma keying compositing


> February 13th

Intensity transformations

  • Negative
  • Gain/bias
  • Log/Gamma
  • Image Histogram
  • Otsu global thresholding


> February 7th

The image formation process

  • Light and the visible spectrum
  • The BRDF
  • The imaging process
  • Sampling and Quantization
  • Relationships between pixels


> February 6th

Introduction

  • Course informations
  • What is computer vision?
  • Optical illusions to understand human vision
  • Computer vision vs. Computer graphics
  • Applications
  • A brief history



Last update Tue Feb 08 2022 09:22:04 GMT+0000 (Coordinated Universal Time)