Print
Univis
Search
 
FAU-Logo
Techn. Fakultät Willkommen am Institut für Informatik FAU-Logo

Computer Vision [CV]

Summary


Dates & Rooms:
Thursday, 12:15 - 13:45; Room: 0.68
Tuesday, 9:00 - 10:30; Room: 0.68



Course Description

Computer Vision involves the (semi-) automatic extraction of
information from images. The image data itself can take many forms:
color or black-and-white images, video sequences, multiple cameras,
data from medical scanners, etc. The information that should be
extracted can also vary depending on the application: locating an
object in an image (image database search), precisely measuring the
dimensions of an object (quality control), following a moving item
(surveillance), identifying letters and numbers (optical character
recognition), estimating the position  and orientation of a specific
object (robot arm guidance), etc. As a result, the field of computer
vision covers a wide variety of topics, which may sometimes, at first
glance, seem unrelated.

This course provides an introduction to the field of Computer Vision,
focusing on the underlying algorithmic, geometric and optic issues. It
starts with a description of image formation, including geometric,
optic and electronic aspects of the image formation process. Lower
level algorithms are then presented on the extraction of different
types of image features (edge detection, texture, color,
multi-resolution analysis, Hough transform, deformable contours). The
course will also cover topics associated with extracting information
from multiple images (stereo, motion). The last set of topics will
cover higher level analysis like grouping, and classification with
examples on image retrieval and face detection.

 

 

Exam

  • The marked examinations can be inspected on Tuesday, September 23, 2014 from 8-10am in room 0.151-115 (Cauerstr. 7/9, 91058 Erlangen).
  • The distribution of grades is: 
         Grade:  #
         1.0        6
         1.3       13
         1.7        7
         2.0       16
         2.3        6
         2.7        3
         3.0        2
         3.3        4
         3.7        3
         4.0        3
         4.3        0
         4.7        1
         5.0        3
  • Mean grade:     2.2 +- 1.0
    Median grade:  2.0
  • For students preparing a CV-project, the grades will be transferred to MeinCampus, when the final grades are known.

General Information

  • Tuesday's lectures start 10 minutes earlier. They are from 8:50am to 10:20am.
  • Tentative course syllabus: It provides a roadmap to the lectures throughout the semester.
  • The lecture videos from Summer Semester 2012 are available Opens external link in new windowhere. (They are only accessible from inside the university network; If you want to watch the videos from home, consider tunnelling the connection).
  • There will be a review lecture on Thursday 03. July 2014. This will give everybody more time to prepare for the review lecture.

  • IMPORTANT UPDATE:

    The Computer Vision Exam is now a WRITTEN EXAM on Saturday 19. July 2014 in room H11 (Cauerstr. 11, 91058 Erlangen), 10am-12noon.

Slides

The updated slides will be posted on the web soon after the corresponding lecture is completed.

In order to prepare yourself for an upcoming lecture, look at the Opens internal link in current windowslides of the previous Summer semester.

 

IntroductionA brief introduction to the various topics of computer vision, course motivation and guidelines.
Image FormationLens, radiometry, geometric optics, coordinate systems, projection.
Cameras: Digital image capture: from image irradiance to pixel values.
Smoothing: Sensor noise and methods for reducing image noise, convolution.
Edge Detection: Gradient-based edge detection, Canny edge detector, Laplacian of Gaussian, Gaussian pyramid, Laplacian pyramid.
Texture: Texture recognition, oriented filters, texture synthesis, shape from texture.
Color:The physics of color, trichromacy, color perception, color spaces, example applications.
Hough Transform:Line detection, circle detection, ellipse detection, HT for arbitrary shapes.
Deformable Models: Active contours, energy functional, greedy minimization, implementation adaptations.
Binocular Stereo: Basic binocular stereo setup, disparity, triangulation, correspondence problem.
Structured Light:Structured light setup, triangulation, binary coding, Kinect sensor.
Multiview Geometry:Epipolar geometry, epipolar constraint, eight-point algorithm.
Motion Analysis:Background subtraction, optic flow, motion field, optic flow computation.
Kalman Filtering:Predictive motion analysis, dynamic system under observation, Kalman filter formulation, extended Kalman filter.
Particle Filtering:Markovian dynamic systems, Bayesian estimation, particle filters, marginalized particle filters.
SIFT:Scale Invariant Feature Transform, keypoint detector, SIFT feature vector construction, Bag of Words
Case Study:Building Rome in a Day.

Supplemental Material

A nice refresher on the linear algebra concepts used in Computer Vision can be found in the attached set of Initiates file downloadslides by Silvio Savarese.

Another very good source of how we linear algebra in imaging is any good textbook on Computer Graphics (e.g. Computer Graphics: Principles and Practice by Hughes, van Dam, McGuire et al; Computer Graphics by Hearn and Baker; Fundamentals of Computer Graphics by Shirley, Ashikhmin, and Marschner) and in particular the chapters on geometrical transformations and viewing

There is a vast selection of tutorials, guides, and books on how to use OpenCV. Here are some possibilities: