Göm meny

TSBB17 Visual Object Recognition and Detection

This course is worth 6 ECTS credits, which corresponds to approximately 160h of work per student. The time is divided among the following activities:

The course is given during the HT period. Note that not all the time slots in the course schedule will be used. A few spare slots have been reserved in case a lecture has to be moved. The actually planned lectures are listed below on this page, and any changes to this plan will be announced during the lectures, and on this page.

People

We all have our offices in the B-building, corridor D, first floor between entrances 25 and 27.

Documents

  • Detailed information and documents related to the two projects will be provided through the LISAM website .
  • Course description in Studiehandboken (the LiTH study guide)

Literature

  • Goodfellow et al., Deep Learning, MIT Press (2016).

    The book is available as full pdf. See also Book webpage.
  • Richard Szeliski, Computer Vision: Algorithms and Applications, Springer Verlag (2011).

    The book is available as an on campus e-book via the LiU library. See also Book webpage.
Material will be handed out or made available on the course LISAM webpage . For side reading on several topics, we have collected pointers to relevant literature available on the course LISAM webpage .

Registration

If you intend to take the course but are not registered, make sure to register ASAP, using the Student portal. You need to be registered on the course to receive course email, and to have results input to Ladok. If you take the course but are not registered to any program at the University, please contact the course examiner in order to make sure that you receive email about the course.

Examination

The course has a written examination in English.

Lecture schedule 2017

The Lecture slides and additional reading materials will be available on the course LISAM webpage.
Date,Time,Room Activity Teacher Material
August 28: 08.15-10
R23
Lecture 1
Introduction
Fahad Khan
August 29: 10.15-12
R23
Lecture 2
Feature Descriptors
Per-Erik
August 30: 13.15-15
R23
Lecture 3
Compound Descriptors and Metrics
Per-Erik
September 1: 08.15-10
R23
Lecture 4
Convolutional Neural Networks: Introduction and Theory
Michael Felsberg
September 04: 08.15-10
R23
Lecture 5
Image Classification with Convolutional Neural Networks
Michael Felsberg
September 05: 10.15-12
R23
Lecture 6
Project 1: Visual Object Recognition
Fahad Khan
September 06: 13.15-15
R23
Lecture 7
Visual Object Detection
Fahad Khan
September 12: 10.15-12
R23
Lecture 8
Visual Object Tracking: Introduction
Michael Felsberg
September 20: 13.15-15
R23
Seminar 1
Presentation of project 1
Fahad Khan
September 25: 08.15-10
R23
Lecture 9
Discriminative Correlation Filters for Visual Tracking
Michael Felsberg
September 26: 10.15-12
R22
Lecture 10
Project 2: Visual Object Tracking
Fahad Khan
October 10: 10.15-12
R23
Seminar 2
Presentation of project 2
Fahad Khan

Projects

The projects are conducted in groups of 5 or 4 students (in order of preference).

  • Project 1: Visual Object Recognition :
    Introductory lecture: September 05: 10.15-12, R23
    Report due: September 18
    Presentation seminar: September 20: 13.15-15, R23
  • Project 2: Visual Object Tracking:
    Introductory lecture: September 26: 10.15-12, R22
    Report due: October 8
    Presentation seminar: October 10: 10.15-12, R23

General resources

We suggest the use of following software:

  • MatConvNet Deep Learning library in Matlab.
  • Caffe Deep Learning library.
  • Theano Deep Learning library.
  • David Lowe's SIFT implementation for Matlab. This includes binary executables that are compiled into mex-code that runs from Matlab. If you don't know about Matlab mex-files ask your guide.
  • VLFeat has a a useful code library, both for Matlab and C/C++.  For example, there is an alternative implementation of SIFT here, and also an implementation of MSER here. Both are made by Andrea Vedaldi.
  • The Visual Geometry Group at Oxford University maintains code for affine invariant region detectors, produced in cooperation with other groups.
  • LIBSVM A Library for Support Vector Machines (Matlab, Python).

Project repositories

Project code should be developed under versioning control, with changes tracked according to LiU-ID of the participating group members.

  • Option A: Project groups get their repositories from GITLab at IDA Note: this is not GitHub, and GitHub should not be used.
  • Option B: On request each project group can get access to a Subversion repository, with individual login by each project member.

    Documentation for Subversion can be found here:

    If you are using a Windows based computer, we recommend that you use the Tortoise client for Subversion.


Senast uppdaterad: 2017-08-27