Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

THIS WEBPAGE IS DEPRECATED - please visit our new website

Tracking and Detection in Computer Vision - Winter Term 2014/15

Administrative Info

Lecture by Dr. Slobodan Ilic
Exercises by: Paul Huang, David Tan, Vasilis Belagiannis, Wadim Kehl

Type: Lecture Module IN2210
Programs: Informatics (Bachelor, Master)
Biomedical Computing (Master)
Robotics, Cognition, Intelligence(Master)
SWS: 2+2
ECTS: 5 Credits
Course Language: English

Time, Location & Requirements

Lectures: Monday 12:15h - 14:00h Media Raum MI 00.13.009A

Exercises: Thursday 12:00h - 14:00h Media Raum MI 00.13.009A

Consultation hours: Tuesday 14:00h - 16:00h Office of the responsible tutor(see names next to the exercise). To get an a slot for consultation send an e-mail to tdcv.tum@gmail.com latest on Sunday before the consultation hours.


  • The classes and exams are in English.
  • For the midterm exam, nothing but your pens and your calculators are allowed.
  • For the final exam, nothing but your pens, your calculators and one DIN A4 page (handwritten, front and back side) with notes are allowed.
  • Bonus points can be earned from the homework projects and the intermediate exam.
  • The final exam brings maximally 100 points. You need to have 50 points in order to pass it. Bonus points are irrelevant for the 50-points-hurdle and are added afterwards to your final exam score.
  • There is no repetition exam.

Site Content


  • Final Exam: Di 10.2.2015; 11:30-13:30; MW 2001, Rudolf-Diesel-Hörsaal (5510.02.001)
  • The dictionary learning exercise is the last exercise, and is considered as bonus. Students who do the exercise can come at 11:00-12:00 on Thursday, 05.Feb. to MI 03.13.010 for the corrections. Due time for code submission is 10am on the same day.
  • Mid-term results here. Students who would like to review their exam sheets can come to office MI 03.13.039 at 11:00-12:00 on Monday, 19.01.
  • The mid-term exam takes place at 12:00 on 27.Nov (Thur.) in Gustav-Niemann-Hörsaal. It is an close-book exam. Only non-programmable calculator is allowed.
  • The latest exercise-grouping list is here (UPDATED on 17.Nov).
  • For all questions please send e-mails to: tdcv.tum@gmail.com. E-mails sent directly to tutors and professors will not be answered. Tutors will only answer exercise-specific questions that they are in charge of.


The exercises will be done in MATLAB and students are expected to do them on their own computer/laptop. In case you do not have your own laptop please let us know by sending an e-mail to: tdcv.tum@gmail.com.

You can also find a short MATLAB tutorial here.


You are required to register via TUMOnline (link)!


Students will be given one week to solve the problems. The exact due dates for each homework are announced next to the exercises on this website and will be mentioned during the exercise sessions. Students have to make groups of TWO students and send the names to tdcv.tum@gmail.com until 20th of October. After that, those who didn't create groups will be associated to groups based on a random selection and will receive a notification about this.

During the checking of the exercises each group will have at 15 min to be questioned to answer the questions. All members of the group will be questioned about the algorithms and their implementation, so only those who can prove that they understood both theory and practice will get the respective points. Thus, having a working exercise doesn't mean that everyone in the group is going to get full points. Please note that only exercises which work might get the maximal number of points. There will be no "debugging-correcting"-sessions for your solutions during the exercise reviews! If you have questions, ask them beforehand by either mail or in person.

All homework should be submitted through e-mail at least one hour before the exercise session (11:00AM) with the following format and information.

  1. To: tdcv.tum@gmail.com
  2. Subject: [TDCV14] Exer<exercise number> - <last names of all members>
    For example: [TDCV14] Exer1 - Huang, Tan
  3. Attachment: The whole source code for this homework.
  4. Body: This should include the (a) full names and Matrikel-Nr. of each member; and, (b) reference to any code used in the homework that is not specified on the exercise sheet or by the tutors.


Computer Vision, as a relatively young research area, has emerged as a key discipline in computer science. This is not only evident by a growing and highly competitive research community with a high impact factor in computer science, but also by the emergence of numerous vision companies turning research ideas into a myriad of commercial applications. Besides well-known studies of 3D geometry and camera models, object tracking and detection in images and videos becomes one of the principal research directions of modern Computer Vision. The main objective of this course is to provide students with a gradual introduction to modern tracking, detection and recognition techniques developed in the last years. The course will provide in-depth knowledge of image features, their detection and description, matching techniques, key-point recognition, basic and advanced tracking algorithms based on image features and image intensities, basics of structure from motion and bundle adjustment, synchronous localization and mapping algorithms as well as object detection using classification approaches. In the end, the students will have a thorough description of the most important tracking and detection techniques. They should be able to understand and implement those solutions and apply them in reasonably complex problems. The concepts described in this course will be accompanied with brief explanations of the necessary mathematical tools. The participants of this course will be given an important basis to follow the vast and growing Computer Vision literature and use the acquired knowledge to solve new practical problems.

Who should attend this course?

Bachelor students in their last years and all Master students that are interested in learning about the modern and well-established concepts and algorithms related to tracking, detection and recognition in Computer Vision, or desire to use those techniques in their research.

Prerequisites: Most of the knowledge required should be part of the normal background in Computer Science, undergraduate/graduate Mathematics and Geometry.


For some basic concepts the textbook "Computer Vision: a modern approach" by David Forsyth and Jean Ponce can be used. Also, most topics can be found in a new book of Rick Szeliski from Microsoft Research, available also on-line. However, since the majority of the topics is state-of-the-art, students will be referred to the relevant publications which will be provided during the course and can be regarded as additional lecture notes.

Lecture Schedule and Content

Date Topic Conducted by Material/Literature
Mon, Oct 13 Introduction Dr. S. Ilic
Mon, Oct 20 Convolution, Non-linear filtering, Gaussian Filtering, Image Derivatives, Edge Detection Dr. S. Ilic
Mon, Oct 27 Local invariant feature detectors: Harris corner, Harris Laplace/Affine, Hessian, Hessian-Laplace/Affine, FAST Dr. S. Ilic
Mon, Nov 03 Feature descriptors: Difference of Gaussians and SIFT, Integral images and SURF, Histogram of Oriented Gradients Dr. S. Ilic
Mon, Nov 10 Keypoint recognition: Randomized trees, FERNS, Keypoint signatures Dr. S. Ilic
Mon, Nov 24 Camera models and projections, Model based tracking, Pose estimation from 2D-3D coresspondencies (DLT, P-n-P), Rotation parametrization Dr. S. Ilic
Mon, Dec 01 Non-linear optimization, Robust estimators, RANSAC Dr. S. Ilic
Mon, Dec 08 Template tracking methods: Lucas-Kanade, Compositional Alg., Inverse Compositional, ESM, Linear Predictor Dr. S. Ilic
Mon, Dec 15 Mean-shift tracking Dr. S. Ilic
Mon, Dec 22 No lectures. Dr. S. Ilic  
Mon, Jan 12 Template matching approaches Dr. S. Ilic
Mon, Jan 19 Kalman and particle filtering for object tracking Dr. S. Ilic
Mon, Jan 26 Tracking with Dictionary Learning Dr. S. Ilic

Exercise Schedule

Date Topic Conducted by Material/Literature
Thu, Oct 16 Matlab Introduction/Convolution, Gaussian Filtering, Image Derivatives (due on Oct 23) Paul Huang and David Tan
Thu, Oct 23 Median and Bilateral Filtering (due on Oct 30) Tolga Birdal and Danilo Djordjevic
Thu, Oct 30 Harris, Harris-Laplace (due on Nov 06) Danilo Djordjevic and Vasilis Belagiannis
Thu, Nov 06 Sift, Dlt, Ransac, Image Stiching (due on Nov 13) Wadim Kehl and Danilo Djordjevic
Thu, Nov 13 Ferns (due on Nov 20) Christian Rupprecht and Vasilis Belagiannis
Thu, Nov 20 Ada-boost classification (due on Dec 11) Fausto Milletari and Paul Huang
Thu, Nov 27 Mid term - -
Thu, Dec 11 Non-linear optimization (due on Dec 18) Paul Huang and Wadim Kehl
Thu, Dec 18 Template Tracking with Linear Predictor (due on Jan 08) Tolga Birdal and David Tan
Thu, Jan 08 Mean-shift Tracking (due on Jan 15) Mira and Fausto Milletari
Thu, Jan 15 Template matching(due on Jan 22) Wadim Kehl and Paul Huang
Thu, Jan 22 Kalman/Particle filter tracking (due on Jan 29) Vasilis Belagiannis and Christian Rupprecht
Thu, Jan 29 Optional: Dictionary learning approaches (due on Feb 05) Fausto Milletari and Tolga Birdal
Thu, Feb 05 Correction of dictionary learning. Room: MI 03.13.010. Time: 11am-12pm. Due time for code submission: 10am. Fausto Milletari -

Title: Tracking and Detection in Computer Vision
Professor: Dr. Slobodan Ilic
Tutors: Paul Huang, David Tan, Vasilis Belagiannis, Wadim Kehl
Type: Lecture
Information: 2+2 SWS, 5 ECTS, Wahlfach im Masterstudiengang Informatik, Wahlfach im Masterstudiengang Biomedical Computing, Wahlfach im Masterstudiengang Robotics, Cognition, Intelligence
Term: 2014WiSe

Edit | Attach | Refresh | Diffs | More | Revision r1.91 - 21 Jan 2016 - 15:40 - SlobodanIlic

Lehrstuhl für Computer Aided Medical Procedures & Augmented Reality    rss.gif