TeachingWs17TDCV

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 2017/18

Administrative Info

Lecture by Dr. Slobodan Ilic
Exercises by: Haowen Deng, Sergey Zakharov, Tolga Birdal, Mai Bui

Type: Lecture Module IN2210
Programs: Informatics (Bachelor, Master)
Biomedical Computing (Master)
Robotics, Cognition, Intelligence(Master)
SWS: 2+4
ECTS: 7 Credits
Course Language: English

Time, Location & Requirements

Lectures: every Monday starting from 23.10.2017 at 14:00-16:00h in 00.13.009A.

Exercises: every Thursday starting from 02.11.2017 at 14:00-16:00h in 00.13.009A.

Requirements:

  • 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.
  • There is no repetition exam.

Contents

Overview

Computer Vision 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. The course will address both hand crafted features and learned features with deep learning approaches. So it will be mixture of established ane emerging methods for object detection, recognition, pose estimation and tracking.

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.

Announcements

The exams are:

  • Results of final course grades can be downloaded from this link.
  • Results of final exam can be downloaded from this link.
  • Results of exercise3 evaluation can be downloaded from this link.
  • Results of exercise2 evaluation can be downloaded from this link.
  • Results of exercise1 evaluation can be downloaded from this link.
  • Mid-term results can be downloaded from this link.
  • Mid-term: Thursday 30.11.2017, 18:30 to 20:00, Location: MW 2001, Rudolf-Diesel-Hörsaal (5510.02.001)
  • Final exam: Friday 23.02.2018, 16:00 to 18:00, Location: MW 0001, Gustav-Niemann-Hörsaal (5510.EG.001)

Exercise projects

The exercises will be done in MATLAB and Python and students are expected to do them on their own computer/laptop. They will consist of four projects that will include one or several topics presented at the lectures. The projects will be presented to the students during the semester and deadlines for the presentations and submissions of the results will be provided. During the regular exercise classes student can work on the project and ask questions to the tutors.

The exact due dates for each project are announced next to the exercise description on this website and will be defined beforehand (check exercise section). Students have to make groups of TWO students and send the names to tdcv.tum@gmail.com. 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. If you are looking for a (TDCV) partner tell us and we will assign you one!

During the the presentation of the results for each project each group will have 10 min to present their solution in terms of slides, and also run the code live. This will be followed by questions from the professor, tutors and other students (~10min). 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 project results presentation! If you have questions, ask them beforehand during the exercise sessions.

All homework should be submitted through e-mail at least one hour before the exercise session with the following format and information.

  1. To: tdcv.tum@gmail.com
  2. Subject: [TDCV17] Exer<exercise number> - <group number> - <last names of all members>
    For example: [TDCV17] Exer1 - Group42 - 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.

You can also find a short MATLAB tutorial here.

Registration

You are required to register via TUMOnline (link)!

Textbooks

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. For machine learning topics it is recommended to use the book of Christopher Bishop, Pattern Recognition and Machine Learning. And for deep learning, the Stanford course on CNNs available 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
23.10. Introduction Dr. S. Ilic Introduction
30.10. Camera models, Model based tracking, Pose estimation from 2D-3D coresspondencies (DLT, P-n-P), Rotation parametrization Dr. S. Ilic Camera models and pose estimation
Related paper:
1. Monocular Model-Based 3D Tracking of Rigid Objects: A Survey.
06.11. Non-linear optimization, Robust estimators, RANSAC Dr. S. Ilic Non-linear optimization, Robust estimators, Ransac
13.11. Convolution, Non-linear filtering, Gaussian filtering, Image derivatives, Edge detection Dr. S. Ilic Filtering and Edge Detection
20.11. Local invariant feature detectors(Harris corners, FAST etc.) and feature descriptors(Difference of Gaussians and SIFT, SURF, HOG) Dr. S. Ilic Feature Detection
Related papers:
1. Feature detectors
2. Harris-Laplace
Feature descriptors
27.11. Keypoint recognition: Randomized and regression trees, FERNS, Hough forests Dr. S. Ilic Keypoint recognition
30.11. Midterm exam Dr. S. Ilic Midterm exam
Solutions midterm exam
04.12. Feature learning and Classification with Deep Neural Networks Dr. S. Ilic Deep Neural Networks
11.12. Haar features; Integral images; Ada-Boost; Viola-Jon Dr. S. Ilic Face detection
18.12.      
08.01. Object detection with deep learning (R-CNN, Fast-RCNN, SSD) Dr. S. Ilic Object Detection with ConvNets
15.01. Canceled Dr. S. Ilic  
22.01. Object detection with deep learning (YOLO, SSD, SSD-6D, Triplet Loss)) Dr. S. Ilic Object Detection with ConvNets
29.01. Template matching Dr. S. Ilic Template Matching
05.02. No lecture Dr. S. Ilic  

Exercise Projects Schedule

If you have questions about a specific exercise, please direct them to the responsible tutor. At the due date the results of the projects will be presented by each group of students followed by the questions of the responsible professor and tutors. The students must send the code a day before the due date of the presentation of their project results. The students should be ready to run the code after their presentation as well as show parts of the code and be prepared to answer the questions about their implementation.

Date Topic Conducted by Material/Literature Sample Output
02.11.-14.12.(due date) Model based pose refinement and tracking T. Birdal Exercise1
Data
helperCode
-
07.12.-25.01.(due date) Random forest based object detection and classification H. Deng Exercise2
Data
Additional Material
Virtual Environment
 
18.01.-22.03.(due date) Object recognition and pose estimation with deep learning S. Zakharov, M. Bui Exercise3
Slides
Data
Environment
 

TeachingForm
Title: Tracking and Detection in Computer Vision
Professor: Dr. Slobodan Ilic
Tutors: Haowen Deng, Sergey Zakharov, Tolga Birdal, Mai Bui
Type: Lecture
Information: 2 + 4; 7 ECTS
Term: 2017WiSe
Abstract:  


Edit | Attach | Refresh | Diffs | More | Revision r1.48 - 31 Oct 2018 - 08:21 - SlobodanIlic

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