Teaching

Fall 2016 - Vision Algorithms for Mobile Robotics

UZH-BMINF010 / ETH-151-0632-00L

The course is open to all the students of the University of Zurich and ETH. Students should register through their own institutions.

Goal of the Course

For a robot to be autonomous, it has to perceive and understand the world around it. This course introduces you to the fundamental computer vision algorithms used in mobile robotics, in particular: feature extraction, multiple view geometry, dense reconstruction, object tracking, image retrieval, event-based vision, and visual-inertial odometry (the algorithm behind Google Tango). Basics knowledge of algebra, geomertry, and matrix calculus are required.

Time and location

  • Lectures: Every Thursday from 10:15 to 12:00 in ETH LFW C5, Universitätstrasse 2, 8092 Zurich.
  • Exercises: Thursdays, roughly every two weeks, from 14:15 to 16:00 in ETH HG E 33.1, Rämistrasse 101, 8092 Zurich.

Please check out the course agenda for the exact schedule (coming soon).

Course Program, Slides, and Add-on Material

Download the Official course program (PDF, 221 KB) - Please note that this is a tentative schedule and the effective content of the lecture can change from week to week.

Lecture Date Lecture and Exercise Title Slides and add-on material
22.09.2016 Lecture 01 - Introduction to Computer Vision and Visual Odometry Slides (last update 22.09.2016)
Visual odometry tutorial Part I (PDF, 526 KB)
Visual odometry tutorial Part II (PDF, 1710 KB)
29.09.2016 Lecture 02 - Image Formation 1: perspective projection and camera models Slides (last update 06.10.2016)
06.10.2016 Lecture 03 - Image Formation 2: camera calibration algorithms
Exercise 01 - Augmented reality wireframe cube
Slides (last update 18.10.2016)
Additional reading on P3P and PnP problems
Exercise 01 (last update 06.10.2016)
Introduction to Matlab
13.10.2016 Lecture 04 - Filtering & Edge detection
Exercise 02 - PnP problem
Slides (last update 13.10.2016)
Exercise 02 (last update 13.10.2016)
20.10.2016 Lecture 05 - Point Feature Detectors, Part 1
Exercise 03 - Harris detector + descriptor + matching
Slides (last update 20.10.2016)
Exercise 03 (last update 25.10.2016)
27.10.2016 Lecture 06 - Point Feature Detectors, Part 2 Slides (last update 27.10.2016)
Additional reading on feature detection
03.11.2016 Lecture 07 - Multiple-view geometry 1
Exercise 04 - Stereo vision: rectification, epipolar matching, disparity, triangulation
Slides (last update 10.11.2016)
Additional reading on stereo image rectification
Exercise 04 (last update 02.11.2016)
10.11.2016 Lecture 08 - Multiple-view geometry 2
Exercise 05 - Two-view Geometry
Slides (last update 16.11.2016)
Additional reading on 2-view geometry
Exercise 05 (last update 10.11.2016)
17.11.2016 Lecture 09 - Multiple-view geometry 3
Exercise 06 - P3P algorithm and RANSAC
Slides (last update 16.11.2016)
Additional reading on open-source VO algorithms
Exercise 06 (last update 16.11.2016)
24.11.2016 Lecture 10 - Dense 3D Reconstruction
Exercise 07 - Intermediate VO Integration
Slides (last update 30.11.2016)
Additional reading on dense 3D reconstruction
Find the VO project downloads below
01.12.2016 Lecture 11 - Optical Flow and Tracking (Lucas-Kanade)
Exercise 08 - Lucas-Kanade tracker
Slides (last update 30.11.2016)
Additional reading on Lucas-Kanade
Exercise 08 (last update 01.12.2016)
08.12.2016 Lecture 12 - Place recognition
Exercise 09 - Recognition with Bag of Words
Slides (last update 07.12.2016)
Additional reading on Bag-of-Words-based place recognition
15.12.2016 Lecture 13 - Visual inertial fusion
Exercise 10 - Bundle Adjustment
Exercise 10 (ZIP, 1736 KB) (last update 15.12.2016)
22.12.2016 Lecture 14 - Event based vision + Scaramuzza's lab visit with live demos
Exercise 11 - final VO integration
 

Grading and VO project (last udpate 26.10.2016)

70% of the final grade is based on the oral exam (30 minutes, exam date: 19.01.2017) and 30% on a visual odometry (VO) mini-project. Project specification and files can be found in the table below.

Description Link(size)
Project specification VO_project_statement_01.pdf (434 kB, last updated 24.11.2016)
FAQ Frequently Asked Questions
Solutions to all exercises all_solns.zip (40.3 kB, last updated 24.11.2016)
Parking garage dataset (easy) parking.zip (208.3 MB)
KITTI 00 dataset (hard) kitti00.zip (2.3 GB)
Malaga 07 dataset (hard) malaga-urban-dataset-extract-07.zip (2.4 GB)
Matlab script to load datasets main.m (2.6 kB)

Recommended Textbooks

  • Robotics, Vision and Control: Fundamental Algorithms, by Peter Corke 2011. The PDF of the book can be freely downloaded (only with ETH VPN) from the author's webpage.
  • Computer Vision: Algorithms and Applications, by Richard Szeliski, Springer, 2010. The PDF of the book can be freely downloaded from the author's webpage.
  • An Invitation to 3D Vision, by Y. Ma, S. Soatto, J. Kosecka, S.S. Sastry.
  • Multiple view Geometry, by R. Hartley and A. Zisserman.

All mentioned textbooks are available in the NEBIS catalogue.

Spring 2015 - Autonomous Mobile Robots

The course is currently open to all the students of the University of Zurich and ETH (Bachelor's and Master's). Lectures take place every Monday (from 16.02.2014 to 30.05.2014) from 14:15 to 16:00 in the ETH main building (HG) in room E 1.2. Exercise take place almost every second Tuesday from 10:15 to 12:00 in the ETH main building in room G1.

The course is also offered as a MOOC (Massive Open Online Course) on edX.

Course Program

Official course webpage.

Recommended Textbook


AMR

R. Siegwart, I.R. Nourbakhsh, and D. Scaramuzza

Introduction to autonomous mobile robots 2nd Edition (hardback)

A Bradford Book, The MIT Press, ISBN: 978-0-262-01535-6, February, 2011

MIT Website Book Website Buy

 

Archived slides, videos, and lecture recordings

Since 2007, Prof. Davide Scaramuzza has been teaching this course at ETH Zurich and since 2012 the course has been shared also with University of Zurich. The lectures are based on Prof. Scaramuzza's book Autonomous Mobile Robots, MIT Press. ETH students can watch previous lectures up until 2012 on the ETH multimedia portal.

All lecture slides and videos of past lectures (updated in 2010) can be downloaded from the following links: