EE 6485 Computer Vision 計算機視覺

Fall 2016, Wed. 3:30pm to 6:20pm, Location DELTA台達209
Instructor: Min Sun

TAs: 胡厚寧

Computer Vision, art by

Course Description

Can computers understand the visual world as we could? This course treats vision as a process of inference from noisy and uncertain data and emphasizes probabilistic, statistical, data-driven approaches. Topics include image processing; segmentation, grouping, and boundary detection; recognition and detection; motion estimation and structure from motion. This class will also lead you to the discussion of applications applying state-of-the-art techbiques in recognition, detection, and video analysis.

The course will consist of four programming projects, one final project, and a few self-tutorial sessions (12 minutes for each team of 5 students). Please find information about projects and self-tutorial sessions in the syllabus.


This course requires programming experience (mainly Matlab) as well as linear algebra, basic calculus, and basic probability. Previous knowledge of visual computing will be helpful.


Readings will be assigned in "Computer Vision: Algorithms and Applications" by Richard Szeliski. The book is available for free online or available for purchase.


Awesome computer vision github link
Awesome deep learning github link


Your final grade will be made up from You will lose 10% each day for late projects. However, you have three "late days" for the whole course. That is to say, the first 24 hours after the due date and time counts as 1 day, up to 48 hours is two and 72 for the third late day. This will not be reflected in the initial grade reports for your assignment, but they will be factored in and distributed at the end of the semester so that you get the most points possible.

Contact Info and Office Hours:

You can contact the professor with any of the following: Office Hours

Tentative Syllabus

lectureClass DatesTopicSlidesReadingExtra Info (e.g., Homework/Exam)
1W, Sept. 14Introduction to computer vision and cameras & optics pdf,pdf2Szeliski 1, 2.1 (especially 2.1.5) 
git and github pdfhomework 0 out
W, Sept. 21No Class (Plz attend GTC) Make up class in the following weekend.
Image Formation and Filtering   
2W, Sept. 24Light and color & Image filtering & MATLAB Tutorialpdf,pdf2,pdf3 Szeliski 2.2, 2.3, and 3.2homework 0 due
W, Sept. 28No Class (Teachers' day)  
3W, Oct. 5Thinking in frequency pdf Szeliski 3.4homework 1 (hybrid image) outhybrid image by cwc1612
hybrid image by 胡厚寧
Image pyramids and applications & self-tutorial
pdf Szeliski 3.5.2 and 8.1.1
Feature Detection and Matching   
4W, Oct. 12Continue & Edge detection pdf Szeliski 4.2 
Interest points, corners, and local image features pdf pdf2 Szeliski 4.2 
5W, Oct. 19Feature matching and hough transform pdf Szeliski 4.3homework 1 due
Model fitting and RANSAC & self-tutorial
pdf2 Szeliski 4.3homework 2 (image stitching) out stitched images by lisajwhl
stitched images by lisajwhl
6W, Oct. 26*Panorama Stitching pdf Szeliski 9 
Multiple Views and Motiong   
Stereo and Structure from Motion pdf pdf2 Szeliski 7 
7W, Nov. 2SfM & cere-solver & self-tutorial see aboveSzeliski 4.1.4 and 8.4 
Feature Tracking and Optical Flow pdf Szeliski 4.1.4 and 8.4 
Machine Learning Crash Course   
8W, Nov. 9Machine learning intro and clustering pdf Szeliski 5.3homework 2 due & project proposal due
Machine learning: classification pdf pdf2 homework 3 (scene recognition) outscene recognition by THShih
W, Nov. 16 Sports Day (運動會). No Class
9W, Nov. 23Recognition overview, bag of features pdf Szeliski 14 
large-scale instance recognition & self-tutorial pdf Szeliski 14.3.2 
10W, Nov. 30Detection with sliding windows: Viola Jones and Dalal Triggs pdf pdf2 Szeliski 14.1homework 3 due
Mixture of Gaussians and advanced feature encoding pdf homework 4 (face detection) outface detection by anXDddface detection by anXDdd
11W, Dec. 7 Modern Object Detection: DPM &self-tutorial
Modern Object Detection: Selective Search pdf  
12W, Dec. 14Deep Learning: introduction pdf pdf homework 4 due
Deep Learning: CNN pdf homework 5 (deep classification) out
13W, Dec. 21Deep Learning: recent work pdf1 pdf2 midterm project report due
Deep Learning: object detector pdf  
14W, Dec. 28Invited Talk: Video Understanding Using Weak Supervision from Natural Language
homework 5 due
Project Pitch 2 hours  
15W, Jan. 4 Project presentation: 15 teams pdf 
16W, Jan. 11Project presentation: 10 teams
Th, Jan. 12final project report due

Project Proposal Format:

- max 4 pages;
- 3 sections:
- final format: pdf, please!

Project Progress (mid-term) Report Format:

- max 4 pages;
- 3 sections:
- CVPR final format: pdf, please!

Project Pitch:

- Max 5 minutes (See videos in Kickstarter for inspiration); - Content: - We will use a peer-review system.

Project Final Report Format:

- Max 10 pages;
- Title and authors
- Abstract: short summary of the project with main results
- 6 sections:
- CVPR final format: pdf, please!
You can look at one of the recent instructor publications (such as this) as an example.

Project Report Evaluation:

- Your project report will be evaluated based on the quality of the writing, the clarity of your technical explanation and, overall, how well you get your message across. If you follow the structure above, you'll have good chances to do a good job. :)

Project Source Code:

There is no need to attach a print out of the source codes to the manuscript. Final source codes of your working program need to be shared with TA and the instructor on github (open or private repos are fine); this file is due on the project submission deadline date.

Project Presentation in Class:

- The presentation must be at most 10 minutes long. Please see below for detailed presentation guidelines,

Presentation format:

Your slides should consist of a title slide, followed by slides that discuss the following aspects of your project: Please do not plan on using more than 5-6 slides.


- Your team will be evaluated based on the clarity of the presentation, quality of the slides, how well you get your message across, and how well you handle the questions at the end. Note that the presentation can still contain ongoing/preliminary results; final results may be included in the final report. - We will use a peer-review system.


The materials from this class rely significantly on slides prepared by other instructors, especially James Hayes, Fei-Fei Li, and Silvio Savarese. Each slide set and assignment contains acknowledgements.