Everyone has large photo collections these days. How can you intelligently find all pictures in which your dog appears? How can you find all pictures in which you are frowning? Can we make cars smart, e.g., can the car drive you to school while you finish your last homework? How can a home robot understand the environment, e.g., switch on a tv when being told so and serve you dinner? If you take a few pictures of your living room, can you reconstruct it in 3D (which allows you to render it from any new viewpoint and thus allows you to create a "virtual tour" of your room)? Can you reconstruct it from one image alone? How can you efficiently browse your home movie collection, e.g. find all shots in which Tom Cruise is chasing a bad guy?

This class is an introduction to fundamental concepts in image understanding, the subdiscipline of artificial intelligence that tries to make the computers "see". It will survey a variety of interesting vision problems and techniques. Specifically, the course will cover image formation, features, object and scene recognition and learning, multi-view geometry and video processing. Since Kinect is popular these days, we will also try to squeeze recognition with RGB-D data into the schedule. The goal of the class will be to grasp a number of computer vision problems and understand basic approaches to tackle them for real-world applications.

Prerequisites: A second year course in data structures (e.g., CSC263H), first year calculus (e.g., MAT135Y), and linear algebra (e.g., MAT223H) are required. Students who have not taken CSC320H will be expected to do some extra reading (e.g., on image gradients). Matlab will extensively used in the programming excercises, so any prior exposure to it is a plus (but not a requirement).

back to top

When emailing us, please put CSC420 in the subject line.

Information Sheet

The information sheet for the class is available here.

Programming Language(s)

You are expected to do some programming assignments for the class. You can code in either Matlab, Python or C. However, in class we will provide the examples and functions in Matlab. Note also that most Computer Vision code online is in Matlab so it's useful to learn it. Knowing C is only a plus since you can interface your C code to Matlab via "mex".

Please make sure you have access to MATLAB with the Image Processing Toolbox installed.


This class uses piazza. On this webpage, we will post announcements and assignments. The students will also be able to post questions and discussions in a forum style manner, either to their instructors or to their peers.

Please sign up here in the beginning of class.

back to top

We will not directly follow any textbook, however, we will require some reading in the textbook below. Additional readings and material will be posted in the schedule table as well as the resources section.

back to top

Each student is expected to complete five assignments which will be in the form of problem sets and programming problems, and complete a project.


Assignments will be given every two weeks. They will consist of problem sets and programming problems with the goal of deepening your understanding of the material covered in class. All solutions and programming should be done individually. There will be five assignments altogether, each worth 10% of the final grade.

Submission: Solutions to the assignments should be submitted through CDF. The preferred format is PDF, but we will also accept Word. Unless stated otherwise in the Assignments' instructions include the code (for exercises that ask for code) within the solution document. An ideal example of how the code can be included can be found here. We also don't mind if you print-screen your matlab functions and include the pictures as long as they are of good quality to be read. If you are using Matlab's built-in functions within your code you should not include them. But include all your code.

Deadline: The solutions to the assignments should be submitted by 11.59pm on the date they are due. Anything from 1 minute late to 24 hours will count as one late day.

Lateness policy: Each student will be given a total of 3 free late days. This means that you can hand in three of your assignments one day late, or one assignment three days late. It is up to you to make a good planning of your work. After you have used your 3 day budget, your late assignments will not be accepted.

Plagiarism: We take plagiarism very seriously. Everything you hand in to be marked, namely assignments and projects, must represent your own work. Read How not to plagiarize.


Each student will be given a topic for the project. You will be able to choose from a list of projects, or propose your own project which will need to be discussed and approved by your instructor. You will need to hand in a report which will count 30% of your grade. Each student will also need to present and be capable to defend his/her work. The presentation will count 20% of the grade.

The final grade will be computed as follows:

(5 assignments, each worth 10%)
(report: 30%, presentation: 20%)

back to top

The course will cover image formation, feature representation and detection, object and scene recognition and learning, multi-view geometry and video processing. Since Kinect is popular these days, we will also try to squeeze recognition with RGB-D data into the schedule.

Image Processing
Linear filters
Edge detection
Features and matching
Keypoint detection
Local descriptors
Low-level and Mid-level grouping
Region proposals
Hough voting
Face detection and recognition
Object recognition
Object detection
Part-based models
Image labeling
Image formation
Multi-view reconstruction
Video processing
Action recognition
close Tentative Schedule

back to top

DateTopicReading SlidesAdditional materialAssignments
Sept 11Course Introduction lecture1.pdf Tutorial: intro to Matlab
Image Processing
Sept 11Linear FiltersSzeliski book, Ch 3.2lecture2.pdfcode: finding Waldo, smoothing, convolution
Sept 16Edge DetectionSzeliski book, Ch 4.2lecture3.pdfcode: edges with Gaussian derivatives
Sept 18Image PyramidsSzeliski book, Ch 3.5lecture4.pdf Assignment 1: due Sept 27, 11.59pm, 2014
Sept 23State-of-the-art Edge DetectionP. Dollar, C. Zitnick, Structured Forests for Fast Edge Detection, ICCV'13lecture5.pdfcode: Structured Edge Detection Toolbox by Dollar et al.
Features and Matching
Sept 25Keypoint Detection: Harris Corner DetectorSzeliski book, Ch 4.1.1
pages:   209-215
Sept 30Keypoint Detection: Scale Invariant KeypointsSzeliski book, Ch 4.1.1
pages:   216-222
Oct 2Local Descriptors: SIFT,
Szeliski book, Ch 4.1.2
Lowe's SIFT paper
lecture8.pdfcode: compiled SIFT code, VLFeat's SIFT codeAssignment 2: due Oct 12, 11.59pm, 2014
Oct 7Robust Matching, HomographiesSzeliski book, Ch 6.1lecture9.pdf
Oct 9Homographies continued Lec. 9 cont.code: Soccer and screen homographyProjects: due Dec 10, 11.59pm, 2014
Oct 14Camera ModelsSzeliski, 2.1.5, pp. 46-54
Zisserman & Hartley, 153-158
Oct 16Camera Models Lec. 10. cont.Assignment 3: due Oct 26, 11.59pm, 2014
Oct 21Stereo: Parallel Optics lecture11.pdfcode: Yamaguchi et al.
Oct 23Stereo: Parallel OpticsLec. 11 cont.
Oct 28Stereo: General CaseSzeliski book, Ch. 11.1
Zisserman & Hartley, 239-261
Oct 30Fast RetrievalSivic & Zisserman, Video Googlelecture13.pdfAssignment 4: due Nov 13, 11.59pm, 2014
Nov 4Recognition: OverviewGrauman & Leibe, Visual Object Recognitionlecture14.pdf
Nov 6Recognition: TodayLec. 14 cont.
Nov 11Recognition: HistoryMundy, Object Recognition in the Geometric Eralecture15.pdf
Nov 13Recognition: History 2 Lec. 15 cont.Jialiang Wang's Tutorial on classification
Nov 20Implicit Shape ModelB. Leibe et al., Robust Object Detection with Interleaved Categorization and Segmentationlecture16.pdfAssignment 5: due Nov 30, 11.59pm, 2014
Nov 25The HOG DetectorHOG paperlecture17.pdf
Nov 27Deformable Part-based Model,
DPM paperlecture18.pdf
Dec 2All You Wanted To Know About Neural NetworksInvited lecture: Alex Schwinglecture20.pdf

back to top

Whether you are enrolled in the class or just casually browsing the webpage, please leave feedback about the class / material. You can do it here. Thanks!

back to top

We will post the top scoring solutions for the extra credit exercises.

Assignment 1: Seam Carving

The exercise was to remove horizontal and/or vertical seams, i.e. paths with the smallest sum of gradients. We followed Avidan and Shamir's "Seam Carving for Content-Aware Image Resizing" paper.

Mian Wei
Stanislav Ivashkevich
Brendan Op 't Root
Andrew George Berneshawi
Anderson Akio Gohara
Wonjoon Goo
Xuanyi Hong
Chandeep Singh

Assignment 2: Window Detection

The exercise was to detect all frontal windows in a given image. Four students submitted solutions, all were great and spot on. Here we are showing the top two competitors, along with their accuracy measured with the F1-score. Huazhe won with 92.3% and also has the least tuneable parameters -- very impressive. Mian achieved a higher recall (detected all windows!) but a slightly lower precision. Congrats to Huazhe and Mian!

Huazhe Xu (F1-score: 92.3%)
Mian Wei (F1-score: 83.1%)
Brendan Op't Root (F1-score: 75.0%)
Stanislav Ivashkevich (F1-score: 66.7%)

Assignment 3: Drive a Car in Monocular Images

In this extra credit exercise, a monocular image is given along with the intrinsic camera parameters. We also know that the image plane is orthogonal to the ground. The goal is to realistically render a 3D CAD model in the scene. We got some great renderings! The best videos have been created by Andrew Berneshawi, congrats!

Andrew George Berneshawi


Mian Wei

Wonjoon Goo

Huazhe (Harry) Xu

Amy Ka-Wai Yang

Ilia Samsonov

Assignment 4: Car Segmentation

We held a competition in car segmentation. Input is a stereo image pair and the output is an image labeling of car vs background. 25 image pairs with ground-truth were provided for training, while test had 20 image pairs. The best, and very impressive, performance 71.1% was achieved by Andrew Berneshawi, followed by Huazhe Xu (67.4%) and Stanislav Ivashkevich (66.3%). Performance is measured as intersection-over-union between GT car pixels and predicted car pixels. Congrats to all participants! Below we are showing a few example segmentations for top 5 participants.


We had five possible projects with the option of coming up with own idea for the project. Below are some of the best results.

Project 1

For this project three clips from the TV series Buffy The Vampire Slayer were given. The task was to compute shots (chunks of video where camera motion is smooth), determine which shots were night or day, detect and track faces, determine which faces were a close-up, and which face belonged to Buffy. Extra credit was to determine if Buffy was talking or not.

Project 2

This project was tackling subproblems in the domain of autonomous driving. We worked with stereo pair data from the KITTI dataset, the road segmentation benchmark. Ground-truth labels were available for road segmentation and objects (in 3D) for the training subset, but not for test. The tasks were: road classification, object detection and viewpoint classification, 3D bounding box estimation.

Project 3

The goal of this project was to analyze video clips of broadcast news. The tasks were: shot detection, detect logo in the video automatically (without knowledge of which logo and where it appears in the clip), detect and track faces, classify faces into male/female.

back to top

back to top