Schedule and Syllabus

Unless otherwise specified the course lectures and meeting times are Tuesdays and Thursdays from 1:30pm to 2:50pm in the Building 200-002.

Students with Documented Disabilities: Students who may need an academic accommodation based on the impact of a disability must initiate the request with the Office of Accessible Education (OAE). Professional staff will evaluate the request with required documentation, recommend reasonable accommodations, and prepare an Accommodation Letter for faculty. Unless the student has a temporary disability, Accommodation letters are issued for the entire academic year. Students should contact the OAE as soon as possible since timely notice is needed to coordinate accommodations. The OAE is located at 563 Salvatierra Walk (phone: 723-1066, URL:

This is the syllabus for the Fall 2017 iteration of the course.
Event TypeDateDescriptionCourse Materials
Lecture 1 Tuesday
September 26
Course introduction
Computer vision overview
Course logistics
Introduction slides [pptx] [pdf]
Logistics slides [pptx] [pdf]
Lecture 1 notes [pdf]
Lecture 2 Thursday
September 28
Color + Math basics
Physics of light
Human encoding of color
Color Spaces
White Balancing
Vectors and Matrices
Color spaces slides [pptx] [pdf]
Lecture 2 notes [pdf]
python/numpy tutorial [pdf]
HW0 Due Monday
October 2, 11:59pm
Homework #0 due
[Homework #0]
Lecture 3 Tuesday
October 3
Linear algrebra
Transformation matrixes
Eigenvalues and eigenvectors
Matrix calculus and hessian
Linear algebra slides [pptx] [pdf]
Lecture 3 notes [pdf]
Lecture 4 Thursday
October 5
Pixels and filters
Pixels and image representation
Linear systems
Convolutions and cross-correlations
Pixels and filters slides [pptx] [pdf]
Lecture 4 notes [pdf]

HW1 Due Monday
October 10, 11:59pm
Homework #1 due
Filters - Instagram
[Homework #1]
Lecture 5 Tuesday
October 10
Edge detection
Derivative of gaussians
Sobel filters
Canny edge detector
Edge detection slides [pptx] [pdf]
Lecture 5 notes [pdf]
Lecture 6 Thursday
October 12
Features and fitting
Local features
Harris corner detection
Features and fitting slides [pptx] [pdf]
Lecture 6 notes [pdf]
Lecture 7 Tuesday
October 17
Feature descriptors
Difference of gaussians
Scale invariant feature transform
Image stitching
Feature descriptors slides [pptx] [pdf]
Lecture 7 notes [pdf]
HW2 Due Wednesday
October 18, 11:59pm
Homework #2 due
Edges - Smart car lane detection
[Homework #2]
Lecture 8 Thursday
October 19
Energy function
Seam carving
Resizing slides [pptx] [pdf]
Lecture 8 notes [pdf]
Lecture 9 Tuesday
October 24
Semantic segmentation
Gestalt theory of perceptual grouping
Aggomerative clustering
Superpixels and oversegmentation
Semantic segmentation slides [pptx] [pdf]
Lecture 9 notes [pdf]
HW3 Due Wednesday
October 25, 11:59pm
Homework #3 due
Panorama - Image stitching
[Homework #3]
Lecture 10 Thursday
October 26
Mean shift
Clustering slides [pptx] [pdf]
Lecture 10 notes [pdf]

Lecture 11 Tuesday
October 31
Object recognition
Nearest neighbors
Classification pipeline
Object recognition slides [pptx] [pdf]
Lecture 11 notes [pdf]
HW4 Due Wednesday
November 1, 11:59pm
Homework #4 due
Resizing - Seam carving
[Homework #4]
Lecture 12 Thursday
November 2
Dimensionality reduction
Singular value decomposition
Principal component analysis
Dimensionality reduction slides [pptx] [pdf]
Lecture 12 notes [pdf]
Lecture 13 Tuesday
November 7
Face identification
Eigenfaces and fisherfaces
Linear Discriminant Analysis
Face identification slides [pptx] [pdf]
Lecture 13 notes [pdf]
HW5 Due Wednesday
November 8, 11:59pm
Homework #5 due
Segmentation - Clustering
[Homework #5]
Lecture 14 Thursday
November 9
Visual Bag of Words
Texture features
Visual bag of words
Image pyramids
Visual bag of words slides [pptx] [pdf]
Lecture 14 notes [pdf]
Lecture 15 Tuesday
November 14
Detecting objects by parts
Deformable parts model
Object detection
Deformable parts slides [pptx] [pdf]
Lecture 15 notes [pdf]
HW6 Due Wednesday
November 15, 11:59pm
Homework #6 due
Recognition - Classification
[Homework #6]
Lecture 16 Thursday
November 16
Image classification
Semantic hierarchy
Fine grained classes
Detection slides [pptx] [pdf]
Lecture 16 notes [pdf]
Lecture 17 Tuesday
November 28
Optical Flow
Lucas-Kanade method
Horn-Schunk Method
Pyramids for large motion
Common Fate
Motion [pptx] [pdf]
Lecture 17 notes [pdf]
HW7 Due Wednesday
November 29, 11:59pm
Homework #7 due
Object detection - constellation models
[Homework #7]
Lecture 18 Thursday
November 30
Feature Tracking
Lucas Kanade Tomasi (KLT) tracker
Tracking slides [pptx] [pdf]
Lecture 18 notes [pdf]
Lecture 19 Tuesday
December 5
Introduction to deep learning
Convolutional neural networks
Deep learning slides [pptx] [pdf]
Lecture 19 notes [pdf]
HW8 Due Wednesday
December 6, 11:59pm
Homework #8 due
Tracking - Optical flow
[Homework #8]
Lecture 20 Thursday
December 7
Final Review
Summary of class
Final review talk [pptx] [pdf]
Final Monday December 11,12:15 to 3:15pm
Location: 320-105
Practice final [pdf]