This course provides an introduction to computer vision and computational photography. The course will cover basic principles of image processing, image recognition using both classical methods and deep learning, and multiple view geometry for visual navigation. It will explore the topics of image formation, image features, image stitching, image and video segmentation, motion estimation, tracking, and object and scene recognition.
The course is organized around several projects. Through these projects you will learn the theory and practical skills required to obtain a computer vision engineering job.
Links to the lecture slides can be found on ELMS .
Date | Topic | Assigned Reading |
---|---|---|
01/25 | Introduction to Computer Vision | David Jacobs' Preassessment Notes |
01/30 | Linear Algebra / Least Squares | |
2/1 | Ridge Regression and Regularization | |
2/6 | Singular Value Decomposition (SVD) Principal Component Analysis (PCA) |
PCA and SVD with numpy tutorial |
2/8 | Filtering | |
2/13 | Image Pyramids and Frequency Domain | Szeliski textbook, Section 3.2 |
2/15 | Canny Edge Detection | Szeliski textbook, Sections 3.4 and 3.5 |
2/20 | Corner Detection | Szeliski textbook, Section 7.1 |
2/22 | Feature Descriptors and SIFT | |
2/27 | Image Classification Bag of Words |
|
3/1 | Image Classification Support Vector Machines (SVM) |
Szeliski textbook, Section 6.2.1 |
3/6 | Multivariable Calc Refresher Neural Networks |
Szeliski textbook, Section 5.1.4 |
3/8 | Neural Networks | |
3/13 | Convolutional Neural Networks | |
3/15 | Convolutional Neural Networks | |
3/20 | Spring Break | |
3/22 | Spring Break | |
3/27 | 2D Transformations Projective Coordinates |
Szeliski textbook, Section 3.6 Cyrill Stachniss Lecture |
3/29 | 2D Transformations Projective Coordinates |
|
4/3 | Homographies RANSAC |
|
4/5 | Geometric Camera Models | David Jacobs' 3D Geometry Notes |
4/10 | Geometric Camera Models | |
4/12 | Two-view Geometry | |
4/17 | Stereo and Structured Illumination | |
4/19 | Structure from Motion | |
4/24 | Segmentation | |
4/26 | Optical Flow | |
5/1 | Tracking | |
5/3 | Tracking | |
5/8 | Digital Photography | |
5/10 | Computational Photography |
Instructor: Christopher Metzler (metzler at umd.edu)
Office: IRB 4236
Office Hours: Wednesdays 3:45-5:45 pm
Name | Office hours | |
---|---|---|
Kevin Zhang | kzhang24 at umd.edu | Wednesdays 1:30-3:30 pm |
Mingyang Xie | mingyang at umd.edu | Tuesdays 3:00-5:00 pm |
Sazan Mahbub | smahbub at umd.edu | Thursdays 3:00-5:00 pm |
Office hour locations TBD.
Posted homeworks and programming assignments can be found on ELMS.