CMSC 426 - Computer Vision



Section 0201:

This course offers an introduction to Computer Vision and Computational Photography. The course will cover basic principles of Image Processing, Multiple View Geometry for Visual Navigation, and Image Recognition using Classical and Deep Learning . It will explore the topics of image formation , image feature, image stitching, image and video segmentation, motion estimation, tracking, and object and scene recognition. The course is intended for anyone interested in processing images or video, or interested in acquiring general background in real-world perception. The course is , organized around a number of projects. Through these projects you will learn the theory and practical skills required in jobsof computer vision engineering.

Course Information

All concepts will be covered in class lecture, and in the lecture notes. However, we also recommend the following books as good references:

References:
  • Computer Vision: Algorithms and Applications, Richard Szeliski, Springer, 2010 Online version
  • Computer Vision: A Modern Approach: D. Forsythe and J. Ponce, Prentice-Hall, 2003 (available online)
  • Digital Image Processing, Prentice Hall, Rafael Gonzalez, and Richard Woods, 2008.
  • Multiple View Geometry in Computer Vision, Cambridge University Press, Richard Hartley, and Andrew Zisserman, 2003.

Schedule

Exam Dates:


  • Midterm: Thursday, October 17, during lecture
  • Final Project: Friday, December 13, 11:59 PM

Lectures


Week of
Tuesday
Thursday
08/26 Introduction to Computer Vision Linear Algebra / Least Squares
(normal Equation)
09/02 Ridge Regression /
Eigen values and vectors		 Singular Value Decomposition
09/09 Principal Components Analysis (PCA) K-Means Algorithm /
Gaussian Mixture Models (GMM)
09/16 Expectation-Maximization
(Ref: Pattern recognition and
Machine Learning by Bishop)		 Intro to Image Processing
09/23 Cross-Correlation Edge detection
09/30 Canny edge detection Class canceled
10/07 Harris corner detection Scale-Invariant Feature
Transform (SIFT)
10/14 Review Midterm
10/21 Projective Transformations Homography
10/28 Homography conclusion /
Hough Transform 		Image Motion
11/04 Iterative Lukas-Kanade /
Texture 		Speeded Up Robust Features (SURF)
11/11 Support Vector Machines (SVM) /
Mathematics behind SVM's		 Bag of Visual Words
11/18 Histogram of Oriented Gradients Gradient Descent Algorithm
11/25 Neural Networks Thanks giving break
12/02 Convolutional Neural Networks Wrap-Up

Staff

Instructor: Mohammad Nayeem Teli (nayeem at cs.umd.edu)

Office: IRB 1128
Office Hours: Tu/Th 2:00 - 3:00 PM


Teaching Assistants



Name Office hours
Yu Fang Friday 2:00 - 4:00 PM
Kumar Gaurav Monday 4:00 - 6:00 PM
Wednesday 4:00 - 5:00 PM
Friday 9:00 - 10:00 AM


All TA office hours take place in AVW 1120. Please note that a TA may need to leave 5 minutes before the end of the hour in order to go to his/her class. Please be understanding of their schedules.

Class Resources

Online Course Tools
  • ELMS - This is where you can see your final grades and homework solutions.
  • Piazza - This is the place for class discussions. Please do not post homework solutions here.


Background Material
The following web pages provide some background and other helpful information.



Exam Related Material

Homeworks

Click the name of an assignment below to see its specifications.


Homework Name
Due Date
Homework 1 11:59 PM, Sep. 14, 2019
Project 1 11:59 PM, Sep. 27, 2019
Homework 2 11:59 PM, Oct. 12, 2019
Homework 3 11:59 PM, Oct. 26, 2019
Project 2 11:59 PM, Nov. 10, 2019
Project 3 11:59 PM, Nov. 26, 2019
Project 4 11:59 PM, Dec. 15, 2019