For students who are enrolled in this course: To access the full version of this website, you need to 1) get a Google account (you can cancel Gmail and use your regular email), 2) join this Google group using your Google account, and 3) log with the Google account at the bottom of this page.

Title: Computer Vision I  

Course number: 91.423 (undergraduate) 91.543 (graduate) 

Session: Fall 2015

Instructor: Kate Saenko, saenko@cs.uml.edu  

Location: Olsen Hall, Room 410 

Meeting Times: Tue/Thu 4-5:15pm

Office Hours:  Olsen 223, Tue/Thu 3-4pm, and by appointment.


Catalog listing   
Computer vision has seen remarkable progress in the last decade, fueled by the ready availability of large online image collections, rapid growth of computational power, and advances in representations and algorithms. Applications range from 3-D scene reconstruction, to visual Simultaneous Localization and Mapping (SLAM) for robotics, to real-time human body pose estimation. This introductory computer vision course explores various fundamental topics in the area, including the principles of image formation, local feature analysis, segmentation, multi-view geometry, image warping and stitching, structure from motion, and object recognition.

Prerequisites

This is an upper-level undergraduate or graduate course. Students should have completed the following courses (or their equivalents):

  • 91.102 Computing II
  • 92.132 Calculus II 
  • 92.322 Discrete Structures II

In addition, the course can be taken as part of the two-course project sequence in combination with 91.422 Machine Learning (this course is not currently a pre-requisite.)

Textbooks


The main textbook for the course is Computer Vision: Algorithms and Applications by Richard Szeliski.

The secondary optional textbook is Computer Vision: A Modern Approach by David A. Forsyth, and Jean Ponce.

Also see OpenCV resources for useful books about OpenCV for homeworks and projects.

Software and Hardware

The course will use the OpenCV  library. To facilitate programming assignments, additional software libraries may be made available to the students.

Meeting Format

The class will meet twice a week for a 75 min lecture, taught by the instructor.

Syllabus Overview

  • Image Formation, Camera Calibration
  • Color Perception, Color Spaces
  • Filters and Pyramids
  • Local Image Features, Feature Detectors and Descriptors
  • Image Alignment and Stitching, Panoramas
  • Stereo Vision
  • Structure from Motion
  • RGB-D cameras
  • Object Recognition and Detection
  • Convolutional Neural Networks for Object Recognition
  • Action and Scene Recognition

Student Learning Outcomes

After the completion of the course, the students should be able to understand 

  • the design, construction and evaluation of a computer vision system
  • the mathematical foundations of several mainstream computer vision algorithms
  • major classes of approaches in the literature
  • practical issues involved in implementing computer vision projects
  • current state of the art

These goals will be evaluated through homeworks and a final project.

Deliverables/Graded work

Students will be evaluated based on the following graded work (subject to change):

  • best 6 of 7 homeworks: 40% 
  • class participation: 10%
  • final project: 50% 

Students enrolled in the graduate section will be expected to submit additional work and/or achieve a higher percentage on the exams to receive the same grade as undergraduate section students. 

Late Policy

  • 20% off per day
  • up to 4 days
Submitting Homework and Deliverables

Students MUST submit the finished homework using ‘submit’, unless stated otherwise in the assignment handout. Please refer to this page


on how to submit an assignment using ‘submit’ command on the Computer Science servers. You need a CS department account, which you can get from the helpdesk in 312. Note, your files will be overwritten by duplicate submission.

Important: if you cannot submit an assignment on time because of CS department server issues, please IMMEDIATELY 
  1. send an email to help@cs.uml.edu, 
  2. cc: the instructor and TA(s), 
  3. do not modify the timestamps on your files, i.e. timestamps should be from before the deadline, even if the files are submitted later. 
Only doing (1)-(3) can result in late charge reversal.

Academic Honesty Policy: Students are expected to honor all CS department and UMass Lowell policies related to academic honesty and integrity. Violators risk failing the course in addition to any actions taken by university administration. The default CS department policy is that a student who cheats will fail the course. The University's policy is described here. A definition of plagiarism is here. All work on exams must be the student's own work. All work on homework assignments must also be the student's own work, with the following exceptions: 1) hints provided by the instructor or TA may be used but must be acknowledged in writing in the student's work; 2) high-level hints from another student may also be used if a student is unable to make progress on an assignment problem on his/her own; this type of hint must also be acknowledged in writing in the student's work. Detailed collaboration among students on homework assignments is not permitted. Students cannot obtain homework answers from web sites. 

Religious Observance: UMass Lowell respects the religous observances of students. If religious obligations conflict with course due dates and/or examinations, students should notify the professor in writing well in advance of the due date.