Welcome to CMSC426

 Computer Vision Spring 2019

Overview

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, stereo, SLAM, 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.

Grading

  • Projects 50 %
  • Homework 25%
  • MidTerm 20%
  • Class Participation 5%

Prerequisites

Programming proficiency is the only hard pre-requisite. We recommend familiarity with Matlab. Furthermore, students taking the class should be comfortable with basic Linear Algebra and calculus.

Software

We will use MATLAB as the programming platform throughout this course, available to UMD students through .

Assignments

All projects are intended to be done in groups of upto 3. However, homeworks MUST be done individually.

Late Policy

We encourage students to submit in time. Late are submissions are accepted for five days for a 20% reduction in points

Logistics

All class announcements will be made through Piazza . Please use Piazza to contact TAs, rather than email.

All projects and homeworks are to be submitted using ELMS .

.

Course Outcomes

  • Knowledge of image formation process
  • Knowledge of image processing techniques for color and gray level images: edge detection, corner detection, segmentation
  • Basic knowledge of video processing, motion computation and 3D vision and geometry
  • Basic Knowledge of applying machine learning for Recognition Tasks
  • Ability to implement vision algorithms in Matlab
  • Ability to write a project report and discuss the results

Collaboration Policy

Collaboration is encouraged, but one should know the difference between collaboration and cheating. Cheating may be defined as using or attempting to use unauthorized assistance, material, or study aids in academic work or examinations. Some examples of cheating are: collaborating on a take-home exam or homework unless explicitly allowed; copying homework; handing in someone else's work as your own; and plagiarism. You are welcome to collaborate with your peers, but it's important that your work is an expression of *your* understanding, and not merely something you copied from a peer. So, we place strict limits on collaboration:

  • You must clearly cite your collaborators by name at the top of your report. This includes Piazza posts referenced.
  • You may not share or copy each other's code. You can discuss how your code works, and the concepts it implements, but you can't just show someone your code.
  • For homeworks, when it comes to formulating or writing solutions, you must work alone. For example, if you're working with your peers on a common whiteboard, you may not simply copy from that whiteboard; you must write your answer separately, based on your own understanding of what you discussed.
You may use free and publicly available external sources (such as books, journal and conference publications, and web pages) as research material for your answers. You may not use any service that involves payment, and you must clearly and explicitly cite all outside sources and materials that you made use of. We consider the use of uncited external sources as portraying someone else's work as your own, and as such it is a violation of the University's policies on academic dishonesty. We take this policy seriously: violations may result in a zero grade for the assignment, or even failing the course. Unless otherwise specified, you should assume that that the UMD Code of Academic Integrity applies.

Campus Policies

It is our shared responsibility to know and abide by the University of Maryland’s policies that relate to all courses, which include topics like:

  • Academic integrity
  • Student and instructor conduct
  • Accessibility and accommodations
  • Attendance and excused absences
  • Grades and appeals
  • Copyright and intellectual property

Please visit www.ugst.umd.edu/courserelatedpolicies.html for the Office of Undergraduate Studies’ full list of campus-wide policies and follow up with me if you have questions