Essential information:

Prerequisites:

This is a college-wide course (crossed-listed under both CS and ECE), and hence, there is no formal prerequisite for this course. However, no formal prerequisite does not imply that you need no academic reparation. Upper-division standing in CS or ECE (or another engineering department) is required, which means that adequate background in calculus, linear algebra, differential equations, and probability is assumed. Familiarity with at least one high-level programming language (e.g., Python, Matlab, C, C++, and Java) is also assumed. We will use Matlab and Python for programming assignments. While Matlab can be slow, it is an excellent development environment for fast prototyping. It has built-in functions for reading, writing, and displaying images, and the Image Processing Toobox has lots of useful functionalities. You do not have to be an expert in Matlab to take this course, but must be willing to learn quickly (see Tutorial page).

Grading:

• Homeworks (four - five programming assignments) = 60%
• Midterm exam = 15%
• Final exam = 25%
• Homework due dates will be clearly marked on the handouts and posted on the class web site. In general, you have about about two weeks to turn in a programming project. Plan your schedule wisely as late assignment turnins will be severely penalized without a documented emergency.

Textbooks:

The following is partial list. In particular, Szeliski's book (PDF version) is free to download. Be warned that we will not follow any book closely and will rely mostly on our class notes and additional assigned readings. However, it is strongly recommend that you have some reference books.

• Forsyth and Ponce, Computer Vision, a Modern Approach
• Szeliski, "Computer Vision, Algorithms and Applicatins"
• Hartley and Zisserman, "Multiple View Geometry in Computer Vision"
• Faugeras, "Three-Dimensional Computer Vision, A Geometric Viewpoints"
• Horn, "Robot Vision"

Lab:

All engineering students should have access to the ECI labs. You can also use your personal computers for programming assignments and class projects. If you use Matlab, you can obtain a copy for free to install on your personal computer. You can also access ECI lab machines remotely.

For CS students, CSIL (Computer Science Instructional Lab) should be available to you. The policy of the CS Department allows anyone taking a CS course to obtain a CoE account with access to CSIL. At the beginning of each quarter, the CoE Account System manages most of this automatically. For students with a CoE account, it extends CSIL access to them. For those students without an account, it allow them to create one here.

The important thing to note is that as long as you are an engineering student with a CoE account, you are set to take this class. You will have access to your home directory and essential software (Matlab, Python, etc.) from any CoE machine in CSIL and ECI labs. You will also have access to the electronic turnin program at /usr/bin/turnin to electronically turn in your programs for grading.

Objectives:

An introduction to the field of Computer Vision (also known as Machine Vision or Image Understanding or Computational Vision). The aim of computer vision is to make computers "see" by processing images and/or video. By knowing such things as how images are formed, information about the sensors (cameras), and information about the physical world, it is possible (at least in some cases) to infer information about the world from an image or set of images. For example, one may wish to know the color of an apple, the width of a printed circuit trace, the size of an obstacle in front of a robot on Mars, the identity of a person's face in a surveillance system, the motion of an object, the vegetation type of the ground below, or the location of tumor in an MRI scan - automatically, from images. Computer vision studies how such tasks can be done, and how they can be done robustly and efficiently. Originally seen as a sub-area of artificial intelligence, computer vision has been an active area of research for almost 40 years.

People learn computer vision with of a variety of motivations. Some want to better understand biological vision - how people and animals see, how the eye and the brain work together to enable sight, etc. Others want to build robots that can perceive and react to the environment around them. Others are interested in multimedia databases, image compression, human-computer interaction, security and surveillance, medical imaging, and other areas. Whatever the motivation or application, there are several topics that are fundamental to work in computer vision and are important to almost any application.

Topics covered :

• Image formation - geometry, radiometry, camera calibration
• Color models and perception
• Edge detection and filtering
• Region segmentation
• Stereo and multiple views
• Motion processing
• Tracking
• object recognition
• Recent applications

During the course we will touch upon applications in biological vision and learning, robotics, image databases, video processing/compression, medical imaging, computer graphics, and human-computer interaction. By the end of the course, you should understand what computer vision is all about - why it is a difficult and interesting problem (actually, set of problems), what can it be used for, and what are the main tools and techniques. You will gain experience both conceptually and practically, by homework assignments that involve solving problems and programming vision routines. You will see many examples of working vision systems and research projects pushing the state of the art.

This is not primarily a programming course - that is, the main goal is to learn the concepts, not to learn a programming language or particular programming techniques. However, coding examples of the concepts is the best way to demonstrate (and facilitate) your knowledge of them.

The course will introduce a mixture of "traditional" and "modern" techniques. "Traditional" techniques largely focus on high-precision, low-level analysis. Drawn heavily upon mathematics and geometry, traditional CV techniques have proven useful in applications such as camera calibration, tracking and 3D reconstruction and modeling. More recently, CV researchers are exploring high-level, highly-adaptable deep learning techniques on, say, object recognition, scene segmentation, and event analysis. We will introduce both classes of approaches in this course.

General class policies and announcements:

• This class has a Web site at http://www.cs.ucsb.edu/~cs181b. You will find there useful information such as lecture notes, assignment deadlines, and on-line copies of syllabus and programming assignments. It is your responsibility to check the Web site on a regular basis.
• This class also has a Piazza website for discussion. Again, it is your responsibility to check the Web site on a regular basis.

• Important Piazza etiquette:
  • Be professional and courteous - this is not a place to vent your frustration!
  • Describe your problems clearly but succinctly - you are wasting your time composing long questions in the Twitter era,
  • Remember the rule of gives-and-takes: you want people to help you, you should try to help others if possible; however,
  • Don't post suggestions that you are not sure of or are intentinally misleading, and
  • Most importantly, never ever post your codes on the discussion website (small program snippets where you need help are ok).
    
• Late assignment turnin will be severely penalized without proof of a documented emergency. 20% will be taken off for any fraction of a day late, up to two days. I.e., if you turn in an assignment late by less than 24 hours, 20% will be taken off. If you turn in an assignment late by more than 24 hours but less than 48 hours, 40% will be taken off. No late assignment turnins will be accepted after the second day past the due day. This policy applies to all homework assignments, no exception.
• For all programming assignments, you must keep a copy of your codes in the E1 or CSIL Lab. You must not edit or change them in any way after you turn them in electronically for grading. The purpose of this backup copy is to help resolving dispute regarding assignment grading (e.g., the turnin process corrupts the codes). You need to have a backup copy (with a time stamp showing the codes were last modified before the deadline). A backup copy on your own computer is not acceptable.
• There is no group programming assignment in this class. You should do all the assignments on your own. Consult your TAs and instructor if you have any question. Any act of cheating, plagiarism, or collaboration on assignments will result an "F" grade in this class; however minor the infringement may be.
• If you have any questions concerning your homework/program/exam grades, you should bring them to your TAs first. If the questions cannot be resolved to your satisfaction, you should then consult the instructor. Any dispute over grades must be resolved in a timely manner, within two weeks from the time grades are emailed to you.
  
• Class attendance is highly recommended. You are responsible for everything that goes on in class. "I wasn't there" and "I didn't know" are not valid excuses for missing something important!
• Weekly one-hour discussion sections, led by the TA, will focus on (1) presenting supplementary material (such as practical examples) to the lectures and (2) answering questions (about lecture topics, homework problems, programming issues, etc.). It is expected that students attend these sessions - you are responsible for what goes on during the discussion sessions also.
• The two discussion sessions in a week will be lead by the same TA and devoted to the same topics. You can choose to attend either one (9am or 10am on Friday).
• Students are encouraged to give the TA (and, if appropriate, the instructor) feedback regarding topics or issues they would like to have discussed during this time.

Academic Honesty Policy

In this class, you are expected to subscribe to the highest standard of academic honesty. This means that every idea that is not your own must be explicitly credited to its author. Failure to do this constitutes plagiarism.

Plagiarism includes using ideas, code, and old solution sets from any other students or individuals, or any sources other than the required text, without crediting these sources by name. In this class, the homework includes several programming assignments. You are encourage to discuss problems with your instructor and TA. You may not copy codes from other students, or give your codes to others under any circumstances.

Academic dishonesty will not be tolerated. Any student caught of academic dishonesty will be reported to the proper authority for disciplinary action. You will receive a failing grade for this course and may be suspended or dismissed from the university.

Back to the Course Home Page