CS231M · Mobile Computer Vision

Spring 2014

Prof. Silvio Savarese
Office Hour:
Wednesday at 4:45 PM, Gates 228 http://cvgl.stanford.edu/silvio/
Dr. Kari Pulli (Nvidia)
Office Hour:
By Appointment
Time and Classroom
Mon, Wed 3:15 PM — 4:30 PM
Room 2, Building 200
Teaching Assistants
Saumitro Dasgupta
Office Hours:
Monday 1pm — 3pm, Gates B24A
Francois Chaubard
Office Hours:
Thursday 5pm — 7pm, Gates B24B

Course Information

The course surveys recent developments in computer vision, graphics and image processing for mobile applications.

Topics of interest include: feature extraction, image enhancement and digital photography, 3D scene understanding and modeling, virtual augmentation, object recognition and categorization, human activity recognition.

As part of this course, students will familiarize with a state-of-the-art mobile hardware and software development platform: an Nvidia Tegra-based Android tablet, with relevant libraries such as OpenCV and FCam. Tablets will be available for each student team.

In the first part of the course students will:

In the second part students will work on a class project as well as present and discuss papers related to state-of-the-art mobile vision applications.

Student will be required to summarize their results into a project write-up and present their projects in class.

Some examples of projects are:

Problem Sets

Students will be evaluated on the main tasks above through two problem sets. Each problem set will cover the following areas of computer vision:

Programming assignments will be implemented on an NVIDIA Tegra based Android tablet. Starter code will be provided for each problem set.

Project Proposal Guidelines

Your proposal (maximum 4 pages) should include the following:

  1. Title and authors
  2. Introduction: the problem you want to solve and why
  3. Technical details
    • How do you propose to solve it?
    • The target mobile platform
  4. Milestones (dates and sub-goals)
  5. References

Please submit your proposal as a PDF document.

Paper Presentation Guidelines


What to cover.


Class participation.

Project Presentation Guidelines

Final Project Report Guidelines

General Guidelines:

Include the following:


Grading Policy


Knowledge of linear algebra, probability, as well as concepts introduced in either CS131 or CS231A and CS232 (or equivalent) are necessary for understanding the material covered in this class. C++ (or Java) programming experience is expected.

Number of Units

3 or 4 — Every student is required to do a course project.


We would recommend posting class related questions on Piazza.

You can also reach the course instructors and TAs at cs231m-spr1314-staff@lists.stanford.edu.