Computer Vision 2026 Spring

Quick links: schedule, policies, Ketangpai (assignment submission)



Computer vision is a science which uses cameras and computers to "see" and "understand" the world. Research related to computer vision attempts to establish artificial intelligence systems to obtain "information" from image data. The "information" here is defined by Shannon which can be used to help make a "decision". Because perception can be regarded as extracting information from sensory signals, computer vision can be considered as a science that study how to make artificial system "perceive" from images or multi-dimensional data. This year we will focus on an elementary hands-on introduction to computer vision, with topics including image formation, feature detection, motion estimation, image mosaics, 3D shape reconstruction, object/face detection and recognition, and deep learning.

Instructor: QI Lin (qilin -at- ouc.edu.cn)

Lectures: Friday, 10:30AM-12:15PM
424 Learning Complex South Building

Labs: Friday (odd-numbered weeks), 13:30PM-15:20PM
C104 Information South Building

TAs: we don't have TAs this year. 😢

Instructor and TA office hours: Friday (odd-numbered weeks), 15:30PM-16:30PM

Contacting the course staff: For emergencies and special circumstances, please email the instructor or use Ketangpai.

Prerequisites: Data structures and algorithms, Python programming, linear algebra, multi-variable calculus,statistics. No previous exposure to image processing, graphics or machine learning is required.

Grading scheme:

  • Attendence: 10% of the grade
  • Programming assignments: 20% of the grade
    • SOLO work
    • Will be using Python, PyTorch (or TensorFlow, PaddlePaddel, MindSpore) on your own computer or on cloud based platforms such as Google Colab, Baidu AI Studio, Huawei ModelArts.
  • Final Exam: 70% of the grade, paper based, closed book.
Be sure to read the course policies!

Schedule (tentative)

Date Topic Assignments
March 13 Introduction: Slides, Readings: Szeliski, Chapter 1 (Introduction) Self-study: Python/numpy tutorial
March 20 Image filtering: Slides, Readings: FCV 5, 6, 7  
March 27 Image filtering cont., Readings: FCV 5, 6, 7 Lab 1: Hybrid Images

Resources

Tutorials

Useful textbooks available online

Acknowledgement

This course is developed based on various Computer Vision curricula, utilizing slides and materials generously shared by researchers in the field.

Webpage template credit: SVETLANA LAZEBNIK.