CPSC 4070/6070: Applied Computer Vision
(2024 Spring)
Location: Watt Family Innovation Center 208
Time: Tue/Thur 3:30-4:45 pm
Credits: 3
Instructor: Siyu Huang, Assistant Professor at Clemson University
Email: siyuh@clemson.edu
Office hours: Tue 2:00-3:00 pm, McAdams Hall 218
Course overview
This course offers an introduction to fundamental principles and real-world applications of 2D, 3D, and deep learning-based computer vision. Major topics include image filtering, feature detection and matching, recognition and tracking, scene understanding, camera imaging geometry, stereo vision, and deep learning-based vision. Students will learn to implement interesting computer vision algorithms in a series of well designed projects. Students will also explore intriguing research questions during a final project. This course will be of particular interest to students seeking to delve into fields of image processing and computer vision.
Prerequisites
This course requires students to have basic knowledge in linear algebra, basic probability, and Python programming. Knowledge in signal processing and machine learning is recommended but not necessary.
Assignments and Grading
* Students will be allowed a total of five late days per course. Each additional late day will incur a 10% penalty.
Five homework assignments (60% = 12%*5)
Convolution and cross-correlation
Canny Edge Detector, Hough transform
Harris corner detector, RANSAC, HOG descriptor
Face detection
Lukas-Kanade tracking
A final project (30%)
Final project proposal (5%)
Proposal presentation (5%)
Final project paper (10%)
Final presentation (10%)
Class participation (1o%)
Schedule (Tentative)
Note: Assignment out, Deadline
Date Lecture Presenter
1/11 Introduction [slides] Siyu Huang
Basic Image Processing
1/16 What is an Image; Sampling and Aliasing [slides] Siyu Huang
1/18 Image Filtering (Part I) [slides] Siyu Huang
Assignment #1 out - Convolution and cross-correlation
1/23 Image Filtering (Part II) [slides] Siyu Huang
1/25 Image Filtering in Frequency Domain [slides] Siyu Huang
1/30 Edge Detection [slides] Siyu Huang
Assignment #1 due - Convolution and cross-correlation
Assignment #2 out - Canny Edge Detector, Hough transform
2/1 Corner Detection [slides] Siyu Huang
Assignment #3 out - Harris corner detector and HOG descriptor
2/6 Feature Descriptors [slides] Siyu Huang
Recognition
2/8 Image Recognition, Bag of Words [slides] Siyu Huang
Assignment #2 due - Canny Edge Detector, Hough transform
Assignment #4 out - Face detection
2/13 Image Segmentation (Part I) [slides] Siyu Huang
2/15 Image Segmentation (Part II) [slides] Siyu Huang
Stereo Vision
2/20 Image Transformations [slides] Siyu Huang
Assignment #3 due - Harris corner detector and HOG descriptor
Assignment #5 out - Lukas-Kanade tracking
2/22 Image Homographies [slides] Siyu Huang
2/27 Image Alignment [slides] Siyu Huang
2/29 Camera Models [slides] Siyu Huang
3/5 Camera Calibration [slides] Chaoyi Zhou
Assignment #4 due - Face detection
Video
3/7 Optical Flow [slides] Siyu Huang
3/12 Tracking [slides] Siyu Huang
Deep Learning Era
3/14 Machine Learning for Computer Vision [slides] Siyu Huang
Assignment #5 due - Lukas-Kanade tracking
3/19, 3/21 Spring Break
3/26 Project Proposal Presentation-I Grad Students
3/28 Project Proposal Presentation-II Undergrad Students
Final project proposal due
4/2 Deep Learning, Pytorch, Palmetto [slides] Siyu Huang
4/4 Object Detection, Semantic Segmentation [slides] Siyu Huang
4/9 Image Generation [slides] Siyu Huang
Final Project Presentation
4/11 Novel View Synthesis Xi Liu
4/16 Final project preparation and QA Siyu Huang
4/18 Final project presentation Students
4/23 Final project presentation Students
4/25 Final project presentation Students
Final project paper due
5/5 Grades delivered