CPSC 4070/6070: Applied Computer Vision
(2025 Spring)
(2025 Spring)
Location: Watt Family Innovation Center 308
Time: Tue/Thur 5:00-6:15 pm
Credits: 3
Instructor: Siyu Huang (siyuh@clemson.edu), Assistant Professor at Clemson University
Instructor Office Hour: Tuesday 4:00-5:00 pm, McAdams Hall 218
TA: Maha Almaimani (malmaim@clemson.edu)
TA Office Hour: Tuesday/Thursday 10:00-11:00 am, https://clemson.zoom.us/j/96562292188
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.
Recommended Materials
Computer Vision: Algorithms and Applications (http://www.szeliski.org/Book/)
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 (35%)
Project proposal presentation (5%)
Final project blog post (20%)
Final presentation (10%)
5 bonus points for top 20% blog posts picked by student mutual evaluation
Class participation (5%)
Note: Assignment out, Deadline
Date Lecture Presenter
1/9 Introduction [slides] Siyu Huang
Basic Image Processing
1/14 What is an Image; Sampling and Aliasing [slides] Siyu Huang
1/16 Image Filtering (Part I) [slides] Siyu Huang
Assignment #1 out - Convolution and cross-correlation
1/21 Image Filtering (Part II) [slides] Siyu Huang
1/23 Image Filtering in Frequency Domain [slides] Siyu Huang
1/28 Edge Detection [slides] Siyu Huang
Assignment #1 due - Convolution and cross-correlation
Assignment #2 out - Canny Edge Detector, Hough transform
1/30 Corner Detection [slides] Siyu Huang
Assignment #3 out - Harris corner detector and HOG descriptor
2/4 Feature Descriptors [slides] Siyu Huang
Assignment #2 due - Canny Edge Detector, Hough transform
Recognition
2/6 Image Recognition, Bag of Words [slides] Siyu Huang
Assignment #4 out - Face detection
2/11 Image Segmentation (Part I) [slides] Siyu Huang
2/13 Image Segmentation (Part II) [slides] Siyu Huang
Assignment #3 due - Harris corner detector and HOG descriptor
Stereo Vision
2/18 Image Transformations [slides] Siyu Huang
2/20 Image Homographies [slides] Siyu Huang
Assignment #4 due - Face detection
2/25 Image Alignment [slides] Siyu Huang
2/27 Camera Models [slides] Siyu Huang
3/4 Camera Calibration, Structure-from-Motion [slides] Chaoyi Zhou
3/6 Project Proposal Presentation-I Students
3/11 Project Proposal Presentation-II Students
Videos
3/13 Optical Flow [slides] Siyu Huang
3/18, 3/20 Spring Break
3/25 Tracking [slides] Siyu Huang
Deep Learning Era
3/27 DL-based Computer Vision [slides] Siyu Huang
Assignment #5 out - Lukas-Kanade tracking
4/1 Deep Learning, Pytorch, Palmetto [slides] Siyu Huang
4/3 Object Detection, Semantic Segmentation [slides] Siyu Huang
Assignment #5 due - Lukas-Kanade tracking
4/8 Image Generation [slides] Siyu Huang
4/10 Novel View Synthesis Xi Liu
Final Project Presentation
4/15 Final project presentation Students
4/17 Final project presentation Students
Final project blog post due, links released to students for mutual evaluation
4/22 Final project presentation Students
4/24 Final project presentation Students
4/27 Blog post mutual evaluation due
5/5 Grades Submitted