Course Information
Term: Spring 2022
Class Level: Graduate
Activity Type: Lecture
Days & Times: Monday & Wednesday 1:00 PM – 2:15 PM
Location: ECSN 2.126
Instructor: Prof. Yu Xiang
Office Location: ECSS 4.702
Office Hours: Monday & Wednesday 3:30PM – 4:30 PM
Teaching Assistant: Jikai Wang
Office Hours: Tuesday 1:00PM – 2:00 PM
All the course materials can be found here.
Course Description
Theory and practice of computer vision. Provides in-depth overview of computer vision, including geometric primitives and transformations, camera models, image features, epipolar geometry and stereo, structure from motion and SLAM, 3D reconstruction, variations of modern neural networks and various recognition problems such as object detection, semantic segmentation, and human pose estimation.
Textbooks
Richard Szeliski. Computer Vision: Algorithms and Applications. 2011th Edition. Springer.
ISBN-13: 978-1848829343
ISBN-10: 1848829345
Second Edition Draft
David Forsyth, Jean Ponce. Computer Vision: A Modern Approach, 2nd Edition. Pearson, 2011. (Optional)
ISBN: 9789332550117
Richard Hartley. Multiple View Geometry in Computer Vision, 2nd Edition. Cambridge University Press, 2004. (Optional)
ISBN-13: 978-0521540513
ISBN-10: 0521540518
Grading Policy
- Homework (50%)
- Assignment 1 (10%)
- Assignment 2 (10%)
- Assignment 3 (10%)
- Assignment 4 (10%)
- Assignment 5 (10%)
- Team Project (45%)
- Project proposal (5%)
- Project mid-term report (10%)
- Project presentation (15%)
- Project final report (15%)
- In-class Activity (5%)
Project
- Project proposal description (PDF)
- Project mid-term report requirement (PDF)
- Project presentation and final report requirement (PDF)
Homework
- Assignment 1 (PDF, programming)
- Assignment 2 (PDF, programming)
- Assignment 3 (PDF, programming)
- Assignment 4 (PDF, programming)
- Assignment 5 (PDF, programming)
Learning from the “Cracker Box”
Guest Lecturer
Dr. Fei Xia from Google Research talked about Embodied AI on 4/27/2022.
Lectures
| Date | Topic |
| Week 1, 1/17 | Martin Luther King Day |
| Week 1, 1/19, Lecture 1 | Introduction to Computer Vision (slides) |
| Week 2, 1/24, Lecture 2 | Image Formulation: Geometric Primitives and Transformations (slides) |
| Week 2, 1/26, Lecture 3 | Image Formulation: 3D Rotations (slides) |
| Week 3, 1/31, Lecture 4 | Image Formulation: Camera Models (slides) |
| Week 3, 2/2, Lecture 5 | Image Formulation: Visual Rendering I (slides) |
| Week 4, 2/7, Lecture 6 | Image Formulation: Visual Rendering II (slides) |
| Week 4, 2/9, Lecture 7 | Feature Detection and Matching: Keypoint Features I (slides) |
| Week 5, 2/14, Lecture 8 | Feature Detection and Matching: Keypoint Features II (slides) |
| Week 5, 2/16, Lecture 9 | Feature Detection and Matching: Edges, Contours and Lines (slides) |
| Week 6, 2/21, Lecture 10 | 3D Vision: Camera Calibration and Pose Estimation (slides) |
| Week 6, 2/23, Lecture 11 | 3D Vision: Epipolar Geometry and Stereo (slides) |
| Week 7, 2/28, Lecture 12 | 3D Vision: Structure from Motion and SLAM (slides) |
| Week 7, 3/2, Lecture 13 | 3D Vision: 3D Reconstruction (slides) |
| Week 8, 3/7, Lecture 14 | Deep Learning: Convolutional Neural Networks I (slides) |
| Week 8, 3/9, Lecture 15 | Deep Learning: Convolutional Neural Networks II (slides) |
| Week 9, 3/14 | Spring Break |
| Week 9, 3/16 | Spring Break |
| Week 10, 3/21, Lecture 16 | Deep Learning: Recurrent Neural Networks (slides) |
| Week 10, 3/23, Lecture 17 | Deep Learning: Transformers (slides) |
| Week 11, 3/28, Lecture 18 | Deep Learning: Generative Neural Networks (slides) |
| Week 11, 3/30, Lecture 19 | Deep Learning: Neural Networks for 3D Data (slides) |
| Week 12, 4/4, Lecture 20 | Recognition: Visual Representation Learning (slides) |
| Week 12, 4/6, Lecture 21 | Recognition: Optical Flow and Correspondences (slides) |
| Week 13, 4/11, Lecture 22 | Recognition: Object Detection (slides) |
| Week 13, 4/13, Lecture 23 | Recognition: Semantic Segmentation (slides) |
| Week, 14, 4/18, Lecture 24 | Recognition: Pose Estimation of Objects, Humans and Hands (slides) |
| Week 14, 4/20, Lecture 25 | Recognition: Images and Languages (slides) |
| Week 15, 4/25, Lecture 26 | Application: Computer Vision in Robotics (slides) |
| Week 15, 4/27 | Guest Lecture: Dr. Fei Xia Hierarchical Learning Approaches for Long Horizon Robotics Tasks (slides) |
| Week 16, 5/2 | Project Presentation I Group 1: Visual Navigation Using ORB-SLAM3 (slides, demo) Group 2: Teaching Robots to Explore Unseen Environments (slides) Group 3: Interacting with Virtual Environment through Hand Pose Estimation (slides, demo) Group 4: Image Segmentation (slides) Group 6: Pose Based Form Correction Trainer (slides, demo) Group 8: Parking Spot Detection OpenCV (slides) Group 9: Identity Verification using Siamese Neural Networks (slides) Group 11: Few-shot Object Classification in Clutter Scenes (slides) Group 16: Solving Sudoku using Object Character Recognition (slides) |
| Week 16, 5/4 | Project Presentation II Group 10: Visual Question Answering (slides) Group 12: Scene Description Generation (slides) Group 13: A Study on Artist Attestation (slides) Group 14: Object Detection with DETR (slides) Group 15: Comparative Analysis of Blood Cell Image Classification (slides) Group 17: Referring Expression Comprehension with Audio Query (slides) Group 18: Image Segmentation for Platypuses in Nature (slides) Group 19: Image Grounding using Attention based Transformer (slides) Group 20: Cutting-Edge Techniques for Depth Map Super-Resolution (slides) |