Homework
- cs131 @ stanford
- ...
Overview
...
Instructor: Zhixun Su, Junjie Cao, jjcao@dlut.edu.cn; TA: ?; QA: https://piazza.com?
关于大作业：共7个，每人交一份纸质版本，作为课程成绩的依据。截止时间2019.06.24. 作业描述， 材料1， 材料2.
When & where
Mon. 8:00 - 9:35am, 研409; Thur. 13:30 - 15:05pm, 研409
Schedule
| Topic | Lab assignments | Reading |
|---|---|---|
| 1. Introduction; Image processing | ||
| 2. Filtering; Anisotropic diffusion | ||
| 3. Haar transform, Fourier transform, Wavelets | ||
| 4. Edge detection (Derivative of gaussians, Sobel filters, Canny edge detector) | ||
| 5. Camera Calibration | ||
| 6. Multiview Stereo | ||
| 7. Segmentation, snakes, PDE, clustering | ||
| 8. Segmentation, saliency, Subspace clustering | ||
| 9. Local Feature Detection; | Harris, Scale invariant features. | Sec 4.1 in [RS]; David Lowe, IJCV 2004. |
| 10. Local Image Feature Description & Matching; | SIFT, HoG, Matching. | Sec 4.1.3, 4.3.2 in [RS]; David Lowe, IJCV 2004. |
| 11. Optical Flow | ||
| 12. Object recognition | ||
| 13. Tracking; Deep learning | ||
| 14. Deep learning-tips | ||
| 15. CNN | ||
| 16. 2d human pose detection |
Book
There is no requirement to buy a textbook. The goal of the course is to be self contained, but sections from three textbooks will be suggested for more formalization and information.- [FP] D. A. Forsyth and J. Ponce. Computer Vision: A Modern Approach (2nd Edition), 2011.
- [RS] Richard Szeliski. Computer Vision: Algorithms and Applications, 2010.
- [GBC] Ian Goodfellow and Yoshua Bengio and Aaron Courville, Deep Learning, by MIT, online.
- Concise Computer Vision by Reinhard Klette
- [HZ] R. Hartley and A. Zisserman. Multiple View Geometry in Computer Vision, 2003
Course
- [CV] CS131 Computer Vision: Foundations and Applications @ Stanford, 2018.
- [CV, Advance] CS231A: Computer Vision, From 3D Reconstruction to Recognition @ Stanford by Silvio Savarese
- [CV] CSCI 1430: Introduction to Computer Vision @ Brown，2019
- CSE152: Introduction to Computer Vision by Hao Su, 2018
- [DP]: CS231n: Convolutional Neural Networks for Visual Recognition @ Stanford by Feifei Li
- [DP]: CS 330: Deep Multi-Task and Meta Learning @ Stanford
- [DP]: CS 230: Deep Learning @ Stanford by Prof. Andrew Ng and Kian Katanforoosh
Schedule 2019
| Topic | Lab assignments | Reading |
|---|---|---|
| 1. Introduction; Image processing | ||
| 2. Filtering; Anisotropic diffusion | ||
| 3. Haar transform, Fourier transform, Wavelets | ||
| 4. Edge detection (Derivative of gaussians, Sobel filters, Canny edge detector) | ||
| 5. Camera Calibration | ||
| 6. Multiview Stereo | ||
| 7. Segmentation, snakes, PDE, clustering | ||
| 8. Segmentation, saliency, Subspace clustering | ||
| 9. Local Feature Detection; | Harris, Scale invariant features. | Sec 4.1 in [RS]; David Lowe, IJCV 2004. |
| 10. Local Image Feature Description & Matching; | SIFT, HoG, Matching. | Sec 4.1.3, 4.3.2 in [RS]; David Lowe, IJCV 2004. |
| 11. Optical Flow | ||
| 12. Object recognition | ||
| 13. Tracking; Deep learning | ||
| 14. Deep learning-tips | ||
| 15. CNN | ||
| 16. 2d human pose detection |