·International
| Course Information
《视觉计算理论与工程实践》课程简介
Introduction of Visual Computing Theory and Engineering
课程名称 (Course Name) ：Visual Computing Theory and Engineering
课程代码 (Course Code）：F034606
学分/学时 (Credits/Credit Hours)：2/36
开课时间 (Course Term )：春spring
开课学院（Course School）: 电子信息与电气工程学院 seiee
任课教师（Teacher）: Li Song（宋利）
课程讨论时数（Course Hours）: 3 小时(Hours)
课程实验数（Lab Hours）: 3 小时(Hours)
课程内容简介(Course Contents Introduction):
The audiences of this elective class are graduated students in School of Electronic Information and Electrical Engineering, featured by practical engineering works. The main contents include visual models, image texture analysis and synthesis, motion analysis, multiview geometry, machine learning in computer vision, visual computing theory, etc. It is intended to be a broadly accessible course about visual computation related application, such as gist extraction, image structure extraction, photo inpainting, color video or image carton, video stabilization, image stitching, multi-objects tracking, color image stereo matching, structure from motion, object recognition from video surveillance and abnormal events detection, etc.
教学大纲(Course Outline):
Lecture 1: Introduction
Lecture 2: David Marr's Visual Computing Theory
Lecture 3: HVS Basics, V1 Sparse Model and Visual Attention Model
Lecture 4: Image Restoration and Image Ill-Inverse Problem
Lecture 5: OpenCV Introduction and Cases Analysis (with Discuss)
Lecture 6: Feature Descriptors
Lecture 7: Motion and Geometry
Lecture 8: Segmentation and Tracking
Lecture 9: Statistical and Machine Learning
Lecture 10: Open Contest and Challenge Introduction
Lecture 11: Project Report and Discuss.
课程进度计划(Course Schedule):
|
Week |
Content |
Required for students |
|
1 |
Overview of this course and background knowledge(Lecture 1) |
previewing chapter 1 of ref[1] |
|
2 |
Introduction of David Marr's Visual Computing Theory(Lecture 2) |
previewing Marr's book (ref[7]) |
|
3 |
HVS Basics, V1 Sparse Model and Visual Attention Model(Lecture 3) |
previewing ref[3] |
|
4 |
Image Restoration and Image Ill-Inverse Problem(Lecture 4) |
preview Chapter 1-3 of ref[4] |
|
5 |
OpenCV Introduction and Feature Descriptors-I (Lecture 5) |
Install OpenCV and run demos before class. |
|
6 |
Feature Descriptors-II(no class) |
Reading my course documents and preparing discuss next class. |
|
7 |
Review of Lecture 6 and Lecture 7 |
previewing related Chapters in ref[1][2] and ref[5] |
|
8 |
Segmentation and Tracking(Lecture 8) |
preview chapter 5 in ref[1] and chapter 19 in ref[2] |
|
9 |
Statistical and Machine Learning(lecture 9) |
preview chapter 14 in ref[1] and ref[6] |
|
10 |
Open Contest and Challenge (lecture 10) |
preview the PASCAL VOC Challenge |
|
11 |
Project Report and Discuss(lecture 11) |
preparing your team project short report. |
课程考核要求(Course Examination Requirements)：
Grading Policy:
Show and discuss in class: 30%
Homework or Problem sets: 30%
Final project: 40%
参考文献(Course References)：
1. R. Szeliski, "Computer Vision: Algorithms and Applications", Springer, 2010.
2. S. Prince, "Computer vision: models, learning and inference", Cambridge University Press, 2012.
3. D. Hubel, "Eye, Brain and Vision", Scientific American Library, 1988, ISBN 0-7167-5020-1
4. Nikos Paragio, Yunmei Chen, Olivier Faugeras, "Handbook of mathematical models in computer vision", Springer, 2006
5. Richard Hartley, Andrew Zisserman, "Multiple view geometry in computer vision" (2nd Edition), Cambridge university press, 2003
6. Christopher M. Bishop, "Pattern recognition and machine learning", Springer, 2006.
7. David Marr, "Vision: A Computational Investigation into the Human Representation and Processing of Visual Information", MIT Press, 2010.