Course title |
電腦視覺 Computer Vision: from recognition to geometry |
Semester |
107-1 |
Designated for |
COLLEGE OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCE GRADUATE INSTITUTE OF COMMUNICATION ENGINEERING |
Instructor |
簡韶逸 |
Curriculum Number |
EEE5053 |
Curriculum Identity Number |
943 U0550 |
Class |
|
Credits |
3.0 |
Full/Half Yr. |
Half |
Required/ Elective |
Elective |
Time |
Wednesday 7,8,9(14:20~17:20) |
Room |
電二143 |
Remarks |
與王鈺強合授 The upper limit of the number of students: 80. |
Ceiba Web Server |
http://ceiba.ntu.edu.tw/1071CV |
Course introduction video |
|
Table of Core Capabilities and Curriculum Planning |
Table of Core Capabilities and Curriculum Planning |
Course Syllabus
|
Please respect the intellectual property rights of others and do not copy any of the course information without permission
|
Course Description |
本課程的內容涵蓋電腦視覺的多個面向,從image processing, recognition/detection, 到geometry等方向都在課程內容之中,期能讓修課同學對電腦視覺領域有完整的認識。
課程網要如下:
Introduction to human vision systems
Camera basic, image formation and basic Image processing
Feature detection and matching
Machine learning basics
Deep learning basics
Recognition and detection
Segmentation
Projective Geometry, Transformations and Estimation/Camera calibration
Camera Geometry and Single View Geometry
Two-View Geometry
Dense motion estimation/stereo
Structure from motion
3D reconstruction/depth sensing
Computational photography
Object tracking
Advanced topics in CV
. |
Course Objective |
本課程的內容涵蓋電腦視覺的多個面向,從image processing, recognition/detection, 到geometry等方向都在課程內容之中,期能讓修課同學對電腦視覺領域有完整的認識。
本課程和另外一門課程Deep Learning for Computer Vision互相搭配,兩們課皆修將可對此領域有全盤且深入的學習。 |
Course Requirement |
需具備基本程式設計能力,本課程可能會使用C/C++/Python進行實作 |
Student Workload (expected study time outside of class per week) |
|
Office Hours |
Appointment required. |
Designated reading |
使用自編之講義,部分內容由參考書目而來。 |
References |
Richard Szeliski, Computer Vision: Algorithms and Applications, Springer, 2011.
Richard Hartley and Andrew Zisserman, Multiple View Geometry in Computer Vision, Second Edition, Cambridge, 2003.
Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, The MIT Press, 2016.
|
Grading |
No. |
Item |
% |
Explanations for the conditions |
1. |
作業 |
60% |
四次程式作業 |
2. |
分組期末專題 |
35% |
定題式期末專題,最多三人一組 |
3. |
上課情況 |
5% |
上課平時成績 |
|
Week |
Date |
Topic |
第1週 |
9/12 |
Introduction to human vision systems |
第2週 |
9/19 |
Camera basic, image formation and basic Image processing |
第3週 |
9/26 |
Feature detection and matching |
第4週 |
10/03 |
Machine learning basics |
第5週 |
10/10 |
國慶日放假 |
第6週 |
10/17 |
Deep learning basics |
第7週 |
10/24 |
Recognition and detection |
第8週 |
10/31 |
Segmentation |
第9週 |
11/07 |
Projective Geometry, Transformations and Estimation/Camera calibration |
第10週 |
11/14 |
Camera Geometry and Single View Geometry |
第11週 |
11/21 |
Two-View Geometry |
第12週 |
11/28 |
Dense motion estimation/stereo |
第13週 |
12/05 |
Structure from motion |
第14週 |
12/12 |
3D reconstruction/depth sensing |
第15週 |
12/19 |
Computational photography |
第16週 |
12/26 |
Object tracking |
第17週 |
1/02 |
Advanced topics in CV |