Course Name: Computer Vision
| Course Code:S2293235
|
Semester: 5
| Credit: 2
|
Program: Computer science
|
Course Module: Optional
|
Responsible: Jianrong Wang
| E-mail: wjr@tju.edu.cn
|
Department: Tianjin International Engineering Institute
|
Time Allocation (1 credit hour = 45 minutes)
Exercise
| Lecture
| Lab-study
| Project
| Internship
(days)
| Personal
Work
| 8
| 12
| 20
|
|
| 10
|
|
Course Description
Computer vision aims to recover useful information about a 3D scene from its 2D projections (images), such as the depth and structure, motion, surfaces curvature and orientation of 3D objects and status and meaning of the actions of 3D scene. In this course, basic concept, theories and algorithms of computer vision are introduced. Students will learn basic operations on images in this course, such as edge detection, stereo vision, 3D motion analysis and other knowledge of the image, while the contour, texture, shadow, light flow, camera calibration, 3D surface graph algorithms and reconstruction will also be discussed in detail.
|
Prerequisite
Data structures: Strengthen basic data structures and object-oriented programming skills. And lay a solid foundation for subsequent computer science courses.
Working knowledge of C/C++ : Basic programming skills training.
Linear algebra: It’s the course that tells linear relationship between variables discipline.
Vector calculus. Vector calculus is a branch of mathematics concerned with differentiation and integration of vector fields, primarily in 3-dimensional Euclidean space.
|
Course Objectives
In computer vision, the goal is to develop methods that enable a machine to “understand” or analyze images and videos. In this introductory computer vision course, we will explore various fundamental topics in the area, including
Image formation,
Feature detection and segmentation, and to
Multiple view geometry, recognition and learning, and video processing.
|
CourseSyllabus
Image Formation and Filtering: Basic knowledge about image.
Feature Detection and Matching: Knowledge about Image features’ extraction and processing.
Multiple Views and Motion: Deep study about scene motion characteristics.
Machine Learning Crash Course and Recognition: To complete the identification process after the learning process.
|
Textbooks & References
Richard Szeliski.Computer Vision: Algorithms and Applications. Microsoft Research, 2010.
M. Aiello.Spatial Reasoning: Theory and Practice. 2002.
M.Bishop. Pattern Recognition and Machine Learning, Information Science and Statistics, Springer, 2007.
Gary Bradski and Adrian Kaebler.Learning OpenCV: computer vision with the opencv library. 2008.
|
Capability Tasks
CT1: To have ability to synthesize knowledge of relevant disciplines.
CT2: To be familiar with the use of the knowledge, malleable.
CT3: To use tools to solve practical problems.
CT4: To make completion of the pilot.
CT9: To use what they have learned into the business team and communicate with others.
CS1: To master mathematical methods and tools commonly used in computer science to understand how computer works.
CS2: Acquire computer software theory and master information processing knowledge.
|
Achievements
To understand basic concepts of computer vision, development and application of computer vision, computer vision status quo. - Level: N
To understand camera imaging principle and pinhole camera imaging model. - Level: A
To understand basic introduction to projective geometry and mathematical expression method of geometric elements. - Level: M
To grasp Multi-view geometry theory, including single vision projective geometry measurement, the basic concepts of the outer electrode geometry in two-view geometry, and derivation and meaning of fundamental matrix and essential matrix. - Level: N
To grasp Stereoscopic method, including three-dimensional object depth information from the image obtained by double cameras, including direct reconstruction and layered reconstruction theory. - Level: A
To grasp visual system calibration, including Tsai 3D calibration Templates calibration algorithm, 2D calibration Templates calibration algorithm, calibration algorithm based on a round of calibration algorithm, 1D calibration algorithm, calibration algorithm based on self-calibration algorithm Kruppa equation. - Level: A
|
Students: Computer science,Year 3
|
