《Computer Vision》Course Syllabus
Author:管理员 Time:2017-04-11 Hit:209

Computer Vision》Course Syllabus

Course Name

Computer Vision

Instructor

Prof. Liangfu Li

Course Type

Elective Course

Prerequisite Courses

C Language; Linear Algebra; Advanced   Mathematics

Discipline

Computer Science

Learning Method

Lecture, Project practice

Semester

1st semester

Hours

40

Credit

2

 

1. Objective & Requirement

The object of this course is the graduate students of computer science and technology. This course aims at theory and technology which will thoroughly introduce typical applications of computer vision principle, technology, frontier research content and the computer vision in the military field. This course will teach students in computer machine vision processing theory and technology and related application research.

This course includes computer vision summary, computer vision applications in the military field, traditional algorithms of computer vision, frontier technology, etc. In the learning process the students will get study notes that cover the main contents of this course. The students will practice a small projects combined his research direction and computer vision applications, in order to complete the task of learning this course. The first course of the curriculum is advanced mathematics, linear algebra, basic probability theory, matrix, linear space, computer advanced programming language, and object-oriented programming technology.

2. Topics to be covered

We will cover the following core topics plus a set of selected topics:

(i) The basic theory of computer vision (basic visual principles, projection model, basic methods and practical algorithm, including the human vision, feeling field, visual information of multi-level parallel processing, visual information integration and feedback, image analysis).

(ii) 2D vision (2D motion analysis, Hough transform, Fourier descriptor, image segmentation, texture analysis of statistical methods, from the texture restoration shape, light and shade analysis, photometric stereo, color perception and color visual processing, color constancy).

(iii) 3D vision (depth image and stereo vision, camera calibration, vision system calibration, object representation, 3D motion analysis and object recognition).

3. Textbook

Richard Szeliski, Computer Vision: Algorithms and Applications, 2010.

4. Reference Books

  1. D. Comaniciu, An algorithm for data-driven bandwidth selection, IEEE Transactions on Pattern Analysis and Machine Intelligence [J]. 2003, 25(2): 281-288.

  2. E. Parzen. On estimation of probability function and mode. Annals of Mathematical statistics [J]. 1962, 33(3): 1-18.

  3. A.K. Jain, R.P.W. Duin, Mao Jianchang. Statistical pattern recognition: a review. IEEE Transactions on Pattern Analysis and Machine Intelligence [J]. 2000, 22(1): 4-37.

  4. M. Mason, Z. Duric. Using histograms to detect and track objects in color video. 30th Applied Imagery Pattern Recognition Workshop [C], 10-12 Oct. 2001. 154-159.

  5. K. Fukunaga, L.D.Hostetler. The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Transactions on Information Theory [J]. 1975, 21(1): 32-40.

  6. Cheng Yizong. Mean shift, mode seeking, and clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence [J]. 1995, 17(8): 790-799.

  7. D. Comaniciu, P. Meer. Mean shift: a robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence [J]. 2002, 24(5): 603-619.

  8. D. Comaniciu, V. Ramesh, and P. Meer. Kernel-based object tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence [J]. 2003, 25(5): 564-577.

  9. D. Comaniciu, V. Ramesh, P. Meer. Real-time tracking of non-rigid objects using mean shift. Computer vision and pattern recognition [J]. 2000, 2: 142-149.

5. Course Evaluation (Tentative)

Course teaching                    50%

Course Project                         50%