National Institute of Technology Rourkela

राष्ट्रीय प्रौद्योगिकी संस्थान राउरकेला

ଜାତୀୟ ପ୍ରଯୁକ୍ତି ପ୍ରତିଷ୍ଠାନ ରାଉରକେଲା

An Institute of National Importance

Syllabus

Course Details

 Go Back

Subject {L-T-P / C} : CS3303 : Computer Vision { 3-0-0 / 3}

Subject Nature : Theory

Coordinator : Dr. Puneet Kumar Jain

Syllabus

UNIT – I: Fundamentals of Image Processing and Computer Vision
What is an Image and Computer Vision, Image formation, Camera Projection, Sampling and Aliasing, Image Filtering, Frequency domain analysis of Image, Pyramids and Wavelet

UNIT – II: Feature detection and matching
Edge detection, Feature points and corners, Local Image features, SIFT, Hough transform, Feature Descriptors, Feature Matching

UNIT – III: Camera Geometry and Multiple View
Camera Geometry, Camera calibration, Stereo vision, Epipolar geometry, Image Alignment, RANSAC, Optical Flow

UNIT – IV: Recognition and Motion estimation
Image Classification, Object detection, Semantic segmentation

Course Objectives

  • The course will introduce computer vision, including fundamentals of image formation, camera imaging geometry, feature detection and matching, stereo, motion estimation and tracking, image classification, scene understanding, and pattern recognition.
  • The course will equip the students with programming experience from implementing computer vision and object recognition applications.
  • The course will develop basic methods for applications that include finding known models in images, depth recovery from stereo, camera calibration, image stabilization, automated alignment, tracking, boundary detection, and recognition.
  • The course will develop the intuitions and mathematics of the methods in class and then learn about the difference between theory and practice in homework.

Course Outcomes

After completing this course, the student must demonstrate the knowledge and ability to: <br />CO1: Recognize and describe both the theoretical and practical aspects of image formation and computing with images. <br />CO2: Understand the basics of 2D and 3D Computer Vision and Connect issues from Computer Vision to Human Vision. <br />CO3: Become familiar with the significant technical approaches in computer vision, including registration, alignment, and image matching. <br />CO4: Get exposure to advanced concepts leading to object categorization and segmentation in images. <br />CO5: Build computer vision applications.

Essential Reading

  • Richard Szeliski, Computer Vision: Algorithms and Applications, 2nd ed., The University of Washington, 2022 , Reference: http://szeliski.org/Book/
  • D. Forsyth and J. Ponce, Computer Vision - A modern approach, 2nd ed, Pearson Education India, 2015 , Reference: http://luthuli.cs.uiuc.edu/~daf/CV2E-site/cv2eindex.html

Supplementary Reading

  • Richard Hartley and Andrew Zisserman, Multiple View Geometry in Computer Vision, 2nd ed., Cambridge University Press, 2004 , Reference: http://www.r-5.org/files/books/computers/algo-list/image-processing/vision/Richard_Hartley_Andrew_Zisserman-Multiple_View_Geometry_in_Computer_Vision-EN.pdf
  • Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, MIT Press, 2016 , Reference: https://www.deeplearningbook.org/

Journal and Conferences

  • CVPR: IEEE Conference on Computer Vision and Pattern Recognition
  • ICCV: International Conference on Computer Vision
RELATED LINKS