CS6350: Computer Vision

July - November, 2022

Course Contents

Computer Vision Handout Download Slide

  • Objectives:
    • Computer Vision focuses on development of algorithms and techniques to analyze and interpret the visible world around us. This requires understanding of the fundamental concepts related to multi-dimensional signal processing, feature extraction, pattern analysis visual geometric modeling, stochastic optimization etc. Knowledge of these concepts is necessary in this field, to explore and contribute to research and further developments in the field of computer vision. Applications range from Biometrics, Medical diagnosis, document processing, mining of visual content, to surveillance, advanced rendering etc.
  • References

    Textbooks
    Richard Szeliski, Computer Vision: Algorithms and Applications, Springer-Verlag London Limited 2011.

    Computer Vision: A Modern Approach, D. A. Forsyth, J. Ponce, Pearson Education, 2003.


    References
    Richard Hartley and Andrew Zisserman, Multiple View Geometry in Computer Vision, Second Edition, Cambridge University Press, March 2004.

    Christopher M. Bishop; Pattern Recognition and Machine Learning, Springer, 2006

    R.C. Gonzalez and R.E. Woods, Digital Image Processing, Addison- Wesley, 1992.
    K. Fukunaga; Introduction to Statistical Pattern Recognition, Second Edition, Academic Press, Morgan Kaufmann, 1990.

    Journals
    IEEE-T-PAMI (IEEE Transactions on Pattern Analysis and Machine Intelligence).
    IJCV (International Journal of Computer Vision) - Springer.

    Lecture Slides

    Topic-Wise References

    1 Introduction  Download Slide
    2 Neighborhood and Connectivity of pixels Download Slide
    3 Fourier Theory and Filtering in spatial and spectral domains Download Slide
    4 (i)Enhancement & (ii)Restoration Download Slide
    5 Histogram based image processing Download Slide
    6 3D transformations and projection

    Download Slide

    7 Concepts in Edge Detection Download Slide
    8 Hough Transform Download Slide
    9 Image segmentation Download Slide
    10 Pattern Recognition Download Slide
    11 Motion Detection and Tracking Download Slide
    12 Shape from Shading Download Slide
    13 Texture analysis using Gabor filters Download Slide
    14 SCALE-SPACE - Theory and Applications Download Slide
    15 Local Feature Detectors and Descriptors Download Slide
    13 Motion Download Slide
    17 Wavelet transform Download Slide
    18 Morphology Download Slide
    19 Image Restoration Download Slide

    Additional Resources


  • Video Lectures Links:

  • Github Links:
  • Interesting links:
  • Term Project Assignment



    Term Project Allotment List: To be Decided

    Term Project Assignment List
    SL No. Problem Statement Performance based marks (indicative) Group IDs Alloted
    Details
    Satisfactory Good Excellent
    1 Domain Adaptation for Object Detection in target domain using weakly-supervised / self-supervised or semi-supervised settings - - 39 -- Download Slide
    2 Face Recognition using Face Images obtained from the Internet - - 40 -- Download Slide
    3 YOLOv5++ for overlap object detection from cluttered indoor shots, invariant to sensor, lighting and affine transformation - - 40 -- Download Slide
    4 Video Analytics: Prediction, affordances; or any new/novel ideas/tasks yet unheard of in CV/DL paradigm * - - 42 -- Download Slide
    5 Monocular 3D Object Detection for indoor objects - - 42 -- Download Slide
    6 Scene Segmentation of indoor Panorama - - 41 -- Download Slide
    7 Joint Image Deblurring/Super-Resolution and Low-light Image Enhancement - - 38 -- Download Slide
    8 Learn image auto-correction (brush restoration) and auto-enhancement from few training samples # - - 42 -- Download Slide
    9 Image to Image transformation (few samples) using VAE, GANs etc - - 41 -- Download Slide
    10 Real (True) depth estimation from indoor scenes, given a model (DL tool) for virtual depth estimation - - 42 -- Download Slide
    11 3D Topologically-Aware Semantic Scene reconstruction and depth map / wireframe / Point-Cloud from single RGB panorama scene (or Two views) - - 43 -- Download Slide
    12 Synthesis(Generation) of adversarial (image) datasets to prove null hypothesis on DL systems (pick any SOA: OR, FR, Segmentation) - - 40 -- Download Slide
    13 Auto-estimation of homography over a planar patch, from a single view # - - 37 -- Download Slide
    14 Object-Goal Navigation task by learning from environment - - - -- Download Slide

    * Get permission from course instructor for the novel plan of work.
    # Can be solved using shallow techniques of computer vision

    Tutorial

      Note: These dates are tentative.
    Tutorial No. Date Time
    1 02/08/2022   08:00-08:50  
    2 23/08/2022 08:00-08:50
    3 06/09/2022 08:00-08:50
    4 27/09/2022 08:00-08:50
    5 11/10/2022 08:00-08:50
    6 25/10/2022 08:00-08:50

    Schedule

    Marks Distribution

    Logistic Details


    Class Schedule (Slot B)
    Monday

    9:00 a.m. - 9:50 a.m.
    Tuesday
    8:00 a.m. - 8:50 a.m.
    Wednesday
    12:00 noon - 12:50 p.m.
    Friday
    11:00 a.m. - 11:50 a.m.


    Announcements

    Optional TPA : 15th October, 2022

    Extra Class : To be announced

    Final TPA Review: Slot 1: 12/11/2022 and 19/11/2022, Slot 2: 23/11/2022 and 24/11/2022

    Self-study


    Slides for Self-Study Content

    Sl. no. Content (pdf filename) Portion Link
    1 Neighborhood and Connectivity of pixels Entire pdf Download Slide
    2 Fourier Theory and Filtering in spatial and spectral domains Slides 1-27, 37-44

    Download Slide

    3 Enhancement Slides 21-27

    Download Slide

    4 Histogram based image processing First 23 slides

    Download Slide

    5 3D transformations and projection Slides 1-10

    Download Slide

    6 Concepts in Edge Detection Slides 57-67, 70-93(Adv. studies)

    Download Slide

    7 Hough Transform Slides 35-40

    Download Slide

    8 Pattern Recognition Slides 44-63

    Download Slide

    9 Local Feature Detectors and Descriptors First 25 slides

    Download Slide

        Note: