Syllabus
PROFESSIONAL ELECTIVES
Electives in Computer Vision
Unit I
Introduction, Image Formation – geometric primitives and transformations, photometric image formation, projective geometry, Camera Geometry, Sensor and Image Model, Camera Extrinsics and Intrinsics, Homogeneous Coordinates, DLT and Camera Calibration. Implementation of camera calibration algorithm using checker board.
Unit II
Stereo Geometry – Geometry of the Image Pair, Epipolar Geometry, Fundamental matrix and Essential Matrix, Direct Solution for Fundamental and Essential Matrix. Depth estimation from Stereo geometry, Multi-View geometry, Pose estimation. Feature Detection- points and patches, Förstner Operator, edges, lines, corners
Unit III
Feature Descriptors and Matching – SIFT Features and RANSAC, Feature-Based Alignment – Image Stitching, Dense motion estimation – Optical flow, Kalman Filter. Deep Learning Architectures for computer vision: AlexNet on ImageNet, VGGNet on ImageNet, GoogleNet on ImageNet
Objectives and Outcomes
Course Objectives
- The intent of this course is to familiarize the students on the fundamental concepts of Computer Vision and Image Processing.
- This course covers the basis of image formation in a camera and camera calibration under different environment.
- The course covers detection of various image features and matching them across images for practical applications such as image stitching, motion estimation and object tracking.
- The course introduces few deep learning architectures that form the backbone for real world computer vision applications.
Course Outcomes
CO1: Understand the formation of an image in the camera and apply projective transformations, calibration algorithms
to model a camera in the real world.
CO2: Understand stereo, multi view geometry concepts and apply algorithms for depth estimation.
CO3: Apply Feature Detection, Descriptors and Matching methods on images.
CO4: Analyze the performance of basic deep learning architectures for computer vision applications.
CO-PO Mapping
| PO/PSO |
PO1 |
PO2 |
PO3 |
PO4 |
PO5 |
PO6 |
PO7 |
PO8 |
PO9 |
PO10 |
PO11 |
PO12 |
PSO1 |
PSO2 |
| CO |
| CO1 |
3 |
3 |
2 |
2 |
2 |
– |
– |
– |
2 |
1 |
– |
2 |
3 |
2 |
| CO2 |
3 |
3 |
2 |
2 |
2 |
– |
– |
– |
– |
– |
– |
2 |
3 |
2 |
| CO3 |
3 |
3 |
2 |
2 |
2 |
– |
– |
2 |
2 |
2 |
– |
2 |
3 |
2 |
| CO4 |
3 |
3 |
2 |
2 |
3 |
– |
– |
3 |
3 |
3 |
– |
2 |
3 |
2 |
Evaluation Pattern
Evaluation Pattern: 70:30
| Assessment |
Internal |
End Semester |
| Mid Term Exam |
20 |
|
| Continuous Assessment Theory (*CAT) |
10 |
|
| Continuous Assessment Lab (*CAL) |
40 |
|
| **End Semester |
|
30 (50 Marks; 2 hours exam) |
*CAT – Can be Quizzes, Assignments, and Reports
*CAL – Can be Lab Assessments, Project, and Report
**End Semester can be theory examination/ lab-based examination/ project presentation
Text Books / References
Textbook(s)
Szeliski R. “Computer Vision: Algorithms and Applications”, Springer. New York. 2010.
David A. Forsyth, “Computer Vision: A Modern Approach”, 2nd edition, 2012.
Dr.Adrian Rosebrock, “Deep learning for computer vision with python”, PYIMAGESEARCH, 2017.
Reference(s)
- Hartley and A. Zisserman, “Multiple View Geometry in computer vision,” Cambridge University Press, 2000.
Amin Ahmadi Tazehkandi, “Hands-On Algorithms for Computer Vision: Learn how to use the best and most practical computer vision algorithms using OpenCV”,Packt Publishing, 2018.
