CS570 Computer Vision
Nazar Khan
Human beings (and even animals) "look" at the real-world and extract extremely accurate information extremely efficiently. Computers can fail catastrophically at this task! In this course we look into why "Vision" is a difficult problem to solve and we go through successful, mathematically well-founded techniques used to solve the Vision problem.
This course is a useful application of mathematical concepts from Linear Algebra and Calculus. Therefore, the students could do well by brushing up on their Linear Algebra, Calculus and programming skills before taking this class. The techniques learned here can be useful for other areas such as Image Processing, Machine Learning, Artificial Intelligence and Computer Graphics.
CS 570 is a graduate course worth 3 credit hours.
Lectures: Monday and Wednesday, 10:15 a.m. - 11:45 a.m. Room 14, FCIT, Allama Iqbal (Old) Campus
Google Classroom:
Office Hours: Monday, 2:30 p.m. - 3:30 p.m. or by appointment
Grading:
Assignments |
35% |
Project |
15% |
Quizzes |
5% |
Tests |
5% |
Mid-Term |
15% |
Final |
25% |
Prerequisites
Books and Other Resources
No single book will be followed as the primary text. Helpful online and offline resources include:
Image Processing
Computer Vision
Lectures
# |
Topics |
Slides |
Videos |
Recitations |
Readings |
Miscellaneous |
1 |
Introduction
|
|
||||
2 |
Background Math I
|
Friday November 26: Recitation 1
|
|
|||
3 |
Background Math II
|
|
||||
4 |
Image Filtering
|
Friday December 3: Recitation 2
|
|
|||
5 |
Derivative Approximations
|
|
||||
6 |
Derivative Filtering & Edge Detection
|
Saturday December 11: Recitation 3
|
|
|
||
7 |
The Structure Tensor
|
|
||||
8 |
Corner Detection
|
Saturday December 18: Recitation 4
|
|
|
||
9 |
Local Image Descriptors I
|
|
||||
10 |
Local Image Descriptors II
|
Friday December 24: Recitation 5
|
|
|||
11 |
Hough Transform
|
|
||||
12 |
Deep Learning -- I
|
Friday January 14: Recitation 6
|
|
|||
13 |
Deep Learning -- II
|
|
|
|
||
14 |
Convolutional Neural Network (CNN)
|
Friday January 21: Recitation 7
|
|
|||
|
|
|||||
15 |
Object Detection, Classification and Segmentation via Mask R-CNN
|
Object Detection, Classification and Segmentation via Mask R-CNN |
|
|
||
16 |
Object Detection, Classification and Segmentation via Mask R-CNN
|
Object Detection, Classification and Segmentation via Mask R-CNN |
Friday February 4: Recitation 8
|
|
||
17 |
2D Spatial Transformations
|
|
||||
18 |
Estimating and Applying Transformations
|
Friday February 11: Recitation 9
|
|
|||
19 |
... DLT continued Image Warping
|
|
||||
20 |
Robust Estimation
|
Friday February 18: Recitation 10
|
|
|||
21 |
Optic Flow -- Local I
|
|
|
|
||
22 |
Optic Flow -- Local II
|
Friday February 25: Recitation 11
|
|
|||
23 |
Optic Flow -- Global
|
|
|
|
||
24 |
Camera Geometry
|
|
|
|||
25 |
Camera Anatomy
|
Friday March 11: Recitation 12
|
|
|
||
26 |
|
|
||||
|
|