Schedule
A tentative schedule below (subject to change as we progress).
Date Main Topic Subtopics Items due week 1 (Tue: 01/25)
Introduction to Computer Vision (part 1)
Lecture slide 1a
Brief introduction
Course logistics
What is computer vision?
From Images to 3D Models How computers can automatically build realistic 3D models from 2D images acquired with a handheld camera. Marc Pollefeys and Luc Van Gool. ACM Communication'2002
week 1 (Thu: 01/27)
Introduction to Computer Vision (part 2)
Lecture slide 1b
Why is computer vision so primitive?
What makes vision hard?
How does human vision work?
What is state-of-the-art?
Review quiz
week 2 (Tue: 02/01)
Filtering
Lecture slide 2a
Task: manipulating an image?
Image fundamentals
What are the assumptions?
Assumptions for removing noise
Image filtering
Cross-correlation problem
week 2 (Thu: 02/03)
Filtering (continued)
Lecture slide 2b
Convolution
Filtering examples
Practical considerations
Activity: speeding up the convolution?
Review quiz
week 3 (Tue: 02/08)
Edge detection
Lecture 3 slide
Edges and gradients
Computing gradients
Dealing with noise
Canny edge detection
Implementation issues
week 3 (Thu: 02/10)
Edge detection (continued)
Line detection
Hough transform
Hough transform in practice
Activity: a convoluted way of computing gradients?
Review quiz
week 4 (Tue: 02/15)
Segmentation
Lecture 4 slide
Image segmentation
Segmentation as clustering
Clustering on real images
Mean shift clustering
Segmentation with complete graph
week 4 (Thu: 02/17)
Segmentation (continued)
Activity: the problem with cuts?
Normalized cut
Segmentation with spanning trees
Activity: applying popular segmentation on real images
Review quiz
week 5 (Tue: 02/22)
Feature points
Lecture 5 slide
Feature points
Corner detection
Activity: Matrices, error functions, and corners
Identifying corners
Identifying scale and orientation
week 5 (Thu: 02/24)
Feature points (continued)
Scale Invariant Feature Transform (SIFT)
Image and feature matching
Activity: How slow it is?
Activity: applying SIFT on real images
Deep feature learning with Siamese Neural Network (Reza AIPR'20)
Review quiz
week 6 (Tue: 03/01)
Deep Learning
Lecture 6 slide
Neural Network
Convolutional Neural Network (CNN)
CNN Success
Convolution
Spatial pooling
Non-linearity
Case studies of different CNN architectures
week 6 (Thu: 03/03)
Deep learning
Practical implementation of CNN in PyTorch
Review quiz
week 7 (Tue: 03/08)
Midterm exam review
week 7 (Thu: 03/10)
Midterm Exam
week 8 (Tue: 03/15)
Spring break (no class)
week 8 (Thu: 03/17)
Spring break (no class)
week 9 (Tue: 03/22)
Transformation
Lecture 7 slide
Image warping
Activity: Warping
Linear transformation
Homogenous coordinates
Affine and projective transformation
week 9 (Thu: 03/24)
Image matching
Image matching
RANdom SAmple Consensus (RANSAC)
Activity: how many rounds?
RANSAC parameters and implementation details
Review quiz
week 10 (Tue: 03/29)
Projection
Lecture 8 slide
Cameras and projection
Activity: shrinking apertures
Aperture trade-offs
Consequence of projection
week 10 (Thu: 03/31)
Projection (continued)
Modeling projection
Activity: projection practice
Generalizing the model
Adding a lens
Review quiz
week 11 (Tue: 04/05)
Stereo
Lecture 9 slide
Depth from stereo
Epipolar geometry
Epipolar constraint
The case of parallel cameras
Parallel cameras and rectification
week 11 (Thu: 04/07)
Stereo (continued)
Naive stereo matching
Scanline stereo
Stereo matching with deep neural network
Review quiz
week 12 (Tue: 04/12)
Markov Random Fields
Lecture 10 slide
Markov Random Field (MRF)
Some applicaiton of MRFs
Binary MRFs
Graph cuts
Dense pixel-level image labeling with graph-cuts (Reza IROS'17, IROS'19)
Advantage of MRFs
Review quiz
week 12 (Thu: 04/14)
Recognition
Lecture 11 slide
Introduction to recognition
Bag of parts models
Object localization
HOG-based detection
Deformable part models (DPM)
week 13 (Tue: 04/19)
Deep learning-based recognition
Lecture 12 slide
Introduction to deep learning-based recognition
Convolutional neural network for object detection
Fast R-CNN
Mast R-CNN
YOLO
Review quiz
week 13 (Thu: 04/21)
Beyond recognition
Lecture 13 slide
Deep learning for semantic segmentaiton
Review quiz
week 14 (Tue: 04/26)
Beyond recognition
Generative Adversarial Network (GAN)
Recurrent Neural Network (RNN, LSTM, Transformer)
week 14 (Thu: 04/28)
Final project discussion
Course Evaluation
week 15 (Tue: 05/03)
Project presentation
week 15 (Thu: 05/05)
Project presentation
Week 16 (Tue: 05/10)
Final Exam
TBA
TBA
Final Project Code + Report (due by 05/10)
Acknowledgement
Many of the above slides are modified from the excellent class notes of similar course offered in Indiana University. The instructor is extremely thankful to Prof David Crandall (Indiana University) for making his notes available personally to the instructor.