Machine Learning Summer School 2008 - Kioloa

Learning in Computer Vision

author: Simon Lucey, Carnegie Mellon University

Description

This tutorial he will cover some of the core fundamentals in vision and demonstrate how they can be interpreted in terms of machine learning fundamentals. Unbeknownst to most researchers in the field of machine learning, the fundamentals of object registration and tracking such as optical flow, interest descriptors (e.g., SIFT), segmentation and correlation filters are inherently related to the learning topics of regression, regularization, graphical models, generative models and discriminative models. As a result many aspects of vision can be interpreted as applied forms of learning. From this discussion on fundamentals we shall also explore advanced topics in object registration and tracking such as non-rigid object alignment/ tracking and non-rigid structure from motion and how the application of machine learning is continuing to improve these technologies.

Categories

Top: Computer Science: Computer Vision

You might be experiencing some problems with Your Video player.

*Slides*
0:00	Object Registration and Tracking from a Learning Perspective (Part I)
0:01	Some Motivation for Course
4:28	Vision and Learning
6:18	Vision and Learning
6:43	Vision and Learning
7:56	Vision and Learning
8:08	Overall Course Outline
12:29	Overall Course Outline
14:30	Task of Alignment/Registration
16:09	Why is it hard?
17:18	Why is it hard?
21:09	Why is it hard?
22:18	Two Problems in Registration
23:54	Challenge #1: Learning
25:33	Challenge #2: Fitting
26:35	Important Message
27:02	Warp Functions
40:55	Different Warp Functions
42:08	Learnt Warps
44:43	Aliasing
46:12	Aliasing
46:39	Image Interpolation
47:52	Image Interpolation
48:15	Image Interpolation
49:05	Naive Approach to Registration
50:09	Naive Approach to Registration
53:12	Naive Approach to Registration
54:37	Measures of Image Similarity
56:56	Measures of Image Similarity
57:58	Measures of Image Similarity

Lecture rating

People found this lecture:
Worth seeing
because it is:
Valuable and informative
Well presented
Easily understandable
Acceptably recorded
You need to login to cast your vote.

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.