Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

University of Central Florida

Scale-invariant Feature Transform (SIFT) - Lecture 5

University of Central Florida via YouTube

Overview

Explore the Scale-invariant Feature Transform (SIFT) in this comprehensive lecture from the UCF Computer Vision Video Lectures 2012 series. Delve into the intricacies of SIFT, developed by David Lowe at UBC, as Dr. Mubarak Shah guides you through key point extraction, advantages, and invariant local features. Learn the steps for extracting key points, including scale space concepts, approximation of LOG by Difference of Gaussians, and building a scale space. Discover techniques for scale space peak detection, key point localization, and outlier rejection. Examine orientation assignment and its similarity to the IT cortex. Master the extraction of local image descriptors at key points, understanding descriptor regions and key point matching. Gain valuable insights into this powerful computer vision technique through detailed explanations and visual aids.

Syllabus

SIFT: David Lowe, UBC
SIFT - Key Point Extraction
Advantages
Invariant Local Features
Steps for Extracting Key Points
Scale Space (Witkin, IJCAI 1983) • Apply whole spectrum of scales
Approximation of LOG by Difference of Gaussians
Building a Scale Space
How many scales per octave?
Initial value of sigma
Scale Space Peak Detection
Key Point Localization
Initial Outlier Rejection
Further Outlier Rejection
Orientation Assignment
Similarity to IT cortex
Extraction of Local Image Descriptors at Key Points
Descriptor Regions (n by n)
Key point matching

Taught by

UCF CRCV

Reviews

Start your review of Scale-invariant Feature Transform (SIFT) - Lecture 5

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.