Lecture-15 - Hand Gesture Recognition, Aerobic exercises,...

Info iconThis preview shows pages 1–18. Sign up to view the full content.

View Full Document Right Arrow Icon
Hand Gesture Recognition, Aerobic exercises, Events Lecture-15 Copyright Mubarak Shah 2003
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Hand Gesture Recognition Copyright Mubarak Shah 2003
Background image of page 2
Seven Gestures Copyright Mubarak Shah 2003
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Gesture Phases • Hand fixed in the start position . • Fingers or hand move smoothly to gesture position . • Hand fixed in gesture position . • Fingers or hand return smoothly to start position. Copyright Mubarak Shah 2003
Background image of page 4
Finite State Machine Copyright Mubarak Shah 2003
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Main Steps • Detect fingertips. • Create fingertip trajectories using motion correspondence of fingertip points. • Fit vectors and assign motion code to unknown gesture. •M atch Copyright Mubarak Shah 2003
Background image of page 6
Detecting Fingertips Copyright Mubarak Shah 2003
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Vector Extraction Copyright Mubarak Shah 2003
Background image of page 8
Vector Representation of Gestures Copyright Mubarak Shah 2003
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Results Copyright Mubarak Shah 2003
Background image of page 10
Publication http://www.cs.ucf.edu/~vision/papers/shah/94/D AS94.pdf (James Davis and Mubarak Shah. Visual Gesture Recognition , Vision, Image and Signal Processing, Vol 141, No. 2, April 1994.) http://www.cs.ucf.edu/~vision/papers/CS-TR-93- 11.pdf (James Davis and Mubarak Shah. Gesture Recognition , European Conference on Computer Vision,1994.) Copyright Mubarak Shah 2003
Background image of page 11

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Action Recognition Using Temporal Templates Jim Davis and Aaron Bobick Copyright Mubarak Shah 2003
Background image of page 12
Main Points • Compute a sequence of difference pictures from a sequence of images. • Compute Motion Energy Images (MEI) and Motion History Images (MHI) from difference pictures. • Compute Hu moments of MEI and MHI. • Perform recognition using Hu moments. Copyright Mubarak Shah 2003
Background image of page 13

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
MEI and MHI Motion-Energy Images (MEI ) ) , , ( ) , , ( 1 0 i t y x D t y x E i ! " ! " # ! Change Detected Images Motion History Images (MHI) Copyright Mubarak Shah 2003 $ % & ( ) ! ! " " otherwise t y x H t y x D if t y x H ) 1 ) 1 , , ( , 0 max( 1 ) , , ( ) , , (
Background image of page 14
MEIs Copyright Mubarak Shah 2003
Background image of page 15

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Color MHI Demo Copyright Mubarak Shah 2003
Background image of page 16
Summary Use seven Hu moments of MHI and MEI to recognize different exercises. Use seven views (-90 degrees to +90 degrees in increments of 30 degrees). For each exercise several samples are recorded using all seven views, and the mean and covariance matrices for the seven moments are computed as a model. During recognition, for an unknown exercise all seven moments are computed, and compared with all 18 exercises using Mahalanobis distance. The exercise with minimum distance is computed as the match. They present recognition results with one and two view sequences, as compared to seven view sequences used for model generation.
Background image of page 17

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 18
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 10/04/2011 for the course CAP 6411 taught by Professor Shah during the Spring '09 term at University of Central Florida.

Page1 / 76

Lecture-15 - Hand Gesture Recognition, Aerobic exercises,...

This preview shows document pages 1 - 18. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online