EyesWeb XMI Multimodal data recording, playing and analysis M. Mancini, Università di Genova (Italy)

Slides:



Advertisements
Similar presentations
Perceiving Animacy and Arousal in Transformed Displays of Human Interaction 1 Phil McAleer, 2 Barbara Mazzarino, 2 Gualtiero Volpe, 2 Antonio Camurri,
Advertisements

Methods 9 scenarios were used in total: 5 scenarios invovled interactions between 2 people, such as dancing, chasing, following and circling. 3 scenarios.
Descriptive schemes for facial expression introduction.
Expressive Tangible Acoustic Interfaces Antonio Camurri, Corrado Canepa, and Gualtiero Volpe InfoMus Lab, DIST-University of Genova, Viale Causa 13, Genova,
Linear Kinematics Chapter 3. Definition of Kinematics Kinematics is the description of motion. Motion is described using position, velocity and acceleration.
Image Processing Lecture 4
Classical Doppler Shift Anyone who has watched auto racing on TV is aware of the Doppler shift. As a race car approaches the camera, the sound of its engine.
Digital Image Processing In The Name Of God Digital Image Processing Lecture3: Image enhancement M. Ghelich Oghli By: M. Ghelich Oghli
Automatic Tracing of Vocal Fold Motion in High Speed Laryngeal Video Erik Bieging.
Instructor: Mircea Nicolescu Lecture 13 CS 485 / 685 Computer Vision.
Handwriting: Registration and Differential Equations.
Nicholas Lawrance | ICRA Minimum Snap Trajectory Generation for Control of Quadrotors (Best Paper ICRA 2011) Daniel Mellinger and Vijay Kumar GRASP.
Broadcast Court-Net Sports Video Analysis Using Fast 3-D Camera Modeling Jungong Han Dirk Farin Peter H. N. IEEE CSVT 2008.
6/9/2015Digital Image Processing1. 2 Example Histogram.
Video Object Tracking and Replacement for Post TV Production LYU0303 Final Year Project Spring 2004.
LYU0603 A Generic Real-Time Facial Expression Modelling System Supervisor: Prof. Michael R. Lyu Group Member: Cheung Ka Shun ( ) Wong Chi Kin ( )
CS292 Computational Vision and Language Visual Features - Colour and Texture.
Chapter 37 Special Relativity. 37.2: The postulates: The Michelson-Morley experiment Validity of Maxwell’s equations.
Physics 2011 Chapter 2: Straight Line Motion. Motion: Displacement along a coordinate axis (movement from point A to B) Displacement occurs during some.
A Gentle Introduction to Bilateral Filtering and its Applications Limitation? Pierre Kornprobst (INRIA) 0:20.
Spectral contrast enhancement
What’s Making That Sound ?
Enabling enactive interaction in virtualized experiences Stefano Tubaro and Augusto Sarti DEI – Politecnico di Milano, Italy.
Explaining Motion P4. Speed In real life, it’s pretty rare for an object to go at exactly the same speed for a long period of time Objects usually start.
Safety is a way of life Safety Features that should be present in every car.
Expressive Emotional ECA ✔ Catherine Pelachaud ✔ Christopher Peters ✔ Maurizio Mancini.
 Refers to sampling the gray/color level in the picture at MXN (M number of rows and N number of columns )array of points.  Once points are sampled,
Perception Introduction Pattern Recognition Image Formation
Full-body motion analysis for animating expressive, socially-attuned agents Elisabetta Bevacqua Paris8 Ginevra Castellano DIST Maurizio Mancini Paris8.
L.I. Petrova “Specific features of differential equations of mathematical physics.” Investigation of the equations of mathematical physics with the help.
Recognition, Analysis and Synthesis of Gesture Expressivity George Caridakis IVML-ICCS.
DESCRIBING MOTION: Kinematics in One Dimension CHAPTER 2.
Stylization and Abstraction of Photographs Doug Decarlo and Anthony Santella.
motiontranslationaverage speed Rotation kinematics center of mass Center of gravity gravitational force Gravity displacement direction Vector quantity.
Reynolds Transport Theorem We need to relate time derivative of a property of a system to rate of change of that property within a certain region (C.V.)
December 9, 2014Computer Vision Lecture 23: Motion Analysis 1 Now we will talk about… Motion Analysis.
Robotics. What is a robot? Have you seen a robot? Where? – In a photo? – Video? – In real life?
ME451 Kinematics and Dynamics of Machine Systems Review of Differential Calculus 2.5, 2.6 September 11, 2013 Radu Serban University of Wisconsin-Madison.
Extracting features from spatio-temporal volumes (STVs) for activity recognition Dheeraj Singaraju Reading group: 06/29/06.
Autonomous Robots Vision © Manfred Huber 2014.
Integration for physically based animation CSE 3541 Matt Boggus.
EE3010_Lecture3 Al-Dhaifallah_Term Introduction to Signal and Systems Dr. Mujahed Al-Dhaifallah EE3010: Signals and Systems Analysis Term 332.
POSITION AND COORDINATES l to specify a position, need: reference point (“origin”) O, distance from origin direction from origin (to define direction,
INTRODUCTION TO BIOMECHANICS. What is Biomechanics? The study of how the physical laws of mechanics and physics apply to the “Human Body” Why? Improve.
Product: Microsoft Kinect Team I Alex Styborski Brandon Sayre Brandon Rouhier Section 2B.
CS Spring 2010 CS 414 – Multimedia Systems Design Lecture 4 – Audio and Digital Image Representation Klara Nahrstedt Spring 2010.
Image features and properties. Image content representation The simplest representation of an image pattern is to list image pixels, one after the other.
THE EYESWEB PLATFORM - OVERVIEWTHE EYESWEB PLATFORM - OVERVIEW The EyesWeb XMI multimodal platform Overview 5 March 2015.
California State University, LA Presented by Amanda Steven StevenAamirObaid.
Differential Equations MTH 242 Lecture # 16 Dr. Manshoor Ahmed.
Occlusion Tracking Using Logical Models Summary. A Variational Partial Differential Equations based model is used for tracking objects under occlusions.
Derivative Examples 2 Example 3
Control engineering ( ) Time response of first order system PREPARED BY: Patel Ravindra.
Presented by Huanhuan Chen University of Science and Technology of China 信号与信息处理 Signal and Information Processing.
MTH1170 Higher Order Derivatives
Signals and systems By Dr. Amin Danial Asham.
Gender Classification Using Scaled Conjugate Gradient Back Propagation
Special Theory of Relativity
Devil physics The baddest class on campus Pre-DP Physics
Multimedia Information Retrieval
Range Imaging Through Triangulation
Motion.
4.1 Describing Motion Our goals for learning:
PRINCIPLE OF LINEAR IMPULSE AND MOMENTUM
Multimedia Information Retrieval
Outline: 5.1 INTRODUCTION
Interactive media.
Kinematics in one-Dimension
Lecture 2: Signals Concepts & Properties
Lark Kwon Choi, Alan Conrad Bovik
Presentation transcript:

EyesWeb XMI Multimodal data recording, playing and analysis M. Mancini, Università di Genova (Italy)

Goal 1.record multimodal data: video (rgb or silhouette) audio sensor 2.play multimodal data 3.analyze multimodal data in real-time silhouette (if available) Contraction Index Quantity of Motion sensor energy smoothness

1.Recording media file writer N-th video frame clock csv file writer tsv file writer N M-th sensor frame K-th audio buffer current time

2.Player media file reader N-th video frame csv file reader tsv file reader N current time M-th sensor frame

Global measures depending on full body movement (e.g., body orientation, overall motion direction). Measures from psychological research, e.g., Boone & Cunningham’s amount of upward movement. Cues from Rudolf Laban’s Theory of Effort, e.g., directness, impulsiveness. Cues derived from analogies with audio analysis, e.g., Inter Onset Intervals, frequency analysis. Kinematic measures such as velocity, acceleration, average and peak velocity and acceleration. 3.Analysis: Expressive Features

SMIs (Silhouette Motion Images) carry information on variations of a blob (usually the silhouette of a user) in the last few frames. Silhouette Motion Images

SMIs are different with respect to MHIs, since they do not include the last silhouette, i.e., the current posture. Thus, SMIs carry information about the movement detected by the video-camera in the last n frames. The SMI area can be therefore considered as a measure of the detected amount of motion. The SMI area, normalized by the silhouette area, is called Motion Index (or Quantity of Motion). Motion_Index[t] = Area(SMI[t, n]) / Area(Silhouette[t]) Note that this is an approximated measure: e.g., movement against the video-camera is not detected. SMIs and Motion Index

Motion Index can also be computed by differently weighting pixels in the input blob. So, it is possible to compute a Motion Index where pixels near to the centre of the blob weight more than pixels near to the contour (i.e., something more similar to the physical concept of momentum). Or it is possible to compute a Motion Index where pixels near to the contour weight more than pixels near to the centre of the blob (i.e., a more perceptual measure where limbs have a stronger impact on perception of movement). Weighted Motion Index

Contraction Index is a measure of how the user’s body uses the space surrounding it. The simplest way to compute it is the ratio between the area of the blob and the area of the bounding rectangle. CI = Area(Blob) / Area(Bounding rectangle) Contraction Index

Silhouette Features Extraction media file reader N-th silhouette frame blob extractor QoM extractor CI extractor csv file writer current time

Sensor Features Extraction tsv file reader acceleration differentiate jerk (1/fluidity) integrate energy csv file writer current time