The Shape of Animations Jason Harrison (Fiddling with the algorithms of Jeffery Boyd and Jim Little, and the animations of Jessica Hodgins, James O’Brien.

Slides:



Advertisements
Similar presentations
Gestures Recognition. Image acquisition Image acquisition at BBC R&D studios in London using eight different viewpoints. Sequence frame-by-frame segmentation.
Advertisements

The Extended Cohn-Kanade Dataset(CK+):A complete dataset for action unit and emotion-specified expression Author:Patrick Lucey, Jeffrey F. Cohn, Takeo.
Real-Time Dynamic Wrinkles Caroline Larboulette Marie-Paule Cani GRAVIR Lab, Grenoble, France.
Fundamental Concepts of Motor Development Developmental Systems Theories.
Sensor network Routing protocol A study on LEACH protocol and how to improve it.
CS-378: Game Technology Lecture #9: More Mapping Prof. Okan Arikan University of Texas, Austin Thanks to James O’Brien, Steve Chenney, Zoran Popovic, Jessica.
Computer Graphics Computer Animation& lighting Faculty of Physical and Basic Education Computer Science Dep Lecturer: 16 Azhee W. MD.
Computer Animation Rick Parent Computer Animation Algorithms and Techniques Figure Animation.
Scalability with many lights II (row-column sampling, visibity clustering) Miloš Hašan.
Cognitive Issues in Virtual Reality Wickens, C.D., and Baker, P., Cognitive issues in virtual environments, in Virtual Environments and Advanced Interface.
Local Descriptors for Spatio-Temporal Recognition
Shape and Dynamics in Human Movement Analysis Ashok Veeraraghavan.
Advanced Computer Graphics (Fall 2010) CS 283, Lecture 24: Motion Capture Ravi Ramamoorthi Most slides courtesy.
Detecting and Tracking Moving Objects for Video Surveillance Isaac Cohen and Gerard Medioni University of Southern California.
Vision Computing An Introduction. Visual Perception Sight is our most impressive sense. It gives us, without conscious effort, detailed information about.
Human Action Recognition
Image-Based Rendering using Hardware Accelerated Dynamic Textures Keith Yerex Dana Cobzas Martin Jagersand.
Vision-based Control of 3D Facial Animation Jin-xiang Chai Jing Xiao Jessica Hodgins Carnegie Mellon University.
Video Based Gait Analysis in Biometric person authentication Jani Rönkkönen.
Video Surveillance is Useless Peter Kovesi School of Computer Science & Software Engineering The University of Western Australia.
Jan SedmidubskySeptember 23, 2014Motion Retrieval for Security Applications Jan Sedmidubsky Jakub Valcik Pavel Zezula Motion Retrieval for Security Applications.
MULTIMEDIA TECHNOLOGY SMM 3001 MEDIA - GRAPHICS. In this chapter how the computer creates, stores, and displays graphic images how the computer creates,
Chapter 10: Computer Graphics
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley Chapter 10: Computer Graphics Computer Science: An Overview Tenth Edition.
Motion Object Segmentation, Recognition and Tracking Huiqiong Chen; Yun Zhang; Derek Rivait Faculty of Computer Science Dalhousie University.
DIGITAL SIGNAL PROCESSING (DSP) VT (D3) VT (D4) VTxxxxxx (D4 LJ-PJJ) HOME Base Gedung.
FiiNaL ExAm by: cHUcKiiE. What is Computer Graphics? Computer graphics is a sub-field of computer science and is concerned with digitally synthesizing.
Computer Graphics An Introduction. What’s this course all about? 06/10/2015 Lecture 1 2 We will cover… Graphics programming and algorithms Graphics data.
Gait Recognition Guy Bar-hen Tal Reis. Introduction Gait – is defined as a “manner of walking”. Gait recognition – –is the term typically used to refer.
Computer Vision, Robert Pless Lecture 11 our goal is to understand the process of multi-camera vision. Last time, we studies the “Essential” and “Fundamental”
A Camera-Projector System for Real-Time 3D Video Marcelo Bernardes, Luiz Velho, Asla Sá, Paulo Carvalho IMPA - VISGRAF Laboratory Procams 2005.
Digital Media Lecture 8: Vector Graphics 3D Georgia Gwinnett College School of Science and Technology Dr. Jim Rowan.
Automatic Joint Parameter Estimation from Magnetic Motion CaptureData James F.O”Brien Robert E. Bodenheimer Gabriel J Brostow Jessica K. Hodgins Presented.
Action as Space-Time Shapes
12/7/10 Looking Back, Moving Forward Computational Photography Derek Hoiem, University of Illinois Photo Credit Lee Cullivan.
Segmentation of Vehicles in Traffic Video Tun-Yu Chiang Wilson Lau.
FREE-VIEW WATERMARKING FOR FREE VIEW TELEVISION Alper Koz, Cevahir Çığla and A.Aydın Alatan.
CS 527 – Computer AnimationOctober 17, 2006 Estimating Cloth Simulation Parameters from Video Kiran S. Bhat, Christopher D. Twigg, Jessica K. Hodgins,
Representation and modelling 3 – landscape specialisations 4.1 Introduction 4.2 Simple height field landscapes 4.3 Procedural modeling of landscapes- fractals.
Animation CS 551 / 651 Perception of Physically Simulated Humans Hodgins et al., 1998.
CS-378: Game Technology Lecture #15.5: Physically Based Simulation Prof. Okan Arikan University of Texas, Austin Thanks to James O’Brien, Steve Chenney,
Zhang & Liang, Computer Graphics Using Java 2D and 3D (c) 2007 Pearson Education, Inc. All rights reserved. 1 Chapter 11 Animation.
1 Perception and VR MONT 104S, Fall 2008 Lecture 20 Computer Graphics and VR.
Structure from Motion Paul Heckbert, Nov , Image-Based Modeling and Rendering.
Image features and properties. Image content representation The simplest representation of an image pattern is to list image pixels, one after the other.
“Articulatory Talking Head” Showcase Project, INRIA, KTH. Articulatory Talking Head driven by Automatic Speech Recognition INRIA, Parole Team KTH, Centre.
MOTION Motion: Change in position over time and is described by speed, velocity and acceleration.
Procedural Animation and Physics Engine Yingcai Xiao.
Date of download: 7/9/2016 Copyright © 2016 SPIE. All rights reserved. Photo of measurement boat and unit. Figure Legend: From: Development of shape measurement.
Applications and Rendering pipeline
Computer Animation Algorithms and Techniques
Three-Dimensional Computer Animation
Computer Graphics.
Gait Recognition Gökhan ŞENGÜL.
A Forest of Sensors: Using adaptive tracking to classify and monitor activities in a site Eric Grimson AI Lab, Massachusetts Institute of Technology
Gender Classification Using Scaled Conjugate Gradient Back Propagation
Game Development Unity3D.
Chapter 10: Computer Graphics
Interactive Computer Graphics
© University of Wisconsin, CS559 Fall 2004
Video-based human motion recognition using 3D mocap data
The Functional Space of an Activity Ashok Veeraraghavan , Rama Chellappa, Amit Roy-Chowdhury Avinash Ravichandran.
Eric Grimson, Chris Stauffer,
Visual Tracking of Cell Boundaries and Geometries
Applications of Cellular Neural Networks to Image Understanding
Naoki Watanabe et al. BTS 2017;2:
Filtering Things to take away from this lecture An image as a function
Computer Graphics Lecture 15.
Measuring the Similarity of Rhythmic Patterns
Presentation transcript:

The Shape of Animations Jason Harrison (Fiddling with the algorithms of Jeffery Boyd and Jim Little, and the animations of Jessica Hodgins, James O’Brien and Jack Tumblin)

Animation Metrics l “rate” animations by using metrics l use comparisons for databases, analysis, description... l aim for metrics based on human perceptual processes l Start with “Shape of Motion”

Shape of Motion l Jeffery Boyd and Jim Little l analysing video without models l optical flow l time varying signals l relative phases of signals l feature vector

N+1 frames... optical flow time-varying scalars scalar sequences phases {s 11, s 12,…, s 1n }{s 12, s 22,…, s 2m }{s n1, s n2,…, s nm } 11 22 mm... (phase reference) (s 1, s 2, …, s m ) feature vector(F 1, F 2, …, F m-1 ) phase features F 1 =  1 -  m F 2 =  2 -  m F m-1 =  m-1 -  m... “Shape of Motion”: Data Flow

Scalars computed l x coordinate of centroid l x coordinate of centroid weighted by |(u,v)| l y coordinate of centroid weighted by |(u,v)| l weighted centroid x - unweighted centroid x l weighted centroid y - unweighted centroid y l aspect ratio l aspect ratio weighted by |(u,v)| l aspect - weighted aspect l x coordinate of centroid weighted by |u| l y coordinate of centroid weighted by |u| l x coordinate of centroid weighted by |v| l y coordinate of centroid weighted by |v|

Boyd and Little’s Experiment l 6 participants l Walk for about 15 minutes l Toss first 2 passes l Analyse 7 passes l Compare between participants (control variable)

Example Gait (total sequence is 76 frames long)

Results aspect ratio x coordinate of centroid

Human Perceptions and Judgements of Motions l Jessica Hodgins, James O'Brien, and Jack Tumblin at Georgia Tech l participant study l dynamics model used to simulate runner l wireframe and polygonal models l camera moves steadily with runner

Animations: l 72 4-second running animations (36 of each model) l shoulder swing l motion computed dynamically l currently lost on /imager/raid

“Shape of Animations”: Data Flow l remove moving floor (chroma key) l crop and scale down by half l convert to grey scale l compute optical flow l compute fundamental frequency l pick good reference signal for phase l compute feature vectors

Fundamental Frequency l Median frequency of sequences for an animation l (min/max/ave/median) Stick figure animation

Any patterns? phase

One pattern x coordinate of centroid aspect ratio

Future Work l order sequences based on features? l clustering, rankings? l automatic analysis? l polygonal versus stick models?

Effect of Rendering Models? l geometry and surface appearances l lighting l camera position, parameters and movement l should resolution and frame rate be an issue?