Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

Chathika Gunaratne Defense

No description
by

Chathika Gunaratne

on 4 August 2013

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Chathika Gunaratne Defense

Age For Variety!
More than just wrinkles and grey hair!
Simulating biomechanical effects of aging
Automation is very rare
Crowd Simulation Diversity
Simulating biomechanical aging for crowd diversity
Simulating Gait and Postural Effects of Aging
for Improved Diversity in Virtual Crowds

Chathika Gunaratne, Prasad Wimalaratne
University Of Colombo School Of Computing,
Sri Lanka

More diverse the crowd greater the realism (McDonnel et al. 2008)
1987
Present...
Greater
continuity
in diversity
Genetic representation of characteristics
Gamete production and reproduction of generations of characters
+
More natural variety
Effects of Aging
Physical
Hyperkyphosis
Facial deformations
Vertebral deformations
Locomotion
Gait speed
Start-up time
Acceleration
Cognitive/Psychological
Dementia
Parkinson's disease
Alzheimer's disease
Having characters at different ages within a crowd
Having characters at a variety of states in regard to physical/locomotion/psychological capability
Diversity!
Boulic et al used a parametric character model to inject calculated motion attributes into the character
Stereotypic old characters within GTA San Andreas
SVRs
Age
Fitness Index
Gait Parameter Values
&
Vertebral angles
Age-able Character
BML Character
Behavior Parameter Predictor
BML Realizer
Skeletal Definition
LIBSVM -- A Library for Support Vector Machines
by: Chih-Chung Chang and Chih-Jen Lin
Local Similarity Minimization
used for spatial diversity
Experiment 1:
Realism of Postural changes
Experiment 2:
Realism of Gait Changes
Experiment 3:
Improvement in Crowd Diversity
Posture
Walking
Pattern
Conclusions
Support Vector Regression can be successfully used to predict age-related character behavior at real-time
Simulating the biomechanical changes in humans due to aging
does
improve crowd diversity
Postural deterioration is more prominent than gait deterioration between young and old characters
Step frequency is as important in simulation of aged gait as is step size
Local Similarity Minimization can effectively distribute similar character further apart, avoiding clustering
(Aligns with McDonnell et al conclusion)
Only used gait deterioration
Used predictive equations
Our objectives:
Study the impact of using both gait & postural deterioration
Using machine learning techniques instead of predictive equations
Predicts it's posture and gait capabilities according to its age and fitness index
nearest neighbors given repulsion score by similarity of age and fitness index
aggregate repulsion of k nearest neighbors determines the direction of adjustment
Can simulating the biomechanical effects of aging significantly improve the diversity of a crowd?
33%
60%
Had 8 older agents
Motivation
Concept
Objective
Appearance
Diversity
Motion Diversity
Diverse Crowd
Gu and Deng 2011
Vieira et al
Assassin's Creed
GTA San Andreas
Reynolds
Star Wars
V = 1.669 - 0.0119 * age
Full transcript