Paul D. Varcholik ACTIVE Laboratory Institute for Simulation and Training University of Central Florida James L. Merlo LTC, US Army.

Slides:



Advertisements
Similar presentations
My name is Dustin Boswell and I will be presenting: Ensemble Methods in Machine Learning by Thomas G. Dietterich Oregon State University, Corvallis, Oregon.
Advertisements

ACCELEROMETER-BASED, GRIP-FREE CONTROLLER Tyler (You-Chi) Le ECE4220 Fall 2011 Dr. DeSouza December 5 th, 2011.
IntroductionMethods Participants  7 adults with severe motor impairment.  9 adults with no motor impairment.  Each participant was asked to utilize.
Bryan Donyanavard Nik Sumikawa. Project Description Transfer data between two mobile phones via Bluetooth. A unique cell phone movement will establish.
Happy Home Helper Jeremy Searle Apr 28, 2004 A Learning Home Automation System.
Collaborative Work Systems, Inc CWS Collaborative Work Systems, Inc Geo-Docent: Improving Human, Team, and Organizational Performance with Geographically.
Part of the Joint Project by HKBU, HKIVE and Several Local Mobile Service Providers for Accurate Low-cost Mobile localization Support Vector Regression.
Development of An Affordable Loop Detector Simulator (LOOPSIM) for In- Laboratory Traffic Research and Training Patikhom Cheevarunothai, Dr.Yinhai Wang.
UPM, Faculty of Computer Science & IT, A robust automated attendance system using face recognition techniques PhD proposal; May 2009 Gawed Nagi.
Mark CerritelliMatthew Fister Charles Cole Mine Yalcinalp.
P08006: Physical Therapy Motion Tracking System Sponsor: National Science Foundation Customer: Nazareth Physical Therapy Clinic Josemaria Mora Electrical.
18-549: Midas Project Presentation : Game Glove Project Presentation Project Proposal, Requirements, Competitive Analysis Inbae Lee
Artificial Neural Networks (ANNs)
Learn how to make your drawings come alive…  Lecture 2: SKETCH RECOGNITION Analysis, implementation, and comparison of sketch recognition algorithms,
Hand Movement Recognition By: Tokman Niv Levenbroun Guy Instructor: Todtfeld Ari.
Musical Virtual Reality Applications Michael Kriegel.
Introduce about sensor using in Robot NAO Department: FTI-FHO-FPT Presenter: Vu Hoang Dung.
Knowledge Systems Lab JN 8/24/2015 A Method for Temporal Hand Gesture Recognition Joshua R. New Knowledge Systems Laboratory Jacksonville State University.
Feature Extraction Spring Semester, Accelerometer Based Gestural Control of Browser Applications M. Kauppila et al., In Proc. of Int. Workshop on.
SoundSense: Scalable Sound Sensing for People-Centric Application on Mobile Phones Hon Lu, Wei Pan, Nocholas D. lane, Tanzeem Choudhury and Andrew T. Campbell.
Academic Experience with Wide Area Sensors by Virgilio Centeno Virginia Tech PSC, Distributed Generation, Advanced Metering and Communications March 9,
南台科技大學 資訊工程系 Posture Monitoring System for Context Awareness in Mobile Computing Authors: Jonghun Baek and Byoung-Ju Yun Adviser: Yu-Chiang Li Speaker:
Machine Learning. Learning agent Any other agent.
Ink and Gesture recognition techniques. Definitions Gesture – some type of body movement –a hand movement –Head movement, lips, eyes Depending on the.
1 7-Speech Recognition (Cont’d) HMM Calculating Approaches Neural Components Three Basic HMM Problems Viterbi Algorithm State Duration Modeling Training.
PPT 206 Instrumentation, Measurement and Control SEM 2 (2012/2013) Dr. Hayder Kh. Q. Ali 1.
Hoelzl Gerold. Overview  Motivation  System design  Summary  Future work Hoelzl Gerold.
Presentation on Neural Networks.. Basics Of Neural Networks Neural networks refers to a connectionist model that simulates the biophysical information.
7-Speech Recognition Speech Recognition Concepts
Side Channel Attacks through Acoustic Emanations
Parallel Artificial Neural Networks Ian Wesley-Smith Frameworks Division Center for Computation and Technology Louisiana State University
©G. Millbery 2001Communications and Networked SystemsSlide 1 Purpose of Network Components  Switches A device that controls routing and operation of a.
 The most intelligent device - “Human Brain”.  The machine that revolutionized the whole world – “computer”.  Inefficiencies of the computer has lead.
Slice&Dice: recognizing food preparation activities using embedded accelerometers Cuong Pham & Patrick Olivier Culture Lab School of Computing Science.
Gesture Recognition & Machine Learning for Real-Time Musical Interaction Rebecca Fiebrink Assistant Professor of Computer Science (also Music) Princeton.
Particle Filters.
Lecture 15 – Social ‘Robots’. Lecture outline This week Selecting interfaces for robots. Personal robotics Chatbots AIML.
Net-Centric Software and Systems I/UCRC Copyright © 2011 NSF Net-Centric I/UCRC. All Rights Reserved. Bio-Com Project Project Lead: Krishna Kavi and Robert.
Scaling to several dancers… High Speed Sensor Fusion Vocabulary of features Capacitive proximity to 50 cm 6-axis IMU - 1 Mbps TDMA radio 100 Hz Full State.
School of something FACULTY OF OTHER Facing Complexity Using AAC in Human User Interface Design Lisa-Dionne Morris School of Mechanical Engineering
Analysis of Movement Related EEG Signal by Time Dependent Fractal Dimension and Neural Network for Brain Computer Interface NI NI SOE (D3) Fractal and.
TIU Tracking System Introduction Intel's large and complex validation labs contain many Testing Interface Unit's(TIU) used in validating hardware. A TIU.
Marwan Al-Namari 1 Digital Representations. Bits and Bytes Devices can only be in one of two states 0 or 1, yes or no, on or off, … Bit: a unit of data.
Gyro (yee-roh) Designed by Joshua Lewis. Introduction  Inverted Pendulum  ATMega MicroProcessor  Inertial Measurement Unit  PID Control Algorithm.
Linear Classifiers Rubine & CA-Linear Ruben Balcazar.
Hand Gesture Recognition Using Haar-Like Features and a Stochastic Context-Free Grammar IEEE 高裕凱 陳思安.
Team Members Ming-Chun Chang Lungisa Matshoba Steven Preston Supervisors Dr James Gain Dr Patrick Marais.
Unit 1—Computer Basics Lesson 1 Understanding Computers and Computer Literacy.
COMP135/COMP535 Digital Multimedia, 2nd edition Nigel Chapman & Jenny Chapman Chapter 2 Lecture 2 – Digital Representations.
Saisakul Chernbumroong, Shuang Cang, Anthony Atkins, Hongnian Yu Expert Systems with Applications 40 (2013) 1662–1674 Elderly activities recognition and.
Course Aims This course will help you understand the latest technologies & how they work. You will lean how to develop computer programs to solve problems.
IEEE AI - BASED POWER SYSTEM TRANSIENT SECURITY ASSESSMENT Dr. Hossam Talaat Dept. of Electrical Power & Machines Faculty of Engineering - Ain Shams.
1 7-Speech Recognition Speech Recognition Concepts Speech Recognition Approaches Recognition Theories Bayse Rule Simple Language Model P(A|W) Network Types.
GloveFX Patent Liability Ryan DeFord Fred Grandlienard Kevin Mohr Andrew Gregor.
Development of Indian Sign Language Recognition System BY DEEPANAIR.V.S B.S.ANANTHALEKSHMI GAYATHRIMOHAN Guided By DR.DEVARAJ.
Musical Instrument Virtual
ARTIFICIAL NEURAL NETWORKS
Posture Monitoring System for Context Awareness in Mobile Computing
Walking Speed Detection from 5G Prototype System
Vijay Srinivasan Thomas Phan
Massachusetts Institute of Technology
Kocaeli University Introduction to Engineering Applications
Playback control using mind
network of simple neuron-like computing elements
An Improved Neural Network Algorithm for Classifying the Transmission Line Faults Slavko Vasilic Dr Mladen Kezunovic Texas A&M University.
Creating Data Representations
Department of Electrical Engineering
Visual Recognition of American Sign Language Using Hidden Markov Models 문현구 문현구.
Automatic Handwriting Generation
Machine Learning.
Presentation transcript:

Paul D. Varcholik ACTIVE Laboratory Institute for Simulation and Training University of Central Florida James L. Merlo LTC, US Army US Military Academy West Point

Gestural Communication

Problem Statement  Reliable communications between military personnel is critical  Hand gestures are used when vocal means are inadequate  Line of sight issues may cause visual signals to be unreliable

Our Research  Purpose To determine the usefulness of a computer mediated gesturing recognition system for non- visual communication  Scope Provide a proof of concept which would lay the groundwork for future research  Research Questions Have we developed a recognition system capable of accurately converting and transmitting a visual communication mode into a non-visual form? Do computer-mediated gestures provide a viable form of non-visual communication?

Input Device Nintendo Wiimote  Nintendo Wiimote 3-axis accelerometer Wireless (Bluetooth) Inexpensive COTS 100Hz Sampling Rate

Output Devices Tactile Belt  Auditory (headphones)  Tactile Display Wireless (Bluetooth) 1.2 lbs (w/o battery) Elastic belt 8 tactors at 45-degree increments

Tactile Patterns Emulating Standard Army Hand Signals (FM 21-60)

Gesture Recognition  Machine Learning Algorithms (3 implemented for evaluation) Linear Classifier AdaBoost Artificial Neural Network (evolved w/ NEAT)  29 Features Based on work by Rubine (1991) on 2D symbol recognition Example features: ○ Bounding Volume Length ○ Min, Max, Median, Mean (X, Y, Z) ○ Starting Angle, Total Angle Traversed, Total Gesture Distance

Training & Visualization UI  Arbitrary gesture set  Left-hand, right-hand, both-hands  3D animated soldier  Text label display  Sound display  Tactile display  Wiimote visualization  Data serialization  UI Independent of recognition API

Experiments & Results  Several experiments run to date Different algorithms and gesture sets Accuracy > 94% Classification time < 10ms / gesture Linear classifier best performer (for training time and classification considered together) AdaBoost (highest accuracy, but slower training time than linear classifier) ANN w/ NEAT (worst performer – requires more training data)

Discussion  Proved Concept System capable of accurately converting and transmitting a visual communication mode into a non-visual form.  Wiimote is a convenient and inexpensive device for experimentation. Technology transfers to more robust hardware (e.g. instrumented glove).  Wiimote produces some ambiguous data (e.g. static poses). Additional attachment (e.g. gyroscopes) required for more accuracy.  Experiments indicate promising form of communication – more experiments are needed.

Future Work  Determine the maximum number of gestures that can be accurately recognized  Gesture rejection  Dynamic mapping between gesture, sound, and tactile sequence  Scenario development for realistic experimentation (establishing context)  Transmitting signal data via RF (currently sent to local device or via UDP/IP)

USMA Collaboration  CDT Robert Darket, CDT Zachary Schaeffer (Principal Investigators)  Application: Training Collect exemplar gestures from SMEs Validate less-experienced soldier’s gestures against exemplars

Video Demonstration

Paul D. Varcholik ACTIVE Laboratory Institute for Simulation and Training University of Central Florida James L. Merlo LTC, US Army US Military Academy West Point