neuro it roadmap successful in the physical world
Download
Skip this Video
Download Presentation
Neuro-IT Roadmap: Successful in the Physical World

Loading in 2 Seconds...

play fullscreen
1 / 27

Neuro-IT Roadmap: Successful in the Physical World - PowerPoint PPT Presentation


  • 75 Views
  • Uploaded on

Neuro-IT Roadmap: Successful in the Physical World. Robust perception Image processing Speech recognition Multimodal human machine interaction System integration Scene analysis and representation. Automotive: Overtake-Checker and Door-Opener Assistant. Dr. Axel Techmer

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about ' Neuro-IT Roadmap: Successful in the Physical World' - lana-kane


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
neuro it roadmap successful in the physical world
Neuro-IT Roadmap: Successful in the Physical World
  • Robust perception
    • Image processing
    • Speech recognition
    • Multimodal human machine interaction
  • System integration
  • Scene analysis and representation
automotive overtake checker and door opener assistant
Automotive: Overtake-Checker and Door-Opener Assistant

Dr. Axel Techmer

Infineon Technologies

security face detection recognition
Security: Face Detection & Recognition
  • Leading edge approach of face detection (University of Bochum)
  • Detection of face regions (a)
  • Pre-selecting of frontal faces (b)
  • Face recognition (c,d)
    • Elastic graph matching
    • Gabor Wavelet Transform

Ruhr University Bochum

vision instruction processor vip
Vision Instruction Processor (VIP)

Infineon Technologies, Corporate Research, Systems Technology

vision instruction processor vip1

16 parallel

Processing

Elements

Vision Instruction Processor (VIP)

Prototype available since May 2001:

  • SIMD - Architecture
  • 204 instructions
  • 10 Million logic transistors
  • On-chip memory: 37KB
  • Technology: 0.35µm
  • Clock: 100 MHz
  • Power consumption: 100µW/MOPS
  • Die size: 22mm x 23mm
  • Peak Performance: 53 GOPS
  • PCI-Board with VIP and camera submodules
  • Software Tools for VIP:
    • Compiler, Debugger, Profiler
  • Software Tools on Host:
    • MS Visual C++ with VPL++-Library
  • Application demonstrators
    • Car Vision, Face recognition, MPEG2, Graphic

in 0.13µm CMOS Technology:

  • Clock: 200 MHz
  • Peak Perf.: 106 GOPS
  • Die Size: 70 mm²
  • Power Consump.: 700 mW

Infineon Technologies, Corporate Research, Systems Technology

car vision components hardware

othersensors

Vehiclecontrol

CPU

othersensors

Car Vision Components - Hardware

Dr. Axel Techmer

Infineon Technologies

neuro it roadmap successful in the physical world1
Neuro-IT Roadmap: Successful in the Physical World
  • Robust perception
    • Image processing
    • Speech recognition
    • Multimodal human machine interaction
  • System integration
  • Scene analysis and representation
fft resolves neither frequency nor temporal structure

20 ms window

|FFT| resolves neither frequency nor temporal structure
  • |FFT|
  • frequency resolution: 50 Hz
  • temporal resolution: 20 ms
classical sound processing for speech recognition1
Classical Sound Processing for Speech Recognition

time structure of speech signal (<20 ms)

is lost in the magnitude spectrum (|FFT|)

Humans extract both temporal- and spectral

information for robust speech recognition

auditory sound processing
Auditory Sound Processing

sound

signal

ear

canal

middle

ear

auditory sound processing1
Auditory Sound Processing

100µm

sound

signal

ear

canal

middle

ear

inner ear

hydrodynamics

dynamic compression in the inner ear

BW

speech range

speech range

rate threshold

Dynamic Compression in the Inner Ear

Inner ear model responses to 1 kHz tones

apical

basal

auditory sound processing2
Auditory Sound Processing

sound

signal

ear

canal

middle

ear

inner ear

hydrodynamics

sensory

cell

synaptic

mechanisms

coding of sound into action potentials
Coding of Sound into Action Potentials

regular firing pattern (Dt=10 ms  f0=100 Hz)

high

frequency

F0

low

neuro it roadmap successful in the physical world2
Neuro-IT Roadmap: Successful in the Physical World
  • Robust perception
    • Image processing
    • Speech recognition
    • Multimodal human machine interaction
  • System integration
  • Scene analysis and representation
audio visual speech recognition1
Audio-Visual Speech Recognition

Tracking of lip motion with sub-pixel precision

audio visual speech recognition2
Audio-Visual Speech Recognition

Tracking of lip motion with sub-pixel precision

“two - one - seven - three - five - nine - eight - zero - four - six”

Hidden-

Markov

Speech

Recognizer

multi modal pointing gaze gestures mimics
Multi-modal: Pointing, gaze, gestures, mimics,…

Dr. Axel Steinhage, Infineon Technologies AG

neuro it roadmap successful in the physical world3
Neuro-IT Roadmap: Successful in the Physical World
  • Robust perception
    • Image processing
    • Speech recognition
    • Audio-visual speech recognition
    • Multimodal human machine interaction
  • System integration
  • Scene analysis and representation
slide24

Man-Machine-Interaction based on natural communication channels

Dr. Axel Steinhage, Infineon Technologies

Items presented by VPA

Virtual Personal Assistant (VPA)

Cheap sensors

(Webcam,

Microphone)

Interactive comunication between user and VPA

Natural channels speech, lip-motion, gestures ...

slide25

Man-Machine-Interaction based on natural communication channels

Dr. Axel Steinhage, Infineon Technologies

Human expert via Advanced Videophone (HHI)

Items presented by VPA

Advanced Videophone

Virtual Personal Assistant (VPA)

Cheap sensors

(Webcam,

Microphone)

Interactive comunication between user and VPA

Natural channels speech, lip-motion, gestures ...

what do we earn from neuro it
What do we earn from Neuro-IT ?
  • Sensitive Sensors
  • Robust perception
    • Image processing
    • Speech recognition

Robust processing

  • “Tools for Neuroscience”

“Successful in the Physical World”

World knowledge

“Constructed brain”

  • Scene analysis and representation
  • Intelligent human-machine interaction
    • Natural feedback
    • Intelligent virtual person

 “Conscious Machines”

  • Self learning Software

 “Factor 10”

Digital and/or analog

neuronal networks

  • Massively parallel processing hardware
neuro it roadmap successful in the physical world4
Neuro-IT Roadmap: Successful in the Physical World

Werner HemmertInfineontechnologies AGCPR-ST

Prof. Dr. Dr. h.c. H.-P. Zenner

Prof. Dr. A.W. Gummer

Prof. Dr. D.M. Freeman

Dr. M. Mermelstein, B. Tsai

U. Dürig, M. Despont, G. Genolet,

U. Drechsler, P. Vettiger, G. Binning

Prof. Dr. U. Ramacher

J.-P. de la Cruz-Guiterrez, M. Holmberg

Dr. A. Steinhage, Dr. A. Techmer

ad