MobileASL Making Cell Phones Accessible to the Deaf Community

Send This

Download

Comment

Favourite

more

Rating :

Rate It:

Embed :

Post a comment

Post Comment on Twitter Post Comment on SlideWorld

Comments:

Subscribe to follow-up comments

Notes

Hide Notes

Slide 1 :

MobileASL: Making Cell Phones Accessible to the Deaf Community Richard Ladner University of Washington

Slide 2 :

2 Two Themes MobileASL Cyber-Community for Advancing Deaf and Hard of Hearing in STEM (Science Technology Engineering and Math)

Slide 3 :

3 Current Technology(text) TTY PDAs (text, pictures, non-real-time video) Benefits: Low bandwidth Mobile (PDAs) Problems: English, not ASL

Slide 4 :

4 Current Technology(video) Set-top boxes Web cams Benefits: ASL, not English Problems: Requires high bandwidth Not mobile

Slide 5 :

5 Challenges: Limited network bandwidth Limited processing power on cell phones Our goal: ASL communication using video cell phones over current U.S. cell phone network

Slide 6 :

6 Cell Phone Network Constraints MobileASL is about fair access to the current network As soon as possible, no special accommodations Not geographically limited Lower bitrate = more accessible 3G = 3rd Generation Special service Not yet widespread Will still have congestion Low bit rate goal GPRS (General Packet Radio Service) Ranges from 30kbps to 80kbps (download) Perhaps half that for upload

Slide 7 :

7 Architecture Camera Encoder Transmitter Sender Player Decoder Receiver Receiver Cell Phone Network Cell phone Encoder

Slide 8 :

8 Codec Used: x264 Open source implementation of H.264 standard Doubles compression ratio over MPEG2 x264 offers faster encoding Off-the-shelf H.264 decoder can be used

Slide 9 :

9 Outline Motivation Introduction MobileASL Focus Group Eyetracking Motivation Video Phone Study Compression Challenges Current Work Conclusions

Slide 10 :

10 MobileASL Focus Group 4 Deaf people, mid-20s to mid-40s, Open ended questions: Physical Setup Camera, distance, … Features Compatibility, text, … Privacy Concerns ASL is a visual language Scenarios Lighting, driving, relay services, …

Slide 11 :

11 Implications of Focus Group “I don’t foresee any limitations. I would use the phone anywhere: the grocery store, the bus, the car, a restaurant, … anywhere!” There is a need within the Deaf Community for mobile ASL conversations Existing video phone technology (with minor modifications) would be usable

Slide 12 :

12 Outline Motivation Introduction MobileASL Focus Group Eyetracking Motivation Video Phone Study Compression Challenges Current Work Conclusions

Slide 13 :

13 Eyetracking Studies Participants watched ASL videos while eye movements were tracked Important regions of the video could be encoded differently * Muir et al. (2005) and Agrafiotis et al. (2003)

Slide 14 :

14 Eyetracking Results 95% of eye movements within 2 degrees visual angle of the signer’s face (demo) Implications: Face region of video is most visually important Detailed grammar in face requires foveal vision Hands and arms can be viewed in peripheral vision * Muir et al. (2005) and Agrafiotis et al. (2003)

Slide 15 :

15 Outline Motivation Introduction MobileASL Focus Group Eyetracking Motivation Video Phone Study Compression Challenges Current Work Conclusions

Slide 16 :

16 Mobile Video Phone Study 3 Region-of-Interest (ROI) values 2 Frame rates, frames per second (FPS) 3 different Bit rates 15 kbps, 20 kbps, 25 kbps 18 participants (7 women) 10 Deaf, 5 hearing, 3 CODA* All fluent in ASL * CODA = (Hearing) Child of a Deaf Adult

Slide 17 :

17 Example of ROI Varied quality in fixed-sized region around the face (demo) 2x quality in face 4x quality in face

Slide 18 :

18 Examples of FPS Varied frame rate: 10 fps and 15 fps For a given bit rate: Fewer frames = more bits per frame (demo)

Slide 19 :

19 Questionnaire

Slide 20 :

20 User Preferences Results Bit Rate Frame Rate Region of Interest

Slide 21 :

21 Implications of results A mid-range ROI was preferred Optimal tradeoff between clarity in face and distortion in rest of “sign-box” Lower frame rate preferred Optimal tradeoff between clarity of frames and number of frames per second Results independent of bit rate

Slide 22 :

22 Outline Motivation Introduction MobileASL Focus Group Eyetracking Motivation Video Phone Study Compression Challenges Current Work Conclusions

Slide 23 :

23 Rate, distortion and complexity optimization H.264 encoder Inputparameters Raw video Compressed video H.264 standard provides 50% bit savings over MPEG 2, but with higher complexity. Objective: Achieve best possible quality for least encoding time at a given bitrate

Slide 24 :

24 Time – Complexity Tradeoff Encoding Time MSE

Slide 25 :

25 Encoding/Decoding on the Cell Phone Implemented a command-line version of x264 on a cell phone using Windows Mobile Edition 5.0.

Slide 26 :

Slide 27 :

27 Outline Motivation Introduction MobileASL Focus Group Eyetracking Motivation Video Phone Study Compression Challenges Current Work Conclusions

Slide 28 :

28 Current Work Dynamic Region-of-Interest Skin detection algorithms Activity Recognition Fingerspelling, signing, “listening” User Interface Small screen issues Building the System Transmission, Receiving, Playing Packet loss on GPRS

Slide 29 :

29 Thanks Co-PIs Eve Riskin and Sheila Hemami Graduate Students Anna Cavender, Rahul Vanam, Neva Cherniavsky, Frank Ciaramello, Dane Barney Undergraduate Students Jessica DeWitt, Loren Merritt National Science Foundation

Slide 30 :

Advancing Deaf & Hard of Hearing in Computing Alliance for Access to Computing Careers

Slide 31 :

31 AccessComputing Alliance The goal of the AccessComputing Alliance is to increase the participation of people with disabilities in computing fields. Funded by the National Science Foundation, Broadening Participation in Computing (NSF/BPC) Based at the University of Washington www.washington.edu/accesscomputing

Slide 32 :

32 AccessComputing Alliance Partners Gallaudet University Microsoft Regional Alliances for Persons with Disabilities in STEM University of Southern Maine, New Mexico State University and University of Washington ACM SIGACCESS

Slide 33 :

33 Activities College transition & bridge programs Communities of Practice (CoPs) Capacity building Institutes AccessComputing Knowledge Base of FAQs,case studies, promising practices Tutoring Internships e-mentoring

Slide 34 :

34 Advancing Deaf & Hard of Hearing in Computing Goals Raise the bar for deaf and hard of hearing in computing fields Establish UW Bridge Academy Establish e-Mentoring Community Develop Community of Practice (dhhCoP) Encourage collaborations http://www.washington.edu/accesscomputing/dhh

Slide 35 :

35 Raising the Bar For deaf and hard of hearing students with skills in math and/or science considering computing as a major Careers in: Computer Science Computer Engineering Information Systems Information Science

Slide 36 :

36 Computing Fields Computer Science Programming Software Systems Networks Artificial Intelligence Theoretical Computer Engineering Software & hardware systems Embedded systems Applications Information Systems Business solutions Databases System management Information Science Library Science Organization of inforamation Human factors Involves psychology, sociology and anthropology

Slide 37 :

37 University of Washington Summer Academy 9-week program for 10 students who are deaf or hard of hearing, beginning with the 2007 summer term. Students will take UW courses for college credit (e.g. Introduction to Programming, Precalculus, Calculus) Group project hopefully in animation Field trips to local industry

Slide 38 :

38 e-Mentoring Community High school and college students Computing professors Postsecondary students Professionals in computer fields With and without disabilities Discuss opportunities in computing fields Mentoring, peer and social support

Slide 39 :

39 Community of Practice (CoP) DHH CoP includes professionals and students who want to actively promote computing careers for deaf and hard of hearing persons Join by contacting me ladner@cs.washington.edu

Slide 40 :

40 Collaborate with Advancing Deaf & Hard of Hearing in Computing Let us know about interested students. Let us know about interested professionals Participate in e-mentoring community Participate in dhh Community of Practice Participate in Capacity Building

Slide 41 :

41 Advancing Deaf & Hard of Hearing in Computing Thank you!

Slide 42 :

42 ASL ASL is the preferred language for over 1,000,000 Deaf people in the U.S. ASL is not a code for English Signs usually occur within the “sign-box” Composed of location, orientation, shape of hands and arms + facial expressions Usually uses 2 hands, but one-handed signing not uncommon

Inflammatory cell In...

Community Acquired P...

Community Acquired M...

Infiltrating Basal c...

Genetic mechanisms t...

T cell B cell Sir ...

Free Powerpoint Templates

	cavender@cs.washington.edu 5 Years ago.



614 Views, 0 favourite
PowerPoint Slide Presentation on MobileASL is a video compression project at the University of Wash more PowerPoint Slide Presentation on MobileASL is a video compression project at the University of Washington with the goal of enabling real-time video conversations in American Sign Language over the standard GPSR cell phone network in the U.S. less
More By User Flag as inappropriate Select your reason for flagging this presentation as inappropriate. If needed, use the feedback form to let us know more details. Cancel