Panacea - Augmented Reality

1,296 views
1,210 views

Published on

Published in: Design
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total views
1,296
On SlideShare
0
From Embeds
0
Number of Embeds
394
Actions
Shares
0
Downloads
0
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

Panacea - Augmented Reality

  1. 1. PANACEA<br />TWANACEA<br />* Possible names for the application<br />
  2. 2. The Team <br />Navneet<br />Nikhil<br />Manohar<br />Ritesh<br />
  3. 3. For people who are on webex<br /> Please visit this URL for all the videos that we play. <br />http://tinyurl.com/twdemo<br />
  4. 4. We built <br />“ <br />An augmented reality application to be used inside an Enterprise to manage contacts and location services.<br />“ <br />
  5. 5. Augmented Reality?<br />Augmented reality (AR) is a term for a live direct or an indirect view of a physical, real-world environment whose elements are augmented by computer-generated sensory input, such as sound or graphics<br />Simple Defn : overlaying of digital data on the real world.<br />* Courtesy – wikipedia and howstuffworks.com <br />
  6. 6.
  7. 7.
  8. 8. Contacts<br />Problems<br />
  9. 9. Contacts<br />Problems<br />Ritesh M NayakDeveloper<br />ThoughtWorks Technologies (India) Pvt Ltd2nd Floor, Tower C, Corporate Block, Diamond District Airport Road, Bangalore - 560 008, Indiatel : +91 80 4064 9570, fax : +91 80 2508 9584<br />riteshm@thoughtworks.com <br />… passé <br />
  10. 10. Contacts<br />Problems<br /> My next visiting card will look like this <br />Ritesh M Nayak<br />With Best Wishes <br />ThoughtWorks Technologies (India) Pvt Ltd2nd Floor, Tower C, Corporate Block, Diamond District Airport Road, Bangalore - 560 008, Indiatel : +91 80 4064 9570, fax : +91 80 2508 9584<br />riteshm@thoughtworks.com <br />. . .You know why? <br />
  11. 11. Contacts<br />Problems<br />My only use for it now is to attach it to gifts that I give. <br />
  12. 12. A radical new way of exchanging contacts inside the enterprise<br />vCards 2.0 <br />
  13. 13. Contacts Management<br />Video Demo – Play Video 1 on the supporting website <br />
  14. 14. You meet these guys at X-Conf. How long do you think it will take you exchange your contact information? <br /> We say about 10 seconds! <br />
  15. 15. How we do this. <br />Tech<br />
  16. 16. Application Walkthrough<br />Video Demo – Play Video 5 on the supporting website <br />
  17. 17. - 3 step process<br /> - Core of the idea is a ML<br />Algorithm for face recognition<br /><ul><li>As with any ML algorithm, the larger the training set, the better the quality of the algorithm. </li></ul> Face Recognition<br />Status flags convey what thread is currently active and processing.<br />
  18. 18. Step 1<br />Detection /Scanning<br />No faces in this image <br />Face Detection –algorithm to detect if there is a face present on the given image. <br />
  19. 19. Step 2<br />Recognition<br />Point out the faces that were detected<br />Face Recognition – Once a face is detected, the face has to be processed by an algorithm which will associate a unique id from the training set.<br />
  20. 20. Step 3<br /> Data/Action Fetch<br />Augement real time image with info bubble<br />PrateekshaUday<br />nono@hotmail.com<br />9889090123<br />Once the algorithm returns a unique identifier based on the processed image, we fetch the data corresponding to that id. In our case, the details from Active Directory. (actually, not just AD)<br />
  21. 21. Implementation and Challenges<br />Uh Oh!<br />
  22. 22.
  23. 23. Face Recognition<br />Video Demo – Play Video 2 on the supporting website <br />
  24. 24. First Approach<br /> Training Set<br />Manual Training<br />Face Detection<br />LDAP<br />Face Recognition<br />Service Calls<br />App<br />Massive Database of Photos<br />
  25. 25. Problems with this approach <br />Too Painful<br /> Training Set<br />Manual Training<br />Face Detection<br />Face Recognition<br />Service Calls<br />App<br />Not Real time – Not scalable<br />
  26. 26. We found Open Source Computer Vision. A free library that does object detection, recognition and 500 other image processing algorithms.<br />Yay!<br />OpenCV is a C++ library <br />
  27. 27. Second Approach<br />Gives<br />Compile Using<br />opencv.so<br />C++ Libraries<br />Android NDK<br />opencv.so<br />Java Native Interface (JNI)<br />App<br />
  28. 28. Pros & Cons - Second Approach<br />opencv.so<br />Java Native Interface (JNI)<br />App<br />Not Accurate<br />Near Real time<br />No Service Calls<br />Poor Training data<br />Totally in Phone<br />
  29. 29. Hybrid Approach<br />Face Detection<br />Scanning Mode<br />Face?<br />Yes<br />Face Recognition<br />Training Mode<br />
  30. 30. A new way of putting up Assistance and event posters.<br />Posters<br />
  31. 31. Contacts<br />Problems<br />Wait! Is there a name of a person as well? So, now I know the person as well his/her phone number.<br />What happens if the Phone number changes?<br />Exposed Phone numbers are dangerous. Can be abused by telemarketers<br />
  32. 32. A new way of putting up assistance posters. No numbers, no hassles. <br />For all Travel related Queries<br />
  33. 33. X-Conf 4 – March 5th<br />Event Posters - Revisited<br />//TODO: Add functionality that will add this event to your calendar and notify you 10 mins before the event <br />Title: Don't do that, then! (Doctor, it hurts when I rewrite legacy applications)<br />* Photo courtesy thoughtworker.com<br />
  34. 34. Presence <br />* VISION<br />@starkcoffee - hopefully my.thoughtworks will be a completely fresh experience to TWers !<br />
  35. 35. * Almost there<br />Dinesh Tantri – Geek Lunch<br />Talk: Introducing my.thoughtworks<br />Give Feedback , ask questions – use panacea<br />Event / Conference Feedback – 1<br />
  36. 36. Event / Conference Feedback - 2<br />* Almost there<br />Talk: Introducing my.thoughtworks!<br />Comments<br />Feedback<br />
  37. 37. * VISION<br />Visual URL’s and Bookmarking<br />Use OCR to save this URL on a poster or on a hoarding.<br />
  38. 38. Wait, does this mean we need to train photos of every employee?Damn, that’s painful.Luckily . . . We have a solution<br />
  39. 39. Distributed Dataset Training<br />Video Demo – Play Video 3 on the supporting website <br />
  40. 40. Possibilities …<br />* Stock photo from stck.xchng<br />
  41. 41.
  42. 42. Do you know these applications?<br />* Logos courtesy their corresponding websites<br />
  43. 43. Location<br />Problems<br /> Only 13% of the smart phones sold across the world are Location Aware<br /> Less than 4% of all mobile phones sold last year were Location aware.<br /> * Stats courtesy: http://textopiablog.wordpress.com/2010/02/22/how-many-people-own-a-location-aware-device/<br />
  44. 44. Location<br />Problems<br />Too many places. Search doesn’t solve the problem either. <br />*screen shot courtesy google.com <br />
  45. 45. Location<br />Problems<br />Roof top Restaurant<br />Roof top - Bar<br />Pizzeria<br />Chinese Restaurant<br />Cafe<br />Multiple Avenues – Same GPS Location <br />
  46. 46. Creating and using GPS agnostic Hyper local communities<br /> Location<br />
  47. 47. But, how? <br /> Most smartphones come with a good camera. Given that we already had the technology to recognize faces, we just appropriated it to make a location service just like FourSquare or Gowalla. <br /> (our algorithms can be trained on other objects as well, like boards, toys etc)<br />
  48. 48. Introducing the PlaceMark!<br />Join my community and share your thoughts<br />
  49. 49. HyperLocal Communities<br />Video Demo – Play Video 4 on the supporting website <br />
  50. 50. Enterprise Network<br />Chicago<br />Bangalore<br />Pune<br />Chennai<br />Melbourne<br />
  51. 51. Implementation<br />Face Detection<br />Scanning Mode<br />Face?<br />Yes<br />Face Recognition<br />Location?<br />
  52. 52. Genesis, Ideation and Development<br />Prototype<br />
  53. 53. Mockups<br />* We used http://iphonemockup.lkmc.ch/ for smart phone mockups<br />
  54. 54. Application Architecture<br />Main UI Surface<br />Overlays<br />Camera<br />Info Overlay<br />status Overlay<br />Processing<br />Android native detection<br />Recognition service<br />Gab server<br />Location server<br />PANACEA<br />

×