1 / 9

Code: CS 893 JIS College of Engineering, WBUT

VTR. Code: CS 893 JIS College of Engineering, WBUT. Virtual Trial Room. The Augmented Reality Technique. Presented By:. Abhinav Biswas & Soumalya Dutta. VTR. What is it ?. Portrays an augmented view of the user in a dynamic real-time Live Video mode with virtual superimposed clothes

yonah
Download Presentation

Code: CS 893 JIS College of Engineering, WBUT

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. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. VTR Code: CS 893JIS College of Engineering, WBUT Virtual Trial Room The Augmented Reality Technique Presented By: Abhinav Biswas & Soumalya Dutta

  2. VTR What is it ? • Portrays an augmented view of the user • in a dynamic real-time Live Video mode • with virtual superimposed clothes • Implements a virtual mirror • with interactive digital options onscreen • Immediately allows the user to see • if a clothing’s color/style suits his/her body • before he can actually decide to buy it. A software that :

  3. VTR How to use it ? • User stands in front of the digital screen • Various onscreen options get displayed • Like Category (Men, Women, Kids). • Selects option using simple Hand Motion • Then the augmented image with virtual clothes is shown. • Adjusts the placement of the cloth item • With onscreen options like Zoom In/Out, Up/Down etc. • Finally take a snap, save or print it. • Also now the user can decide whether the cloth is worth a buy. An intuitive way :

  4. VTR How we made it ? • Face Tracking, Motion Detection • OpenCV 2.3.1 • Swing Java 1.6, • Front-end GUI. • JavaCV – The OpenCV Wrapper • With hardware accelerated image processing features. • Eclipse Helios 3.6 • The wonder tool, An extensive IDE Technologies used : OpenCV

  5. VTR System Design Grab video frame from Webcam & flip it. Implement Face Detection on each frame using HaarCascade classifier Motion Detection using frame difference method Parallel Processing Track selected options based on detected motion & act accordingly Super Impose virtual cloth image on the frame based on detected face Options Scaling & Positioning Overlay replacement, (Next/Previous) Adjustment of the overlay Show frames in a video mode

  6. VTR Face Tracking • Taking a Large No Samples • Creating the Description file • Packing the positive samples into a vector file • Training the classifier • Converting the trained cascade into a cascade file The HaarCascade Classifier method :

  7. VTR Motion Detection • Absolute difference of consecutive frames with threshold value. • Detection of Hand motion in pre-defined areas. • System response based on selected option. Frame Difference method :

  8. VTR Future Scope • Retail Industry – Shopping Malls • Online Web Shopping • one-click share on Facebook.com • virtual mirror for eye-wear (sunglasses) & necklace • Automated smile detection for easy snapshot. • Auto-suggestion of cloth items, etc. • Implementation : • New Features :

  9. VTR Thank You ! Presented By: Mr. Abhinav Biswas, Mr. Soumalya Dutta http://abhinavtheprince.blogspot.com

More Related