Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

HPAD Software Design Presentation

this is a prototype for our presentation we are going to demo in our SDS presentation
by

Abdelrahman Mahmoud

on 1 July 2011

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of HPAD Software Design Presentation

Motivation of the project? Introduction Thesis Statement We are to develop an API that will be fed by a VGA camera, and through image processing the API will recognize hand gestures and postures that can then be interpreted to perform the desired action Software Requirements Functional Requirements Select Input.
Mode Setup.
Set Callback functions.
Start Processing.
Stop Processing. Non Functional Requirements Efficiency
Accuracy
Usability
Extendibility Interaction Diagrams Class Diagram Software Design Hand Posture Recogntion & Tracking Descisions State Machines PLAN B PLAN A Timeline "We Would like to thank Dr. Joshua Gluckman for his enormous amount of help & continuous support." By,
Abdelrahman Mahmoud
Amin Al-Marsafy
Mohamed Ibrahim
Mohamed Selouky
Tarek Hefni

Supervised By,
Dr. Joshua Gluckman

Thesis Coordinator,
Dr. Ahmed Rafea Hand Posture Recognition & Tracking over Simple Backgrounds Two distinct colors for each hand. Colors we want to detect are not discreet values.
Computing the center of blobs
Tracking two hands. Develop a more intuitive human/computer interface
Control and manipulate various computer applications easily.
Produce efficient results in less time. Challenges 1. Colored blobs at the finger tips
2. Background does not contain red and blue. Hand Posture Recognition &Tracking in Normal User Enviroment! Good Lighting.. Normal background, no special gear Decisions Use blob detection to identify the locations of finger tips, palms.
Use skin detection in YCrCb color space
Use particle filtering to track the posture Challenges Implementation of Ridges
Use particle filtering without the ridges info Architecture Outline Motivation of the project?
Software design
Human computer interaction (HCI) component
Hand posture recognition component
Testing applications
Decisions of the project
Timeline
Questions Human Computer Interaction (HCI) What is?
Challenges & Decisions? How? Progress? How? Restrictions on User Enviroment Scale & Rotation Invariant Blobs & Ridges Detector.
Partical Filtering to track the posture Experimentation? Why Two Plans (A & B)? Using Image Processing to recongize hands from Images captured through a web camera... Because We want to develop components in parallel.
Because Image Processing is not an easy subject. Testing Apps Decisions of the Project: Posture is defined by number of fingers
No Machine Learning.
Developing project components in parallel. One Slide Left..... 1. Blobs number
2. Blobs Position Interaction Diagram Complex Tracker ---- 13 fps
Simple Tracker ---- 30 fps Testing Machine Specs MacBook Pro
Processor: Core2 Due 2.4 GHz
RAM: 2 G.B DDR 3
VGA: Nvidia 9600 GT
Camera: ISight
OS: Windows 7 RC - 32 bit Much faster than our exper. in 491
{Show Video}
Full transcript