Unformatted text preview:

Pupil Detection and Tracking System Lior Zimet Sean Kao EE 249 Project Mentors Dr Arnon Amir Yoshi Watanabe 1 Outline Introduction and Goals Design Methodology Model of Computation Mapping and Implementation Verification Conclusions December 5 2002 EE 249 Project Presentation Lior Zimet and Sean Kao 2 Motivation Human computer interfaces are becoming more important New interfaces may benefit from knowledge of the location of the user s eyes Auto stereoscopic displays Virtual Reality interfaces Facial recognition systems Eye gaze tracking December 5 2002 EE 249 Project Presentation Lior Zimet and Sean Kao 3 Goals Exercise design process from functional specification to implementation and verification Develop an embedded system that will find the two dimensional location of a user s pupils Apply various methodologies we have learned Use a heterogeneous collection of various components in a real time environment December 5 2002 EE 249 Project Presentation Lior Zimet and Sean Kao 4 Background Human pupils may be found using two infrared light sources An on axis light source will give the redeye effect December 5 2002 EE 249 Project Presentation Lior Zimet and Sean Kao 5 Background An off axis light source will give a darkpupil effect We can synchronize the two light sources with the capturing device December 5 2002 EE 249 Project Presentation Lior Zimet and Sean Kao 6 Difference of the two Images December 5 2002 EE 249 Project Presentation Lior Zimet and Sean Kao 7 Design Methodology Begin with a definition of the system with illustrations Make a formal specification using the Unified Modeling Language Describe the system using a behavioral model Explore architectural space Map functionality into chosen architecture Verify implementation December 5 2002 EE 249 Project Presentation Lior Zimet and Sean Kao 8 System Definition Take in an image illuminated with two different light sources Find the pupils in the image Calculate the position of the pupils Output the coordinates Sensor Light control User Interface Image Processing Sensor December 5 2002 Video stream handling Pupil Detection Tracking EE 249 Project Presentation Lior Zimet and Sean Kao 2D Location Output Interface 9 UML Diagrams UML is used for formally describing a system Use case diagram shows functions of the system without implying how it is done Class diagram shows what functional blocks are used Sequence diagrams show how the usecases are executed December 5 2002 EE 249 Project Presentation Lior Zimet and Sean Kao 10 Use Case Diagram System Illuminate Target uses uses Synchronize Illumination with Image Capture Capture Image Image Target uses extends Activate System extends Calculate Pupil Position Modify Settings User extends Format Data Receiver Use Case 1 User activates the system 2 User may modify system characteristics 3 System synchronizes illumination with image capturing 4 System calculates pupil position based on caputed images 5 System outputs position based on output format invariant On axis and off axis LEDs may not be lit at the same time December 5 2002 EE 249 Project Presentation Lior Zimet and Sean Kao 11 Class Diagram implementation class IR Light Source Location bool on axis off axis Activate Deactivate 2 1 implementation class Synchronizer FrameType bool Odd Even implementation class System Clock Frequency implementation class Display Activat OnAxis Light Activat OffAxis Light Send Tick Display Locations 1 1 1 1 1 1 implementation class Sensor Brightness int Resolution int Get Image Send Pixel Data Send Next Frame Signal Send Next Line Signa Send Next Pixel Signal Initialize 1 implementation class Image Processor implementation class Memory Handler Current Location long 1 1 1 Store Pixel Advance Line Advance Frame Get Pixel 1 1 1 Subtract2Lines Threshold Line Connect Components Track Components Store Pupil Locations Send Pupil Locations n struct Pupil Locations LocationX int LocationY int 1 1 1 1 2 1 implementation class Controller 1 3 struct Frame Size long 1 Initialize December 5 2002 n struct Pixel LocationX int LocationY int Value byte n EE 249 Project Presentation Lior Zimet and Sean Kao 1 struct Line Size int 12 Y Chart of the Project System Behavior System Architecture Mapping Refine Implementation of System First we ll describe the system behavior with an appropriate model of computation December 5 2002 EE 249 Project Presentation Lior Zimet and Sean Kao 13 Model of Computation Processes large amounts of data in a similar way Dataflow model is the most appropriate Our system is not control centric But some parts of the system are easier to describe using sequential algorithms Mixed models of computation December 5 2002 EE 249 Project Presentation Lior Zimet and Sean Kao 14 Simulink versus Ptolemy Virgil Ptolemy has the ability to mix models of computation and has support for synchronous dataflow But Virgil does not have a simple way to integrate sequential algorithms Simulink has extensive support for sequential algorithms Matlab But lacks clearly defined semantics combination of dataflow and discrete event December 5 2002 EE 249 Project Presentation Lior Zimet and Sean Kao 15 Simulink Model of Computation Use one clock to synchronize the system No implicit definitions how many tokens are generated or used We use counters and synchronous signals to determine how many tokens are on edges December 5 2002 EE 249 Project Presentation Lior Zimet and Sean Kao 16 Simulink Model Image capture model source Subtraction and threshold FIFO Update properties of known objects in a frame Calculate X Y coordinates from those properties December 5 2002 Properties of objects on a line Connect objects in different lines Display the coordinates EE 249 Project Presentation Lior Zimet and Sean Kao 17 Verifying the Functionality Obtained images from IBM Almaden Research Center Run Simulink model on half scale images and verify the behavioral model December 5 2002 EE 249 Project Presentation Lior Zimet and Sean Kao 18 System Architecture on Y Chart System Behavior System Architecture Mapping Refine Implementation of System Next we ll define the system architecture December 5 2002 EE 249 Project Presentation Lior Zimet and Sean Kao 19 System Architecture Image capture device Programmable hardware Frame buffer FIFO Interface controller Architecture Space PC Image Programmable capture device hardware Frame buffer FIFO December 5 2002 PC EE 249 Project Presentation Lior Zimet and Sean Kao Interface controller 20


View Full Document

Berkeley ELENG C249A - Pupil Detection and Tracking System

Documents in this Course
Load more
Loading Unlocking...
Login

Join to view Pupil Detection and Tracking System and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Pupil Detection and Tracking System and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?