16
TELEKINESYS Group Members: Mir Murtaza SM Rasikh Mukarram Shiraz Sohail

TELEKINESYS Group Members: Mir Murtaza SM Rasikh Mukarram Shiraz Sohail

Embed Size (px)

Citation preview

Page 1: TELEKINESYS Group Members: Mir Murtaza SM Rasikh Mukarram Shiraz Sohail

TELEKINESYSGroup Members:

Mir MurtazaSM Rasikh Mukarram

Shiraz Sohail

Page 2: TELEKINESYS Group Members: Mir Murtaza SM Rasikh Mukarram Shiraz Sohail

INTRODUCTION

REAL WORLD PROBLEM• Projection of screen is widely used in

presentations and teaching at IBA.

• The presenter keeps himself/herself in the proximity of the computer system to control it.

• Lacks the naturalness of the interaction.

• Our proposed solution: Control the mouse functions with hand gestures

IBA CED

Page 3: TELEKINESYS Group Members: Mir Murtaza SM Rasikh Mukarram Shiraz Sohail

SOLUTION Using camera to allow the same kind of user input as touch-screens do, but with a lower price and a larger screen.

Page 4: TELEKINESYS Group Members: Mir Murtaza SM Rasikh Mukarram Shiraz Sohail

OUR APPROACH

• CAMERA-PROJECTOR CONFIGURATION CONTROLS THE MOUSE.

• CAMERA HAND + GESTURES’ DETECTION

• HAND DETECTION AND GESTURE DETECTION: USING LED LIGHTS

• HAND +GESTURES DETECTION MOUSE FUNCTIONS

Page 5: TELEKINESYS Group Members: Mir Murtaza SM Rasikh Mukarram Shiraz Sohail

IMPLEMENTATION

THE SYSTEM DESIGN• INPUT

• INTERFACE

• OUTPUT

Page 6: TELEKINESYS Group Members: Mir Murtaza SM Rasikh Mukarram Shiraz Sohail

METHODOLOGY Input includes:

1. Valid Region Detection

2. Hand Detection Using LED Lights

3. Gesture Detection• Interface communicate between

the recognition part and the OS. • Input data Interface• Interface performs the action

Page 7: TELEKINESYS Group Members: Mir Murtaza SM Rasikh Mukarram Shiraz Sohail

Valid Region Detection• Valid region is the projected screen.• Rectangular Screen property.• openCV function cvfindcountours.

• Valid and Invalid region

• The alignment of web camera• User confirmation of screen

Page 8: TELEKINESYS Group Members: Mir Murtaza SM Rasikh Mukarram Shiraz Sohail

Hand Detection Using LED Lights• LED lights locates position of the

hand.

• Three LED lights sufficient.

• Noise filtering can be done in two ways:

1. Set the level of threshold to filter all the light of less intensity.

2. Cover the camera lens with a black film negative.

Page 9: TELEKINESYS Group Members: Mir Murtaza SM Rasikh Mukarram Shiraz Sohail

Gesture Detection• A maximum of three light sources

can be detected:

1. The light that is closest to the track point is the first light F;

2. The second light at the left hand side of F is L;

3. The third light at the right hand side of F is R.

Page 10: TELEKINESYS Group Members: Mir Murtaza SM Rasikh Mukarram Shiraz Sohail

Gesture Detection By LED Poistions• forefinger LED light point F

• When light L appears on the left hand side of light F, then left click is executed.

• When light R appears on the right hand side of light F, then right click is executed.

• If three lights appear for a second, then the function of scrolling is executed.

• Valid and invalid gestures.

Page 11: TELEKINESYS Group Members: Mir Murtaza SM Rasikh Mukarram Shiraz Sohail

Software Requirements

• OpenCV – computer vision library.

• C++ – working with OpenCV to analyze the hand shape and gesture.

• Bloodshed Dev-C++ – acts as complier

• Matlab – for machine learning.

Page 12: TELEKINESYS Group Members: Mir Murtaza SM Rasikh Mukarram Shiraz Sohail

Hardware Requirements1. Projector Installed in every class of IBA.

2. Webcam Easily available and affordable. Laptop’s camera can also be used.

3. LED Lights: Three 1V LED lights + 9V battery + Gloves

Page 13: TELEKINESYS Group Members: Mir Murtaza SM Rasikh Mukarram Shiraz Sohail

End deliverables• A webcam with a particular resolution with its lens covered with a black film

negative to filter all the noise and light entering into the classroom.

• A Hand Glove with LED system integrated. This covers three 1Volt LED lights connected in parallel with a 9 volt battery. The battery lifetime is around 20 days if kept switched on continuously. The system also consists of 1pos On-Off switch which is used for simultaneous control of all 3 LED lights.

Page 14: TELEKINESYS Group Members: Mir Murtaza SM Rasikh Mukarram Shiraz Sohail

Related Work• Sit Chu Wah, Sin Kwok San and Luk

Tsan Kwong• Prof. Brian Kan-Wing MAK

• Attila Licsár1, Tamás Szirányi1,2

Page 15: TELEKINESYS Group Members: Mir Murtaza SM Rasikh Mukarram Shiraz Sohail

Future Scope• Projects’ completion is base for uncovered hand and gesture recognition system.

• The hand gestures complexity

• Our research and work plan for future.

Page 16: TELEKINESYS Group Members: Mir Murtaza SM Rasikh Mukarram Shiraz Sohail

References• Sit Chu Wah, Sin Kwok San and Luk Tsan Kwong• Prof. Brian Kan-Wing MAK

• Attila Licsár1, Tamás Szirányi1,2

• Antonis A. Argyros and Manolis I.A. Lourakis