Vous êtes sur la page 1sur 2

Real-time Gesture Recognition and Robot control

Through Blob Tracking


AIM:
This paper presents vision based interface that has been designed to instruct a device
Switching through gestures with blob detection techniques using image processing.
INTRODUCTION:
As the need for human-computer interaction (HCI) grows in many aspects of the digital
world, various ways of communicating with computers have been exploited and there is little doubt
that hand gesture is one of the most intuitive ways for this end. More and more applications in
virtual reality (VR), gaming, human-robot interaction (HRI) and HCI based on hand gesture and
posture recognition have emerged in the past decade. Its not new to study on a remote control for
home appliance such as air conditioner using humans free hand gesture instead of cumbersome
hand-held wireless remote controllers. Nevertheless, to the best of our knowledge, there exists no
commercial remote controller that uses free hand gesture because it requires high robustness to
various illumination changes in living room and full automation without any constraint or direct
intervention of users. Although there are some studies to satisfy the requirements, most researches
on gesture recognition have been devoted to solve sophisticated problems such as understanding
sign languages by interpreting sequences of 3D motion or shape of Hands.
EXISITING SCHEME:
In previous approaches, the device can be switched on or off by using radio frequency
technology and IR transmitting technology. By using such a technology, different kinds of remote
can be used to control the various devices. Generally, there are two types of remote controls: Infra
red, and Radio frequency. Infrared remote controls work by sending pulses of infrared light to a
device, while RF remote controls use radio waves in much the same way. Pragmatically, the biggest
difference between the two is range. IR remote controls require a clear line of sight to the receiving
device and their range maxes out at about 30 feet (9.14 meters). RF remote controls can go through
walls and around corners, with a range of roughly 100 feet (30.48 meters).

PROPOSED SYSTEM:
We propose a system, using which the user can control the device in any environment using
various gestures commands. Here the user operates the switching through a laptop or a PC with inbuilt webcam or external webcam. This webcam is used to capture real time video stream of hand

gestures with blob detection is to generate commands for the divice switching. Using the gesture
technique developed, divice is switched without any intraction.

BLOCK DIAGRAM:
Device 2

Power Supply
Section

ARM11
(BCM2835)
USB
HOST

USB camera

IO
PORT

Relay
Driver
circuit

Device 2

SRAM
(512MB)

FLASH
(8GB)

System Requirement:
Software Requirement:
Language

Embedded C.

Compiler

arm-linux-gcc 4.4.6.

OS

LINUX (Ubuntu11.4).

Hardware Requirement:

ARM11(BCM2835)

USB Camera

RELAY, ULN2003

Optocoupler

Vous aimerez peut-être aussi