23-01-2011, 09:57 PM
SixthSense
Gokul Sudhakaran
Department of Computer Science and Engineering
Government Engineering College, Thrissur
Gokul Sudhakaran
Department of Computer Science and Engineering
Government Engineering College, Thrissur
presentation:
[attachment=8397]
Overview
● Introduction
● Features
● Gesture Recognition
● Applications
● Merits and Demerits
● Enhancements
Introduction
● Steve Mann-> Father of SixthSense
● Later developed by Pranav Mistry, a PhD
student at MIT
● 'SixthSense' is a wearable gestural
interface that augments the physical world
around us with digital information and lets
us use natural hand gestures to interact
with that information.
Features
● Connects digial world to the real world
● It uses a mini projector coupled with
camera and cellphone- that acts as
computer and is connected to cloud.
● Makes the digital aspect of our life more
intuitive, interactive and natural
● Technologies used
– Hand augmented Reality
– Gesture Recognition
Features
– Image capturing, processing and
manipulation
● Hardware
Gesture Recognition
● Motion Segmentation
● Skin Colour Model
● Geometric Analysis
● Motion Trajectories
● Recognizing Motion Patterns using Time
Delay neural network
Motion Segmentation
● estimates a 2D motion field by matching a
multiscale set of region primitives
● perform well in situations where pixelbased
methods fails
● region primitives are fairly robust to noise
and illumination changes
● multiscale set of regions used to find their
correspondences. The reason is that a
multiscale algorithm provides a much
richer description of regions available for
matching
Motion Segmentation
● For a pair of frames, (It,It+1), the algorithm
identifies regions in each frame
comprising the multiscale intraframe
structure
● Regions at each scale are then matched
across frames.
● Motion segmentation generates regions
that have uniform motion