가속도 센서를 이용한 동적 손 제스쳐 인식
- 가속도 센서를 이용한 동적 손 제스쳐 인식
- Date Issued
- Keypad based input method has been widely used for mobile device, such as mobile phone, MP3 player and remote control of electronic devices.
As devices has more functions, keypad become more complex.
Demand for intuitive interface and recent improvement of sensor and embbedded system technology enable gesture-based interface for mobile device.
There are some research interests in gesture recognition with mobile device that contains accelerometer and gyroscope.
More atention has also been paid to gesture recognition with an accelerometer only, due to the relatively bulky size and high price of a gyroscope.
Isolated gesture recognition is a kind of gesture recognition problem, which is to recognize single gesture from given data.
It reqires a kind of pre-processing step to identify block of data involving single gesture before recognition process, whereas continuous gesture recognition system does not. This thesis has
three main contribution on accelerometer based gesture recognition.
First, we suggested an accelerometer based isolated gesture recognition system.
Gravity acceleration components are removed form 3-d acceleration signals.
Then,blocks of acceleration signals, involving single gesture, are extracted.
Extracted blocks are applied to gesture model, to calculate likelihoods. Likelihoods for each gesture models are adjusted by corresponding weights. Weighted values
of likelihood are finally used to determine a gesture model that best matches
the input data in the recognition system. Hidden Markov models (HMMs) are
used to model each gesture. In contrast other HMM-based approach, we use
continuous LR HMMs and modified recognition criterion istead of discrete ergodic
HMMs and maximu likelihood criterion.
Second, we proposed an accelerometer based continuous gesture recognition
system. Our HMMs-based isolated gesture recognition system can be
exteneded continuous gesture recognition system by merging each HMMs to
one huge HMM. This approach can be seen as 2-layered HMMs, the 1st-layer
modeled the transition between gesture models, and 2nd-layer modeled each
gesture. Maximum likelihood criterion, used in isolated gesture recognition
system, can not be used to predict newly incoming acceleration signals in continuous
gesture recognition system. Instead of the criterion, ？？-based approach
is used to predict test data.
Finally, we suggest pseudo velocity signals, which is transformed from acceleratioin
signals, for improvement of discriminative power. If we transform acceleration
signals to other signals which represent velocity, including direction
and speed of motion, it will be helpful to recognize the gesture. Accumulation
of acceleration signals can be used for approximation of velocity signals. But
in this case, noise of acceleration signals is also accumulated. As noise level
of acceleration signal is high, due to lack of rotation information and imperfect
gravity component removal, noise level of estimated velocity is extrimly high.
We adapt template based approach, which is free from noise accumulation.
- Article Type
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.