Hand Gesture Based Wheelchair Movement Control for Disabled Person Using MEMS.

ABSTRACT

This paper is to develop a wheel chair control which is useful to the physically disabled person with his
hand movement or his hand gesture recognition using Acceleration technology. Tremendous leaps have
been made in the field of wheelchair technology. However, even these significant advances havent been
able to help quadriplegics navigate wheelchair unassisted. It is wheelchair which can be controlled by
simple hand gestures. It employs a sensor which controls the wheelchair hand gestures made by the
user and interprets the motion intended by user and moves accordingly. In Acceleration we have
Acceleration sensor. When we change the direction, the sensor registers values are changed and that
values are given to microcontroller. Depending on the direction of the Acceleration, microcontroller
controls the wheel chair directions like LEFT, RIGHT, FRONT, and BACK. The aim of this paper is to
implement wheel chair direction control with hand gesture reorganization

NEED OF PROJECT

This paper to develop a wheel chair control which is useful to the physically disabled person with his
hand movement or his hand gesture reorganization. With the help of the wheel chair physically disabled
person would able to move himself to the desired location with the help of hand gestures which controls
the movement of the chair. This paper aims to provide a feasible solution to those handicapped people
who do not have the ability to maneuver the wheelchair by themselves. These include people with
serious paralytic condition. Wheelchair automated control systems proved to be versatile tools for many
problems in human-computer interface systems. Basically, they are used for providing better usability of
a computer or a system for people, including disabled people.

TECHNOLOGY

Micro-electromechanical systems (MEMS) are free scales enabling technology for acceleration and
pressure sensors. MEMS based sensor products provide an interface that can sense, process or control
the surrounding environment. Micro-Electro Mechanical Systems, or MEMS, is a technology that in its
most general form can be defined as miniaturized mechanical and electro-mechanical elements (i.e.,
devices and structures) that are made using the techniques of micro fabrication. MEMS based sensors
are a class of devices that builds very small electrical and mechanical components on a single chip.
MEMS-based sensors are a crucial component in automotive electronics, medical equipment, hard disk
drives, computer peripherals, wireless devices and smart portable electronics such as cell phones and
PDAs. The functional elements of MEMS are miniaturized structures, sensors, actuators, and
microelectronics, the most notable (and perhaps most interesting) elements are the micro sensors and
micro actuators. Micro sensors and micro actuators are appropriately categorized as transducers,
which are defined as devices that convert energy from one form to another. In the case of micro sensors,
the device typically converts a measured mechanical signal into an electrical signal. MEMS technology
provides the following advantages: cost-efficiency, low power, miniaturization, high performance, and
integration. Functionality can be integrated on the same silicon or in the same package, which reduces
the component count. This contributes to overall cost savings. Hence with this paper we can save the
physically disabled persons who use wheel chairs they can control their wheel chair with their hand
movements.

LITERATURE SURVEY
When an unfortunate event affects the motor capacity of a person, it is necessary to use devices like
wheelchairs that offer a means of displacement for patients with motors problems of the lower limbs.
Tremendous leaps have been made in the field of wheelchair technology. However, even these
significant advances havent been able to help quadriplegics navigate wheelchair unassisted. Some
patients that cannot manipulate the wheelchair with their arms due to a lack of force or psychomotor
problems in the superior members, request electric wheelchairs, frequently manipulated with joysticks;
however, the joystick manipulation is even not practical and frequently it must be handle with the
mouth. The present article presents the partial results in the development of a wheelchair controlled by
an intuitive interface, where the instructions are given by hand gesture instructions. The advances are
presented in the realization of the control software using a Webcam and some distances and presence
sensors controlled by a PIC microcontroller that establishes the communication with a program
developed in Lab view. This paper is inspired from an IEEE Research Paper Titled A Wearable Head-
Mounted Sensor Based Apparatus for Eye Tracking Applications that was presented in the IEEE
International Conference on Virtual Environments, Human-Computer Interfaces, and Measurement
Systems Istanbul, Turkey, dated 14-16 July 2008. The above paper approach was dealing with wheelchair
control using eye ball movement with slight modification to it. Our paper deals with the control of
wheelchair motion by hand gesture.

VARIOUS TECHNIQUE USED IN WHEELCHAIR CONTROL

There is a vast development in the field of wheelchairs. Out of all the methodologies, HCI (Human
Computer Interface) and HMI (Human Machine Interface) are the latest and most effective techniques.
In user interface systems both bio-signals and non bio-signals are used as a medium of control. Bio-signal
based devices mainly use bio-signals like EEG, EOG or EMG as control signals. The bio-signal based
approach is used for completely paralyzed patients who can only use their bio-signals as the only
resource to control [5].

EEG based The Electroencephalography (EEG) records electrical brain signals from the scalp, where the
brain signal originates from postsynaptic potentials, aggregates at the cortex, and transfers through the
skull to the scalp. BCI is a device that extracts EEG data from brain and converts it into device control
commands using signal processing techniques. EEG techniques are non-invasive and low cost. However,
it brings great challenges to signal processing and pattern recognition, since it has relatively poor signal-
to-noise ratio and limited topographical resolution and frequency range [6, 7, and 8].

EMG based EMG measures electrical currents that are generated in muscles during its contraction. A
muscle fiber contracts when it receives an action potential. The EMG observed is the sum of all the
action potentials that occur around the electrode site. In almost all cases, muscle contraction causes an
increase in the overall amplitude of the EMG. EMG signals can be used for a variety of applications
including clinical applications, HCI and interactive computer gaming. They are easy to acquire and of
relatively high magnitude than other bio-signals. On the other hand, EMG signals are easily susceptible
to noise. EMG signals contain complicated types of noise that are caused by inherent equipment noise,
electromagnetic radiation, motion artifacts, and the interaction of different tissues. Hence preprocessing
is necessary to filter unwanted noise in EMG. The EMG signals also have different signatures depending
on age, muscle development, motor unit paths, skin fat layer, and gesture styles. The external
appearances of two individuals gestures might look identical, but the characteristic EMG signals are
different [9].
EOG based EOG based technique are very useful for persons who born with any congenital brain disorder
or for those who are suffer from severe brain trauma. EOG signals records the potential difference
between the retina and cornea of the eye. When the eyes are rolled upward or downward, positive or
negative pulses are generated. As the rolling angle increases, amplitude of pulse also increases and the
width of the pulse is in directly proportional to the eyeball rolling process [10, 11].

Non Bio-signal based Non bio-signal based devices provide 100% accuracy and require less training for
patients. In general, non-bio signals based techniques which make use of joystick control, sip-n-puff
control, tongue control, Touch screen controlled, Voice actuated, head movement tracking etc [5]. In this
method using air presser to generates control signals by sipping (inhaling) or puffing (exhaling) in a tube.
This technology generates four control signals for motorized wheelchair which are initial hard puffs, hard
sip, initial hard sip, and hard puff. It is mostly used for quadriplegics having injury in their spinal cord or
people with ALS. But this is not good for individual with week breathing.

Head Orientation Tracking Technique Here in this method, head movements are transformed into cursor
movements on the screen. Cursor movements are proportional to head movements. Head movements
are calculated by different methods like accelerometer placed in a patients cap or by capturing video of
head movements. But the problem with this technique is that differentially able people of certain
categories such as cerebral palsy patients cannot even move their head comfortably. Another problem of
this technique is that forehead continuously needs to face the camera [12, 13].

Chin Control Technique In this technique chin is put in cup shape joystick and is usually controlled by
neck movements (flexion, extension, and rotation). The major problem that arises in this mode of control
is the need for constant pressure in chin cup [14].

Eye Tracking Technique In this technique wheelchair is controlled by an optical type eye tracking system
(screen based system). Camera is used to continuously track the features of eye. There after a calibration
algorithm is used to find the direction of eye gaze in real time. Than according to gazed position, screen
movement control signals are calculated to control the wheelchair [15, 16 and 17].

Tongue Controlled This technology is based on Faradays law. Permanent magnet is used here and is
attached to tongue. As the tongue move in air core induction coil, the inductance is changed. A Hall
Effect sensor is placed in the stud of tongue. Hall Effect sensor is a transducer that varies its output in
response to change in magnetic field. The movement of tongue is traced by of Hall Effect sensor.
Thereafter, the Output signals are collected that provide continuous real time analog output [18].

Image Processing Algorithm Here, webcam is used for capturing image input from the finger of user.
After that we use an image processing algorithm (image blurring, RGB to HSV conversion, HSV
thresholding) that helps in finger detection. According to direction of finger, wheelchair moves in left-
right or in front back direction [19].

Brain Actuated Wheelchair using Brain Wave Sensor There is billions of interconnected neuron in human
brain. The way, neurons are connected to each other depicts the various thought processes and
emotional states. This pattern of neurons connection keeps on changing according to the human thought
& process different electrical signals. For sensing these electrical signals, brain wave sensor is used that
convert the data into packets- which are transmitted through bluetooth medium. Level analyzer unit
(LAU) is used to receive raw data. The extraction and processing of the signal is done using Matlab
platform. The control commands are transmitted to the robotic module to process. With this entire
system, any robot can be moved according to the human thoughts and it can be turned by blink muscle
contraction. By using this brainwave concept executed in wheelchair the handicap can easily controls
wheel chair [20].

Accelerometer Based In accelerometer based wheelchair, we have an acceleration sensor that is also
known as tilt sensor. When we tilt the object, the values registered by sensor are changed and these
values are given to microcontroller. Depending on the direction of the tilt, microcontroller controls the
wheelchair directions as LEFT, RIGHT, FRONT and BACK [21].

Based on Deictic Approach The deictic approach uses the vision of the environment as a control
interface. This vision must be as close as possible to the perception of the user so that the interface is
intuitive and therefore easy to use. To move, the user specifies the location within the environment he
wants to go to by pointing at it on the interface. Then the wheelchair will move automatically to that
position. As the command is given from time to time, it does not require much effort from the user [22].

Touch screen controlled The mode of input control to the wheelchair is touch screen. When user wants
to change the direction, the touch screen sensor is modeled by pressing finger against the various
quadrants on the touch screen, which has different values for different direction [23].

Voice actuated in this technique user speak in microphone and the voice recognition system compares
the voice command with pre-stored memory and generates a control signal to control the movements of
wheels [24, 25 and 26].

DRAW BACKS OF PRESENTLY AVAILABLE WHEELCHAIRS

Most significant technical issue in the currently available wheelchairs is cost versus accuracy.
Unavailability of wheelchairs for particular disabilitiy is also a considerable issue. Also, the present
systems are unable to monitor the surrounding conditions and the health condition of the patient. There
is also no wheelchair available till date for the bed lying patient. No wheelchair available for mentally
challenged people also. Above all the other important aspect to consider is the physical barrier that
place additional requirement on strength and durability of wheelchairs.

FUTURE SCOPE OF WHEELCHAIRS

Proposed method is controlling of the wheelchair by the thought process. In this technology person can
control the motion of the same by just thinking. This vehicle can be modeled in such a way that it can be
easily turned into a semi sleeper mode in order to make the patient feel more comfortable and thereby
reducing the continuous one mode sitting problem. Other already invented methods in wheelchair can
also be incorporated with this [3]. Like step climbing wheelchair and inter communication between
devices-which is just an upcoming project trying to be implemented on road vehicles. The
communication aid with these wheelchairs will help the deaf and dumb to communicate with each
others too [3]. These all are the (much more can be thought of) proposed for the Future scopes of smart
wheelchairs.