A Survey on Smart Devices for Object and Fall Detection

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 09 Issue: 01 | Jan 2022 www.irjet.net p-ISSN: 2395-0072
© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 879
A Survey on Smart Devices for Object and Fall Detection
Sakshi Dudhal1, Komal Dayma2, Abhishek Mathukiya3, Namaha Mulki4 , Mohan Kumar 5
1,2,3,4B.E. Student, Dept. of Electronics and Telecommunication, Atharva College of Engineering, Mumbai, India
5Professor, Dept. of Electronics and Telecommunication, Atharva College of Engineering, Mumbai
----------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - — Elderly falls almost invariably result in major
health problems, as well as a loss of physical fitness. As
technology advances, we have more options for protecting
the elderly. The use of low-power components allows for the
creation of a wearable alerting device. Sensors have made
sensor system design and deployment easier. The Global
Positioning System (GPS) makes it easier to find the elderly.
If you fall, we're constructing a fall detector with sensors
and a microcontroller that will send an SMS to concerned
people with your location so they can get help right away.
We are developing an object detector that will inform the
user of impediments when their vision acuity deteriorates
with age, and it can also be utilized by blind persons.
Key Words: Smart Glasses, Ultrasonic Sensors, Blind
People, Object detection, Accelerometer, Gyroscope
1.INTRODUCTION
Falling is one of the most dangerous things that may
happen to an aged person. With the ever-increasing
elderly population, there is a pressing need for the
development of fall detection systems, which is why we
are offering a cheap fall detector that can not only deliver
a fall warning but also the location where the fall occurred.
Because we believe that prevention is always better than
treatment, we've also included obstacle detection in our
project. Smart glasses are a representation of this. A pair
of glasses with an obstacle detecting module in the center,
a processing unit, and an output device make up this
device. Traditional navigation devices, such as the blind
cane, determine direction by tapping the ground or
walking around the object; the structure is simple, single
function, easy to use; however, the secondary effect is not
readily apparent; in fact, when using the blind, many
problems arise, such as poor road conditions, uneven
surfaces, and hanging in front of obstacles; ordinary cane
cannot be proven accurate, posing a serious threat to the
safety of blind Travellers. A smart ultrasonic glasses for
blind people consists of a pair of wearable glasses,
ultrasonic sensors for detecting obstacles in the blind
man's path, a buzzer to give sound in the direction of the
obstacle from the man, a central processing unit consisting
of Arduino NANO which takes the information from the
sensor about the obstacle distance and processes the
information according to the coding done and sends the
output through the buzzer, and power supply is provided
by a battery. The sensor is placed between the top bar and
bridge of the optical glasses. All of the components are
wired to the central unit by single strand copper wires,
and the central unit is powered by a USB connection.
Ultrasonic sensors will be the ideal sensors to utilize since
ultrasound has a strong point, the energy consumption of
a slow wave travelling in the medium over a relatively
long distance. As a result, it is frequently used to measure
distances across long distances. At the same time,
ultrasound for objects in the dark, dust, smoke,
electromagnetic interference, poisonous, and other hard
situations has a degree of adaptability, with a wide variety
of applications. The ultrasonic sensor is attached to the
glasses in a perpendicular position. As the blind man
approaches the obstruction, the distance sent by the
sensors to the central unit decreases. Many navigation
devices now include seeing-eye guide dogs, guide dogs
who can see to some extent, despite the fact that the
journey is to protect the safety of the blind. However,
there are still some issues: training a guide dog is more
difficult, and it usually takes 3-6 months; however,
training a skilled guide dog takes about two years; in
addition, with dog daily life consumer spending, the cost it
takes to reach the million; and guide dogs have a limited
life cycle. ultrasonic glasses according to the requirements
are relatively inexpensive, resulting in a device that is
affordable to everyone. These smart glasses are quite
simple to use and comprehend. If a blind person uses it for
2-3 times, he or she will understand how it works and will
be able to handle it effortlessly
2.PROPOSED PROTOCOL
If a fall is detected, an alert is triggered, and the system
responds immediately by sending a warning and location
to the person responsible for the old person's care. A
gyroscope and an accelerometer sensor are included
within the MPU6050 sensor module. The gyroscope
determines the direction, while the accelerometer offers
angle information such as X, Y, and Z-axis data. The
magnitude of the acceleration will be compared to the
threshold value to detect the fall. If a fall is detected, the
gadget sends an email and a notification to the individual
concerned. To deliver a notification with the IoT App, a
Node MCU ESP8266 is utilized as a microcontroller and
Wi-Fi module. The processing unit is coupled to the
obstacle detecting module and the output device. A
ultrasonic sensor serves as the obstacle detection module,
while a control module serves as the processing unit, and a
buzzer serves as the output unit. The control unit activates
the ultrasonic sensors, which gather information about the
barrier in front of the man, analyses it, and then provides
the result through the buzzer. In this project, a sensor

detects an object from a distance, and if it is within 30 cm,
it emits a sound and alerts the user; if it is closer, it emits a
louder sound.
3.LITERATURE REVIEW
Diverse review publications provide an overview of the
evolution of fall detection from various perspectives. It is
vital to re-illustrate the trends and progress on a regular
basis due to the rapid development of smart sensors and
related analytical methodologies. From 2014 through
2020, we selected the most highly referenced review
papers. The trends, problems, and advancement in this
discipline are demonstrated in these selected review
papers. Author-Chaudhuri et al. (2014) examined fall
detection devices for persons of all ages from a variety of
viewpoints, including background, objectives, data
sources, eligibility criteria, and intervention approaches. A
total of almost 100 papers were chosen and examined. The
studies were separated into groups based on a variety of
factors, including the age of the individuals, the technique
of evaluation, and the equipment employed in detecting
systems. They pointed out that the majority of the
research were based on made-up data. [1] Author -Zhang
et al (2015) conducted another survey that focused on
vision-based fall detection systems and their
corresponding benchmark data sets, which have not been
covered in previous evaluations. Individual single RGB
cameras, infrared cameras, depth cameras, and 3D-based
systems using camera arrays were classified as vision-
based approaches to fall detection. Because such systems
rely on a large number of cameras positioned from various
angles, occlusion issues are often mitigated, resulting in
lower false alarm rates. Depth cameras have grown in
popularity because, unlike RGB camera arrays, they do not
require extensive calibration and are less obtrusive in
terms of privacy. Zhang et al. (2015) also looked at
various fall detection systems based on the individuals'
activity/inactivity, shape (width-to-height ratio), and
motion. While the review provides an in-depth look into
vision-based systems[2], The benchmark data sets
acquired by Microsoft Kinect and related cameras were
examined by Author-Cai et al (2017). They looked at 46
publicly available RGB-D data sets, with 20 of them being
widely used and acknowledged. They compared and
emphasized the properties of all data sets in terms of
application appropriateness. Electronics have become
more compact and less expensive as a result of continual
and rapid development. [3] Author-Igual et al (2013), for
example, found that low-cost cameras and accelerometers
embedded in cellphones may be the most practical
technology solution for fall detection research. Igual et al.
(2013) [4]identified two significant trends in how
research in this subject is evolving, notably the use of
vision and smartphone-based sensors for input and
machine learning for data processing. In addition, they
identified three major challenges: I real-world deployment
performance, (ii) usability, and (iii) acceptance. The term
"usability" refers to how useful a technology is to elderly
people. Falin Wu is the author of this piece. She proposed a
method and system for fall detection in this research,
which is based on a combination of information collected
from several sensors in the wearable device. [5] Author
Yuxi Wang proposes WiFall, a device-free fall detection
system that uses Channel State Information as an indicator
in this work. WiFall is designed to detect old people falling,
but it can also detect other actions. In extensively
deployed off-the-shelf WiFi infrastructure, WiFall takes
advantage of the physical layer Channel State Information
(CSI). To show the WiFall servers' viability and
effectiveness, we use commodity 802.11 laptops. 11n NICs
and do extensive tests in three different situations with
varied Tx-Rx configurations. WiFall's experimental results
suggest that it can detect falls with reasonable accuracy
and a low false alarm rate. At this time, WiFall is capable of
detecting the most typical daily behaviors such as walking,
sitting, standing up, and falling. In the future, we will
consider more particular activities. WiFall is currently
developed for and tested with only one single person in
the area of interest, similar to other device-free activity
identification systems that use wireless signals. It is now
difficult to distinguish a person's activity from that of
other users. When numerous persons are doing different
things at the same time, their movements will have a
mutual effect on signal transmission. When only one
person is undertaking activities, the positions of other
items will also have an impact on the signal propagation
paths. As a result, proposing a comprehensive propagation
model that takes into account the interaction between
signal fluctuation and numerous human activities is not
straightforward. Meanwhile, because there are numerous
combinations when considering different numbers,
activities, and positions of objects, building the training
database using learning methods is too expensive.
Nonetheless, we continue to believe that WiFall may be
used to critical use cases and that wireless technologies
will greatly benefit the human healthcare industry. [6]
Himadri Nath Saha is the author (2016) To help visually
impaired persons overcome their difficulties, this study
introduces a Smart Vision system that gives them with
quick and easy support. The major goal of this project is to
create a low-cost, reliable, portable, and user-friendly
solution for persons who are visually impaired. The
product will be an assistive buddy for visually impaired
users, with functions such as voicing out the current date
and time, current weather, top 10 news items for the day,
OCR, colour detection, and obstacle detection using
ultrasonic sensors. The Smart Vision System's trial results
suggest that it can significantly improve the user's
experience. As a result, it can be used as a consumer
device to assist visually impaired persons. [7]Author-
Jinqiang Bai (2018) This research offers a revolutionary
ETA (Electronic Travel Aids)-smart guiding device in the
shape of a pair of eyeglasses for giving these people
efficient and safe assistance to overcome the problem of
travelling for the sight impaired. A unique multi-sensor

fusion based obstacle avoiding method is proposed, which
uses both the depth sensor and the ultrasonic sensor to
overcome the issues of recognizing small impediments
and transparent obstacles, such as the French door. Three
types of audio signals have been developed for completely
blind people to help them determine which way to travel.
Visual augmentation that uses the AR (Augment Reality)
approach and incorporates the traversable direction is
used for persons who are nearsighted. The prototype,
which consists of a pair of display glasses and a number of
low-cost sensors, has been constructed, and its efficiency
and accuracy have been evaluated by a number of people.
[8] Ankita Bhuniya is the author (2017) presented a
study on smart eyewear obstacle detection, Blind mobility
is one of the most significant obstacles that visually
impaired people face in their daily lives. The loss of their
eyesight severely limits their lives and activities. In their
long-term investigation, they usually navigate using a
blind navigation system or their gathered memories. The
major goal of this project is to create a low-cost,
dependable, portable, user-friendly, low-power, and
robust navigation solution. This paper (Smart Glasses for
Blind People) is intended for people who are visually
challenged. It features a built-in sensor that sends out
ultrasonic waves in the direction the person is moving by
scanning at a maximum range of 5-6 meters and 30
degrees. The sensor identifies the impediment and
communicates the information to the gadget, which
generates an automated voice in the earphone attached to
the person's ear. [23] G. Sahithya, K. Sahithya, K.
Sahithya, K. Sahith (2019) They describe an electronic
gadget for obstacle detection and facial recognition to aid
visually impaired individuals in social interactions in this
paper. Blind persons have poor eyesight, making it
difficult for them to notice others in society, and this
device assists the user in walking without clashing with
any impediments in their way. The device is a pair of
smart glasses with an ultrasonic sensor, a Raspberry Pi
camera, and a Raspberry Pi installed. The ultrasonic
sensors are connected to a Raspberry Pi, which receives
data signals from the sensors for additional processing
and detects impediments up to 1000cm away from the
user. According to the database list, a Pi camera is used to
recognize the person in front of the sight impaired The
aforementioned survey studies primarily focus on the
many types of sensors that can be utilized for fall detection
and obstacle detection.
4. CONCLUSIONS
The fall detector may detect a physically challenged
person's fall and send a notification to the concerned
person/doctor along with the location. Also, in sectors
such as glassware, it can be used to detect falls of fragile
items to prevent damage. As people's vision deteriorates
with age, smart glasses can be used to detect impediments
in front of them and inform the user, preventing collisions
and reducing injuries. It can also be utilized by those who
are blind.
5. ACKNOWLEDGEMENT
Team members would like express our deep appreciation
and gratitude to Atharva College Of Engineering (ACE) and
all those who support us to complete this project. Special
gratitude to our supervisor Prof. Mohan Kumar for his
contribution and help to coordinate our project especially
in writing this report. In addition, the team members
would like to extend thanks to Principle S.P. Kellurkar,
Atharva college of Engineering for supporting us in this
project by providing the Guidance of teachers and online
classes for doubt discussions. Finally, no words can
describe our huge gratitude and appreciation to our
parents and family for their tremendous encouragement
and support throughout this challenging and great journey
of the project.
6. REFERENCES
[1] Chaudhuri S., Thompson H., and Demiris G. (2014).
Fall detection devices and their use with older adults: a
systematic review. J. Geriatr. Phys. Ther. 37, 178. doi:
10.1519/JPT.0b013e3182abe779
[2] Zhang Z., Conly C., and Athitsos V. (2015). “A survey
on vision-based fall detection,” in Proceedings of the 8th
ACM International Conference on PErvasive Technologies
Related to Assistive Environments (Las Vegas: ACM), 46.
doi: 10.1145/2769493.2769540
[3] Cai Z., Han J., Liu L., and Shao L. (2017). RGB-D datasets
using Microsoft Kinect or similar sensors: a survey.
Multimedia Tools Appl. 76, 4313–4355. doi:
10.1007/s11042-016-3374-6
[4] Igual R., Medrano C., and Plaza I. (2013). Challenges,
issues and trends in fall detection systems. Biomed. Eng.
Online 12, 66. doi: 10.1186/1475-925X-12-66.
[5]Falin Wu, Hengyang Zhao, Yan Zhao, Haibo Zhong,
"Development of a Wearable-Sensor-Based Fall Detection
System", International Journal of Telemedicine and
Applications, vol. 2015, Article ID 576364, 11 pages, 2015.
https://doi.org/10.1155/2015/576364
[6] Wang Y., Wu K., and Ni L. M. (2017b). Wifall: device-
free fall detection by wireless networks. IEEE Trans.
Mobile Comput. 16, 581–594. doi:
10.1109/TMC.2016.2557792 Control, Automation,
Robotics and vision(ICARCV),2016 14th Internatonal
Conference,2016.
Electronics(ICCE),2016 IEEE International
Conference,2016.
[7] Himadri Nath Saha,Ratul Dey,Shopan DeyOctober
2017DOI:10.1109/IEMCON.2017.8117194Conference:

Information Technology, Electronics and Mobile
Communication Conference (IEMCON), 2017 8th IEEE
Annual At: Vancouver, BC, Canada
[8] “Smart guiding glasses for visually impaired people” in
indoor environment Jinqiang Bai, Shiguo Lian, Zhaoxiang
Liu, K. Wang, Dijun Liu Published 2017
Computer Science
IEEE Transactions on Consumer Electronics
[9] T.O.Hoydal,J.A.Zelano,”An alternative mobility aid for
the blind :the ultrasonic cane”, Bioengineering Conference
Proceedings of the 1991 IEEE Seventeenth Annual
NorthEast,1991.
[10]Chinese Author “An intelligent auxiliary system blind
glasses”, CN106937909A, 11th July,2017.
[11] Humberto Orozco Cervantes “Intelligent glasses for
he visually impaired”, US20150227778A1,13th Aug,2015.
[12] Hsieh Chishenng “Electronic talking stick for blind”,
US5097856A,24th March,1992
[13]J. Y. Hwang, J. M. Kang, and H. C. Kim, “Development
of novel algorithm and real-time monitoring ambulatory
system using bluetooth module for fall detection in the
elderly,” in Proceedings of the 26th Annual International
Conference of the IEEE Engineering in Medicine and
Biology Society (IEMBS '04), vol. 1, pp. 2204–2207, San
Francisco, Calif, USA, September 2004.
View at: Publisher Site | Google Scholar
[14]A. Bueno-Cavanillas, F. Padilla-Ruiz, J. J. Jiménez-
Moleón, C. A. Peinado-Alonso, and R. Gálvez-Vargas,
“Risk factors in falls among the elderly according to
extrinsic and intrinsic precipitating causes,” European
Journal of Epidemiology, vol. 16, no. 9, pp. 849–859, 2000.
[15]M. E. Tinetti, W. L. Liu, and E. B. Claus, “Predictors
and prognosis of inability to get up after falls among
elderly persons,” The Journal of the American Medical
Association, vol. 269, no. 1, pp. 65–70, 1993.
[16]E. M. Bertera, B. Q. Tran, E. M. Wuertz, and A.
Bonner, “A study of the receptivity to telecare technology
in a community-based elderly minority population,”
Journal of Telemedicine and Telecare, vol. 13, no. 7, pp.
327–332, 2007.
[17]J. Fleming and C. Brayne, “Inability to get up after
falling, subsequent time on floor, and summoning help:
prospective cohort study in people over 90,” British
Medical Journal, vol. 337, no. 7681, pp. 1279–1282, 2008.
[18]D. Kunkel, R. M. Pickering, and A. M. Ashburn,
“Comparison of retrospective interviews and prospective
diaries to facilitate fall reports among people with stroke,”
Age and Ageing, vol. 40, no. 2, pp. 277–280, 2011.
[19]U. Lindemann, A. Hock, M. Stuber, W. Keck, and C.
Becker, “Evaluation of a fall detector based on
accelerometers: a pilot study,” Medical and Biological
Engineering and Computing, vol. 43, no. 5, pp. 548–551,
2005.
[20]M. Kangas, A. Konttila, P. Lindgren, I. Winblad, and
T. Jämsä, “Comparison of low-complexity fall detection
algorithms for body attached accelerometers,” Gait &
Posture, vol. 28, no. 2, pp. 285–291, 2008.
[21]Q. T. Huynh, U. D. Nguyen, S. V. Tran, A. Nabili, and
B. Q. Tran, “Fall detection using combination
accelerometer and gyroscope,” in Proceedings of the
International Conference on Advances in Electronics
Devices and Circuits (EDC '13), Kuala Lumpur, Malaysia,
2013.
View at: Google Scholar
[22]J. Klenk, C. Becker, F. Lieken et al., “Comparison of
acceleration signals of simulated and real-world backward
falls,” Medical Engineering & Physics, vol. 33, no. 3, pp.
368–373, 2011.
[23] Bhuniya, A., Laha, S., Maity, D.K., Sarkar, A.,
Bhattacharyya, S. (2017). Smart glass for blind people.
Modelling, Measurement and Control D, Vol. 38, No. 1, pp.
102-110. https://doi.org/10.18280/mmc_d.380109*
[24] K. Sahithya, G. Lakshmi Tejaswi, K. Hari Gopal, B.
Pavan Karthik “A New Method For Recognition And
Obstacle Detection For Visually Challenged Using Smart
Glasses Powered With Raspberry Pi” Published Online
May 2020 in IJEAST (http://www.ijeast.com)

A Survey on Smart Devices for Object and Fall Detection

More Related Content

Similar to A Survey on Smart Devices for Object and Fall Detection (20)

More from IRJET Journal (20)

Recently uploaded (20)

A Survey on Smart Devices for Object and Fall Detection