Alive Human Body Detection system using an

Autonomous Mobile Rescue Robot

Sandeep Bhatia
Assistant Professor, ECE Deptt.
Raj Kumar Goel Institute of Tech.
Ghaziabad (U.P) India
Sandeepbhatia_1711@yahoo.co.in

Hardeep Singh Dhillon

Nitin Kumar

Assistant Professor, ECE Deptt.

Punjab College of Engg. & Tech.
Lalru Mandi, India
hardeepsingh.ec08@pec.edu.in

Assistant Professor, ECE Deptt.

Sunderdeep Engineering College
Ghaziabad (U.P) India
coolguynitin18@yahoo.co.in

Abstract In this paper, a new approach for detecting alive

humans in destructed environments using an autonomous
robot is proposed. Human detection in an unmanned area
can be done only by an automated system. Alive human
body detection system proposed a monitoring system using
ultrasonic sensors and camera to record, transmit and
analyze conditions of human body. The task of identify
human being in rescue operations is difficult for the robotic
agent but it is simple for the human agent. In order to detect
a human body, an autonomous robot must be equipped with
a specific set of sensors that provide information about the
presence of a person in the environment around. This work
describes an autonomous robot for rescue operations. The
proposed system uses an ultrasonic sensor in order to detect
the existence of living humans and a low-cost camera in
order to acquire a video of the scene as needed. Additional,
other sensors include temperature, fire and metal detector
works as bomb sensor to detect the presence of bomb in
Warfield and in rescue operations. Having detected a sign of
a living human, the ultrasonic sensor Triggers the camera to
show live scene. The video is then displayed on the screen.
This approach requires a relatively small number of data to
be acquired and processed during the rescue operation. This
way, the real-time cost of processing and data transmission
is considerably reduced. This system has the potential to
achieve high performance in detecting alive humans in
devastated environments relatively quickly and costeffectively. The detection depending on a number of factors
such as the body position and the light intensity of the scene.
Results show that the system provides an efficient way to
track human motion. The aim of this article is to present our
experience with various sensors designed and developed.
Keywords-Autonomous mobile robot, Human Detection,
Motion Detection, Mobile Robot, Navigation, Rescue,
Robotics, ultrasonic sensor, Urban Search and Rescue.

I.

INTRODUCTION

Disasters can disrupt economic and social balance of the

society. Natural disasters occur frequently nowadays.
Many human beings are victims of such occurrences.
Because of high rise buildings and other manmade
structures urban and industrial areas can be consider to be
more susceptible to disasters. These disasters can be
categorized into natural and human induced disasters.
Natural disasters include floods, storms, cyclones,
bushfires and earthquakes where as besides natural
disasters, the urban environment is prone to human
induced disasters such as transportation accidents,
industrial accidents and major fires. During such
calamities, especially disasters, in order to prevent loss of

life and property various essential services (like fire

brigades, medical and paramedical personnel, police) are
deployed. Some lose their lives because of not being
treated at time. According to the field of Urban Search
and Rescue (USAR), the probability of saving a victim is
high within the first 48 hours of the rescue operation,
after that, the probability becomes nearly zero. Generally,
Rescue People cannot enter into some parts / places of the
war field or in the earth quake affected areas. All of these
tasks are performed mostly by human and trained dogs,
often in very dangerous and risky situations. To avoid
such losses, a robotic system can perform well for
providing alert (detection) of human being.
The main purpose of the robot is to detect alive human
beings after the occurrence of natural calamities with the
help of Ultrasonic sensor. The robot based system will
sense the radiation of human being and condition the
sensed signal to communicate to the control section of
this robot. Based on the responded commands the robot
will react upon. The rescuer may become a victim who
needs to be rescued. This is why since some years mobile
robots have been proposed to help them and to perform
tasks that neither human, dogs nor existing tools can do.
For this project, we will focus only on robots which will
work in a disaster environment of manmade. The
proposed system uses an ultrasonic sensor in order to
detect the existence of living humans and a low-cost
camera in order to capture video of the scene as needed.
Having detected a sign of a living human, the ultrasonic
sensor triggers a camera to capture a video of the scene.
The simulated robot is assumed to have the capability to
determine its current location in real-time, to wirelessly
communicate with the rescue team, and to locally store
the status and location information about the trapped
victims in case the wireless communications link is
temporarily disconnected.
While detecting human being, there may be some
obstacle on the way of robot. In order to identify the
obstacle and to have an alternate path to perform its
defined task an ultrasonic detection is used which
effectively fulfills this operation.
Traditionally, equipped robots faced a lot of problems:
i) A very high communication cost was incurred due to
the large number of transmitted images to the operator.
ii) More than 25% of the communications between
Wireless robot and the control unit was extremely noisy

and therefore was useless. This eventually led to a loss of

communication between the robots and the operator. As a
result, the robots stopped working totally.
iii) A very high processing cost is also incurred by the
Capturing, storing, and transmitting a large number of
images.
iv) Third, there was a continuous need for illumination
due to the dark nature of these environments. This
requires a relatively large power supply, which is not
feasible in such situations.
II.

RELATED WORK

In this section, a brief discussion of some of the related

work is presented; focusing on the used approach and its
advantages and disadvantages. Remote Operated and
Controlled Hexapod (ROACH): [12] ROACH is a six
legged design that provides significant advantages in
mobility over wheeled and tracked designs. It is equipped
with predefined walking gaits, cameras which transmit
live audio and videos of the disaster site, as well as
information about locations of objects with respect to the
robots position to the interface on the laptop. Kohga:
University of Tokyo - The most complicated task for
most of the USAR robots has been working on a rough
terrain. Specialized robots have been designed for these
types of environments such as KOHGA the snake like
robot. The robot is constructed by connecting multiple
crawler vehicles serially, resulting in a long and thin
structure so that it can enter narrow space.
Quality work has been done in the field of robotics.
These robots came into existence in the early 21st century
but since then enormous improvements have been made
in the concept, design owing to which their capabilities
have improved significantly. Various rescue robots have
been developed and some of these are CRASAR
(Centre for Robot-Assisted Search and Rescue):
University of South Florida. This robot[10] was used for
first time in real conditions on 11th September 2001 in
the World Trade Centre disaster. Different sensors like
millimetre wave radar for measuring distance, a colour
CCD camera for vision and a forward-looking infrared
camera for the human heat detection are used in it.
Burion [6] presented a project that aims to provide a
sensor suite for human detection for the USAR robots.
This study evaluated several types of sensors for
detecting humans such as pyroelectric sensor, USB
camera, microphone, and IR camera. The pyroelectric
sensor was used to detect the human body radiation, but
its limitation was its binary output. The USB camera was
used for motion detection, but its limitation was its
sensitivity to changes in light intensity. The microphone
was used for long duration and high amplitude sound
detection, but it was severely affected by noise. Lastly,
the IR camera was used to detect humans by their heat
image, but it was affected by other nearby hot objects.
The main idea was to detect a change in the image scene
by checking the values of the pixels. Several images for

the scene were acquired and subtracted from each other to

discover if a motion has occurred. The used technique
was fairly efficient in detecting the victims. However, the
robot was not fully autonomous and was dependent on
the operator.
Gas analysis based bio-sensors [6] CO2 sensors allow
to detect the carbon dioxide emission, and even the
breathing cycle of a victim. It is thus possible to
determine if he is still alive but the disadvantage is that
the response time of a CO2 sensor is very slow and that
the sensor has to be very close to the victim to have
useful data because it is very directional and depends
much on the air conditions like humidity, temperature,
wind, and dust. This makes it difficult to use it in a
disaster area so this approach was not pursued in this
project. Like the CO2 sensor, SpO2 is used to determine
if somebody is still alive. It needs direct contact with the
person. SpO2 sensing of blood oxygen content requires
only the pressing of a small, cool, red light on any bare
inch of skin. It is not a common sensor in robotics. This is
not a commercially available sensor.
Greer, Kerrow, & Abrantes 2002, [9] represented a
thorough understanding of the urban disaster environment
and an appreciation for traditional search and rescue
techniques are crucial to determining the success of a
hovering robot solution. In this paper search and rescue
environment is described, the applications of robots in
urban search and rescue, an outline of robotic
competitions in simulating a real rescue environment is
described.
Bahadori [16] presents an analysis of techniques that
have been studied in the recent years for human body
detection (HBD) via visual information. The focus of this
work is on developing image processing routines for
autonomous robots operating for detecting victims in
rescue environments. The paper both discusses problems
arising in human body detection from visual information
and describes the methods that are more adequate to be
applied in a rescue scenario. Finally, some preliminary
experiments for such methods in recognizing rescue
victims are reported.
Pissokas [1] describe the social impact of urban
devastations has given rise to the field of Urban Search
and Rescue Robotics. The aim of this article is to present
our experience and experimental results with various
sensors designed and developed.
III.

BLOCK DIAGRAM

As shown in fig 1. This system consists of transmitter and

receiver unit. Furthermore transmitter unit consist of
rotational unit which has a specific set of sensors mount
on it and a microcontroller. Receiver unit consist of
camera which gets activated and starts capturing images
as soon as ultrasonic sensor detects motion of human
being and buzzer gets a beep and there is also an LCD
which is used to display the temperature, motion and
metal detection.

be changed by making necessary changes in the program

developed.
Start

Navigate

Ultrasonic sensor
checks for Motion

No
Ultrasonic signal?

Others sensors
gets activated

Yes
Buzzer gives a beep
Fig. 1 Human Body Detection System Based on Sensors

IV.

FLOW CHART

As shown in fig 2, In the flow chart of developed system

first the Robocar navigate in a open field and ultrasonic
sensor checks for motion if yes then buzzer gets a beep
and camera gets activated and acquire an image, at this
time others sensors get activated, this will show the
presence of human being and transmitter unit will send
the current location and information to the receiver end, if
No then Ultrasonic sensor again checks for motion. If
receiver unit detects motion then robocar takes 900 turn
either left or right.
V.

Stop

Camera gets activated

Acquire an image

Process an image

HARDWARE RESULTS

In order to simulate the robot, a laptop used T.V Tune

Card as well as LCD to display data interfaced wirelessly
to the Robot mechanism. A Robot is equipped with
following sensors and camera:
i) Bomb (Metal) sensor to detect the presence of
suspected material in Rescue operations.
ii) An ultrasonic sensor to detect human motion and
obstacles come in the way of Robot.
iii) Temperature and fire sensor to measure temperatures
and display them on LCD in the form of three states
High, Low and Medium.
iv)Camera to record and display data when sensor
triggers it.
According to the hardware developed, the buzzer beeps
as soon as ultrasonic sensor detects motion. The robocar
which otherwise follows a particular pattern stops for 810 seconds as soon as motion is detected. After some
delay when there is no motion the robocar again follows
the same pattern. The pattern which robocar follows can

Manually Capturing is started

No

Human
Detected? Yes
Yes

Send location and information to rescue team

Done

Stop
Fig 2. Flow chart of the Developed System

A.
Circuit Diagram of Transmitter unit using
ORCAD

Hardware of Transmitter and Receiver Unit

Fig. 5 & 6. Complete Hardware for the system

Fig. 3 Transmitter Circuit Diagram

B.

Fig. 7. Motion, Temperature and Metal Detection display on LCD

VI.

Circuit Diagram of Receiver unit using ORCAD

TRANSMITTER END PROTOCOL

Hurdle Detected..P2.1 (Active high)

Metal Detected.P2.0 (Active low)
Temperature sensor
Limit 1 .P2.2
Limit 2 ..P2.3 Both are active high

Fig. 4 Receiver Circuit Diagram

HARDWARE DEVELOPED

RF sending
10 P3.0
11 P3.1
12 P3.2
13 P3.3
H-Bridge
14 P3.4
15 P3.5 p (pins) All are connected to MCUunit
16 P3.6
17 P3.7
Relay P1.0
LED
P 1.1
Protocol
D3 D 2 D 1 D 0
0 0
Temp. Low
0 1
Medium..L1
1 0
Hot temperature.L2
0
1
0
1

No hurdle
Motion Detected
No metal
Metal detected
VII. SOFTWARE RESULTS

When the ultrasonic sensor detects a signal, the control

program orders the camera to display the surrounding

area. If a human is detected, the system sends its current

location to the rescue team in addition to the video
display if needs be. Figure 2. Shows the flowchart of the
system operation.
The Robot also has a wireless RF Transmitter and sends
the message to the Remote Location whenever it finds
any alive human. As soon as motion is detected, data is
taken serially through serial port. Since the sensor has a
digital output it sends logic 1 for motion detected and
logic 0 for no motion. As soon as logic 1 is sent, i.e.
according to the program developed a is transmitted
serially to the PC, the webcam gets activated and
manually capturing is activated.

wide range of sensors have been developed, but there are

many problems faced by them such as cost, size,
environment difficulties etc.
REFERENCES
[1]

[2]
[3]

[4]

Assembly language programming has used in order to

simulate the robot. We can also use MATLAB in order to
operate robocar.

[5]

APPLICATIONS

[6]

In military applications to detect the presence of

human being.

[7]

In Rescue operations where human reach is not

possible.

VIII.

In Medical applications to detect motion.

[8]

In Warfield affected areas, to detect the presence

of bomb.

[9]

IX.

CONCLUSION

The goal of this research was to provide a low cost rescue

robot for human detection in a disaster environment.
Though, the existing Urban Search and Rescue Robots
are equipped with various sensors, but the problem with
them is the cost. The sensors used in the development of
this project are easily available and cost effective.
In this paper, a new method for detecting surviving
humans in destructed environments using simulated
autonomous robot is proposed. The robot uses two levels
of sensing in order to achieve higher cost-effectiveness in
the detecting process in terms of the actual cost of
equipment, the processing cost, the communication cost,
the storage cost, and the power cost. The first level is an
ultrasonic sensor that is used as the primary sensor in
order to detect the existence of living humans in a scene.
The second level is a human body shape sensor. This
level uses low-cost web camera in order to confirm the
existence of a human shape. The robot is assumed to be
equipped with a simple Temperature and bomb sensor in
order to detect fire in Rescue scenario and suspected
metal respectively and a wireless communication link in
order to communicate with the rescue team whenever a
need arises.
X.

FUTURE SCOPE

Since the system developed is a low cost system therefore

it has a wide future scope. Though many systems with a

[10]
[11]

[12]
[13]

[14]
[15]

[16]
[17]

[18]
[19]

P i s s o k a s , J o h n a n d M a l c o l m , C h r i s Experiments with
Sensors for Urban Search and Rescue Robots Dept. of Computer
Science, University of Essex a n d Division of Informatics,
University of Edinburgh, Scotland UK, 2001..
Rufaida Shamroukh, Fahed Awad Detection of surviving humans
in destructed environments using a simulated autonomous robot
IEEE Transaction, March 24-26, 2009.
Carlos Marques, Pedro Lima, Rodrigo Ventura Semi-autonomous
robot for rescue operations Proceedings of the 2006 IEEE/RSJ
International Conference on Intelligent Robots and Systems,
October 9 - 15, 2006, Beijing, China.
R. Fuksis, M. Greitans, E. Hermanis Motion Analysis and
Remote Control System using Pyroelectric Infrared Sensors
IEEE, 2008. No. 6(86), PP. 69-72.
Jean Schultz, Jill L. Drury, Holly A. Yanco Evaluation of
Human-Robot Interaction Awareness in Search and Rescue
IEEE, 2004, PP. 2327-2332.
Steve Burion Human Detection for Robotic Urban Search and
Rescue Info science database of the publications and research
reports. Technical Report, February, 2004. Record number 29999.
Kun-Mu Chen, Yong Huang, Jianping Zhang and Adam Norman
Microwave Life-Detection Systems for Searching Human
Subjects Under Earthquake Rubble or Behind Barrier IEEE
Transactions, Biomedical Engineering, VOL. 27, NO. 1, January
2000, PP. 105-114.
Binoy Shah and Howie Choset. "Survey on Urban Search and
Rescue Robotics" Journal of the Robotics Society of Japan,
Vol.22, No.5, Page.582-586, 2004.
Greer, D., Kerrow, P. M., & Abrantes, J. Robots in urban Search
and Rescue Operations Australasian Conference on Robotics and
Automation, Auckland, 27-29 November, 2002, PP. 25-30.
Casper, J. Human-Robot Interactions during the Robot-Assisted
Urban Search and Rescue Response at the World Trade Center,
IEEE, 2003, PP.367-385.
Afak Sekmen, Ali S., Kawamura, Kazuhiko, and Wilkes, Mitch
An Application of Passive HumanRobot Interaction: Human
Tracking Based on Attention Distraction IEEE, Vol. 32, No. 2,
March 2002, PP. 248-259.
Amerada, T., Yams, T., Igarashit, H., & Matsunos, F.
Development of the Snake-like Rescue Robot KOHGA IEEE,
2004, PP. 5081-5086.
Ying-Wen Bai, Li-Sih Shen and Zong-Han Li Design and
Implementation of an Embedded Home Surveillance System by
Use of Multiple Ultrasonic Sensors IEEE Transactions on
Consumer Electronics, Vol. 56, No. 1, February 2010, PP. 119124.
Kai-Rui Zhao, Xin-Min Wang, Van Li, and Xiang Yu, "A Lifedetection System for Special Rescuing Robots" IEEE, 2006.
Miyama, S., Imai, M. & Anzai, Y. (2003). Rescue Robot under
Disaster Situation: Position Acquisition with Omni-directional
Sensor, in Proceedings of the 2003 IEEERSJ Int. Conference on
Intelligent Robots and Systems, Las Vegas, Nevada, October.
Bahadori, Shahram., Iocchi, Luca. Human Body Detection in the
RoboCup Rescue Scenario Department of informatics, Rome
Italy.
Roger, B., Hong, T., Madhavan, R., & Weiss, B, 3D Range
Imaging for Urban Search and Rescue Robotics Research, in
Proceedings of the 2005 IEEE, International Workshop on Safety,
Security and Rescue Robotics, Japan, PP. 164-169, June 2005.
Hong liu, Ning dong, Hongbin zha Omni-directional Vision
based Human Motion Detection for Autonomous Mobile Robots
IEEE, 2006.
Song, Byunghun., Choi , Haksoo and Lee, Su, Hyung,
Surveillance Tracking System Using Passive Infrared Motion
Sensors in Wireless Sensor Network IEEE, PP. 463-816.