Development of image processing based human tracking and control algorithm for a service robot
1. Development of Image Processing based
Human Tracking and Control Algorithm for
A Service Robot
2. Abstract:
This paper presents a human detection algorithm and an obstacle avoidance
algorithm for a service robot that provides a service tracking. The mobile robot
will have the ability to follow a human and avoid dynamically moving obstacles in
an unstructured outdoor environment. To detect a human by an Image processing,
we defined features of the human body in xml file and employed a support vector
data description method. In order to avoid moving obstacles while tracking a
person, we defined an ultrasonic obstacle sensor, each obstacle using the relative
distance between the robot and an obstacle. For smoothly by passing obstacles
without collision, a dynamic obstacle avoidance algorithm for the service robot is
implemented, which directly employed a real-time position vector between the
robot and the shortest path around the obstacle.
3. Objective:
An Image processing based system is used to detect
objects and to follow the path of the environment in
robotic systems .In this project, we use a Image
processing algorithm to detect a human. The Camera is
placed on the robot at torso height and scans an
environment at this height. Whenever a human is
detected, we use pattern recognition of various shapes
in clustered data scanned from a human torso.
4. Existing Method:
Proposed Method:
In the proposed method we will use Opencv image processing library in
order to detect the Human body in the video and track him accordingly
where as an ultrasonic sensor will used in order to detect the body distance
from the robot and any obstacle present and act accordingly.
In the existing method, the concept implemented was based on a non
reliable technology in real time, where in an outdoor environment there
are more disadvantages that the system can mislead if more humans are
in its path.
6. An ARM 11 architecture based Raspberry pi board is used
to implemented the concept, a USB camera will be
connected to the board.
Using Open Source Computer Vision library (OpenCV) will
train the human body shape and structure to the program.
Whenever a Human body is present in from the camera,
the algorithm will detect it and draw a rectangular around
the body for identification and starts its movements.
Obstacle Avoidance: If any obstacle is located between a
marathoner and the MSR and is moving slower than the
MSR, avoiding the obstacle will be done using the
ultrasonic sensor and simultaneously the robot will be
tracking the human.
7. ARM stands for Advanced RISC Machine
The ARM11 is based on the ARMv6 instruction
set architecture
Bi-endian – can operate in either little-endian or
big-endian format
Most devices today use little-endian
Actually uses two instruction sets – the 32-bit
ARM and the 16-bit Thumb
8. Raspberry Pi is a credit-card sized computer
that plugs into your TV and a keyboard.
It is a capable little computer which can be
used in electronics projects, and for many of
the things that your desktop PC does, like
spreadsheets, word-processing and games.
It also plays high-definition video. We want
to see it being used by kids all over the world
to learn how computers work, how to
manipulate the electronic world around
them, and how to program.
10. r8
r9/sb
r10/sl
r11
r12
r13/sp
r14/lr
r15/pc
r0
r1
r2
r3
r4
r5
r6
r7Register variables
Must be preserved
Arguments into function
Result(s) from function
otherwise corruptible
(Additional parameters
passed on stack)
Scratch register
(corruptible)
Stack Pointer
Link Register
Program Counter
The compiler has a set of rules known as a
Procedure Call Standard that determine how to
pass parameters to a function (see AAPCS)
CPSR flags may be corrupted by function call.
Assembler code which links with compiled code
must follow the AAPCS at external interfaces
The AAPCS is part of the new ABI for the ARM
Architecture
Register
- Stack base
- Stack limit if software stack checking selected
- R14 can be used as a temporary once value stacked
- SP should always be 8-byte (2 word) aligned
11. Camera plays a vital role in
automation purpose. The
camera is used for monitoring of
a room from a remote place.
The camera used is a USB
camera. Whenever the user
clicks on to video button on
loaded webpage, the
corresponding room video will
be streamed on to webpage .For
this purpose we use a MJPG
streamer. The below figure
shows the camera that has been
used for monitoring of a room.
12. The sensor is primarily
intended to be used in
security systems for
detection of moving objects,
but can be effectively
involved in intelligent
children’s toys, automatic
door opening devices, and
sports training and contact-
less-speed measurement
equipment.
13. This chip contains 4 enable
pins. Each enable pin
corresponds to 2 inputs.
Based on the input values
given, the device connected
to this IC works accordingly.
14. motors are used to
efficiently convert electrical
energy into mechanical
energy. Magnetism is the
basis of their principles of
operation. They use
permanent magnets,
electromagnets and exploit
the magnetic properties of
materials in order to create
these amazing machines
DC Motor
15. Implementation:
Obstacle Avoidance: If any obstacle is located between a marathoner and
the MSR and is moving slower than the MSR, avoiding the obstacle will be
done using the ultrasonic sensor and simultaneously the robot will be
tracking the human.
An ARM 11 architecture based Raspberry pi board is used to
implemented the concept, a USB camera will be connected to the board.
Using Open Source Computer Vision library (OpenCV) will train the
human body shape and structure to the program. Whenever a Human
body is present in from the camera, the algorithm will detect it and draw
a rectangular around the body for identification and starts its
movements.
16. Applications:
Conclusion:
Advantages:
Security
Industry
High Accuracy
Easy to implement
A marathoner service robotic system will be designed for human
detection . When the intruder is in front of the sensor than the MSR,
the MSR does not consider the intruder as an obstacle but using the
algorithm identifies the human body. Therefore, the MSR did not
show any avoidance behavior. By applying the modified technique an
advanced system will be developed.
17. References:
1. MarathonWorld. (2012). [Online]. Available: http://www.marathonworld.com
2. I. J. Cox and S. L. Hingorani, “An efficient implementation of Reid’s multiple
hypothesis tracking algorithm and its evaluation for the purpose of visual
tracking,” IEEE Trans. Pattern Anal.Mach. Intell., vol. 18, no. 2, pp. 138–150,
Feb. 1996.
3. J. K. Aggarwal and Q. Cai, “Human motion analysis: A review,” in Proc. IEEE Proc.
Nonrigid Articulated Motion Workshop, 1997, pp. 90–102.
4. J. MacCormick and A. Blake, “A probabilistic exclusion principle for tracking
multiple objects,” in Proc. 7th IEEE Int. Conf. Comput. Vision, 1999, pp. 572–
578.