Upload
shanmuga-raja
View
221
Download
0
Embed Size (px)
Citation preview
8/2/2019 06060330
1/6
Wireless Indoor Surveillance Robot
Hou-Tsan Lee, Wei-Chuan Lin, Ching-Hsiang Huang, Yu-Jhih Huang
Department of Information Technology, TakMing University of Science and Technology
Abstract:Self-propelled patrolling vehicle can patrol periodically in the designed area as a surveillance robot to ensure the safety
like men do. The proposed robot based on the self-propelled vehicle not only can save manpower but also ensure the
operation of surveillance being well performed. Due to the limitation of manpower and the fixed camera positions,using surveillance is different from the traditional patrolling system. The paper proposes a self-propelled patrolling
vehicle which can move automatically to a wider range and record the monitored image within a predefined patrolling
route to improve the performance of the traditional patrolling system. Besides, the surveillance robot can be connected
to the mobile device or website on Internet at anytime and anywhere. Furthermore, the vehicle can be remote controlled
by the instruction sent form the server or Smartphone to move to the position to get the indoor image we want. On the
other hand, the position of self-propelled vehicles can be detected by the RFID readers mounted on the wall of the
patrolling path as a feedback. The IP-CAM is also mounted on the proposed robot to record the images and transmit
them back to the server via WiFi system for face tracking and discriminating analysis. As an alarm report, the proposed
surveillance would use the build-in MSN module to notice users of the predefined events when happened. Experimentalresults are given in the paper to validate its performance.
Keywords: Surveillance RobotWireless IPCAMRFID readerface detection
1. INTRODUCTIONAs the incidents of theft grew more frequent, the
applications of security systems are more popular than
ever to prevent the damages caused by theft whether at
home or working places. The traditional security systemgives some protection via fixed cameras but still has
some dead zone cannot be monitored. Therefore, this paper proposes mobile security monitoring system to
improve the security of the traditional system. The
comparison diagram between the proposed andtraditional security system is shown in Fig. 1. A
self-propelled patrolling vehicle acts as a security
patroller in the security system, which can monitor not
only the fixed area but also those dead zones of the
traditional fixed surveillance system. The remote
monitoring capabilities can also be enhanced by usingthe wireless network to control the surveillance robot.
Besides, the face detection system is also adopted to
record and recognize the intruders. [1][2][3] No matter
where the user is, he can monitor the indoor status byusing network.
C
Fig. 1. The traditional and proposed security system
OpenCV is an open source, and it can be used in
most of the platforms such as the operating system of
Linux and Windows. [4] OpenCV is developed by theIntel Corporation for image processing and it provides
interface to create pictures by C programming language,
etc.. It can be used to handle object tracking, face
recognition, texture analysis, and the dynamic image processing of webcam. [5] In this paper, OpenCVtechnology is used for face detection. RFID system
identifies the object by using the radio frequency
technology to read the information stored in the small
IC chip attached on the object. [6][7] In this way, RFID
system can be used to track object by processing a
non-contact, short-range automatic identificationtechnology. The RFID system is adopted in the
proposed scheme including tags, reader, and the host
computer to record the position of the surveillance robot.
Tag is a data storage device; the Reader reads
information from the Tag and sends to the host
computer for further processing. When sensing the radiowaves emitted by the reader, the tag produces a
"magnetic induction" to trigger the RF transmitter
module to send the built-in EEPROM information back
to the reader. The reader then transmits the information
to host computer through the RS-232, or USB interface.
There are two kinds of RFID tags such as active and
passive. The passive type is chosen in the proposed
scheme.
Adopting the proposed surveillance robot of the
paper, the security of indoor surveillance is upgraded.
The self-propelled vehicle will give more informationthan the traditional security system. Experimental
results are also provided to validate the performance ofthe proposed system.
SICE Annual Conference 2011September 13-18, 2011, Waseda University, Tokyo, Japan
PR0001/11/0000-2164 400 2011 SICE- 2164 -
8/2/2019 06060330
2/6
2.SYSTEM ARCHITECTUREThe proposed self-propelled monitoring and
surveillance vehicle can be divided into following parts:wireless IPCAM video capture system, face detection
system, remote monitor and alarm transmitter system,
RFID position detection systems, and wirelessmonitoring and control system. [8][9][10] The diagram
of system architecture is shown in Fig. 2.
Fig. 2 The architecture of the proposed system
The self-propelled vehicle uses RFID technology to
control the moving direction. RFID tag is installed in
the right-hand side of the self-propelled vehicle. When
the self-propelled vehicle moves to a RFID reader on
the predefined patrolling path, the RFID reader detects
the RFID tag and sends the signal back to the server to
show the detected position on the map to indicate the
status of the self-propelled vehicle. Smartphone(Android) can also receive the position of the vehicle or
send control commands through the PC server to control
the direction of self-propelled vehicle. Face detectionsubsystem uses the Intels OpenCV library to detect
human face in the monitored place. [11][12] There are
two wireless IPCAMs mounted on the self-propelled
vehicle to monitor the front and rear of the vehicle for
face detection. If a human face is detected in the image
file, the server would trigger the MSN agent to sendwarning message to the user. User can use the PC,
notebook, or Smartphone to monitor the situation on
line and/or drive the self-propelled vehicle to the spots
where the users want it to be. The system description isshown in Table 1.
The PC server provides the remote monitor websitewhich is installed with Microsoft IIS and the ASP.NET
web program. Users can connect this website for
monitoring the place via wireless IPCAM by PC,
Notebook, or Smartphone. The RFID position detection
system as shown in Fig. 3, the RFID tag is mounted onthe right-hand side of the self-propelled vehicle. By
detecting tags, a predefined routing path can be trailed.
The detected information is also displayed on the map
of the PC monitor or on the display of the Smartphone.
The server can also send guidance control command to
the self-propelled vehicle for the next position of theRFID reader.
Fig. 3 RFID position detection system
The self-propelled vehicle is controlled through the
WiFi module by receiving socket data from the server.
The control center of the self-propelled vehicle is
DFRduino RoMeo 328 microcontroller. The
microcontroller receives control command through thesocket data of the server to control the motion of
self-propelled vehicle. Generally, the patrolling path ofthe self-propelled vehicle is predefined. If the warning
message is detected, users can guide the self-propelled
vehicle by remote control through Smartphone as
shown in Fig. 4.
Fig. 4 Smartphone control system
3.THE HARDWARE ARCHITECTURE OFTHE SELF-PROPELLED VEHICLE
Fig. 5 shows the hardware architecture of the
self-propelled vehicle. As previous mentioned, the
microcontroller of the self-propelled vehicle is
DFRduino RoMeo 328. There are 14 sets of digital I/O
interface (including 6 sets of PWM output), 8 sets of
emulating analog I/O interfaces, 2 pairs of DC motordrives, 6 input buttons in the Atmega168 based
microcontroller.
- 2165 -
8/2/2019 06060330
3/6
Fig.5 The hardware architecture of theself-propelled
vehicle
The bottom layer of the self-propelled vehicle
including four 3V DC motors, DFRduino RoMeo 328microcontroller, WiFi module, RFID tag and charger
interface is shown in Fig. 6. When the self-propelled is
going to run out of power, it would detect the position
of charger and go to it automatically for charging. The
WiFi module receives the control command from theserver or Smartphone. The RFID tag in the
self-propelled vehicle is used to detect its own position
in the routing path and display the position of theself-propelled vehicle on the server.
Fig.6 The sketch of bottom layer
The first layer of the self-propelled vehicle is theelectricity detection PCB and power supply module as
shown in Fig. 7. The power supply module uses the 12V
battery to provide the power for two D-LINK wireless
IPCAM (5V 1.2A) and the DFRduino RoMeo 328
microcontroller (12V). The electricity detection PCB is
used to detect the battery status and shows the result bydisplaying the LED in red/green light.
Fig. 7 The sketch of first layer
The second layer of the self-propelled vehicle is the
battery, PCB and two D-LINK wireless IPCAM as
shown in Fig. 8. The regulator mounted on PCB should
guarantee the steady output power of 12V. Therefore,
the regulator on PCB can prevent the power from thecharger to damage components in the self-propelledvehicle.
Fig. 8 The sketch of second layer
The third layer of the self-propelled vehicle is simply
the solar panel. The realized implementation of
self-propelled vehicle is shown as Fig. 9.
Fig. 9 The implementation of the self-propelled vehicle
4.EXPERIMENTAL RESULTSThe wireless IPCAM mounted on the self-propelled
vehicle should be specified IP by login the account and password given by the manufacturer. When the
self-propelled vehicle is patrolling, the image files of
pictures would be captured and stored in the temporary
memory of the IPCAM. The server then get the imagefiles via WiFi system and show them on the display as
below.
Fig. 10 Display result of local wireless IPCAM (left:
- 2166 -
8/2/2019 06060330
4/6
front; right: rear)
Fig. 11 shows the face detection application program
implements by JNI provided by OpenCV. [11] There are
100 pictures used for face detection. In face detection
process, bigger size of the search window would
increase the failure rate of face detection. The resolutionof the picture is also an important factor of the facedetection. The higher resolution would increase
successful rate of face detection. In the indoor
environment, input file of image resolution is chosen as
320*200 for each picture. And, if the left/right detection
angle between face and IPCAM is greater than 30
degrees, the face detection method is useless. It is also
failed if the down angle between face and IPCAM is
greater than 15 degrees and the up angle between face
and IPCAM is greater than 30 degrees. On the other
hand, the distance between image and IPCAM would
also influence the resolution of face detection, more
than 2.25 meter is not available. If the resolution isincreased to 640*480, the maximal distance between
image and IPCAM can be extended to 4.2 meter. The
test result of the limitations is shown in Tab. 2 with the
testing process shown in Fig. 12.
Fig. 11 Face detection application program
Fig. 12 The limit angle of face detection
When a human face is detected, the MSN system will
notify the user by sending messages by MSN as shown
in Fig. 13. Then, the message will be shown on the
MSN and/or on the Smartphone of the user as shown inFig. 14.
Fig. 13 The warning message of face detection viaMSN
(a) Warning message on MSN
(b) Warning message on Smartphone
Fig. 14 shows the warning message appeared on the (a)
MSN or (b) Smartphone.
The tag of Self-propelled patrolling vehicle would be
detected by a series of RFID readers mounted on the
patrolling path to guide the vehicle. (There are 6 RFID
readers in Fig. 2) As the self-propelled vehicle being
detected by the RFID reader, this information would be
sent back to the PC server and record the time and
position of the vehicle simultaneously. And, the position
of the vehicle will be marked on the map and shown on
the monitor of PC server or the display of the
Smartphone as shown in Fig. 15(a) and/or (b),
- 2167 -
8/2/2019 06060330
5/6
respectively.
(a) The display on monitor
(b) The display on Smartphone
Fig. 15 The position of the self-propelled vehicle
5.CONCLUSIONThe proposed system is implemented by a PC server,
a self-propelled vehicle and some small smart devices
via wireless networks to provide the functions of
surveillance and remote control. To summarize, there
are some conclusion of the proposed system can be
addressed as bellows:
The wireless IPCAM being equipped with in amobile vehicle to obtain wider range of
monitoring.
The warning message can be sent back to thesecurity center and/or the user by MSN and/or
Smartphone.
Face detection technique is adopted in theproposed system to identify the intruders.
The self-propelled vehicle can be navigated byMSN and/or Smartphone if necessary and
displayed its position by RFID readers mounted
on the wall along the patrolling route.
The proposed indoor surveillance system is
developed with some proper design described in
previous section. With experimental results, the
feasibility of the proposed scheme is validated.
ACKNOWLEDGE
This paper is sponsored by the projects of NSC
99-2221-E-147-004- and NSC 100-2221-E-147-001- inTaiwan.
REFERENCE
[1] Chien-Yu Wang, Utilization Of DeformableTemplates In Real-Time Face Tracking System, master
thesis, National Sun Yat-sen University, p22~39, July,
2007.
[2] Yao-Zhang Xie, A Study of Real-Time FaceTracking with an Active Camera, master thesis,
National Sun Yat-sen University, p6~21, April, 2005.
[3] Viola Paul, J. Jones. Michael, Rapid ObjectDetection Using a Boosted Cascade of Simple
Features, IEEE CVPR, Vol.1, NO. 2, p511~518, Dec.
2001.
[4] Min Zuo Guangping Zeng Xuyan Tu, College ofComputer and Information Engineering, Beijing
Technology and Business University, China, Research
and improvement of face detection algorithm based on
the OpenCV, ICISE 2010, p1413, Dec. 2010
[5] Jung-Hyun Park Kwee Bo Sim , Dept. of Electr. &Electron. Eng., ChungAng Univ., Seoul, A design of
mobile robot based on Network Camera and sound
source localization for intelligent surveillance system,
ICCAS 2008, p674, Oct. 2008.Introduction to the RFID,
http://www.cc.ntu.edu.tw/chinese/epaper/0002/2007092
0_2005.htm
[6] Yang Xiao Yanping Zhang, Dept. of Comput. Sci.,Univ. of Alabama, Tuscaloosa, AL, USA, Surveillanceand Tracking System with Collaboration of Robots,
Sensor Nodes, and RFID Tags, ICCCN 2009, p1 ,
Aug. 2009
[7] Basic Concept of Android System,http://developer.android.com/index.html
[8] Kyunghoon Kim Soonil Bae KwanghakHuh ,Robot Bus. Group, Samsung Techwin in
Seongnam, South Korea, Intelligent surveillance and
security robot systems, IEEE ARSO 2010, p70, Oct.
2010Android Socket[1],
http://www.hiapk.com/bbs/thread-6210-1-1.html
[9] Meng-Shiun Yu Horng Wu Huei-Yung Lin, Dept.of Electr. Eng., Nat. Chung Cheng Univ., Chiayi,
Taiwan, A visual surveillance system for mobile robot
using omnidirectional and PTZ cameras, SICE 2010,
p37, Aug. 2010.
[10] Gary Bradski, Adrian Kaehler, VadimPisarevsky, Learning-Based Computer Vision with
Intels Open Source Computer Vision Library, Intel
Technology Journal, Vol 9,Issue 2, p119~131, 19 May
2005.
[11] Luo, R.C. Chou, Y.T. Liao, C.T. Lai, C.C. Tsai,A.C. ,Nat. Chung Cheng Univ., Min-Hsiung, NCCU
Security Warrior: An Intelligent Security Robot
System, IEEE IECON 2007, p2960, Nov. 2007.
- 2168 -
8/2/2019 06060330
6/6
[12] Ching-Heng Ku Yen-Chieh Cheng, ChineseCulture Univ., Taipei, Remote surveillance by network
robot using WLAN and mobile IPv6 techniques, IEEE
TENCON 2007, p1, Oct. 30 2007-Nov. 2 2007.
Table 1 Sub-system functional description
Sub-system Function description
WirelessIPCAM video
capture system
Accordance to the temporary path provided by the manufacturer tocapture the pictures through wireless IPCAM and convert into image
files.
Face detection
systemFace detection for each captured image files
Remote
monitor andalarm
transmittersystem
Transmit warning message to user through MSN robot
Remote
monitor website
system
Remote monitoring function of watching the indoor status,
self-propelled vehicle, and the newest detected face
RFID position
detection
systems
Reading the RFID tag of self-propelled vehicle, and display the car
position by the installed RFID reader. These information is recorded
in the server database
Self-propelledvehicle
The server controls self-propelled vehicles through the wirelessnetwork
Smartphone
monitoring and
control system
Remote controls self-propelled vehicles and monitors the images ofwireless IPCAM by the Android mobile phone
Table 2 The distance and image limit of face detection
Image size
Distance
between face
and IPCAM
Limit of faceup angle
Limit of facedown angle
Limit of face
turn left
angle
Limit of face
turn rightangle
640*480