DEVELOPMENT OF REMOTE VEHICLE

MONITORING SYSTEM FOR

SURVEILLANCE APPLICATIONS
Thishone. P Samson Isaac. J
PG Scholar Assistant Professor
Department of Electrical Technology Department of Electrical Technology
Karunya University, Coimbatore, India. Karunya University, Coimbatore, India.
[email protected] [email protected]

ABSTRACT-- This paper focuses on the development of a portable road side sensor system for vehicle
classification, and speed measurement. Vehicle classification is done based on the vehicle length and
an estimate of the height of the vehicle. Vehicle length is estimated from the product of occupancy
and estimated speed. The average vertical vehicle height is estimated using ultrasonic sensors that
are vertically spaced by 2 m. To calculate the speed of the vehicle with an accuracy of 95%. The
developed sensor system is compact, portable, wireless, and in-expensive. Data are presented from
a large number of vehicles and different type of vehicles are passed in the roadside. To the types of
vehicle and speed of the particular vehicle is displayed in the display unit. Finally, the remote
monitoring system is used in Lab-VIEW.
Keywords: vehicle classification, vehicle speed measurement, vehicle height, Display unit.

I) INTRODUCTION:

This paper describes a portable sensing system that can be placed adjacent to a road and can
be used for vehicle counting, vehicle classification, and vehicle speed measurements. The proposed
system can make these traffic measurements reliably for traffic in the lane adjacent to the sensors.
The developed signal processing algorithms enable the sensor to be robust to the presence of traffic
in other lanes of the road.

Vehicle classification into pre-defined classes such as cars, trucks, and tractor trailers
typically requires measuring the size or length of vehicle. Classification model based on feature
extraction from piecewise slope rate values in single loop inductive signature data was pursued in
and classified vehicles into 15 classes. However, the accuracy rate is not 100% and can vary from
40% to 100%, depending on the amount of “problematic” data present in the sensor readings and
the class of vehicle under consideration. Finally, the traffic remote monitoring system used in
LabVIEW.
II) PROPOSED SYSTEM:

In the proposed system we use ultrasonic transmitter and receiver for sensing the
vehicle. The controller used here is AT mega 128 microcontrollers which has more memory and
five ports which has capability of performing multitasking. ZigBee module is used for the
transferring of information to control section as shown.

Figure 1: Block Diagram of Proposed System

VEHICLE DETECTION:

As stated above, because the environment of a moving vehicle greatly

varies, it is so difficult to detect vehicles using a single feature or pre-established vehicle templates.
Although we use various features or templates for various environments, we must apply the
appropriate algorithm to the current environment and these may be any obstacles to implement the
real-time processing system. In this paper, we first divide the environment into two conditions by
the intensity of illumination and apply a proper algorithm for each.

1)Start the operation for ultrasonic sensor

2)Detect the signal.

3)Collect the different data’s

4)Run the program.

5)Displaying the data unit

6)End the program.

Figure2: FLOW CHART FOR VEHICLE Figure3: Flowchart of Car Classification

CLASSIFICATION

SENSOR AND MEASUREMENT SYSTEM:

Figure 4: ULTRASONIC SENSOR

FEATURES:

• Supply Voltage – 5 VDC

• Supply Current – 30 mA type; 35 mA max
• Range – 2 cm to 3 m (0.8 in to 3.3 yards)
• Input Trigger – positive TTL pulse, 2 us min, 5 as typ.
• Echo Pulse – positive TTL pulse, 115 up to 18.5 MS
• Echo Hold-off – 750 as from fall of Trigger pulse
• Burst Frequency – 40 kHz for 200 as
• Burst Indicator LED shows sensor activity
OBJECT DISTANCE MEASUREMENT:
This is done in two parts. The first part consists of taking visual information of the object. We are
using a camera to take images and we would use various image processing techniques to extract
the object from the image. The second part consists of taking the range information of the object.
We are using an ultrasonic sensor for this job. For a fixed field, the horizontal and vertical distance
the camera can see is constant at a particular distance. If the angle of vision is known, then we can
find the area if we know the distance. Obstacle avoidance is the task of satisfying the control
objective subject to non-intersection or non-collision position constraints. Normally obstacle
avoidance involves the pre-computation of an obstacle-free path along which the controller will
then guide a robot. Though inverse perspective mapping helps to find the distance of the objects
far
away from the car with the help of known camera parameters and generating a model but it takes
more computations
INFRARED BASED OPTICAL SENSOR:
A passive infrared sensor (PIR sensor) is an electronic sensor that measures infrared (IR) light
radiating from objects in its field of view. They are most often used in PIR-based motion detectors.
Infrared light is a small part of the light spectrum. In order to understand night vision, it is
important to understand something about light. The amount of energy in a light wave is related to
its wavelength: Shorter wavelengths have higher energy. Of visible light, violet has the most
energy, and red has the least.
 Figure:5 INFRARED SENSOR

Working of IR LED Sensor is followed by four types,

1. IR LED work similar to normal LED
2. IR LED Transmit an Infrared light
3. IR light is not visible to necked eye
4. IR Light detected by Photodiode
IR sensor it consists of the two types are,
1. Digital IR Sensor
2. Analog IR Sensor
6.2.1: Digital IR Sensor:
Digital IR sensor is digital. It presented High or Low Value (1’s and 0’s)
6.2.1: Analog IR sensor:
Analog sensor detection depends on intensity of light received.
DATA ACQUISTION SYSTEM:
An Arduino is connected to the Ultrasonic Sensor. An ultrasonic sensor is calculated to
distance measurement in cm. After the process of the given data s are collected to the
storage unit. The ultrasonic sensor which may be collected data are passed to the AT mega
128 processors.

SENSOR MODULE is,

1) Ultrasonic sensor HC-SR04 is used here to measure distance in range of 2cm-

400cm with accuracy of 3mm. The sensor module consists of ultrasonic
transmitter, receiver and the control circuit. ...
 2) Distance= (Time x Speed of Sound in Air (340 m/s))/2.
3) Timing Diagram.

Figure:6 Ultrasonic Sensor interface to the Arduino Figure:7 Testing outputs for ultrasonic sensor

Figure 8: Sensor placement of Road Lane

To the waveform generation of the distance measurement is calculated to the levels of the
plot levels are shown in the figure. It’s a standard IR sensor for obstacle detection and
line detection purposes. The Sensor is provided with a potentiometer for calibration and
comes with an added advantage of selecting analog or digital output. The solder jumper
setting for output selection is available on the bottom side.
1)TREE BASED ON NEURAL NETWORKS:

Figure 9: Tree based algorithm using vehicle classification

HARDWARE RESULTS:

Figure: 10 Ultrasonic Sensor Interfaced to AT mega 128 Figure 11: Initialization of LCD

Figure 12: Scorpio Detection and Speed Monitoring Figure 13: Hyundai I 20 Detection and Speed Monitoring
Figure 14: INNOVA Detection and Speed Monitoring Figure 15: SWIFT Detection and Speed Monitoring

Figure 16: Height Calculations of SCORPIO figure 17: Height Calculation of HONDA CITY

figure 18: Height Calculation of SWIFT figure 19: Height Calculation of HYUNDAI i10
SOFTWARE RESULTS:
Finally, the displaying output will be displayed from the display unit, but ZigBee
unit will be used in transmitted and receiving unit. As the formation of the power supply will have
passed on the 6volt battery source will connect to the transmitted and receiving unit. A supply
power voltage is connected to the capacitor level of the positive and negative branch of the module.
The Lab-VIEW are displaying to the front panel of an experiment and the block diagram will be
plotted to the block diagram slide will be used in the several documents. To the several documents
of the LabVIEW results are displayed to the displaying unit.
To the LabVIEW result will be displayed from the collected different data are
passed to the hardware unit but select the one data of the maximum value of three values are
collected after the process of the vehicle name will be displayed the displaying unit.
For example, of one Ultrasonic sensor will be placed on the road side. Sensor will be turned on
from the power supply. Power supply will be going on the 6volts from the transmitting and
receiving end of the hardware unit.

Figure20: Lab VIEW based data acquisition system Figure21: Initialization of lab VIEW in Front panel

Figure22 Lab VIEW results of Hyundai i10 of block diagram Figure23: Lab VIEW results of HYUNDAI I 10 front panel
 Table 1: Sensor readings for Low End and High End vehicles

S.NO CAR TYPE LOW END High END

(cm) (cm)

1 SWIFT 28 32

2 HYUNDAI I 10 50 55

3 SCORPIO 2.6 4.6

4 INNOVA 18 22

Figure24: Lab VIEW results of SCORPIO in Block Diagram Figure25: Lab VIEW results of SCORPIO in front panel

Figure26: Lab VIEW results of SWIFT of block diagram Figure27: Lab VIEW results of SWIFT of front panel
S.NO CAR TYPE LOW END High END

(cm) (cm)

1 SWIFT 172 168

2 HYUNDAI I 10 150 145

3 SCORPIO 197.4 195.4

4 INNOVA 182 178

Table 2. Calculated height of the vehicle

TABLE3: COLLECTED DATA

Figure 28: Waveform Generation

Advantages:

• The developed sensor system is

 Compact,

 Portable,

 Wireless.

Applications:

• Used to monitor the number of vehicles passing in the road which can be used for the
survey.

• Used to determine the density of vehicle and helps to control traffic problems and it can be
used as a reference to the Government for building Bridges.

• Used to measure the speed of the vehicle in order to avoid accidents. By using smoke sensor
traffic light control system can also be included

CONCLUSION:

This paper has proposed a portable and low-cost sensing system based on an ultrasonic sensor that
can be placed adjacent to the height of the road and be used for traffic speed measurement, and
vehicle classification in the lane adjacent to the sensors. The vehicle classification and speed
measurement in this paper are enabled using multiple sensors are used. Through experimental data
from 188 vehicles, it is shown that the traffic levels accuracy of the system is 99%.

REFERENCES:

1) Saer Taghvaeeyan and Rajesh Raja Mani “Portable Roadside Sensors for Vehicle Counting,
Classification, and speed Measurement”, IEEE Transactions on Intelligent Transportation System.
Vol. 15, No. 1. Feb. 2014.

2) S. Gupte, O. Masoud, R. F. K. Martin, and N. P. Papani kolopoulos, “Detection and

classification of vehicles,” IEEE Transaction Intelligent Transportation System, vol. 3, no. 1, pp.
37–47, Mar. 2002
3) H. Cheng, H. Du, L. Hu, and C. Glazier, “Vehicle detection and classification using model-
based and fuzzy logic approaches,” Transportation Res. Rec., J. Transp. Res. Board, vol. 1935, pp.
154–162, 2005

4)Amirali Jazayeri, Hongyuan Cai, Member, Vehicle Detection and Tracking in Car Video Based
on Motion Model IEEE, Jiang Yu Zheng, Senior Member, IEEE, and Mehran Tuckerman, Senior
Member, IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, VOL.
12, NO. 2, JUNE 2011

5) Yong-Kul Ki, Member, Model for Accurate Speed Measurement Using Double-Loop Detectors
IEEE, and Doo-Kwon Biak, Member, IEEE TRANSACTIONS ON VEHICULAR
TECHNOLOGY, VOL. 55, NO. 4, JULY 2006

6) C. Sun, “An investigation in the use of inductive-loop signatures for vehicle classification,”
California PATH Program, Inst. Transp. Studies, Richmond, CA, USA, 2000.

7)J. Zhanfeng, C. Chen, B. Coifman, and P. Varaiya, “The PeMS algorithms for accurate, real-
time estimates of g-factors and speeds from single-loop estimates of g-factors and speeds from
single-loop detectors,” in Proc. IEEE ITSC, Aug. 2001, pp. 536–541.
8) M. Pursula and P. Pikkarainen, “A neural network approach to vehicle classification with
double loops,” in Proc. 17th Australian Rd. Res. Board Conf., 1994, pp. 29–44.
Part 4.
9) C. Sun, “An investigation in the use of inductive loop signatures for vehicle classification,”
Inst. Transp. Studies, Univ. California, Berkeley, CA, California PATH Research Report UCB-
ITS- PRR-2000-4, Mar. 2000.
10) NEMA Standards Publication TS 1 Traffic Control Systems, 1989, Washington, DC: Natl.
Electronic Manufactures Assoc.
11) Speed Enforcement System Standards, Apr. 2002, Seoul, Korea: National Police Agency.
12) A Certification Test of Speed Enforcement System. Seoul, Korea: Road Traffic Safety
Authority, 2001.
13) R. Wilshire, R. Black, R. Grochoske, and J. Higginbotham, Traffic control systems handbook.
Washington, DC: Inst. Transp. Eng., Apr. 1985. Report FHWA-IP-85-12.
14)C. Sun, S. G. Ritchie, and K. Tsai, “Algorithm development for derivation of section-related
measures of traffic system performance using inductive loop detectors,” in Transportation
Research Record 1483. Washington, DC: TRB, National Res Council., 1995, pp. 171–180. Yong-