Smart road condition checker

A.V.N.Perera
REG.NO:509062566

EEY 7883 Individual Project

(Progress Report 1)

Supervisor
Mrs. Hemali Pasqual

Department of Electrical & Computer Engineering

Faculty of Engineering Technology
20/08/2022

1
 Supervisor’s Comments

Name Mrs. H Pasqual

Comments This project will be a useful product. But student

should consider how the users are motivated in
fixing this device in their vehicles during the
design.

Signature

Date 20/08/2022

2
 CHAPTER 1

INTRODUCTION
1.1 PROBLEM OVERVIEW

Google map helps to us to find an unknown destination during traveling. But we do

not know whether these roads are in good condition or not. Sometimes the shown
routes have potholes and insufficient road width. There is no source of information
provided to know about the road conditions and pothole status of the roads in Sri
Lanka. So if we can provide a solution to know about it earlier, people can have a
happy and relaxed journey.
This project develops an electronic device to identify the road condition, before
starting the journey. Using this system, drivers and the other people who visit our
country as a tourist can get more benefits. Also, we can save the additional money
which is to be paid for inspectors who check the road condition can be reduced.
People can save additional time that they spend for roads which are not in a good
condition.
This system helps drivers to alert the road condition. This information is made
available in the Google map and when we search Google map we will be able to know
about the road condition too. Using this system we can identify road condition
whether it is a perfect road along which we can go without any accident and without
any time waste. Here the current situation on the road is automatically identified by
the pictures and sensors and that data will be updated to the Google map from the
previous vehicles passed through the road. Here there is a device with a camera and
sensors that detect width of road and crack points of the road. This device will be
mounted on the vehicle.
A mobile application is used to automatically update these data to the Google map.
When a vehicle goes through a broken road system will automatically recognize them
and update it to Google instantly. Then next vehicle can avoid using that road and can
prevent the harm.
Using these system drivers and the other people who visit our country as a tourist can
get more benefits using this system. Also we can save the additional money which is
to be paid for inspectors who check the road condition. People can save additional
time that they spend for traffic. And now the days we can save our fuel too.
Another special purpose is that State and Local maintenance departments are tasked
with keeping roads in good repair, which includes monitoring the roads to detect the
presence of cracks, potholes, and other distress. Currently, this is done by inspectors,

3
who drive out to each location and record the conditions on paper. This is a tedious and
often inconsistent process. Using specialized vehicles outfitted with sensors can automate
the data collection process significantly. However, these vehicles are expensive, costing
as much as $600,000. Another way of collecting data is through citizen reports, but these
are often only about severe and acute problems. In this project, we present a system to
monitor the condition of roads on a continuous basis, at low cost, with consistent quality,
and with minimal human intervention.

My approach involves using images collected by commodity devices such as sensors to

obtain information about the road condition. These devices can mounted in service-
vehicles like cabs, garbage trucks, police cars, public vehicle etc., which already make
regular rounds on city roads for other purposes. With this system the whole street
network of a city can be continuously monitored at a much lower initial and operating
cost than traditional methods.

1.2 AIM
The aim of this project is to develop a system to alert the condition of roads to drivers.
1.3 OBJECTIVE
Develop a hardware unit that can be fixed in the vehicle to identify the
road condition.
 Design the hardware unit which has following features:
 Gives the width of the road before the journey. It can be verified
two vehicles can passed through at same movement.
 Identifies potholes that situated on the road before the journey.
 Automatically updates the above information of the road to the Google
using a kind of mobile application.

4
 CHAPTER 2

LITERATURE SURVEY
2.1 EXISTING ROAD DETECTION METHODS.

2.1.1 ARAN - Automated Road Analyzer

Figure 2.1 ARAN - Automated Road Analyzer

The ARAN 9000 can be outfitted with as few or as many of the standard ARAN
subsystems as required. It can be used as a profiler, video logger, mobile mapper, or
full-scale data collection system. Production-ready ARAN 9000’s is ready to be
configured and delivered, and, as with the previous ARAN platform, the ARAN 9000
is fully modular to allow for customer-specific configuration and the ability to
upgrade with additional subsystems as required.

An ARAN is a specially modified vehicle that houses an extensive set of sensors

(including laser reflectometers, ultrasonic sensors, accelerometers, global positioning
systems, gyroscopes, video and machine vision systems) and computers, along with
other highly advanced technology subsystems. The purpose of all this technology is to
provide transportation departments with information about their roadways and right-
of ways, including their condition and the location of specific features and/or faults.
This data is critical to the management decision process that involves billions of
dollars of assets, and maintenance budgets of millions of dollars each year.

5
An ARAN provides information to support better management decisions by collecting
consistent, accurate, data quickly and cost effectively. It is capable of measuring up to
15 different data items in a single pass, with very high accuracy. This data can be
collected continuously, at traffic speeds from 15 mph up to highway speeds. Some of
the information that can be collected includes.

 The ride quality of the roadway [longitudinal profile / roughness (IRI)]

 The wearing of the roadway in the wheel paths [rutting]
 The grade and cross-slope of the roadway
 Real time video imagery of the roadway pavement and right-of-way imagery
 Precise location information of specific features on or near the roadway
(Purchase of Surveyor software required)
 Faulting of concrete pavements.

The City of Tucson's Pavement Management Staff is currently working on making

much of this data available as colored roadway segments on a map of Tucson that will
be accessible via the internet.

Figure 2.2 sub unit mounted on the vehicle.

2.1.2 Adaptive Road Crack Detection System by Pavement Classification

A road distress detection system involving the phases needed to properly deal with
fully automatic road distress assessment. A vehicle equipped with line scan cameras,
laser illumination and acquisition HW-SW is used to storage the digital images that
will be further processed to identify road cracks. Pre-processing is firstly carried out
to both smooth the texture and enhance the linear features. Non-crack features
detection is then applied to mask areas of the images with joints, sealed cracks and
white painting that usually generate false positive cracking. A seed-based approach is

6
proposed to deal with road crack detection, combining Multiple Directional Non-
Minimum Suppression (MDNMS) with a symmetry check. Seeds are linked by
computing the paths with the lowest cost that meet the symmetry restrictions. The
whole detection process involves the use of several parameters. A correct setting
becomes essential to get optimal results without manual intervention. A fully
automatic approach by means of a linear SVM-based classifier ensemble able to
distinguish between up to 10 different types of pavement that appear in the Spanish
roads is proposed. The optimal feature vector includes different texture-based
features. The parameters are then tuned depending on the output provided by the
classifier. Regarding non-crack features detection, results show that the introduction
of such module reduces the impact of false positives due to non-crack features up to a
factor of 2. In addition, the observed performance of the crack detection system is
significantly boosted by adapting the parameters to the type of pavement.

Figure 2.3 Rear of the vehicle used to acquire and store the road images.

A global overview of the automatic distress detection system is shown in Figure 2.3
where the main components are described using a block diagram. The input of the
system is 4,000 × 1,000 pixels images with 1 mm of resolution in both axis. These
images are obtained by integrating 1,000 images of both line scan cameras.

Global overview of the proposed adaptive road distress detection system that is
divided into four main stages: road surface classification, pre-processing, non-crack
features detection, and crack detection. The output of the classifier is used to adapt the
system parameters.

7
2.2 SIMILAR MOBILE APPLICATIONS.
2.2.1 Kansas department of transportation.

Figure 2.4 Kansas web page.

Kansas department of transportation is a leader in providing intelligent information
solutions to the traffic management market. This can learn about road conditions,
construction detours and travel weather information for the Kansas Turnpike and any
Interstate, U.S., or state highway in Kansas and Nebraska. By combining its unique
IP, products, decades of expertise in traffic management, hyper-local weather
solutions and information technologies, Kansas department of transportation offers a
broad range of Intelligent Transportation System ("ITS") solutions to customers
worldwide.
2.2.2 The 511PA Mobile Application
511PA is Pennsylvania's official travel information service which provides travellers
with reliable, current traffic and weather information, as well as links to other
transportation services. 511PA is designed to help motorists reach their destination in
the most efficient manner when traveling in Pennsylvania.The 511PA mobile
application covers all Penn DOT - and Pennsylvania Turnpike-operated roadways for
roughly 40,000 miles of roadway. Traffic incidents and construction alerts are
reported on all roadways and traffic speeds are reported on approximately 15,000
miles of roadway.
With 511PA, travelers can find such information such as:

 Traffic conditions
 Traffic Speeds,
 Live traffic camera images
 Highway construction updates

8
2.3 Current road conditions in Sri Lanka.
The functions performed by the RDA consist mainly of the maintenance and
development of the roads and bridges in the National Highway Network and
the planning, design and construction of new highways, bridges and
expressways to augment the existing network. We have almost manual
gathered data base system about road condition. Following map helps to
provide general road condition in Sri Lanka.

Figure 2.5 National road networks in Sri Lanka.

9
 2.3.1 Expressway Operation Maintenance & Management Division

Expressway Operation Maintenance and Management Division under the Road

Development Authority is highly responsible for the maintenance and management
operations of the expressway network in Sri Lanka. EOM&M Division is doing its’
operations under six main sections as follows.

 User fee collection section

 Traffic controlling section
 Maintenance section
 Mechanical section
 Electrical and Electronic section
 IT section

The tasks of the Expressway Traffic and Patrolling Unit are to maintain the
Expressways at the optimum condition to ensure traffic safety and smooth traffic
flow. Non-recurring incidents such as accidents, landslides, floods or traffic
congestion to threaten the optimum condition of the Expressway must be dealt with
by promptly restoring the Expressway to a desirable state. Patrolling is the most
important activity in the expressway by the Traffic and Patrolling Unit. This is done
by using patrol cars travelling along the expressway. During patrol the fallen objects
are being removed vehicles stuck on the expressway are being dragged immediately
in order to prevent traffic accidents on the expressway.

Maintenance section is there to carry out all types of the maintenance operations
related with the expressway. For examples, repairing damaged guard rails, cutting
grass on both borders of the road, maintaining all the properties on the expressway.
This section is responsible for the clearness of the expressway and the enclosed areas.
They are checking for the pot holes, cracks, and other damages on the way and repair
them properly. They are also responsible for maintaining gutters, culverts, etc., on the
road sides. If they are in bad condition and need repairs the maintenance section must
take the immediate actions to repair them in order to keep the expressway a safe place
for users.

RDA almost having a vehicle such as ARAN - Automated Road Analyser mention on
2.1.1. It is specially modified vehicle that houses an extensive set of sensors including
laser reflectometers, ultrasonic sensors, accelerometers, global positioning systems,
gyroscopes, video and machine vision systems and computers, along with other
highly advanced technology subsystems. For a one round it cost more than $ 500.
Therefore it does not use regular inspections.

10
 CHAPTER 3

SURVEY ON WHY & WHAT PEOPLE

NEEDS
 https://docs.google.com/forms/d/e/1FAIpQLSeoW_HfGNEh7cCquEoyH6
oLTJeijOkmOMF1IYzHU-dNVTLAXw/viewform?usp=pp_url+

11
12
13
14
15
16
According to above data it has been identified most of people faced similar problems
related to road conditions in Sri Lanka. Low cost reliable device liked to mount on
vehicles by them. There is no source of information provided to know about the road
conditions and pothole status of the roads in Sri Lanka RDA yet. RDA has manual
method done by man power to update the current situation of the road by inspectors.
This method is very expensive method, because man power and travel expenses. This
manual inspection was taken too much time to problem verification. Sri Lanka
government has big issue to maintaining highway by using specified vehicle (like
ARAN automated road analyser) with this economic crisis. Low cost smart road
condition is a good solution to solve out above problems in our country.

17
 CHAPTER 4

PROPOSED METHODOLOGY
SMART ROAD CONDITION CHECKER is a fully integrated system for the
automatic detection and characterization of cracks in road flexible pavement surfaces,
which does not require manually labelled samples, is proposed to minimize the human
subjectivity resulting from traditional visual surveys. The first task addressed, crack
detection, is based on learning from samples paradigm, where a subset of the
available image database is automatically selected and used for unsupervised training
of the system. The system is constructed, to characterize the detected potholes'
connect components. Potholes are labelled according to the types defined in the
Portuguese Distress Catalogue, with each different crack present in a given image
receiving the appropriate label. Moreover, a novel methodology for the assignment of
Potholes severity levels is introduced, computing an estimate for the width of each
detected pothole. Experimental pothole detection and characterization results are
presented based on images captured during a visual road pavement surface survey
over Portuguese roads, with promising results. This is shown by the quantitative
evaluation methodology introduced for the evaluation of this type of system,
including a comparison with human experts' manual labelling results.

4.1 Block diagram

Fig. 4.1 – Method of building smart road condition checker

18
  Here the system has been proposed the automatic width of the road and
detected potholes by sensors marked on the Google map. Detected data stored
in PC or microchip in raspberry Pi. The place where the pothole will be
detected is monitored by using the Google map.

 Using the sensors the information regarding the pothole is updated on the PC
and also the information sends to the officials for the future recovery. This
project minimized the human effect done by RDA supervisors to analyse road
condition.

 SOFTWARE REQUIRMENT:
Raspberry Pi OS

 HARDWARE REQUIRMENT:
Raspberry Pi project board, GPS module, Ultrasonic sensor, Accelerometer,
Buzzer and PC.

After identifying the current condition of the road using a web page they will be
updated on Google the map. Some specific signs and symbols are used to identify
these conditions on the map.
 If there is low network coverage within the considered area. Raspberry pi
microchip helps to store the data.

19
4.2 About the hardware and software components
4.2.1 Raspberry Pi

Raspberry Pi is a series of small single-board computers (SBCs) developed in

the United Kingdom by the Raspberry Pi Foundation in association with Broadcom.
The Raspberry Pi project originally leaned towards the promotion of teaching
basic computer science in schools and in developing countries . The original model
became more popular than anticipated, selling outside its target market for uses such
as robotics. It is widely used in many areas, such as for weather monitoring, because
of its low cost, modularity, and open design. It is typically used by computer and
electronic hobbyists, due to its adoption of the HDMI and USB standards.

Figure 4.2 raspberry pi project Board

4.2.2 SKG13BL GPS module

The signals obtained by the GPS receiver takes note of the precise latitudinal and
longitudinal parameters and connect it to the GSM module for the purpose of
transferring the information to the respective authorized centre. The input voltages
required. A GPS receiver must be locked on to the signal of at least 3 satellites to
calculate a 2-D position (latitude and longitude) and track movement. With four or
more satellites in view, the receiver can determine the user's 3-D position (latitude,
longitude and altitude). Enhanced features include video features, trace mode, history
track and network support.

Figure 4.3 GPS module with antenna

20
4.2.3 Ultrasonic Sensor

Ultrasonic Sensor HC-SR04 is an active ultrasonic sensor and contains a transmitter

and a receiver. It is used to measure distance at which humps are present in front of it.
The ultrasonic sensor transmits high frequency sound waves and waits for the
reflected wave to hit the receiver. Ultrasonic sensor are basically used to measure the
distances between the object place in front of it and the sensor. The ultrasonic sensor
works on Doppler Effect. The distance is calculated based on the time taken by the
ultrasonic pulse to travel a particular distance. HC-SR04 works at 40 KHz frequency
and can measure distance of objects in the range 2-400cm with a 15o angle of
detection.

4.2.4 Accelerometer

Accelerometer is a sensor which converts accelerations from motion or gravity to

either analogue or digital electrical signals. The raw data set from the accelerometer is
the acceleration of each axis in the units of gravitational force which is convertible to
other units also. The raw data is represented in a set of vectors .The acceleration data
is collected from pothole and hump respectively, the system collects three axis
readings X Y &Z. The ADXL345 is a low power, 3-axis MEMS accelerometer that
utilizes the I2C and SPI serial interfaces.

4.2.5 Buzzer

A buzzer or beeper is an audio signalling device, buzzer used in this project is an

alarming device, Buzzer is an integrated structure of electronic transducers ,DC power
supply ,Active buzzer 5v rated power can be directly connected to a continues sound.

4.2.6 Raspberry Pi OS

Raspberry Pi OS is highly optimized for the Raspberry Pi line of compact single-

board computers with ARM CPUs. It runs on every Raspberry Pi except the Pico
microcontroller. Raspberry Pi OS uses a modified LXDE as its desktop environment
with the Open box stacking window manager, along with a unique theme.

21
4.3 EXPECTED FEATURES OF THE SYSTEM
 Very simple to use.
 Create a Google application.
 Low maintains cost.

4.4 ADVANTAGES AND DISADVANTAGES OF THE SYSTEM

4.4.1 ADVANTAGES

 This system helps drivers to alert the road condition.

 This information is made available in the Google map through a mobile
application.
 Can save the additional money which is to be paid for inspectors who check
the road condition. People can save additional time that they spend for traffic.

4.4.2 DRAWBRACKS

 Cannot update pictures trough the Google map.

 When we mark road condition additional details cannot be included e.g. the
width and depth of pits on the road.
 User should have internet connection to get web search results.

4.5 CHALLENGES

 In categorizing data according to feature of the situation.

 Time taken for data processing.
 Motivating to mount this equipment for every vehicles.
 Getting most accurate data from the vehicle.
 Less network coverage in some rural area.

22
5 TIME PLAN
Jun July Aug Sep Oct Nov Dec Jan Feb Mar Apr May

2012 2012 2013 2013 2013 2013 2013 2013 2013 2013 2013 2013
Proposal and
feasibility
project
Review of other
&preparing
systems and
project proposal
literature survey
15/07/2011
Progress report1

Progress
presentation#1

System
Designing &
simulations

Progress report2

Progress
presentation#2

Implementation
testing and
verification of
results

Final report `
submission and
Final
presentation

23
6 REFERENCES
[1] https://www.eng.auburn.edu/research/centers/ncat/about/facilities/automatic-road-
analyzer.html.

[2] Akhil n, Dinumohan , Fayis p, Sijagopinath,” Railway Crack Detection System”,

International Research Journal of Engineering and Technology (IRJET) ,Volume: 03
Issue: 05 | May-2016

[3] Prof. P.Navaraja, “CRACK DETECTION SYSTEM FOR RAILWAY TRACK

BY USING ULTRASONIC AND PIR SENSOR”, International Journal of Advanced
Information and Communication Technology (IJAICT) ,Volume -1, Issue-1, May
2014

[4] Computer Engineering Department, Polytechnic School, University of Alcalá,

Alcalá de Henares, Madrid 28871, Spain; E-Mails: miguel.gavilan@aut.uah.es
(M.G.); david.balcones@aut.uah.es (D.B.); oscar.marcos@aut.uah.es (O.M.);
sotelo@aut.uah.es (M.A.S.); ignacio@aut.uah.es (I.P.); mocana@depeca.uah.es
(M.O.) Adaptive Road Crack Detection System by Pavement Classification

[5] A. Tsukada, M. Ogawa and F. Galpin, “Road structure based scene understanding
for intelligent vehicle systems”, International Conference on Intelligent Robots and
Systems, Taipei, Taiwan, (2010) October 18-22.

[6] J. Zavadil, J. Tuma and V. M. F. Santos, “Traffic signs detection using blob
analysis and pattern recognition”, 13th International Carpathian Control Conference,
High Tatras, Slovakia, (2012) May 28-31.

[7] H. Oliveira and P. L. Correia, “Automatic Road Crack Detection and

Characterization”, IEEE Transactions on Intelligent Transportation Systems, vol. 99,
(2012).

[8] W. Wei, L. Boying and B. Peng, “Automatic Road Crack Image Preprocessing for
Detection and Identification”, Second International Conference on Intelligent
Networks and Intelligent Systems, Tianjin, China, (2009) November 1-3.

[9] K. Hui, J. Y. Audibert and J. Ponce, “General Road Detection From a Single
Image”, IEEE Transactions on Image Processing, vol. 19, no. 8, (2010).

[10] M. Mazaheri and S. Mozaffari, “Real time adaptive background estimation and
road segmentation for vehicle classification”, 19th Iranian Conference on Electrical
Engineering, Tehran, Iran, (2011) May 17-19.

24
[11] D. B. Lewis, J. M. Keller, M. Popescu and K. Stone, “Dirt road segmentation
using color and texture features in color imagery”, IEEE Symposium on
Computational Intelligence for Security and Defence Applications, Ottawa, Canada,
(2012) July 11-13.

[12] Y. Sebsadji, J. P. Tarel, P. Foucher and P. Charbonnier, “Robust road marking

extraction in urban environments using stereo images”, IEEE Intelligent Vehicles
Symposium, La Jolla, US, (2010) June 21-24.

[13] F. M. Sebdani and H. Pourghassem, “A robust and real-time road line extraction
algorithm using hough transform in intelligent transportation system application”,
IEEE International Conference on Computer Science and Automation Engineering,
Zhangjiajie, China, (2012) May 25-27.

[14] Z. Wang and B.G. Cai, “A ROI setting method for vehicle detection in urban
environment”, IEEE-APS Topical Conference on Antennas and Propagation in
Wireless Communications, Cape Town, South Africa, (2012) September 2-7.

[15] https://www.raspberrypi.com/documentation/

[16] www.ehow.com/how_7928508_build_ir_transmitter.

[17]https://www.kandrive.org/@101.43512,39.04521,6?show=roadReports,constructi
onReports,trafficSpeeds,electronicSigns,normalCameras,winterDriving

25
26
27