ASSESMENT REPORT ON

Team ID & Title: Mining and suggestion using the data obtained through
11 pothole detection

Submitted
as part of CSE3999-Technical Answers for Real World Problems

Reg. No: 16BCE0042

Name: Nannapaneni Thejesh

Reg. No: 15BCE0242

Name: Karthik

To

Sasikala R

School of Computer Science and Engineering

April 2019
 Index
Chapter Topic Page No.
1 Abstract & Keywords 1
2 Objectives 2
3 Literature Review
3.1. National Status 3
3.2. International Status 4
4 Requirements 5
4.1. Hardware 6
4.2. Software 7
5 Design 8
6 Invention Details
6.1. Objects of the Invention 9
6.2. Summary of Invention 9
6.3. Brief Description of the Drawings 9
6.4. Detailed Description of the Invention 9
6.5. Working Examples 10
6.5.1. Working Example 1 10
6.5.2. Working Example 2 10
6.5.3. Working Example 3 10
7 Implementation
7.1. Pseudo Code 11
8 Results 12
9 Conclusions 13
10 References 14
 Chapter 1
ABSTRACT

Roads have been flooded with the traffic. It has become difficult to manage this traffic. This is
the prime need behind making a vehicle intelligent enough to aid driver in various aspects. One
of the existing methods is that capturing the pot holes with camera and subjecting it to some
techniques in image processing to detect pot holes. It is time seeking and not that accurate
enough to detect the exact existence and width of the potholes. So here we are with additional
features like if the driver goes in the same way again, our system intimates him/her beforehand
and its efficiency is high due to use of ultrasonic sensors. One of the issues is regarding
connectivity. All the way till the end of use of vehicle, the system should be connected to the
local database so that it could load the location and information of potholes. With this idea we
can prevent the accidental damages caused to the vehicles and passengers due to these potholes
on the roads.

Keywords: Potholes, Ultra-Sonic Sensors, Micro Controller, Vehicle, Road, Driver, Speed
Breakers, Connectivity, Detection, Access Point
 CHAPTER 2
OBJECTIVES

1 To develop a real-time user-friendly application and ultrasonic sensors for

detecting discontinuities along the terrain.

2 Updating information (like location, position) into the database about the

discontinuities in the terrain and adding it to the information broadcast.

3 Because of ultrasonic sensors, driver will get notified well in advance about any

discontinuities in the terrain and adding it to the information broadcast.

4 We will develop a quick-time application which will help in signalling the driver

about a pothole as quickly as possible

5 Hence main objective of our project is to prevent the car and the passengers inside

from any damages and inconveniences.

 CHAPTER 3
LITERATURE REVIEW

3.1. National Status:

1. Shonil Vijay (2006), IIT Bombay: The objective of this project is to develop a low cost
vision-based driver assistance system over FPGA, to provide a solution of detection
and avoidance of potholes in the path of a vehicle on road. This project used an FPGA
model to deploy image processing algorithms efficiently so that the output can be
achieved in real time.

2. Sachin Bharadwaj and Golla Varaprasad (2013), IET Digital Library: This study
discusses a solution for detection of potholes in the path of an autonomous vehicle
operating in an unstructured environment. Here, a vision approach is used since the
simulated potholes are significantly different from the background surface.
Furthermore, using this approach, pothole can only be detected in case of uniform
lighting conditions. The solution to the problem is developed in a systematic manner.
Initially, a specific camera and frame grabber are chosen, then camera is mounted on
top of the autonomous vehicle and the images will be acquired. Then, a software
solution is designed using MATLAB.

3. Gunjan Chugh , Divya Bansal and Sanjeev Sofat(2014), PEC University,

Chandigarh: This paper presents a detailed survey of methods for detecting road
conditions. Form the survey, it is noted that the most commonly used sensors
accelerometer and GPS.

4. Shambhu Hegde and Harish (2014), International conference, Hyderabad: This

paper aims at proposing a novel pothole detection system, which assists the driver to
avoid potholes on the roads by giving prior warnings. The idea is to build a robot vehicle
that is capable of detecting the potholes and transferring this information to the nearby
vehicles in the vicinity.

5. Aniket Kulkarni and Nitish Mhalgi (2014), V.E.S. Institute of Technology, Mumbai:
This paper investigates an application of mobile sensing detection of potholes on roads.
They described a system and an associated algorithm to monitor the pothole conditions
on the road. This system, that they call the Pothole Detection System, uses
Accelerometer Sensor of Android smartphone for detection of potholes and GPS for
plotting the location of potholes on Google Maps using machine learning concepts.
3.2. International Status:
1. Larry Matthies and Alonzo Kelly (1996), Jet Propulsion Laboratory, USA: This paper
describes how to detect obstacles during off-road autonomous navigation, unmanned
ground vehicles (UGV's) must sense terrain geometry and composition (i.e. terrain
type) under day, night, and low-visibility conditions. To sense terrain geometry, we
have developed a real-time stereo vision system that uses a Datacube MV200 and a
68040 CPU board to produce 256 x 45-pixel range images in about 0.6 seconds/frame.

2. Reinholds Zviedris (2011), University of Latvia, Lativa: This paper describes lessons
learned from their field tests, which have exposed the deficiencies in terms of collected
data quality. They are developing a vehicular participatory sensing application using
Android smart-phones for pothole detection. Nevertheless, the tests provide invaluable
experience for planing future field tests and improvements to the test execution
procedure for vehicular sensing researchers.

3. Christain Koch and Ioannis Brilakis (2011), Elsivier: In this paper they present a
method for automated pothole detection in asphalt pavement images. In the proposed
method an image is first segmented into defect and non-defect regions using histogram
shape-based thresholding. Based on the geometric properties of a defect region the
potential pothole shape is approximated utilizing morphological thinning and elliptic
regression.

4. He Youquan and Wang Jian (2011), International Congress, Shanghai: In order to

detect the three-dimensional cross-section of pavement pothole more effectively, this
paper proposes a method which employs optical imaging principle of three-dimensional
projection transformation to obtain pictorial information of pothole's cross-section in
pothole detection. Multiple digital image processing technologies, including: image
pre-processing, binarization, thinning, three-dimensional reconstruction, error analysis
and compensation are conducted in the series of image analysis and processing.
Experimental results indicate that the method is markedly superior to traditional
methods in many aspects.

5. X. Yu and E.Salari(2011), IEEE Interational Conference, Mankato,USA:

In this paper, they introduced an efficient and more economical approach for
pavement distress inspection by using laser imaging. After the pavement images are
captured, regions corresponding to potholes are represented by a matrix of square tiles
and the estimated shape of the pothole is determined. The vertical, horizontal distress
measures, the total number of distress tiles and the depth index information are
calculated providing input to a three-layer feed-forward neural network for pothole
severity and crack type classification. The proposed analysis algorithm is capable of
enhancing the pavement image, extracting the pothole from background and analysing
its severity.
 CHAPTER 4
REQUIREMENTS

4.1. Hardware Requirements

4.1.1. List of Hardware Components (Example)

a) Arduino Uno

b) GPS module

c) Ultrasonic Sensor

d) USB 2.0 Cable

e) Breadboard

f) Resistors-10k, 270k and 330k ohm

g) Jumper wires
4.1.2. a. Description of Hardware Component:

Fig. 1: Raspberry pi

Name of Item: Arduino Uno

– Model: Atmega328P

– Vendor: Generic

– Price: ₹ 455

– Spec: Operating voltage 5V, Input Voltage 7-12 V, Digital I/O pins-14,
Analog input pins-6.

Component Functionality:

Small size, cheap and open hardware, which runs many of the main components of the board–
CPU, graphics, memory, the USB controller, etc.

Application: 1) Arduino Based Home Automation System

2) Arduino Based Auto intensity control of Street lights

Reference URL:

https://www.amazon.in/Uno-ATmega328P-Compatible-ATMEGA16U2-
Arduino/dp/B015C7SC5U/ref=sr_1_4?keywords=arduino+uno&qid=1554391438&s=compu
ters&sr=1-4
Name of Item: Ultrasonic sensor
– Model: HC-SR04

– Vendor: Balaji electronics, Vellore

– Price: ₹ 150

– Spec: 5V, 15 mA, 40 Hz, range = 2 - 400 cm

Component Functionality: Measure distance to an object by using sound waves.

Application: 1) To measure Tank Level.

2) Distance Measurement.

3) Robotic sensing.

4) Vehicle detection for car wash and automotive assembly, etc.

Reference URL:

https://www.electroschematics.com/8902/hc-sr04-datasheet/
Summary of Components in Tabular form:

S.No Item Model Spec Vendor Price

In Rs.
1 Arduino Uno Operating Generic, 455
voltage 5V,
Atmega328P Amazon
Input
Voltage 7-
12 V,
Digital I/O
pins-14,
Analog
input pins-6.

2 Ultrasonic sensor HC-SR04 5V, 15 mA, Balaji 150

40 Hz, range electronics,
= 2 - 400 cm Vellore

3 GPS module Neo6Mv2 With Antena Xcluma,Amazon 1000

and built in
EEPROM
4 Breadboard GL-12 - Balaji ele. 60
5 Resistors 10k, 270k, - Balaji ele. 2
330k
6 Jumper wires Female-male Balaji ele. 12
Connection

Total 1324/-
Table 1: Summary of Hardware Components

4.2. Software Requirements

S.No Item versions Vendor Price Description Reference

1 Arduino March online Free Debian based microsoft store
IDE 2019 computer OS
for Arduino
Uno

2 Python 3.7.0 online Free A powerful www.python.org

IDLE python editor
Table 2: Summary of Software Components
 CHAPTER 5
Design

Arduino is connected to Ultrasonic sensor and GPS module. Data is stored into cloud where
a excel file containing Street name, number of potholes and latitude, longitude (as if now)
values will be given. This excel sheet is then used by data mining algorithms to get helpful
predictions.
 CHAPTER 6
INVENTION DETAILS

6.1. Objects of the Invention: It is common knowledge that roads are fraught with many
dangers such as bumps, manholes, large stones, etc. without adequate warning signs,
making travel, both on foot as well as on an automobile very risky, especially at night.
There is a need for a reliable and robust early warning system which would accurately
detect abrupt discontinuities in terrain like potholes, manholes, bumps, etc. which can be
used by pedestrians.

6.2. Summary of Invention: One of the main difficulties in developing countries is

maintenance of roads. Well maintained roads contribute a major portion to the country’s
economy. Identification of pavement distress such as potholes and humps not only help
drivers to avoid accidents or vehicle damages, but also helps authorities to Maintain
roads. Hence its is an important issue to find out the hurdles on the road that are
dangerous to the vehicle and the driver inside the vehicle even.

6.3 Brief Description of the Drawings: In the circuit made, a 330-ohm resistor is
connected to the ultrasonic sensor. Another 470-ohm resistor is connected to the two pins
of the raspberry pi with male to male connection wires.

6.4. Detailed Description of the Invention:

6.5. Working Examples

6.5.1 Working Example 1:
Production Line Sensors:
Ultrasonic sensors can be applied to the manufacturing process for automated process
control on the factory floor while also being an indispensable tool for companies to
maximize efficiency through precise measurement and control.

Ultrasonic sensors can streamline the production processes.

6.5.2 Working Example 2:
Distance Measurement:
Ultrasonic sensors can measure the distance to a wide range of objects regardless of
shape, color or surface texture. They are also able to measure an approaching or receding
object.

6.5.3 Working Example 3:

Tank Level:
Liquid level sensors are integral to process control and inventory management in many
industries.

At Migatron, we engineer two types of level sensors, point level sensors (proximity
sensors which is a type of ultrasonic sensor) and continuous level sensors (analog
sensors). The type of sensor appropriate for your liquid level measurement depends on the
application.
 CHAPTER 7
IMPLEMENTATION
6.1. Pseudo Code
 CHAPTER 8
RESULTS
6.1. Snap shots
 CHAPTER 9
Conclusions

Taking into account the current road scenarios, there is a need to devise a system which warns
the driver about the upcoming potholes. Many on-going projects in the field of vehicular
networks are working in the direction of providing driver with relevant information about roads
and traffic movements. We present here, a novel idea of Pothole Detection & Warning System
which aims at providing appropriate information to the driver about potholes. We have
implemented this system which would continuously detect the potholes on the road and detect
the hardware’s location and send the data to the server side. In this document, we have
described the working, the hardware requirements, the software requirements that it will use to
run the system. The data obtained from here is being can be given to the concerned road
management authority for the further procedures. Therefore, driver’s safety may be improved
with the establishment of real-time pothole detection system for sharing the pothole
information. If such system is implemented it could result in various helps to the public as well
as the governmental body for the development of the country. In this project, various choices
for implementing the System have been studied and compared to each other on various
criterion. We intend to develop a system which characterize road condition into categories like
smooth, moderately uneven and highly uneven from the results of the experiments through our
project.
 Chapter 10
REFERENCES

1. R Gass, J Scott, C Diot, “Measurements of In-Motion 802.11 Networking”, IEEE

Workshop on Mobile Computing System and Applications, 2006 .

2. X Zhang, JK Kurose, BN Levine, D Towsley, H Zhang , “Study of a bus-based

disruption-tolerant network: mobility modeling and impact on routing”, 13th annual
ACM international conference, 2007.

3. “http://www.its.dot.gov/vii”, RITA | ITS | Vehicle Infrastructure Integration, JAN 2007.

4. “http://dev.emcelettronica.com/datasheet/st/LIS3L06AL”, Datasheet of ST LIS3L06AL

accelerometer, JAN 2008.

5. “http://www.gps.gov/”, Global Positioning System, JAN 2007.