Shambhavi Report

CONTRIVER®, Mysore
Department of computer science and engineering
INTERNSHIP TRAINING REPORT

Submitted in partial fulfilment of the requirements for the certification of
30 days internship training program
SUBMITTED BY
SHEETAL PHULARI
(3GN20IS042)
Under the Guidance of
Ms. SANGEETHA
Department of Information science and engineering
M/S CONTRIVER®
# 609, 1st Floor, Sinchana Clinic, Panchamantra Rd, Kuvempu Nagara,
Mysuru, Karnataka 570023
2023 - 2024
CONTRIVER®
# 609, 1st Floor, Sinchana Clinic, Panchamantra Rd, Kuvempu Nagara,
Mysuru, Karnataka 570023
Department of Department of computer science and engineering
TRAINING CERTIFICATE
This is to certify that Ms.SHEETAL PHULARI (3GN20IS042). bonafide students of College of
Degree in partial fulfillment for the award of “Training Certificate” in Department of
Information science and engineering of the CONTRIVER, Mysore during the year 2023-2024. It is
certified that he/she as undergone internship during the time period from 16/08/2023 to
30/09/2023 of all working days corrections/suggestions indicated for internal validation have been
incorporated in the report deposited to the guide and trainer. The training report has been
approved as it satisfies the organizational requirements in respect of Internship training prescribed
for the said qualification.
Mrs. SYEDA ARBINA Ms. SANGEETHA Shri. SANJAY B

KAUSAR Bachelor of engineering. DMT, B.E.
Bachelor of engineering. Sr. Production Head and Chief
Executive Officer
ACKNOWLEDGEMENT
It is our privilege to express gratitude to all those inspired us and guided to complete the
internship-training program. This work has remained incomplete without the direct and indirect
help of many people who have guided us in the success of this internship. We are grateful to
them.
Date:
Place: Mysore
- SHEETAL PHULARI
RESUME
SHEETAL PHULARI
INFORMATION SCIENCE AND ENGINEERING
CONTACT INFORMATION
ADDRESS:
D/O S h i v k u m a r P h u l a r i ,
KIADB Housing Area,Beside BSNL Tower,
Naubad Bidar,Karnataka-585402
EMAIL
ID:sheetalphulari07@gmail.com
CONTACT NO:+91 7892958001
OBJECTIVE
To work in a very challenging and competitive job environment with an appraisal and growth
combination, where I would be able to significantly contribute to the organization’s requirements
while continuously enhancing my skill-set.
ACADEMIC INFORMATION
EDUCATION QUALIFICATIONS:
COURSE/EXAM INSTITUTION YEAR OF PASSING MARKS OBTAINED

IN %
S.S.L.C Millennium Public 2018 68

School, Bidar
PUC Sri Channabasaveshwar 2020 68

Gurukul,Kardyal,Bidar
B.E(CSE) Gurunanak Dev 2024

Engineering College,
Bidar
TRAINING/ INTERNSHIP
TRAINING ML using Python and Web

Development
INTERNSHIP Contriver
COMPUTER SKILLS
 Packages : MS Office, MS powerpoint, MS excel
  Programming Languages : C, Python,C++,HTML,CSS
PROJECT DETAILS
PROJECT: Road Lane Line Detection
Abstract: Road lane detection is a multifeature detection problem that has become a real challenge for
computer vision and machine learning techniques.
PERSONAL STRENGTH
 Hardworking, dedicated, responsible, self confident,self motivated
PERSONAL PROFILE
Name : Sheetal Phulari
Father’s name : Shivkumar Phulari
DOB : 07-01-2003
Marital Status : Single
Nationality : Indian
Languages Known : Kannada, English
Personal address : KIADB Housing area Beside BSNL Tower Naubad

Bidar, Karnataka -585402
DECLARATION
I hereby declare that all the information’s are correct and true to the best of my knowledge and belief.
DATE:
Place: Mysuru
Yours Sincerely
(SHEETAL PHULARI)
CONTENTS
CHAPTER 1
INTRODUCTION........................................................................................ 2-10
1.1 INTRODUCTION.........................................................................................2
1.2 MOTIVATION............................................................................................3
1.3 DIGITAL IMAGE PROCESSING.............................................................. 4
1.3.1 STEPS IN IMAGE PROCESSING......................................................5
1.3.2 IMAGE IN MATRIX REPRESENTATION...................................... 6
1.3.3 TYPES OF AN IMAGE...................................................................... 6
1.4 SELF DRIVING CARS................................................................................7
1.5 LANE DETECTION BY VEHICLE............................................................ 8
1.5.1 DISTORTION CORRECTION........................................................... 8
1.5.2 CREATE A BINARY IMAGE...........................................................9
1.6 PROBLEM STATEMENT........................................................................10
CHAPTER 2
LITERATURE SURVEY.......................................................................... 11-26
2.1 EDGE DETECTION................................................................................. 11
2.2 FILTER OUT NOISE............................................................................... 11
2.2.1 CONVOLUTION.............................................................................. 11
2.2.2 CONVOLUTION OPERATION.......................................................12
2.3 SAMPLE I/P O/P OF CANNY EDGE DETECTION............................... 17
2.4 HOUGH TRANSFORM SPACE.............................................................. 18
2.4.1 THEORY OF HOUGH TRANSFORM SPACE.............................. 19
2.5 IMPLEMENTATION OF HOUGH TRANSFORM SPACE...................20
2.6 VARIATIONS AND EXTENSIONS....................................................... 21
2.6.1 GRADIENT DIRECTION................................................................. 21
2.6.2 KERNEL BASED HOUGH TRANSFORM..................................... 21
2.6.3 3-D KERNEL BASED HOUGH TRANSFORM.............................. 21
2.7 HOUGH TRANSFORM OF CURVE AND ITS GENERALIZATION.... 22
2.8 CIRCLE DETECTION PROCESS............................................................23
2.9 DETECTION OF 3-D OBJECTS.............................................................. 23
2.10 USING WEIGHTED FEATURES.......................................................... 24
2.11 CAREFULLY CHOSEN PARAMETER SPACE.................................. 24
2.12 EFFICIENT ELLIPSE DETECTION ALGORITHM............................. 25
2.13 EXISTING SYSTEMS.............................................................................25
2.14 LIMITATIONS OF EXISTING SYSTEMS.......................................... 25
2.15 PROPOSED SYSTEM.............................................................................26
CHAPTER 3
SYSTEM REQUIREMENT.................................................................... 27-29
3.1 SYSTEM CONFIGURATION................................................................. 27
3.1.1 SOFTWARE CONFIGURATION...................................................27
3.1.2 HARDWARE COFIGURATION....................................................29
CHAPTER 4
SYSTEM DESIGN...................................................................................30-36
4.1 PROPOSED SYSTEM OVERVIEW...................................................... 30
4.1.1 IMAGE PROCESSING METHODOLOGY.................................. 31
4.2 ARCHITECTURE...................................................................................33
4.3 CANNY EDGE DETECTION ARCHITECTURE................................. 35
4.4 PROJECT MODULES.............................................................................36
CHAPTER 5
IMPLEMENTATION............................................................................. 41-52
5.1 PSEUDO CODE........................................................................................41
CHAPTER 6
RESULTS AND DISCUSSIONS.............................................................53-58
CONCLUSION...............................................................................................59
FUTURE SCOPE............................................................................................59
BIBLIOGRAPHY...........................................................................................60
LIST OF FIGURES
Figure 6.1 Solid white curve..........................................................................................................53
Figure 6.2 Solid white curve annotated........................................................................................53
Figure 6.3 Solid white right...........................................................................................................54
Figure 6.4 Solid white right annotated..........................................................................................54
Figure 6.5 Solid yellow curve........................................................................................................55
Figure 6.6 Solid yellow curve annotated......................................................................................55
Figure 6.7 Solid yellow curve 2....................................................................................................56
Figure 6.8 Solid yellow curve 2 annotated...................................................................................56
Figure 6.9 Solid yellow left...........................................................................................................57
Figure 6.10 Solid yellow left annotated........................................................................................57
Figure 6.11 White carlane switch..................................................................................................58
Figure 6.12 White carlane switch annotated.................................................................................58
Road Lane Line Detection 2023-24
ABSTRACT
Lane detection is a challenging problem. It has attracted the attention of the computer vision
community for several decades. Essentially, lane detection is a multifeature detection problem that
has become a real challenge for computer vision and machine learning techniques. Although many
machine learning methods are used for lane detection, they are mainly used for classification rather
than feature design. But modern machine learning methods can be used to identify the features that
are rich in recognition and have achieved success in feature detection tests. However, these methods
have not been fully implemented in the efficiency and accuracy of lane detection. In this paper, we
propose a new method to solve it. We introduce a new method of preprocessing and ROI selection.
The main goal is to use the HSV color transformation to extract the white features and add preliminary
edge feature detection in the preprocessing stage and then select ROI on the basis of the proposed
preprocessing. This new preprocessing method is used to detect the lane. By using the standard KITTI
road database to evaluate the proposed method, the results obtained are superior to the existing
preprocessing and ROI selection techniques.
Key words: Lane detection, Computer vision, Intelligent Vehicles, Hough Transform Visual
Guides
Department of Testing and Programing, Contriver Page 1

Chapter 1 INTRODUCTION
1.1 INTRODUCTION
Road lane line detection is a crucial component of advanced driver assistance systems (ADAS) and
autonomous vehicles, as it plays a fundamental role in ensuring safe and precise navigation on the road.
Machine learning techniques have revolutionized the field of lane line detection, offering robust and
real-time solutions for identifying and tracking road lanes. Traditionally, lane line detection relied on
rule-based methods and image processing techniques, which often struggled to adapt to varying road
conditions and complex scenarios. However, with the advent of machine learning, particularly deep
learning models, the accuracy and reliability of lane line detection have greatly improved.
With the rapid development of society, automobiles have become one of the transportation tools for
people to travel. In the narrow road, there are more and more vehicles of all kinds. As more and more
vehicles are driving on the road, the number of victims of car accidents is increasing every year. How
to drive safely under the condition of numerous vehicles and narrow roads has become the focus of
attention. Advanced driver assistance systems which include lane departure warning (LDW), Lane
Keeping Assist, and Adaptive Cruise Control (ACC) can help people analyse the current driving
environment and provide appropriate feedback for safe driving or alert the driver in dangerous
circumstances. This kind of auxiliary driving system is expected to become more and more perfect.
However, the bottleneck of the development of this system is that the road traffic environment is
difficult to predict. After investigation, in a complex traffic environment where vehicles are numerous
and speed is too fast, the probability of accidents is much greater than usual. In such a complex traffic
situation, road colour extraction, texture detection, road boundary, and lane marking are the main
perceptual clues of human driving. Lane detection is a hot topic in the field of machine learning and
computer vision and has been applied in intelligent vehicle systems.
1.2 MOTIVATION
There are many researchers who have worked and are working on creating and developing many
techniques in intelligent transportation systems with advanced driving assistances system which are
able to ensure the safety in the roads and congested traffic conditions. The road accidents are the main
causes for the sudden death in this world. Even though we have many good and advanced techniques
in this world, we are left over with something to make it better than before. There are chances from
different angles. The road lane detection and object detection is also the other important way that we
can improve the safety in roads. Vehicle crashes remain the leading cause of accident death and
injuries in Malaysia and Asian countries claiming tens of thousands of lives and injuring millions of
people each year. Most of these transportation deaths and injuries occur on the nation’s highways.
The United Nations has ranked Malaysia 30th among countries with the highest number of fatal road
accidents, registering an average of 4.5 deaths per 10,000 registered vehicles.
It is not only limited to one country most of the traffic congested countries like U.S, India, other Asian
countries have many calculation of deaths and injuries.
1.3 DIGITAL IMAGE PROCESSING

Image processing is a method to perform some operations on an image, in order to get an enhanced
image or to extract some useful information from it. It is a type of signal processing in which input is
an image and output may be image or characteristics/features associated with that image. Nowadays,
image processing is among rapidly growing technologies. It forms core research area within
engineering and computer science disciplines too. Image processing is a method to perform some
operations on an image, in order to get an enhanced image and or to extract some useful information
from it. If we talk about the basic definition of image processing then “Image processing is the
analysis and manipulation of a digitized image, especially in order to improve its quality”.
Digital-Image: An image may be defined as a two-dimensional function f(x, y), where x and y are
spatial (plane) coordinates, and the amplitude of fat any pair of coordinates (x, y) is called the intensity
or grey level of the image at that point. In another word An image is nothing more than a two-
dimensional matrix (3-D in case of coloured images) which is defined by the mathematical function
f(x, y) at any point is giving the pixel value at that point of an image, the pixel value describes how
bright that pixel is, and what colour it should be.
Image processing is basically signal processing in which input is an image and output is image or
characteristics according to requirement associated with that image.
1.3.1 STEPS IN IMAGE PROCESSING
Image processing basically includes the following three steps:
• Importing the image via image acquisition tools;

• Analysing and manipulating the image;
• Output in which result can be altered image or report that is based on image analysis
There are two types of methods used for image processing namely, analogue and digital image

processing. Analogue image processing can be used for the hard copies like printouts and
photographs. Image analysts use various fundamentals of interpretation while using these
visual techniques. Digital image processing techniques help in manipulation of the digital
images by using computers. The three general phases that all types of data have to undergo
while using digital technique are pre-processing, enhancement, and display, information
extraction.
What is an Image?
An image is defined as a two-dimensional function, F (x, y), where x and y are spatial coordinates,
and the amplitude of F at any pair of coordinates (x, y) is called the intensity of that image at that
point. When x, y and amplitude values of F are finite, we call it a digital image. In other words, an
image can be defined by a two-dimensional array specifically arranged in rows and columns. Digital
Image is composed of a finite number of elements, each of which elements have a particular value at
a particular location. These elements are referred to as picture elements, image elements, and pixels.
A Pixel is most widely used to denote the elements of a Digital Image.
1.3.2 IMAGE IN MATRIX REPRESENTATION

As we know, images are represented in rows and columns we have the following syntax in
which images are represented:
The right side of this equation is digital image by definition. Every element of this matrix is called
image element, picture element, or pixel.
1.3.3 TYPES OF AN IMAGE

Binary Image– The binary image as its name suggests, contain only two pixel elements i.e. 0 & 1,
where 0 refers to black and 1 refers to white. This image is also known as Monochrome.

Black and White Image– The image which consist of only black and white colour is called Black
and White Image.
8 Bit Colour Format– It is the most famous image format. It has 256 different shades of colours in
it and commonly known as Grayscale Image. In this format, 0 stands for Black, and 255 stands for
white, and 127 stands for grey.
16 Bit Colour Format– It is a colour image format. It has 65,536 different colours in it. It is also
known as High Colour Format. In this format the distribution of color is not as same as Grayscale
image.
A 16-bit format is actually divided into three further formats which are Red, Green and Blue. That
famous RGB format.
1.4 SELF DRIVING CARS

A self-driving car (sometimes called an autonomous car or driverless car) is a vehicle that uses a
combination of sensors, cameras, radar and artificial intelligence (AI) to travel between destinations
without a human operator. To qualify as fully autonomous, a vehicle must be able to navigate without
human intervention to a predetermined destination over roads that have not been adapted for its use.
Levels of autonomy in self-driving cars
The U.S. National Highway Traffic Safety Administration (NHTSA) lays out six levels of automation,
beginning with zero, where humans do the driving, through driver assistance technologies up to fully
autonomous cars. Here are the five levels that follow zero automation:
Level 1: Advanced driver assistance system (ADAS) aid the human driver with either steering,
braking or accelerating, though not simultaneously. ADAS includes rear view cameras and features
like a vibrating seat warning to alert drivers when they drift out of the traveling lane.
Level 2: An ADAS that can steer and either brake or accelerate simultaneously while the driver
remains fully aware behind the wheel and continues to act as the driver.
Level 3: An automated driving system (ADS) can perform all driving tasks under certain
circumstances, such as parking the car. In these circumstances, the human driver must be ready to re-
take control and is still required to be the main driver of the vehicle.

Level 4: An ADS is able to perform all driving tasks and monitor the driving environment in certain
circumstances. In those circumstances, the ADS is reliable enough that the human driver needn't pay
attention.
Level 5: The vehicle's ADS acts as a virtual chauffeur and does all the driving in all circumstances.
The human occupants are passengers and are never expected to drive the vehicle.
1.5 LANE DETECTION BY VEHICLE

Lane lines are being drawn , Also you can see the radius of curvature is being calculated to
help the vehicle steer. It is cheap to equip cars with a front facing camera. Much cheaper than RADAR
or LIDAR. Once we get a camera image from the front facing camera of self-driving car, we make
several modifications to it. The steps It followed are detailed below:
1.5.1 Distortion correction

Image distortion occurs when a camera looks at 3D objects in the real world and transforms them into
a 2D image. This transformation isn’t always perfect and distortion can result in a change in apparent
size, shape or position of an object. So we need to correct this distortion to give the camera an
accurate view of the image. This is done by computing a camera calibration matrix by taking several
chessboard pictures of a camera. See example below of a distortion corrected image. Please note that
the correction is very small in normal lenses and the difference isn’t visible much to the naked eye.
Figure 1: Describing the original image and undistorted image

Figure 2: Examples of lane detection
1.5.2 Create a binary image

Now that we have the undistorted image, we can start our analysis. We need to explore different
schemes so that we can clearly detect the object of interest on the road, in this case lane lines while
ignoring the rest. It can be done by this two ways:
• Using Sobel operator to compute x-gradient
The gradient of an image can be used to identify sharp changes in colour in a black and white
image. It is a very useful technique to detect edges in an image. For the image of a road, we
usually have a lane line in either yellow or white on a black road and so x-gradient can be
very useful.
• Explore other colour channels
HSV (Hue, Saturation and Value) colour space can be very useful in isolating the yellow and
line white lines because it isolates colour (hue), amount of colour (saturation) and brightness
(value). We can use the S colour channel in the image.
1.5.3 Features of lane marking
• Adapts to various types of roads.
• Color, style and width of markings recognition.
• Detects all road markings in the picture.
• Integrated navigation system, see the track ego lane change and offer advice. Adapts
to different weather and light condition
1.6 PROBLEM STATEMENT

Given an image captured from a camera attached to a vehicle moving on a road in which captured
road may or may not be well levelled, or have clearly delineated edges, or some prior known patterns
on it, then road detection from a single image can be applied to find the road in an image so that it
could be used as a part in automation of driving system in the vehicles for moving the vehicle in
correct road. In this process of finding the road in the image captured by the vehicle, we can use some
algorithms for vanishing point detection using Hough transform space, finding the region of interest,
edge detection using canny edge detection algorithm and then road detection. We use thousands of
images of different roads to train our model so that the model could detect the road which is present
in the new image processed through the vehicle.

Chapter 2
LITERATURE SURVEY
2.1 EDGE DETECTION

Edges characterize boundaries and are therefore a problem of fundamental importance in image
processing. Edges in images are areas with strong intensity contrasts – a jump in intensity from one
pixel to the next. Edge detecting an image significantly reduces the amount of data and filters out
useless information, while preserving the important structural properties in an image.Canny edge
detection algorithm is also known as the optimal edge detector. Cranny’s intentions were to enhance
the many edge detectors in the image.
 The first criterion should have low error rate and filter out unwanted information while the useful
information preserve.
 The second criterion is to keep the lower variation as possible between the original image and the
processed image.
 Third criterion removes multiple responses to an edge
Based on these criteria, the canny edge detector first smoothens the image to eliminate noise. It then
finds the image gradient to highlight regions with high spatial derivatives. The algorithm then tracks
along these regions and suppresses any pixel that is not at the maximum using non-maximum
suppression. The gradient array is now further reduced by hysteresis to remove streaking and thinning
the edges.
2.2 FILTER OUT NOISE

2.2.1 CONVOLUTION
First step to Canny edge detection require some method of filter out any noise and still preserve
the useful image. Convolution is a simple mathematic method to many common imageprocessing
operators.

Figure 3.a: An example small image (left), kernel (right)
2.2.2 CONVOLUTION OPERATION

Convolution is performed by sliding the kernel or mask over a greylevel image. The kernel starts
from the top left corner and moves through entire image within image boundaries. Each kernel
position corresponds to a single output pixel. Each pixel is multiplied with the kernel cell value
and added together. The output image will have M-m+1 rows and N-n+1 column, M image rows
and N image columns, m kernel rows and n kernel columns. The output image will be smaller
when compared to the original image. This is due to the bottom and right edge pixels, which
can’t be completely mapped by the kernel therefore m –1 right hand pixel and n-1 bottom pixels
can’t be used.
Step 1: Gaussian filtering to remove noise
The first step of canny edge detection is to filter out any noise in the original image before trying to
locate and detect any edges. The Gaussian filter is used to blur and remove unwanted detail and noise.
By calculating a suitable 5 X 5 mask, the Gaussian smoothing can be performed using standard
convolution method. A convolution mask is much smaller than the actual image. As a result, the mask
is slid over the image, calculating every square of pixels at a time.Gaussian filter uses 2D distribution
to perform convolution. The larger the width of the Gaussian mask, the lower is the detector's
sensitivity to noise. The weight of the matrix is concentrated at the center, therefore any noise
appearing in the outside columns and rows will be eliminated, as the weight decreases outward from
the center value. The localization error in the detected edges also increases slightly as the Gaussian
width is increased. The increasing of standard deviation reduces or blurs the intensity of the noise.

Figure 3.b: Gaussian filter in mathematical form
Figure 3.c: Original Image on top and Gaussian filtered image at bottom
Step 2: Sobel Operator
After smoothing the image and eliminating the noise, the next step is to find the edge strength by
taking the gradient of the image. The Sobel operator performs a 2-D spatial gradient measurement
on an image. Then, the approximate absolute gradient magnitude (edge strength) at each point can
be found by the formula below which is simpler to calculate compared to the above exact gradient
magnitude
Approximate gradient magnitude given below:
| | = | x| + | y|
The Sobel operator uses a pair of 3x3 convolution masks, one estimating the gradient
in the x-direction (columns) and the other estimating the gradient in the ydirection (rows).
Sobel x and y masks shown below each one estimates gradient x direction and y direction
respectively:
Figure 3.d: Original image and image after sobel operation

Step 3: Finding Gradient angle
Finding the edge direction is trivial once the gradient in the x and y directions are known.
However, you will generate an error whenever sum of x is equal to zero i.e. y value in
denominator meaning calculating arctan of infinity. So, the edge direction will equal to 90 or 0
degrees depend on Gx value and 0 degrees depend on y value.
Step 4: Tracing the edge in the image using (angle)
Once the edge direction is known, the next step is to relate the edge direction to a direction that
can be traced in an image. So, if use the 5x5 matrix to calculate the angle of the edge, the
smaller the matrix the fewer angles would have in the image
xx x x
xxx x
x xxx
a xxx
x x x
xxx x
x x

By looking at the center pixel "a", there are four possible directions when describing the surrounding
pixels - 0 degrees (in the horizontal direction), 45 degrees (along the positive diagonal), 90 degrees
(in the vertical direction), or 135 degrees (along the negative diagonal), 180 degrees region is just an
mirror region of 0 degrees region. Therefore, any edge direction calculated will be round up to the
closest angle.
So, any edge direction falling within the A and E (0 to 22.5 & 157.5 to 180 degrees) is set to 0 degrees.
Any edge direction falling in the D (22.5 to 67.5 degrees) is set to 45 degrees. Any edge direction
falling in the C (67.5 to 112.5 degrees) is set to 90 degrees. And finally, any edge direction falling
within the B (112.5 to 157.5 degrees) is set to 135 degrees.
Figure 3.e: Tracing an Edge of an Image

The bigger the matrix the greater number of angles one could get, which implies the edge
angle will be more precise i.e. will follow the edge better, but on the down side it will be a
bigger computation task as now the kernel/mask size is bigger.
Step 5: Non maximum Suppression

After the edge directions are known, non-maximum suppression is applied. Non- maximum
suppression is used to trace along the gradient in the edge direction and compare the value
perpendicular to the gradient. Two perpendicular pixel values are compared with the value in the edge
direction. If their value is lower than the pixel on the edge then they are suppressed i.e. their pixel value
is changed to 0, else the higher pixel value is set as the edge and the other two suppressed with a pixel

value of 0.We wish to mark points along the curve where the magnitude is biggest. We can do this by
looking for a maximum along a slice normal to the curve (non-maximum suppression). These points
should form a curve. There are then two algorithmic issues: at which point is the maximum, and where
is the next one?
Step 6: Hysteresis
Finally, hysteresis is used as a means of eliminating streaking. Streaking is the breaking up of an edge
contour caused by the operator output fluctuating above and below the threshold. If a single threshold,
T1 is applied to an image, and an edge has an average strength equal to T1, then due to noise, there
will be instances where the edge dips below the threshold. Equally it will also extend above the
threshold making an edge look like a dashed line. To avoid this, hysteresis uses 2 thresholds, a high
and a low. Any pixel in the image that has a value greater than T1 is presumed to be an edge pixel, and
is marked as such immediately. Then, any pixels that are connected to this edge pixel and that have a
value greater than T2 are also selected as edge pixels. If you think of following an edge, you need a
gradient of T2 to start but you don't stop till you hit a gradient below T1.
Figure 3.f: Showing Canny Edge Detection Process

2.3 Sample Input and Output of Canny Edge Detection Algorithm
Figure 2.g: Describing the Input Image
Figure 3.h: Describing the Output Image
2.4 HOUGH TRANSFORM SPACE

The Hough transform is a feature extraction technique used in image analysis, computer vision, and
digital image processing. The purpose of the technique is to find imperfect instances of objects within
a certain class of shapes by a voting procedure. This voting procedure is carried out in a parameter
space, from which object candidates are obtained as local maxima in a so-called accumulator space that

is explicitly constructed by the algorithm for computing the Hough transform.The classical Hough
transform was concerned with the identification of lines in the image, but later the Hough transform
has been extended to identifying positions of arbitrary shapes, most commonly circles or ellipses. The
Hough transform as it is universally used today was invented by Richard Duda and Peter Hart in 1972,
who called it a "generalized Hough transform" after the related 1962 patent of Paul Hough. The
transform was popularized in the computer vision community by Dana H Ballard through a 1981
journal article titled "Generalizing the Hough transform to detect arbitrary shapes"
2.4.1 Theory of Hough Transform Space

In automated analysis of digital images, a sub problem often arises of detecting
simple shapes, such as straight lines, circles or ellipses. In many cases an edge detector can be used as
a pre-processing stage to obtain image points or image pixels that are on the desired curve in the image
space. Due to imperfections in either the image data or the edge detector.
Figure 2.i: Hesse Normal Form Graph
It is therefore possible to associate with each line of the image a pair (r, θ). The (r, theta) plane is
sometimes referred to as Hough space for the set of straight lines in two dimensions.
2.5 IMPLEMENTATION OF HOUGH TRANSFORM SPACE
The linear Hough transform algorithm uses a two-dimensional array, called an accumulator, to
detect the existence of a line described by r=x cos theta+ y sin theta. The dimension of the
accumulator equals the number of unknown parameters, i.e., two, considering quantized values of
r and θ in the pair (r, θ). For each pixel at (x, y) and its neighborhood, the Hough transform
algorithm determines if there is enough evidence of a straight line at that pixel. If so, it will
calculate the parameters (r, θ) of that line, and then look for the accumulator's bin that the
parameters fall into, and increment the value of that bin. By finding the bins with the highest values,
typically by looking for local maxima in the accumulator space, the most likely lines can be

extracted, and their (approximate) geometric definitions read off. (Shapiro and Stockman, 304)
The simplest way of finding these peaks is by applying some form of threshold, but other
techniques may yield better results in different circumstances – determining which lines are found
as well as how many.
2.6 VARIATIONS AND EXTENSIONS
2.6.1 Using the gradient direction to reduce the number of votes

An improvement suggested by O'Gorman and Clowes can be used to detect lines if one takes into
account that the local gradient of the image intensity will necessarily be orthogonal to the edge.
Since edge detection generally involves computing the intensity gradient magnitude, the gradient
direction is often found as a side effect. If a given point of coordinates (x, y) happens to indeed be
on a line, then the local direction of the gradient gives the θ parameter corresponding to said line,
and the r parameter is then immediately obtained. (Shapiro and Stockman, 305) The gradient
direction can be estimated to within 20°, which shortens the sinusoid trace from the full 180° to
roughly 45°. This reduces the computation time and has the interesting effect of reducing the number
of useless votes, thus enhancing the visibility of the spikes corresponding to real lines in the image.
2.6.2 Kernel Based Hough Transform (KHT)
Fernandes and Oliveira suggested an improved voting scheme for the Hough transform that allows
a software implementation to achieve real-time performance even on relatively large images (e.g.,
1280×960). The Kernel-based Hough transform uses the same (r, theta) parameterization proposed
by Duda and Hart but operates on clusters of approximately collinear pixels. For each cluster, votes
are cast using an oriented Elliptical-Gaussian kernel that models the uncertainty associated with the
best-fitting line with respect to the corresponding cluster. The approach not only significantly
improves the performance of the voting scheme, but also produces a much cleaner accumulator and
makes the transform more robust to the detection of spurious lines.

2.7 HOUGH TRANSFORM OF CURVES, AND ITS GENERALIZATION FOR

ANALYTICAL AND NON-ANALYTICAL SHAPES
Although the version of the transform described above applies only to finding straight lines, a similar
transform can be used for finding any shape which can be represented by a set of parameters. A circle,
for instance, can be transformed into a set of three parameters, representing its centre and radius, so
that the Hough space becomes three dimensional. Arbitrary ellipses and curves can also be found this
way, as can any shape easily expressed as a set of parameters.
2.8 CIRCLE DETECTION PROCESS
Altering the algorithm to detect circular shapes instead of lines is relatively straightforward.
• First, we create the accumulator space, which is made up of a cell for each pixel. Initially each
cell is set to 0.
• For each edge point (i, j) in the image, increment all cells which according to the equation of a
circle ((i-a)2+(j-b)2=r2 ) could be the centre of a circle. These cells are represented by the letter a
in the equation
• For each possible value of a found in the previous step, find all possible values of b which satisfy
the equation.
• Search for local maxima in the accumulator space. These cells represent circles that were detected
by the algorithm.
If we do not know the radius of the circle we are trying to locate beforehand, we can use a
threedimensional accumulator space to search for circles with an arbitrary radius. Naturally, this is
more computationally expensive. Y circle's area is still present within it.
2.9 Detection of 3D objects (Planes and cylinders)
Hough transform can also be used for the detection of 3D objects in range data or 3D point
clouds. The extension of classical Hough transform for plane detection is quite
straightforward. A plane is represented by its explicit equation z=axx+ayy+d for which we
can use a 3D Hough space corresponding to ax, ay and d. This extension suffers from the
same problems as its 2D counterpart i.e., near horizontal planes can be reliably detected, while
the performance deteriorates as planar direction becomes vertical (big values of ax and ay
amplify the noise in the data). This formulation of the plane has been used for the detection
of planes in the point clouds acquired from airborne laser scanning [13] and works very well
because in that domain all planes are nearly horizontal.

2.10 USING WEIGHTED FEATURES

One common variation detail. That is, finding the bins with the highest count in one stage can be used
to constrain the range of values searched in the next.
2.11 CAREFULLY CHOSEN PARAMETER SPACE
A high-dimensional parameter space for the Hough transform is not only slow, but if implemented
without forethought can easily overrun the available memory. Even if the programming environment
allows the allocation of an array larger than the available memory space through virtual memory, the
number of page swaps required for this will be very demanding because the accumulator array is used
in a randomly accessed fashion, rarely stopping in contiguous memory as it skips from index to
index.Consider the task of finding ellipses in an 800x600 image.
2.12 EFFICIENT ELLIPSE DETECTION ALGORITHM

Yonghong Xie and Qiang Ji give an efficient way of implementing the Hough transform for ellipse
detection by overcoming the memory issues As discussed in the algorithm (on page 2 of the paper),
this approach uses only a one-dimensional accumulator (for the minor axis) in order to detect ellipses
in the image. The complexity is O(N3 ) in the number of non-zero points in the image.
2.13 EXISTING SYSTEM
In the current existing system is permitted only to use in ideal road conditions such as runway. This
could not be used in general roads because the edge detection used till now was Simulink Edge
Detection which is implemented in MATLAB. The secondary thing is in current system Hough
transform Space is only used for angle rotation and has very limited road dataset to detect the objects
in single dimension of an image
2.14 LIMITATIONS OF EXISTING SYSTEM
The Hough transform is only efficient if a high number of votes fall in the right bin, so that the bin
can be easily detected amid the background noise. This means that the bin must not be too small, or
else some votes will fall in the neighboring bins, thus reducing the visibility of the main bin.
2.15 PROPOSED SYSTEM
In our proposed system we use Canny Edge Detection replacing the Simulink Edge Detection which
is recent and efficient implementation in Python instead of MATLAB. Since, Python is the Scripting
and Statistical Modelling Language it supports faster execution for mathematical functions which
could be used by Canny Edge Detection technique. Secondly, we use Hough Transform Space for 3-
Dimensional Object detection which could faster and accurate compared to single dimension object
detection.
Chapter 3 SYSTEM REQUIREMENTS

3.1 SYSTEM CONFIGURATION
3.1.1 Software Configuration

the Software Configurations that are required.
 Operating System: Windows 11/10/8/7 (incl. 64-bit), Mac OS, Linux
 Operating System lies in the category of system software. It basically manages all the
resources of the computer. An operating system acts as an interface between the software and
different parts of the computer or the computer hardware. The operating system is designed in
such a way that it can manage the overall resources and operations of the computer.
 We have used Windows 11 OS for our project
 Language: Python 3.5

 Python is an easy to learn, powerful programming language. It has efficient high-level data
structures and a simple but effective approach to object-oriented programming.
Python’s elegant syntax and dynamic typing, together with its interpreted nature, make it an
ideal language for scripting and rapid application development in many areas on most
platforms.
 IDE: Jupyter Notebook/ Spyder 3
 The Jupyter Notebook is an open-source web application that allows you to create and share
documents that contain live code, equations, visualizations, and narrative text.
Uses include data cleaning and transformation, numerical simulation, statistical
 Python Libraries
 OpenCV: OpenCV is a huge open-source library for computer vision, machine learning, and
image processing. OpenCV supports a wide variety of programming languages like Python,
C++, Java, etc.
 Numpy: The name “Numpy” stands for “Numerical Python”. It is the commonly used library.
It is a popular machine learning library that supports large matrices and multidimensional data.
It consists of in-built mathematical functions for easy computations.
3.1.2 Hardware Configuration
The minimum Hardware configurations that are required are:

 Processor: To handle vast amounts of image data and perform sophisticated machine learning
algorithms, a quick and powerful CPU is required. A processor from Intel Core i5 or i7 series or
a similar would work.
 Memory (RAM): A considerable amount of image data and machine learning models must be
stored and processed, hence a sufficient amount of RAM is needed. Although 16GB or more may
be needed for apps that demand additional memory, 8GB is the least amount that is advised.
 Storage: To store video and image data, machine learning models, and other software
components, there must be enough storage space. Fast data access and processing require an SSD
with at least 256GB of storage space.

Chapter 4 SYSTEM DESIGN
4.1 PROPOSED SYSTEM OVERVIEW
Figure 4.1 Proposed System Overview

4.1.2 IMAGE PROCESSING METHODOLOGY
Digital image processing consists of the manipulation of images using digital computers. Its use
has been increasing exponentially in the last decades. Its applications range from medicine to
entertainment, passing by geological processing and remote sensing. Multimedia systems, one of
the pillars of the modern information society, rely heavily on digital image processing.
4.2 ARCHITECTURE
System architecture of a road detection from a single image using computer vision consists mainly
the image which can be sent to a model and the output which consists of marking of detections of a
road. The system architecture starts by selecting a required image which is captured by driving camera
of a self-driving car. This should consist of all the details along with the road which should be detected
by the computer. This image should be sent to the model. All these algorithms are compounded
together to form a edge. detection model by Canny’s process. The selected image is first sent to
Canny’s model and edges are found in an image. This edge detected image is then sent into road line
detection model which is formed using Hough Transform Space algorithm. Hough transform space
algorithm normalizes the sent image and then changes the value of in the normalized trigonometric
line equation and thus detects the required road lines in an image. The only image with edges is sent
into the Hough Transform Space algorithm, because the image with more noise takes large time for
calculation rather than the image consists only edges of an image.
Image showing an architecture of a project: Road Detection from an Image using ComputerVision

4.3 CANNY EDGE DETECTION ARCHITECTURE:
This process consists of mainly four functions in it. The image can be of any type which consists of
change in intensity in it. The change in intensity of pixels in an image defines the edges in an image.
The canny edge detection mainly focuses on change in intensity in an image. The change in pixel’s
intensities from high intensity to low intensity is known as edge. At first, the color image is changed
into black and white image and is passed to smoothening technique. We use Gaussian blur as a
smoothening technique followed by gradient calculations, Non- maximum suppression and double
threshold. Edge detection mainly use derivatives of pixel intensities in an image and then reduce the
complexity of an image. The edge is detected when there is change in intensity from high
low which refers white shades to black shades (in gray scale image) in an image. Gray Scale image
is used because it would be easy to process the gray scale image than the colored image. A gradient
calculation process is used for calculating the through Sobel filters.Non-Maximum suppression is
a process of thinning of edges that should be occurred in a required output image. Then a double
thresholding is done to intensify the strong pixels of an output image and to close the intensity of
weaker pixels in an image.

4.4 PROJECT MODULES
Road Lane Line Detection from a single image using Computer Vision consists of image insertion,
model building and then testing. The model evaluation is done manually by the developer. We
divided the complete project into mainly four modules. They are as follows:
 Module 1: Selecting the appropriate testing image.
 Module 2: Preprocessing the selected image.
 Module 3: Edge Detection Implementation.
 Module 4: Hough Transformation.

 Module 5: Evaluating the output.
Module 1: Selecting the appropriate testing image
It is the most important process in the project. Single Image from testing dataset is taken such a
way that it reaches our implementation of a model. Each model we implement takes a resultant
image as an input and process it further to produce an output. This selection of image is more
important because implementation of each model requires an image input for processing.
Module 2: Preprocessing the selected image

Preprocessing plays a major role in producing the required output in sufficient required amount of
time. Preprocessing of selected image mainly undergo the gray scale conversion and smoothening
techniques which would be considered as the first process in Canny’s process. The selected image
is converted into gray scale through the open source computer vision package.
Data preprocessing techniques might include:
Grey Scale Image Conversion:

Convert color images to grayscale to reduce computation complexity: in certain problems you’ll
find it useful to lose unnecessary information from your images to reduce space or computational
complexity.
Module 3: Edge Detection Implementation
The next step in the process if edge detection, which is main part in the program and required to
detect the edges in the image irrespective of details present in an image. We use Canny Edge
Detection Algorithm to implement the edge detection techniques because the other processes
which are also used to find the edges in an image would contain detailed images compared to

Canny Edge Detection Technique. Canny Edge Detection technique mainly consists of four
processes in it.
The general criteria for edge detection include:

I. Detection of edge with low error rate, which means that the detection should accurately catch
as many edges shown in the image as possible.
II. The edge point detected from the operator should accurately localize on the center of the
edge.
III. A given edge in the image should only be marked once, and where possible, image noise
should not create false edges.
Module 4: Hough Transformations
Hough Transformations require a Hough transformation space which is used to rotate the angles of a
trigonometric line equation and then specify the lines present in an edge detected image. If the
trigonometric line in rotation meets the edges in the image, then it may consider for applying the
model trained for detecting roads in an image. The training is done in Hough transformation space
which is used to detect the actual road lines from an image. When the Hough transformations and
training is done, then the road lines are detected on the selected image.The Hough transform is a
technique which can be used to isolate features of a particular shape within an image. Because it
requires that the desired features be specified in some parametric form, the classical Hough transform
is most commonly used for the detection of regular curves such as lines, circles, ellipses, etc. A
generalized Hough transform can be employed in applications where a simple analytic description of
a feature(s) is not possible. Due to the computational complexity of the generalized Hough algorithm,
we restrict the main focus of this discussion to the classical Hough transform.
We can analytically describe a line segment in a number of forms. However, a convenient equation
for describing a set of lines uses parametric or normal notion:
X cos t + Y sin t = r
Module 5: Evaluating the output
Evaluation of output is done through confusion matrix and the accuracy metrics when a testing
dataset is passed.This forms a confusion matrix and then accuracy, precision scores can be noted.
This process is known as Evaluation. Thus, all the accuracy and precision of a model are noted.

Chapter 5
IMPLEMENTATION
5.1 PSEUDO-CODE
1. grayscale(img):
- This function takes an input image ìmg` and converts it to grayscale using OpenCV's
`cv2.cvtColor` function. Grayscale images have only one channel, representing the intensity of each
pixel.
2. canny(img, low_threshold, high_threshold):
- This function applies the Canny edge detection algorithm to the input image ìmg` with
specified low and high threshold values. It detects edges in the image, highlighting sudden changes
in intensity.
3. gaussian_blur(img, kernel_size):
- Applies Gaussian blur to the input image ìmg` using a specified kernel size. Gaussian blurring
helps reduce noise in the image, which is important for edge detection.
4. region_of_interest(img, vertices):
- Masks the input image ìmg` to keep only the region defined by the polygon specified by
`vertices`. This function is used to focus on a specific region of interest, typically the area where lane
lines are expected.
5. draw_lines(img, lines, color, thickness):
- This function is used to draw lines on an image. It takes a list of lines, where each line is
represented as a pair of points (x1, y1) and (x2, y2), and draws them on the input image ìmg`. The
lines are drawn in the specified `color` with the given `thickness`.
6. Main script:
import matplotlib.pyplot as plt import
matplotlib.image as mpimg import numpy
as np import cv2 from moviepy.editor
import VideoFileClip import math import
os
low_threshold = 50 high_threshold
= 150
rho = 2

grayscale(img):
"""Applies the Grayscale transform
This will return an image with only one color channel
but NOTE: to see the returned image as grayscale you
should call plt.imshow(gray, cmap='gray')""" return
cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
def canny(img, low_threshold, high_threshold):

"""Applies the Canny transform""" return
cv2.Canny(img, low_threshold, high_threshold)
def gaussian_blur(img, kernel_size): """Applies a Gaussian

Noise kernel""" return cv2.GaussianBlur(img, (kernel_size,
kernel_size), 0)
def region_of_interest(img, vertices):

mask = np.zeros_like(img)
channel_count = img.shape[2] # i.e. 3 or 4 depending on your image ignore_mask_color
= (255,) * channel_count
else:
ignore_mask_color = 255
def draw_lines(img, lines, color=[255, 0, 0], thickness=10):

"""
NOTE: this is the function you might want to use as a starting point once you want
to average/extrapolate the line segments you detect to map out the full extent of
the lane (going from the result shown in raw-lines-example.mp4 to that shown in
P1_example.mp4).
0: return
draw_right = True
elif slopes[i] < 0 and x1 < img_x_center and x2 < img_x_center:
left_lines.append(line)

# Run linear regression to find best fit line for right and left lane lines
# Right lane lines
right_lines_x = []
right_lines_y = []
for line in right_lines:

x1, y1, x2, y2 = line[0]
right_lines_x.append(x1)
right_lines_x.append(x2)
right_lines_y.append(y1)
right_lines_y.append(y2)
if len(right_lines_x) > 0:
right_m, right_b = np.polyfit(right_lines_x, right_lines_y, 1) # y = m*x + b else:
right_m, right_b = 1, 1
draw_right = False
# Left lane lines

left_lines_x = []
left_lines_y = []
for line in left_lines:

x1, y1, x2, y2 = line[0]
left_lines_x.append(x1)
left_lines_x.append(x2)
left_lines_y.append(y1)
left_lines_y.append(y2)
if
len(left_lines_x) > 0:

left_m, left_b = np.polyfit(left_lines_x, left_lines_y, 1) # y = m*x + b else:

left_m, left_b = 1, 1
draw_left = False
# Find 2 end points for right and left lines, used for drawing the line
# y = m*x + b --> x = (y - b)/m y1
= img.shape[0] y2 = img.shape[0] *
(1 - trap_height)
right_x1 = (y1 - right_b) / right_m

right_x2 = (y2 - right_b) / right_m
left_x1 = (y1 - left_b) / left_m

left_x2 = (y2 - left_b) / left_m
# Convert calculated end points from float to

int y1 = int(y1) y2 = int(y2) right_x1 =
int(right_x1) right_x2 = int(right_x2) left_x1
= int(left_x1) left_x2 = int(left_x2)
# Draw the right and left lines on image if

draw_right:
cv2.line(img, (right_x1, y1), (right_x2, y2), color, thickness) if
draw_left:
cv2.line(img, (left_x1, y1), (left_x2, y2), color, thickness)
def hough_lines(img, rho, theta, threshold, min_line_len, max_line_gap):

"""
ìmg` should be the output of a Canny transform.
Returns an image with hough lines drawn.

"""
lines = cv2.HoughLinesP(img, rho, theta, threshold, np.array([]), minLineLength=min_line_len,
maxLineGap=max_line_gap)
line_img = np.zeros((*img.shape, 3), dtype=np.uint8) # 3-channel RGB image
draw_lines(line_img, lines) return line_img
# Python 3 has support for cool math symbols.
def weighted_img(img, initial_img, α=0.8, β=1., λ=0.):

"""
ìmg` is the output of the hough_lines(), An image with lines drawn on it.
Should be a blank image (all black) with lines drawn on it.
ìnitial_img` should be the image before any processing.
The result image is computed as follows:
initial_img * α + img * β + λ
NOTE: initial_img and img must be the same shape!
"""
return cv2.addWeighted(initial_img, α, img, β, λ)
def filter_colors(image):
"""
Filter the image to include only yellow and white pixels
"""
# Filter white pixels white_threshold = 200 #130 lower_white =
np.array([white_threshold, white_threshold, white_threshold]) upper_white =
np.array([255, 255, 255]) white_mask = cv2.inRange(image, lower_white,
upper_white) white_image = cv2.bitwise_and(image, image,
mask=white_mask)
# Filter yellow pixels

hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV) lower_yellow

= np.array([90,100,100]) upper_yellow = np.array([110,255,255])
yellow_mask = cv2.inRange(hsv, lower_yellow, upper_yellow)
yellow_image = cv2.bitwise_and(image, image, mask=yellow_mask)
# Combine the two above images image2 =

cv2.addWeighted(white_image, 1., yellow_image, 1., 0.)
return image2
def annotate_image_array(image_in):
""" Given an image Numpy array, return the annotated image as a Numpy array """
# Only keep white and yellow pixels in the image, all other pixels become black
image = filter_colors(image_in)
# Read in and grayscale the image

gray = grayscale(image)
# Apply Gaussian smoothing

blur_gray = gaussian_blur(gray, kernel_size)
# Apply Canny Edge Detector

edges = canny(blur_gray, low_threshold, high_threshold)
# Create masked edges using trapezoid-shaped region-of-interest

imshape = image.shape vertices = np.array([[\
((imshape[1] * (1 - trap_bottom_width)) // 2, imshape[0]),\
((imshape[1] * (1 - trap_top_width)) // 2, imshape[0] - imshape[0] * trap_height),\
(imshape[1] - (imshape[1] * (1 - trap_top_width)) // 2, imshape[0] - imshape[0] * trap_height),\
(imshape[1] - (imshape[1] * (1 - trap_bottom_width)) // 2, imshape[0])]]\
, dtype=np.int32) masked_edges =
region_of_interest(edges, vertices)

# Run Hough on edge detected image line_image = hough_lines(masked_edges, rho, theta,

threshold, min_line_length, max_line_gap)
# Draw lane lines on the original image initial_image =

image_in.astype('uint8') annotated_image =
weighted_img(line_image, initial_image)
return annotated_image
def annotate_image(input_file, output_file):

""" Given input_file image, save annotated image to output_file """
annotated_image = annotate_image_array(mpimg.imread(input_file))
plt.imsave(output_file, annotated_image)
def annotate_video(input_file, output_file):

""" Given input_file video, save annotated video to output_file """
video = VideoFileClip(input_file)
annotated_video = video.fl_image(annotate_image_array)
annotated_video.write_videofile(output_file, audio=False) # End helper functions
# Main script if name

== ' main ':
from optparse import OptionParser
# Configure command line options parser = OptionParser()

parser.add_option("-i", "--input_file", dest="input_file",
help="Input video/image file") parser.add_option("-o", "--
output_file", dest="output_file", help="Output
(destination) video/image file") parser.add_option("-I", "--
image_only", action="store_true", dest="image_only",
default=False, help="Annotate image (defaults to
annotating video)")

# Get and parse command line options

options, args = parser.parse_args()
input_file = options.input_file
output_file = options.output_file
image_only = options.image_only
if image_only:
annotate_image(input_file, output_file)
else:
annotate_video(input_file, output_file)
Chapter 6 RESULTS AND DISCUSSIONS
Figure 6.1: Solid White Curve
This image contains a white curved lane which later will be processed to annotate the lanes.

Figure 6.2: Solid White Curve Annotated
This image is processed image of figure 6.1 in which the road lanes are marked with red lines
Figure 6.3: Solid White Right

This image contains a white straight lane which later will be processed to annotate the lanes.
Figure 6.4: Solid White Right Annotated
This image is processed image of figure 6.3 in which the road lanes are marked with red lines

Figure 6.5: Solid Yellow Curve
This image contains a yellow curved lane which later will be processed to annotate the lanes.
Figure 6.6: Solid Yellow Curve Annotate
Figure 6.7: Solid Yellow Curve 2

This image contains a yellow curved lane which later will be processed to annotate the lanes. This is an
second example of yellow lanes.
Figure 6.8: Solid Yellow Curve 2 Annotated
This image is processed image of figure 6.7 lines
Figure 6.9: Solid Yellow Left
This image contains a yellow straight lane which later will be processed to annotate the lanes.

CONCLUSION
In conclusion, road lane line detection using machine learning represents a significant advancement in
the field of computer vision and autonomous driving. This technology plays a crucial role in enhancing
road safety, enabling self-driving vehicles, and improving the overall driving experience. Through the
utilization of various machine learning algorithms and techniques, such as convolutional neural
networks (CNNs) and image processing, accurate lane line detection can be achieved even in
challenging and dynamic real-world conditions.
FUTURE SCOPE
The future scope of road lane line detection using machine learning is exceptionally promising, with
a wide range of potential applications and advancements on the horizon. One of the most significant
areas of impact lies in the realm of autonomous vehicles. As self-driving technology continues to
evolve, lane detection will play a crucial role in ensuring the safe and reliable navigation of these
vehicles. Enhanced accuracy and robustness in lane detection systems will be essential for autonomous
cars to handle various real-world scenarios. Moreover, advanced driver assistance systems (ADAS)
will see further improvements, benefiting from more sophisticated lane detection algorithms to
enhance driver safety and comfort. The integration of multiple sensors, such as radar, lidar, and V2X
communication, will provide a holistic understanding of the road environment, contributing to safer
and more efficient transportation.

BIBLIOGRAPY
• Simplilearn.ML Tutorial
• Scikit-learn: Machine Learning in Python.
• Pandas Documentation: powerful data analysis tools for Python.
• " Road Lane-Line Detection " Dataset. Kaggle.
• Bird, S., Klein, E., & Loper, E. (2009). Natural Language Processing with Python. O'Reilly
Media.
• Gonzalez, R.C., and Woods, R.E. (2008). "Digital Image Processing." Pearson Education.
• Sonka, M., Hlavac, V., and Boyle, R. (2007). "Image Processing, Analysis, and Machine
Vision." Cengage Learning.
• Jain, A.K. (1989). "Fundamentals of Digital Image Processing." Prentice-Hall.
• Prince, S.J.D. (2012). "Computer Vision: Models, Learning, and Inference." Cambridge
University Press.
• Burger, W., and Burge, M.J. (2016). "Digital Image Processing: An Algorithmic Introduction
Using Java." Springer.
• Robust Drivable Road Region Detection for Fixed-Route Autonomous Vehicles Using
MapFusion Images. Authors - Yichao Cai, Dachuan Li, Xiao Zhou, Xingang Mou
https://pubmed.ncbi.nlm.nih.gov/30486408/
• Lane-GAN: A Robust Lane Detection Network for Driver Assistance System in High Speed
and Complex Road Conditions. Authors - Yan Liu , Jingwen Wang , Yujie Li, Canlin Li,
Weizheng Zhang. https://pubmed.ncbi.nlm.nih.gov/35630183/
• Lane Detection Algorithm for Intelligent Vehicles in Complex Road Conditions and
Dynamic Environments. Authors - Jingwei Cao , Chuanxue Song , Shixin Song , Feng Xiao, Silun
Peng https://pubmed.ncbi.nlm.nih.gov/31323875/
• A computer vision-based lane detection technique using gradient threshold and huelightness-
saturation value for an autonomous vehicle. Authors - Almukhtar Firas HushamLI
ZhaiMiah ShahajanNoman Md. Abdullah AlOmarov BatyrkhanRahaman Md. FaishalRay
SamratWang Chengping. https://core.ac.uk/works/129594808

Shambhavi Report

Uploaded by

Copyright:

Available Formats

Shambhavi Report

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Shambhavi Report

Uploaded by

Copyright:

Available Formats

CONTRIVER®, Mysore

Department of computer science and engineering

INTERNSHIP TRAINING REPORT

Under the Guidance of

Department of Information science and engineering

Department of Department of computer science and engineering

Mrs. SYEDA ARBINA Ms. SANGEETHA Shri. SANJAY B

COURSE/EXAM INSTITUTION YEAR OF PASSING MARKS OBTAINED

S.S.L.C Millennium Public 2018 68

PUC Sri Channabasaveshwar 2020 68

B.E(CSE) Gurunanak Dev 2024

TRAINING ML using Python and Web

 Hardworking, dedicated, responsible, self confident,self motivated

Name : Sheetal Phulari

Father’s name : Shivkumar Phulari

Marital Status : Single

Languages Known : Kannada, English

Personal address : KIADB Housing area Beside BSNL Tower Naubad

Department of Testing and Programing, Contriver Page 1

1.3 DIGITAL IMAGE PROCESSING

• Importing the image via image acquisition tools;

Department of Testing and Programing, Contriver Page 3

1.3.2 IMAGE IN MATRIX REPRESENTATION

1.3.3 TYPES OF AN IMAGE

Department of Testing and Programing, Contriver Page 4

1.4 SELF DRIVING CARS

Department of Testing and Programing, Contriver Page 5

1.5 LANE DETECTION BY VEHICLE

1.5.1 Distortion correction

Figure 1: Describing the original image and undistorted image

Department of Testing and Programing, Contriver Page 6

Figure 2: Examples of lane detection

1.5.2 Create a binary image

1.6 PROBLEM STATEMENT

Department of Testing and Programing, Contriver Page 8

2.1 EDGE DETECTION

2.2 FILTER OUT NOISE

Department of Testing and Programing, Contriver Page 9

Figure 3.a: An example small image (left), kernel (right)

2.2.2 CONVOLUTION OPERATION

Department of Testing and Programing, Contriver Page 10

Figure 3.b: Gaussian filter in mathematical form

Figure 3.d: Original image and image after sobel operation

Department of Testing and Programing, Contriver Page 12

Figure 3.e: Tracing an Edge of an Image

Step 5: Non maximum Suppression

Department of Testing and Programing, Contriver Page 13

Figure 3.f: Showing Canny Edge Detection Process

Department of Testing and Programing, Contriver Page 14

2.3 Sample Input and Output of Canny Edge Detection Algorithm

Figure 2.g: Describing the Input Image

Figure 3.h: Describing the Output Image

2.4 HOUGH TRANSFORM SPACE

Department of Testing and Programing, Contriver Page 15

2.4.1 Theory of Hough Transform Space

Figure 2.i: Hesse Normal Form Graph

2.5 IMPLEMENTATION OF HOUGH TRANSFORM SPACE

Department of Testing and Programing, Contriver Page 16

2.6 VARIATIONS AND EXTENSIONS