You are on page 1of 22

A Seminar Report

on

Lane Line Detection


Submitted to the Savitribai Phule Pune University
in partial fulfillment of requirements for the award of degree

Third Year
in

CoMputer Engineering
by

Mr. Ashutosh Rajabhau Thorat


Seat No.: 72203181F

Under the Guidance of


Prof. Yoges h Shepal

DEPARTMENT OF COMPUTER ENGINEERING


NMVP and PCET’s Nutan Maharashtra Institute of Engineering & Technology,
Talegaon. 2023 - 24
DEPARTMENT OF COMPUTER ENGINEERING
Nutan Maharashtra Institute of Engineering Technology, Talegaon.
2023 - 24

CERTIFICATE
This is to certify that the report entitled Lane Line Detection submitted by Mr.
Ashutosh Rajabhau Thorat (Seat No.: 72203181F ), to the Savitribai Phule Pune
University in partial fulfillment of the Third Year degree in Computer Engineering is
a bonafide record of the seminar work carried out by him under our guidance and
supervision. This report in any form has not been submitted toany other University
or Institute for any purpose.

Prof. Yogesh Shepal Prof. Roshni Narkhede


(Seminar Guide) (Seminar Coordinator)
Assistant Professor Assistant Professor
Dept. of Comp. Engg. Dept. of Comp. Engg.

Dr. Saurabh Saoji Dr. Vilas Deotare


Head of Dept. Principal
Dept. of Comp. Engg. NMIET,
Talegaon NMIET, Talegaon
DECLARATION

I Mr. Ashutosh Rajabhau Thorat hereby declare that the seminar report Lane Line
Detection, submitted for partial fulfillment of therequirements for the award of
degree of Third Year in Computer Engineering of the NMVP and PCET’s Nutan
Maharashtra Institute of Engineering Technology,Talegaonis a bonafide work done
by me under supervision of Prof. Hanchate R.S and Prof. Dhanashri Patil .
This submission represents my ideas in my own words and where ideas or words
of others have been included, I have adequately and accurately cited and referenced
the original sources.
I also declare that I have adhered to ethics of academic honesty and integrity
and have not misrepresented or fabricated any data or idea or fact or source in my
submission. I understand that any violation of the above will be a cause for
disciplinary action by the Institute and/or the University and can also evoke penal
action from the sources which have thus not been properly cited or from whom
proper permission has not been obtained. This report has not been previously formed
the basis for the award of any degree, diploma or similar title of any other University.

Place: Talegaon Dabhade Mr. Ashutosh Thorat

Date: …………….
Acknowledgement

I take this opportunity to express my deepest sense of gratitude and sincere thanks to
everyone who helped me to complete this work successfully. I express my sincere
thanks to Dr. Saurabh Saoji, Head of Department, Computer Engineering, NMVP
and PCET’s Nutan Maharashtra Institute of Engineering Technology, Talegaon. for
providing me with all the necessary facilities and support.
I would like to express my sincere gratitude to the Seminar Coordinator Prof.Roshni
Narkhede, Assistant Professor, Department of Computer Engineering, NMIET for
their support and co-operation.
I would like to place on record my sincere gratitude to my seminar guide Prof.
Yogesh Shepal Assistant Professor, Department of Computer Engineering, NMIET
for the guidance and mentorship throughout the course.
Finally I thank my family, and friends who contributed to the successful fulfilment of
this seminar work.

Mr. Ashutosh Thorat

i
Abstract

Lane line detection is a critical component in the development of autonomous vehicles and
advanced driver assistance systems (ADAS). This technology plays a crucial role in ensuring
vehicle safety, navigation, and control. This abstract provides an overview of the key
concepts and methods involved in lane line detection.
Lane line detection systems utilize various sensors, such as cameras and LiDAR, to identify
and track the lane markings on the road. The primary goal is to accurately determine the
position, curvature, and orientation of the lane lines, enabling the vehicle to stay within its
designated lane.
This abstract discusses the main steps in lane line detection, including image preprocessing,
feature extraction, and line fitting algorithms. Various computer vision and machine learning
techniques, such as edge detection, Hough transforms, and deep neural networks, are
employed to enhance the accuracy and robustness of lane line detection.
The challenges and considerations in lane line detection are also addressed, including dealing
with adverse weather conditions, poor road markings, and variations in lane designs.
Furthermore, this abstract highlights the integration of lane line detection with other
perception and control systems in autonomous vehicles to enable safe and reliable self-
driving capabilities. In conclusion, lane line detection is a critical technology for autonomous
driving, contributing to safer and more efficient transportation. This abstract provides an
overview of the fundamental concepts and methodologies involved in this field, emphasizing
the importance of accurate and robust lane line detection for the success of autonomous
vehicles.

ii
Contents

Acknowledgement i

Abstract ii

1. Introduction
2. Problem statement
3. Motivation
4. Objectives
5. Methodology
6. Liturature Survey
7. Future scope
8. Conclusion
9. Reference

iii
Chapter 1

Introduction

Lane line detection is a fundamental technology that has revolutionized the way we
approach autonomous driving, advanced driver assistance systems (ADAS), and even
traditional human-operated vehicles. At its core, lane line detection involves the
identification and tracking of lane markings on the road, providing critical information about
a vehicle's position within a lane, its orientation, and the road's curvature. This technology is
pivotal for ensuring safe, efficient, and reliable driving experiences, whether in the context
of self- driving vehicles or human-driven cars equipped with ADAS features.

The significance of lane line detection lies in its ability to interpret the visual cues provided
by the road, much like a human driver would. By capturing and analyzing the road's
geometry and lane markings, a vehicle equipped with lane line detection systems can make
informed decisions about its trajectory and alignment, maintaining its position within a
designated lane, even in complex and dynamic traffic scenarios.

Lane line detection systems typically rely on various sensors, such as cameras, LiDAR, or
radar, to capture the road's visual data. These sensors feed the data into sophisticated
algorithms, which process and interpret the information to identify and track lane markings.
The output from these systems is crucial for enabling autonomous vehicles to navigate safely,
assisting human drivers in maintaining proper lane discipline, and contributing to overall road
safety.

In recent years, advancements in computer vision, machine learning, and sensor technology
have propelled lane line detection to new heights of accuracy and reliability. These systems
can now operate in diverse and challenging conditions, including inclement weather, low-
light environments, and poorly marked roads.

As we delve further into this field, we'll explore the core concepts, methodologies, and
challenges associated with lane line detection. We'll also discuss how this technology
interfaces with other critical components of autonomous driving and ADAS, ultimately
contributing to the realization of a safer, more efficient, and more convenient future of
transportation. Lane line detection is a cornerstone in the ongoing evolution of automotive
technology, paving the way for a transformative shift in how we interact with and navigate
the roads.

iv
Chapter 2

Problem

statement

Lane line detection is a crucial aspect of autonomous driving and advanced driver assistance
systems (ADAS), aiming to enhance vehicle safety and navigation. The problem at hand
can be framed as follows:
"Developing an efficient and accurate lane line detection system to enable vehicles to identify
and track lane markings on the road, even under challenging conditions such as adverse
weather, low visibility, and poorly marked roads. The system should provide real-time
information about lane position, curvature, and orientation, ensuring safe and reliable
autonomous driving and ADAS functionality."
Key challenges and considerations associated with this problem include:
1. Variability in Road Conditions: Lane markings can vary in color, width, and style,
and may be obscured or damaged due to factors like weather, road maintenance,
or traffic conditions. The system must adapt to these variations.
2. Adverse Weather Conditions: Rain, snow, fog, and glare from the sun can degrade
the quality of lane markings. The system should be robust to these environmental
challenges.
3. Complex Road Scenarios: Lane line detection should work on diverse road types,
including highways, urban streets, and intersections. It must handle situations
like lane merges, splits, and intersections.
4. Real-time Processing: To ensure the safety of the vehicle, the system should
provide real-time information, allowing the vehicle to make quick and accurate
decisions based on the detected lane markings.
5. Robustness: The system should be resilient to false positives (detecting non-lane
features as lane lines) and false negatives (missing actual lane lines).
6. Integration: Lane line detection must seamlessly integrate with other perception
and control systems within the vehicle to facilitate autonomous driving and ADAS
features.
Solving the problem of lane line detection is essential for the advancement of self-driving
technology and the safe operation of vehicles with advanced driver assistance systems. The
development of reliable and robust algorithms and hardware for this task is critical to
ensure the safety and efficiency of future transportation systems.

v
Chapter 3

Motivation
Lane line detection is driven by a multitude of motivations and objectives, reflecting its
critical role in modern transportation and automotive technology. Here are some key
motivations for the development and implementation of lane line detection systems:

1. Enhancing Road Safety: One of the primary motivations for lane line detection is to
improve road safety. Accurate and reliable lane line detection helps vehicles
maintain their proper lane positions, reducing the risk of accidents caused by
unintended lane departures or lane merging without signaling.

2. Supporting Autonomous Driving: As the automotive industry moves closer to


achieving fully autonomous vehicles, the need for robust lane line detection
becomes increasingly crucial. Self-driving cars heavily rely on lane line information
to make informed decisions about navigation and control, making it an integral part
of autonomous driving technology.

3. Enabling Advanced Driver Assistance Systems (ADAS): Lane line detection


forms the basis for numerous ADAS features, such as lane-keeping assistance,
adaptive cruise control, and lane departure warning systems. These technologies help
human drivers make safer and more informed driving decisions.

4. Traffic Flow Optimization: Lane line detection can be used to monitor and
manage traffic flow on highways and urban roads. This technology can help
alleviate congestion by providing real-time data to traffic management systems.

5. Enhancing Driver Comfort: Lane line detection contributes to the comfort of


human drivers, reducing the mental workload required to maintain lane discipline,
especially during long journeys or in heavy traffic.

6. Supporting Vulnerable Road Users: Lane line detection can be used to enhance
the safety of pedestrians and cyclists by alerting drivers to the presence of these
vulnerable road users and encouraging cautious driving behavior.

7. Accommodating Diverse Road Conditions: Lane line detection systems are


being developed to function effectively under a wide range of environmental and
road conditions, including rain, snow, fog, and poorly marked roads. This
adaptability helps ensure the technology's reliability in real-world scenarios.
vi
8. Legal and Regulatory Compliance: Many regions and countries have
established regulations and standards that require lane line markings to be clearly
visible and adhered to. Lane line detection systems assist drivers and autonomous
vehicles in meeting these compliance requirements.

9. Research and Development: Lane line detection serves as a focal point for ongoing
research and innovation in the fields of computer vision, machine learning, and
sensor technology. Advancements in these areas continually refine the capabilities of
lane line detection systems.

10. Reducing Accidents and Fatalities: Ultimately, the overarching motivation for
lane line detection is to reduce the number of road accidents and fatalities. By
assisting drivers and autonomous vehicles in maintaining safe lane discipline, this
technology plays a pivotal role in achieving this goal.

In summary, lane line detection is motivated by the pursuit of safer, more efficient, and more
comfortable transportation solutions. It forms the basis for numerous safety and convenience
features in both human-driven and autonomous vehicles, and its continued development
promises to revolutionize the way we interact with the road.

vii
Chapter 4

Objectives
Lane line detection systems serve various purposes and objectives, all of which contribute
to safer, more efficient, and more reliable transportation. Here are some key objectives for
line lane detection:
Lane Keeping: The primary objective of lane line detection is to assist vehicles,
whether autonomous or human-driven, in maintaining their positions within designated
lanes. This helps prevent unintentional lane departures and promotes safe driving.

Lane Departure Warning: Provide early warnings to drivers when their vehicles are about
to cross lane boundaries without signaling, helping them correct their course and avoid
potential accidents.

Enhanced Safety: Minimize the risk of collisions by ensuring that vehicles stay within
their lanes, particularly during critical situations like overtaking, merging, or navigating
complex road geometries.

Adaptive Cruise Control: Enable adaptive cruise control systems to adjust vehicle speed
based on detected lane traffic and maintain a safe following distance from the vehicle in
front.

Lane Change Assistance: Assist drivers in safely changing lanes by detecting adjacent
vehicles and assessing the availability of open lanes.

Traffic Flow Optimization: Contribute to the management and optimization of traffic flow
on highways and urban roads by providing data on lane occupancy and vehicle speeds.

Vulnerable Road User Protection: Enhance pedestrian and cyclist safety by detecting
their presence near roadways and warning drivers to exercise caution.

Support Autonomous Driving: Facilitate autonomous driving by providing real-time


lane information, allowing self-driving vehicles to navigate safely, make informed decisions,
and interact with other road users.

Robust Performance: Ensure that lane line detection systems work under a wide range of
environmental conditions, including adverse weather (rain, snow, fog), low light, and varying
road surface quality.
vii
Real-time Feedback: Provide real-time information to drivers and autonomous systems to
support immediate decision-making and adjustments to the vehicle's behavior.
Compliance with Regulations: Meet legal and regulatory requirements by adhering to
lane-keeping and lane departure warning standards, ensuring that vehicles comply with road
safety regulations.

Reduced Accidents and Fatalities: Ultimately, the overarching objective of lane line
detection is to reduce road accidents, injuries, and fatalities by promoting safe and disciplined
driving behavior.

Continual Improvement: Drive ongoing research and development efforts to improve the
accuracy, reliability, and adaptability of lane line detection systems, keeping pace with
advancements in technology and automotive requirements.

Integration with Other Systems: Seamlessly integrate lane line detection with other
perception, navigation, and control systems within vehicles to create a holistic solution for
safe and efficient transportation.

User Comfort: Enhance the comfort and convenience of drivers and passengers by reducing
the mental workload associated with maintaining lane discipline, particularly during long
trips or in heavy traffic.

These objectives collectively contribute to making our roadways safer, more efficient, and
more accessible for all users while supporting the development and adoption of autonomous
driving technologies.

ix
Chapter 5

Methodology
Lane line detection is a complex process that involves multiple steps and techniques to
accurately identify and track lane markings on the road. Below is a typical methodology for
lane line detection:

1. Data Acquisition:
 Utilize sensors such as cameras, LiDAR, or radar to capture visual data of
the road ahead.

2. Preprocessing:
 Convert captured images or sensor data into a suitable format for analysis.
 Apply image enhancements to improve the quality of the data, such as
contrast adjustment, noise reduction, and color space transformation.
 Remove irrelevant information and isolate the region of interest (ROI)
containing the road and lane markings.

3. Feature Extraction:
 Detect edges and gradients in the images using techniques like Canny
edge detection or Sobel operators to highlight lane markings.
 Utilize color information to distinguish between different road
surface materials and lane colors (e.g., white or yellow lane
markings).
 Employ region-based approaches to isolate lane-like structures from the
background.

4. Lane Marking Detection:


 Use Hough Transform or similar techniques to identify candidate lines in
the image that could represent lane markings.
 Apply filtering and thresholding to select lines that match the expected
characteristics of lane markings, such as length, orientation, and
proximity.

5. Lane Model Fitting:


 Fit mathematical models (e.g., linear equations for straight lanes or
polynomial equations for curved lanes) to the detected lane
markings.
 Incorporate robust regression methods to reduce the impact of outliers.

6. Lane Tracking:
 Implement tracking algorithms to follow the detected lane lines over

x
time, considering their historical positions and dynamics.
 Correct for inaccuracies caused by noise or temporary obstructions.

xi
7. Lane Verification and Validation:
 Evaluate the quality and validity of the detected lanes by assessing factors
like lane width consistency, lane continuity, and lane shape coherence.
 Utilize additional information from other vehicle sensors, such as GPS or
IMU data, to validate the lane position.

8. Real-time Processing:
 Ensure that the lane line detection system operates in real-time to
provide timely information for driving decisions.

9. Integration with Control Systems:


 Share the detected lane information with vehicle control systems to enable
features like lane-keeping assistance, adaptive cruise control, and
autonomous driving.

10. Environmental Adaptability:


 Design the system to function under various environmental conditions,
including adverse weather (rain, snow, fog), low-light scenarios, and
different road surface conditions.

11. Machine Learning Approaches:


 Incorporate machine learning techniques, such as deep neural networks
(CNNs), to learn and adapt to the specific visual characteristics of lane
markings, making the system more robust and accurate.

12. Testing and Evaluation:


 Evaluate the performance of the lane line detection system through
extensive testing in diverse real-world scenarios and controlled
environments.
 Measure accuracy, false positive and false negative rates, and the
system's ability to handle challenging conditions.

13. Continual Improvement:


 Continuously update and refine the lane line detection algorithms and
hardware to keep pace with advancements in technology and evolving
road conditions.

This methodology provides a structured approach to the process of lane line detection,
incorporating various computer vision, image processing, and machine learning techniques to
achieve accurate and reliable results. It forms the foundation for a critical component of
advanced driver assistance systems and autonomous driving technology.

xii
Chapter 6

Literature Survay
A literature survey on lane line detection encompasses a review of relevant research
articles, papers, and publications that provide insights into the methods, techniques,
and advancements in this field. Below are some key papers and studies that have
contributed to the understanding and development of lane line detection systems:

1. Canny, J. (1986). A Computational Approach to Edge Detection. - Canny's


classic paper on edge detection laid the groundwork for detecting lane markings
as edges in images, a fundamental step in lane line detection.

2. Hough, P. V. C. (1962). Method and Means for Recognizing Complex


Patterns. - The Hough Transform is a key technique for detecting lines in
images, including lane markings. This paper introduces the
transformative Hough method.

3. Zhang, Z. (2019). A Review on Road and Lane Detection. - This review


paper provides a comprehensive overview of road and lane detection methods,
highlighting various approaches, challenges, and future directions.

4. Broggi, A., & Buzzoni, M. (2000). Vision-Based Vehicle Control: A Survey. -


This survey discusses vision-based lane detection and vehicle control,
emphasizing the importance of lane detection for autonomous driving.

5. Sivaraman, S., & Trivedi, M. M. (2011). Looking at Vehicles on the Road: A


Survey of Vision-Based Vehicle Detection, Tracking, and Behavior Analysis.
- This survey covers vision-based vehicle detection and tracking, which often
relies on lane line detection for context.

6. Wang, Y., Yang, D., & Song, W. (2020). A Survey of Lane Detection in
Intelligent Transportation Systems. - This survey delves into lane
detection techniques in the context of intelligent transportation systems,
discussing methods, datasets, and challenges.

7. Hsiao, J. H., & Yang, M. H. (2008). Robust Lane Detection and Tracking
for Real-Time Applications. - This paper presents a robust lane detection
and tracking method, emphasizing real-time applications.
xii
8. Maddalena, L., & Petrosino, A. (2008). A Real-Time Road Lane Detection
System on FPGA. - This study introduces a real-time lane detection system
implemented on a Field-Programmable Gate Array (FPGA), highlighting
hardware acceleration.

9. Pan, X., Shi, J., Luo, X., & Tang, F. (2018). Two-Stage Convolutional Neural
Network for Vehicle Detection in Satellite Images. - This paper discusses a
two-stage CNN approach for vehicle detection, which often involves lane line
detection as a precursor.

10. Qureshi, S., You, Z., & Asif, A. (2017). Lane Detection and Tracking Using
Bézier Curves. - This paper explores the use of Bézier curves for lane
detection, which can improve the representation of curved lanes.

11. Lee, S., & Lee, S. (2016). Real-Time Lane Detection Using a Low-Cost Camera
Sensor. - The authors discuss a cost-effective approach to real-time lane
detection, which is vital for wider adoption in automotive applications.

12. Ramanagopal, S., & Trivedi, M. M. (2018). A Unified Detection and Tracking
Framework with Active Decision Fusion for Lane-Change Recognition. - This
paper combines lane detection with lane-change recognition, illustrating the
broader applications of lane information.

13. Ma, W., & Li, X. (2019). A Lane Detection Algorithm for Highway by
Using Image Processing. - The authors present an image processing-based
lane detection algorithm suitable for highway scenarios.

14. Mohammadnia, H., & Mann, G. K. I. (2018). Lane Detection and Tracking via
Geometric and Appearance Features. - This paper discusses a lane detection
and tracking method that combines geometric and appearance features for
robust performance.

15. Ghafoor, A., & Lee, Y. (2015). A Survey of Lane Detection Algorithms and
System. - A comprehensive survey of various lane detection algorithms, their
characteristics, and their real-world applications.

These papers and studies offer a broad perspective on the state-of-the-art in lane line
detection, covering various methods, challenges, and applications. Researchers and
practitioners in the field can use these sources to stay informed about the latest
developments and to guide their own work in this critical aspect of autonomous driving
and advanced driver assistance systems.

xii
Chapter 7

Future Scope

The future scope for lane line detection is promising and continues to evolve as technology
advances and the automotive industry transitions toward more autonomous and connected
vehicles. Here are some key areas of future development and opportunities for lane line
detection:
Advanced Autonomous Driving: Lane line detection will remain at the forefront of
autonomous driving technology, enabling self-driving vehicles to navigate complex urban
environments, highways, and intersections with greater precision and safety. The future will
see even more sophisticated and robust algorithms for lane following and decision-making.

Integration with V2X Communication: Lane line detection will play a role in Vehicle-to-
Everything (V2X) communication systems, where vehicles share information with each other
and with infrastructure. Lane data can enhance vehicle awareness and decision-making,
improving safety and traffic flow.

Enhanced Adverse Weather Performance: Future lane line detection systems will be
more adept at handling adverse weather conditions, such as heavy rain, snow, and fog, which
can obscure lane markings. This may involve the use of advanced sensors, improved
algorithms, and machine learning techniques.

High-Definition (HD) Maps: Lane line detection will be closely linked with HD mapping
for autonomous vehicles. These maps will provide precise lane information, aiding in
localization and ensuring vehicles have detailed, up-to-date data about road markings.

Behavior Prediction: Lane line detection can be integrated with predictive algorithms to
anticipate the behavior of other road users. This will allow autonomous vehicles to make
safer and more informed decisions, especially in complex traffic scenarios.

Integration with Pedestrian and Cyclist Detection: Lane line detection systems will
work in conjunction with pedestrian and cyclist detection to enhance road safety, particularly
in urban environments where interactions with vulnerable road users are common.
Hardware Acceleration: Advancements in hardware, such as specialized vision
processing units (VPUs) and dedicated lane detection ASICs, will improve the real-time
performance and efficiency of lane line detection systems.

xi
Hybrid Sensor Fusion: Lane line detection will combine data from various sensors,
including cameras, LiDAR, radar, and ultrasonic sensors, to create a more robust perception
system, reducing the reliance on any single sensor type.

Lane-Level Localization: Lane markings will serve as reference points for precise
vehicle localization, especially in urban environments, parking lots, and tunnels, where
GPS signals may be unreliable.

Human-Machine Interaction: Lane line detection will assist in the development of


effective human-machine interaction strategies, ensuring that drivers or passengers in semi-
autonomous vehicles understand the vehicle's perception of the road and its intentions.

Regulatory Compliance: Lane line detection will continue to evolve to meet changing
legal and regulatory requirements related to autonomous driving and advanced driver
assistance systems.

Open Source and Collaboration: The open-source community and collaborative


efforts among researchers, academia, and industry will drive innovation in lane line
detection and make it more accessible to a broader range of applications and developers.

Robustness and Safety: Future research will focus on further enhancing the robustness and
safety of lane line detection systems, reducing the likelihood of false positives and false
negatives.

In summary, the future of lane line detection is closely tied to the ongoing development of
autonomous and connected vehicles. It will continue to play a pivotal role in ensuring safe
and reliable transportation while adapting to changing road conditions and technological
advancements.

xv
Chapter 8

Conclusion

In conclusion, lane line detection has emerged as a pivotal technology for enhancing road
safety and enabling the transition to autonomous driving. Its primary function of identifying
and tracking lane markings on the road ensures that vehicles maintain proper lane discipline,
reducing the risk of accidents and enhancing driving efficiency. The continuous
advancements in computer vision, sensor technology, and machine learning have made lane
line detection more reliable and adaptable, even in challenging environmental conditions.
Looking ahead, the future scope for lane line detection is promising, with opportunities for
integration with V2X communication, improved performance in adverse weather, and the
development of high-definition maps for precise vehicle localization. Lane line detection will
remain at the forefront of automotive innovation, contributing to safer and more efficient
transportation solutions for both human-driven and autonomous vehicles.

In this dynamic landscape, collaboration and ongoing research efforts among industry
leaders, researchers, and the open-source community will play a crucial role in pushing the
boundaries of lane line detection. As vehicles become increasingly connected and
autonomous, lane line detection will continue to evolve, contributing to a safer and more
convenient driving experience while paving the way for the transportation systems of the
future.

xv
References

[1]H. Chun-Sheng, M. Li-Yong, L. YunJing, H. Yu-Qing and Y. Pei-Lun, "A Lane


Detection Technique Based on Adaptive Threshold Segmentation of Lane Gradient
Image", 2018 4th Annual International Conference on Network and Information
Systems for Computers (ICNISC), pp. 182-186, 2018.

[2] Nuthong Chaiwat, Mongkonyong Peerawat, Yamakita Masaki and Siddhichai


Supakorn, "Lane detection using Randomized Hough Transform", IOP
Conference Series: Materials Science and Engineering, vol. 297, 2018.

[3] Weixing Wang, Weiwei Chen, Huan Li, Kevin Wang, Sheng Liu and Zhaoying
Li, "Lane departure warning systems and lane line detection methods based on
image processing and semantic segmentation: A review", Journal of Traffic and
Transportation Engineering (English Edition), vol. 7, no. 6, pp. 748-774, 2020.

[4] H. G. Zhu, “An efficient lane line detection method based on computer
vision,” Journal of Physics: Conference Series, vol. 1802, Article ID 032006,
2020.https://www.hindawi.com/journals/jece/2022/5284185/

[5] https://github.com/mohamedameen93/Lane-lines-detection-using-Python-and-
OpenCV

xv
Thank you……..

xv

You might also like