SSLA Based Traffic Sign and Lane Detection for

Autonomous cars

ABSTRACT

The Self-Driving Cars are also known as Autonomous Vehicles. This Car has the ability to sense
around the environment. These sensed parameters are processed and according to it the different
actuators in the car will work without any human involvement. An Autonomous car work like a
normal car but without any human driver. Autonomous cars rely on sensors, actuators, machine
learning algorithms and Software to perform all the Automated Functions. The Software part is
very important for Autonomous vehicles. The Software architecture acts as a bridge between
Hardware Components and Application. The Standardized Software for Automotive cars is
AUTOSAR. The AUTOSAR is a Standardized Architecture between Application Software and
Hardware. This Standardized Architecture provide all Communication Interfaces, Device
Drivers, Basic Software and Run-Time Environment. There are two important modules in Self-
Driving Cars. They are Lane Detection and Traffic Signal detection which works automatically
without any Human Intervention. A Machine Learning Algorithm is proposed in this paper. This
Algorithm is mainly used to train the shape models and helps to detect the shape for Traffic Sign
detection and Lane Detection. These both tasks are programmed using python with Open cv2
library file, numpy library file and Hough Detection technique is used to detect the appropriate
circles of the traffic signals. By using all these tools, all the shape models are trained using
Supervised training Algorithm and the detection is performed in such a way to help Autonomous
cars to detect the lane and traffic Sign.

INTRODUCTION

Safety is the important aspect which must be noticed while driving vehicles. In a survey it is
been published that more 10 lakhs of people die in the road accidents in a country. The Road
accident happened due to Human Errors are about 98%. So, to avoid this all over the world
Autonomous Cars are under Research and Development. The term Autonomous Cars is that the
car drives itself using various technologies without any Human intervention. For Autonomous
Cars Software task development is very much important. The Software architecture acts as a
bridge between Hardware Components and Application. The Standardized Software for
Automotive cars is AUTOSAR. This Standardized Architecture provide all Communication
Interfaces, Device Drivers, Basic Software and Run-Time Environment. There are two important
tasks in Autonomous cars they are Lane detection and Traffic Sign Detection. These two tasks
are important because many accidents are due to malfunction of these two tasks. A New
Algorithm SSLA (Shape Supervised Learning Algorithm) is proposed in this paper. The Hough
Line Transformation is the technique which is used to detect the Traffic Sign Detection.
Matplolib and numpy is the library files in python used for Lane Detection. These two
techniques are possible by Open CV, numpy libraries in python. The Hough line Transformation
is used to detect any shapes. In order to detect the Lane in which the car is to drive is by using
various Edge detection techniques which makes use of colours in python.

LITERATURE SURVEY

Autonomous cars: Past, present and future a review of the developments in the last
century, the present scenario and the expected future of autonomous vehicle technology

The field of autonomous automation is of interest to researchers, and much has been
accomplished in this area, of which this paper presents a detailed chronology. This paper can
help one understand the trends in autonomous vehicle technology for the past, present, and
future. We see a drastic change in autonomous vehicle technology since 1920s, when the first
radio controlled vehicles were designed. In the subsequent decades, we see fairly autonomous
electric cars powered by embedded circuits in the roads. By 1960s, autonomous cars having
similar electronic guide systems came into picture. 1980s saw vision guided autonomous
vehicles, which was a major milestone in technology and till date we use similar or modified
forms of vision and radio guided technologies. Various semi-autonomous features introduced in
modern cars such as lane keeping, automatic braking and adaptive cruise control are based on
such systems. Extensive network guided systems in conjunction with vision guided features is
the future of autonomous vehicles. It is predicted that most companies will launch fully
autonomous vehicles by the advent of next decade. The future of autonomous vehicles is an
ambitious era of safe and comfortable transportation.
Traceability maintenance: factors and guidelines

Traceability is an important concern for numerous software engineering activities. Establishing

traceability links is a challenging and cost-intensive task, which is uneconomical without suitable
strategies for maintaining high link quality. Current approaches to Traceability Management
(TM), however, often make important assumptions and choices without ensuring that the
consequences and implications for trace-ability maintenance are feasible and desirable in
practice. In this paper, therefore, we identify a set of core factors that influence how the quality
of traceability links can be maintained. For each factor, we discuss relevant challenges and
provide guidelines on how best to ensure viable traceability maintenance in a practical TM
approach. Our guidelines are meant to be used by tool developers and users to select the most
appropriate TM approach for their needs. Our results are based on and supported by data
collected from interviews conducted with: (i) 9 of our industrial and academic project partners to
elicit requirements for a TM tool, and (ii) 24 software development stakeholders from 15
industrial cases to provide a broader overview of the current state of the practice on TM. To
evaluate the feasibility of our guidelines, we investigate a set of existing TM approaches used in
industry with respect to our guidelines.

Knowledge and skills requirements for the software design and testing of automotive
application
The required knowledge and skills that should be provided to the novice developer, designing
and testing the safety critical device in automotive industry using Hardware-in-the-Loop (HiL),
are presented in the paper. They should be available to the student finishing the MSc level of
Electrical Engineering or Mechatronics that aims to seek the employment in the automotive
industry. The development process is presented in short, together with the brief explanations of
phases, which include some typical examples of written text in the documentation (requirements,
test cases, etc.). The process follows the Automotive SPICE and focuses on the tip of the V-
model. The presented text can serve as a useful information in the process of adapting the
existing curriculum to the new occurring needs introduced by the new development and testing
processes in industry.

Driverless Car: Autonomous Driving Using Deep Reinforcement Learning in Urban

Environment
Deep Reinforcement Learning has led us to newer possibilities in solving complex control and
navigation related tasks. The paper presents Deep Reinforcement Learning autonomous
navigation and obstacle avoidance of self-driving cars, applied with Deep Q Network to a
simulated car an urban environment. The approach uses two types of sensor data as input:
camera sensor and laser sensor in front of the car. It also designs a cost-efficient high-speed car
prototype capable of running the same algorithm in real-time. The design uses a camera and a
Hokuyo Lidar sensor in the car front. It uses embedded GPU (Nvidia-TX2) for running deep-
learning algorithms based on sensor inputs.

3D Objects Detection in an Autonomous Car Driving Problem

The autonomous driving problem is one of the most actual problems in both research and
industrial fields. Autonomous vehicles are designed to optimize traffic congestion, minimize the
number of traffic accidents, provide the ability to transport goods in dangerous conditions for
humans, expand the possibilities of using cars for people with disabilities, etc. To successfully
solve this problem, it is necessary to consider several subtasks, including localization and
mapping, static and dynamic object detection, motion planning, and control. In this paper, we
consider one of the tasks of an autonomous vehicle control system: 3D objects detection and
localization. We investigate existing detection methods that use heterogeneous information from
various sensors such as cameras, depth sensors, and LIDARs. To evaluate the effectiveness of
these methods in an autonomous driving problem, we conduct the experimental studies on real
and simulated data obtained using CARLA - an open-source simulator for autonomous driving
research.

Autonomous Cars: Research Results, Issues, and Future Challenges

Throughout the last century, the automobile industry achieved remarkable milestones in
manufacturing reliable, safe, and affordable vehicles. Because of significant recent advances in
computation and communication technologies, autonomous cars are becoming a reality. Already
autonomous car prototype models have covered millions of miles in test driving. Leading
technical companies and car manufacturers have invested a staggering amount of resources in
autonomous car technology, as they prepare for autonomous cars' full commercialization in the
coming years. However, to achieve this goal, several technical and nontechnical issues remain:
software complexity, real-time data analytics, and testing and verification are among the greater
technical challenges; and consumer stimulation, insurance management, and ethical/moral
concerns rank high among the nontechnical issues. Tackling these challenges requires thoughtful
solutions that satisfy consumers, industry, and governmental requirements, regulations, and
policies. Thus, here we present a comprehensive review of state-of-the-art results for
autonomous car technology. We discuss current issues that hinder autonomous cars' development
and deployment on a large scale. We also highlight autonomous car applications that will benefit
consumers and many other sectors. Finally, to enable cost-effective, safe, and efficient
autonomous cars, we discuss several challenges that must be addressed (and provide helpful
suggestions for adoption) by designers, implementers, policymakers, regulatory organizations,
and car manufacturers.

Traffic Sign Detection for Navigation of Autonomous Car Prototype using Convolutional
Neural Network

The Autonomous Car is one of Artificial Technology's innovations in the driving field. Many
features of Autonomous Car which are using a sensor. One of its navigation feature which use
camera sensor to navigate using the traffic sign. But this navigation feature, which uses Traffic
Sign, is implausible to be found in Indonesia. In this paper, it will be developed a Detection
System for Autonomous Car to navigate using the Traffic Sign, so Autonomous Car can navigate
according to the Traffic Sign, which is detected with the Autonomous Car. Using a camera
sensor and YOLO Deep Learning, Autonomous Car will recognize the Traffic Sign and
classified Traffic Sign as with its function. From this classification, Autonomous Car will
respond as the detected Traffic Sign means and will activate Autonomous Car's Actuator.

Safety of crews of autonomous cars

The contribution deals with problems of a passive safety of autonomous vehicles, focused on
specifics of car-crash accident. The paper describes a non-standard side crash test of two
passenger cars, during which the interior equipment and placement of test figurines inside car
were accommodated to simulate an expected arrangement of future autonomous cars. Motion of
the equipment inside the car interior was tracked during the test with the focus on its possible
impact on passenger's safety. The contribution further deals with specifics of autonomous vehicle
crew protection from the point of view of passive and integrated safety.
EXISTING SYSTEM

In the existing work there are Automotive cars which work through Sensors, Actuators and an
Embedded System Control. Here the Lane Keeping is very much important in terms of safety
measures to prevent road accidents. In the Concept of Lane keeping the LiDar, radar and GPS is
used in existing research work to keep the vehicles in the lane. Also, the lane keeping in the
existing papers are achieved through ADAS based system with the help of Adaptive cruise
control and this technique is performed through Deep Neural Networks [15].The Simulation part
is possible in Carla Software also. In existing research works and models the traffic sign and lane
detection is done through SVM. Where thousands of images are put into training models to get
an accurate output model.

Disadvantage

1. Time consuming process.

2. Less Accuracy.

PROPOSED SYSTEM

In this paper author is introducing concept for self-driving car by using OPEN-CV2 and Machine
Learning algorithms. CV2 Hough algorithm is used to detect LANE while driving car and
Machine Learning algorithm get trained on available TRFFAIC SIGNS and in video if any such
signal available then Machine Learning algorithm will predict and recognized.

To train this algorithms we need to have high configuration system with TERABYTES RAM
and Harddisk with good speed processor but our normal 8GB system will not trained such huge
dataset so we took some traffic signals and then trained ML model so our system can detect
LANE and SIGNS but not with high accuracy and to get 100% output we need to trained model
with Heavy Configuration system.

Advantage

1. Gives Accurate result.

2. Taking Less time

MODULES

To implement this project we have designed following modules

Generate & Load Machine Learning Model: Using this module we will train ML model and
then load it

Upload Video & Detect Hough Lane, Signal: Using this module we will upload TEST video
and then CV2 HOUGH algorithm will detect LANE and ML will detect and recognize traffic
signs.

REFERENCES

[1]K. Bimbraw, "Autonomous cars: Past, present and future a review of the developments in the
last century, the present scenario and the expected future of autonomous vehicle technology,"
2015 12th International Conference on Informatics in Control, Automation and Robotics
(ICINCO), Colmar, France, 2015, pp. 191-198.

[2] Maro S, Anjorin A, Wohlrab R, Steghöfer JP. “Traceability maintenance: factors and
guidelines.” International Conference on Automated Software Engineering (pp. 414- 425), 2020.

[3] J. Zabavnik, A. Riel, M. Marguč, M. Rodič.” Knowledge and skills requirements for the
software design and testing of automotive applications”2020

[4] Pawan Deshpande, "Road Safety and Accident Prevention in India: A review", Int J Adv
Engg Tech., vol. V, no. II, pp. 64-68, April-June 2014.

[5] A. R. Fayjie, S. Hossain, D. Oualid and D. Lee, "Driverless Car: Autonomous Driving Using
Deep Reinforcement Learning in Urban Environment," 2018 15th International Conference on
Ubiquitous Robots (UR), Honolulu, HI, USA, 2018, pp. 896-901, doi:
10.1109/URAI.2018.8441797.

[6] A. Agafonov and A. Yumaganov, "3D Objects Detection in an Autonomous Car Driving
Problem," 2020 International Conference on Information Technology and Nanotechnology
(ITNT), Samara, Russia, 2020, pp. 1-5, doi: 10.1109/ITNT49337.2020.9253253.
[7] R. Hussain and S. Zeadally, "Autonomous Cars: Research Results, Issues, and Future
Challenges," in IEEE Communications Surveys & Tutorials, vol. 21, no. 2, pp. 1275-1313,
Secondquarter 2019, doi: 10.1109/COMST.2018.2869360.

[8] M. Ikhlayel, A. J. Iswara, A. Kurniawan, A. Zaini and E. M. Yuniarno, "Traffic Sign

Detection for Navigation of Autonomous Car Prototype using Convolutional Neural Network,"
2020 International Conference on Computer Engineering, Network, and Intelligent Multimedia
(CENIM), Surabaya, Indonesia, 2020, pp. 205-210, doi: 10.1109/CENIM51130.2020.9297973.

[9] A. Josef Mík and B. P. Bouchner, "Safety of crews of autonomous cars," 2020 Smart City
Symposium Prague (SCSP), Prague, Czech Republic, 2020, pp. 1-5, doi:
10.1109/SCSP49987.2020.9133942.

[10] Sandhya, D. R., Sivakumar, P., & Balaji, R. (2019). AUTOSAR Architecture Based Kernel
Development for Automotive Application. In International Conference on Intelligent Data
Communication Technologies and Internet of Things (ICICI) 2018. ICICI 2018 (Vol. 26).
Springer.

[11]. Sivakumar, P., Devi, R. S., Buvanesswaran, A. D., Kumar, B. V., Raguram, R., &
Ranjithkumar, M. (2020, July). Model-Based Testing of Car Engine Start/Stop Button
Debouncer Model. In 2020 Second International Conference on Inventive Research in Comput
ing Applications (ICIRCA) (pp. 1077-1082). IEEE.

[12] Sivakumar, P., RS Sandhya Devi, A. Neeraja Lakshmi, B. VinothKumar, and B. Vinod.
"Automotive Grade Linux Software Architecture for Automotive Infotainment System." In 2020
International Conference on Inventive Computation Technologies (ICICT), pp. 391-395. IEEE,
2020.

[13] Sivakumar, P., Devi, R. S., Buvanesswaran, A. D., Kumar, B. V., Raguram, R., &
Ranjithkumar, M. (2020, July). Model-Based Testing of Car Engine Start/Stop Button
Debouncer Model. In 2020 Second International Conference on Inventive Research in
Computing Applications (ICIRCA) (pp. 1077-1082). IEEE
[14] Yuen, Kum Fai, Yiik Diew Wong, Fei Ma, and Xueqin Wang. "The determinants of public
acceptance of autonomous vehicles: An innovation diffusion perspective." Journal of Cleaner
Production 270 (2020): 121904.

[15] Saini, S., Nikhil, S., Konda, K. R., Bharadwaj, H. S., & Ganeshan, N. (2017, June). An
efficient vision-based traffic light detection and state recognition for autonomous vehicles. In
2017 IEEE Intelligent Vehicles Symposium (IV) (pp. 606-611). IEEE.