We use cookies to give you the best experience possible. By continuing we’ll assume you’re on board with our cookie policy

Vehicle controlling Paper

Words: 1418, Paragraphs: 139, Pages: 5

Paper type: Essay , Subject: Transportation


Automated vehicle controlling using image

processing and Raspberry Pi


dept. ofComputer Science &Engg,

SVIT, India

[email protected]

Harini SH

dept. ofComputer Science &Engg,

SVIT, India

[email protected]

Sreelatha PK

Assistant Professor

dept. ofComputer Science &Engg,

SVIT, India

[email protected]

Madhuri K

dept. ofComputer Science &Engg,

SVIT, India

[email protected]

Nandini M G

dept. ofComputer Science &Engg,

SVIT, India

[email protected]

Abstract —Vehicle controlling has become atedious job these

days, we need to control the vehicle because itcauses many

Don't use plagiarized sources. Get Your Custom Essay on Vehicle controlling
Just from $13,9/Page

Get Essay

accidents due to human mistakes. we present an automated

vehicle controlling system which uses image processing

algorithms to control the vehicle and also obstacle detection

system so that we avoid any obstructions caused to humans.

The designed bot takes the input from the pi-camera which

will capture the images and the bot will be automatedly

controlled. The system will use alateral control algorithm the

objective ofthis algorithm istokeep the vehicle inthe center of

the road. Position and orientation of the vehicle will be

managed by the image processing algorithms. Two different

algorithms used here are based on pixel intensity and other on

vanishing points. The obstacle in front of the vehicle will be

detected using ultrasonic sensors which gives the input to the

system and the bot will be stopped when an object isinfront of

them .

Keywords — Autonomous vehicle ,pi-camera ,obstacle detection,

raspberry pi,ultrasonic sensor .


Nowadays, the rate of signal jumping has become high and due to

these accidents has also been increased day by day. There are

many methods and rules which has come into the picture toavoid

jumping of signals. One of the methods include fixing of cameras

in the signal so that the person who jumped the signal will be

captured and will be fined for the action, but this method will not

avoid human death caused due to jumping of signals moreover it

has been increased.

So, an autonomous vehicle which uses an image processing

technique for controlling ismuch necessary. The main idea of this

project isto develop an automated vehicle which will be able to

control the vehicle from jumping of signals and also detecting the

obstacles infront ofit.

The bot which will be developed will be having araspberryPi

which isthe heart of the entire vehicle where all the controlling

actions will be carried out and the programmes that are used for

controlling actions will be loaded on tothe raspberryPi. The signal

detection will be carried out by various image processing

techniques because itisone of the best technique that can be used

and itwill provide the exact results and also isthe fastest way to

compute the results. The obstacle detection will be carried out by

using the sensors. In our project, we will be using ultrasonic

sensors, which will calculate the distance from the developed bot

and the obstacle in front of itand will stop the vehicle in such a

way that itwill not cause any problem tothe human and aswell as

other vehicles.


The system architecture consists of the following camera input,

speedometer input, tracking, speed control, and obstacle detection.

Fig 1.system architecture

Camera Input:

We intend touse acamera with alarge field ofvision. This field of

vision should extend from 0.5m before the vehicle to 30m ahead.

This camera islocated just about the from tire hood. Itisangled in

order to get the field of vision. The camera has the following


? Itisahigh- resolution camera so that itsees clearly in its

field ofvision.

? Itcaptures images atintervals of0.1ms.

? The images have adepth of 2bits i.e the camera can detect

only four colors ofthe most.


We have aspeedometer on the vehicle. This analog input is

digitalized and given as an input to the control unit. The

speedometer on many vehicles ishighly inaccurate. So we intend

to use abetter quality speedometer as its reading are very crucial

incollision detection.

Control unit:

This isthe heart ofthe system which takes inputs from camera and

speedometer and processses itusing the programs written inahigh

-level language such as C, Python. The program written inCwill

have image processing as its main part. This image processing

program takes the sampled frame from the camera and analyzes it

using image processing algorithms. Depending upon the difference

from the standard picture stored inthe memory, the speed control,

the tracking and obstacle detection sub-routines will be called.


The painted tracks on the road form areference for the vehicle to

move. The vehicle to move along an imaginary line exactly in

between these two paths. Any deviations are detected by image

processing. Those differences are minimized by afeedback control


Obstacle Detection:

Suppose some vehicles come within the field of vision of the

camera itenters the critical distance [not safe distance for driving].

The image processor detects it. It also finds the approximate

distance of the object from the user by counting the row number

from the bottom half of the image. Itthen signals the braking

mechanism tostart working.

Speed Control:

The speed control isactivated only when there isno difference in

the image captured and the ideal image. At this point of time, the

vehicle istraveling inastraight line. The speed of the vehicle has

to be regulated to maintain safety. Hence the input of the

speedometer iscompared with the ideal value of the speed. Ifthe

speed isless, then the accelerator isused toincrease the speed by a

particular value. The amount of acceleration given depends upon

the difference in the ideal and present speed. After making this

small change, the control shifts back tothe main image processing



The system flow diagram isdivided into two parts:

1. Image processing for traffic signal detection

2. Obstacle detection

Fig 2:image processing for traffic signal detection

Image processing for traffic signal detection:

The camera image will be given asinput which will be inthe RGB format and then the image will be converted from RGB to Grayscale image that is color filtering will be done using the following formula Gray=(R+G+B)/3 and then this converted image i..e. binary image will be segmented. The goal of segmentation istosimplify the image and then the traffic sign will also be detected in the same stage and then the feature will be extracted here in our project the feature that we need to extract is the stop sign inthe signal board. Then finally the stop board will be detected using the image processing techniques and the vehicle will be stopped asitrecognizes the sign on the board.

Fig 3:obstacle detection using anultrasonic sensor

Obstacle detection:

The obstacle detection by the vehicle will be performed inthe following way, The front, and side ultrasonic sensors gives the input for the vehicle ifthere isany obstacle infront of bot then the motor will be stopped else itwill calculate the error by finding out the difference from the measured distance tothe target distance and this serves as the input to the proportional, integral and derivative controller(PID). The objective of this controller isto control the speed, the pressure of the vehicle and then based on the output of this controller the motor will control the speed of right and left wheels of the vehicle and this process will be continuing inregular intervals oftime.


Our main idea is autonomous vehicle controlling which will

control the vehicle from jumping of signals through which

accidents will be avoided and will reduce the death rates that are

caused due to accidents and also to detect the obstacle coming in

front of the vehicle because this isone more cause of accidents so

that itwill not unnecessarily hit other vehicles and also speed will

be controlled. This will help in asafe journey of people on the

road and also asafe movement ofvehicles intraffic.


[1] Yue Wanga, Eam Khwang Teoh & Dinggang Shenb, traffic

using image processing 22 (2004) available

at:www.elseviercomputerscience.com, pp. 269 –280.

[2] H. Dahlkamp, A. Kaehler, D. Stevens, S. Thrun, and G.

Bradski. Self-supervised monocular road detection in desert

terrain. G. Sukhatme, S. Schaal, W. Burgard, and D. Fox,

editors& Proceedings of the Robotics Science and Systems

Conference ,Philadelphia, PA, 2006. International Journal of

Computer Applications (0975 –8887) Volume 113 –No. 9,

March 2015

[3] Joel C. McCall &Mohan M. Trivedi, Vision -Based Lane

Estimation and Tracking for Driver Assistance: Survey,

System, and Evaluation, IEEE Transactions on Intelligent

Transportation Systems, vol. 7,no. 1,March 2006, pp. 20-37.

[4] Tushar Wankhade & Pranav Shriwas, Design of Lane

Detecting and Following Autonomous Robot, IOSR Journal

of Computer Engineering (IOSRJCE) ISSN: 2278-0661

Volume 2,Issue 2(July-Aug. 2012), pp. 45-48.

[5] Xiaodong Miao, Shunming Li & Huan Shen, On-Board lane

detection system for intelligent vehicle based on monocular

vision, International Journal on Smart Sensing and Intelligent

Systems, vol. 5,no. 4,December 2012, pp. 957-972.

[6] A. Bar Hillel, R. Lerner, D. Levi, &G. Raz. Recent progress

in road and lane detection: asurvey. Machine Vision and

Applications, Feb. 2012, pp. 727 –745

[7] Narathip Thongpan, & Mahasak Ketcham, The State of the

Art inDevelopment aLane Detection for Embedded Systems

Design, Conference on Advanced Computational

Technologies & Creative Media (ICACTCM ’2014) Aug. 14-

15, 2014

[8] Narayan Pandharinath Pawar & Minakshee M. Patil, Driver

Assistance System based on Raspberry Pi, International

Journal ofComputer Applications (0975 –8887) Volume 95–

No.16, June 2014, pp. 36-39.

[9] J.M.A. Alvarez, A.M. Lopez & R. Baldrich ,Illuminant-

Invariant Model-Based Road Segmentation. Intelligent

Transportation Systems, IEEE Transactions on, 12, 2008, pp

184 –193.

[10] W. Maddern, A. Stewart, C. McManus, B. Upcroft, W.

Churchill, & P. Newman, Illumination Invariant Imaging:

Applications in Robust Vision-based Localization, Mapping

and Classification for Autonomous Vehicles ,Proceedings of

the Visual Place Recognition in Changing Environments

Workshop, IEEE International Conference on Robotics and

Automation (ICRA), Hong Kong, China, 2014.

About the author

This sample is done by Scarlett with a major in Economics at Northwestern University. All the content of this paper reflects her knowledge and her perspective on Vehicle controlling and should not be considered as the only possible point of view or way of presenting the arguments.

Check out more papers by Scarlett:

How to cite this page

Choose cite format:

Vehicle controlling. (2019, Dec 20). Retrieved from https://paperap.com/vehicle-controlling-best-essay/

Is Your Deadline Too Short?
Let Professionals Help You

Get Help

Our customer support team is available Monday-Friday 9am-5pm EST. If you contact us after hours, we'll get back to you in 24 hours or less.

By clicking "Send Message", you agree to our terms of service and privacy policy. We'll occasionally send you account related and promo emails.
No results found for “ image
Try Our service

Hi, I am Colleen from Paperap.

Hi there, would you like to get such a paper? How about receiving a customized one? Click to learn more https://goo.gl/CYf83b