TRAFFIC RULES VIOLATION DETECTION SYSTEM
1Associate Professor, Department of CSE, Ballari Institute of Technology & Management, Ballari 2,3,4,5 Final Year Students, Department of CSE, Ballari Institute of Technology & Management, Ballari ***
Abstract ThemajorityofvehiclesonroadinIndiaisincreasingfasterbecauseofwhichtrafficmanagementhasbecome one of the main problems. The effectivemanagement of traffic is possible when every violation on the road is often detected. The use of conventional/manualmethod together with existing technologies to detect trafficrule violation is inefficient as a results of which traffic managementhasbecomeverydifficult.Duringthisproject,the system is proposed with the assistance of image processing technologies to detect major violation like over speeding and helmet detection togetherwithnumberplaterecognitionprocesswhichwillmakejoboftrafficmanagementeasier.
Key Words: Data Collection, Python OpenCV, Object Detection, TensorFlow, OCR.
1.INTRODUCTION
Traffic rule violationsare nowa big problem forthe majorityof emerging nations in the modern, changing world. Both the numberofmotorcyclesontheroadandthenumberoftrafficlawoffencesaregrowingquickly.Regulatingtraffichasalways been difficult and risky to find violations. Despite the fact that Traffic management has automated, making it a highly difficultchallenge.Variedplatesizes,rotations,andlightingthatisn'tconsistentconditionsatthetimeanimagewastaken.
Themajorpurposeofthisprojectistocontroltrafficruleviolationscorrectlyandefficiently.Theproposedmodelincludes a computer based camera based automated system for image capture. so as to detect number plates more quickly and simply, the project offers Automatic Number Plate Recognition (ANPR) approaches moreover as additional image manipulation methods for plate localization and character recognition. The SMS based module is employed to alert the ownersofthevehiclesafterdeterminingtheautomobilenumberfromthequantityplate,theirtrafficinfractions.
The ability to extract and recognise the characters of a car number plate from an image automatically. is all that numberplate detection in this project entails. This system has a camera that can take a picture, locate a number in the picture, and then extract characters using a character recognition Programme. Due to the low cost and widespread use of motorbikes, rigorous regulations are necessary to prevent accidents. Since wearing a helmet is required by traffic laws, breakingthemcarriesseriouspenalties
2. LITERATURE SURVEY
Aniruddha Tonge et al. [2020] In the suggested technique, the system detects motorcycle using YOLO based object detection, and then checks each motorcycle for particular violations, such as not wearing a helmet or crosswalk. A CNN (Convolutionalneuralnetwork)basedclassifierisusedtodetecthelmetviolations.[1].
Ruben J Franklin et al. [2020] Computer vision based violation detection systems are a highly effective instrumentfor tracking andpenalizingtraffic infractions. Fortraffic infractiondetections such as signal violation,motorcyclespeed,and motorcyclecount,thissystemisproposedbuiltusingYOLOV3objectdetection.[2].
Chetan Kumar B et al. [2020] Applications for traffic surveillance use object detection algorithms like convolutionneural networks(CNN).Aneuralnetworkhasatleastonehiddenlayerintheinputandoneintheoutput.[3].
Siddharth Tripathi et al. [2019] In this article they have used an intelligent known as CBITS. It will discuss the following functionsuchasemissionmonitoring,accidentidentification.[4].
HelenRoseMampilayiletal.[2019]Thisresearchoffersasystemthatdetectsone waytrafficruleviolationsautomatically and without the intervention of a person. Three wheeled vehicles were taken into account because they had a higher proclivityforbreakingone waytrafficlaws.[5].
International Research Journal of Engineering and Technology (IRJET) e ISSN:2395 0056
Volume: 09 Issue: 06 | June 2022 www.irjet.net p ISSN:2395 0072
Ali Sentas et al. [2019] Techniques for analyzing videos areutilized in traffic research for a variety of tasks, including counting and classifying vehicles, detecting crashes, and evaluating traffic density. Vehicle identification, tracking wrong wayviolationdetectionaremadepossiblewiththeproposedsystem.[6].
M. Purohit et al. [2018] The authors used four feature extraction techniques on the Raspberry Pi 2 (B), including Scale InvariantFeatureTransform(SIFT),Speeded UpRobustFeatures(SURF),TemplateMatching,OrientedFAST,andRotated BRIEF(ORB),toidentifyobjectssuchascars,helmets,licenseplates,andseatbeltsfortrafficdatasets.[7].
S.P.ManiRaj et al. [2018]Inthesuggestedsystem,whereeverystepisautomated,agooddatabasemaybekeptto track driverrecordsregardingtrafficrulebreaches.Italsoallowsforthepaymentoffingerprintsandfacilitatesinthedetection ofunauthorizedanddrunkdrivers.[8].
Shashank Singh Yadav et al. [2018] In this research, the Kmeans linear regression, z score and hierarchical temporal memory clustering algorithm are used to investigate trajectory based anamoly identification utilizing spatial temporal analysis. An objectspatiallocalizationisseenasanevent.[9].
R.Shreyas et al. [2017]Itis nowincredibly difficulttocontroltrafficandenforcethelawbykeeping trackofevery single car. Utilization of Automation Nowadays, plate recognition is used more and more to manage traffic flow and is comparabletotheautomaticelectronictollcollectingmethod.[10].
3. PROPOSED METHODOLOGY
TodesignanddevelopatrafficrulesviolationdetectionsystemusingMachineLearning.
4. WORKING MODEL
APCisusedintherecognitionsystemtocapturethecar registrationnumberplate.Underpoorenvironmentalconditions, asshowninthefollowingpoint,carlicenceplateimagesareillegiblewhentakenbythesystem:
1.Overexposure,reflection,orshadowsresultinpoorlightingandlowcontrast.
2.Unfavorableweatherconditions,suchasrainorsmog.
3.Imagesthatarehazy.
4.loweringtheimage'sillumination.
Thesystemwillrecognizethevehicle'slicenseplateandconvertthephotostograyscaleimages.The grayscalephotosare thenconvertedtobinaryimages,whichonlyincludethenumbers'0'and'1'.Followingthebinarygraphics,thesystemwill segmenttheautomobilelicenseplate'spersonality.Thecharacterandnumberwillbesegmentedforeachseparatefigure. Afterthat,allofthecharactersandnumberswillbeconvertedtobinaryformintermsofthematrixandrecognizedbythe neuralnetwork.Afterthat,imagecroppingandrecognitioncomenext.
1.Takeapicturewithyourwebcam.
2.Changetheimage'sscaletoasmallersize.
3.Determinethelocationofthenumberplate.
4.Segmentation.
5.Identificationbynumber.
6.Savethefileinthespecifiedformat.
1) Takeapicturewithyourwebcam:AfterTakingapicturewithyourwebcam.Savethecapturedimagetoapicture documentforfartherprocessing.
2)Convert the picture to binary format: Determine the opacity of the image. Calculate the image's correct threshold value.Usingthecomputedthreshold, converttheimagetoabinarypicture.
International Research Journal of Engineering and Technology (IRJET) e ISSN:2395 0056
Volume: 09 Issue: 06 | June 2022 www.irjet.net p ISSN:2395 0072
3) Look for the number plate area. Determine the image's width and height. Fill little holes with numbers from the numberplatetomakethenumberplateregionlargeenoughtoisolatefromthefigure.
4) SeparationClippingtheplateregionextractsonlyafewofplateareas,reducingtheamountofnoiseintheimage.
5) Identification based on a number Create a template file from the template images you've saved. Resize the segmentedimagetomeetthetemplate'sdimensions.
6) Save the document in the format you specified. In write mode, open a text file. Save the number recognition procedure'scharactertoatextfileintheformatyoudecide.
Figure4.1:BlockDiagram
5. RESULT AND DISCUSSION
In this study, a programme is being created to identify motorcyclists who do not follow the helmet laws. Motorcycle identification, helmet identification, and license plate recognition of motorcyclists riding without a helmet are the three maincomponentsoftheprogramme.The maincriterionistouseCNNtoseeiftheAhelmetiswornbythe rider.Whena rider is discovered without a helmet, the number plate of the motorcycle is recognised using tesseract OCR (Optical Character Recognition).The motorcycle/non motorcycle categorization is 93 percent accurate, the helmet/non helmet classificationis85percentaccurate,andlicenseplaterecognitionis51percentaccurate,foratotal accuracyofaround76 percent.Theaccuracywillimprovebyincreasingthetrainingdatacollectionandimagequality.
Fig.5.1.Front/HomePage
Thehomepageallowstheuserstoaccesstheapplication.
Fig.5.2.Imagecapturing.
Inthispicture,thecameradetectsthemotorcycleandalsodetectswhetherthepersoniswearinghelmetornot.
Fig.5.3.ConsoleScreen.
Whenthehelmetisnotfound,thenitisprintedonthescreen.
Fig.5.4.CapturingtheLicenseplate.
Once the helmetis not detected, then the license plate iscaptured.
International Research Journal of Engineering and Technology (IRJET) e ISSN:2395 0056
Volume: 09 Issue: 06 | June 2022 www.irjet.net p ISSN:2395 0072
Fig.5.5.Detectionofnumberplate. Thelicencenumberisdetectedandprintedonthescreenafterthenumberplateiscaptured.
Fig.5.6.Messagesenttotheowner.
Whenaviolationisdiscovered,anotificationisdeliveredtothevehicle'sowner.
Fig.5.7.CapturingSingnalJump.
Inthispicture,thecameracapturestheredsignal.Whentheredsignaliscaptured,thesignaljumpingviolationisdetected.
Volume: 09 Issue: 06 | June 2022 www.irjet.net p ISSN:2395 0072
Fig.5.8.Messagesenttotheowner. WhentheSignaljumpviolationisdetected,thenthemessageissenttotheownerwhocommittedtheviolation.
6. CONCLUSION
The existing system is inefficient due to large number of vehicles on the road which makes it difficult to track multiple violationsoccurringatsametimeasaresultofwhichmanyviolatorsgetawaywithoutbeingpunished.Theexistingsystem requires lot of workforce hence adding extra pressure on the traffic officials. The proposed system can cover few of the loopholes in the existing system with features like multiple over speeding detectionsimultaneously, automatic helmet wear detection, triple riding detection system and violation/fine alert system hence providing better, safer and smart replacementtoexistingsystem.
7. FUTURE SCOPE
The traffic rules violation detection system can cover few ofthe loopholes in the existing system with the features like multipleoverspeedingdetectionsimultaneously,automatichelmetweardetection,signaljumping,noparkingzones hence providingbetter,saferandsmartreplacementtoexistingsystemforTrafficpoliceintheroadtransportation.
8. REFERENCES
[1] Aniruddha Tonge, S. Chandak, R. Khiste, U. Khan and L. A. Bewoor, "Traffic Rules Violation Detection using Deep Learning," 2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA), 2020, pp. 1250-1257,doi:10.1109/ICECA49313.2020.9297495.
[2] Ruben.J Franklin and Mohana, “Traffic Signal Violation Detection using Artificial Intelligence and Deep Learning, ”2020 5th International Conference on Communication and Electronics Systems (ICCES), 2020, PP. 839 844, doi: 10.1109/ICCES48766.2020.9137873.
[3] ChetanKumarB,R.PunithaandMohana,"PerformanceAnalysisofObjectDetectionAlgorithmforIntelligentTraffic SurveillanceSystem,"2020SecondInternationalConferenceonInventiveResearchinComputingApplications(ICIRCA),2020, pp.573,579,doi:10.1109/ICIRCA48905.2020.9182793.
[4] Siddharth Tripathi, Uthsav Shetty, Asif Hasnain, Rohini Hallikar,"Cloud Based Intelligent Traffic System to Implement Traffic Rules Violation Detection and Accident Detection Units", Proceedings of the Third International Conference onTrendsinElectronicsandInformatics(ICOEI2019)IEEEXplorePartNumber:CFP19J32-ART;ISBN:978-15386 9439-8.
International Research Journal of Engineering and Technology (IRJET) e ISSN:2395 0056
Volume: 09 Issue: 06 | June 2022 www.irjet.net p ISSN:2395 0072
[5] Helen Rose Mampilayil and R. K., "Deep learning based Detection of One Way Traffic Rule Violation of Three Wheeler Vehicles," 2019 International Conference on Intelligent Computing and Control Systems (ICCS), 2019, pp. 1453 1457,doi:10.1109/ICCS45141.2019.9065638.
[6] Ali Şentas, S. Kul and A. Sayar, "Real Time Traffic Rules Infringing Determination Over the Video Stream: Wrong WayandClearwayViolationDetection," 2019InternationalArtificialIntelligenceandDataProcessingSymposium(IDAP), 2019,pp.1 4,doi:10.1109/IDAP.2019.8875889.
[7] M.PurohitandA.R.Yadav,"Comparisonoffeatureextractiontechniquestorecognizetrafficruleviolationsusinglow processing embedded system," 2018 5thInternational Conference on Signal Processingand Integrated Networks (SPIN), 2018,pp.154 158,doi:10.1109/SPIN.2018.8474067
[8] S.P.ManiRaj,B.Rupa,P.S. SravanthiandG. K. Sushma,"SmartandDigitalized Traffic Rules Montioring System," 2018 3rd International Conference on Communication and Electronics Systems (ICCES), 2018, pp. 969 973, doi: 10.1109/CESYS.2018.8724086.
[9] Shashank Singh Yadav, V. Vijayakumar and J. Athanesious, "DetectionofAnomalies in Traffic SceneSurveillance," 2018 Tenth International Conference on Advanced Computing (ICoAC), 2018, pp. 286 291, doi: 10.1109/ICoAC44903.2018.8939111.
[10] R. Shreyas, B. V. P. Kumar, H. B. Adithya, B. Padmaja and M. P. Sunil, "Dynamic traffic rule violationmonitoring system using automatic number plate recognition with SMS feedback," 2017 2nd International Conference on TelecommunicationandNetworks(TEL NET),2017,pp.1 5,doi:10.1109/TEL NET.2017.8343528.