Deep Learning Based Vehicle Rules Violation Detection and Accident Assistance

International Research Journal of Engineering and Technology (IRJET) e ISSN: 2395 0056

Volume: 09 Issue: 07 | July 2022 www.irjet.net p ISSN: 2395 0072

Deep Learning Based Vehicle Rules Violation Detection and Accident Assistance

1Professor, Department. of CSE, East West Institute of Technology, Bangalore, Karnataka, India 2 4Department of CSE, East West Institute of Technology, Bangalore, Karnataka, India. ***

Abstract There’s be high growth in population and most of the people prefer comfort. Nowadays a greater number of automobiles are being purchased in cities and also in growing rural areas. Due to more number vehicles results in heavy traffic, and controlling traffic is becoming more and more tough for the traffic police to handle. Other effect is a greater number of accidents occur which may lead to loss of several lives. In these situations, it creates necessity for develop a effective system that helps in detection oftrafficviolations and help in regulating the trafficrulesandreduceinconvenienceto the people. This proposed system can be put it in use in detecting violations such as Signal jumping, Triple riding, Helmet detection, No parking and can also detect the accidents that occur and the found traffic violators can be apprehended for breaking these rules, this framework is to assist traffic police who monitor the traffic manually in the IT cell.

degreesurveillanceinputandalsothesystemswillhavehigh GPU which is very much required for this framework to workeffectivelyandefficiently.InFigure1wecanobserve theTMC[TrafficManagementCenter]wherethemajorityof presentedsystemwillbeputinuse.

Words: Violation Detection, YOLO ,Convolutional Neural Network, Accident Assistance, Image AI

1.INTRODUCTION

ATrafficviolationdetectionframeworkmustberealized inrealtimeasthespecialiststrackthestreetsallthetime. Hence,trafficpolicewillbeateaseinactualizingsaferroads precisely,butmoreovereffectively;asthetrafficdetection system identifies violation quicker than people. A better frameworkthatiseasytouseandworkwellinmonitoring the traffic and taking actions against those violators and detectingaccidentsandprovidingassistanceisestablished. This framework is to assisttraffic police who monitor the trafficmanuallyintheITcellandalsowiththelivecamera monitoring present in those TMC’s (Traffic Management Centre) it is easy to track the violation and if there’s any accident found or detected it can be assisted right away withoutanydelay.Themonitoringframeworkcanbescaled exterior the city to provincial & thruways without extra takingatoll.Sincethevideoisbeingcapturedthetotalcity willbecoveredratherthan onlysignalsand intersections. This moreover enables traffic police to capture traffic violationhappeninginlittlepathstothruwayswhereverthe camera is present. These monitoring of violations and assistancetoaccidentscanbeefficientlybemonitoredand trackedin TrafficManagement Centre/Traffic Operations Centre’s.TMChavehigh speedmonitoringsystem,with360

1.1 Literature Survey

TheFrameworkthatpreviouslyexistedwasonlyableto identifyasingleviolationandalsothecapturedimagesbythe trafficpolicewerenotenoughforproperidentificationofthe violators. The captured images or the video by the traffic policeweresenttheITcellwherethefootageswerechecked manually to identify the violator. Because of that many violatorswouldbeleftoutandwouldgounrecognized.As thisis handledmanually,itgetstobeatiringworkforthe group to continuously screen the screens and not let any violation go undetected through such tremendous traffic withinthenation.

2. PROPOSED SYSTEM

Theobjectiveoftheprojectistocomputerizethetrafficrul esviolationlocationsystemand also this framework is to assisttrafficpolicewhomonitorthetrafficmanuallyinthe ITcellandmaketheirjobatease.AtTMCorTrafficITCell theyscreenlivevideostreamsoftrafficandwiththehelpof theproposedframeworktheviolatorswillbedetectedeasily andbecauseofthesystemhigh speedprocessortherewon’t be any delays. Once the violations are detected the framework checks for the number plate, once. that is

International Research Journal of Engineering and Technology (IRJET) e ISSN: 2395 0056

Volume: 09 Issue: 07 | July 2022 www.irjet.net p ISSN: 2395 0072

identifiedaSMSalertissenttotheviolator.Ifanyaccidents aredetectedinthelivestreams,thenaswiftassistancecan be delivered to that location with the help of TMC. Identifyingandfollowingthe vehicle andtheiractivities preciselyisthemostneedoftheframework.Withthehelpof this,Policeofficerscanbeateaseandwillbeabletoidentify theviolationsthatareinthetrafficfootageandalsobeable togetthedetailsoftheviolator’svehiclefromtheimageand thevideos.

processing, the use of an averaging filter to filter out the noise,globalbasicthresholdingtoremovethebackground and consider only the image and a high pass filter to sharpentheimagebyamplifyingthefinerdetails.Ininitial step of pre processing is converting the image data from RGBtoGreyscale.Itcanbeobtainedbyapplyingthebelow formulatotheRGBimage.

Figure2:SystemArchitecture

Thefigure2depictsthebasicsystemarchitecturewhich includestheinputimageasavideothroughcameraandthis imageisprocessedandifanyviolationsthenhelmet,triple riding,signaljumpingandnoparkingarealldetected.

2.1DataAcquisition

Figure3:DataAcquisition

As shown in the Figure 3 theinformationset is collected from a source and atotalanalysisis carried out. Thepictureischosento beutilizedfor training/testing purposesas it werein the event thatit matches ourrequirementsandisn'trepeated.

2.2Pre ProcessingtheDataSet

TheFigure4showshowthedatasetisinvolvedinconverting the image from the RGB format to greyscale to ease

Figure4:Pre processingtheDataset

NoiseRemoval:

Noise removal algorithm is the method of removing or diminishingthenoisefromthepicture.Thenoiseexpulsion calculations reduce or expel the visibility of noise by smoothingthecompletepictureclearingoutregionsclose differentiateboundaries.Noiseremovalisthesecondstepin imagepre processing.Herethegrayscalepicturewhichwas gotten within the last step is given as input. Here we are makingutilizeMedianFilterwhichcouldbeaNoiseRemoval Technique.

2.3FeatureExtraction

WeutilizeastrategycalledHistogramOrientationGradient (HOG) to extract the highlights from the pre processed picture gotten as input. In Figure 5 we can observe the featureextractionfromtheimage.Itincludesdifferentsteps likefindingGxandGy,whicharegradientsabouteverypixel within the x and y axes. After calculating Gx and Gy, magnitude and angle of each pixel is calculated using the formulaementionedbelow.

Magnitude (μ) =√(G_x^2+G_y^2) Angle(θ)=|(tan 1)(G_y/G_x)|

International Research Journal of Engineering and Technology (IRJET) e ISSN: 2395 0056

Volume: 09 Issue: 07 | July 2022 www.irjet.net p ISSN: 2395 0072

2.5ViolationDetection

Figure5:FeatureExtraction

2.4ClassificationusingCNN:

When CNN is used for classification, we don’t have to do featureextraction.FeatureExtractionwillalsobecarriedout by CNN. We feed the pre processed image directly to CNN classifiertoobtainthetypeofrequireddatathatispresent. Asshownintheflowchartfigure6classificationofmatrixis doneinstep by stepmanner.

a.) Yolo: YOLO also known as ‘You Only Look Once’ is basedconvolutionalneuralnetworks(CNN)toidentify objects in real time. This algorithm performs by puttinginasingleneuralnetworkonafull sizedimage andthenthatimageisdividedinseveralsubpartsand withthehelpofboundingboxesandtheprobabilities foreachofthoseboxesarepredicted.Anyimagethat is inserted will be applied with grid lines then each grid box is check for the probability of the trained image.Ifanobjectcenterisappearedwithinacertain gridcell,thenthatcellwillberesponsiblefordetecting it.Aboundingboxisnothingbutaoutlinethatshows upanobjectinanimage.Asshowninthefigure7a person is detected within a bounding box. It uses a singleboundingboxregressiontopredicttheheight, width,center,andclassofobjects.ForOptimizingit uses thesum squared errorloss functionwhichisa betterwaytooptimizetheimages.

Figure7:Yoloboundingbox

b.) OCR:Thisalgorithmismainlyusedtopinpointcertain fragmentorthefigureincomputerisedimageorina videostream.Inthepresentedframeworkasshown in the figure 8 OCR is used for Recognition of CharactersontheLicensePlates.Thealgorithmisnot only restricted for pointing out the words, it is also abletoidentifyandreadnumbersandcodesthatare present in the input. Its applications are abundant across many industries for pointing out long string charactersandletteralongwithserialnumerical.In thefigurewecanobservetherecognitionofnumber plates.

Figure6:ClassificationusingCNN

Figure8:OCRforNumberPlateRecognition

c.) ImageAI:Thisisanopen sourcepythonlibrarythatis builtonTensorFlow,itwouldhelpdeveloperstobuild applications and systems that have self contained DeepLearningandComputerVisioncapabilitiesusing simpleandlesslineofcode. ImageAIgivesanawfully strong still simpler to utilize set of classes and function modules. that would help in performing complexvideoobjectdetectionsandalsointracking and video analysis. It supports many other deep learningalgorithmssuchasYOLOV3andTinyYolov3 etc.,ThislibrarydoesrequirehighspeedGPUtorun smoothlyasitprovidesfastandaccurateoutputs.In thepresentedsystemthislibraryisusedfordetecting the accidents that occur in video footages or in an imageinput.

3. RESULT & CONCLUSIONS

This presented system can be utilized for tracking violationsandalsoinprovidingassistancesforanyoccurring accidents.ThesetaskscanbetrackedinTMC/NOC’s.Traffic violations can be detected efficiently with the algorithm proposed. The program runtime on a normal computer is slow whereas in GPU system or high processing speed capacity computers it will be quite fast. The framework provides an effective way to identify the vehicles that violatestrafficrulesandbytrackingtheaccidentsitgivesa waytoassisttheaccidentscenesfaster.

When the figure 9 is uploaded, at first Motorcycle is detected,thenitschecksforotherviolationsandidentifies theviolationastripleriding.belowistheoutput.

Figure10:

When the figure 10 is uploaded, at first Motorcycle is detected,thenitschecksforotherviolationsandidentifies the violation as triple riding and no helmet violation is detectedasshownbelow.

Figure9:

Figure11:

Whenthefigure11isuploaded,atfirstvehiclesaredetected, ifitisdetectedthenitschecksforredcolorinimageandif

identifiedit showsviolationassignaljumpinginthebelow output.

Figure12:

The figure 12 is identified by the system as it checks the vehiclesforviolatingnoparking.Outputisshownbelow.

.

Figure13:

In figure 13, accident is detected, we can observe the predictionsandprobabilities.Thepredictionsaredonefor identifyingfireinthescene,sparsetraffic,densetrafficand accidents.

Figure14:

Infigure14,theuseofOCRalgorithmcanbeobserved.The numberplateisdetectedwiththehelpofopenalprAPI and the result is as shown. After detecting number plate SMS intimationissenttotheviolator.

Figure15:

In figure 15, we can observe SMS alert that is sent by the systemafteridentifyingtheviolator’snumberplate.

CONCLUSION

Thepresentedsystemwillbeabletosupplementthework of traffic police and assist them in pin pointing the violations.Andalso,itmakestheirjobeasiertocontrolthe trafficandtakeanyrequiredmeasuresagainsttheviolators. Itcreatesconsciousnesswithinthepeopleofthecountyto strictlyfollowthetrafficrules.Detectingaccidentsinalive streamandalsointherecordedvideoshelpstheTMCtotake actionsfasterandprovideassistanceinbetterway.

REFERENCES

[1] Nikhil Chakravarthy Mallela, Rohit Volety, Srinivasa Perumal R, Nadesh R K,IEEE,” Detection of the triple ridingandspeedviolationontwo-wheelersusingdeep learningalgorithms”

[2] P.Meghana,S.SagarImambi,P.Sivateja,K.Sairam2019, “ImageRecognitionforAutomaticNumberPlate”.

International Research Journal of Engineering and Technology (IRJET) e ISSN: 2395 0056

[3] FelixWilhelmSiebert,DeikeAlbers,UAungNaing,Paolo Perego, Chamaiparn Santikarn, 2019 , “Patterns of motorcycle helmet use A naturalistic observation studyinMyanmar”.

[4] .Narong Boonsirisumpun, Wichai Puarungroj, and Phonratichi Wairotchanaphuttha, 2018,” Automatic Detector for Bikers with no Helmet using Deep Learning”.

[5] Tsung Yi, Lin Priya, Goyal Ross, Girshick Kaiming ,He Piotr Doll´ar,2020,”Focal Loss for Dense Object Detection“.

[6] C.Vishnu,DineshSingh,C.KrishnaMohanandSobhan Babu,2017,”DetectionofMotorcyclistswithoutHelmet inVideosusingConvolutionalNeuralNetwork”

[7] ]AmirgaliyevBeibut, KairanbayMagzhan, Kenshimov Chingiz, 2018,” Effective Algorithms and Methods for AutomaticNumberPlateRecognition”.

[8] ]Yuan Jing, BaharYoussefi, MitraMirhassani, RobertoMuscedere,2017,” An Efficient FPGA Implementation of Optical Character Recognition for LicensePlateRecognition”.

[9] Sergio Robles Serrano , German Sanchez Torres and John Branch Bedoya, 2021, “Automatic Detection of Traffic Accidents from Video Using Deep Learning Techniques”.

[10] Worawut Yimyam, Mahasak Ketcham,2017, “The AutomatedParkingFeeCalculationUsingLicensePlate RecognitionSystem”.

Volume: 09 Issue: 07 | July 2022 www.irjet.net p ISSN: 2395 0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal