While travelling, safety is one of the most important things that should be kept in mind. Due to the negligence of people, number of road accidents continue to increase in India. To decrease the number, one of the most important things is the proper implementation of traffic rules. The proper implementation of traffic rules ensures the safety of people since traffic rules are designed for the proper flow vehicles on roads and to ensure safety. The objective of this work is to improve the implementation of traffic rules by automating the process of identification of traffic rule violators from images. The proposed methodology focuses to detect different types of traffic rule violators, the riders without helmets and bike with three people violating traffic rules. It is necessary to detect motorcycle present in an image for consideration of all these cases. The steps like helmet detection, triple seat detection and number plate detection are followed after motorcycle detection in an image. Deep learning techniques are studied and implemented for all these cases. YOLOv3 algorithm is used in the implementation of the proposed methodology. Different deep learning models are trained to detect objects. The proposed system uses three deep learning models for detection of these objects. Different models are trained for detection of different objects in the input image. The proposed work results into 88.5% mean average precision for motorcycle detection model and 91.8% for number plate detection.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Traffic Rule Violation Detection System: Deep Learning Approach


    Additional title:

    Lect. Notes Electrical Eng.


    Contributors:


    Publication date :

    2022-06-26


    Size :

    11 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Traffic Rules Violation Detection using Deep Learning

    Tonge, Aniruddha / Chandak, Shashank / Khiste, Renuka et al. | IEEE | 2020


    Traffic Rule Violation Detection using Detectron2 and Yolov7

    Choudhari, Rutvik / Goel, Shubham / Patel, Yash et al. | IEEE | 2023



    DEEP LEARNING BASED TRAFFIC VIOLATION ENFORCEMENT SYSTEM AND METHOD

    JUNG BOOEUN / CHOI HEUNGMOOK / KIM YOUNGKYU et al. | European Patent Office | 2020

    Free access

    TRAFFIC VIOLATION DETECTION DEVICE, SYSTEM, TRAFFIC VIOLATION DETECTION METHOD, AND PROGRAM

    HARADA NAOYUKI / UMETANI HIDEO / MATSUI SHUHEI et al. | European Patent Office | 2018

    Free access