The development of self-driving cars has always been an extensive research field for the automobile industry. To make a capable self-driving car, many challenges need to be resolved. Detection of the road condition is one of them. This paper focuses on a particular part-detection of speed bumps and potholes using a camera and analyzing the video feed with the help of artificial intelligence. To solve this problem a popular and lightweight algorithm, SSD (Single Shot Multibox Detector) is used. This is an optimal choice because of being lightweight and also accurate enough to run on mobile devices and to use in real-life situations. For detecting speed bumps and potholes, a dataset has been created based on the road structure of Bangladesh as the main priority of this system is to work on the local environment. Raspberry Pi has been used as the main processing unit because of being small but powerful. A warning system has been implemented so that it can warn the onboard driver about the upcoming pothole or speed bump. This system can also send a signal to the speed controller unit of the car to reduce the speed on detection to avoid accidents or damages to the car. The speed control unit is a microcontroller-based system that uses an ATmega328 microcontroller and L298 motor driver. This paper summarizes the combination of an artificial intelligence-based detection system injunction with a microcontroller-based speed control system in a cost-effective way that can be used in building self-driving cars.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Speed Bump & Pothole Detection with Single Shot MultiBox Detector Algorithm & Speed Control for Autonomous Vehicle


    Contributors:
    Tithi, Aditi (author) / Ali, Firoj (author) / Azrof, Sadman (author)


    Publication date :

    2021-07-08


    Size :

    2205321 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Real-Time Train Detection Based on Improved Single Shot MultiBox Detector

    Xu, Yuchuan / Gao, Chunhai / Yuan, Lei et al. | British Library Conference Proceedings | 2020


    Fast single shot multibox detector and its application on vehicle counting system

    Chen, Lili / Zhang, Zhengdao / Peng, Li | IET | 2018

    Free access

    Real-Time Train Detection Based on Improved Single Shot MultiBox Detector

    Xu, Yuchuan / Gao, Chunhai / Yuan, Lei et al. | Springer Verlag | 2020


    Real-Time Train Detection Based on Improved Single Shot MultiBox Detector

    Xu, Yuchuan / Gao, Chunhai / Yuan, Lei et al. | TIBKAT | 2020


    Fast single shot multibox detector and its application on vehicle counting system

    Chen, Lili / Zhang, Zhengdao / Peng, Li | Wiley | 2018

    Free access