High performance ultrasonic sensors are commonly used in medical applications. Ultrasonic sensors are also used in autonomous driving for near-field sensing. Its low cost is one of its main advantages and thus it is necessary to have low computational complexity for the classification algorithms. In this paper, we propose an efficient capsule neural network to provide a detailed height analysis of detected objects. We apply a novel re-sorting and re-shaping method to feed the neural network with ultrasonic data. We evaluated the proposed method under different environmental conditions and obtained high validation accuracy of 99% at a run-time of 0.2 ms. We compare it with a conventional CNN and demonstrate better accuracy and run-time.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Capsule Neural Network based Height Classification using Low-Cost Automotive Ultrasonic Sensors


    Contributors:


    Publication date :

    2019-06-01


    Size :

    879362 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    CAPSULE NEURAL NETWORK BASED HEIGHT CLASSIFICATION USING LOW-COST AUTOMOTIVE ULTRASONIC SENSORS

    Pöpperli, Maximilian / Gulagundi, Raghavendra / Yogamani, Senthil et al. | British Library Conference Proceedings | 2019


    Vehicle-Type Classification Using Capsule Neural Network

    Mane, Deepak / Kharche, Chaitanya / Bankar, Shweta et al. | Springer Verlag | 2022


    Embedded ultrasonic sensors for automotive radar

    Adams, T. | Fraunhofer Publica | 2010

    Free access


    Sensors for Automotive Remote Road Surface Classification

    Bystrov, Aleksandr / Hoare, Edward / Tran, Thuy-Yung et al. | IEEE | 2018