Predicting the condition of the road is an important task for autonomous vehicles to make driving decisions. Vehicles are expected to slow down or stop for potential road risks such as road cracks, bumps and potholes. Vision systems are widely used to provide such information given the rich colours and textures carried by images. This paper presents a weakly-supervised deep learning method to classify road images into two category sets. The first category identifies the existence of bumps or ramps in the image. The second category determines the road roughness given an input image. These two outputs are combined into a single convolutional neural network (CNN) to classify the camera image simultaneously. As a supervised learning method, deep learning algorithms normally require a large amount of training data with manually annotated labels. The annotation process is, however, very time-consuming and labour-intensive. This paper presents a method to avoid this costly process using a pipeline to automatically generate ground-truth labels by incorporating IMU and wheel encoder data. This automated pipeline does not require human effort to label images and will not be impeded by adverse environmental or illumination conditions. The experimental results presented show that after training the model using the automatically generated labels, the two-output CNN is capable to achieve good accuracy for classifying road conditions.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Weakly-supervised Road Condition Classification Using Automatically Generated Labels


    Beteiligte:
    Zhou, Wei (Autor:in) / Cruz, Edmanuel (Autor:in) / Worrall, Stewart (Autor:in) / Gomez-Donoso, Francisco (Autor:in) / Cazorla, Miguel (Autor:in) / Nebot, Eduardo (Autor:in)


    Erscheinungsdatum :

    20.09.2020


    Format / Umfang :

    878427 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Video Classification via Weakly Supervised Sequence Modeling

    Liu, Jingjing / Chen, Chao / Zhu, Yan et al. | British Library Online Contents | 2016


    Video Classification via Weakly Supervised Sequence Modeling

    Liu, Jingjing / Chen, Chao / Zhu, Yan et al. | British Library Online Contents | 2016



    Classification and weakly supervised pain localization using multiple segment representation

    Sikka, K. / Dhall, A. / Bartlett, M. S. | British Library Online Contents | 2014