In this paper, we present an online learning framework for traversable region detection fusing both appearance and geometry information. Our framework proposes an appearance classifier supervised by the sparse geometric clues to capture the variation in online data, yielding dense detection result in real time. It provides superior detection performance using appearance information with weak geometric prior and can be further improved with more geometry from external sensors. The learning process is divided into three steps: First, we construct features from the super-pixel level, which reduces the computational cost compared with the pixel level processing. Then we classify the multi-scale super-pixels to vote the label of each pixel. Second, we use weighted extreme learning machine as our classifier to deal with the imbalanced data distribution since the weak geometric prior only initializes the labels in a small region. Finally, we employ the online learning process so that our framework can be adaptive to the changing scenes. Experimental results on three different styles of image sequences, i.e., shadow road, rain sequence, and variational sequence, demonstrate the adaptability, stability, and parameter insensitivity of our weak geometry motivated method. We further demonstrate the performance of learning framework on additional five challenging data sets captured by Kinect V2 and stereo camera, validating the method’s effectiveness and efficiency.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Scalable Learning Framework for Traversable Region Detection Fusing With Appearance and Geometrical Information


    Beteiligte:
    Wang, Yue (Autor:in) / Liu, Yong (Autor:in) / Liao, Yiyi (Autor:in) / Xiong, Rong (Autor:in)


    Erscheinungsdatum :

    2017-12-01


    Format / Umfang :

    4002369 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Scene Parsing and Fusion-Based Continuous Traversable Region Formation

    Xiao, Xuhong / Ng, Gee Wah / Tan, Yuan Sin et al. | British Library Conference Proceedings | 2015


    Functional device integrated into a traversable surface and method for producing a traversable surface with same

    HESLINGA DICK / BOULANGER AMANDINE / COQUELLE ERIC et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    A mapping and localization framework for scalable appearance-based navigation

    Segvic, S. / Remazeilles, A. / Diosi, A. et al. | British Library Online Contents | 2009