Place recognition for loop closure detection lies at the heart of every Simultaneous Localization and Mapping (SLAM) method. Recently methods that use cameras and describe the entire image by one holistic feature vector have experienced a resurgence. Despite the success of these methods, it remains unclear how a descriptor should be constructed for this particular purpose. The problem of choosing the right descriptor becomes even more pronounced in the context of life long mapping. The appearance of a place may vary considerably under different illumination conditions and over the course of a day. None of the handcrafted descriptors published in literature are particularly designed for this purpose. Herein, we propose to use a set of elementary building blocks from which millions of different descriptors can be constructed automatically. Moreover, we present an evaluation function which evaluates the performance of a given image descriptor for place recognition under severe lighting changes. Finally we present an algorithm to efficiently search the space of descriptors to find the best suited one. Evaluating the trained descriptor on a test set shows a clear superiority over its hand crafted counter parts like BRIEF and U-SURF. Finally we show how loop closures can be reliably detected using the automatically learned descriptor. Two overlapping image sequences from two different days and times are merged into one pose graph. The resulting merged pose graph is optimized and does not contain a single false link while at the same time all true loop closures were detected correctly. The descriptor and the place recognizer source code is published with datasets on http://www.mrt.kit.edu/libDird.php.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    How to learn an illumination robust image feature for place recognition


    Beteiligte:
    Lategahn, Henning (Autor:in) / Beck, Johannes (Autor:in) / Kitt, Bernd (Autor:in) / Stiller, Christoph (Autor:in)


    Erscheinungsdatum :

    2013-06-01


    Format / Umfang :

    1664236 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    HOW TO LEARN AN ILLUMINATION ROBUST IMAGE FEATURE FOR PLACE RECOGNITION

    Lategahn, H. / Beck, J. / Kitt, B. et al. | British Library Conference Proceedings | 2013


    Linear subspaces for illumination robust face recognition

    Batur, A.U. / Hayes, M.H.I.I.I. | IEEE | 2001


    Linear Subspaces for Illumination Robust Face Recognition

    Batur, A. U. / Hayes, M. H. / IEEE | British Library Conference Proceedings | 2001


    Illumination-robust and anti-blur feature descriptors for image matching in abdomen reconstruction

    Liu, H. / Xiao, Y. / Tang, W. D. et al. | British Library Online Contents | 2014


    A Bilinear Illumination Model for Robust Face Recognition

    Lee, J. / Moghaddam, B. / Pfister, H. et al. | British Library Conference Proceedings | 2005