This work addresses the problem of semantic image segmentation of nighttime scenes. Although considerable progress has been made in semantic image segmentation, it is mainly related to daytime scenarios. This paper proposes a novel method to progressive adapt the semantic models trained on daytime scenes, along with large-scale annotations therein, to nighttime scenes via the bridge of twilight time — the time between dawn and sunrise, or between sunset and dusk. The goal of the method is to alleviate the cost of human annotation for nighttime images by transferring knowledge from standard daytime conditions. In addition to the method, a new dataset of road scenes is compiled; it consists of 35,000 images ranging from daytime to twilight time and to nighttime. Also, a subset of the nighttime images are densely annotated for method evaluation. Our experiments show that our method is effective for knowledge transfer from daytime scenes to nighttime scenes, without human annotation.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime


    Beteiligte:
    Dai, Dengxin (Autor:in) / Gool, Luc Van (Autor:in)


    Erscheinungsdatum :

    01.11.2018


    Format / Umfang :

    891284 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Sign registration in daytime and nighttime driving

    Shinar,D. / Drory,A. / Ben-Gurion Univ.of the Negev,Beer Sheva,IL | Kraftfahrwesen | 1983


    Traffic Safety Evaluation of Nighttime and Daytime Work Zones

    G. L. Ullman / M. D. Finley / J. E. Bryden et al. | NTIS | 2008



    Nighttime versus Daytime Horizontal Curve Design Consistency: Issues and Concerns

    Stamatiadis, Nikiforos / Psarianos, Basil / Apostoleris, Konstantinos et al. | ASCE | 2019