Under the “safe, green, efficient and intelligent” requirements of modern railway construction, it's important and challenging to improve the automated and intelligent railway inspection system, which is an essential part of building domestic transportation infrastructure. Furthermore, the enhancement of images collected in low-light environments is an indispensable prerequisite for the railway inspection system to carry out intelligent analysis. Therefore, a low-light image enhancement means inspired by the Retinex theory based on CycleGAN is advanced. Specifically, a residual neural network is designed to decompose input images. Meanwhile, the unsupervised learning model CycleGAN is selected to adjust brightness maps. In addition, the BM3D algorithm is used to reduce the noise in reflection images. Eventually, extensive experiments on multiple data sets show that the proposed method can better restore image details, obtain more comfortable visual effects and more natural colors. Moreover, the enhancement results are better than the majority of classic methods.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Image Enhancement for Railway Inspections Based on CycleGAN under the Retinex Theory


    Beteiligte:
    Zheng, Shuo (Autor:in) / Dai, Shenghua (Autor:in)


    Erscheinungsdatum :

    19.09.2021


    Format / Umfang :

    2768568 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Retinex processing for automatic image enhancement

    Rahman, Z.-u. / Jobson, D. J. / Woodell, G. A. | British Library Online Contents | 2004


    Issues About Retinex Theory and Contrast Enhancement

    Bertalmío, M. / Caselles, V. / Provenzi, E. | British Library Online Contents | 2009


    Retinex processing for automatic image enhancement [4662-47]

    Rahman, Z. / Jobson, D. J. / Woodell, G. A. et al. | British Library Conference Proceedings | 2002


    A multi-scale retinex algorithm for image enhancement

    Yuehu Liu, / Yuanqi Su, / Yunfeng Zhu, et al. | IEEE | 2005


    Foggy Image Enhancement Based on Filter Variable Multi-Scale Retinex

    Zeng, F. / Wu, Q. / Du, J. | British Library Conference Proceedings | 2014