Power line extraction is not only crucial for unmanned aerial vehicles (UAVs) obstacle avoidance, but also a fundamental step for fault diagnosis of power lines. Therefore, achieving robust and accurate extraction of power lines in aerial images is essential to enable intelligent UAVs inspection. Unfortunately, power line extraction is an extremely challenging task, and all the current methods attempt to utilize a single model to solve the problem of power line extraction in complex and variable scenes. This results in insufficient generalization ability and suboptimal computational efficiency. In this work, we propose a power line scene classification network based on complexity assessment, named SceneNet, which can provide a solution for tackling power line extraction challenges. First, we propose a human–machine hybrid reasoning model to obtain the ground truth of image complexity reasonably and build the first benchmark dataset that can be used for automatic classification research of power line scenes. Second, we propose an improved StyleGAN3 model and loop transfer learning strategy for data augmentation. Most importantly, the SceneNet comprises a multifeature joint embedding module and a feature encoding–decoding module. On one hand, it achieves the multilevel fusion of artificial features and high-dimensional semantic features. On the other hand, we use a self-attention mechanism to enable full use of the contextual association between each block of the fusion feature map. The SceneNet has successfully achieved the mapping and pattern recognition between the abstract concept and the concrete features. Experimental results demonstrate that the SceneNet is obviously superior to the existing 12 state-of-the-art models, and it provides guidance and delineation of applicable scenes for power line extraction methods.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    SceneNet: A Multifeature Joint Embedding Network With Complexity Assessment for Power Line Scene Classification


    Beteiligte:
    Zhao, Le (Autor:in) / Yao, Hongtai (Autor:in) / Fan, Yajun (Autor:in) / Ma, Haihua (Autor:in) / Li, Zhihui (Autor:in) / Tian, Meng (Autor:in)


    Erscheinungsdatum :

    2023-12-01


    Format / Umfang :

    19601752 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Moving shadow detection with multifeature joint histogram

    Su, Y. / Li, A. / Cai, Y. et al. | British Library Online Contents | 2014


    Subregion Multifeature Fusion Oblique Vehicle Detection Algorithm

    Zeng, Juan / Li, Shou-yi / Zhang, Hong-chang | ASCE | 2020


    Multifeature fusion using pulse-coupled neural networks

    Inguva, R. Johnson, J. U. Schamschula, M. P. | British Library Conference Proceedings | 1999


    Scene complexity assessment method and system

    TAN JIYUAN / FENG YAN / GUO WEIWEI et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Corner detection algorithm based on multifeature [4550-38]

    Zhang, K. / Wang, J. / Zhang, Q. | British Library Conference Proceedings | 2001