This paper applies deep learning to obstacle identification in UAV flight. In order to achieve a better recognition effect, the dataset collates the two types of images of the simulation software screenshots and real-life photos. The basic principle of YOLO is briefly introduced. On the basis of not modifying the network, the data set is continuously trained using the pre-trained parameters. In this paper, we mainly optimize the loss function. The first is to optimize the difference between the simulation software screenshots and real photos by adding another weight. The second is class optimization, which increases the proportion of samples with low class confidence, like UAVs with different structures and colors. Finally achieved a good recognition effect.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Low-altitude Fixed-wing UAV Obstacle Recognition Based on Deep Learning


    Beteiligte:
    Ding, Dian (Autor:in) / Wang, Yangzhu (Autor:in) / Xiao, Yao (Autor:in) / Han, Zhen (Autor:in)


    Erscheinungsdatum :

    2018-08-01


    Format / Umfang :

    254595 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Optical flow-based obstacle avoidance of a fixed-wing MAV

    Rezaei, Mahdi / Saghafi, Fariborz | Emerald Group Publishing | 2011



    High-Speed Obstacle-Avoidance with Agile Fixed-Wing Aircraft

    Bulka, Eitan / Nahon, Meyer | IEEE | 2019


    A Fast Obstacle Collision Avoidance Algorithm for Fixed Wing UAS

    Lin, Zijie / Castano, Lina / Xu, Huan | IEEE | 2018


    Flight Corridor Construction Method for Fixed-Wing UAV Obstacle Avoidance

    Wang, Zhongming / Zou, Fei / Ma, Zhaowei et al. | Springer Verlag | 2023