With the rapid development of spacecraft technology, spacecraft, which is mainly represented by satellites, has become an important military resource for the extraordinary success of space attack and defense in various countries. Accurately identifying the type of satellite and the components of the satellite’s windsurfing, nozzles, and star sensors is important prerequisites and safeguards for space attack and on-orbit maintenance. In this paper, the deep learning based convolutional neural network YOLO model is used to identify the space satellite and its components, and the three dimensional models and the physical models image set of the two satellite models are trained for close-range front view, long distance, occlusion, and motion blur. Satellites and satellite components are identified under different conditions. In some cases , the recognition accuracy of satellite and satellite components is more than 90%, it is of great significance in the field of on-orbit services, space attack and defense confrontation.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Spatial Multi-object Recognition Based on Deep Learning


    Beteiligte:
    Liu, Wang (Autor:in) / Xiao, Hewen (Autor:in) / Chengchao, Bai (Autor:in)


    Erscheinungsdatum :

    01.10.2019


    Format / Umfang :

    2241347 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Multi-objective recognition based on deep learning

    Liu, Xin / Wu, Junhui / Man, Yiyun et al. | Emerald Group Publishing | 2020



    Vehicle Color Recognition With Spatial Pyramid Deep Learning

    Hu, Chuanping / Bai, Xiang / Qi, Li et al. | IEEE | 2015


    Industrial robot control with object recognition based on deep learning

    Chen, Xi / Guhl, Jan | BASE | 2018

    Freier Zugriff

    Weakly Supervised Learning of Part-Based Spatial Models for Visual Object Recognition

    Crandall, D. J. / Huttenlocher, D. P. | British Library Conference Proceedings | 2006