Real-time astronaut visual tracking is the most important prerequisite for flying assistant robot to follow and assist the served astronaut in the space station. In this paper, an astronaut visual tracking algorithm which is based on deep learning and probabilistic model is proposed. Fine-tuned with feature extraction layers’ parameters being initialized by ready-made model, an improved SSD (Single Shot Multibox Detector) network was proposed for robust astronaut detection in color image. Associating the detection results with synchronized depth image measured by RGB-D camera, a probabilistic model is presented to ensure accurate and consecutive tracking of the certain served astronaut. The algorithm runs 10 fps at Jetson TX2, and it was extensively validated by several datasets which contain most instances of astronaut activities. The experimental results indicate that our proposed algorithm achieves not only robust tracking of the specified person with diverse postures or dressings but also effective occlusion detection for avoiding mistaken tracking.


    Access

    Download


    Export, share and cite



    Title :

    Astronaut Visual Tracking of Flying Assistant Robot in Space Station Based on Deep Learning and Probabilistic Model


    Contributors:
    Rui Zhang (author) / Zhaokui Wang (author) / Yulin Zhang (author)


    Publication date :

    2018




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown






    Astronaut/EVA construction of Space Station

    HEARD, JR., WALTER / BUSH, HAROLD / WATSON, JUDITH et al. | AIAA | 1988


    Robonaut: A Robotic Astronaut Assistant

    R. O. Ambrose / M. A. Diftler | NTIS | 2001


    Robonaut: A Robotic Astronaut Assistant

    Ambrose, Robert O. / Diftler, Myron A. | NTRS | 2001