Yunda Sun
ABSTRACT
To obtained the trajectory of an orbiting satellite is a fundamental and vital step for space rendezvous and manipulation by space robots. Due to the freely and rapidly motion of on-orbiting satellites, the sudden change in appearance, orbiting satellite tracking is difficult for traditional tracker, which usually relies on a single bounding box of the target object. However, more information should be provided by visual tracking such as binary mask. In this paper, we proposed a SOST (Segmentation-based Orbiting Satellite Tracking) algorithm that improves the performance of tracking. Our method, SOST, improves the tracking performance by generating a mask map obtained from segmentation within the initial bounding box. The final bounding box will be refined using the segmentation result. Experiment using real on-orbit rendezvous and docking video from NASA (Nation Aeronautics and Space Administration), simulated satellite animation sequence from ESA (European Space Agency) and image sequences of 3D printed satellite model took in our laboratory demonstrate the robustness, versatility and fast speed of our method compared to state-of-the-art tracking methods. Our dataset will be released for academic use in future.
- Gao, Y. and S. Chien, Review on space robotics: Toward top-level science through space exploration. Science Robotics, 2017. 2(7): p. eaan5074.Google Scholar
Cross Ref
- Yoshida, K., Achievements in space robotics. IEEE Robotics & Automation Magazine, 2009. 16(4): p. 20--28.Google Scholar
- Fehse, W., Automated rendezvous and docking of spacecraft. Vol. 16. 2003: Cambridge university press.Google Scholar
- Kelsey, J.M., et al. Vision-based relative pose estimation for autonomous rendezvous and docking. in 2006 IEEE aerospace conference. 2006. IEEE.Google Scholar
- Bolme, D.S., et al. Visual object tracking using adaptive correlation filters. in Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on. 2010. IEEE.Google ScholarCross Ref
- Comaniciu, D. and P. Meer, Mean shift: A robust approach toward feature space analysis. IEEE Transactions on pattern analysis and machine intelligence, 2002. 24(5): p. 603--619.Google Scholar
- Danelljan, M., et al. ECO: Efficient Convolution Operators for Tracking. in CVPR. 2017.Google Scholar
- Danelljan, M., et al. Beyond correlation filters: Learning continuous convolution operators for visual tracking. in European Conference on Computer Vision. 2016. Springer.Google ScholarCross Ref
- Danelljan, M., et al. Adaptive color attributes for real-time visual tracking. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014.Google ScholarDigital Library
- Henriques, J.F., et al., High-speed tracking with kernelized correlation filters. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015. 37(3): p. 583--596.Google Scholar
- Simonyan, K. and A. Zisserman, Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.Google Scholar
- Harris, C.G. and M. Stephens. A combined corner and edge detector. in Alvey vision conference. 1988. Citeseer.Google Scholar
- Canny, J., A computational approach to edge detection, in Readings in computer vision. 1987, Elsevier. p. 184--203.Google Scholar
- Lowe, D.G.J.I.J.o.C.V., Distinctive Image Features from Scale-Invariant Keypoints. 2004. 60(2): p. 91--110.Google Scholar
- Bay, H., T. Tuytelaars, and L.V. Gool. SURF: Speeded Up Robust Features. in European Conference on Computer Vision. 2006.Google Scholar
- Lourakis, M. and X. Zabulis. Model-based visual tracking of orbiting satellites using edges. in Ieee/rsj International Conference on Intelligent Robots and Systems. 2017.Google Scholar
- Nam, H., M. Baek, and B.J.a.p.a. Han, Modeling and propagating cnns in a tree structure for visual tracking. 2016.Google Scholar
- Danelljan, M., et al. Convolutional features for correlation filter based visual tracking. in Proceedings of the IEEE International Conference on Computer Vision Workshops. 2015.Google ScholarDigital Library
- Bertinetto, L., et al. Fully-convolutional siamese networks for object tracking. in European conference on computer vision. 2016. Springer.Google ScholarCross Ref
- Li, B., et al. High performance visual tracking with siamese region proposal network. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.Google ScholarCross Ref
- Li, B., et al. Siamrpn++: Evolution of siamese visual tracking with very deep networks. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019.Google ScholarCross Ref
Index Terms
- Segmentation-based orbiting satellite tracking
Recommendations
Practical horizon plane for low earth orbiting (LEO) satellite ground stations
TELE-INFO'09: Proceedings of the 8th Wseas international conference on Telecommunications and informaticsCommunication via satellite begins when the satellite is positioned in the desired orbital position. Ground stations can communicate with LEO (Low Earth Orbiting) satellites only when the satellite is in their visibility region. The duration of the ...
Practical horizon plane and communication duration for low earth orbiting (LEO) satellite ground stations
Communication via satellite begins when the satellite is positioned in the desired orbital position. Ground stations can communicate with LEO (Low Earth Orbiting) satellites only when the satellite is in their visibility region. The visibility region is ...
Downlink performance comparison for Low Earth Orbiting satellite ground stations at S-band in Europe
MIC '08: Proceedings of the 27th IASTED International Conference on Modelling, Identification and ControlMicrosatellites in Low Earth Orbits (LEO) have been in use for the past two decades. Low Earth Orbit satellites are used for public communication and also for scientific purposes. Thus, it may be expected that such missions will be further developed in ...
Comments