DOI 10.17586/0021-3454-2023-66-4-297-305
UDC 004.032.26
ESTIMATION OF ORBITAL OBJECT ORIENTATION PARAMETERS BASED ON RESULTS OF SPACE ROBOT OBSERVATION USING MACHINE VISION ALGORITHMS
A. F. Mozhaisky Military Space Academy, Department of Autonomous Control Systems;
Read the full article
Abstract. The problem of estimating the orientation parameters of a spacecraft observed from a space robot is considered, and various approaches to its solution are presented. Results of the study of the accuracy of two approaches to estimating the parameters of the spacecraft orientation from results of a space robot observation using the technical vision methods and convolutional neural networks, are presented. In the first approach, the neural network is used to determine the screen coordinates of the object's special points projections in the image. The second approach is based on the use of a trained convolutional neural network, which directly generates the Euler angles from the observed image.
Keywords: space robot, uncooperative spacecraft, machine vision, orientation, convolutional neural networks
References:
References:
- Cherny I.V. Novosti kosmonavtiki (Space News), 2010, no. 11, pp. 34–36. (in Russ.)
- Wilson J.R. Aerospace America, 2007, рр. 30–35.
- MEV-1 (Mission Extension Vehicle–1) and MEV-2, http://eoportal.org/web/eoportal/satellite-missions/m/mev-1.
- Stepanov D.N., Bakhshiyev A.V., Smirnova E.Yu., Polovko S.A. Voprosy radioelektroniki. Seriya: Tekhnika Televideniya, 2016, no. 1, pp. 61–77. (in Russ.)
- Kanaeva E., Gurevich L., Vakhitov A. Proc. of the British Machine Vision Conference (BMVC), 2015, рр. 162.1–162.12.
- Lepetit V., Moreno-Noguer F., Fua P. Intern. Journal of Computer Vision, 2009, no. 2(81), pp. 155–166.
- Yinqiang Zheng, Satoshi Sugimoto, Imari Sato, Masatoshi Okutomi, Computer Vision and Pattern Recognition (CVPR), 2014, рр. 430–437, DOI: 10.1109/CVPR.2014.62
- Lowe D.C. Proc. Intern. Conf. Computer Vision, 1999, vol. 2, рр. 1150–1157.
- Bay H., Ess A., Tuytelaars T., Van Gool L. Computer Vision Image Understanding, 2008, vol. 110, рр. 346–359.
- Rublee E., Rabaund V., Konolige K., Bradski G. Proc. Intern. Conf. Computer Vision, 2011, рр. 2564–2571.
