Journal of the Korean Society for Aeronautical & Space Sciences (한국항공우주학회지)

The Korean Society for Aeronautical and Space Sciences (한국항공우주학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Deep Neural Network based Recognition Model for Space Debris Vision Tracking System

심층신경망 기반 우주파편 영상 추적시스템 인식모델에 대한 연구

  • Lim, Seongmin (Department of Aerospace System Engineering, Korea University of Science & Technology) ;
  • Kim, Jin-Hyung (IT Convergence Technology Team, Korea Aerospace Research Institute) ;
  • Choi, Won-Sub (IT Convergence Technology Team, Korea Aerospace Research Institute) ;
  • Kim, Hae-Dong (IT Convergence Technology Team, Korea Aerospace Research Institute)
  • Received : 2017.06.26
  • Accepted : 2017.08.29
  • Published : 2017.09.01
Download PDF
⟨ Previous Next ⟩

Abstract

It is essential to protect the national space assets and space environment safely as a space development country from the continuously increasing space debris. And Active Debris Removal(ADR) is the most active way to solve this problem. In this paper, we studied the Artificial Neural Network(ANN) for a stable recognition model of vision-based space debris tracking system. We obtained the simulated image of the space environment by the KARICAT which is the ground-based space debris clearing satellite testbed developed by the Korea Aerospace Research Institute, and created the vector which encodes structure and color-based features of each object after image segmentation by depth discontinuity. The Feature Vector consists of 3D surface area, principle vector of point cloud, 2D shape and color information. We designed artificial neural network model based on the separated Feature Vector. In order to improve the performance of the artificial neural network, the model is divided according to the categories of the input feature vectors, and the ensemble technique is applied to each model. As a result, we confirmed the performance improvement of recognition model by ensemble technique.

지속적으로 우주파편이 증가하고 있는 상황에서 국가 우주자산을 안전하게 보호하고 우주개발국으로서 우주환경 보호에 관심을 가지는 것은 중요하다. 우주파편의 급격한 증가를 막기 위한 효과적인 방법 중 하나는 충돌위험이 큰 우주파편들, 그리고 임무가 종료된 폐기위성을 직접 제거해 나가는 것이다. 본 논문에서는 영상기반 우주파편 추적시스템의 안정적인 인식모델을 위해 인공신경망을 적용한 연구에 대해 다루었다. 한국항공우주연구원에서 개발한 지상기반 우주쓰레기 청소위성 테스트베드인 KARICAT을 활용하여 우주환경이 모사된 영상을 획득하였고, 깊이불연속성에 기인한 영상분할 후 각 객체에 대한 구조 및 색상 기반 특징을 부호화한 벡터를 추출하였다. 특징벡터는 3차원 표면적, 점군의 주성분 벡터, 2차원 형상정보, 색상기반 정보로 구성되어있으며, 이 범주를 기반으로 분리한 특징벡터를 입력으로 하는 인공신경망 모델을 설계하였다. 또한 인공신경망의 성능 향상을 위해 입력되는 특징벡터의 범주에 따라 모델을 분할하여 각 모델 별 학습 후 앙상블기법을 적용하였다. 적용 결과 앙상블 기법에 따른 인식 모델의 성능 향상을 확인하였다.

Keywords

References

  1. "ESA BR-336 Space Debris: The ESA Approach", ESA Brochures, Apr. 2017.
  2. Seong, J. D., Kim, H. D. Lim, S. M., "An Analysis of three-dimensional collision probability according to approaching objects to the KOMPSAT series", Journal of the Korean Society for Aeronautical and Space Sciences, Vol. 41, No. 2, 2013, pp. 156-168. https://doi.org/10.5139/JKSAS.2013.41.2.156
  3. Seong, J. D., Kim, H. D. Choi, H. Y., "A Study of the Disposal Maneuver Planning for LEO satellite", Journal of the Korean Society for Aeronautical and Space Sciences, Vol. 44, No. 4, 2016, pp. 352-362. https://doi.org/10.5139/JKSAS.2016.44.4.352
  4. J.C. Liou and N.L. Johnshon, "Risks in space from orbiting debris", Science, 311(5795): pp.340-341, January, 2006. https://doi.org/10.1126/science.1121337
  5. Kim, H. D., Kim, M. K., "Recent Status on Active Space Debris Removal Technologies", Journal of the Korean Society for Aeronautical and Space Sciences, Vol. 43, No. 9, 2015, pp. 845-857. https://doi.org/10.5139/JKSAS.2015.43.9.845
  6. Krizhevsky, A., Sutskever, I., and Hinton, G., "Imagenet classification with deep convolutional neural networks", In Advances in Neural Information Processing Systems(NIPS), 25, 2012, pp. 1106-1114
  7. Girshick, R., Donahue, J., Darrell, T., Malik, J., "Rich feature hierarchies for accurate object detection and semantic segmentation", Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Columbus, OH, 2014, pp. 580-587
  8. Szegedy, C., Toshev, A., and Erhan, D., "Deep neural network for object detection", In Advances in Neural Information Processing Systems(NIPS), 26, 2013, pp. 2553-2561
  9. Zhao, S. P., and Khorasani, K., "A Recurrent Neural Network Based Fault Diagnosis Scheme for a Satellite", Proceedings of the 33rd Annual Conference of the IEEE Industrial Electronics Society(IECON), Taipei, Taiwan, Nov. 5-8, 2007.
  10. Kim, J. H., Lee, D. W., Cho, K. R., Min, C. O., Cho, S. J., "Trajectory Optimization and the Control of a Re-entry Vehicle during TAEM Phase using Artificial Neural Network", Journal of the Korean Society for Aeronautical and Space Sciences, Vol. 37, No. 4, 2009, pp. 350-358. https://doi.org/10.5139/JKSAS.2009.37.4.350
  11. Chen, X., Xiang, S., Liu, C. L., and Pan, C. H., " Vehicle Detection in Satellite Images by Hybrid Deep Convolutional Neural Networks", IEEE Geoscience and Remote Sensing Letters, Vol. 11, No. 10, Oct, 2014, pp. 1797-1801 https://doi.org/10.1109/LGRS.2014.2309695
  12. Langkvist, M., Kiselev, A., Alirezaie, M. and Loutfi, A., "Classification and Segmentation of Satellite Orthoimagery Using Convolutional Neural Networks", Remote Sensing, Vol. 8, No. 4, 2016, pp. 329-349 https://doi.org/10.3390/rs8040329
  13. Hu, M. G., Wang, J. F. and Ge, Y., "Super-Resolution Reconstruction of Remote Sensing Images Using multifractal Analysis", Sensors, Vol. 9, No. 11, 2009, pp. 8669-8683. https://doi.org/10.3390/s91108669
  14. Linares, R. and Furfaro, R., "Space Object Classification Using Deep Convolutional Neural Networks", Proceedings of the 19th International Conference on Information Fusion(FUSION), Jul. 5-8, 2016, pp. 1140-1146
  15. Han, P., Du, J. and Fang, M., "Spatial Object Tracking Using an Enhanced Mean Shift Method Based on Perceptual Spatial-Space Generation Model", Journal of Applied Mathematics, Vol. 2013, 2013.
  16. Rosso, F., Gallo, Allasia, W., Enrico, L., F., Prinetto, P., Rolfo, D., Trotta, P., Favetto, A., Paleari, M. and Ariano, P., "Stereo vision system for capture and removal of space debris", Proceedings of the Design and Architectures for Signal and Image Processing(DASIP), Cagliari, Italy, Oct. 2013, pp. 201-207.
  17. Opromolla, R., Fasano, G., Rufino, G. and Grassi, M., "A Model-Based 3D Template Matching Technique for Pose Acquisition of an Uncooperative Space Object", Sensors, Vol. 15, 2015, pp. 6360-6382
  18. Petit, A., Marchand, E. and Kanani, K., "Tracking complex targets for space rendezvous and debris removal applications", Proceedings of IEEE/RSJ International conference on Intelligent robots and systems, Vilamoura, Portugal, Oct. 2012, pp. 4483-4488
  19. Choi, W. S., Cho, D. H., Song, H. R., Kim, J. H., Ko, S. J., Kim, H. D., "A 5-DOF Ground Testbed for Developing Rendezvous/Docking Algorithm of a Nano-satellite", Journal of the Korean Society for Aeronautical and Space Sciences, Vol. 43, No. 12, 2015, pp. 1124-1131. https://doi.org/10.5139/JKSAS.2015.43.12.1124
  20. Kim, J. H., Choi, W. S., Cho, D. H., Kim, H. D., Lim, S. M., "Visual Information Based Detection and Tracking Algorithm for Capture of Space Debris using Nano-satellite", Proceedings of 29th Workshop on Image Processing and Image Understanding (IPIU 2017), 2017.
  21. Kim, J. H., Lim, S. M., Kim, H. D., "Depth discontinuity based target space debris candidate ROI Extraction from RGB-D image", Proceedings of the 2017 KSAS Spring Conference, 2017, pp. 518-519
  22. Tensorflow, Retrieved Aug. 10, 2017 from https://www.tensorflow.org
  23. Keras, Retrieved Aug. 10, 2017 from https://keras.io/