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

  • 제48권10호
  • /
  • Pages.783-789
  • /
  • 2020
  • /
  • 1225-1348(pISSN)
  • /
  • 2287-6871(eISSN)
한국항공우주학회 (The Korean Society for Aeronautical and Space Sciences)
권호 표지
DOI QR코드

DOI QR Code

의미론적 분할된 항공 사진을 활용한 영상 기반 항법

Vision-based Navigation using Semantically Segmented Aerial Images

  • 투고 : 2020.07.20
  • 심사 : 2020.09.14
  • 발행 : 2020.10.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

영상 기반 항법은 GPS/INS 통합 항법 시스템의 취약점을 보강할 수 있는 보조 항법 기술로 비행체에서 촬영한 항공 영상과 기존의 데이터베이스를 비교하여 비행체의 위치를 구한다. 하지만 데이터베이스가 생성된 시점은 항공 영상 촬영 시점과 다를 수밖에 없으며, 이러한 시점 차이로 인해 두 영상 간의 다른 특징점들이 생성된다. 즉, 유사하지만 다른 두 영상이므로 일반적인 영상 대조 알고리즘을 항법 문제에 적용하기 힘들다. 따라서 본 논문에서는 인공지능 기법인 의미론적 분할을 활용하여 항공 영상에서 항법에 필요한 정보를 분류한 후 영상 대조를 수행하는 방법을 제안한다. 의미론적 분할로 시점 변화, 촬영 조건 변화가 있더라도 강건하게 두 영상이 정합 되도록 한다. 제안한 방법은 시뮬레이션과 비행 실험을 통해 성능을 확인하며, 일반적인 영상 대조 알고리즘을 이용하여 항법을 수행한 결과와 비교한다.

This paper proposes a new method for vision-based navigation using semantically segmented aerial images. Vision-based navigation can reinforce the vulnerability of the GPS/INS integrated navigation system. However, due to the visual and temporal difference between the aerial image and the database image, the existing image matching algorithms have difficulties being applied to aerial navigation problems. For this reason, this paper proposes a suitable matching method for the flight composed of navigational feature extraction through semantic segmentation followed by template matching. The proposed method shows excellent performance in simulation and even flight situations.

키워드

참고문헌

  1. Kim, J. M. and Leeghim, H., "INS/Multi-Vision Integrated Navigation System Based on Landmark," Journal of the Korean Society for Aeronautical and Space Sciences, Vol. 45, No. 8, July 2017, pp. 671-677. https://doi.org/10.5139/JKSAS.2017.45.8.671
  2. Won, D. H., Chun, S. B., Sung, S. K., Cho, J. S. and Lee, Y. J., "Observability Analysis of a Vision-INS Integrated Navigation System Using Landmark," Journal of the Korean Society for Aeronautical and Space Sciences, Vol. 38, No. 3, March 2010, pp. 236-242. https://doi.org/10.5139/JKSAS.2010.38.3.236
  3. Conte, G. and Doherty, P., "Vision-based unmanned aerial vehicle navigation using georeferenced information," EURASIP Journal on Advances in Signal Processing, 2009, 10.
  4. Wu, A. D., "Vision-based navigation and mapping for flight in GPS-denied environments," PhD Thesis, Georgia Institute of Technology, 2010.
  5. Dumble, S. J. and Gibbens, P. W., "Airborne vision-aided navigation using road intersection features," Journal of Intelligent and Robotic Systems, Vol. 78, No. 2, May. 2015, pp. 185-204. https://doi.org/10.1007/s10846-014-0056-3
  6. Hong, K. W., Kim, S. J., Bang, H. C., Kim, J. W., Seo, I. W. and Pak, C. H., "Particle Filters using Gaussian Mixture Models for Vision-Based Navigation," Journal of the Korean Society for Aeronautical and Space Sciences, Vol. 47, No. 4, April 2019. pp. 274-282. https://doi.org/10.5139/JKSAS.2019.47.4.274
  7. Lowe, D. G., "Distinctive image features from scale-invariant keypoints," International journal of computer vision, Vol. 60, No. 2, November 2004, pp. 91-110. https://doi.org/10.1023/B:VISI.0000029664.99615.94
  8. Bay, H., Ess, A., Tuytelaars, T. and Van Gool, L., "Speeded-up robust features (SURF)," Computer vision and image understanding, Vol. 110, No. 3, June 2008, pp. 346-359. https://doi.org/10.1016/j.cviu.2007.09.014
  9. Calonder, M., Lepetit, V., Strecha, C. and Fua, P., "Brief: Binary robust independent elementary features," In European conference on computer vision, Springer, Berlin, Heidelberg, September 2010, pp. 778-792.
  10. Karami, E., Prasad, S. and Shehata, M., "Image matching using SIFT, SURF, BRIEF and ORB: performance comparison for distorted images," arXiv preprint arXiv:1710.02726.
  11. He, K., Gkioxari, G., Dollár, P. and Girshick, R., "Mask r-cnn," Proceedings of the IEEE international conference on computer vision 2017, pp. 2961-2969.
  12. Noh, H. W., Hong, S. H. and Han, B. H., "Learning deconvolution network for semantic segmentation," Proceedings of the IEEE international conference on computer vision 2015, pp. 1520-1528.
  13. Long, J., Shelhamer, E. and Darrell, T., "Fully convolutional networks for semantic segmentation," Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 3431-3440.
  14. Chai, D., Newsam, S. and Huang, J., "Aerial image semantic segmentation using DCNN predicted distance maps," ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 161, March 2020, pp. 309-322. https://doi.org/10.1016/j.isprsjprs.2020.01.023
  15. Montoya-Zegarra, J. A., Wegner, J. D. and Schindler, K., "Semantic segmentation of aerial images in urban areas with class-specific higherorder cliques," ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. 2, 2015, pp. 127-133. https://doi.org/10.5194/isprsannals-II-3-W4-127-2015
  16. Hong, K. W., Kim, S. J. and Bang, H. C., "Vision-based Navigation using Gaussian Mixture Model of Terrain Features," AIAA Scitech 2020 Forum, Jan 2020, p. 1344.
  17. Briechle, K. and Hanebeck, U. D., "Template matching using fast normalized cross correlation," Optical Pattern Recognition XII, International Society for Optics and Photonics, Vol. 4387, March 2001, pp. 95-102.
  18. Mahmood, A. and Khan, S., "Exploiting transitivity of correlation for fast template matching," IEEE Transactions on Image Processing, Vol. 19, No. 8, August 2010, pp. 2190-2200. https://doi.org/10.1109/TIP.2010.2046809
  19. Uchida, A., Ito, Y. and Nakano, K., "Fast and accurate template matching using pixel rearrangement on the GPU," 2011 Second International Conference on Networking and Computing IEEE, December 2011, pp. 153-159
  20. Pele, O. and Werman, M., "Accelerating pattern matching or how much can you slide?," Asian Conference on Computer Vision, November 2007, pp. 435-446.