KSCE Journal of Civil and Environmental Engineering Research (대한토목학회논문집)

Korean Society of Civil Engeneers (대한토목학회)
권호 표지
DOI QR코드

DOI QR Code

Comparative Performance Analysis of Feature Detection and Matching Methods for Lunar Terrain Images

달 지형 영상에서 특징점 검출 및 정합 기법의 성능 비교 분석

  • Hong, Sungchul (Korea Institute of Civil Engineering and Building Technology) ;
  • Shin, Hyu-Soung (Korea Institute of Civil Engineering and Building Technology)
  • 홍성철 (한국건설기술연구원, 미래융합연구본부) ;
  • 신휴성 (한국건설기술연구원, 미래융합연구본부)
  • Received : 2020.04.01
  • Accepted : 2020.04.30
  • Published : 2020.08.01
Download PDF
⟨ Previous Next ⟩

Abstract

A lunar rover's optical camera is used to provide navigation and terrain information in an exploration zone. However, due to the scant presence of atmosphere, the Moon has homogeneous terrain with dark soil. Also, in extreme environments, the rover has limited data storage with low computation capability. Thus, for successful exploration, it is required to examine feature detection and matching methods which are robust to lunar terrain and environmental characteristics. In this research, SIFT, SURF, BRISK, ORB, and AKAZE are comparatively analyzed with lunar terrain images from a lunar rover. Experimental results show that SIFT and AKAZE are most robust for lunar terrain characteristics. AKAZE detects less quantity of feature points than SIFT, but feature points are detected and matched with high precision and the least computational cost. AKAZE is adequate for fast and accurate navigation information. Although SIFT has the highest computational cost, the largest quantity of feature points are stably detected and matched. The rover periodically sends terrain images to Earth. Thus, SIFT is suitable for global 3D terrain map construction in that a large amount of terrain images can be processed on Earth. Study results are expected to provide a guideline to utilize feature detection and matching methods for future lunar exploration rovers.

달 로버의 광학 카메라는 로버의 주행정보와 탐사 지역의 3차원 지형정보를 제공한다. 하지만 대기가 없는 달은 단조로운 지형과 어두운 색조의 토양으로 구성되며, 달의 혹독한 환경에서 로버는 낮은 데이터 저장 용량과 연산 성능을 가진다. 따라서 로버의 안전한 주행과 성공적인 달 탐사를 위해서는 달의 지형 및 환경 특성에 강인한 특징점 검출 및 정합 기법 사용이 검토되어야 한다. 본 연구에서는 달 탐사 로버가 취득한 지형 영상을 대상으로 SIFT, SURF, BRISK, ORB, AKAZE들의 성능을 비교 분석하였다. 실험 결과 SIFT와 AKAZE가 달 지형 특성에 강인한 성능을 보여 주었다. AKAZE는 SIFT에 비해 적은 개수의 영상 정합점들을 검출하였으나, 높은 정확도를 가지며 가장 빠르게 영상 정합점들을 검출하였다. 따라서 정확하고 신속한 연산이 필요한 로버 주행 정보 생성에 적합하다. SIFT는 가장 무거운 연산 속도를 보이나, 가장 많은 영상 정합점들을 안정적으로 검출하였다. 달 탐사 로버는 주기적으로 지형 영상을 지구로 전송한다. 따라서 많은 양의 지형 영상을 처리할 수 있는 지구에서 3차원 지형도 구축을 위해 사용하는 것이 적합하다. 본 연구 결과는 향후 달 탐사 로버에서 특징점 검출 기법들의 활용을 위한 가이드라인을 제공할 수 있을 것으로 기대된다.

Keywords

References

  1. Ahn, M. S. and Lee, Y. G. (2008). "Trend of rover development and mission analysis of lunar exploration rovers." In Proceedings of The Korean Society For Aeronautical And Space Sciences, Korea, pp. 1301-1304 (in Korean).
  2. Alcantarilla, P. F., Nuevo, J. and Bartoli, A. (2013). "Fast explicit diffusion for accelerated features in nonlinear scale spaces." In Proceedings of British Machine Vision Conference, Bristol, United Kingdom, pp. 13.1-13.11.
  3. An, P., Liu, Y., Zhang, W. and Jin, Z. (2018). "Vision-based simultaneous localization and mapping on lunar rover." In Proceedings of IEEE 3rd International Conference on Image, Vision and Computing, Chongqing, China, pp. 487-493.
  4. Bay, H., Tuytelaars, T. and Gool, L. V. (2008). "SURF: Speeded up robust features." Computer Vision and Image Understanding, Vol. 110, No. 3, pp. 346-359. https://doi.org/10.1016/j.cviu.2007.09.014
  5. Choi, S., Lee, D., Bae, J., Ryu, D., Ju, G. and Sim, E. (2015). "Introduction to Chang'e-3 and Analysis of Estimated Mission Trajectory"The Korean Society for Aeronautical and Space Sciences, Vol. 43, No. 11, pp. 984-997, DOI: http://dx.doi.org/10.5139/JKSAS.2015.43.11.984 (in Korean).
  6. Choi, Y. J., Mohammad, G. F., Hong, S. H. and Shon, H. G. (2019). "Feature-based matching algorithms for registration between LiDAR point cloud intensity data acquired from MMS and image data from UAV." Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 37, No, 6, pp. 453-464, DOI: https://doi.org/10.7848/ksgpc.2019.37.6.453 (in Korean).
  7. Cowan, B., Imanberdiyev, N., Fu, C., Dong, Y. and Kayacan, E. (2016). "A performance evaluation of detectors and descriptors for UAV visual tracking." In Proceedings of 14th International Conference on Control, Automation, Robotics and Vision, Phuket, Thailand, pp. 1-6.
  8. Eom, W. S., Kim, Y. G., Lee, J. H., Choi, G. H. and Sim, E. S. (2012). "Development trends of unmanned planetary exploration rover by NASA." Current Industrial and Technological Trends in Aerospace, Vol. 10, No. 2, pp. 102-111. (in Korean).
  9. European Space Agency (ESA) (2016). Moon village: A vision for global cooperation and space 4.0, Available at: https://www.esa.int/About_Us/Ministerial_Council_2016/Moon_Village (Accessed: March 4, 2020).
  10. Fischler, M. A. and Bolles, R. C. (1981). "Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography." Communications of the ACM, Vol. 24, No. 6, pp. 381-395. https://doi.org/10.1145/358669.358692
  11. Fuke, Y. and Krotkov, E. (1996). "Dead reckoning for a lunar rover on uneven terrain." In Proceedings of IEEE International Conference on Robotics and Automation, Vol. 1, Minneapolis, USA, pp. 411-416.
  12. Hong, S. C. and Shin, H. S. (2018). "Trend analysis of lunar exploration missions for lunar base construction." Journal of the Korea Academia-Industrial Cooperation Society, Vol. 19, No. 7, pp. 144-152, DOI: https://doi.org/10.5762/KAIS.2018.19.7.144 (in Korean).
  13. Hong, S. C., Chung, T. I. Park, J. M. and Shin, H. S. (2019). "Research on development of construction spatial information technology, using rover's camera system." Journal of the Korea Academia-Industrial Cooperation Society, Vol. 20, No. 7, pp. 630-637, DOI: https://doi.org/10.5762/KAIS.2019.20.7.630 (in Korean).
  14. Ju, G. H. (2016). "Development status of domestic & overseas space exploration & associated technology." Journal of The Korean Society for Aeronautical and Space Sciences, Vol. 44, No. 8, pp. 741-757, DOI: https://doi.org/10.5139/JKSAS.2016.44.8.741 (in Korean).
  15. Jung, H. J. and Yoo, J. S. (2015) "Feature matching algorithm robust to viewpoint change." Journal of Korea Institute of Communication Sciences, Vol. 40, No. 12, pp. 2363-2371, DOI: http://dx.doi.org/10.7840/kics.2015.40.12.2363 (in Korean).
  16. Kim, K. J. (2017). "A research trend on lunar resource and lunar base." The Journal of the Petrological Society of Korea, Vol. 26, No. 4, pp. 373-384, DOI: https://doi.org/10.7854/JPSK.2017.26.4.373 (in Korean).
  17. Kim, S. J., Lee, S. W. and Seo, D. M. (2019). "A comparative analysis of image feature extraction algorithm for generation of panorama images in tunnel." In Proceedings of The Korean Institute of Information Scientists and Engineers, pp. 1409-1411.
  18. Kim, S. R., Yoo, H. J., Sohn, K. H. (2012). "FAST and BRIEF based real-time feature matching algorithms." In Proceedings of Spring Conference on Korean Institute of Broadcast and Media Engineers, pp. 1-4 (in Korean).
  19. Kim, Y. R. and Song, Y. J. (2019). "Observational arc-length effect on orbit determination for Korea pathfinder lunar orbiter in the earth-moon transfer phase using a sequential estimation." Journal of Astronomy and Space Sciences, Vol. 36, No. 4, pp. 293-306. https://doi.org/10.5140/JASS.2019.36.4.293
  20. Lakshmi, M. D., Mirunalini, P., Priyadharsini, R. and Mirnalinee, T. T. (2018). "Review of feature extraction and matching methods for drone image stitching." In Proceedings of International Conference on ISMAC in Computational Vision and Bio-Engineering, Palladam, India, pp. 595-602.
  21. Lee, T. J., Jang, B. M., Lee, D. H., Han, K. M., Park, K. S. and Cho, D. I. (2013a). "Performance evaluation of various feature detector & descriptor algorithms." In Proceedings of Institute of Control, Robotics and Systems, pp. 381-382.
  22. Lee, W. B., Ju, G. H., Choi, G. H. and Sim, E. S. (2011). "Development trends of space robots." Current Industrial and Technological Trends in Aerospace, Vol. 9, No. 2, pp. 158-175 (in Korean).
  23. Lee, Y. H., Park, J. H. and Kim, Y. S. (2013b). "Comparative analysis of the performance of SIFT and SURF." Journal of the Semiconductor & Display Technology. Vol. 12, No. 3. pp. 59-64. (in Korean).
  24. Leutenegger, S., Chli, M. and Siegwart, R. Y. (2011). "BRISK: Binary robust invariant scalable keypoints." In Proceedings of International Conference on Computer Vision, Barcelona, Spain, pp. 2548-2555.
  25. Lowe, D. G. (2004). "Distinctive image features from scale invariant keypoints." International Journal of Computer Vision, Vol. 60, No. 2, pp. 91-110. https://doi.org/10.1023/B:VISI.0000029664.99615.94
  26. Muja, M. and Lowe, D. G. (2009). "Flann, fast library for approximate nearest neighbors." In Proceedings in International Conference on Computer Vision Theory and Applications, Lisboa, Portugal, pp. 331-340.
  27. NASA (2018). Yutu, Available at: https://solarsystem.nasa.gov/missions/yutu/in-depth/ (Accessed: March 2, 2020).
  28. NASA (2019). Commercial lunar payload services, Available at: https://www.nasa.gov/content/ commercial-lunar-payload-services (Accessed: March 3, 2020).
  29. NASA (2020). Artemis, Available at: https://www.nasa.gov/artemis program (Accessed: March 3, 2020).
  30. Norris, J. S., Powell, M. W., Vona, M. A., Backes, P. G. and Wick, J. V. (2005). "Mars exploration rover operations with the science activity planner." In Proceedings of the 2005 IEEE International Conference on Robotics and Automation, Barcelona, Spain, pp. 4618-4623.
  31. Rublee, E., Rabaud, V., Konolige, K. and Bradski, G. (2011). "ORB: An efficient alternative to SIFT or SURF." Proceedings of International Conference on Computer Vision, Barcelona, Spain, pp. 2564-2571.
  32. Shin, H. S. and Hong, S. C. (2018). "A deep-learning based automatic detection of craters on lunar surface for lunar construction." Journal of the Korean Society of Civil Engineers, KSCE, Vol. 38, No. 6, pp. 859-865, DOI: https://doi.org/10.12652/Ksce.2018.38.6.0859 (in Korean).
  33. Tareen, S. A. K. and Saleem, Z. (2018). "A comparative analysis of sift, surf, kaze, akaze, orb, and brisk." In Proceedings of International conference on computing, mathematics and engineering technologies, Sukkur, Pakistan, pp. 1-10.
  34. The Planetary Society (2016). Chang'e 3 data: Rover panoramic camera (PCAM), Available at: http://planetary.s3.amazonaws. com/data/change3/pcam.html (Accessed: February 10, 2020).
  35. Wu, W., Li, C., Zuo, W., Zhang, H., Liu, J., Wen, W., Su, Y., Ren, X., Yan, J., Yu, D., Dong, G., Wang, C., Sun, Z., Liu, E., Yang, J. and Ouyang, Z. (2019). "Lunar farside to be explored by Chang'e-4." Nature Geoscience, Vol. 12, No. 4, pp. 222-223. https://doi.org/10.1038/s41561-019-0341-7