DOI QR코드

DOI QR Code

영상 스티칭 관점에서 SIFT 특징점 추출시간 감소를 위한 파라미터 분석

Parameter Analysis for Time Reduction in Extracting SIFT Keypoints in the Aspect of Image Stitching

  • 문원준 (광운대학교 전자재료공학과) ;
  • 서영호 (광운대학교 인제니움학부대학) ;
  • 김동욱 (광운대학교 전자재료공학과)
  • Moon, Won-Jun (Department of Electronic Materials Engineering, Kwangwoon University) ;
  • Seo, Young-Ho (Ingenium College of Liberal Arts, Kwangwoon University) ;
  • Kim, Dong-Wook (Department of Electronic Materials Engineering, Kwangwoon University)
  • 투고 : 2018.06.18
  • 심사 : 2018.07.05
  • 발행 : 2018.07.30

초록

최근 가상현실(VR, Virtual Reality) 등 가장 많은 분야에서 가장 활발히 응용되고 있는 영상매체 중 하나가 전방위 영상 또는 파노라마 영상이다. 이 영상은 다양한 방법으로 획득된 영상들을 스티칭하여 생성하는데, 그 과정에서 스티칭에 필요한 특징점들을 추출하는데 가장 많은 시간이 소요된다. 이에 본 논문은 현재 가장 널리 사용되고 있는 SIFT 특징점을 추출하는 연산시간을 감소하는 것에 목적을 두고 SIFT 특징점들을 추출에 관여하는 파라미터들을 분석한다. 본 논문에서 고려하는 파라미터는 가우시안 필터링에 사용되는 가우시안 커널의 초기 표준편차, 국소극점을 추출하기 위한 가우시안 차영상군의 수, 그리고 옥타브 수의 세 가지이다. SIFT 알고리즘으로는 이 알고리즘을 제안한 Lowe 방식과 컨볼루션 캐스캐이드(convolution cascade) 방식인 Hess 방식을 고려한다. 먼저 각 파라미터 값이 연산시간에 미치는 영향을 분석하고, 실제 스티칭 실험을 수행하여 각 파라미터가 스티칭 성능에 미치는 영향을 분석한다. 마지막으로 두 분석결과를 토대로 성능저하 없이 연산시간을 최소로 하는 파라미터 값들을 추출한다.

Recently, one of the most actively applied image media in the most fields such as virtual reality (VR) is omni-directional or panorama image. This image is generated by stitching images obtained by various methods. In this process, it takes the most time to extract keypoints necessary for stitching. In this paper, we analyze the parameters involved in the extraction of SIFT keypoints with the aim of reducing the computation time for extracting the most widely used SIFT keypoints. The parameters considered in this paper are the initial standard deviation of the Gaussian kernel used for Gaussian filtering, the number of gaussian difference image sets for extracting local extrema, and the number of octaves. As the SIFT algorithm, the Lowe scheme, the originally proposed one, and the Hess scheme which is a convolution cascade scheme, are considered. First, the effect of each parameter value on the computation time is analyzed, and the effect of each parameter on the stitching performance is analyzed by performing actual stitching experiments. Finally, based on the results of the two analyses, we extract parameter value set that minimize computation time without degrading.

키워드

참고문헌

  1. Institute for Information & communications Technology Promotion, Technology Development Trend and Market Forecast of VR/AR, Weekly Technology Trends, Vol.1803, July, 2017.
  2. D. G. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints," International Journal of Computer Vision, Vol.60, No.2, pp.91-110, Jan. 2004, https://doi.org/10.1023/B:VISI.0000029664.99615.94.
  3. M. Brown, and D. G. Lowe, "Automatic Panoramic Image Stitching using Invariant Features," International Journal of Computer Vision, Vol. 74, No.1, pp.59-73, Aug. 2007, https://doi.org/10.1007/s11263-006-0002-3.
  4. F. C. Huang, S. Y. Huang, J. W. Ker, and Y. C. Chen "High- Performance SIFT Hardware Accelerator for Real-Time Image Feature Extraction," IEEE Transactions on Circuits and Systems for Video Technology, Vol.22, No.3, pp.340-351, Mar. 2012, doi: 10.1109/TCSVT.2011.2162760.
  5. M. Grabner, H, Grabner, and H. Bischof, "Fast approximated SIFT," Asian Conference on Computer Vision, pp.918-927, 2006, https://doi.org/10.1007/11612032_92.
  6. Y. Ke, and R. Sukthankar, "PCA-SIFT: A more distinctive representation for local image descriptors," IEEE CVPR2004, Washington DC, USA, pp.506-513, July, 2004, doi: 10.1109/CVPR.2004.1315206.
  7. H. Bay, T. Tuytelaars, and L. V. Gool "SURF: Speeded Up Robust Features," European Conference on Computer Vision, Graz, Austria, pp.404-417, 2006, https://doi.org/10.1007/11744023_32.
  8. R. Hess, "An Open-Source SIFT Library," ACM Multimedia, Firenze, Italy, pp.1493-1496, Oct. 2010.
  9. J. Qiu, T. Huang, and T. Ikenaga, "A FPGA-based dual-pixel processing pipelined hardware accelerator for feature point detection in SIFT," 5th International Joint Conference on INC, IMS and IDC, Seoul, South Korea, pp.1668-1674, Nov. 2009, doi: 10.1109/NCM.2009.38.
  10. H. D. Chati, F. Muhlauer, T. Braum, C. Bobda, and K. Berns, "Hardware/software co-design of a key point detector on FPGA," 15th Annual IEEE Symposium on Field-Programmable Custom Computing Machines, Napa, USA, pp.355-356, 2007, doi: 10.1109/FCCM.2007.61.
  11. M. Lalonde, D. Bryns, L. Gargon, N. Teasdale, and D. Laurendeau, "Real-time eye blink detection with GPU-based SIFT tracking," 4th Canadian Conference on Computer and Robot Vision, Montreal, Canada, pp.481-487, 2007, doi: 10.1109/CRV.2007.54.
  12. G. Hsu, C. Lin, and J. Wu, "Real-time 3-D object recognition using scale invariant feature transform and stereo vision," 4th International Conference on Autonomous Robots Agents, Wellington, New Zealand, pp.239-244, 2009, doi: 10.1109/ICARA.2000.4803919.
  13. K. Mikolajczyk and C. Schmid, "A performance evaluation of local descriptors," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.27, No.10, pp.1615-1630, Oct. 2004, doi: 10.1109/TPAMI.2005.188.
  14. http://www.cs.cmu.edu/afs/cs.cmu.edu/academic/class/15463-f10/www/proj4/www/junjieli/
  15. http://www.cs.cmu.edu/afs/andrew/scs/cs/15-463/ f07/proj4/www/lisachan/
  16. http://hugin.sourceforge.net/tutorials/two-photos/en.shtml
  17. https://sites.google.com/a/umich.edu/eecs442-winter2015/home- work/image-stitching
  18. http://www.cad.zju.edu.cn/home/gfzhang/training/Panorama/Panorama.htm
  19. https://courses.engr.illinois.edu/cs498dwh/fa2010/lectures/Lecture%2017%20-%20Photo%20Stitching.pdf