Journal of Korean Society for Geospatial Information Science (대한공간정보학회지)

Korea Spatial Information Society (대한공간정보학회)
권호 표지
DOI QR코드

DOI QR Code

Time Series Image Stereo Matching Experiment Using the Overlap Method

중첩 방식을 이용한 시계열 영상의 스테레오 정합 실험

  • Received : 2015.03.10
  • Accepted : 2015.03.24
  • Published : 2015.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, experimented how to increase corresponding points which are obtained through stereo matching for dense 3D reconstruction. After extracting a snapshot image from the images acquired through stereo CCTVs, the matching points obtained using the SIFT matching and RANSAC procedure were gradually overlapped. In conclusion, it was confirmed that as images are overlapped, the number of matching points continues to grow.

본 논문에서는 CCTV 영상으로 조밀한 3차원 복원을 하기 위하여 스테레오 정합 과정으로 얻어지는 정합점을 증가시키기 위한 실험을 진행하였다. 실험에서는 시간의 경과에 따라 연속적으로 촬영된 스테레오 CCTV 영상에서 시계열별로 단영상을 추출한 뒤, SIFT 정합 알고리즘과 RANSAC 알고리즘을 적용하여 얻어진 정합점을 순차적으로 중첩하였으며, 결과적으로 정합점의 중첩과정이 반복될수록 정합점 수가 계속해서 증가하는 것을 확인할 수 있었다.

Keywords

References

  1. Bay, H., Ess, A., Tuytelaars, T., Gool, L.V., 2008, 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
  2. Byun, K. W., Im, J. U., Kim, D. D., Nam, K. G., 2008, The 3D shape reconstruction system based on active stereo matching, Proceedings of the of The Institute of Electronics And Information Engineers, pp. 1003-1004.
  3. Cho, Y. W., Pyeon, M. W., Kim, D. S., 2013, Comparison of image matching algorithms in the spatial information system, Proceedings of the Korean Society for Geospatial Information System, pp. 139-142.
  4. Cho, Y. W., 2014, A study on the matching point generation of color image for hyper live mapping, Master's Thesis, Konkuk University, pp. 3-27.
  5. Choi, S. L., Kim, T, M., Yu, W. P., 2009, Performance evaluation of RANSAC family
  6. Jang, I. W., Pyeon, M. W., Kim, D. S., Cho, Y. W., 2013, Analysis of the image matching point increase trends using the overlap method, Proceedings of The Korean Society For Geospatial Information System, pp. 131-134.
  7. Jeong, S. S., Han, S. H., Park, H. K., Heo, J., Cho, H. S., Kim, S. M., 2009, Segmentation of tettrstrial LiDAR point cloud data using RANSAC algorithm, 35th Annual Conference of Korean Society Of Civil Engineers, pp. 1567-1570.
  8. Kim, J. H., Pyeon, M. W., 2014, An experiment of eliminating mismatching points on stereo images for RDM, Proceedings of the Korean Society For Geospatial Information System, pp. 147-148.
  9. Kim, S. J., Kim, K. H., Jun, H. S., 2002, 3D reconstruction from an image sequence, Proceedings of the Korea Multimedia Society Conference, pp. 487-490.
  10. Kim, S. J., Lee, I. P., 2008, 3D road modeling using LIDAR data and a digital map, Korean Journal of Geomatics, Korean Society of Subveying Geodecy, Photogrammetry And Cartography, Vol. 26, No. 2, pp. 165-173.
  11. Kim, Y. T., Park, J. Y., Park, K. T., Moon, Y. S., 2011, Improved feature matching method for stereo image, Proceedings of the Institute Of Electronics And Information Engineers, pp. 970-973.
  12. Lee, J. M., Kim, D. H., Choi, J. S., 2004, A study on stereo matching algorithm using disparity space image, The Institute of Electronics Engineers of Korea - Signal Processing, The Institute of Electronics Engineers of Korea, Vol. 41, No. 6(WN.300), pp. 9-18.
  13. Lee, J. J., Jang, H. J., Kim, G. Y., Choi, H. I., 2006, Robust parameter estimation using fuzzy RANSAC, Journal of KISS : Software and Applications, Korea Information Science Society, Vol. 33, No. 2, pp. 252-266.
  14. Paik, Y. M., Choi, H. J., Seo, Y. H., Kim, D. W., 2010, Improve stereo matching by considering the characteristic points of the image and the cost function, The journal of the Korea Institute of Maritime Information & Communication Sciences, The Korea Institute of Information and Communication Engineering, Vol. 14, No. 7, pp. 1667-1679. https://doi.org/10.6109/jkiice.2010.14.7.1667
  15. Se, S., Lowe, D.G. and Little, J.J., 2005, Vision-based global localization and mapping for mobile robots, Robotics, IEEE Transactions on, Vol. 21, No. 3, pp. 364-375. https://doi.org/10.1109/TRO.2004.839228
  16. Seo, Y. H., Kim, S. H., Choi, J. S., 2005, Three-dimensional reconstruction using the dense correspondences from sequence images, The Journal of The Korean Institute of Communication Sciences, Vol. 30, No. 8C, pp. 775-782.
  17. Youm, M. K., Yoon, H. S., Whang, J. S., Lee, D. H., 2013, Development of the advanced SURF algorithm for efficient matching of stereo image, Journal of the Korean Society For Geospatial Information System, Vol. 21, No. 2, pp. 11-17. https://doi.org/10.7319/KOGSIS.2013.21.2.011