DOI QR코드

DOI QR Code

The study of the stereo X-ray system for automated X-ray inspection system using 3D-reconstruction shape information

3차원 형상복원 정보 기반의 검색 자동화를 위한 스테레오 X-선 검색장치에 관한 연구

  • Received : 2014.06.16
  • Accepted : 2014.07.21
  • Published : 2014.08.31

Abstract

As most the scanning systems developed until now provide radiation scan plane images of the inspected objects, there has been a limitation in judging exactly the shape of the objects inside a logistics container exactly with only 2-D radiation image information. As a radiation image is just the density information of the scanned object, the direct application of general stereo image processing techniques is inefficient. So we propose that a new volume-based 3-D reconstruction algorithm. Experimental results show the proposed new volume based reconstruction technique can provide more efficient visualization for X-ray inspection. For validation of the proposed shape reconstruction algorithm using volume, 15 samples were scanned and reconstructed to restore the shape using an X-ray stereo inspection system. Reconstruction results of the objects show a high degree of accuracy compared to the width (2.56%), height (6.15%) and depth (7.12%) of the measured value for a real object respectively. In addition, using a K-Mean clustering algorithm a detection efficiency of 97% is achieved. The results of the reconstructed shape information using the volume based shape reconstruction algorithm provide the depth information of the inspected object with stereo X-ray inspection. Depth information used as an identifier for an automated search is possible and additional studies will proceed to retrieve an X-ray inspection system that can greatly improve the efficiency of an inspection.

X-선 탐지장치는 검색 대상물에 대한 단면 정보만을 제공하기 때문에 내용물에 대한 판정의 한계가 있다. 스테레오 X-선 탐지 장치는 검색 대상체에 대한 단면 정보와 논문에서 제안된 볼륨기반의 3차원 형상복원 알고리즘을 통해 3차원 정보를 제공하여 검색효율을 높일 수 있다. 또한, 고속 검색을 위해 자동화 검색에 대한 식별자로 형상복원 결과를 적용하고자 유사한 모형의 15개 샘플에 대한 형상 복원 및 검출율을 분석하였다. 검색대상 모델에 대한 복원 결과는 실측 모델과 비교할 때 각각 폭 (2.56%), 높이 (6.15 %)와 깊이 (7.12 %)의 오차를 보이며 높은 정확도를 나타내었다. 또한 K-Mean 클러스터링 알고리즘을 적용하여 실험한 결과 97 %의 검출 효율이 보였다. 본 논문의 결과는 자동화 시스템을 위한 새로운 검색식별자를 제시하며 추가연구를 통해 검색 시스템의 효율성 향상을 위한 연구를 진행할 것이다.

Keywords

References

  1. Domingo Mery, "X-ray Testing: The State of the Art.", The e-Journal of Nondestructive Testing(NDT), Vol. 18, No. 09, pp. 01, 2013.
  2. Hitachi, "Cargo cintainer X-ray inspection systems", Hitachi Review Vol. 53, No. 2, pp. 97, 2004.
  3. A. Noble, R. Gupta, J. Mundy, A. Schmitz, R. Hartley, W. Hoffman, "CAD-based inspection using X-ray stereo", Proceedings - IEEE International Conference on Robotics and Automation, pp. 23
  4. Gupta, R., A. Noble, R. Hartley, J. Mundy, A. Schmitz, Camera calibration for 2.5-D X=ray metrology. Proc. ICIP'95, Vol.3, (1995)
  5. Gupta, R. and R. Hartley, Linear push- broom camera, IEEE Trans PAMI, 19(9), pp963-975, (1997) https://doi.org/10.1109/34.615446
  6. Zhigang Zhu and Yu-Chi Hu, "Gamma /x-ray linear pushbroom stereo for 3D cargo inspection," Proc. SPIE, Conference on Non-Intrusive Inspection Technologies, Vol. 6213, 621304, (2006)
  7. Younggwan-Hwang, Namho-Lee, Seungmin-Lee "The Study of the Geometric Structure Optimization for the Stereo X-ray Inspection System Using the Calibration" Journal of the KAIS, Vol.11, No.9, pp 3422-3427, 2010 https://doi.org/10.5762/KAIS.2010.11.9.3422
  8. Nam-ho Lee, Young-Gwan Hwang, Jong-Won Park, Yong-gon Lim "A Study on Stereo Visualization of the X-ray Scanned Image Based on Dual-line Sensors," Journal of the KIICE, Vol.14, No.9, (2010) https://doi.org/10.6109/jkiice.2010.14.9.2083
  9. Nam-ho Lee, Soon-Yong Park, Young-Gwan Hwang, Jong-Won Park, Yong-gon Lim "A Study on Stereo Visualization of the X-ray Scanned Image Based on Volume Reconstruction", Journal of the KIICE, Vol. 15, No. 7, pp. 1583-1590, (2011). https://doi.org/10.6109/jkiice.2011.15.7.1583