Korean Journal of Remote Sensing (대한원격탐사학회지)

Korean Society of Remote Sensing (대한원격탐사학회)
권호 표지
DOI QR코드

DOI QR Code

Detection of Group of Targets Using High Resolution Satellite SAR and EO Images

고해상도 SAR 영상 및 EO 영상을 이용한 표적군 검출 기법 개발

  • Kim, So-Yeon (Department of Geoinformation Engineering, Sejong University) ;
  • Kim, Sang-Wan (Department of Geoinformation Engineering, Sejong University)
  • 김소연 (세종대학교 지구정보공학과) ;
  • 김상완 (세종대학교 지구정보공학과)
  • Received : 2015.02.03
  • Accepted : 2015.04.17
  • Published : 2015.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, the target detection using both high-resolution satellite SAR and Elecro-Optical (EO) images such as TerraSAR-X and WorldView-2 is performed, considering the characteristics of targets. The targets of our interest are featured by being stationary and appearing as cluster targets. After the target detection of SAR image by using Constant False Alarm Rate (CFAR) algorithm, a series of processes is performed in order to reduce false alarms, including pixel clustering, network clustering and coherence analysis. We extend further our algorithm by adopting the fast and effective ellipse detection in EO image using randomized hough transform, which is significantly reducing the number of false alarms. The performance of proposed algorithm has been tested and analyzed on TerraSAR-X SAR and WordView-2 EO images. As a result, the average false alarm for group of targets is 1.8 groups/$64km^2$ and the false alarms of single target range from 0.03 to 0.3 targets/$km^2$. The results show that groups of targets are successfully identified with very low false alarms.

본 연구에서는 고해상도 위성영상인 TerraSAR-X와 WorldView-2 등을 융합하여 표적의 특성을 고려한 표적군(Group of targets) 검출을 수행하였다. 관심 대상으로 하는 표적은 고정되어 있으며, 군(Group)을 이루고 있는 특징이 있다. 표적 후보를 검출하기 위해 대상 물체의 레이더 후방산란 특성을 이용한 Constant False Alarm Rate (CFAR) 알고리즘을 적용하였다. 검출된 표적 후보군으로부터 비표적을 제거하기 위해 표적의 크기 정보를 이용한 화소 클러스터링, 표적군을 이루는 표적들간의 배치 특성을 이용한 네트워크 클러스터링. 그리고 SAR 간섭기법 적용이 가능한 간섭쌍이 있는 경우 긴밀도 정보를 이용하였다. 또한, 오경보(False Alarm)를 감소시키고 최종 표적을 결정하기 위해, 표적의 형태 정보를 추출할 수 있는 Electro-Optical (EO) 영상을 바탕으로 효과적인 타원 검출 기법을 개발하였다. 개발된 표적군 검출 알고리즘을 10개 지역에 적용한 결과, 표적군 검출율은 100%, 단일 표적에 대한 오경보율은 0.03~0.3개/$km^2$, 평균 오경보는 1.8군/$64km^2$로 낮은 오경보와 높은 검출율을 보이며 표적군이 검출되었다. 본 연구에서 개발된 표준화된 표적 검출 기법은 향후 무인화된 표적 검출 시스템 구축에 핵심적인 기술이 될 것으로 전망한다.

Keywords

References

  1. AIR POWER AUSTRALIA, 2014. http://www.ausairpower.net.
  2. AMI, 2014. http://www.aussiemodeller.com.au.
  3. Chan, L., S.Z. Der and N.M. Nasrabadi, 2005. A joint compression-discrimination neural transformation applied to target detection, IEEE Transactions on Systems, Man, and Cybernetics, Part B, pp. 670-681.
  4. Changlin, W. and Z. Xuelian, 2007. Analysis of Man-Made Target Detection in SAR Imagery, Proc. of presented at the annual meeting of the Envisat Symposium, Montreux, April 23-27.
  5. Chen D. and X. Li, 2009. Target Detection in SAR Image Based-on Wavelet Transform and Fractal Feature, Proc. of Image and Signal Processing, 2009. CISP '09. 2nd International Congress on, 1-4.
  6. Fan, B., 2013. Registration of Optical and SAR Satellite Images by Exploring the Spatial Relationship of the Improved SIFT, IEEE Geoscience and Remote Sensing Letters, 10(4): 657-661. https://doi.org/10.1109/LGRS.2012.2216500
  7. Gao G., L. Liu, L. Zhao, G. Shi, and G. Kuang, 2009. An adaptive and fast CFAR algorithm based on automatic censoring for target detection in highresolution SAR iimages, IEEE Trans. Geosci. Remote Sens., 47(6): 1685-1697. https://doi.org/10.1109/TGRS.2008.2006504
  8. Javidi, B., 2002, Image Recognition and Classification: Algorithms, Systems, and Applications, Marcel Dekker, USA.
  9. Lee, K.J., 2009. Three Dimensional Object Recognition using PCA and KNN, The Korea Contents Society, 9(8): 57-63 (in Korean with English abstract).
  10. Lowe, D.G., 2004. Distinctive image features from scale-invariant keypoints. IJCV, 60(2): 91-110. https://doi.org/10.1023/B:VISI.0000029664.99615.94
  11. Moon, H., R. Chellappa, and A. Rozenfeld, 2002. Optimal edge-based shape detection, IEEE transactions on Image Processing, 11(11): 1209-1226. https://doi.org/10.1109/TIP.2002.800896
  12. Novak, L.M., G.J. Owirka, W.S. Brower and A.L. Weaver 1997. The automatic target recognition system in SAIP, The Lincoln Laboratory J., 10(2): 187-202.
  13. Park, M., C. Kim, and J. Park, 2011. A Study on Canny Edge Detector Design Based on Image Fuzzification, The Journal of the Korea Institute of Maritime Information & Communication Sciences, 15(9): 1925-1931 (in Korean with English abstract). https://doi.org/10.6109/jkiice.2011.15.9.1925
  14. Perlovsky, L.I., W.H. Schoendorf, B.J. Burdick, D.M. Tye et al., 1997. Model-based neural network for target detection in SAR images, IEEE Trans. Image Process, 6(1): 203-216. https://doi.org/10.1109/83.552107
  15. Song, W.Y., S-H. Rho, C-H. Jung, Y-K., Kwag, 2010. Synthetic Aperture Radar Target Detection Using Multi-Cell Averaging CFAR Scheme, Journal of Electromagnetic Engineering and Science, 21(2): 164-169 (in Korean with English abstract).
  16. Song, W. Y., 2011. Target Detection using SAR/EO Multi-Sensor Images, Korea Aerospace University, Korea (in Korean with English abstract).
  17. Suri S. and P. Reinartz, 2010. Mutual-information-based registration of TerraSAR-X and Ikonos imagery in urban areas, IEEE Trans. Geosci. Remote Sens., 48(2): 939-949. https://doi.org/10.1109/TGRS.2009.2034842
  18. SimHQ Inc., 2014. http://www.simhq.com.
  19. Ye, W., C. Paulson, D.O. Wu and J.Li, 2008. A Rotation-Invariant Transform for Target Detection in SAR Images, Proc. of SPIE 6970, Algorithms for Synthetic Aperture Radar Imagery XV, April 15.

Cited by

  1. KOMPSAT-5 Spotlight Mode SAR 영상을 이용한 웨이브글라이더 탐지 사례 보고 vol.34, pp.2, 2018, https://doi.org/10.7780/kjrs.2018.34.2.2.10