Journal of Korea Multimedia Society (한국멀티미디어학회논문지)

Korea Multimedia Society (한국멀티미디어학회)
권호 표지
DOI QR코드

DOI QR Code

Multiple Ship Object Detection Based on Background Registration Technique and Morphology Operation

배경 구축 기법과 형태학적 연산 기반의 다중 선박 객체 검출

  • 김원희 (부경대학교 IT융합응용공학과) ;
  • ;
  • 김종남 (부경대학교 IT융합응용공학과) ;
  • 문광석 (부경대학교 전자공학과)
  • Received : 2012.03.15
  • Accepted : 2012.10.09
  • Published : 2012.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

Ship object detection is a technique to detect the existence and the location of ship when ship objects are shown on input image sequence, and there are wide variations in accuracy due to environmental changes and noise of input image. In order to solve this problem, in this paper, we propose multiple ship object detection based on background registration technique and morphology operation. The proposed method consists of the following five steps: background elimination step, noise elimination step, object standard position setting step, object restructure step, and multiple object detection steps. The experimental results show accurate and real-time ship detection for 15 different test sequences with a detection rate of 98.7%, and robustness against variable environment. The proposed method may be helpful as the base technique of sea surface monitoring or automatic ship sailing.

선박 객체 검출 기술은 입력된 비디오 및 영상 데이터에서 선박 객체가 존재하는 경우 선박의 위치를 검출하는 기술로서 입력 영상의 환경 변화와 잡음의 영향에 따라서 검출 정확도의 편차가 높다. 이런 문제점을 해결하기 위하여 본 논문에서는 배경 구축 기법과 형태학적 연산 기반의 다중 선박 객체 검출 기술을 제안한다. 제안하는 방법은 배경 제거 단계, 잡음 제거 단계, 객체 기준 위치 설정 단계, 객체 재구성 단계, 다중 객체 검출 단계 등 5단계를 거쳐서 선박을 검출한다. 다양한 변수를 고려한 15가지 실험 비디오를 대상으로 한 실험을 통해서 98.7%의 검출율을 나타내었으며, 환경 변화에 강인한 검출을 수행하는 것을 확인할 수 있었다. 제안하는 방법은 해상 관제와 선박 자동 운항 기술의 기반 기술로서 유용하게 사용될 수 있다.

Keywords

References

  1. F. Porikli, "Achieving Real-Time Object Detection and Tracking Under Extreme Conditions," Journal of Real-time Image Processing, Vol. 1, No. 1, pp. 33-40, 2006. https://doi.org/10.1007/s11554-006-0011-z
  2. L. Vibha, M. Venkatesha, P.G. Rao, N. Suhas, P.D. Shenoy, K.R. Venugopal, and L.M. Patnaik, "Moving Vehicle Identification using Background Registration Technique for Traffic Surveillance," International Multi-Conference of Engineers and Computer Scientists, Vol. 1, pp. 19-21, 2008.
  3. J. Cezar Silveira Jacques, C. Rosito Jung, and S. Musse, "Background Subtraction and Shadow Detection in Grayscale Video Sequences," Proc. of the XVIII Brazilian Symposium on Computer Graphics and Image Processing, pp. 189-197, 2005.
  4. Z. Wei, D. Lee, D. Jilk, and R. Schoenberger, "Motion Projection for Floating Object Detection," Proc. of the 3rd International Conference on Advances in Visual Computing, Vol. 2, pp. 152-161, 2007.
  5. A. Khashman, "Automatic Detection, Extraction and Recognition of Moving Objects," International Journal of Systems Applications Engineering & Development, Vol. 2, Issue 1, pp. 43-51, 2008.
  6. W. Li, K. Yang, J. Chen, Q. Wu, and M. Zhang, "A Fast Moving Object Detection Method via Local Neighborhood Similarity," Proc. of the 2009 IEEE International Conference on Mechatronics and Automation, pp. 4500-4505, 2009.
  7. F. Bi, B. Zhu, L. Gao, and M. Bian, "A Visual Search Inspired Computational Model for Ship Detection in Optical Satellite Images," IEEE Geoscience and Remote Sensing Letters, Vol. 9, No. 4, pp. 749-753. 2012. https://doi.org/10.1109/LGRS.2011.2180695
  8. A. Monnet, A Mittal, N. Paragios, and V. Ramesh, "Background Modeling and Subtraction of Dynamic Scenes," Proc. ICCV 2003, pp. 1305-1312, 2003.
  9. A. Elgammal, D. Harwood, and L.S. Davis, "Non-parametric Model for Background Subtraction," Proc. ECCV 2000, pp. 751-767, 2000.
  10. B.D. Lucas and T. Kanade, "An Iterative Image Registration Technique with an Application to Stereo Vision", Proc. of Image Understanding Workshop, pp. 121-130. 1981.
  11. 김낙빈, "형태학적 연산을 이용한 운송 컨테이너 영상의 문자 분할," 한국멀티미디어학회논문지, Vol. 2, No. 4, pp. 390-399, 1999.

Cited by

  1. The Construction of the Automatic Object Targeting System for Sailing Lookout vol.17, pp.7, 2013, https://doi.org/10.6109/jkiice.2013.17.7.1583