DOI QR코드

DOI QR Code

Object Detection Method in Sea Environment Using Fast Region Merge Algorithm

해양환경에서 고속 영역 병합 알고리즘을 이용한 물표 탐지 기법

  • 정종면 (목포해양대학교 해양컴퓨터공학과) ;
  • 박계각 (목포해양대학교 국제해사수송과학부)
  • Received : 2012.04.20
  • Accepted : 2012.10.08
  • Published : 2012.10.25

Abstract

In this paper, we present a method to detect an object such as ship, rock and buoy from sea IR image for the safety navigation. To this end, we do the image smoothing first and the apply watershed algorithm to segment image into subregions. Since watershed algorithm almost always produces over-segmented regions, it requires posterior merging process to get meaningful segmented regions. We propose an efficient merger algorithm that requires only two times of direct access to the pixels regardless of the number of regions. Also by analyzing IR image obtained from sea environments, we could find out that most horizontal edge come out from object regions. For the given input IR image we extract horizontal edge and eliminate isolated edges produced from background and noises by adopting morphological operator. Among the segmented regions, the regions that have horizontal edges are extracted as final results. Experimental results show the adequacy of the proposed method.

본 논문에서는 선박의 안전 항행을 위하여 해양 IR 영상으로부터 선박, 암초, 부이 등과 같은 해상 물표를 탐지하기 위한 기법을 제안한다. 이를 위하여 먼저 주어진 IR 영상을 평탄화 한 후, 워터쉐드 알고리즘을 이용하여 영역을 분할한다. 워터쉐드 알고리즘은 거의 항상 과분할된 영역을 생성하기 때문에 의미있는 영역 분할을 위해 과분할 영역에 대한 병합 과정이 필요하다. 우리는 빠른 병합을 위해 픽셀에 대한 직접 접근을 단 2회만 수행하는 효율적인 영역 병합 알고리즘을 제안한다. 또한 해양 IR 영상에 대한 분석을 통해 해양 물표에서는 수평방향의 에지가 집중적으로 나타나는 것을 확인하였다. 따라서 본 논문에서는 주어진 영상으로부터 수평에 지를 추출한 후 모폴로지 연산을 통해 배경 및 잡음에 의해 만들어진 고립된 수평에지를 제거한 다음, 이전 단계에서 얻은 분할된 영역 중 수평 방향의 에지영역을 갖는 영역을 물표 영역으로 검출한다. 마지막으로 실험을 통하여 제안된 기법의 타당성을 보였다.

Keywords

References

  1. D. FaulKemer, Shipping Safety, Ingenia, 2003.
  2. Dong Jin Kim, and Su Yong Kwak, "Evaluation of Human Factors in Ship Accedents in the Domestic Sea," Journal of the Ergonomics Society of Korea, vol. 30, no. 1, pp. 87-98, 2011. https://doi.org/10.5143/JESK.2011.30.1.87
  3. A. Toffoli, J. M. Lefevra, E. Bitner-Gregersen, and J. Monbaliu, "Toward the Identification of Warning Criteria: Analysis of a Ship Accident Database," Journal of Applied Ocean Research, vol. 27, pp. 281-291, 2005. https://doi.org/10.1016/j.apor.2006.03.003
  4. A. Toffoli, J. M. Lefevra, E. Bitner-Gregersen, J. Monbaliu, "Towards the identification of warning criteria : Analysis of a ship accident database," Journal of applied ocean research vol. 27, pp. 281-291, 2005. https://doi.org/10.1016/j.apor.2006.03.003
  5. S. Gaarder, K. Rongstad, M. Olofsson, "Impact of human elements in marine risk management," Guedes Soares C., Advances in safety and reliability, pp. 857-898, Pergamon, 1997.
  6. V. E, Vicker, "Plateu equalization algorithm for real- time display of high-quality infrared imagery," Optical engineering, vol. 35, no. 7, pp. 1921-1926, July 1996. https://doi.org/10.1117/1.601006
  7. Q. Chen et al, "An efficient approach to extraction ROI from infrared image sequence," Proc. of SPIE Advances in infrared imaging and application, vol. 7383, 738345-1, doi:10.1117/12.835140, June 2009.
  8. K. Brunstrom et al, "Object detection in cluttered infrared images," Optical engineering, vol. 42, no. 2, pp. 388-399, February 2003. https://doi.org/10.1117/1.1531637
  9. J. Jeong and K. Park, "Object detection algorithm using edge information on the sea environment," Journal of the Korea Society of Computer and Information, vol. 16, no. 9, pp. 69-76, 2011. https://doi.org/10.9708/jksci.2011.16.9.069
  10. Richard E. Woods, Rafael C. Gonzalez, Digital Image Processing Third Edition, Pearson Education International, 2010.
  11. Fernand Meyer, "An algorithm optimal pour la ligne de partage des eaux.," Dans 8me congres de reconnaissance des formes et intelligence artificielle, vol. 2, pp. 847-857, Lyon, France, 1991.
  12. S.W. Lu and H. Xu, "Textured image segmentation using autoregressive model and artificial neural network," Pattern Recognition, vol. 28, no. 12, pp. 1807-1817, 1995. https://doi.org/10.1016/0031-3203(95)00051-8

Cited by

  1. A Scale Invariant Object Detection Algorithm Using Wavelet Transform in Sea Environment vol.23, pp.3, 2013, https://doi.org/10.5391/JKIIS.2013.23.3.249
  2. Robust Object Extraction Algorithm in the Sea Environment vol.24, pp.3, 2014, https://doi.org/10.5391/JKIIS.2014.24.3.298