DOI QR코드

DOI QR Code

통계적 특성에 의한 객체 영상 검출방안

The Object Image Detection Method using statistical properties

  • Kim, Ji-hong (Department of Information and Communication Engineering, Semyung University)
  • 투고 : 2018.04.11
  • 심사 : 2018.07.04
  • 발행 : 2018.07.31

초록

본 논문은 영상에 포함된 객체 특징을 추출하기 위한 연구로서, 말레이시아 산림에서 드론으로 항공 촬영된 산림 영상사진을 이용하여 실제로 산림 속에 존재하는 나무를 파악하기 위한 방법을 기술한다. 일반적으로 회색조 영상특징 추출방법으로는 LBP 방식과 GLCM 방식, Gabor 필터 방식 등이 많이 사용되고 있다. 본 연구에서는 드론으로 촬영된 영상이므로 나뭇잎 질감이 매우 유사하기 때문에, 질감 자체보다는 표본으로 채취한 샘플들에 대한 통계적 특성을 이용한 객체 추출 방식을 제안한다. 이를 위하여 먼저 샘플 영상을 생성하고, 생성된 샘플영상과 원 영상간의 상호상관관계를 이용하여 객체를 검출한다. 각 샘플영상들에 대한 평균치 및 표준편차는 객체 샘플을 분간하고, 판단하기 위한 중요한 자료로 사용될 수 있으며, 또한 RGB 모델과 HSV 모델의 각 신호성분들을 분석하여 객체판단에 유용한 샘플 영상에 대한 통계값을 이용함으로서 객체 추출 확률을 높일 수 있다.

As the study of the object feature detection from image, we explain methods to identify the species of the tree in forest using the picture taken from dron. Generally there are three kinds of methods, which are GLCM (Gray Level Co-occurrence Matrix) and Gabor filters, in order to extract the object features. We proposed the object extraction method using the statistical properties of trees in this research because of the similarity of the leaves. After we extract the sample images from the original images, we detect the objects using cross correlation techniques between the original image and sample images. Through this experiment, we realized the mean value and standard deviation of the sample images is very important factor to identify the object. The analysis of the color component of the RGB model and HSV model is also used to identify the object.

키워드

참고문헌

  1. V. Arvis, C. Debain, M. Berducat, A. Benass, "Generalization of the co-occurrence matrix for colour images : application to colour texture classification," image Analysis & Stereology, vol.23, no.1, pp 63-72, March 2004. https://doi.org/10.5566/ias.v23.p63-72
  2. N. Jain, S. S. Salankar, "content-based image retrieval using gabor texture feature and color histogram," International Journal of Enhanced research in science technology & engineering, vol. 3 Issue 9, pp 97-102, Sept. 2014.
  3. T. Ojala, M. Pietikinen, D. Harward, "A Comparative Study of Texture Measures with Classification Based on Featured Distributions," Pattern Recognition, vol. 29, no.1 pp 51-59, January 1996. https://doi.org/10.1016/0031-3203(95)00067-4
  4. F. R Siqueira, W. R. Schwartz, H. Pedrini, "Multi-Cable Gray Level Co-occurrence Matrices for Texture Description," Neurocomputing, vol.120, no.23. pp.336-s45, November 2017.
  5. V. Sebastian, A. Unnnikrishnan, K. Balakrishman, K., "Grey Level Co-occurrence Matrices : Generalization and Some New Features," International Journal of Computer Science, Engineering and Information Technology, (IJCSEIT), vol.2. no.2, pp 151-157, April 2012. https://doi.org/10.5121/ijcseit.2012.2213
  6. M. Benco, R. Hudec, P. Kamencay, M. Zachariasova, S. Matuska, "An Advanced Approach to Extraction of Color Texture Features Based on GLCM," International Journal of Advanced Robotic Systems, vol. 2, no.1 pp.1-8, July 2014. https://doi.org/10.1504/IJMRS.2014.064334
  7. K. W. Lee et al, "Implementation of GLCM/GLDV based Texture Algrorithm and Its Application to High Resolution Imagery Analysis," Korea Journal of Remote Sensing, vol.21, no.2, pp.121-133, Feb. 2005.
  8. H. S. Cho et al,"Region of Interest Extraction Method and Hardware Implementation of Matrix Pattern Image," Journal of the Korea Institute of Information and Communication Engineering, vol.19, no.4, pp 940-947, April 2015. https://doi.org/10.6109/jkiice.2015.19.4.940
  9. L. Nani., S. Brahnam, S. Ghidoni, E. Menegatti, T. Barrier, "Different approaches for extracting information from the co-occurrence matrix," PLoS One. 26;8(12):e83554. doi: 10.1371./journal.pone.0083554. eCollection. vol.8, no.12, pp 1-16, December 2013.

피인용 문헌

  1. 효율적인 그래프 기반 2단계 슈퍼픽셀 생성 방법 vol.23, pp.12, 2018, https://doi.org/10.6109/jkiice.2019.23.12.1520