DOI QR코드

DOI QR Code

Infrared Image Segmentation by Extracting and Merging Region of Interest

관심영역 추출과 통합에 의한 적외선 영상 분할

  • Yeom, Seokwon (School of Computer and Communication Engineering, Daegu University)
  • 염석원 (대구대학교 정보통신공학부)
  • Received : 2016.11.20
  • Accepted : 2016.12.20
  • Published : 2016.12.25

Abstract

Infrared (IR) imaging is capable of detecting targets that are not visible at night, thus it has been widely used for the security and defense system. However, the quality of the IR image is often degraded by low resolution and noise corruption. This paper addresses target segmentation with the IR image. Multiple regions of interest (ROI) are extracted by the multi-level segmentation and targets are segmented from the individual ROI. Each level of the multi-level segmentation is composed of a k-means clustering algorithm an expectation-maximization (EM) algorithm, and a decision process. The k-means clustering algorithm initializes the parameters of the Gaussian mixture model (GMM) and the EM algorithm iteratively estimates those parameters. Each pixel is assigned to one of clusters during the decision. This paper proposes the selection and the merging of the extracted ROIs. ROI regions are selectively merged in order to include the overlapped ROI windows. In the experiments, the proposed method is tested on an IR image capturing two pedestrians at night. The performance is compared with conventional methods showing that the proposed method outperforms others.

적외선 영상은 야간에 표적의 탐지가 가능하여 보완과 감시분야에 활용도가 높다. 그러나 가시광선 영상에 비하여 해상도가 낮고 잡음의 영향이 크다는 단점이 있다. 본 논문에서는 적외선 영상의 표적을 분할하는 방법을 연구한다. 표적을 포함하는 다수의 관심영역(Region of Interest)을 다단계 분할 방법을 이용하여 추출하고 관심영역을 입력영상으로 다단계 분할방법을 다시 적용하여 표적을 분할한다. 다단계 분할 방법의 각 단계는 가우시안 혼합모델의 파라미터를 초기화 하고 추정하는 k-means 클러스터링(Clustering)과 EM(Expectation-Maximization) 알고리즘과 추정된 사후확률을 이용하여 각 화소의 클러스터를 결정하는 단계로 구성된다. 본 논문에서 추출된 관심영역을 선택하고 통합하는 방법을 제안한다. 관심영역의 통합은 근접한 모든 관심영역의 윈도우를 포함하도록 이루어진다. 실험에서는 야간의 보행자로부터 획득한 적외선 영상에 제안된 방법을 적용하고 다른 분할 방법과 비교하여 제안한 방법이 우수함을 보인다.

Keywords

References

  1. M. Vollmer and K.-P. Mollmann, Infrared Thermal Imaging: Fundamentals, Research and Applications, Wiley-VCH, 2010.
  2. J. H. Lee and H. Yoon, "Design and Implementation of the Stop line and Crosswalk Recognition Algorithm for Autonomous UGV", Journal of the Korean Institute of Intelligent Systems, vol. 24, no. 3, pp. 271-278, 2014. https://doi.org/10.5391/JKIIS.2014.24.3.271
  3. J. Baek, J. Kim, C. Yoon, and E. Kim, "Part-based Hand Detection Using HOG", Journal of the Korean Institute of Intelligent Systems, vol. 23, no. 6, pp. 551-557, 2013. https://doi.org/10.5391/JKIIS.2013.23.6.551
  4. J. Lee, J.-Y. Lee, and C.-H. Hyun, "Coin Recognition and Classification Using Digital Image Processing", Journal of the Korean Institute of Intelligent Systems, vol. 22, no. 1, pp. 7-11, 2012. https://doi.org/10.5391/JKIIS.2012.22.1.7
  5. Q. Lin, Y.-J. H, and H.-S. Hahn, "Lane Detection in Complex Environment Using Grid-Based Morphology and Directional Edge-link Pairs", Journal of the Korean Institute of Intelligent Systems, vol. 20, no. 6, pp. 786-792, 2010. https://doi.org/10.5391/JKIIS.2010.20.6.786
  6. J.-S. Lee, Y.-C. Lim, and Y.-J. Ryoo, "Vision - based Self Localization Using Ceiling Artificial Landmark for Ubiquitous Mobile Robot", Journal of the Korean Institute of Intelligent Systems, vol. 15, no. 5, pp. 560-566, 2005. https://doi.org/10.5391/JKIIS.2005.15.5.560
  7. S. Erturk, "Region of interest extraction in infrared images using one-bit transform," IEEE Trans. on Signal Processing Letters, vol. 20, no. 10, pp. 952-955, 2013. https://doi.org/10.1109/LSP.2013.2274637
  8. D. K. Shin and Y. S. Moon, "Extraction of infrared target based on Gaussian mixture model," IEEK Trans. on Smart Processing and Computing, vol. 2, no. 6, pp. 332-338, 2013.
  9. C. W. Park, J. M. Lee, Y. M. Kim, Y. Kim, T. L. Song, K. T. Park, and Y. S. Moon, "Extracting targets from regions-of-interest in infrared images using a 2-D histogram," Optical Engineering, vol. 50, no. 2, pp. 027003-1-4, 2011 https://doi.org/10.1117/1.3536471
  10. D.-S. Lee and S. Yeom, "Infrared image segmentation with Gaussian mixture modeling", SPIE Defense Security Sensing, vol. 8406, no. 83551J, pp. 1-5, 2012.
  11. S. Yeom and D.-S. Lee, "Multilevel segmentation of infrared images with Gaussian mixture modeling," DSP In-Vehicle, 2013.
  12. S. Yeom, "Multi-level segmentation of infrared images with region of interest extraction," International Journal of Fuzzy Logic and Intelligent Systems, vol. 16, no. 4, 2016.
  13. S. Yeom, "A Study on Infrared Image Segmentation with Region of Interest Extraction," Proceedings of KIIS Autumn Conference, vol. 26, no. 2, pp. 246-253, 2016.
  14. S. Yeom, D.-S. Lee, J.-Y. Son, M.-K. Jung, Y. Jang, S.-W. Jung, and S.-J. Lee, "Real-time outdoor concealed-object detection with passive millimeter wave imaging," Optics Express, vol. 19, no. 3, pp. 2530-2536, 2011. https://doi.org/10.1364/OE.19.002530
  15. http://guideinfrared.com/