Journal of the Korea Society of Computer and Information (한국컴퓨터정보학회논문지)

Korean Society of Computer Information (한국컴퓨터정보학회)
권호 표지
DOI QR코드

DOI QR Code

Gunnery Classification Method Using Profile Feature Extraction in Infrared Images

적외선 영상에서의 시계열 특징 추출을 이용한 Gunnery 분류 기법 연구

  • Received : 2014.06.19
  • Accepted : 2014.09.19
  • Published : 2014.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Gunnery has been used to detect and classify artilleries. In this paper, we used electro-optical data to get the information of muzzle flash from the artilleries. Feature based approach was applied; we first defined features and sub-features. The number of sub-features was 38~40 generic sub-features, and 2 model-based sub-features. To classify multiclass data, we introduced tree structure with clustering the classes according to the similarity of them. SVM was used for each non-leaf nodes in the tree, as a sub-classifier. From the data, we extracted features and sub-features and classified them by the tree structure SVM classifier. The results showed that the performance of our classifier was good for our muzzle flash classification problem.

Gunnery 표적으로부터 발생하는 영상특징은 장비의 위치를 탐지하고 종류를 판별하는 주요 정보로 활용될 수 있다. 본 논문에서는 Gunnery 영상에서 표적 영역의 밝기값을 획득하여 특징을 추출하고 분류하는 기법을 제안한다. 제안하는 기법에서는 38~40개의 신호 기반 특징과 2개의 모델 기반 특징을 추출하여 분석하고 분류모델에 적용한다. 다중 클래스 분류를 위하여 트리(tree) 기반의 분류 모델을 설계하였으며, 시스템에서 요구하는 Gunnery의 종류와 특성에 따라 유사도를 정의하여 트리 구조를 설계하였다. 트리 구성 단계에서는 각 레벨마다 SVM(Support Vector Machine)을 이용하여 분류 하였으며 시스템에서 요구하는 분류 성능을 만족함을 확인하였다.

Keywords

References

  1. Anthony N. Dills, "Classification of battlespace detonations from temporally resolved multi-band imagery and mid-infrared spectra," Air Force Institute of Technology, 2005.
  2. A. B. Ritter, A. Y. Weisberg, T. J. Slusarchyk, J. J. Lisowski, and B. A. Hibbeln, "Transient Event Characterization," 1999 IEEE Aerospace Conference Proceedings, Vol. 4, pp. 273-280, March 1999.
  3. A. B. Ritter, T. J. Slusarchyk, and J. J. Lisowski, "Enhancement and Assessment of a Transient Event Characterization Algorithm," 2000 IEEE Aerospace Conference Proceedings, Vol. 3, pp. 343-349, March 2000.
  4. S. Hagerty, C. Hilliard and A. Haralson, "Real-time Discrimination of Battlefield Ordnance Using Remote Sensing Data," 2000 IEEE Aerospace Conference Proceedings, Vol. 3, pp. 329-342, March 2000.
  5. J. H. Kim, G. H. Park, J. H. Jung, and Y. S. Moon, "Gunnery Classification Method using Shape 시계열 정보 of Profile and GMM," Journal of IEEK, Vol. 48 CI, No. 5, pp. 16-23, Sept. 2011.
  6. Young-Gu Lee and Woo-Seung Choi, "Learning Networks for Learning the Pattern Vectors Causing Classification Error," Journal of KSCI, Vol. 10, No. 5, pp. 77-86, Nov. 2005.
  7. S. K. Kang, Y. U. Kim, I. M. So, and S. T. Jung, "Enhancement of the Correctness of Marker Detection and Marker Recognition based on Artificial Neural Networks," Journal of KSCI, Vol. 13, No. 1, pp. 89-97, Jan. 2008.
  8. Kwang Seong Kim and Doosung Hwang, "Support Vector Machine Algorithm for Imbalanced Data learning," Journal of KSCI, Vol. 15, No. 7, pp. 11-17, July 2010. https://doi.org/10.9708/jksci.2010.15.7.011
  9. J. H. Kim, K. H. Jang, J. H. Lee, and Y. S. Moon, "Multi-target Classification Method Based on Adaboost and Radial Basis Function," Journal of IEEK, Vol. 47 CI, No. 3, pp. 22-28, May 2010.