고해상도 위성영상의 객체기반 분석을 위한 영상 분할 기법 개발 및 평가 = Development and Evaluation of Image Segmentation Technique for Object-based Analysis of High Resolution Satellite Image

다국어 초록 (Multilingual Abstract)

Image segmentation technique is becoming increasingly important in the field of remote sensing image analysis in areas such as object oriented image classification to extract object regions of interest within images. This paper presents a new method for image segmentation to consider spectral and spatial information of high resolution satellite image.
Firstly, the initial seeds were automatically selected using local variation of multi-spectral edge information. After automatic selection of significant seeds, a segmentation was achieved by applying MSRG which determines the priority of region growing using information drawn from similarity between the extracted each seed and its neighboring points. In order to evaluate the performance of the proposed method, the results obtained using the proposed method were compared with the results obtained using conventional region growing and watershed method. The quantitative comparison was done using the unsupervised objective evaluation method and the object-based classification result. Experimental results demonstrated that the proposed method has good potential for application in the object-based analysis of high resolution satellite images.

국문 초록 (Abstract)

영상분할은 관심대상이 되는 물체의 영역을 추출하기 위한 객체기반 영상분류의 전처리과정으로서 원격탐사 영상분석에서 그 중요성 날로 커지고 있다. 본 연구에서는 고해상도 위성영상의 분광 및 공간정보를 반영할 수 있는 새로운 분할방법을 제안한다. 이를 위해 우선 다중분광 에지정보의 지역적 변이특성을 이용하여 영상에서 자동으로 초기시드 점을 추출하였다. 추출된 시드 점과 이웃하는 점들과의 유사성을 기반으로영역 확장의 우선순위를 결정하는 MSRG기법을 이용하여 영상분할을 수행하였다. 제안된 기법의 효율성을평가하기 위해 기존에 위성영상분할에 많이 사용된 유역분할법과 영역성장기법과의 시각적/정량적 비교평가를 수행하였다. 정량적 비교평가 방법으로는 무감독 영상분할 평가 측정치와 동일한 조건하에서 수행된 객체기반 분류 정확도를 이용하였다. 실험 결과 제안한 기법은 고해상도 위성영상의 객체기반 분석에 유용하게적용될 수 있으리라 판단된다.

참고문헌 (Reference)

1 변영기, "시드 기반 영역확장기법을 이용한 고해상도 위성영상 분할기법 개발" 한국측량학회 28 (28): 421-430, 2010

2 한유경, "서그먼트 기반의 Spatial Feature 추출을 통한 고해상도 영상 분류정확도 개선" 서울대학교 2009

3 Vincent, L, "Watershed in digital space: An efficient algorithm based on immersion simulation" 13 (13): 583-598, 1991

4 Chabrier, S, "Unsupervised evaluation of image segmentation appliation to multispectral images" 2004

5 Puissant, A, "The utility of texture analysis to improve per-pixel classification for high to very high spatial resolution imagery" 26 (26): 733-745, 2005

6 Xiao, P, "Segmentation of multispectral high-resolution satellite imagery using log Gabor filters" 31 (31): 1427-1439, 2010

7 Adams, R, "Seeded Region Growing" 16 : 641-647, 1994

8 Zhang, X, "Object-oriented method for urban mapping using IKONOS imagery" 31 (31): 177-196, 2010

9 Li, R, "Object-oriented classification of high-resolution remote sensing imagery based on an improved colour code and support vector machine" 31 (31): 1453-1470, 2010

10 Wang, Z, "Object-oriented Classification and Application in Land Use Classification Using SPOT-5 PAN imagery" 3158-3160, 2004

11 Stow, D, "Object-based classification of residential Land use within Accra, Ghana based on QuickBird satellite data" 28 (28): 5167-5173, 2007

12 Zhang, Y, "Multi-resolution and multispectral image fusion for urban object extraction" 960-966, 2004

13 Colditz, R, "Influence of image fusion approaches on classification accuracy: A case study" 27 (27): 3311-3335, 2006

14 Zhang, H, "Image Segmentation Evaluation: A survey of Un supervised Methods" 110 : 260-280, 2008

15 Gonzalez, R.C, "Digital image processing" Prientice-Hall 612-615, 2002

16 Ketting, R.L, "Classification of multispectral image data by extraction and classification of homogeneous objects" 14 (14): 19-26, 1976

17 Sapiro, G, "Anisotropic Diffusion of Multivalued Images with Applications to color Filtering" 5 (5): 1582-1585, 1996

18 Chen, Z, "A new process for the segmentation of high resolution remote sensing imagery" 27 (27): 4991-5001, 2006

19 Tomoas, N, "A comparison of urban mapping methods using high resolution digital imagery" 69 (69): 963-972, 2003