Iterative Trimming Algorithm을 이용하여 자동추출된 KOMPSAT-3A 훈련자료 신뢰성 평가
Reliability Evaluation of KOMPSAT-3A Training Data Automatically Selected Using Iterative Trimming Algorithm
1
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
최근까지 영상분류에서 핵심적인 과정이라 할 수 있는 훈련자료 선정이 주로 수작업에 의존하여 특징적인 지점을 선택하는 방식으로 진행되고 있다. 본 논문에서는 과거에 구축된 공간정보를 바탕으로 Iterative Trimming Algorithm을 이용한 자동화된 훈련자료 추출 기법을 제안하고 활용 가능성에 대해 검정하였다. 2015년에 발표된 세종시 세분류 토지피복지도 정보를 토대로 2018년 KOMPSAT-3A 위성영상 분류를위한 훈련자료를 추출하였으며 이를 이용하여 토지피복 분류를 실시하였다. 이를 위해 토지 유형별 확률분포를 커널밀도추정을 통해 추정하고 확률이 낮은 자료를 이상치로 간주하여 제거하는 방식으로 훈련자료를 선별하였다. 부트스트랩을 통해 산출된 토지유형별 이상치 제거 비율은 토지 유형에 따라 다르게 나타났다. 이상치 제거 비율은 시가화지역의 경우0.08, 농업/초지는 0.16, 산림은 0.04, 나대지는 0.16, 수역은 0.04일 때 가장 높을 분류 정확도를 보였다. 이상치 제거 후 선택된 훈련자료를 이용하여 토지피복 분류를 실시하고 정확도를 검정하였다. 최대우도법 분류에 대한 정확도 검정 결과 전체정확도는 약80%로 나타났고 토지유형별 분류 정확도에는 편차가 있었다. 본 논문을 통해 인위적인 자료수집과정없이 과거에 제작된 GIS 자료를 활용하여 훈련자료를 수집하고 이를 이용하여 고해상도 영상을 분류할수 있다는 것을 확인하였다.
Abstract
Image classification is one of the key issues of remote sensing technology and selecting training data is an essential process in supervised image classification. Dramatically increasing imagery data require more effective and automated classification techniques. The traditional process of selecting training data requires intensive manpower and, as a result, it has been costly and time-consuming. This study proposed an automatic training data extraction technique using outdated geographic information system (GIS) data and its applicability was tested. We used a high-resolution KOMPSAT-3A satellite image taken on July 7, 2018, and the land cover map in 2015 for the test of automated training data extraction based on the iterative trimming algorithm. First, the training data were extracted based on the polygon of the land cover map. Then, the probability distributions of each land cover class were estimated using kernel density estimation. The outliers were removed in the order of low probability. The bootstrap technique was used to determine the ratio of removing outliers. The ratios were different among the land cover classes. The removing ratio was 0.08 for the urbanized area, 0.16 for agriculture/land, 0.04 for forests, 0.16 for bare soil and 0.04 for water. With the refined training data, image classification was conducted. This approach allows automatic extraction of training data based on GIS data without manual digitizing. It is expected to contribute to an automatic and timely update of the urban land cover map with high-resolution imagery.
참고문헌 (14)
- 조기환, "토지피복 공간정보를 활용한 자동 훈련지역 선택 기법", 지적과 국토정보, 48(2), pp.171~183 (2018), 한국국토정보공사[DOI]
- "환경공간정보서비스"[URL]
- Acharya, T. D., "Land cover classification using a KOMPSAT-3A multi-spectral satellite image", Applied Sciences, 6(11), pp.371~ (2016)
- Attarzadeh, R., "Object-based building extraction from high resolution satellite imagery", The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 39, pp.57~60 (2012)
- Cohen, J., "A coefficient of agreement for nominal scales", Educational and Psychological Measurement, 20(1), pp.37~46 (1960)
- Congalton, R. G., "A review of assessing the accuracy of classification of remotely sensed data", Remote Sensing of Environment, 37(1), pp.35~46 (1991)
- Desclee, B., "Forest change detection by statistical object-based method", Remote Sensing of Environment, 102(1-2), pp.1~11 (2006)
- Huang, X., "Automatic labelling and selection of training samples for high-resolution remote sensing image classification over urban areas", Remote Sensing, 7(12), pp.16024~16044 (2015)
- Ko Byoungchul, "Automatic medical image annotation and keyword-based image retrieval using relevance feedback", Journal of Digital Imaging, 25(4), pp.454~465 (2012)
- Liaw, A., "Classification and regression by randomForest", R News, 2(3), pp.18~22 (2002)
- "R: A language and environment for statistical computing" (2017)[URL]
- Radoux, J., "Image-to-map conflict detection using iterative trimming", Photogrammetric Engineering & Remote Sensing, 76(2), pp.173~181 (2010)
- Zhang, L., "Region of interest extraction in remote sensing images by saliency analysis with the normal directional lifting wavelet transformation", Neurocomputing, 179, pp.186~201 (2016)
- Venables, W. N., "Modern Applied Statistics with S" (2002), Springer