• 대한원격탐사학회지
• /
• 제40권2호
• /
• pp.179-190
• /
• 2024

This study aims to compare supervised classification methods with phenology-based approaches, specifically pixel-based and segment-based methods, for accurate crop mapping in agricultural landscapes. We utilized Sentinel-2A imagery, which provides multispectral data for accurate crop mapping. 31 normalized difference vegetation index (NDVI) images were calculated from the Sentinel-2A data. Next, we employed phenology-based approaches to extract valuable information from the NDVI time series. A set of 10 phenology metrics was extracted from the NDVI data. For the supervised classification, we employed the maximum likelihood (MaxLike) algorithm. For the phenology-based approaches, we implemented both pixel-based and segment-based methods. The results indicate that phenology-based approaches outperformed the MaxLike algorithm in regions with frequent rainfall and cloudy conditions. The segment-based phenology approach demonstrated the highest kappa coefficient of 0.85, indicating a high level of agreement with the ground truth data. The pixel-based phenology approach also achieved a commendable kappa coefficient of 0.81, indicating its effectiveness in accurately classifying the crop types. On the other hand, the supervised classification method (MaxLike) yielded a lower kappa coefficient of 0.74. Our study suggests that segment-based phenology mapping is a suitable approach for regions like South Korea, where continuous cloud-free satellite images are scarce. However, establishing precise classification thresholds remains challenging due to the lack of adequately sampled NDVI data. Despite this limitation, the phenology-based approach demonstrates its potential in crop classification, particularly in regions with varying weather patterns.

• 한국군사과학기술학회지
• /
• 제13권1호
• /
• pp.147-155
• /
• 2010

Landcover information of access-denied area was extracted from low-medium and high resolution satellite image. Training for supervised classification was performed to refer visually by landcover map which is made and distributed from The Ministry of Environment. The classification result was compared by relating data of FACC land classification system. As we rasterize digital military map with same pixel size of satellite classification, the accuracy test was performed by image to image method. In vegetation case, ancillary data such as NDVI and image for seasons are going to improve accuracy. FACC code of FDB need to recognize the properties which can be automated.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제9권3호
• /
• pp.301-310
• /
• 2003

본 논문에서는 고해상도 위성영상의 효과적인 분류를 위한 감독분류 시스템을 설계하고 구현하였다. 구현된 시스템은 분류의 정확도 향상을 위한 훈련데이타의 효율적인 선택을 위해서 다양한 인터페이스와 통계자료를 제공한다. 또한, 다양한 위성영상 포맷의 지원과 새로운 감독분류 알고리즘의 확장을 용이하게 하기 위하여 시스템을 모듈화 하였으며, 분광 특성을 고려한 분류의 적용이 가능하다. 분류 알고리즘으로는 평행육면체 분류, 최소거리 분류, 마하라노비스 거리 분류, 최대우도 분류, 퍼지 분류의 감독분류기법을 이용하여 고해상도 위성영상의 처리를 지원한다. 본 시스템의 적용은 고해상도 IKONOS 위성영상을 입력으로 하고, 그 결과를 분석하여 봄으로써 시스템의 응용 가능성을 보여준다.

• 한국측량학회지
• /
• 제38권5호
• /
• pp.435-441
• /
• 2020

Sentinel-2A satellite imagery provides VNIR (Visible Near InfraRed) and SWIR (ShortWave InfraRed) wavelength bands, and it is known to be effective for land cover classification, cloud detection, and environmental monitoring. Greenhouse is one of the middle classification classes for land cover map provided by the Ministry of Environment of the Republic of Korea. Since greenhouse is a class that has a lot of changes due to natural disasters such as storm and flood damage, there is a limit to updating the greenhouse at a rapid cycle in the land cover map. In the present study, we utilized Sentinel-2A satellite images that provide both VNIR and SWIR bands for the detection of greenhouse. To utilize Sentinel-2A satellite images for the detection of greenhouse, we produced high-resolution SWIR bands applying to the fusion technique performed in two stages and carried out the detection of greenhouse using SVM (Support Vector Machine) supervised classification technique. In order to analyze the applicability of SWIR bands to greenhouse detection, comparative evaluation was performed using the detection results applying only VNIR bands. As a results of quantitative and qualitative evaluation, the result of detection by additionally applying SWIR bands was found to be superior to the result of applying only VNIR bands.

• Journal of the Korean Data and Information Science Society
• /
• 제18권3호
• /
• pp.629-636
• /
• 2007

A kernel type semi-supervised estimate is proposed. The proposed estimate is based on the penalized least squares loss and the principle of Gaussian Random Fields Model. As a result, we can estimate the label of new unlabeled data without re-computation of the algorithm that is different from the existing transductive semi-supervised learning. Also our estimate is viewed as a general form of Gaussian Random Fields Model. We give experimental evidence suggesting that our estimate is able to use unlabeled data effectively and yields good classification.

• 전기전자학회논문지
• /
• 제17권3호
• /
• pp.254-259
• /
• 2013

본 논문에서는 준감독 학습 알고리즘(Semi-Supervised Learning Algorithm)의 학습데이터에 필요한 소수의 레이블 데이터를 능동적으로 선택하기 위한 무감독경쟁학습 알고리즘인 VCNN(Vector Centroid Neural Network)을 제안한다. 준감독 학습 알고리즘에서 레이블 데이터의 선택은 학습 결과 큰 영향을 미치고, 레이블 데이터를 선택하는데 있어 많은 비용과 전문적인 지식이 필요하다. 본 논문에서 능동적이고 효율적인 레이블 데이터 선택을 검증하기 위하여 UCI database 와 caltech dataset 을 이용하여 실험한 결과, 기존의 레이블 데이터 선택 방법과 비교하여 안정된 분류 결과와 최소의 오차율을 나타냈다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권9호
• /
• pp.4317-4335
• /
• 2018

Semi-supervised multi-view latent space learning is gaining considerable popularity recently in many machine learning applications due to the high cost and difficulty to obtain the large amount of label information of data. Although some semi-supervised multi-view latent space learning methods have been presented, there is still much space for improvement: 1) How to learn latent discriminant intact feature representations by employing data of multiple views; 2) How to exploit the manifold structure of both labeled and unlabeled point in the learned latent intact space effectively. To address the above issues, we propose an approach called semi-supervised multi-view manifold discriminant intact space learning ($SM^2DIS$) for image classification in this paper. $SM^2DIS$ aims to seek a manifold discriminant intact space for data of different views by making use of both the discriminant information of labeled data and the manifold structure of both labeled and unlabeled data. Experimental results on MNIST, COIL-20, Multi-PIE, and Caltech-101 databases demonstrate the effectiveness and robustness of our proposed approach.

• 한국지역지리학회지
• /
• 제12권4호
• /
• pp.496-507
• /
• 2006

본 연구는 고해상도 자료와 하이퍼스펙트럴 자료를 혼용하여 하와이 화산 국립공원 내 해안 지역의 식생을 분류하고자 하였다. 연구지역에 주로 나타나는 식생은 3종의 초본(broomsedge, natal redtop, and pili)과 작은 관목 등으로 대표되는 비초본으로 구분된다. 분류 기법으로는 unsupervised classification과 supervised classification을 결합한 하이브리드법을 이용하여 전체적으로 3단계 분류과정을 적용하였다. 첫째로는, IKONOS 고해상 위성자료를 이용하여, 식생 및 비식생지역을 unsupervised classification법을 통해 분류하였다. 두 번째로는, minimum noise fraction(MNF) transformation을 이용하여 AVIRIS하이퍼스펙트럴 자료로부터 주성분을 추출하여 자료를 압축하는 과정을 거쳤다. 20미터 해상도를 가진 AVIRIS 픽셀들은 대부분 용암면과 식생면으로부터 반사된 복사신호가 혼합되어 있기때문에, 용암과 식생의 지표피복 비율에 따른 선형모형을 적용하여 용암면이 갖는 반사 신호를 각 픽셀로부터 제거하였다. 최종적으로, 각 픽셀에 대하여, 식생피복 비율에 비례하는 AVIRIS 하이퍼스펙트럴 자료의 식생성분을 토대로 maximum likelihood algorithm에 따라 supervised classification법을 적용하여 초지 및 관목으로 대표되는 지표식생을 분류하였다.

• 대한원격탐사학회지
• /
• 제22권3호
• /
• pp.211-219
• /
• 2006

A random forests classifier is applied to multi-sensor data fusion for supervised land-cover classification in order to account for the importance of variable. The random forests approach is a non-parametric ensemble classifier based on CART-like trees. The distinguished feature is that the importance of variable can be estimated by randomly permuting the variable of interest in all the out-of-bag samples for each classifier. Two different multi-sensor data sets for supervised classification were used to illustrate the applicability of random forests: one with optical and polarimetric SAR data and the other with multi-temporal Radarsat-l and ENVISAT ASAR data sets. From the experimental results, the random forests approach could extract important variables or bands for land-cover discrimination and showed reasonably good performance in terms of classification accuracy.

• 대한원격탐사학회지
• /
• 제20권5호
• /
• pp.315-327
• /
• 2004

Nowadays, interests in land cover classification using not only multi-sensor images but also thematic GIS information are increasing. Often, although useful GIS information for the classification is available, the traditional MLE (maximum likelihood estimation techniques) does not allow us to use the information, due to the fact that it cannot handle the GIS data properly. This paper propose two extended MLE algorithms that can integrate both remote sensing images and GIS thematic data for land-cover classification. They include modified MLE and Bayesian predictive likelihood estimation technique (BPLE) techniques that can handle both categorical GIS thematic data and remote sensing images in an integrated manner. The proposed algorithms were evaluated through supervised land-cover classification with Landsat ETM+ images and an existing land-use map in the Gongju area, Korea. As a result, the proposed method showed considerable improvements in classification accuracy, when compared with other multi-spectral classification techniques. The integration of remote sensing images and the land-use map showed that overall accuracy indicated an improvement in classification accuracy of 10.8% when using MLE, and 9.6% for the BPLE. The case study also showed that the proposed algorithms enable the extraction of the area with land-cover change. In conclusion, land cover classification results produced through the integration of various GIS spatial data and multi-spectral images, will be useful to involve complementary data to make more accurate decisions.