• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2008년도 International Symposium on Remote Sensing
• /
• pp.111-114
• /
• 2008

The existence of noise bands may deform the typical shape of the spectrum, making the accuracy of clustering degraded. This paper proposes a statistical approach to remove noise bands in hyperspectral data using the correlation coefficient of bands as an indicator. Considering each band as a random variable, two adjacent signal bands in hyperspectral data are highly correlative. On the contrary, existence of a noise band will produce a low correlation. For clustering, the unsupervised ${\kappa}$-nearest neighbor clustering method is implemented in accordance with three well-accepted spectral matching measures, namely ED, SAM and SID. Furthermore, this paper proposes a hierarchical scheme of combining those measures. Finally, a separability assessment based on the between-class and the within-class scatter matrices is followed to evaluate the applicability of the proposed noise band removal method. Also, the paper brings out a comparison for spectral matching measures.

• 한국광학회:학술대회논문집
• /
• 한국광학회 2008년도 동계학술발표회 논문집
• /
• pp.71-72
• /
• 2008

과학기술위성3호 부탑재체로 영상분광기(COMIS, Compact Hyperspectral Imager)가 선정되어 2007년 5월부터 개발이 진행되고 있다. COMIS는 2010년 과학기술위성3호에 탑재 발사되어, 위성 궤도 700km 상공에서 해상도 30m을 가지고, 30km 폭의 지표면 또는 대기를 관측할 수 있다. 현재까지 국내에서 개발된 위성탑재 지구관측카메라가 흑백이거나 다분광(3파장)으로 지구관측을 하는 것에 반하여 COMIS는 가시광 및 근적외선 영역에서 16${\sim}$62대역(4${\sim}$15nm 파장 분해능)의 초분광 관측을 수행하게 된다. 초분광 영상은 관측 대상 물성의 상세 구분이 가능한 관계로 군사적 활용을 포함한 원격 탐사의 주요 활용 분야로 대두되고 있다. 본 논문은 과학기술위성3호 부탑재체로 개발되는 영상분광기인 COMIS(Compact Hyperspectral Imager)의 전반적인 개념, 활용 과학을 먼저 소개하고 상세 광학 설계를 발표한다.

• 제어로봇시스템학회논문지
• /
• 제19권12호
• /
• pp.1081-1088
• /
• 2013

Hyperspectral cameras acquire reflectance values at many different wavelength bands. Dimensions tend to increase because spectral information is stored in each pixel. Several attempts have been made to reduce dimensional problems such as the feature selection using Adaboost and dimension reduction using the Simulated Annealing technique. We propose a novel material detection method that consists of four steps: feature band selection, feature extraction, SVM (Support Vector Machine) learning, and target and specific region detection. It is a combination of the band ratio method and Simulated Annealing algorithm based on detection rate. The experimental results validate the effectiveness of the proposed feature selection and band ratio method.

• 한국군사과학기술학회지
• /
• 제14권6호
• /
• pp.1073-1080
• /
• 2011

In this study, a target detection algorithm was proposed for using hyperspectral imagery. The proposed algorithm is designed to have minimal processing time, low false alarm rate, and flexible threshold selection. The target detection procedure can be divided into two steps. Initially, candidates of target pixel are extracted using matching ratio of spectral pattern that can be calculated by spectral derivation. Secondly, spectral distance is computed only for those candidates using Euclidean distance. The proposed two-step method showed lower false alarm rate than the Euclidean distance detector applied over the whole image. It also showed much lower processing time as compared to the Mahalanobis distance detector.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.1194-1196
• /
• 2003

Variations in soil physical and chemical properties can affect agricultural productivity and the environmental implications of crop production. These variations are present and may be important at regional, field, and sub-field (precision agriculture) scales. Because traditional measurements are time-consuming and expensive, reflectance-based estimates of soil properties such as texture, organic matter content, water content, and nutrient status are attractive. Soil properties have been related to reflectance measured with laboratory, in-field, airborne, and satellite sensors. Both multispectral and hyperspectral instruments have been used, with both natural and artificial illumination. Varying levels of accuracy have been obtained, with the best results (r > 0.95) using hyperspectral reflectance data to estimate soil organic matter and water content.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.1049-1051
• /
• 2003

This study investigated the use of airborne image data to provide estimates of within -field variability in soil properties and crop growth as an alternative to extensive field data collection. Hyperspectral and multispectral images were acquired in 2000, 2001, and 2002 for central Missouri experimental fields. Data were converted to reflectance using chemically-treated reference tarps with known reflectance levels. Geometric distortion of the hyperspectral pushbroom sensor images was corrected with a rubber sheeting transformation. Statistical analyses were used to relate image data to field-measured soil properties and crop characteristics. Results showed that this approach has potential; however, it is important to address a number of implementation issues to insure quality data and accurate interpretations.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.1470-1472
• /
• 2003

Hyperion, as hyperspectral data, is carried on NASA’s EO-1 satellite, can be used in more subtle discrimination on forest cover, with 224 band in 360 ?2580 nm (10nm interval). In this study, Hyperion image is used to investigate the effects of topography on the classification of forest cover, and to assess whether the topographic correction improves the discrimination of species units for practical forest mapping. A publicly available Digital Elevation Model (DEM), at a scale of 1:25,000, is used to model the radiance variation on forest, considering MSR(Mean Spectral Ratio) on antithesis aspects. Hyperion, as hyperspectral data, is corrected on a pixel-by-pixel basis to normalize the scene to a uniform solar illumination and viewing geometry. As a result, the approach on topographic effect normalization in hyperspectral data can effectively reduce the variation in detected radiance due to changes in forest illumination, progress the classification of forest cover.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.732-734
• /
• 2003

In the middle -resolution remote sensing, the Ground Sampled Distance(GSD) sensed and sampled by the detector is generally larger than the size of objects(or materials) of interest, in which case several objects are embedded in a single pixel and cannot be detected spatially. This study is intended to solve this problem of a hyperspectral data with high spectral resolution. We examined the detection algorithm, Linear Spectral Mixing Model, and also made a test on the Hyperion data. To find class Endmembers, we applied two methods, Spectral Library and Geometric Model, and compared them with each other.

• 항공우주기술
• /
• 제7권1호
• /
• pp.216-222
• /
• 2008

본 연구에서는 초분광 원격탐사 기법을 이용하여 선박의 접근이 어려운 연안지역의 수심을 산정하고자 한다. 연구에 사용된 영상은 초분광 위성영상인 EO-1 Hyperion 영상이며, 대기보정 및 기하보정을 실시하였다. 보정된 영상은 MNF 변환을 사용하여 밴드를 압축하였다. 또한 각 화소의 실제적인 수심을 산정하기 위하여 대상지역의 Diffuse Attenuation Coefficient를 영상내에서 결정하였다. 그리고 Linear Spectral Unmixing 기법을 사용하여 대상 화소의 Emdmember를 결정하고, 수심을 산정하였다.

• 대한원격탐사학회지
• /
• 제26권6호
• /
• pp.693-703
• /
• 2010

High spectral resolution of hyperspectral data enables analysis of complex natural phenomena that is reflected on the data nonlinearly. Although many manifold learning methods have been developed for such problems, most methods do not consider the spatial correlation between samples that is inherent and useful in remote sensing data. We propose a manifold learning method which directly combines the spatial proximity and the spectral similarity through kernel PCA framework. A gain factor caused by spatial proximity is first modelled with a heat kernel, and is added to the original similarity computed from the spectral values of a pair of samples. Parameters are tuned with intelligent grid search (IGS) method for the derived manifold coordinates to achieve optimal classification accuracies. Of particular interest is its performance with small training size, because labelled samples are usually scarce due to its high acquisition cost. The proposed spatial kernel PCA (KPCA) is compared with PCA in terms of classification accuracy with the nearest-neighbourhood classification method.