• 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.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.519-521
• /
• 2003

Within the paper an approach for the automatic extraction and reconstruction of buildings in urban built-up areas base on fusion of high-resolution satellite image and LIDAR data is presented. The presented data fusion scheme is essentially motivated by the fact that image and range data are quite complementary. Raised urban objects are first segmented from the terrain surface in the LIDAR data by making use of the spectral signature derived from satellite image, afterwards building potential regions are initially detected in a hierarchical scheme. A novel 3D building reconstruction model is also presented based on the assumption that most buildings can be approximately decomposed into polyhedral patches. With the constraints of presented building model, 3D edges are used to generate the hypothesis and follow the verification processes and a subsequent logical processing of the primitive geometric patches leads to 3D reconstruction of buildings with good details of shape. The approach is applied on the test sites and shows a good performance, an evaluation is described as well in the paper.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.399-401
• /
• 2003

This paper presents a geostatistical contextual classifier for the classification of remote sensing data. To obtain accurate spatial/contextual information, a simple indicator kriging algorithm with local means that allows one to estimate the probability of occurrence of certain classes on the basis of surrounding pixel information is applied. To illustrate the proposed scheme, supervised classification of multi-sensor remote sensing data is carried out. Analysis of the results indicates that the proposed method improved the classification accuracy, compared to the method based on the spectral information only.

• Bulletin of the Korean Chemical Society
• /
• 제32권11호
• /
• pp.4005-4010
• /
• 2011

We investigated thermal behavior of spin-coated films of P(HB-co-HHx)/PEG blends by using infraredreflection absorption (IRRAS) spectroscopy and 2D correlation spectroscopy. Based on 2D IRRAS correlation spectra, we could determine the sequence of spectral intensity changes with increasing temperature that PEG band changes first and then a band for crystalline component of P(HB-co-HHx) changes before a band for amorphous component. The intensities of bands for PEG and amorphous P(HB-co-HHx) were changed greatly as PEG weigh % of P(HB-co-HHx)/PEG blends increased. Transition temperatures of P(HB-co-HHx)/PEG blends were successfully determined by 2D gradient mapping method. The transition temperature of spincoated films of 98/2 and 90/10 P(HB-co-HHx)/PEG blends and 80/20 P(HB-co-HHx)/PEG blend determined by 2D gradient map are, respectively, about 137.5 and $132.5^{\circ}C$. Furthermore, P(HB-co-HHx)/PEG blends show an additional transition temperature that have been interpreted in terms of different lamellar thicknesses in spin coated films.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume II
• /
• pp.639-642
• /
• 2006

The intensity-hue-saturation (IHS) technique has become a standard procedure in image analysis. It enhances the colour of highly correlated data. Unfortunately, IHS technique is sensitive to the properties of the analyzed area and usually faces colour distortion problems in the fused process. This paper explores the relationship of colour between before and after the fused process and the change in colour space of images. Subsequently, the fused colours are transformed back into the 'simulative' true colours by the following steps: (1) For each pixel of fused image that match with original pixel (of the coarse spectral resolution image) is transformed back to the true colour of original pixel. (2) The value for interpolating pixels is compensated to preserve the DN ratio between the original pixel and it's vicinity. The 'compensative matrix' is constructed by the DN of fused images and simulation of scaling process. An illustrative example of a Landsat and SPOT fused image also demonstrates the simulative true colour fusion methods.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제32권7호
• /
• pp.674-682
• /
• 2005

본 논문에서는 다중분광 영상의 분류를 위하여 퍼지 G-K(Gustafson- Kessel) 알고리즘과 PCM 알고리즘을 융합한 분류방법을 제안하였다. 제안된 방법은 학습데이타를 이용하여 퍼지 G-K 알고리즘을 수행한 후 그 결과를 이용하여 PCM 알고리즘을 수행한다 PCM 알고리즘과 퍼지 G-K 알고리즘 분류결과를 비교하여 그 결과가 일치하면 해당 항목으로 분류항목을 결정한다. 일치하지 않는 화소는 PCM 알고리즘의 평균내부거리 안쪽에 있는 화소들을 새로운 학습데이타로 하여 베이시안 최대우도 분류를 수행하여 분류항목을 결정한다. 평균내부거리 안쪽에 있는 화소 데이타는 정규분포형태를 보여준다. 다차원 다중분광 영상인 IKONOS와 LANDSAT TM 위성영상을 이용하여 제안된 알고리즘의 효율성을 검증한 결과 퍼지 G-K 알고리즘과 PCM 알고리즘 그리고 전통적인 분류 방법인 최대우도 분류 알고리즘보다 전체 정확도가 더 높은 결과를 얻을 수 있었다

• 대한원격탐사학회지
• /
• 제36권6_2호
• /
• pp.1523-1535
• /
• 2020

원격탐사를 이용한 작황정보 생산은 작물의 생물계절을 이용하여 작물 분류, 생육 모니터링, 생산량 추정 분석이 선행되어야 한다. 생물계절에 추정을 위한 시계열 영상 자료가 필요하지만 KOMPSAT(Korea Multi-Purpose Satellite)만으로 획득하는 것은 물리적 제한이 있으므로 타 지구관측위성과의 융합 활용이 필요하다. 위성자료의 융합 활용을 위해서는 각 위성이 가지는 고유의 방사학적 센서 특성 차이를 극복해야 한다. 본 연구는 위성자료의 융·복합 활용을 위한 첫 단계로서 KOMPSAT-3와 Landsat-8 위성의 교차검보정을 수행하였다. Libya-4 PICS(Pseudo Invariant Calibration Sites)에서 2년간 수집된 위성자료에 대해 초분광위성을 이용하여 산정된 SBAF(Spectral Band Adjustment Factor)를 적용하여 대기상단 반사도를 비교하였다. 교차검보정 결과 KOMPSAT-3와 Landsat-8 위성은 Blue, Green, Red 밴드에서 약 4%, NIR밴드에서 6%의 반사율 차이를 보였다. 온보드 켈리브레이터가 없는 KOMPSAT-3는 Ladnsat-8에 비해 Radiometric Stability가 낮은 것으로 나타났다. 향후 교차검보정의 정확도를 높이기 위해 BRDF(Bidirectional reflectance distribution function) 보정 및 지형보정을 통하여 정규화 된 반사율 자료를 생산하기 위한 노력이 필요하다.

• 대한원격탐사학회지
• /
• 제23권2호
• /
• pp.103-111
• /
• 2007

지금까지 위성영상 정보 처리 분야에서는 분광정보를 이용한 영상분석과 시각적 해석 및 자동 분류에 대한 연구가 주로 수행되었으나, 최근에는 영상자료에서 시각적으로 나타나지 않는 특성이나 공간정보의 추출을 위한 여러 시도가 이루어지고 있다. 본 연구에서는 영상정보의 특성 추출기법인 텍스처 영상 생성기법과 웨이브릿 변환을 연계하여 웨이브릿 기반 텍스처 융합 영상에 대한 연구를 수행하였다. 또한 이러한 영상이 분류 정확도에 어떻게 기여하는 가를 분석하기 위한 적용 사례로 도심지 공간분석과 칼데라 주변지역의 지질학적 구조분석을 수행하였다 영상 분석 시 공간정보 활용을 위한 텍스처 영상 생성기법과 웨이브릿 기반 텍스처 융합 영상 생성기법을 사용하면 원본영상만을 사용하였을 때보다 높은 분류정확도를 보였다. 고해상도 영상을 사용한 도심지의 경우 원본영상에 텍스처영상과 웨이브릿 기반 텍스처 융합 영상을 모두 활용한 경우의 분류정확도가 가장 높은 값을 보였다. 이는 상세화소의 변화가 매우 중요한 도심지의 특성상, 세밀한 공간정보가 최대로 활용되었기 때문으로 해석되어진다. 또한 중 저해상도 영상을 사용한 지질학적 구조분석의 경우 원본영상에 텍스처 영상만을 활용한 경우가 가장 높은 분류정확도를 보였다. 이는 칼데라를 중심으로 한 비교적 크기가 큰 지질학적 구조 분석 시 고도변화와 지열분포 등의 정보가 적당히 단순화 될 필요가 있었기 때문인 것으로 해석된다. 따라서 이러한 기법들을 실제 연구에 적용하기 위해서는 연구의 목적과 위성영상의 해상도 등의 정보를 모두 고려하여 적절한 기법을 잘 적용하는 것이 중요하다.

• Journal of Information Processing Systems
• /
• 제12권2호
• /
• pp.295-309
• /
• 2016

Spectrum sensing is an essential function that enables cognitive radio technology to explore spectral holes and resourcefully access them without any harmful interference to the licenses user. Spectrum sensing done by a single node is highly affected by fading and shadowing. Thus, to overcome this, cooperative spectrum sensing was introduced. Currently, the advancements in multiple antennas have given a new dimension to cognitive radio research. In this paper, we propose a multiple energy detector for cooperative spectrum sensing schemes based on the evidence theory. Also, we propose a reporting mechanism for multiple energy detectors. With our proposed system, we show that a multiple energy detector using a cooperative spectrum sensing scheme based on evidence theory increases the reliability of the system, which ultimately increases the spectrum sensing and reduces the reporting time. Also in simulation results, we show the probability of error for the proposed system. Our simulation results show that our proposed system outperforms the conventional energy detector system.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2002년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.65-65
• /
• 2002

In remote sensing, images are acquired over the same area by sensors of different spectral ranges (from the visible to the microwave) and/or with different number, position, and width of spectral bands. These images are generally partially redundant, as they represent the same scene, and partially complementary. For many applications of image classification, the information provided by a single sensor is often incomplete or imprecise resulting in misclassification. Fusion with redundant data can draw more consistent inferences for the interpretation of the scene, and can then improve classification accuracy. The common approach to the classification of multisensor data as a data fusion scheme at pixel level is to concatenate the data into one vector as if they were measurements from a single sensor. The multiband data acquired by a single multispectral sensor or by two or more different sensors are not completely independent, and a certain degree of informative overlap may exist between the observation spaces of the different bands. This dependence may make the data less informative and should be properly modeled in the analysis so that its effect can be eliminated. For modeling and eliminating the effect of such dependence, this study employs a strategy using self and conditional information variation measures. The self information variation reflects the self certainty of the individual bands, while the conditional information variation reflects the degree of dependence of the different bands. One data set might be very less reliable than others in the analysis and even exacerbate the classification results. The unreliable data set should be excluded in the analysis. To account for this, the self information variation is utilized to measure the degrees of reliability. The team of positively dependent bands can gather more information jointly than the team of independent ones. But, when bands are negatively dependent, the combined analysis of these bands may give worse information. Using the conditional information variation measure, the multiband data are split into two or more subsets according the dependence between the bands. Each subsets are classified separately, and a data fusion scheme at decision level is applied to integrate the individual classification results. In this study. a two-level algorithm using hierarchical clustering procedure is used for unsupervised image classification. Hierarchical clustering algorithm is based on similarity measures between all pairs of candidates being considered for merging. In the first level, the image is partitioned as any number of regions which are sets of spatially contiguous pixels so that no union of adjacent regions is statistically uniform. The regions resulted from the low level are clustered into a parsimonious number of groups according to their statistical characteristics. The algorithm has been applied to satellite multispectral data and airbone SAR data.