ICT 발전트렌드에 대응하는 공간정보의 환경이슈 적용 체계 구축 : 빅데이터 분석과 위성영상 활용을 중심으로

이명진 ( Moung-jin Lee ),이정호 ( Jeongho Lee ),윤정호,심창섭,김근한,채성호,이선민 한국환경연구원 2017 기본연구보고서 Vol.2017 No.-

This study aims to conduct a case study of best practices overseas and a pilot study to deal with major environmental issues in Korea through integration of ICT that has recently become a major issue, focusing on satellite images among various kinds of environmental spatial information. The study analyzed the case in which satellite images were most frequently used in all of environmental spatial information based on the study results made in the previous year. In addition, it analyzed the characteristics of satellite images in Korea and overseas, and examined the cases in which they were used in the field of environment. Furthermore, an applicable technology roadmap was drawn up to apply the case in which satellite images and ICT are integrated ― detecting drought by analyzing the variation of soil moisture ― to Korea, and a pilot study was conducted on the basis of the roadmap in Jeonbuk. There is more and more use of satellite images as an actual tool to resolve various environmental issues as shown in the previous year’s research findings. Thus, to cope with environmental problems through precise earth observation, South Korea will manage at least 8 satellites by 2020. Considering the technical characteristics of the research topic which is integration and use of environmental spatial information of satellite images and ICT, this study comparatively analyzed satellite images classified into earth observation satellites, meteorological/ocean/environmental satellites, and geostationary environmental satellites. In addition, it studied cases in which multi-sensor satellite images are used, especially verifiable projects from overseas about integration and use of satellite images and ICT. Moreover, multifaceted analysis was attempted to empirically review measures against environmental issues through integration and use of environmental spatial information of multi-sensor satellite images and ICT by conducting a detailed analysis by period and field in order to determine which satellite images in particular are mainly used in Korea, using text mining among big data analysis. Based on this analysis, a technology roadmap was drawn up, which is the technical system of integration and use of satellite images and ICT in the actual case of soil moisture. A pilot study was conducted to select the study area for actual implementation of the technology roadmap. Then a method was implemented to analyze and use the data required for observation and verification using satellite images based on ICT. In addition, an application plan was presented based on restructuring of integration and use of ICT and satellite images developed later. The characteristics of local and global satellite images were analyzed and summarized, which can be utilized in the current and future environment field. Data of local and global satellites were also investigated and summarized by classifying them into earth observation satellites (Arirang series, Landsat series), meteorological/ocean/environmental satellites (Chollian series, etc.), and geostationary environmental satellites (TEMPO, Chollian-2B GEMS, etc.). In the case study of using multi-sensor satellite images, total 55 literatures were examined, which used domestic earth observation satellites (Arirang series), meteorological/ ocean/ environmental satellites (Chollian series), and environmental thematic maps. Total 15 cases including hydrologic disasters were examined in the case of using domestic earth observation satellites, total 18 cases including studies on soil moisture were examined in the case of using domestic meteorological/ocean/environmental satellites, and total 22 cases including selection of soil erosion factor were used in the case of using environmental thematic maps. These 55 cases were analyzed in 6 fields: disaster, agriculture, forest, ocean, water quality and climate. As a result of analyzing cases of Korea’s leading satellites Arirang and Chollian as well as environmental thematic maps, about 50% of 55 cases were directly or indirectly related to soil moisture. More specifically, direct or indirect correlation with soil moisture was found in 9 out of 14 cases in the disaster category, 7 out of 7 cases in the agriculture category, 3 out of 8 in the forest category, 1 out of 3 in the ocean category, 5 out of 17 in the water quality category, and 1 out of 6 in the climate category. This showed that research on soil moisture is adequate for research on integration and use of domestic satellites and thematic maps in the field of environment. Based on the above, a case study was conducted on the integration and use of soil moisture-related satellite images and ICT. The advanced cases about integration and use of satellite images and ICT included ‘AfSIS project’, ‘WEAM4i project’, and ‘ERMES project’. This study examined and summarized which technical role is performed by satellite images and ICT in the environmental issues of soil moisture for each case. In analyzing the integration and use of multi-sensor satellite images using big data, the text mining method was used, which is a method of analyzing unstructured data and natural language among various methods of big data analysis. This was conducted in a network analysis through the self-developed text mining program based on the R program developed in the previous year. A detailed analysis was conducted for each time and field regarding which satellite images are mainly used in Korea. In addition, the theoretical background of the integration and use of multi-sensor satellite images was analyzed. This was categorized into spatial resolution, spectral resolution and temporal resolution to present integration method. Based on the above, central spectral wavelength range, and spatial resolution were elicited, which form the basis of integration and use of multi-sensor satellite images in the field of environment. It is necessary to integrate and use the earth observation satellites with good spatial resolution and meteorological/ocean/environmental satellites with good temporal resolution as a integration and utilization of multi-sensor satellite images. In particular, it is necessary to use earth observation satellites that can be ingegrated in 300-500 nm wavelength band provided by Chollian 2B. In restructuring the use of environmental spatial information focusing on satellite images that applied ICT, a measure to resolve actual environmental issues of soil moisture was presented based on the aforementioned plan of integration and use. To this end, a technology roadmap was drawn up to establish the application and utilization scheme of satellite images on soil moisture and ICT, which is intended to apply global advanced projects related to soil moisture (integration of satellite images and ICT) in Korea. More specifically, a technological system is established and presented to apply the integration and use of soil moisture-related satellite images and ICT from overseas verifiable projects in Korea through the following steps: 1) acquiring soil moisture data using satellite images, 2) linking external data by establishing the ICT platform, and 3) providing analysis and utilization services. A pilot study was conducted by selecting an actual study area for demonstration in order to implement the method to analyze and use the data by linking ICT-based external data and observing local soil moisture among the content of technology roadmap. Finally, this study restructured the plan to integrate environmental spatial information focused on satellite images with ICT to resolve environmental issues of soil moisture into a soil moisture time-space monitoring system. The system to apply to environmental issues using soil moisture satellite images and ICT need soil moisture data and climate/air observation data derived from multi-sensor satellite images of earth and environmental observation satellites, as well as in-situ data on soil moisture and related thematic maps. The available environmental spatial information are produced and managed by Korea Aerospace Research Institute, National Environmental Satellite Center, Korea Meteorological Administration, Rural Development Administration, and KEI. Based on this data, ICT such as ‘big data platform,’ ‘artificial intelligence cognitive computing,’ ‘cloud computing,’ ‘IoT (Internet of Things),’ and ‘5G wired and wireless network’ can be used to predict agricultural production, forecast drought damages, provide customized services for consumers such as farming data, and support policy decision making. Review of policy suggestions was carried out in four views. The first is the need to renew and upgrade the environmental thematic maps (content and cycle). The most fundamental element of the environmental thematic map is land cover map, which is made based on satellite images and aerial photographs. In other words, to renew and upgrade the land cover maps as well as environmental thematic maps, it is necessary to integrate basic data focusing on satellite images and latest ICT in the right place. This can be actively used as the basic data to create new industrial values for the general public based on quaternary industries. Thus, it is necessary to actively invest in technological development and conduct research to renew land cover maps and related environmental thematic maps. The second is the need to reestablish the systematic status of satellite images. In the current legal-systematic regulations related to satellite images in Korea, satellite images are a type of satellite information (including communications, sound and voice), without providing their purpose of creating information and distinguishing or defining satellite information according to their use. Information from satellite images in the form of remote sensing can be used as spatial information in various issues of national life, such as environment, climate, land management, transportation, disaster and climate change. integration of data among multi-sensor remote sensing satellites and integration among different fields can be relatively easy, and demands for this is expected to grow in the future. In other words, there is a need for a new system regarding management and use of remote sensing satellite information. The third is the need to expand accessibility to satellite image data. To actualize the potential for policy application with the use of satellite images as well as integration with other fields like ICT, it is necessary to gradually ease the current access control of satellite information. Provisions about information security in laws and systems related to satellite image data must be amended. In addition, security regulations related to satellite images managed by government departments and affiliated agencies related to information security and military security must also be improved immediately, with focus on alleviating access to information. The fourth is the need to increase participation of private enterprises supporting the implementation of the new government policies. The major strategy in the 100 major government projects by the new government is creating jobs, and development of processing software, which is the essence of remote sensing satellite information service, can be acknowledged as the key technology of new future growth engine. Furthermore, not large companies but small and medium-sized enterprises (SMEs) or startups can focus on this business in terms of market size. Therefore, it is important to nurture service startups or specialized SMEs in the fields of remote sensing, ICT and integration and use of these fields as a major part of governance in the new government. It is also necessary to politically encourage the participation of private enterprises instead of having the government or a national institution lead the entire project from data processing and distribution after producing raw satellite images.

The Effect of Wavelet Pair Choice in the Compression of the Satellite Images

진홍성,한동엽 한국지구과학회 2011 한국지구과학회지 Vol.32 No.6

The effect of wavelet pair choice in the compression of the satellite images is studied. There is a trade-off between compression rate and perception quality. The encoding ratio is used to express the compression rate, and Peak Signal-to-Noise Ratio (PSNR) is also used for the perceptional performance. The PSNR and the encoding ratio are not matched well for the images with various wavelet pairs, but the tendency is remarkable. It is hard to find the pattern of PSNR for sampled images. On the other hand, there is a pattern of the variation range of the encoding ratio for each image. The satellite images have larger values of the encoding ratio than those of nature images (close range images). Depending on the wavelet pairs, the PSNR and the encoding ratio vary as much as 13.2 to 21.6% and 16.8 to 45.5%,respectively for each image. For Synthetic Aperture Radar (SAR) images the encoding ratio varies from 16 to 20% while for the nature images it varies more than 40% depending on the choice of wavelet pairs. The choice of wavelet for the compression affects the nature images more than the satellite images. With the indices such as the PSNR and the encoding ratio, the satellite images are less sensitive to the choice of wavelet pairs. A new index, energy concentration ratio (ECR) is proposed to investigate the effect of wavelet choice on the satellite image compression. It also shows that the satellite images are less sensitive than the nature images. Nevertheless, the effect of wavelet choice on the satellite image compression varies at least 10% for all three kinds of indices. However, the important of choice of wavelet pairs cannot be ignored.

비접근 지역에 대한 SPOT 위성영상의 Pseudo영상 구성 및 센서모델 분석

방기인 ( Ki In Bang ),조우석 ( Woo Sug Cho ) 대한원격탐사학회 2001 대한원격탐사학회지 Vol.17 No.1

The paper presents several satellite sensor models and satellite image decomposition methods for inaccessible area where ground control points can hardly acquired in conventional ways. First, 10 different satellite sensor models, which were extended from collinearity condition equations, were developed and then the behavior of each sensor model was investigated. Secondly, satellite images were decomposed and also pseudo images were generated. The satellite sensor model extended from collinearity equations was represented by the six exterior orientation parameters in 1st, 2nd and 3rd order function of satellite image row. Among them, the rotational angle parameters such as ω(omega) and φ(phi) correlated highly with positional parameters could be assigned to constant values. For inaccessible area, satellite images were decomposed, which means that two consecutive images were combined as one image. The combined image consists of one satellite image with ground control points and the other without ground control points. In addition, a pseudo image which is an imaginary image, was prepared from one satellite image with ground control points and the other without ground control points. In other words, the pseudo image is an arbitrary image bridging two consecutive images. For the experiments, SPOT satellite images exposed to the similar area in different pass were used. Conclusively, it was found that 10 different satellite sensor models and 5 different decomposed methods delivered different levels of accuracy. Among them, the satellite camera model with 1st order function of image row for positional orientation parameters and rotational angle parameter of kappa, and constant rotational angle parameter omega and phi provided the best 60m maximum error at check point with pseudo images arrangement.

Generation of Super-Resolution Images from Satellite Images Based on Improved RCAN

Futa Morishima,Huimin Lu,Tohru Kamiya 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11

Satellite images can be analyzed and used for a variety of purposes. In the future, satellite image analysis will become more important since the number of satellites launches, and the amount of satellite data increase every year. Under these circumstances, there are some problems to be solved. One is the existence of low-resolution satellite images. To analyze the lower resolution of satellite images there are some technical issues such as reduction of noise, misclassification of object recognition. Therefore, high-resolution images are necessary. However, high-resolution satellite images are expensive, and its images may not be available in the past satellite images. Super-resolution which is introduced in image processing is a method to solve these problems. Convolutional neural network (CNN)-based methods are effective, and there is a need for models that can perform super-resolution with higher accuracy. In this paper, we propose a method for super-resolving satellite images, based on the improved the RCAN (residual channel attention network) model with SRM (style-based recalibration module). The proposed method improves the PSNR (peak signal to noise ratio) by 0.0181 dB compared to the conventional RCAN model.

특징점 매칭 개선 및 강인추정을 통한 이종해상도 위성영상 자동영상정합

반승환,김태정,Ban, Seunghwan,Kim, Taejung 대한원격탐사학회 2022 대한원격탐사학회지 Vol.38 No.6

Recently, many Earth observation optical satellites have been developed, as their demands were increasing. Therefore, a rapid preprocessing of satellites became one of the most important problem for an active utilization of satellite images. Satellite image matching is a technique in which two images are transformed and represented in one specific coordinate system. This technique is used for aligning different bands or correcting of relative positions error between two satellite images. In this paper, we propose an automatic image matching method among satellite images with different ground sampling distances (GSDs). Our method is based on improved feature matching and robust estimation of transformation between satellite images. The proposed method consists of five processes: calculation of overlapping area, improved feature detection, feature matching, robust estimation of transformation, and image resampling. For feature detection, we extract overlapping areas and resample them to equalize their GSDs. For feature matching, we used Oriented FAST and rotated BRIEF (ORB) to improve matching performance. We performed image registration experiments with images KOMPSAT-3A and RapidEye. The performance verification of the proposed method was checked in qualitative and quantitative methods. The reprojection errors of image matching were in the range of 1.277 to 1.608 pixels accuracy with respect to the GSD of RapidEye images. Finally, we confirmed the possibility of satellite image matching with heterogeneous GSDs through the proposed method.

위성영상 이미지를 활용한 연구 동향 및 데이터셋 리뷰

김세형,강주영,채정우 (사)한국스마트미디어학회 2022 스마트미디어저널 Vol.11 No.1

Like other computer vision research trends, research using satellite images was able to achieve rapid growth with the development of GPU-based computer computing capabilities and deep learning methodologies related to image processing. As a result, satellite images are being used in various fields, and the number of studies on how to use satellite images is increasing. Therefore, in this paper, we will introduce the field of research and utilization of satellite images and datasets that can be used for research using satellite images. First, studies using satellite images were collected and classified according to the research method. It was largely classified into a Regression-based Approach and a Classification-based Approach, and the papers used by other methods were summarized. Next, the datasets used in studies using satellite images were summarized. This study proposes information on datasets and methods of use in research. In addition, it introduces how to organize and utilize domestic satellite image datasets that were recently opened by AI hub. In addition, I would like to briefly examine the limitations of satellite image-related research and future trends. 기존 컴퓨터 비전의 연구 동향과 마찬가지로, 위성영상을 이용한 연구도 GPU 기반의 컴퓨터 연산능력과 이미지 처리와 관련된 딥러닝 방법론의 발전으로 많이 이루어지고 있다. 그로 인해 다양한 분야에 위성영상이 활용되고 있고, 위성 영상을 활용에 관한 연구도 증가하고 있다. 본 연구에서는 위성영상의 연구 활용 분야와 위성영상을 활용한 연구에 이용할 수 있는 데이터셋에 대해 소개하도록 한다. 먼저, 위성영상을 활용한 연구를 수집하여 연구 방법에 따라 분류하였다. 크게 분류 기반 연구와 회귀 기반 연구로 분류하였고, 그 이외의 방법으로 활용한 논문들을 정리하였다. 다음으로 위성영상을 활용한 연구들에서 이용한 데이터셋을 정리하였다. 본 연구에서는 데이터셋의 정보와 연구에서의 활용 방법에 대해 제안한다. 이와 함께 최근 AI hub에서 개방한 국내 위성영상 데이터셋의 정리와 활용 방안에 대해 소개한다. 마지막으로, 위성 이미지 관련 연구의 한계점과 앞으로의 동향을 간략하게 제시하였다.

Vector Quantization Method Based on Satellite Cloud Image

Xumin Liu,Zilong Duan,Xue Yang,Weixiang Xu 보안공학연구지원센터 2015 International Journal of Signal Processing, Image Vol.8 No.11

Automatic vectorization in the field of image processing and recognition is one of development direction. This paper does some relevant researches on satellite cloud image preprocessing, image segmentation, image vector quantization. To improve the effect of noise reduction and preserving image details, this paper puts forward an improved adaptive median filter algorithm; For increasing the speed of image segmentation, this paper puts forward automatic layering algorithm combined with color information. Finally, this paper puts forward automatic vector quantization algorithm based on satellite cloud images and we developed an automatic vector quantization prototype system of satellite cloud images. The research results suggest that our automatic vector quantization algorithm has satellite cloud information automatic extraction function, identification function and vector quantization function.

고해상도 영상에서 기준점 개수에 따른 정확도 평가에 관한 연구

최현,김기홍,박홍기 한국산업융합학회 2018 한국산업융합학회 논문집 Vol.21 No.6

The high-resolution satellite images provided by Kompsat-3A, a multipurpose satellite, have various applications such as digital map generation, 3D image generation, and DEM generation. In order to utilize high-resolution satellite images, the user must create an orthoimage in order to use the image in a suitable manner. The position and the number of the ground reference points affect the accuracy of the orthoimage. In particular, the Kompsat-3A satellite image has a high resolution of about 0.5m, so the difficulty in selecting the ground control points and the accuracy of the selected point will have a great influence on the subsequent application process. Therefore, in this study, we analyzed the influence of the number of ground reference points on the accuracy of the terrestrial satellite images. The high-resolution satellite images provided by Kompsat-3A, a multipurpose satellite, have various applications such as digital map generation, 3D image generation, and DEM generation. In order to utilize high-resolution satellite images, the user must create an orthoimage in order to use the image in a suitable manner. The position and the number of the ground reference points affect the accuracy of the orthoimage. In particular, the Kompsat-3A satellite image has a high resolution of about 0.5m, so the difficulty in selecting the ground control points and the accuracy of the selected point will have a great influence on the subsequent application process. Therefore, in this study, we analyzed the influence of the number of ground reference points on the accuracy of the terrestrial satellite images.

고해상도 위성 영상자료 표준화 동향

이동한(Lee Dong-Han),서두천(Seo Doo-Chun),임효숙(Lim Hyo-Suk) 한국항공우주연구원 2008 항공우주산업기술동향 Vol.6 No.2

본 논문에서는, 위성 영상자료 표준화에 대한 정의 및 표준화에 따른 일반 사용자들의 요구사항들을 설명한다. 위성을 개발하고 운영하더라도 일반 사용자가 사용하지 않는다면 그 위성은 무용지물일 수밖에 없다. 일반 사용자가 위성 영상자료를 원활하게 사용하기 위해서는 위성 영상자료에 대한 표준화가 이루어져야하고 한국항공우주연구원은 아리랑 위성의 개발 기관으로서 위성 영상자료의 표준화를 완수해야한다. 위성 영상자료의 표준화를 위해서는 위성 개발 요구사항, 국제 영상자료 표준화, 일반 사용자 요구사항들을 반영해야 하고, 일반 사용자들에게 제공되는 영상자료도 표준 형식을 수용해야한다. 또한 위성 영상자료 품질을 확보하기 위한 검보정 작업이 필수적으로 수행되어야 한다. 한국항공우주연구원은 이미 운영 중인 아리랑 위성 2호를 포함하여 다목적실용위성 5호와 3호의 표준화를 위한 작업을 단계별로 수행 중이다. In this paper, the definition and the requirement from Users of standardization of high resolution satellite image data will be presented. If Users do not use the satellite image data, the satellite will be useless thing though it has been developed and operated now. The standardization of the satellite image data will make Users use the image data with no problem, so KARI has to do the standardization of it as a space agency that has developed and operated the satellite. For the standardization of it, the technical requirement to develop the satellite, the international standardization for the satellite image data and the requirement from Users will be reflected into the satellite development, and then the format and content of the satellite image data to Users have to be accommodated with the standard format of it. In addition to it, the calibration and validation just make sure of the quality of the satellite image data. For this, KARI has just been doing the standardization of KOMPSAT series in stages.

다중센서 고해상도 위성영상의 딥러닝 기반 영상매칭을 위한 학습자료 구성에 관한 연구

강원빈,정민영,김용일,Kang, Wonbin,Jung, Minyoung,Kim, Yongil 대한원격탐사학회 2022 대한원격탐사학회지 Vol.38 No.6

Image matching is a crucial preprocessing step for effective utilization of multi-temporal and multi-sensor very high resolution (VHR) satellite images. Deep learning (DL) method which is attracting widespread interest has proven to be an efficient approach to measure the similarity between image pairs in quick and accurate manner by extracting complex and detailed features from satellite images. However, Image matching of VHR satellite images remains challenging due to limitations of DL models in which the results are depending on the quantity and quality of training dataset, as well as the difficulty of creating training dataset with VHR satellite images. Therefore, this study examines the feasibility of DL-based method in matching pair extraction which is the most time-consuming process during image registration. This paper also aims to analyze factors that affect the accuracy based on the configuration of training dataset, when developing training dataset from existing multi-sensor VHR image database with bias for DL-based image matching. For this purpose, the generated training dataset were composed of correct matching pairs and incorrect matching pairs by assigning true and false labels to image pairs extracted using a grid-based Scale Invariant Feature Transform (SIFT) algorithm for a total of 12 multi-temporal and multi-sensor VHR images. The Siamese convolutional neural network (SCNN), proposed for matching pair extraction on constructed training dataset, proceeds with model learning and measures similarities by passing two images in parallel to the two identical convolutional neural network structures. The results from this study confirm that data acquired from VHR satellite image database can be used as DL training dataset and indicate the potential to improve efficiency of the matching process by appropriate configuration of multi-sensor images. DL-based image matching techniques using multi-sensor VHR satellite images are expected to replace existing manual-based feature extraction methods based on its stable performance, thus further develop into an integrated DL-based image registration framework.