Unsupervised Image Classification using Region-growing Segmentation based on CN-chain

Lee, Sang-Hoon The Korean Society of Remote Sensing 2004 大韓遠隔探査學會誌 Vol.20 No.3

A multistage hierarchical clustering technique, which is an unsupervised technique, was suggested in this paper for classifying large remotely-sensed imagery. The multistage algorithm consists of two stages. The 'local' segmentor of the first stage performs region-growing segmentation by employing the hierarchical clustering procedure of CN-chain with the restriction that pixels in a cluster must be spatially contiguous. The 'global' segmentor of the second stage, which has not spatial constraints for merging, clusters the segments resulting from the previous stage, using the conventional agglomerative approach. Using simulation data, the proposed method was compared with another hierarchical clustering technique based on 'mutual closest neighbor.' The experimental results show that the new approach proposed in this study considerably increases in computational efficiency for larger images with a low number of bands. The technique was then applied to classify the land-cover types using the remotely-sensed data acquired from the Korean peninsula.

Optimizing Image Size of Convolutional Neural Networks for Producing Remote Sensing-based Thematic Map

Jo, Hyun-Woo,Kim, Ji-Won,Lim, Chul-Hee,Song, Chol-Ho,Lee, Woo-Kyun The Korean Society of Remote Sensing 2018 大韓遠隔探査學會誌 Vol.34 No.4

This study aims to develop a methodology of convolutional neural networks (CNNs) to produce thematic maps from remote sensing data. Optimizing the image size for CNNs was studied, since the size of the image affects to accuracy, working as hyper-parameter. The selected study area is Mt. Ung, located in Dangjin-si, Chungcheongnam-do, South Korea, consisting of both coniferous forest and deciduous forest. Spatial structure analysis and the classification of forest type using CNNs was carried in the study area at a diverse range of scales. As a result of the spatial structure analysis, it was found that the local variance (LV) was high, in the range of 7.65 m to 18.87 m, meaning that the size of objects in the image is likely to be with in this range. As a result of the classification, the image measuring 15.81 m, belonging to the range with highest LV values, had the highest classification accuracy of 85.09%. Also, there was a positive correlation between LV and the accuracy in the range under 15.81 m, which was judged to be the optimal image size. Therefore, the trial and error selection of the optimum image size could be minimized by choosing the result of the spatial structure analysis as the starting point. This study estimated the optimal image size for CNNs using spatial structure analysis and found that this can be used to promote the application of deep-learning in remote sensing.

Adaptive Reconstruction of Harmonic Time Series Using Point-Jacobian Iteration MAP Estimation and Dynamic Compositing: Simulation Study

Lee, Sang-Hoon The Korean Society of Remote Sensing 2008 大韓遠隔探査學會誌 Vol.24 No.1

Irregular temporal sampling is a common feature of geophysical and biological time series in remote sensing. This study proposes an on-line system for reconstructing observation image series contaminated by noises resulted from mechanical problems or sensing environmental condition. There is also a high likelihood that during the data acquisition periods the target site corresponding to any given pixel may be covered by fog or cloud, thereby resulting in bad or missing observation. The surface parameters associated with the land are usually dependent on the climate, and many physical processes that are displayed in the image sensed from the land then exhibit temporal variation with seasonal periodicity. A feedback system proposed in this study reconstructs a sequence of images remotely sensed from the land surface having the physical processes with seasonal periodicity. The harmonic model is used to track seasonal variation through time, and a Gibbs random field (GRF) is used to represent the spatial dependency of digital image processes. The experimental results of this simulation study show the potentiality of the proposed system to reconstruct the image series observed by imperfect sensing technology from the environment which are frequently influenced by bad weather. This study provides fundamental information on the elements of the proposed system for right usage in application.

Open Source Remote Sensing of ORFEO Toolbox and Its Connection to Database of PostGIS with NIX File Importing

Lee, Ki-Won,Kang, Sang-Goo The Korean Society of Remote Sensing 2010 大韓遠隔探査學會誌 Vol.26 No.3

In recent, interests regarding open source software for geo-spatial processing are increasing. Open source remote sensing (OSRS) is regarded as one of the progressing and advanced fields in remote sensing. Nevertheless, analyses or application cases regarding OSRS are not enough for general uses or references. In this study, three kinds of OSRS software in consideration of international popularity, types of functionalities, and development environments are taken into account: OSSIM, Opticks, and ORFEO Toolbox (OTB). First, functional comparison with respect to these is carried out on the level of the preliminary survey. According to this investigation, OTB is chosen as the most applicable OSRS software in this study. Running on OTB, NIX format importing module and database connecting module are implemented for widely general uses and further application. As for an example case, airborne image of NIX format is used to region growing segmentation algorithm in OTB, and then the results are stored and retrieved in PostGIS database to test implemented modules. Conclusively, local customization and algorithm development using OSRS software are necessary to build on-demand applications from the developers' viewpoint.

Automatic Road Extraction by Gradient Direction Profile Algorithm (GDPA) using High-Resolution Satellite Imagery: Experiment Study

Lee, Ki-Won,Yu, Young-Chul,Lee, Bong-Gyu The Korean Society of Remote Sensing 2003 大韓遠隔探査學會誌 Vol.19 No.5

In times of the civil uses of commercialized high-resolution satellite imagery, applications of remote sensing have been widely extended to the new fields or the problem solving beyond traditional application domains. Transportation application of this sensor data, related to the automatic or semiautomatic road extraction, is regarded as one of the important issues in uses of remote sensing imagery. Related to these trends, this study focuses on automatic road extraction using Gradient Direction Profile Algorithm (GDPA) scheme, with IKONOS panchromatic imagery having 1 meter resolution. For this, the GDPA scheme and its main modules were reviewed with processing steps and implemented as a prototype software. Using the extracted bi-level image and ground truth coming from actual GIS layer, overall accuracy evaluation and ranking error-assessment were performed. As the processed results, road information can be automatically extracted; by the way, it is pointed out that some user-defined variables should be carefully determined in using high-resolution satellite imagery in the dense or low contrast areas. While, the GDPA method needs additional processing, because direct results using this method do not produce high overall accuracy or ranking value. The main advantage of the GDPA scheme on road features extraction can be noted as its performance and further applicability. This experiment study can be extended into practical application fields related to remote sensing.

Assimilation of Oceanographic Data into Numerical Models over the Seas around Korea

Kim, Seung-Bum The Korean Society of Remote Sensing 2001 大韓遠隔探査學會誌 Vol.17 No.4

This review provides a summary of data assimilation applied to the seas around Korea. Currently the worldwide efforts are devoted to applying advanced assimilation to realistic cases, thanks to improvements in mathematical foundations of assimilation methods and the computing capabilities, and also to the availability of extensive observational data such as from satellites. Over the seas around Korea, however, the latest developments in the advanced assimilation methods have yet to be applied. Thus it would be timely to review the progress in data assimilation over the seas. Firstly, the definition and necessity of data assimilation are described, continued by a brief summary of major assimilation methods. Then a review of past research on the ocean data assimilation in the regional seas around Korea is given and future trends are considered. Special consideration is given to the assimilation of remotely-sensed data.

OCI and ROCSAT-1 Development, Operations, and Applications

Chen, Paul,Lee, L.S.,Lin, Shin-Fa The Korean Society of Remote Sensing 1999 大韓遠隔探査學會誌 Vol.15 No.4

This paper describes the development, operations, and applications of ROCSAT-l and its Ocean Color Imager (OCI) remote-sensing payload. It is the first satellite program of NSPO. The satellite was successfully launched by Lockheed Martin's Athena on January 26, 1999 from Cape Canaveral, Florida. ROCSAT-l is a Low Earth Orbit (LEO) experimental satellite. Its circular orbit has an altitude of 600km and an inclination angle of 35 degrees. The satellite is designed to carry out scientific research missions, including ocean color imaging, experiments on ionospheric plasma and electrodynamics, and experiments using Ka-band (20∼30GHz) communication payloads. The OCI payload is utilized to observe the ocean color in 7 bands (including one redundant band) of Visible and Near-Infrared (434nm∼889nm) range with the resolution of 800m at nadir and the swath of 702km. It employs high performance telecentric optics, push-broom scanning method using Charge Coupled Devices (CCD) and large-scale integrated circuit chips. The water leaving radiance is estimated from the total inputs to the OCI, including the atmospheric scattering. The post-process estimates the water leaving radiance and generates different end products. The OCI has taken images since February 1999 after completing the early orbit checkout. Analyses have been performed to evaluate the performances of the instrument in orbit and to compare them with the pre-launch test results. This paper also briefly describes the ROCSAT-l mission operations. The spacecraft operating modes and ROCSAT Ground Segment operations are delineated, and the overall initial operations of ROCSAT-l are summarized.

Analysis of the MSC(Multi-Spectral Camera) Operational Parameters

Yong, Sang-Soon,Kong, Jong-Pil,Heo, Haeng-Pal,Kim, Young-Sun The Korean Society of Remote Sensing 2002 大韓遠隔探査學會誌 Vol.18 No.1

The MSC is a payload on the KOMPSAT-2 satellite to perform the earth remote sensing. The instrument images the earth using a push-broom motion with a swath width of 15 km and a GSD(Ground Sample Distance) of 1 m over the entire FOV(Field Of View) at altitude 685 km. The instrument is designed to haute an on-orbit operation duty cycle of 20% over the mission lifetime of 3 years with the functions of programmable gain/offset and on-board image data compression/storage. The MSC instrument has one channel for panchromatic imaging and four channel for multi-spectral imaging covering the spectral range from 450nm to 900nm using TDI(Time Belayed Integration) CCD(Charge Coupled Device) FPA(Focal Plane Assembly). The MSC hardware consists of three subsystem, EOS(Electro Optic camera Subsystem), PMU(Payload Management Unit) and PDTS(Payload Data Transmission Subsystem) and each subsystems are currently under development and will be integrated and verified through functional and space environment tests. Final verified MSC will be delivered to spacecraft bus for AIT(Assembly, Integration and Test) and then COMSAT-2 satellite will be launched after verification process through IST(Integrated Satellite Test). In this paper, the introduction of MSC, the configuration of MSC electronics including electrical interlace and design of CEU(Camera Electronic Unit) in EOS are described. MSC Operation parameters induced from the operation concept are discussed and analyzed to find the influence of system for on-orbit operation in future.

Adjustment of A Simplified Satellite-Based Algorithm for Gross Primary Production Estimation Over Korea

Pi, Kyoung-Jin,Han, Kyung-Soo,Kim, In-Hwan,Lee, Tae-Yoon,Jo, Jae-Il The Korean Society of Remote Sensing 2013 大韓遠隔探査學會誌 Vol.29 No.3

Monitoring the global Gross Primary Pproduction (GPP) is relevant to understanding the global carbon cycle and evaluating the effects of interannual climate variation on food and fiber production. GPP, the flux of carbon into ecosystems via photosynthetic assimilation, is an important variable in the global carbon cycle and a key process in land surface-atmosphere interactions. The Moderate-resolution Imaging Spectroradiometer (MODIS) is one of the primary global monitoring sensors. MODIS GPP has some of the problems that have been proven in several studies. Therefore this study was to solve the regional mismatch that occurs when using the MODIS GPP global product over Korea. To solve this problem, we estimated each of the GPP component variables separately to improve the GPP estimates. We compared our GPP estimates with validation GPP data to assess their accuracy. For all sites, the correlation was close with high significance ($R^2=0.8164$, $RMSE=0.6126g{\cdot}C{\cdot}m^{-2}{\cdot}d^{-1}$, $bias=-0.0271g{\cdot}C{\cdot}m^{-2}{\cdot}d^{-1}$). We also compared our results to those of other models. The component variables tended to be either over- or under-estimated when compared to those in other studies over the Korean peninsula, although the estimated GPP was better. The results of this study will likely improve carbon cycle modeling by capturing finer patterns with an integrated method of remote sensing.

Analysis of Land Cover Changes Based on Classification Result Using PlanetScope Satellite Imagery

Yoon, Byunghyun,Choi, Jaewan The Korean Society of Remote Sensing 2018 大韓遠隔探査學會誌 Vol.34 No.4

Compared to the imagery produced by traditional satellites, PlanetScope satellite imagery has made it possible to easily capture remotely-sensed imagery every day through dozens or even hundreds of satellites on a relatively small budget. This study aimed to detect changed areas and update a land cover map using a PlanetScope image. To generate a classification map, pixel-based Random Forest (RF) classification was performed by using additional features, such as the Normalized Difference Water Index (NDWI) and the Normalized Difference Vegetation Index (NDVI). The classification result was converted to vector data and compared with the existing land cover map to estimate the changed area. To estimate the accuracy and trends of the changed area, the quantitative quality of the supervised classification result using the PlanetScope image was evaluated first. In addition, the patterns of the changed area that corresponded to the classification result were analyzed using the PlanetScope satellite image. Experimental results found that the PlanetScope image can be used to effectively to detect changed areas on large-scale land cover maps, and supervised classification results can update the changed areas.