• Smart Media Journal
• /
• v.13 no.8
• /
• pp.39-48
• /
• 2024

Recently, various studies have emerged that utilize hyperspectral imaging for crop growth analysis and early disease diagnosis. However, the challenge of using numerous spectral bands or finding the optimal bands for crop area remains a difficult problem. In this paper, we propose a method of searching the optimized spectral band of crop area based on deep learning using the hyper-spectral image. The proposed method extracts RGB images within hyperspectral images to segment background and foreground area through a Vision Transformer-based Seformer. The segmented results project onto each band of gray-scale converted hyperspectral images. It determines the optimized spectral band of the crop area through the pixel comparison of the projected foreground and background area. The proposed method achieved foreground and background segmentation performance with an average accuracy of 98.47% and a mIoU of 96.48%. In addition, it was confirmed that the proposed method converges to the NIR regions closely related to the crop area compared to the mRMR method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.6
• /
• pp.658-663
• /
• 2018

Current measuring methods for air quality are based on ground measurement networks and satellite data. New methods of collecting evidence with advanced sensors are needed because current methods have limitations in collecting evidence for the illegal emission of air pollutants at narrow areas or specific sites. This study analyzed the possibility of using an ultraviolet hyperspectral sensor to measure the concentration of nitrogen dioxide and sulfur dioxide. Two types of spectra were used: simulated spectra for gases with various concentrations using a radiative transfer model and observed spectra for each gas for a concentration. To understand the possibility of using a hyperspectral sensor, the differences between the simulated spectra and the observed spectra were analyzed, and the variation of simulated spectra were then analyzed according to the concentration. The results showed good agreement between observed spectra and simulated spectra. In addition, the absorption depth at specific wavelengths in the simulated spectra had a very strong correlation with the gas concentration. The gas concentration could be estimated using the hyperspectral sensor. In the future, validation would be needed to estimate the gas concentration through observations of various concentrations of gases using a hyperspectral sensor.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.225-225
• /
• 2023

하상 측정은 하천 유지관리, 수공구조물 설계 및 보수, 수생태 조사의 필수적인 자료이다. 최근 4대강 대규모 사업 이후 자연적 안정화로 인해 침식 및 재퇴적이 진행되어 정밀 하상 모니터링이 요구되고 있다. 통상적인 하상 조사 기법은 레벨측량 및 RTK-GPS 등을 활용하여 점단위로 직접 계측하는 기법과 수심이 깊을 경우 ADCP와 같은 음향측심기법을 통해 하상변동을 계측하고 있다. 하지만 점단위 직접 측정은 사구와 사련과 같은 하상 구조 교란 및 계측 시 위험을 동반하고 수심자료의 측정오차가 크게 발생하는 한계점이 존재한다. 또한 초음파 방식의 경우 막음길이와 바닥면 노이즈 등의 한계점으로 50 cm 미만의 저수심부 하상 측정이 불가능한 실정이다. 이러한 한계점을 극복하기 위해 최근 드론의 보급으로 수심라이다(Bathymetry LiDAR), SFM, 드론 탑재 초분광 영상을 활용한 초분광수심법과 같은 저고도, 고해상도의 비접촉식 면단위 하상 측정 기법이 대안으로 각광받고 있고 최근 관심은 해당 최신 기술의 성능 점검 및 적용성 평가에 있다. 따라서 본 연구에서는 초분광수심법 중 보편적으로 적용할 수 있는 최적밴드비분석(OBRA)의 성능 점검과 실무 적용성을 국내 하천을 대상으로 검토하였다. 해당 기술의 실무 적용성 평가항목 중 수심 적용 범위가 경제적이고 효율적인 성능 평가의 주된 항목이다. 선행 연구에 따르면 감천을 대상으로 저수심부의 성능 평가를 진행한 결과 상세한 하상계측이 가능하다고 제시하였다. 따라서 본 연구는 낙동강-황강 합류부를 대상으로 전형적인 평수기 탁도 조건에서 초분광수심법을 적용할 경우 최대측정가능수심의 범위를 결정하는 방법 및 결과를 제시하려고 한다. 또한 현장실험 당시 합천댐 방류로 인하여 황강의 탁도가 높아진 상태에 기인하여 고탁도 조건에서 초분광수심법의 적용성 평가도 추가 검토하였다. 해당 연구는 수심과 밴드비의 비선형성을 통해 최적 밴드비 분석의 결과로 도출될 수 있는 상관계수와 평균 제곱근 오차(RMSE)의 동향을 보아 다양한 시나리오의 배제수심을 통해 최대측정가능수심을 산정하였으며 그 이상의 범위는 수심맵 산정에서 제외하였다. 그 결과로 낙동강 본류에서 2.5 m 이하, 황강 지류에서 1.25 m 이하의 최대측정가능수심이 나타났고 해당 범위 이하에서는 상세한 하상이 나타났다. 또한 고탁도 조건인 황강에서는 낙동강에 비해 절반 수준의 최대측정가능수심 범위가 나타나 탁도 조건에 따른 초분광수심법의 한계가 있는 것을 확인하였다.

• Korean Journal of Remote Sensing
• /
• v.30 no.1
• /
• pp.25-36
• /
• 2014

Multispectral image classification of individual tree species is often difficult because of the spectral similarity among species. In this study, we attempted to analyze the suitability of hyperspectral image to classify coniferous tree species. Several image sets and classification methods were applied and the classification results were compared with the ones from multispectral image. Two airborne hyperspectral images (AISA, CASI) were obtained over the study area in the Gwangneung National Forest. For the comparison, ETM+ multispectral image was simulated using hyperspectral images as to have lower spectral resolution. We also used the transformed hyperspectral data to reduce the data volume for the classification. Three supervised classification schemes (SAM, SVM, MLC) were applied to thirteen image sets. In overall, hyperspectral image provides higher accuracies than multispectral image to discriminate coniferous species. AISA-dual image, which include additional SWIR spectral bands, shows the best result as compared with other hyperspectral images that include only visible and NIR bands. Furthermore, MNF transformed hyperspectral image provided higher classification accuracies than the full-band and other band reduced data. Among three classifiers, MLC showed higher classification accuracy than SAM and SVM classifiers.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.22 no.4
• /
• pp.1-11
• /
• 2019

With the development of remote sensing sensor technology, it has become possible to acquire satellite images with various spectral information. In particular, since the hyperspectral image is composed of continuous and narrow spectral wavelength, it can be effectively used in various fields such as land cover classification, target detection, and environment monitoring. Change detection techniques using remote sensing data are generally performed through differences of data with same dimensions. Therefore, it has a disadvantage that it is difficult to apply to heterogeneous sensors having different dimensions. In this study, we have developed a change detection method applicable to hyperspectral image and high spat ial resolution satellite image with different dimensions, and confirmed the applicability of the change detection method between heterogeneous images. For the application of the change detection method, the dimension of hyperspectral image was reduced by using correlation analysis and principal component analysis, and the change detection algorithm used CVA. The ROC curve and the AUC were calculated using the reference data for the evaluation of change detection performance. Experimental results show that the change detection performance is higher when using the image generated by adequate dimensionality reduction than the case using the original hyperspectral image.

• Korean Journal of Remote Sensing
• /
• v.36 no.2_2
• /
• pp.309-323
• /
• 2020

Estimation of chlorophyll a concentration (CHL) on coastal areas using remote sensing has been mostly performed through multi-spectral satellite image analysis. Recently, various studies using hyperspectral imagery have been attempted. In particular, airborne hyperspectral imagery is composed of hundreds of bands with a narrow band width and high spatial resolution, and thus may be more effective in coastal areas than estimation of CHL through conventional satellite image. In this study, comparative analysis of hyperspectral and satellite-based CHL images was performed to estimate CHL in coastal areas. As a result of analyzing CHL and seawater spectrum data obtained by field survey conducted on the south coast of Korea, the seawater spectrum with high CHL peaked near the wavelength bands of 570 and 680 nm. Using this spectral feature, a new band ratio of 570 / 490 nm for estimating CHL was proposed. Through regression analysis between band ratio and the measured CHL were generated new CHL empirical formula. Validation of new empirical formula using the measured CHL showed valid results, with R² of 0.70, RMSE of 2.43 mg m^-3, and mean bias of 3.46 mg m^-3. As a result of applying the new empirical formula to hyperspectral and satellite images, the average RMSE between hyperspectral imagery and the measured CHL was 0.12 mg m^-3, making it possible to estimate CHL with higher accuracy than multi-spectral satellite images. Through these results, it is expected that it is possible to provide more accurate and precise spatial distribution information of CHL in coastal areas by utilizing hyperspectral imagery.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.116-116
• /
• 2021

자연 하천에서의 부유사 농도 계측은 주로 재래식 채집방식을 활용한 직접계측 방식에 의존하여 비용과 시간이 많이 소요되며 점 계측 방식으로 고해상도의 시공간 자료를 측정하기엔 한계가 존재한다. 이러한 한계점을 극복하기 위해 최근 위성영상과 드론을 활용하여 촬영된 다분광 혹은 초분광 영상을 통해 고해상도의 부유사 농도 시공간분포를 측정하는 기법에 대한 연구가 활발히 진행되고 있다. 하지만, 다른 하천 물리량 계측에 비해 부유사 계측 연구는 하천에 따라 부유사가 비균질적으로 분포하여 원격탐사를 통해 정확하고 전역적인 농도 분포를 재현하기는 어려운 실정이다. 이러한 부유사의 비균질성은 부유사의 입도분포, 광물특성, 침강성 등이 하천에서 다양하게 분포하기 때문이며 이로 인해 부유사는 지역별로 다양한 분광특성을 가지게 된다. 따라서, 본 연구에서는 이러한 영향을 고려한 전역적인 부유사 농도 예측 모형을 개발하기 위해 실내 실험을 통해 부유사 특성별 고유 분광 라이브러리를 구축하고 실규모 수로에서 다양한 부유사 조건에 대한 초분광 스펙트럼과 부유사 농도를 측정하는 실험을 수행하였다. 실제 부유사 농도는 광학 기반 센서인 LISST-200X와 샘플링을 통한 실험실 분석을 통해 계측되었으며, 초분광 스펙트럼 자료는 초분광 카메라를 통해 촬영한 영상에서 부유사 계측 지점에 대한 픽셀의 스펙트럼을 추출하여 구축하였다. 이렇게 생성된 자료들의 분광 다양성을 주성분 분석(Principle Component Analysis; PCA)를 통해 분석하였으며, 부유사의 입도 분포, 부유사 종류, 수온 등과의 상관관계를 통해 분광 특성과 가장 상관관계가 높은 물리적 인자를 규명하였다. 더불어 구축된 자료를 바탕으로 기계학습 기반 주요 특징 선택 알고리즘인 재귀적 특징 제거법 (Recursive Feature Elimination)과 기계학습기반 회귀 모형인 Support Vector Regression을 결합하여 초분광 영상 기반 부유사 농도 예측 모형을 개발하였으며, 이 결과를 원격탐사 계측 연구에서 일반적으로 사용되어 오던 최적 밴드비 분석 (Optimal Band Ratio Analysis; OBRA) 방법으로 도출된 회귀식과 비교하였다. 그 결과, 기존의 OBRA 기반 방법은 비선형성을 증가시켜도 좁은 영역의 파장대만을 고려하는 한계점으로 인해 부유사의 다양한 분광 특성을 반영하지 못하였으며, 본 연구에서 제시한 기계학습 기반 예측 모형은 420 nm~1000 nm에 걸쳐 폭 넓은 파장대를 고려함과 동시에 높은 정확도를 산출하였다. 최종적으로 개발된 모형을 적용해 다양한 유사 조건에 대한 부유사 시공간 분포를 매핑한 결과, 시공간적으로 고해상도의 부유사 농도 분포를 산출하는 것으로 밝혀졌다.

• Journal of the Korean earth science society
• /
• v.45 no.3
• /
• pp.214-223
• /
• 2024

The recent increase in maritime traffic and coastal leisure activities has led to a rise in various marine accidents. These incidents not only result in damage to human life and property but also pose a significant risk of marine pollution involving oil and hazardous and noxious substances (HNS) spills. Therefore, effective ship monitoring is crucial for preparing and for responding to marine accidents. This study conducted an aerial experiment utilizing hyperspectral remote sensing to develop a maritime ship monitoring system. Hyperspectral aerial measurements were carried out around Gungpyeong Port in the western coastal region of the Korean Peninsula, and spectral libraries were constructed for various ship decks. The spectral correlation similarity (SCS) technique was employed for ship detection, analyzing the spatial similarity distribution between hyperspectral images and ship spectra. As a result, 15 ships were detected in the hyperspectral images. The color of each ship's deck was classified based on the highest spectral similarity. The detected ships were verified by matching them with high-resolution digital mapping camera (DMC) images. This foundational study on the application of aerial hyperspectral sensors for maritime ship detection demonstrates their potential role in future remote sensing-based ship monitoring systems.

• Korean Journal of Remote Sensing
• /
• v.28 no.4
• /
• pp.347-355
• /
• 2012

A fast algorithm for endmember extraction is proposed in this study which extracts min. and max. pixels from each band after MNF transform as candidate pixels for endmember. This method finds endmembers not from the entire image pixels but only from the previously extracted candidate pixels. The experimental results by N-FINDR using a simulated hyperspectral image data and AVIRIS Cuprite image data showed that the proposed fast algorithm extracts the same endmembers with the conventional methods. More studies on the effect of noise and more adaptive criteria in extracting candidate pixels are expected to increase the usability of this method for more fast and efficient analysis of hyperspectral image data.

• Korean Journal of Remote Sensing
• /
• v.27 no.5
• /
• pp.565-572
• /
• 2011

A modified iterative N-FINDR algorithm is developed for fully automatic extraction of endmembers from hyperspectral image data. This algorithm exploits the advantages of iterative NFINDR technique and Iterative Error analysis technique. The experiments using a simulated hyperspectral image data shows that the optimum number of endmembers can be automatically decided. The extracted endmembers and finally generated abundance fraction maps show the potentialities of the proposed algorithm. More studies are needed for verification of the applicability of the algorithm to the real hyperspectral image data where the absence of pure pixels is common.