• Title/Summary/Keyword: 초분

Search Result 297, Processing Time 0.029 seconds

Anomaly Detection from Hyperspectral Imagery using Transform-based Feature Selection and Local Spatial Auto-correlation Index (자료 변환 기반 특징 선택과 국소적 자기상관 지수를 이용한 초분광 영상의 이상값 탐지)

  • Park, No-Wook;Yoo, Hee-Young;Shin, Jung-Il;Lee, Kyu-Sung
    • Korean Journal of Remote Sensing
    • /
    • v.28 no.4
    • /
    • pp.357-367
    • /
    • 2012
  • This paper presents a two-stage methodology for anomaly detection from hyperspectral imagery that consists of transform-based feature extraction and selection, and computation of a local spatial auto-correlation statistic. First, principal component transform and 3D wavelet transform are applied to reduce redundant spectral information from hyperspectral imagery. Then feature selection based on global skewness and the portion of highly skewed sub-areas is followed to find optimal features for anomaly detection. Finally, a local indicator of spatial association (LISA) statistic is computed to account for both spectral and spatial information unlike traditional anomaly detection methodology based only on spectral information. An experiment using airborne CASI imagery is carried out to illustrate the applicability of the proposed anomaly detection methodology. From the experiments, anomaly detection based on the LISA statistic linked with the selection of optimal features outperformed both the traditional RX detector which uses only spectral information, and the case using major principal components with large eigen-values. The combination of low- and high-frequency components by 3D wavelet transform showed the best detection capability, compared with the case using optimal features selected from principal components.

Estimation of Vegetation for Chinese Cabbage Using Hyperspectral Imagery (초분광 영상을 이용한 배추의 생육 추정)

  • Kim, Won Jun;Kang, Ye Seong;Kim, Seong Heon;Kang, Jeong Gyun;Jun, Sae Rom;sarkar, Tapash Kumar;Ryu, Chan Seok
    • Proceedings of the Korean Society for Agricultural Machinery Conference
    • /
    • 2017.04a
    • /
    • pp.40-40
    • /
    • 2017
  • 본 연구는 빛의 파장대가 넓어 보다 다양한 접근과 검출이 가능한 초분광 카메라 (VNIR spectral camera PS, SPECIN Filand)를 이용하여 정식시기가 다른 배추를 생육단계별로 영상을 취득한 후 배추 캐노피의 전 파장 (400~1000nm)으로 생육 추정모델을 개발하기 위해 수행하였다. 정식시기가 다른 배추를 생육단계별로 초분광 카메라로 영상을 취득한 후 취득된 영상 ($348{\times}1040$)을 ENVI (ver. 5.2, Exelis Visual Information Solutions, USA) 프로그램을 이용하여 식생지수 NDVI로 작물과 배경을 구분하였다. 배추 캐노피 영역에 전 파장을 산출한 후 반사판 영역의 전 파장을 이용하여 광 보정된 반사율을 산출하였다. 통계 프로그램인 R Project (ver.3.3.3, Development Core Team, Vienna, Austria)를 이용하여 배추의 반사율과 계측한 생육 정보를 PLSR (Partial least squares regression) 분석하여 정확도($R^2$) 및 정밀도 (RMSE [g,cm,count], RE [%])로 나타내었고 그 모델은 full-cross validation (FV) 하여 타당성을 검증하였다. 정식시기가 다른 배추의 모든 생육단계의 생육정보를 이용하여 PLSR (Partial least squares regression) 결과 엽장을 추정한 모델의 $R^2$는 84% 이상의 정확도와 RMSE 3.2cm 이하의 좋은 정밀도를 보였다. 엽폭을 추정한 모델의 $R^2$는 73% 이상의 정확도와 RMSE 3.5cm 이하의 정밀도를 보였고 엽수를 추정한 모델의 $R^2$는 93% 이상의 정확도와 RMSE 6.3Count 이하의 정밀도로 보여 캐노피의 전 파장을 이용해 생육을 추정하는 것이 가능하다고 판단되었으며 이 모델들의 타당성 검증에서도 좋은 정확도와 정밀도를 보였다. 그러나 배추의 중요한 생육인자 중 생체중을 추정한 모델의 $R^2$는 89% 이상으로 정확도가 높았으나 RMSE 571.1g 이하로 낮은 정밀도를 보여 생체중을 정확히 추정하기 어려웠다. 따라서 다른 통계분석방법으로 전 파장과 생육정보를 분석하거나 특정 밴드를 선택하여 산출한 식생지수를 이용한 추정 모델의 개발을 통하여 오차를 개선할 필요가 있다고 사료된다. 추후 반복 실험하여 분석한 추정 모델과 비교 분석하여 다양한 환경 및 생물 조건에 범용성을 가진 모델을 개발할 필요가 있다.

  • PDF

Estimation of Nitrate Nitrogen Concentration in Liquid Fertilizer Contaminated Areas using Hyperspectral Images (초분광 영상을 이용한 액비 오염지역의 질산성질소 농도 추정)

  • Lim, Eun Sung;Kim, I Seul;Han, Soo Jeong;Lim, Tai Yang;Song, Wonkyong
    • Journal of the Society of Disaster Information
    • /
    • v.16 no.3
    • /
    • pp.542-549
    • /
    • 2020
  • Purpose: As nitrate nitrogen produced during fermentation of liquid fertilizer is a pollution indicator of water, in this study, four research areas where liquid fertilizer was sprayed were selected, and a model was designed to estimate the concentration of nitrate nitrogen pollution. Method: Prior to shooting on site, a spectrum library was constructed by dividing the ratio of liquid fertilizer into 5 groups: 0%, 25%, 50%, 75%, and 100%. PLSR (Partial least squares regression) method was applied to hyperspectral images acquired in the study area based on the aspect of spectrum. Result: The behavior of nitrate nitrogen was confirmed by 1st and 2nd differentiation of the spectrum of the constructed liquid fertilizer. PLSR concentration estimation modeling was implemented using images from field experiments and compared with actual concentration of nitrate nitrogen. Conclusion: When comparing the PLSR concentration estimation model with the actual concentration of nitrate nitrogen, it was measured that the detection is possible in high concentration areas where the concentration of nitrate nitrogen is 70mg/kg or more.

Change Detection Using Spectral Unmixing and IEA(Iterative Error Analysis) for Hyperspectral Images (IEA(Iterative Error Analysis)와 분광혼합분석기법을 이용한 초분광영상의 변화탐지)

  • Song, Ahram;Choi, Jaewan;Chang, Anjin;Kim, Yongil
    • Korean Journal of Remote Sensing
    • /
    • v.31 no.5
    • /
    • pp.361-370
    • /
    • 2015
  • Various algorithms such as Chronochrome(CC), Principle Component Analysis(PCA), and spectral unmixing have been studied for hyperspectral change detection. Change detection by spectral unmixing offers useful information on the nature of the change compared to the other change detection methods which provide only the locations of changes in the scene. However, hyperspectral change detection by spectral unmixing is still in an early stage. This research proposed a new approach to extract endmembers, which have identical properties in temporally different images, by Iterative Error Analysis (IEA) and Spectral Angle Mapper(SAM). The change map obtained from the difference of abundance efficiently showed the changed pixels. Simulated images generated from Compact Airborne Spectrographic Imager (CASI) and Hyperion were used for change detection, and the experimental results showed that the proposed method performed better than CC, PCA, and spectral unmixing using N-FINDR. The proposed method has the advantage of automatically extracting endmembers without prior information, and it could be applicable for the real images composed of many materials.

1,3-bisdicyanovinylindane 색소를 이용한 선택적 $Hg^{2+}$ 감지 특성

  • Kim, Su-Ho;Kim, Young-Sung;Kim, Sung-Hoon;Son, Young-A
    • Proceedings of the Korean Society of Dyers and Finishers Conference
    • /
    • 2009.11a
    • /
    • pp.19-20
    • /
    • 2009
  • 최근 화학, 물리, 생명과학, 전기, 전자등의 다양한 분야에 활발하게 연구가 이루어지고 있는 초분자 화학은 선택적 분자인지를 위한 효율적인 골격구조와 나아가 다양한 계에 응용할 수 있다. 초분자 화학의 분자인지 과정의 특징은 일반적으로 수용체 (receptor 혹은 host)가 목표가 되는 기질 (substrate, analyte, 혹은 guest)에 대하여 선택적으로 식별하고 반응하는 것이다. 비공유 결합성 상호작용에 의하여 이루어지는 초분자 화학의 분자 인지 과정의 특징은 일반적으로 수용체 (receptor 혹은 host)가 목표가 되는 기질 (substrate, analyte, 혹은 guest)에 대하여 선택적으로 식별하고 반응하는 것이다. 이는 공유결합을 이용하는 분자화학과는 차별화 된 것이다. 수용체는 간단한 구조의 화합물 및 금속 이온들과 같은 기질과 가역적으로 상호 작용할 수 있는 착물을 형성한다. 최근들어 급격한 산업화가 진행되어 환경문제가 심각하게 대두 되어져 왔고, 그 중에서 특히 수은이나 카드뮴에 의한 질병, 납에 의한 중독 등 중금속에 의한 오염이 크게 나타남에도 불구하고, 현재 그러한 중금속을 검출함에 있어 많은 비용과 시간이 드는 문제점이 있다. 또한 우리에게 이로운 금속은 효율적 분석을 통해 환경계와 의료계에 많은 도움을 줄 것으로 사례되므로 화학센서 기술의 개발은 절실히 요구되어지고 있다. 이에 새로운 1,3-bisdicyanovinylindane 을 통해 $Hg^{2+}$ 금속의 감지 여부 알아보고, 그 특성을 파악하고자 한다. 1,3-indandion (2.18g, 14.9mmol), malononitrile (2.95g, 44.7mmol), ethanol 50ml를 20분간 상온에서 용해시킨다. 후에 sodium trihydrate acetate(3.05g)을 첨가한 후 5시간 동안 환류반응 시킨다. 이 과정에서 얻어진 용액을 필터과정을 통하여 에서 합성 반응 중에 생성된 불순물(1,3-dicyanovinylindane-1-one, monocondensation)을 제거한다. 필터과정을 통해 걸러진 미 반응 물질을 제�G 용반응욕액을 증류수(100ml)를 이용하여 희석시키고 난 후 염산을 이용, 산성화 시켜 고체 생성물을 얻어낸다. 이렇게 생성된 고체 생성물은 다시 필터 및 건조를 통하여 회색의 고체 화합물을 얻어낸다. 1,3-bisdicyanovinylindane과 금속이온에 대한 감응도를 확인하기 위하여 metanol/water(1:2)을 용매로 하여 금속이온의 농도를 변화시켜 발색특성을 살펴보았다. 본 색소화합물과 Hg2+에 대한 UV 흡광도 변화 적정결과와 그 화합물의 상태 살펴본 결과 금속이온이 0.2ml씩 더 참가되면서 색의 변화를 뚜렷하게 나타내었다. 반면 그 밖에 이온($Fe^{3+}$, $Ag^{2+}$, $Pd^{2+}$, $Zn^2$, $Fe^{2+}$, $Cu^{2+}$, $Pb^{2+}$)은 UV 흡광도 변화가 적거나 변화 자체가 없었다. 하지만 과량의 $Fe^{3+}$, $Ag^{2+}$, $Pd^{2+}$는 색상 변화를 나타내었으며,이와 같은 흡광도 변화는 금속에 따라 약간의 차이가 있지만, 420nm를 등흡수점으로 하여, 580nm의 파장 영역에 있는 흡수 밴드의 세기는 감소하는 반면 400nm 파장 영역에 있는 흡수 밴드의 세기가 증가하였다. 1,3-bisdicyanovinylindane 화합물은 다양한 생물계 및 환경계에서 요구되는 micro mol에서 milli mol 농도 영역의 $Hg^{2+}$ 이온의 선택적이고 민감한 검출과 정량적인 분석에 유용하게 사용될 수 있을 것이다.

  • PDF

An Analysis of Spectral Characteristic Information on the Water Level Changes and Bed Materials (수위변화에 따른 하상재료의 분광특성정보 분석)

  • Kang, Joongu;Lee, Changhun;Kim, Jihyun;Ko, Dongwoo;Kim, Jongtae
    • Ecology and Resilient Infrastructure
    • /
    • v.6 no.4
    • /
    • pp.243-249
    • /
    • 2019
  • The purpose of this study is to analyze the reflectance of bed materials according to changes in the water level using a drone-based hyperspectral sensor. For this purpose, we took hyperspectral images of bed materials such as soil, gravel, cobble, reed, and vegetation to compare and analyze the spectral data of each material. To adjust the water level, we constructed an experimental channel to control the discharge and installed the bed materials within the channel. In this study, we configured 3 cases according to the water level (0.0 m, 0.3 m, 0.6 m). After the imaging process, we used the mean value of 10 points for each bed material as analytical data. According to the analysis, each material showed a similar reflectance by wavelength and the intrinsic reflectance characteristics of each material were shown in the visible and near-infrared region. Also, the deeper the water level, the lower the peak reflectance in the visible and near-infrared region, and the rate of decrease differed depending on the bed material. We expect the intrinsic properties of these bed materials to be used as basic research data to evaluate river environments in the future.

Detection of Small Green Space in an Urban Area Using Airborne Hyperspectral Imagery and Spectral Angle Mapper (분광각매퍼 기법을 적용한 항공기 탑재 초분광영상의 소규모 녹지공간 탐지)

  • Kim, Tae-Woo;Choi, Don-Jeong;We, Gwang-Jae;Suh, Yong-Cheol
    • Journal of the Korean Association of Geographic Information Studies
    • /
    • v.16 no.2
    • /
    • pp.88-100
    • /
    • 2013
  • Urban green space is one of most important aspects of urban infrastructure for improving the quality of life of city dwellers as it reduces the heat island effect and is used for recreation and relaxation. However, no systematic management of urban green space has been introduced in Korea as past practices focused on efficient development. A way to calculate the amount of green space needed to complement an urban area must be developed to preserve urban green space and to determine 'regulations determining the total amount of greenery'. In recent years, various studies have quantified urban green space and infrastructure using remotely sensed data. However, it is difficult to detect a myriad small green spaces in a city effectively when considering the spatial resolution of the data used in existing research. In this paper, we quantified small urban green spaces using CASI-1500 hyperspectral imagery. We calculated MCARI, a vegetation index for hyperspectral imagery, to evaluate the greenness of small green spaces. In addition, we applied image-classification methods, including the ISODATA algorithm and Spectral Angle Mapper, to detect small green spaces using supervised and unsupervised classifications. This could be used to categorize land-cover into four classes: unclassified, impervious, suspected green, and vegetation green.

A Study on Agricultural Drought Monitoring using Drone Thermal and Hyperspectral Sensor (드론 열화상 및 초분광 센서를 이용한 농업가뭄 모니터링 적용 연구)

  • HAM, Geon-Woo;LEE, Jeong-Min;BAE, Kyoung Ho;PARK, Hong-Gi
    • Journal of the Korean Association of Geographic Information Studies
    • /
    • v.22 no.3
    • /
    • pp.107-119
    • /
    • 2019
  • As the development of ICT and integration technology, many changes and innovations in agriculture field are implemented. The agricultural sector has shifted from a traditional industry to a new industrial form called the 6th industry combined with various advanced technologies such as ICT and IT. Various approaches have been attempted to analyze and predict crops based on spatial information. In particular, a variety of research has been carried out recently for crop cultivation and smart farms using drones. The goal of this study was to establish an agricultural drought monitoring system using drones to produce scientific and objective indicators of drought. A soil moisture sensor was installed in the drought area and checked the actual soil moisture. The soil moisture data was used by the reference value to compare and analyze the temperature and NDVI established by drones. The soil temperature by the drone thermal image sensor and the NDVI by the drone hyperspectral was analyzed the correlation between crop condition and soil moisture in study area. To verify this, the actual soil moisture was calculated using the soil moisture measurement sensor installed in the target area and compared with the drone performance. This study using drone drought monitoring system may enhance to promote the crop data and to save time and economy.

A study on the development of a Blue-green algae cell count estimation formula in Nakdong River downstream using hyperspectral sensors (초분광센서를 활용한 낙동강 하류부 남조류세포수 추정식 개발에 관한 연구)

  • Kim, Gwang Soo;Choi, Jae Yun;Nam, Su Han;Kim, Young Dod;Kwon, Jae Hyun
    • Journal of Korea Water Resources Association
    • /
    • v.56 no.6
    • /
    • pp.373-380
    • /
    • 2023
  • Due to abnormal climate phenomena and climate change in Korea, overgrowth of algae in rivers and reservoirs occurs frequently. Algae in rivers are classified into green algae, blue-green algae, diatom, and other types, and some species of blue-green algae cause problems due to odor and the discharge of toxic substances. In Korea, an algae alert system is in place, and it is issued based on the number of harmful blue-green algae cells. Thus, measuring harmful blue-green algal blooms is very important, and currently, the analysis method of algae involves taking field samples and determining the cell count of green algae, blue-green algae, and diatoms through algal microscopy, which takes a lot of time. Recently, the analysis of algae concentration through Phycocyanin, an alternative indicator for the number of harmful algae cells, has been conducted through remote sensing. However, research on the analysis of the number of blue-green algae cells is currently insufficient. In this study, we water samples for algal analyses were collected from river and counted the number of blue-green algae cells using algae microscopy. We also obtained the Phycocyanin concentration using an optical sensor and acquired algae spectra through a hyperspectral sensor. Based on this, we calculated the equation for estimating blue-green algae cell counts and estimated the number of blue-green algae cells.