• Title/Summary/Keyword: SWIR band

Search Result 25, Processing Time 0.027 seconds

Forest Damage Detection Using Daily Normal Vegetation Index Based on Time Series LANDSAT Images (시계열 위성영상 기반 평년 식생지수 추정을 통한 산림생태계 피해 탐지 기법)

  • Kim, Eun-sook;Lee, Bora;Lim, Jong-hwan
    • Korean Journal of Remote Sensing
    • /
    • v.35 no.6_2
    • /
    • pp.1133-1148
    • /
    • 2019
  • Tree growth and vitality in forest shows seasonal changes. So, in order to detect forest damage accurately, we have to use satellite images before and after damages taken at the same season. However, temporal resolution of high or medium resolution images is very low,so it is not easy to acquire satellite images of the same seasons. Therefore, in this study, we estimated spectral information of the same DOY using time-series Landsat images and used the estimates as reference values to assess forest damages. The study site is Hwasun, Jeollanam-do, where forest damage occurred due to hail and drought in 2017. Time-series vegetation index (NDVI, EVI, NDMI) maps were produced using all Landsat 8 images taken in the past 3 years. Daily normal vegetation index maps were produced through cloud removal and data interpolation processes. We analyzed the difference of daily normal vegetation index value before damage event and vegetation index value after event at the same DOY, and applied the criteria of forest damage. Finally, forest damage map based on daily normal vegetation index was produced. Forest damage map based on Landsat images could detect better subtle changes of vegetation vitality than the existing map based on UAV images. In the extreme damage areas, forest damage map based on NDMI using the SWIR band showed similar results to the existing forest damage map. The daily normal vegetation index map can used to detect forest damage more rapidly and accurately.

A Study on Transferring Cloud Dataset for Smoke Extraction Based on Deep Learning (딥러닝 기반 연기추출을 위한 구름 데이터셋의 전이학습에 대한 연구)

  • Kim, Jiyong;Kwak, Taehong;Kim, Yongil
    • Korean Journal of Remote Sensing
    • /
    • v.38 no.5_2
    • /
    • pp.695-706
    • /
    • 2022
  • Medium and high-resolution optical satellites have proven their effectiveness in detecting wildfire areas. However, smoke plumes generated by wildfire scatter visible light incidents on the surface, thereby interrupting accurate monitoring of the area where wildfire occurs. Therefore, a technology to extract smoke in advance is required. Deep learning technology is expected to improve the accuracy of smoke extraction, but the lack of training datasets limits the application. However, for clouds, which have a similar property of scattering visible light, a large amount of training datasets has been accumulated. The purpose of this study is to develop a smoke extraction technique using deep learning, and the limits due to the lack of datasets were overcome by using a cloud dataset on transfer learning. To check the effectiveness of transfer learning, a small-scale smoke extraction training set was made, and the smoke extraction performance was compared before and after applying transfer learning using a public cloud dataset. As a result, not only the performance in the visible light wavelength band was enhanced but also in the near infrared (NIR) and short-wave infrared (SWIR). Through the results of this study, it is expected that the lack of datasets, which is a critical limit for using deep learning on smoke extraction, can be solved, and therefore, through the advancement of smoke extraction technology, it will be possible to present an advantage in monitoring wildfires.

Comparison between Hyperspectral and Multispectral Images for the Classification of Coniferous Species (침엽수종 분류를 위한 초분광영상과 다중분광영상의 비교)

  • Cho, Hyunggab;Lee, Kyu-Sung
    • 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.

A Study of Tasseled Cap Transformation Coefficient for the Geostationary Ocean Color Imager (GOCI) (정지궤도 천리안위성 해양관측센서 GOCI의 Tasseled Cap 변환계수 산출연구)

  • Shin, Ji-Sun;Park, Wook;Won, Joong-Sun
    • Korean Journal of Remote Sensing
    • /
    • v.30 no.2
    • /
    • pp.275-292
    • /
    • 2014
  • The objective of this study is to determine Tasseled Cap Transformation (TCT) coefficients for the Geostationary Ocean Color Imager (GOCI). TCT is traditional method of analyzing the characteristics of the land area from multi spectral sensor data. TCT coefficients for a new sensor must be estimated individually because of different sensor characteristics of each sensor. Although the primary objective of the GOCI is for ocean color study, one half of the scene covers land area with typical land observing channels in Visible-Near InfraRed (VNIR). The GOCI has a unique capability to acquire eight scenes per day. This advantage of high temporal resolution can be utilized for detecting daily variation of land surface. The GOCI TCT offers a great potential for application in near-real time analysis and interpretation of land cover characteristics. TCT generally represents information of "Brightness", "Greenness" and "Wetness". However, in the case of the GOCI is not able to provide "Wetness" due to lack of ShortWave InfraRed (SWIR) band. To maximize the utilization of high temporal resolution, "Wetness" should be provided. In order to obtain "Wetness", the linear regression method was used to align the GOCI Principal Component Analysis (PCA) space with the MODIS TCT space. The GOCI TCT coefficients obtained by this method have different values according to observation time due to the characteristics of geostationary earth orbit. To examine these differences, the correlation between the GOCI TCT and the MODIS TCT were compared. As a result, while the GOCI TCT coefficients of "Brightness" and "Greenness" were selected at 4h, the GOCI TCT coefficient of "Wetness" was selected at 2h. To assess the adequacy of the resulting GOCI TCT coefficients, the GOCI TCT data were compared to the MODIS TCT image and several land parameters. The land cover classification of the GOCI TCT image was expressed more precisely than the MODIS TCT image. The distribution of land cover classification of the GOCI TCT space showed meaningful results. Also, "Brightness", "Greenness", and "Wetness" of the GOCI TCT data showed a relatively high correlation with Albedo ($R^2$ = 0.75), Normalized Difference Vegetation Index (NDVI) ($R^2$ = 0.97), and Normalized Difference Moisture Index (NDMI) ($R^2$ = 0.77), respectively. These results indicate the suitability of the GOCI TCT coefficients.

Development of Drought Stress Measurement Method for Red Pepper Leaves using Hyperspectral Short Wave Infrared Imaging Technique (초분광 단파적외선 영상 기술을 이용한 고추의 수분스트레스 측정 기술 개발)

  • Park, Eunsoo;Cho, Byoung-Kwan
    • Journal of Bio-Environment Control
    • /
    • v.23 no.1
    • /
    • pp.50-55
    • /
    • 2014
  • This study was conducted to investigate the responses of red pepper (Hongjinju) leaves under water stress. Hyperspectral short wave infrared (SWIR, 1000~1800 nm) reflectance imaging techniques were used to acquire the spectral images for the red pepper leaves with and without water stress. The acquired spectral data were analyzed with a multivariate analysis method of ANOVA (analysis of variance). The ANOVA model suggested that 1449 nm wavebands was the most effective to determine the stress responses of the red pepper leaves exposed to the water deficiency. The waveband of 1449 nm was closely related to the water absorption band. The processed spectral image of 1449 nm could separate the non-stress, moderate stress (-20 kPa), and severe stress (-50 kPa) groups of red pepper leaves distinctively. Results demonstrated that hyperspectral imaging technique can be applied to monitoring the stress responses of red pepper leaves which are an indicator of physiological and biochemical changes under water deficiency.