• Title/Summary/Keyword: Hyperspectral Data

Search Result 202, Processing Time 0.028 seconds

Support Vector Machine Classification of Hyperspectral Image using Spectral Similarity Kernel (분광 유사도 커널을 이용한 하이퍼스펙트럴 영상의 Support Vector Machine(SVM) 분류)

  • Choi, Jae-Wan;Byun, Young-Gi;Kim, Yong-Il;Yu, Ki-Yun
    • Journal of Korean Society for Geospatial Information Science
    • /
    • v.14 no.4 s.38
    • /
    • pp.71-77
    • /
    • 2006
  • Support Vector Machine (SVM) which has roots in a statistical learning theory is a training algorithm based on structural risk minimization. Generally, SVM algorithm uses the kernel for determining a linearly non-separable boundary and classifying the data. But, classical kernels can not apply to effectively the hyperspectral image classification because it measures similarity using vector's dot-product or euclidian distance. So, This paper proposes the spectral similarity kernel to solve this problem. The spectral similariy kernel that calculate both vector's euclidian and angle distance is a local kernel, it can effectively consider a reflectance property of hyperspectral image. For validating our algorithm, SVM which used polynomial kernel, RBF kernel and proposed kernel was applied to land cover classification in Hyperion image. It appears that SVM classifier using spectral similarity kernel has the most outstanding result in qualitative and spatial estimation.

  • PDF

Hyperspectral Image Classification via Joint Sparse representation of Multi-layer Superpixles

  • Sima, Haifeng;Mi, Aizhong;Han, Xue;Du, Shouheng;Wang, Zhiheng;Wang, Jianfang
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.12 no.10
    • /
    • pp.5015-5038
    • /
    • 2018
  • In this paper, a novel spectral-spatial joint sparse representation algorithm for hyperspectral image classification is proposed based on multi-layer superpixels in various scales. Superpixels of various scales can provide complete yet redundant correlated information of the class attribute for test pixels. Therefore, we design a joint sparse model for a test pixel by sampling similar pixels from its corresponding superpixels combinations. Firstly, multi-layer superpixels are extracted on the false color image of the HSI data by principal components analysis model. Secondly, a group of discriminative sampling pixels are exploited as reconstruction matrix of test pixel which can be jointly represented by the structured dictionary and recovered sparse coefficients. Thirdly, the orthogonal matching pursuit strategy is employed for estimating sparse vector for the test pixel. In each iteration, the approximation can be computed from the dictionary and corresponding sparse vector. Finally, the class label of test pixel can be directly determined with minimum reconstruction error between the reconstruction matrix and its approximation. The advantages of this algorithm lie in the development of complete neighborhood and homogeneous pixels to share a common sparsity pattern, and it is able to achieve more flexible joint sparse coding of spectral-spatial information. Experimental results on three real hyperspectral datasets show that the proposed joint sparse model can achieve better performance than a series of excellent sparse classification methods and superpixels-based classification methods.

The Evaluation of on Land Cover Classification using Hyperspectral Imagery (초분광 영상을 이용한 토지피복 분류 평가)

  • Lee, Geun-Sang;Lee, Kang-Cheol;Go, Sin-Young;Choi, Yun-Woong;Cho, Gi-Sung
    • Journal of Cadastre & Land InformatiX
    • /
    • v.44 no.2
    • /
    • pp.103-112
    • /
    • 2014
  • The objective of this study is to suggest the possibility on land cover classification using hyperspectal imagery on area which includes lands and waters. After atmospheric correction as a preprocessing work was conducted on hyperspectral imagery acquired by airborne hyperspectral sensor CASI-1500, the effect of atmospheric correction to a few land cover class in before and after atmospheric correction was compared and analyzed. As the result of accuracy of land cover classification by highspectral imagery using reference data as airphoto and digital topographic map, maximum likelihood method represented overall accuracy as 67.0% and minimum distance method showed overall accuracy as 52.4%. Also product accuracy of land cover classification on road, dry field and green house, but that on river, forest, grassland showed low because the area of those was composed of complex object. Therefore, the study needs to select optimal band to classify specific object and to construct spectral library considering spectral characteristics of specific object.

Applicability of Hyperspectral Imaging Technology for the Check of Cadastre's Land Category (지목조사를 위한 초분광영상의 활용성 검토 연구)

  • Lee, InSu;Hyun, Chang-Uk
    • Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
    • /
    • v.32 no.spc4_2
    • /
    • pp.421-430
    • /
    • 2014
  • Aerial imagery, Satellite imaging and Hyperspectral imaging(HSI) are widely using at mapping those of agriculture, woodland, waters shoreline, and land cover, but are rarely applied at the Cadastre. There are many study cases on the overlay of aerial imagery and satellite imaging with Cadastral Map and the upgrade and registration of Cadastre' Land Category, however, reported as successful. Therefore, this study has been aimed to show the use of the Hyperspectral Imaging technology for Cadastre, especially for the land category. Also, the HSI sensor could function as a geospatial acquisition tool for error checks of the existed land categories, and as a helpful tool for acquiring the attributes and spatial data, such as the agriculture, soil, and vegetation, etc. This result indicates that HSI sensor can implement the Multipurpse Cadastre(MPC) by fusing with the cadastral information.

Prediction of moisture contents in green peppers using hyperspectral imaging based on a polarized lighting system

  • Faqeerzada, Mohammad Akbar;Rahman, Anisur;Kim, Geonwoo;Park, Eunsoo;Joshi, Rahul;Lohumi, Santosh;Cho, Byoung-Kwan
    • Korean Journal of Agricultural Science
    • /
    • v.47 no.4
    • /
    • pp.995-1010
    • /
    • 2020
  • In this study, a multivariate analysis model of partial least square regression (PLSR) was developed to predict the moisture content of green peppers using hyperspectral imaging (HSI). In HSI, illumination is essential for high-quality image acquisition and directly affects the analytical performance of the visible near-infrared hyperspectral imaging (VIS/NIR-HSI) system. When green pepper images were acquired using a direct lighting system, the specular reflection from the surface of the objects and their intensities fluctuated with time. The images include artifacts on the surface of the materials, thereby increasing the variability of data and affecting the obtained accuracy by generating false-positive results. Therefore, images without glare on the surface of the green peppers were created using a polarization filter at the front of the camera lens and by exposing the polarizer sheet at the front of the lighting systems simultaneously. The results obtained from the PLSR analysis yielded a high determination coefficient of 0.89 value. The regression coefficients yielded by the best PLSR model were further developed for moisture content mapping in green peppers based on the selected wavelengths. Accordingly, the polarization filter helped achieve an uniform illumination and the removal of gloss and artifact glare from the green pepper images. These results demonstrate that the HSI technique with a polarized lighting system combined with chemometrics can be effectively used for high-throughput prediction of moisture content and image-based visualization.

THE MODIFIED UNSUPERVISED SPECTRAL ANGLE CLASSIFICATION (MUSAC) OF HYPERION, HYPERION-FLASSH AND ETM+ DATA USING UNIT VECTOR

  • Kim, Dae-Sung;Kim, Yong-Il
    • Proceedings of the KSRS Conference
    • /
    • 2005.10a
    • /
    • pp.134-137
    • /
    • 2005
  • Unsupervised spectral angle classification (USAC) is the algorithm that can extract ground object information with the minimum 'Spectral Angle' operation on behalf of 'Spectral Euclidian Distance' in the clustering process. In this study, our algorithm uses the unit vector instead of the spectral distance to compute the mean of cluster in the unsupervised classification. The proposed algorithm (MUSAC) is applied to the Hyperion and ETM+ data and the results are compared with K-Meails and former USAC algorithm (FUSAC). USAC is capable of clearly classifying water and dark forest area and produces more accurate results than K-Means. Atmospheric correction for more accurate results was adapted on the Hyperion data (Hyperion-FLAASH) but the results did not have any effect on the accuracy. Thus we anticipate that the 'Spectral Angle' can be one of the most accurate classifiers of not only multispectral images but also hyperspectral images. Furthermore the cluster unit vector can be an efficient technique for determination of each cluster mean in the USAC.

  • PDF

SPECTRAL ANALYSIS OF WATER-STRESSED FOREST CANOPY USING EO-l HYPERION DATA

  • Kook Min-Jung;Shin Jung-Il;Lee Kyu-Sung
    • Proceedings of the KSRS Conference
    • /
    • 2005.10a
    • /
    • pp.7-10
    • /
    • 2005
  • Plant water deficiency during drought season causes physiological stress and can be a critical indicator of forest fire vulnerability. In this study, we attempt to analyze the spectral characteristics of water stressed vegetation by using the laboratory measurement on leaf samples and the canopy reflectance spectra extracted from satellite hyperspectral image data. Leaf-level reflectance spectra were measured by varying moisture content using a portable spectro-radiometer. Canopy reflectance spectra of sample forest stands of two primary species (pine and oak) located in central part of the Korean peninsula were extracted from EO-l Hyperion imaging spectrometer data obtained during the drought season in 2001 and the normal precipitation year in 2002. The preliminary analysis on the reflectance spectra shows that the spectral characteristics of leaf samples are not compatible with the ones obtained from canopy level. Although moisture content of vegetation can be influential to the radiant flux reflected from leaf-level, it may not be very straightforward to obtain the spectral characteristics that are directly related to the level of canopy moisture content. Canopy spectra form forest stands can be varied by structural variables (such as LAt, percent coverage, and biomass) other than canopy moisture content.

  • PDF

Feature selection and similarity comparison system for identification of unknown paintings (미확인 작품 식별을 위한 Feature 선정 및 유사도 비교 시스템 구축)

  • Park, Kyung-Yeob;Kim, Joo-Sung;Kim, Hyun-Soo;Shin, Dong-Myung
    • Journal of Software Assessment and Valuation
    • /
    • v.17 no.1
    • /
    • pp.17-24
    • /
    • 2021
  • There is a problem that unknown paintings are sophisticated in the level of forgery, making it difficult for even experts to determine whether they are genuine or counterfeit. These problems can be suspected of forgery even if the genuine product is submitted, which can lead to a decline in the value of the work and the artist. To address these issues, in this paper, we propose a system to classify chromaticity data among extracted data through objective analysis into quadrants, extracting comparisons and intersections, and estimating authors of unknown paintings using XRF and hyperspectral spectrum data from corresponding points.

Comparative Analysis of Target Detection Algorithms in Hyperspectral Image (초분광영상에 대한 표적탐지 알고리즘의 적용성 분석)

  • Shin, Jung-Il;Lee, Kyu-Sung
    • Korean Journal of Remote Sensing
    • /
    • v.28 no.4
    • /
    • pp.369-392
    • /
    • 2012
  • Recently, many target detection algorithms were developed for hyperspectral image. However, almost of these studies focused only accuracy from 1 or 2 data sets to validate and compare the algorithms although they give limited information to users. This study aimed to compare usability of target detection algorithms with various parameters. Five parameters were proposed to compare sensitivity in aspect of detection accuracy which are related with radiometric and spectral characteristics of target, background and image. Six target detection algorithms were compared in aspect of accuracy and efficiency (processing time) by variation of the parameters and image size, respectively. The results shown different usability of each algorithm by each parameter in aspect of accuracy. Second order statistics based algorithms needed relatively long processing time. Integrated usabilities of accuracy and efficiency were various by characteristics of target, background and image. Consequently, users would consider appropriate target detection algorithms by characteristics of data and purpose of detection.

Applicability Evaluation of Endmember Extraction Algorithms on the AISA Hyperspectral Images (AISA 초분광 영상에 대한 Endmember 추출 알고리즘의 적용성 분석)

  • Song, Ahram;Chang, Anjin;Kim, Yong-Il;Choi, Jaewan
    • Korean Journal of Remote Sensing
    • /
    • v.29 no.5
    • /
    • pp.527-535
    • /
    • 2013
  • Extraction of correct endmembers is prerequisite to successful spectral unmixing analysis. Various endmember extraction algorithms have been proposed and most experiments based on endmember extraction have used synthetic image and AVIRIS image data. However, these data can present different characteristics comparing with hyperspectral images acquired from real domestic environment. For this study, a test-bed was constructed for analysing the difference on diverse substances and sizes in domestic areas, and AISA hyperspectral imagery acquired from the test-bed was tested with two well-known endmember extraction algorithms: IEA, and N-FINDR. The results indicated that two different algorithms depended on the number of endmembers and material types in the test-bed. Therefore, optimized number of endmembers and characteristics of materials in test-bed site should be considered for the effective application of endmember extraction algorithms.