- 标题
- 摘要
- 关键词
- 实验方案
- 产品
过滤筛选
- 2018
- Fruit defects
- Jujube
- Principal component analysis
- Hyperspectral imaging
- hyperspectral images
- spectral and spatial features
- classification
- SVM
- mutual information
- GLCM
- Optoelectronic Information Science and Engineering
- Mohammed V University in Rabat
- Southern Taiwan University of Science and Technology
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Compression of Hyperspectral Images Using Luminance Transform and 3D-DCT
摘要： DCT based transform techniques are popular in image compression. In this paper, luminance transform is applied to improve the compression performance of 3-D discrete cosine transform (3D-DCT) in hyperspectral images. The proposed scheme consists of two main steps. Firstly, luminance transform is performed on spectral band groups taking the first band image in a group as the reference. The aim of using luminance transform is to reduce the brightness and contrast difference within spectral band groups. Secondly, compression is performed by 3D-DCT followed by entropy encoding. The performance of the proposed approach is compared to 3D-DCT in terms of signal-to-noise ratio (SNR) and mean spectral angle (MSA). It is observed that applying luminance transform before 3D-DCT provides better results especially at low bit-rates.
关键词： hyperspectral image compression,luminance transform,3D-DCT
更新于2025-09-23 15:21:21
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Hyperspectral Compressive Sensing on Low Energy Consumption Board
摘要： Hyperspectral imaging instruments allow remote Earth exploration by measuring hundreds of spectral bands (at different wavelength channels) for the same area of the Earth surface. The acquired data cube comprises several GBs per flight, which have attracted attention to onboard compression techniques. Typically these compression techniques are expensive from the computational point of view. This paper presents a compressive sensing method implementation on a low power consumption Graphic Processing Unit. The experiments are conducted on a Jetson TX1 board, which is well suited to perform vector operations such as dot products. These experiments have been performed to demonstrate the applicability, in terms of accuracy and time consuming, of these methods for onboard processing. The results show that by using this low power consumption GPU it is possible to obtain real-time performance with a very limited power requirements.
关键词： GPU,Low-Power Consumption,Hyperspectral Imagery,Compressive Sensing
更新于2025-09-23 15:21:21
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Prisma: The Italian Hyperspectral Mission
摘要： PRISMA (PRecursore IperSpettrale della Missione Applicativa) is one the most important investments of Italian Space Agency (ASI) in the field of Optical Remote Sensing for Earth Observation. The PRISMA Space Segment consists of a single spacecraft embarking a state-of-the-art hyperspectral/panchromatic payload using pushbroom scanning technique. The PRISMA Ground Segment inlcudes the Fucino facilities for satellite/mission control and Matera CNM (Multimission National Center) systems, mainly devoted to data acquisition, products archive/delivery and user management. The IDHS facilty processes the payload data downloaded using the CNM X-Band antenna. The launch is scheduled in 2018 (VEGA Launcher) for a five years operational lifetime. This paper reports an overview of the mission and program development.
关键词： Ground Segment,Earth Observation,Products,Hyperspectral mission,PRISMA,Space Segment
更新于2025-09-23 15:21:21
-
A Prediction-Based Spatial-Spectral Adaptive Hyperspectral Compressive Sensing Algorithm
摘要： In order to improve the performance of storage and transmission of massive hyperspectral data, a prediction-based spatial-spectral adaptive hyperspectral compressive sensing (PSSAHCS) algorithm is proposed. Firstly, the spatial block size of hyperspectral images is adaptively obtained according to the spatial self-correlation coefficient. Secondly, a k-means clustering algorithm is used to group the hyperspectral images. Thirdly, we use a local means and local standard deviations (LMLSD) algorithm to find the optimal image in the group as the key band, and the non-key bands in the group can be smoothed by linear prediction. Fourthly, the random Gaussian measurement matrix is used as the sampling matrix, and the discrete cosine transform (DCT) matrix serves as the sparse basis. Finally, the stagewise orthogonal matching pursuit (StOMP) is used to reconstruct the hyperspectral images. The experimental results show that the proposed PSSAHCS algorithm can achieve better evaluation results—the subjective evaluation, the peak signal-to-noise ratio, and the spatial autocorrelation coefficient in the spatial domain, and spectral curve comparison and correlation between spectra-reconstructed performance in the spectral domain—than those of single spectral compression sensing (SSCS), block hyperspectral compressive sensing (BHCS), and adaptive grouping distributed compressive sensing (AGDCS). PSSAHCS can not only compress and reconstruct hyperspectral images effectively, but also has strong denoise performance.
关键词： interspectral prediction,compressive sensing,spatial-spectral adaptation,hyperspectral images
更新于2025-09-23 15:21:21
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Geological Mapping of Hydrothermal Alteration on Volcanoes from Multi-Sensor Platforms
摘要： Hydrothermal alteration due to geothermal fluids often introduces mineral alteration and weathering that poses significant natural hazards around volcanoes. Hydrothermal alteration can be mapped remotely using satellite and airborne derive images. In this study, we explored the capacity of available multispectral satellites, high-resolution airborne hyperspectral and LiDAR imagery to provide an improved geological mapping and classification capability for volcanic terrains. Image classification experiments using a Random Forest approach trained using ground class data to classify 15 ground cover types show that Sentinel-2 and Landsat 8 OLI+TIR can provide a geological map with Overall (OA) and Kappa Accuracies (KA) of 69% and 66% respectively. Classification accuracy was dramatically improved when high-resolution airborne datasets were included. The use of full-spectrum AisaFENIX hyperspectral images improved accuracies to OA = 84% and KA = 82%. The maximum image classification accuracy is reached (OA = 87, KA = 85%) when all input features were combined.
关键词： Sentinel-2,volcano,geological mapping,Landsat 8,LiDAR,hyperspectral imaging
更新于2025-09-23 15:21:21
-
Classification of Hyperspectral Images Using Kernel Fully Constrained Least Squares
摘要： As a widely used classi?er, sparse representation classi?cation (SRC) has shown its good performance for hyperspectral image classi?cation. Recent works have highlighted that it is the collaborative representation mechanism under SRC that makes SRC a highly effective technique for classi?cation purposes. If the dimensionality and the discrimination capacity of a test pixel is high, other norms (e.g., (cid:96)2-norm) can be used to regularize the coding coef?cients, except for the sparsity (cid:96)1-norm. In this paper, we show that in the kernel space the nonnegative constraint can also play the same role, and thus suggest the investigation of kernel fully constrained least squares (KFCLS) for hyperspectral image classi?cation. Furthermore, in order to improve the classi?cation performance of KFCLS by incorporating spatial-spectral information, we investigate two kinds of spatial-spectral methods using two regularization strategies: (1) the coef?cient-level regularization strategy, and (2) the class-level regularization strategy. Experimental results conducted on four real hyperspectral images demonstrate the effectiveness of the proposed KFCLS, and show which way to incorporate spatial-spectral information ef?ciently in the regularization framework.
关键词： least squares,hyperspectral,sparse representation,regularization,image classification,posterior probability,collaborative representation
更新于2025-09-23 15:21:21
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Evaluation of Tidal Effect On Water Constituent Variations Using Optical Observations And Tide Gauge Records in the Dutch Wadden Sea
摘要： In this study, the effect of tide on the variation of concentrations of Chlorophyll-a (Chla) and Suspended Particulate Matters (SPM), retrieved from a complete dataset of diurnal close-range hyperspectral observations recorded at the NIOZ jetty station (NJS) located at the Marsdiep inlet in the Dutch part of the Wadden Sea, was evaluated. The two-stream radiative transfer model 2SeaColor was inverted to retrieve Chla and SPM concentrations per each hyperspectral observation of the quality-controlled dataset. Concurrently with these diurnal observations, tidal information was obtained from the Den Helder station located at 3.7 km from the NJS. From the performed analysis and evaluation of this study, we concluded that the tide has little observable effects on the diurnal changes of SPM concentration at the NJS located in the Dutch part of the Wadden Sea. The results of this evaluation and the favorable location of the NJS, which is not influenced by the tidal phase, will contribute to a better understanding of the seasonal variability of the retrieved Chla and SPM concentration values using diurnal optical observations at the NJS. These long-term retrievals can be used later to do the phenological analysis of Chla concentration values in this region.
关键词： tidal effect,the NIOZ jetty station,2SeaColor model,hyperspectral observations,Radiative transfer modeling (RTM)
更新于2025-09-23 15:21:21
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - A Study on the Aerosol Optical Property Over Validation Sites in Japan for Hisui Atmospherically Corrected Surface Reflectance
摘要： The HISUI Hyperspectral Imager is being developed by Japanese Ministry of Economy, Trade, and Industry (METI), which will deploy on International Space Station (ISS) Japan Experiment Module (JEM) in FY2019. HISUI Level2 surface reflectance product (L2G) will be also provided for each of the VNIR and SWIR bands as research products. We have a plan of HISUI L2G validation, which includes not only surface reflectance itself also the atmospheric parameters, especially aerosol properties. We already have 3 sites that measures the atmospheric parameters day by day. This research shows the aerosol properties over validation sites in Japan on one of the HISUI calibration and validation activities.
关键词： Validation,Skyradiometer,Atmospheric correction,HISUI Hyperspectral Imager,SKYNET
更新于2025-09-23 15:21:21
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Processing, Validation And Quality Control Of Spaceborne Imaging Spectroscopy Data From Desis Mission on the Iss
摘要： The German Aerospace Center (DLR) and Teledyne Brown Engineering (TBE), located in Huntsville, Alabama, USA, cooperate to develop and operate the new space-based hyperspectral sensor DLR Earth Sensing Imaging Spectrometer (DESIS). While TBE provides the Multi-User platform MUSES and infrastructure for operation of the DESIS instrument on the ISS, DLR is responsible for providing the instrument and the processing software as well as instrument in-flight calibration and product quality operations. MUSES has been already launched and installed on the International Space Station ISS in early 2017 and DESIS will follow mid of 2018. We present here an overview of the DESIS instrument, the on-ground data processing, the in-flight calibration and product quality investigations.
关键词： Validation,DESIS,Hyperspectral
更新于2025-09-23 15:21:21
-
A new filter for dimensionality reduction and classification of hyperspectral images using GLCM features and mutual information
摘要： Dimensionality reduction is an important preprocessing step of the hyperspectral images classification (HSI), it is inevitable task. Some methods use feature selection or extraction algorithms based on spectral and spatial information. In this paper, we introduce a new methodology for dimensionality reduction and classification of HSI taking into account both spectral and spatial information based on mutual information. We characterise the spatial information by the texture features extracted from the grey level cooccurrence matrix (GLCM); we use Homogeneity, Contrast, Correlation and Energy. For classification, we use support vector machine (SVM). The experiments are performed on three well-known hyperspectral benchmark datasets. The proposed algorithm is compared with the state of the art methods. The obtained results of this fusion show that our method outperforms the other approaches by increasing the classification accuracy in a good timing. This method may be improved for more performance.
关键词： hyperspectral images,spectral and spatial features,classification,SVM,mutual information,GLCM,grey level cooccurrence matrix,support vector machine
更新于2025-09-23 15:21:21