Nonlinear Feature Extraction for Hyperspectral Images
3
Citation
17
Reference
10
Related Paper
Citation Trend
Abstract:
In this study non-linear dimension reduction methods have been applied to a hyperspectral image in order to increase the classification accuracy in feature extraction step. Furthermore, image segmentation has been ensured the by taking into consideration the spatial synthesis of hyperspectral images and passing from high-dimensional space to low dimensional space. It has been compared the results obtained from the image segmentation made by taking one pixel from this spatial synthesis. The advantages of the effects of the results of the dimension reduction techniques made by facing neighbor pixels on the segmentation of hyper-spectral image have been displayed in the experimental results part.Keywords:
Feature (linguistics)
Feature vector
Abstract. Over the past thirty years, the hyperspectral remote sensing technology is attracted more and more attentions by the researchers. The dimension reduction technology for hyperspectral remote sensing image data is one of the hotspots in current research of hyperspectral remote sensing. In order to solve the problems of nonlinearity, the high dimensions and the redundancy of the bands that exist in the hyperspectral data, this paper proposes a dimension reduction method for hyperspectral remote sensing image data based on the global mixture coordination factor analysis. In the first place, a linear low dimensional manifold is obtained from the nonlinear and high dimensional hyperspectral image data by mixture factor analysis method. In the second place, the parameters of linear low dimensional manifold are estimated by the EM algorithm of find a local maximum of the data log-likelihood. In the third place, the manifold is aligned to a global parameterization by the global coordinated factor analysis model and then the lowdimension image data of hyperspectral image data is obtained at last. Through the comparison of different dimensionality reduction method and different classification method for the low-dimensional data, the result illuminates the proposed method can retain maximum spectral information in hyperspectral image data and can eliminate the redundant among bands.
Cite
Citations (11)
Hyperspectral imaging has become a standard for most applications that require precision based analysis. This is due to the fine spectral resolution that hyperspectral data offers. Target detection based on hyperspectral imaging is one of the significant applications required for numerous defence, surveillance as well as many civilian studies. This involves detailed analysis of all bands of hyperspectral data for presence of the desired target. However, there exist many parameters which may have bearing on the performance of detection algorithm. These include sensor related parameters like noise, calibration etc., spatial parameters like size, shape and location etc. and scene parameters like illumination variation, target composition, colour, background etc. This paper demonstrates the implications of three scene parameters namely illumination, background and colour on detection of many known targets using the hyperspectral data. The hyperspectral data acquired over Rochester Institute of Technology (RIT) for experimental purposes has been used. Three popular detection algorithms namely, ACE, MF, SAM have been implemented for target detection and the impact of selected parameters is assessed.
Full spectral imaging
Cite
Citations (0)
In this paper, a laboratory-based hyperspectral imaging system is used to acquire hyperspectral data cubes from different algae samples of known mixtures. The data are obtained under controlled and repeatable conditions. Hyperspectral image processing is complicated by the size of the corresponding datasets so hyperspectral image pre-processing techniques such as dimensionality reduction are necessary before spectral analysis. We assessed hyperspectral response of mixed algal cultures containing two algae types to characterize the laboratory-based hyperspectral imaging system. Changes in the hyper spectral imaging system's response to variations in volume and combinations of algae concentrations were tested. Preliminary results demonstrate the system's capability to differentiate algal species, concentrations and sample volumes.
Cite
Citations (6)
This paper briefly introduces applications of FT-IR hyperspectral imaging to laboratory analyses and focuses on application of FT-IR/ATR imaging to crop protection products on test and plant surfaces. Results from univariate and multivariate analyses of the hyperspectral images are shown and advantages of the multivariate approach demonstrated.
Univariate
Chemical Imaging
Full spectral imaging
Imaging spectrometer
Cite
Citations (1)
The inherent chemical properties of materials can be brought into perspective using the large amount of spectral information provided by hyperspectral imaging systems. Therefore, the utilization of hyperspectral imaging in industrial applications is gradually increasing. One of the industrial sectors that can benefit from the advantages of hyperspectral imaging is recycling. Plastics which have different chemical properties (PP, PE, PVC, PET and PS) need sorting for plastic waste recycling. In this study, different types of plastics in hyperspectral images acquired using a shortwave infrared (SWIR) hyperspectral imaging system are successfully sorted.
Chemical Imaging
Plastic Waste
Full spectral imaging
Cite
Citations (8)
Hyperspectral imaging based precise fertilization is challenge in the northern Europe, because of the cloud conditions. In this paper we will introduce schemes for the biomass and nitrogen content estimations from hyperspectral images. In this research we used the Fabry-Perot interferometer based hypespectral imager that enables hyperspectral imaging from lightweight UAVs. During the summers 2011 and 2012 imaging and flight campaigns were carried out on the Finnish test field. Estimation mehtod uses features from linear and non-linear unmixing and vegetation indices. The results showed that the concept of small hyperspectral imager, UAV and data analysis is ready to operational use.
Imaging spectrometer
Imaging Spectroscopy
Cite
Citations (60)
<span>Hyperspectral unmixing (HU) is an important technique for remotely sensed hyperspectral data exploitation. Hyperspectral unmixing is required to get an accurate estimation due to low spatial resolution of hyperspectral cameras, microscopic material mixing, and multiple scattering that cause spectra measured by hyperspectral cameras are mixtures of spectra of materials in a scene. It is a process of estimating constituent endmembers and their fractional abundances present at each pixel in hyperspectral image. Researchers have devised and investigated many models searching for robust, stable, tractable and accurate unmixing algorithm. Such algorithm are highly desirable to avoid propagation of errors within the process. This paper presents the comparison of hyperspectral unmixing method by using different kind of algorithms. These algorithms are named VCA, NFINDR, SISAL, and CoNMF. The performance of unmixing process is evaluated by calculating the SAD (spectral angle distance) for each endmembers by using same input of hyperspectral data for different algorithm.</span>
Cite
Citations (1)
The large number of spectral bands acquired by hyperspectral imaging sensors allows us to better distinguish many subtle objects and materials. Unlike other classical hyperspectral image classification methods in the multivariate analysis framework, in this paper, a novel method using functional data analysis (FDA) for accurate classification of hyperspectral images has been proposed. The central idea of FDA is to treat multivariate data as continuous functions. From this perspective, the spectral curve of each pixel in the hyperspectral images is naturally viewed as a function. This can be beneficial for making full use of the abundant spectral information. The relevance between adjacent pixel elements in the hyperspectral images can also be utilized reasonably. Functional principal component analysis is applied to solve the classification problem of these functions. Experimental results on three hyperspectral images show that the proposed method can achieve higher classification accuracies in comparison to some state-of-the-art hyperspectral image classification methods.
Full spectral imaging
Cite
Citations (66)
Hyperspectral imaging technology has been broadly applied in remote sensing because it collects echoed signals from across the electromagnetic (EM) spectrum and provides fruitfully helpful information. However, the processing or transformation of high-data-volume hyperspectral images, also viewed as snapshots varying with the EM spectrum, burdens the hardware resources, especially for the high spectral resolution and spatial resolution cases. To tackle this challenge, a novel reduced-order method based on the dynamic mode decomposition (DMD) algorithm is presented here to analyze hyperspectral images. The method decomposes the spatial-spectral hyperspectral images in terms of spatial dynamic modes and corresponding spectral patterns. Then, these spatial-spectral patterns are utilized to recover the raw hyperspectral images. Our proposed approach is benchmarked by the actual hyperspectral images measured at the Salinas scene. It is demonstrated that the proposed approach can represent the hyperspectral images with a low-rank model in spectral dimension. Our proposed approach could provide a useful tool for the model order reduction of hyperspectral images.
Full spectral imaging
Dynamic Mode Decomposition
Cite
Citations (0)
This paper explores the applicability of new sparse algorithms to perform spectral unmixing of hyperspectral images using available spectral libraries instead of resorting to well-known end member extraction techniques widely available in the literature. Our main assumption is that it is unlikely to find pure pixels in real hyperspectral images due to available spatial resolution and mixing phenomena happening at different scales. The algorithms analyzed in our study rely on different principles, and their performance is quantitatively assessed using both simulated and real hyperspectral data sets. The experimental validation of sparse techniques conducted in this work indicates promising results of this new approach to attack the spectral unmixing problem in remotely sensed hyperspectral images.
Full spectral imaging
Endmember
Cite
Citations (35)