Spectral derivative feature coding for hyperspectral signature analysis

Chang, Chein‐I; Chakravarty, Sumit

doi:10.1117/12.681662

Cited by 7 publications

(7 citation statements)

References 6 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, such a case seldom occurs in multispectral imagery but does happen very often when it comes to hyperspectral imagery such as class 1, class 7, class 9 and class 16 in Fig.1(c). So, (10) is the best compromise between the global sample covariance matrix and class sample covariance matrices (13). However, if the training samples are appropriately selected, the results using (10) are very similar to those obtained by the global sample covariance matrix.…”

Section: Methodsmentioning

confidence: 50%

“…In step 5 the dimensionality allocation d j is broken down into two values. The first value,n VD is the number of dimensions required to classify the p signatures, the second value, q j is the number of dimensions required for m j to distinguish itself from other signatures, note is the selection of the reference signature s. Three candidates can be used for this purpose, data sample mean μ, signature mean one is a better choice depends up applications[8][9][10][11].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Dynamic dimensionality reduction for hyperspectral imagery

Safavi

Liu

Chang

2011

Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVII

Self Cite

View full text Add to dashboard Cite

Data dimensionality (DR) is generally performed by first fixing size of DR at a certain number, say p and then finding a technique to reduce an original data space to a low dimensional data space with dimensionality specified by p. This paper introduces a new concept of dynamic dimensionality reduction (DDR) which considers the parameter p as a variable by varying the value of p to make p adaptive compared to the commonly used DR, referred to as static dimensionality reduction (SDR) with the parameter p fixed at a constant value. In order to materialize the DDR another new concept, referred to as progressive DR (PDR) is also developed so that the DR can be performed progressively to adapt the variable size of data dimensionality determined by varying the value of p. The advantages of the DDR over SDR are demonstrated through experiments conducted for hyperspectral image classification.

show abstract

Section: Methodsmentioning

confidence: 50%

mentioning

confidence: 99%

Dynamic dimensionality reduction for hyperspectral imagery

Safavi

Liu

Chang

2011

Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVII

Self Cite

View full text Add to dashboard Cite

show abstract

“…Such algorithms either designed for specific applications or only used a particular order of derivative. Recently, spectral derivative has been introduced in order to improve spectral discrimination and identification with an approach called spectral derivative feature coding or hyperspectral signature analysis [5]. It has also been used to alleviate spectral distortions [6].…”

Section: Introductionmentioning

confidence: 99%

An improved spectral reflectance and derivative feature fusion for hyperspectral image classification

Wang

Zhang

Chen

et al. 2011

2011 IEEE International Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

In this paper, a new method for improving the classification performance of hyperspectral images with the aid of derivative information is investigated. First, spectral features are filtered and derivatives of different orders at different sampling intervals are computed. Then, the suitable spectral magnitude features and different derivative features are chosen by using segmented principle component analysis feature extraction method with optimal parameters, and are stacked to constitute a new feature cube. Finally, the efficacy of the spectral derivatives in improving the classification performance of the hyperspectral data is testified using support vector machine for AVIRIS hyperspectral data. The experimental results show that the proposed method can improve the classification accuracy compared to the traditional classification techniques with spectral magnitude features even on very small training samples.

show abstract

“…bands simultaneously and, hence, are capable of differentiating surface features that cannot be done by multispectral images [3]- [5]. Image classification is a process that is widely adopted to map man-made and natural features from remotely sensed data.…”

mentioning

confidence: 99%

“…However, remotely sensed image pixels tend to be mixed rather than pure, and it is particularly true to hyperspectal images. Although a hyperspectral signature provides significant spectral information for signature discrimination and classification because of its composition of hundreds of contiguous spectral bands [10], EE (a step of spectral mixture analysis) techniques are often required to interpret the mixed spectral information [11], [12]. Over recent decades, a good number of endmember extraction algorithms (EEAs) are proposed for the purpose of autonomous/supervised EE, which can be categorized into two groups [13]: endmember identification algorithms (EIAs) and endmember generation algorithms.…”

mentioning

confidence: 99%

Chaos Theory-Based Data-Mining Technique for Image Endmember Extraction: Laypunov Index and Correlation Dimension (L and D)

Zhang

Xie

2014

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

It is often hard to collect a large size of high-quality field samples as ground reference points (GRPs) to support image analysis. Endmember extraction (EE) is an important technique to obtain spectrally identifiable image pixels to provide a supplementary solution to field sampling. However, most current EE methods are based on simplex models and thus rarely consider capricious occurrences in the data. The new approach developed in this paper synthesizes two quantitative measures of chaotic tendencies, Lyapunov index (L) and correlation dimension (D) into an integrated statistic, L and D for EE. L and D reconstructs a spectral dataset into phases, over which the chaotic or complex characteristics hidden in the dataset could be rearranged into predictable sequences. Therefore, better endmembers could be selected from the spectral or hyperspectral dataset. The usability and applicability of L and D are tested against the USGS standard spectral library first and then with a Hyperion image classification in Wulate Zhongqi (central county) of Inner Mongolia inChina. L and D, along with four other methods, PPI+n-DV+GRPs, SMACC, VCA, and PPI+VCA, is applied to extract endmembers, which are used as the surrogates of GRPs for creating the training and testing samples and classifying the Hyperion image with two classifiers, spectral angle mapper (SAM) and support vector machine (SVM). The classification results based on GRPs derived from L and D have the overall accuracy and kappa statistics, 81.93% and 0.7905 (by SAM) or 84.11% and 0.814% (by SVM), whereas the other four methods have lower accuracies.

show abstract

Spectral derivative feature coding for hyperspectral signature analysis

Cited by 7 publications

References 6 publications

Dynamic dimensionality reduction for hyperspectral imagery

Dynamic dimensionality reduction for hyperspectral imagery

An improved spectral reflectance and derivative feature fusion for hyperspectral image classification

Chaos Theory-Based Data-Mining Technique for Image Endmember Extraction: Laypunov Index and Correlation Dimension (L and D)

Contact Info

Product

Resources

About