Hyperspectral Texture Research Articles

Using an optimized texture index to monitor the nitrogen content of potato plants over multiple growth stages

Plant nitrogen content (PNC) is vital for evaluating crop nitrogen nutrient status and for net primary productivity. Therefore, rapid and accurate acquisition of crop PNC information can help reduce fertilizer and increase efficiency in modern agriculture. This study investigated whether an optimized texture index constructed from hyperspectral characteristic wavelength images acquired from a unmanned aerial vehicle (UAV) may be used to estimate PNC in potatoes over multiple growth stages. A potato field trial conducted in 2019 in Beijing, China, included different planting densities, nitrogen fertilizer gradients, and potato varieties with three replicates. A UAV remote sensing platform served to acquire hyperspectral images during three critical N demand periods for potatoes. In addition, we simultaneously conducted field sampling to obtain ground-truth PNC measurements. Following the classical form of vegetation indices, 12 texture indices were constructed based on hyperspectral texture features, and an arbitrary variable combination optimization algorithm was used to optimize these indices. Finally, the texture index, which had the highest correlation with potato PNC, was used as the best indicator for estimating the PNC status of potato at multiple growth stages and whether this indicator, in combination with spectral information, could further improve the accuracy of potato PNC estimation was subsequently explored. The results showed that (i) the optimal texture index TTI3 (R494-Cor, R578-Hom, R514-Sem) maintained a good linear relationship with PNC at the late stage of potato growth, and the accuracy and stability of the PNC estimation models constructed based on it was significantly better than that of a single texture metric. (ii) Compared with spectral information alone, the texture index combined with spectral features improved the accuracy of potato PNC estimation. More specifically, TTI3 (R494-Cor, R578-Hom, R514-Sem) combined with the three-band spectral index TBI 5 (530, 734, 514) achieved the best estimation accuracy with calibrated R2, root mean square error (RMSE), and normalized RMSE of 0.77%, 0.28%, and 9.88%, respectively. The results of this study showed that the texture index constructed by combining multiple texture metrics enhanced the association between texture features and potato PNC over multiple growth stages, thus improving the monitoring accuracy of potato nitrogen nutrition status. This study can provide a reference for accurately managing crop nitrogen nutrition.

Comparison of color imaging vs. hyperspectral imaging for texture classification

Many approaches of texture analysis by color or hyperspectral imaging are based on the assumption that the image of a texture can be viewed as a multi-component image, where spatial interactions within and between components are jointly considered (opponent component approach) or not (marginal approach). When color images are coded in multiple color spaces, texture descriptors are based on Multi Color Channel (MCC) representations. By extension, a Multi Spectral Band (MSB) representation can be used to characterize the texture of material surfaces in hyperspectral images. MSB and MCC representations are compared in this paper for texture classification issues. The contribution of each representation is investigated with marginal and/or opponent component strategies. For this purpose, several relevant texture descriptors are considered. Since MSB and MCC representations generate high-dimensional feature spaces, a dimensionality reduction is applied to avoid the curse of dimensionality. Experimental results carried out on three hyperspectral texture databases (HyTexiLa, SpecTex and an original dataset extracted from the Timbers database) show that considering between component interactions in addition to the within ones significantly improves the classification accuracies. The proposed approaches allow also to outperform state of the art hand-designed descriptors and color texture descriptors based on deep learning networks. This study highlights the contribution of hyperspectral imaging compared to color imaging for texture classification purposes but also the advantages of color imaging depending on the considered texture representation.

Hyperspectral Texture Metrology Based on Joint Probability of Spectral and Spatial Distribution.

Texture characterization from the metrological point of view is addressed in order to establish a physically relevant and directly interpretable feature. In this regard, a generic formulation is proposed to simultaneously capture the spectral and spatial complexity in hyperspectral images. The feature, named relative spectral difference occurrence matrix (RSDOM) is thus constructed in a multireference, multidirectional, and multiscale context. As validation, its performance is assessed in three versatile tasks. In texture classification on HyTexiLa, content-based image retrieval (CBIR) on ICONES-HSI, and land cover classification on Salinas, RSDOM registers 98.5% accuracy, 80.3% precision (for the top 10 retrieved images), and 96.0% accuracy (after post-processing) respectively, outcompeting GLCM, Gabor filter, LBP, SVM, CCF, CNN, and GCN. Analysis shows the advantage of RSDOM in terms of feature size (a mere 126, 30, and 20 scalars using GMM in order of the three tasks) as well as metrological validity in texture representation regardless of the spectral range, resolution, and number of bands.

Hyperspectral image classification using graph-based wavelet transform

ABSTRACTGraph-based methods are developed to efficiently extract data information. In particular, these methods are adopted for high-dimensional data classification by exploiting information residing on weighted graphs. In this paper, we propose a new hyperspectral texture classifier based on graph-based wavelet transform. This recent graph transform allows extracting textural features from a constructed weighted graph using sparse representative pixels of hyperspectral image. Different measurements of spectral similarity between representative pixels are tested to decorrelate close pixels and improve the classification precision. To achieve the hyperspectral texture classification, Support Vector Machine is applied on spectral graph wavelet coefficients. Experimental results obtained by applying the proposed approach on Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) and Reflective Optics System Imaging Spectrometer (ROSIS) datasets provide good accuracy which could exceed 98.7%. Compared to other famous classification methods as conventional deep learning-based methods, the proposed method achieves better classification performance. Results have shown the effectiveness of the method in terms of robustness and accuracy.

Relative Spectral Difference Occurrence Matrix: A Metrological Spectral-Spatial Feature for Hyperspectral Texture Analysis

We develop a spectral-spatial feature, Relative Spectral Difference Occurrence Matrix (RSDOM) for hyperspectral texture recognition. Inspired by Julesz's conjecture, the proposed feature is based on spectral difference approach and respects the metrological constraints. It simultaneously considers the distribution of spectra and their spatial arrangement in the hyperspectral image. The feature is generic and adapted for any number of spectral bands and range. We validate our proposition by applying a classification scheme on the HyTexiLa database. An accuracy comparable to local binary pattern approach is obtained, but at a much reduced cost due to the extremely small feature size.

HyTexiLa: High Resolution Visible and Near Infrared Hyperspectral Texture Images.

We present a dataset of close range hyperspectral images of materials that span the visible and near infrared spectrums: HyTexiLa (Hyperspectral Texture images acquired in Laboratory). The data is intended to provide high spectral and spatial resolution reflectance images of 112 materials to study spatial and spectral textures. In this paper we discuss the calibration of the data and the method for addressing the distortions during image acquisition. We provide a spectral analysis based on non-negative matrix factorization to quantify the spectral complexity of the samples and extend local binary pattern operators to the hyperspectral texture analysis. The results demonstrate that although the spectral complexity of each of the textures is generally low, increasing the number of bands permits better texture classification, with the opponent band local binary pattern feature giving the best performance.

An effective hyperspectral image retrieval method using integrated spectral and textural features

Purpose – The purpose of this paper is to improve the retrieval results of hyperspectral image by integrating both spectral and textural features. For this purpose, an improved multiscale opponent representation for hyperspectral texture is proposed to represent the spatial information of the hyperspectral scene. Design/methodology/approach – In the presented approach, end-member signatures are extracted as spectral features by means of the widely used end-member induction algorithm N-FINDR, and the improved multiscale opponent representation is extracted from the first three principal components of the hyperspectral data based on Gabor filters. Then, the combination similarity between query image and other images in the database is calculated, and the first k more similar images are returned in descending order of the combination similarity. Findings – Some experiments are calculated using the airborne hyperspectral data of Washington DC Mall. According to the experimental results, the proposed method improves the retrieval results, especially for image categories that have regular textural structures. Originality/value – The paper presents an effective retrieval method for hyperspectral images.

Hyperspectral Data Spectrum and Texture Band Selection based on the Subspace-rough Set Method

Hyperspectral Data Spectrum and Texture Band Selection based on the Subspace-rough Set Method

Hyperspectral data spectrum and texture band selection based on the subspace-rough set method

In order to improve the utilization rate of spectroscopic data and texture information, this study proposes a method for optimal selection of spectrum and texture features based on automatic subspace division and rough set theory. This method takes advantage of rough set reduct ideology in order to realize the reduction of different types of ground object spectral features on the basis of the conventional subspace division method. In using this method, the primary spectral band based on spectral information can be determined. Then, the grey-level co-occurrence matrix method can be used to calculate the texture information of the primary spectral band and determine the reduction and optimization in order to obtain the final band based on the spectrum and texture information. Verification of this method is made by using CASI data of Heihe Region, China, and AVIRIS data of the Indiana Region, USA, and also using Support Vector Machine (SVM) classification of the original spectral, primary spectral, and final bands. The results indicate the following. (1) The method for optimal selection of the critical spectral band and texture band, based on the rough set theory, can efficiently improve the classification accuracy of high-spatial resolution remote-sensing images. However, the effects for the low-spatial resolution images are minimal. (2) For high-spatial-resolution remote-sensing images, such as roads, trenches, buildings, and other types of object with obvious textural features, the addition of image texture information can increase the degree of distinction of these different types and thereby improve the classification accuracy. However, the addition of the textural information for some objects with similar texture features will cause misclassification and reduce the classification accuracy for these types of images. (3) This method can realize the optimal selection of spectrum and texture bands of a hyperspectral image and has a certain universality. Also, the texture information will be richer and this method will be more practical through increasing the spatial resolution of images.

Study on the polarized reflectance-hyperspectral information fusion technology of tomato leaves nutrient diagnoses

With 25%, 50%, 75%, 100% and 150%, five levels of, nitrogen (N), phosphorus (P) and potassium (K) nutrition stress samples cultivated in Venlo type greenhouse soilless cultivation mode as the research object, polarized reflectance spectra and hyperspectral images of different nutrient deficiency greenhouse tomato leaves were acquired by using polarized reflectance spectroscopy system developed by our own research group and hyperspectral imaging system respectively. The relationship between a certain number of changes in the bump and texture of non-smooth surface of the nutrient stress leaf and the level of polarization reflected radiation was clarified by scanning electron microscopy (SEM). On the one hand, the polarization spectrum was converted into the degree of polarization through Stokes equation, and the four polarization characteristics between the polarization spectroscopy and reference measurement values of N, P and K respectively were extracted. On the other hand, the four characteristic wavelengths of N, P, K hyperspectral image data were determined respectively through the principal component analysis, followed by eight hyperspectral texture features extracted corresponding to the four characteristic wavelengths through correlation analysis. Polarization characteristics and hyperspectral texture features combined with each characteristics of N, P, K were extracted. These 12 characteristic variables were normalized by maximum-minimum value method. N, P, K nutrient levels quantitative diagnostic models were established by SVR. Results of models are as follows: the correlation coefficient of nitrogen r = 0.961 8, root mean square error RMSE= 0.451; correlation coefficient of phosphorus r = 0.916 3, root mean square error RMSE = 0.620; correlation coefficient of potassium r = 0.940 6, root mean square error RMSE = 0.494. The results show that high precision tomato leaves nutrition prediction model could be built by using polarized reflectance spectroscopy combined with high spectral information fusion technology and achieve good diagnoses effect. It has a great significance for the improvement of model accuracy and the development of special instruments. The research provides a new idea for the rapid detection of tomato nutrient content.

Hyperspectral Texture Synthesis Using Histogram and Power Spectral Density Matching

Image synthesis tools provide a means for generating hyperspectral image data without the expense of data collection. An important use of these tools is to provide data for the assessment of image exploitation algorithms. However, the detailed spectral/spatial structure of synthetic images is typically not sufficiently realistic to support the prediction of algorithm performance on real data. In this paper, we develop a new method for hyperspectral texture synthesis that accurately simulates the spectral/spatial structure of real hyperspectral image data. The method uses the multiband histogram to model spectral properties and a 3-D Fourier representation to model within-band and cross-band spatial properties. Since multiband histogram equalization does not have a unique solution, we employ a sorting-based method for equalizing multiband distributions that is efficient and produces an exact histogram match. Spatial properties are matched by equalizing the power spectral density (psd) derived from the 3-D Fourier representation. An iterative scheme is used to equalize the histogram and psd for an input and synthesized image. Experiments show that the iteration tends to converge after a small number of steps. A subspace correction method is used to further refine the spectral accuracy of the synthesized image. We demonstrate the utility of the new technique by presenting real and synthesized images and by analyzing spectral angle deviation from the mean functions that describe spectral properties.

THE TEXTURE CODING METHOD OF MULTISPECTRAL DATA BASED ON SPECTRAL SIMILARITY

As the traditional methods of texture extraction can not be adapted to multispectral and hyperspectral data,this paper presents a coding method of multispectral and hyperspectral data based on spectral similarity.With the concept of mapping mode of multispectral and hyperspectral texture,the new algorithm of texture extraction performs coding by the spectral similarity measure so as to reflect the overall objective texture feature.The method extends the algorithm of extracting texture to multidimensional and hyperdimensional spectral image analysis,and gives multiscale texture combination algorithm.Studies show that the coding mapping method of extracting texture is valid and effective.This paper also demonstrates that the texture feature does greatly improve the accuracy and precision of the classification.