Quantitative analysis of facies variation using ground-based lidar and hyperspectral imaging in Mississippian limestone outcrop near Jane, Missouri

2020 ◽  
Vol 8 (2) ◽  
pp. T365-T378
Author(s):  
Aydin Shahtakhtinskiy ◽  
Shuhab Khan
Keyword(s):  
Hyperspectral Imaging ◽  
Laser Scanner ◽  
Hyperspectral Data ◽  
Geologic Mapping ◽  
Sea Level Fluctuations ◽  
Close Range ◽  
Compositional Variations ◽  
Ground Based Lidar ◽  
Facies Variation ◽  
Mississippian Limestone

Ground-based hyperspectral imaging is useful for geologic mapping because of its high spectral and spatial resolutions at a millimeter to centimeter scale. We have used hyperspectral and terrestrial laser scanner (TLS) data collected in close range to a roadcut near Jane, Missouri, that contains a subvertical outcrop of Lower Mississippian limestone. The outcrop consists of the Compton, Northview, and Pierson Formations, which we evaluated for facies heterogeneity. The sequence near Jane, Missouri, was deposited in shelf margin with high-frequency sea-level fluctuations. These fluctuations introduced lithologic and geometric heterogeneity to the facies, and debris flows brought in carbonate mounds referred to as outrunner blocks. These are important to interpret accurately because of their equivocal depositional origin, which is highly debated by previous workers. We combined hyperspectral data with TLS for an integrated spatial analysis of geometric and compositional variations in facies by accurate, point cloud-registered mineralogical mapping. We mapped several carbonate facies based on spectral signatures of calcite, silt, and clay particles and distinguished pure limestone outrunner blocks from surrounding mud-prone limestone facies with various proportions of silt and clay (a total of approximately 60%). By tracing the classified facies from combined hyperspectral and TLS imagery, we produced a lithostratigraphic framework, which indicates rapid changes in lithology and the presence of shale baffles that vary the character of the Compton through Pierson interval and contribute to heterogeneity in this outcrop. The data suggest a lower energy depositional environment and support the hypothesis of transported outrunner blocks in a distally steepened ramp system. The information that we have evaluated in our study could help to explain reservoir heterogeneity in equivalent carbonate fields.

scholarly journals Multimodal Deep Learning and Visible-Light and Hyperspectral Imaging for Fruit Maturity Estimation

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1288
Author(s):  
Cinmayii A. Garillos-Manliguez ◽  
John Y. Chiang
Keyword(s):  
Deep Learning ◽  
Visible Light ◽  
Hyperspectral Imaging ◽  
Morphological Changes ◽  
Consumer Preference ◽  
Hyperspectral Data ◽  
Sensitivity Analyses ◽  
Deep Convolutional Neural Networks ◽  
Fruit Maturity ◽  
Learning Architectures

Fruit maturity is a critical factor in the supply chain, consumer preference, and agriculture industry. Most classification methods on fruit maturity identify only two classes: ripe and unripe, but this paper estimates six maturity stages of papaya fruit. Deep learning architectures have gained respect and brought breakthroughs in unimodal processing. This paper suggests a novel non-destructive and multimodal classification using deep convolutional neural networks that estimate fruit maturity by feature concatenation of data acquired from two imaging modes: visible-light and hyperspectral imaging systems. Morphological changes in the sample fruits can be easily measured with RGB images, while spectral signatures that provide high sensitivity and high correlation with the internal properties of fruits can be extracted from hyperspectral images with wavelength range in between 400 nm and 900 nm—factors that must be considered when building a model. This study further modified the architectures: AlexNet, VGG16, VGG19, ResNet50, ResNeXt50, MobileNet, and MobileNetV2 to utilize multimodal data cubes composed of RGB and hyperspectral data for sensitivity analyses. These multimodal variants can achieve up to 0.90 F1 scores and 1.45% top-2 error rate for the classification of six stages. Overall, taking advantage of multimodal input coupled with powerful deep convolutional neural network models can classify fruit maturity even at refined levels of six stages. This indicates that multimodal deep learning architectures and multimodal imaging have great potential for real-time in-field fruit maturity estimation that can help estimate optimal harvest time and other in-field industrial applications.

scholarly journals Prediction of Sugar Content in Port Wine Vintage Grapes Using Machine Learning and Hyperspectral Imaging

Processes ◽  
2021 ◽  
Vol 9 (7) ◽  
pp. 1241
Author(s):  
Véronique Gomes ◽  
Marco S. Reis ◽  
Francisco Rovira-Más ◽  
Ana Mendes-Ferreira ◽  
Pedro Melo-Pinto
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Hyperspectral Imaging ◽  
Sugar Content ◽  
Hyperspectral Data ◽  
Machine Learning Algorithms ◽  
Port Wine ◽  
Monitoring And Control ◽  
High Quality ◽  
Harvesting Stage

The high quality of Port wine is the result of a sequence of winemaking operations, such as harvesting, maceration, fermentation, extraction and aging. These stages require proper monitoring and control, in order to consistently achieve the desired wine properties. The present work focuses on the harvesting stage, where the sugar content of grapes plays a key role as one of the critical maturity parameters. Our approach makes use of hyperspectral imaging technology to rapidly extract information from wine grape berries; the collected spectra are fed to machine learning algorithms that produce estimates of the sugar level. A consistent predictive capability is important for establishing the harvest date, as well as to select the best grapes to produce specific high-quality wines. We compared four different machine learning methods (including deep learning), assessing their generalization capacity for different vintages and varieties not included in the training process. Ridge regression, partial least squares, neural networks and convolutional neural networks were the methods considered to conduct this comparison. The results show that the estimated models can successfully predict the sugar content from hyperspectral data, with the convolutional neural network outperforming the other methods.

scholarly journals Characterization of Pharmaceutical Tablets Using UV Hyperspectral Imaging as a Rapid Line to Line Analysis Tool

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4436
Author(s):  
Mohammad Al Ktash ◽  
Mona Stefanakis ◽  
Barbara Boldrini ◽  
Edwin Ostertag ◽  
Marc Brecht
Keyword(s):  
Hyperspectral Imaging ◽  
Large Scale ◽  
Solid Phase ◽  
Ultra Violet ◽  
Principal Component ◽  
Ccd Camera ◽  
Conveyor Belt ◽  
Hyperspectral Data ◽  
Analysis Tool ◽  
Sample Set

A laboratory prototype for hyperspectral imaging in ultra-violet (UV) region from 225 to 400 nm was developed and used to rapidly characterize active pharmaceutical ingredients (API) in tablets. The APIs are ibuprofen (IBU), acetylsalicylic acid (ASA) and paracetamol (PAR). Two sample sets were used for a comparison purpose. Sample set one comprises tablets of 100% API and sample set two consists of commercially available painkiller tablets. Reference measurements were performed on the pure APIs in liquid solutions (transmission) and in solid phase (reflection) using a commercial UV spectrometer. The spectroscopic part of the prototype is based on a pushbroom imager that contains a spectrograph and charge-coupled device (CCD) camera. The tablets were scanned on a conveyor belt that is positioned inside a tunnel made of polytetrafluoroethylene (PTFE) in order to increase the homogeneity of illumination at the sample position. Principal component analysis (PCA) was used to differentiate the hyperspectral data of the drug samples. The first two PCs are sufficient to completely separate all samples. The rugged design of the prototype opens new possibilities for further development of this technique towards real large-scale application.

scholarly journals INFORMATION EXTRACTION IN TOMB PIT USING HYPERSPECTRAL DATA

2018 ◽  
Vol XLII-3 ◽  
pp. 2107-2111
Author(s):  
X. Yang ◽  
M. Hou ◽  
S. Lyu ◽  
S. Ma ◽  
Z. Gao ◽  
...  
Keyword(s):  
Hyperspectral Imaging ◽  
Visual Experience ◽  
Hyperspectral Data ◽  
Shanxi Province ◽  
Bottom Surface ◽  
Archaeological Research ◽  
Reference Images ◽  
Research Findings ◽  
And Storage ◽  
Non Destructive

Hyperspectral data has characteristics of multiple bands and continuous, large amount of data, redundancy, and non-destructive. These characteristics make it possible to use hyperspectral data to study cultural relics. In this paper, the hyperspectral imaging technology is adopted to recognize the bottom images of an ancient tomb located in Shanxi province. There are many black remains on the bottom surface of the tomb, which are suspected to be some meaningful texts or paintings. Firstly, the hyperspectral data is preprocessing to get the reflectance of the region of interesting. For the convenient of compute and storage, the original reflectance value is multiplied by 10000. Secondly, this article uses three methods to extract the symbols at the bottom of the ancient tomb. Finally we tried to use morphology to connect the symbols and gave fifteen reference images. The results show that the extraction of information based on hyperspectral data can obtain a better visual experience, which is beneficial to the study of ancient tombs by researchers, and provides some references for archaeological research findings.

scholarly journals THE FACADE’S DOME OF THE ST. ANTHONY’S BASILICA IN PADUA

2019 ◽  
Vol XLII-2/W11 ◽  
pp. 481-487 ◽  
Author(s):  
M. Diaz ◽  
S. M. Holzer
Keyword(s):  
Data Processing ◽  
Laser Scanning ◽  
Laser Scanner ◽  
Complex Structures ◽  
Modus Operandi ◽  
Time Consumption ◽  
Stratigraphic Analysis ◽  
Entire Structure ◽  
Close Range ◽  
Human Effort

<p><strong>Abstract.</strong> The basilica of St. Anthony in Padua (13th–14th cent.) is one of the most remarkable pilgrimage sites in Italy. To date, the monument itself has never been subject to a comprehensive stratigraphic analysis. Important information about the construction sequence of the building may be conserved in the domed roofs protecting the inner masonry shells.</p><p>The present paper will focus on the dome next to the facade. During the survey, data acquisition via laser scanner have been flanked by standard tasks. Specifically, the stratification analysis of the timber framework of the dome requires to measure the entire structure, including parts with difficult access, and calls for many scan bases to go further the sight obstacles represented by the rafters and the horizontal collar-beams. Therefore, application of laser scanning might appear difficult at first sight.</p><p>The authors will show that the approach confirms the suitability of the laser scanner technology in facing the general complexity of the structure. The development of a graphic documentation in CAD environment entailed a manageable complexity in terms of time-consumption and precision in data processing. So far, the plans reveal the irregular profile of the dome in its inner masonry shell, and of the outer masonry drum. The sections show a two-centre curvature of the elevation of the outer timber shell. However, the joints among the rafters, ribs, and tie-beams still require a series of traditional in-depth assessments acquired in close-range access.</p><p>Nevertheless, the pragmatic investigative modus operandi, tested up to now, does represent a fixed protocol suitable to be iterated and perfected for each cupola. In such complex structures, the laser scanning process confirms to be a valid strategy to reach a good compromise between time consumption, human effort, and millimetre precision. In this way, the collected material provides a first contribution to acquire knowledge on this Italian medieval masterpiece, which stands out on the international scenario for its historical richness and architectural complexity.</p>

scholarly journals Terrestrial Laser Scanning and Settled Techniques: A Support to Detect Pathologies and Safety Conditions of Timber Structures

2013 ◽  
Vol 778 ◽  
pp. 350-357 ◽  
Author(s):  
Clara Bertolini-Cestari ◽  
Filiberto Chiabrando ◽  
Stefano Invernizzi ◽  
Tanja Marzi ◽  
Antonia Spanò
Keyword(s):  
Laser Scanning ◽  
Planning Process ◽  
Laser Scanner ◽  
Texture Mapping ◽  
Surface Model ◽  
Resolution Model ◽  
Close Range ◽  
High Resolution Model ◽  
Increasing Demand ◽  
Non Destructive

Nowadays, there is an increasing demand for detailed geometrical representation of the existing cultural heritage, in particular to improve the comprehension of interactions between different phenomena and to allow a better decisional and planning process. The LiDAR technology (Light Detection and Ranging) can be adopted in different fields, ranging from aerial applications to mobile and terrestrial mapping systems. One of the main target of this study is to propose an integration of innovative and settled inquiring techniques, ranging from the reading of the technological system, to non-destructive tools for diagnosis and 3D metric modeling of buildings heritage. Many inquiring techniques, including Terrestrial Laser Scanner (TLS) method, have been exploited to study the main room of the Valentino Castle in Torino. The so-called “Salone delle Feste”, conceived in the XVIIth century under the guidance of Carlo di Castellamonte, has been selected as a test area. The beautiful frescos and stuccoes of the domical vault are sustained by a typical Delorme carpentry, whose span is among the largest of their kind. The dome suffered from degradation during the years, and a series of interventions were put into place. A survey has revealed that the suspender cables above the vault in the region close to the abutments have lost their tension. This may indicate an increase of the vault deformation; therefore a structural assessment of the dome is mandatory. The high detailed metric survey, carried out with integrated laser scanning and digital close range photogrammetry, reinforced the structural hypothesis of damages and revealed the deformation effects. In addition, the correlation between the survey-model of the intrados and of the extrados allowed a non-destructive and extensive determination of the dome thickness. The photogram-metrical survey of frescos, with the re-projection of images on vault surface model (texture mapping), is purposed to exactly localize formers restoration and their signs on frescos continuity. The present paper illustrates the generation of the 3D high-resolution model and its relations with the results of the structural survey; both of them support the Finite Element numerical simulation of the dome.

scholarly journals Drought Stress Detection in Juvenile Oilseed Rape Using Hyperspectral Imaging with a Focus on Spectra Variability

2020 ◽  
Vol 12 (20) ◽  
pp. 3462
Author(s):  
Wiktor R. Żelazny ◽  
Jan Lukáš
Keyword(s):  
Drought Stress ◽  
Hyperspectral Imaging ◽  
Oilseed Rape ◽  
Treatment Effects ◽  
Vegetation Index ◽  
Principal Component ◽  
Hyperspectral Data ◽  
Stress Detection ◽  
Mean Values ◽  
Standard Deviations

Hyperspectral imaging (HSI) has been gaining recognition as a promising proximal and remote sensing technique for crop drought stress detection. A modelling approach accounting for the treatment effects on the stress indicators’ standard deviations was applied to proximal images of oilseed rape—a crop subjected to various HSI studies, with the exception of drought. The aim of the present study was to determine the spectral responses of two cultivars, ‘Cadeli’ and ‘Viking’, representing distinctive water management strategies, to three types of watering regimes. Hyperspectral data cubes were acquired at the leaf level using a 2D frame camera. The influence of the experimental factors on the extent of leaf discolorations, vegetation index values, and principal component scores was investigated using Bayesian linear models. Clear treatment effects were obtained primarily for the vegetation indexes with respect to the watering regimes. The mean values of RGI, MTCI, RNDVI, and GI responded to the difference between the well-watered and water-deprived plants. The RGI index excelled among them in terms of effect strengths, which amounted to −0.96[−2.21,0.21] and −0.71[−1.97,0.49] units for each cultivar. A consistent increase in the multiple index standard deviations, especially RGI, PSRI, TCARI, and TCARI/OSAVI, was associated with worsening of the hydric regime. These increases were captured not only for the dry treatment but also for the plants subjected to regeneration after a drought episode, particularly by PSRI (a multiplicative effect of 0.33[0.16,0.68] for ‘Cadeli’). This result suggests a higher sensitivity of the vegetation index variability measures relative to the means in the context of the oilseed rape drought stress diagnosis and justifies the application of HSI to capture these effects. RGI is an index deserving additional scrutiny in future studies, as both its mean and standard deviation were affected by the watering regimes.

scholarly journals Hyperspectral Image Classification Using Parallel Autoencoding Diabolo Networks on Multi-Core and Many-Core Architectures

Electronics ◽  
2018 ◽  
Vol 7 (12) ◽  
pp. 411 ◽  
Author(s):  
Emanuele Torti ◽  
Alessandro Fontanella ◽  
Antonio Plaza ◽  
Javier Plaza ◽  
Francesco Leporati
Keyword(s):  
Deep Learning ◽  
Hyperspectral Imaging ◽  
Hyperspectral Image ◽  
Unsupervised Classification ◽  
Hyperspectral Data ◽  
Machine Learning Techniques ◽  
High Data ◽  
Learning Techniques ◽  
Speed Up ◽  
Many Core

One of the most important tasks in hyperspectral imaging is the classification of the pixels in the scene in order to produce thematic maps. This problem can be typically solved through machine learning techniques. In particular, deep learning algorithms have emerged in recent years as a suitable methodology to classify hyperspectral data. Moreover, the high dimensionality of hyperspectral data, together with the increasing availability of unlabeled samples, makes deep learning an appealing approach to process and interpret those data. However, the limited number of labeled samples often complicates the exploitation of supervised techniques. Indeed, in order to guarantee a suitable precision, a large number of labeled samples is normally required. This hurdle can be overcome by resorting to unsupervised classification algorithms. In particular, autoencoders can be used to analyze a hyperspectral image using only unlabeled data. However, the high data dimensionality leads to prohibitive training times. In this regard, it is important to realize that the operations involved in autoencoders training are intrinsically parallel. Therefore, in this paper we present an approach that exploits multi-core and many-core devices in order to achieve efficient autoencoders training in hyperspectral imaging applications. Specifically, in this paper, we present new OpenMP and CUDA frameworks for autoencoder training. The obtained results show that the CUDA framework provides a speed-up of about two orders of magnitudes as compared to an optimized serial processing chain.

Sign in / Sign up

Export Citation Format

Share Document