Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Image Classification”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 955 records · Page 53
All sourcesNASA NTRSDOE OSTI
NASA NTRS1980

Preliminary results of mapping urban land cover with Seasat SAR imagery

The detectability of urban land cover types is explored using digitally processed Seasat SAR imagery of the Denver, Colorado area. Test sites within the metropolitan area were selected to include a cross section of Anderson, et. al. Level II land cover classes and cover types representative of the urban area growth stages. Using the Image 100 interactive processing system each test site was level sliced in an attempt to define specific reflectance boundaries for each cover type and to determine the spectral and spatial characteristics of homogeneous response regions. The rural-urban fringe boundary was readily definable, but a precise Level I and Level II land cover classification was not possible. High density housing could be separated from low density housing and from parks, but reflectance values were often look angle dependent. Confusion between some water and vegetation responses also posed problems.

Henderson, F. M.↗
NASA NTRS1984

The S201 far-ultraviolet imaging survey. II - A field in Cygnus

Far-ultraviolet imagery of a region in Cygnus, a 20 deg diameter field centered near (1950) R. A. 21 h 31.2 m decl. +37 deg 25 arcmin, was obtained by the S201 far-ultraviolet camera during the Apollo 16 mission. In a 10 minute exposure covering the 1250-1600 A wavelength range (effective wavelength 1400 A), 730 star images can be detected, corresponding to a limiting ultraviolet magnitude of about m (1400) = 10. Assuming nominal interstellar extinction values in this region near the galactic plane, this result corresponds to the detection of A0 V stars to a distance of 300 pc and of B0 V stars to 1500 pc. Uncertainties in spectral classification and interstellar extinction for individual objects are probably more significant than calibration or measurement errors. Most of the objects detected are identified with stars in the Smithsonian Astrophysical Observatory Star Catalog (1966), or the Catalog of Stellar Identifications (1979) or both, but 87 objects remain unidentified (or are identified with late-type stars).

Carruthers, G. R.↗
NASA NTRS1989

Geology of the Venus equatorial region from Pioneer Venus radar imaging

The surface characteristics and morphology of the equatorial region of Venus were first described by Masursky et al. who showed this part of the planet to be characterized by two topographic provinces, rolling plains and highlands, and more recently by Schaber who described and interpreted tectonic zones in the highlands. Using Pioneer Venus (PV) radar image data (15 deg S to 45 deg N), Senske and Head examined the distribution, characteristics, and deposits of individual volcanic features in the equatorial region, and in addition classified major equatorial physiographic and tectonic units on the basis of morphology, topographic signature, and radar properties derived from the PV data. Included in this classification are: plains (undivided), inter-highland tectonic zones, tectonically segmented linear highlands, upland rises, tectonic junctions, dark halo plains, and upland plateaus. In addition to the physiographic units, features interpreted as coronae and volcanic mountains have also been mapped. The latter four of the physiographic units along with features interpreted to be coronae.

Senske, D. A.↗
NASA NTRS2015

A High Performance Computing Approach to Tree Cover Delineation in 1-m NAIP Imagery Using a Probabilistic Learning Framework

Tree cover delineation is a useful instrument in deriving Above Ground Biomass (AGB) density estimates from Very High Resolution (VHR) airborne imagery data. Numerous algorithms have been designed to address this problem, but most of them do not scale to these datasets, which are of the order of terabytes. In this paper, we present a semi-automated probabilistic framework for the segmentation and classification of 1-m National Agriculture Imagery Program (NAIP) for tree-cover delineation for the whole of Continental United States, using a High Performance Computing Architecture. Classification is performed using a multi-layer Feedforward Backpropagation Neural Network and segmentation is performed using a Statistical Region Merging algorithm. The results from the classification and segmentation algorithms are then consolidated into a structured prediction framework using a discriminative undirected probabilistic graphical model based on Conditional Random Field, which helps in capturing the higher order contextual dependencies between neighboring pixels. Once the final probability maps are generated, the framework is updated and re-trained by relabeling misclassified image patches. This leads to a significant improvement in the true positive rates and reduction in false positive rates. The tree cover maps were generated for the whole state of California, spanning a total of 11,095 NAIP tiles covering a total geographical area of 163,696 sq. miles. The framework produced true positive rates of around 88% for fragmented forests and 74% for urban tree cover areas, with false positive rates lower than 2% for both landscapes. Comparative studies with the National Land Cover Data (NLCD) algorithm and the LiDAR canopy height model (CHM) showed the effectiveness of our framework for generating accurate high-resolution tree-cover maps.

Segments↗
NASA NTRS1992

Clustering of noisy image data using an adaptive neuro-fuzzy system

Identification of outliers or noise in a real data set is often quite difficult. A recently developed adaptive fuzzy leader clustering (AFLC) algorithm has been modified to separate the outliers from real data sets while finding the clusters within the data sets. The capability of this modified AFLC algorithm to identify the outliers in a number of real data sets indicates the potential strength of this algorithm in correct classification of noisy real data.

Pemmaraju, Surya↗
NASA NTRS1996

Geostatistical approaches to interpolation and classification of remote-sensing data from ice surfaces

Geostatistical methods for interpolation and extrapolation techniques are used in glaciological data analysis. The results of a program involving the mapping of the Antarctica from satellite radar altimeter data are discussed. A combination of high and low resolution techniques was applied in the analysis of the Bering Glacier (Alaska). The global positioning system (GPS) located video data collected from small aircraft and the ERS-1 synthetic aperture radar (SAR) images were used. From the perspective of SAR data analysis, the Bering Glacier surge was the opportunity to characterize the surface of fast flowing ice and the rapid changes in the surface roughness.

Herzfeld, Ute Christina↗
NASA NTRS1983

Evaluation of areas prepared for planting using LANDSAT data

Three different algorithms (SINGLE-CELL, MAXVER and MEDIA K) were used to automatically interpret data from LANDSAT observations of an area of Ribeirao Preto, Brazil. Photographic transparencies were obtained, projected and visually interpreted. The results show that: (1) the MAXVER algorithm presented a better classification performance; (2) verification of the changes in cultivated areas using data from the three different acquisition dates was possible; (3) the water bodies, degraded lands, urban areas, and fallow fields were frequently mistaken by cultivated soils; and (4) the use of projected photographic transparencies furnished satisfactory results, besides reducing the time spent on the image-100 system.

Parada, N. D. J.↗
NASA NTRS1984

Characteristics of playa deposits as seen on SIR-A, Seasat and Landsat coregistered data

A classification technique currently under development has been applied for the qualitative study of a playa located in Northeastern Algeria using coregistered SIR-A, Seasat and Landsat MSS 7 data. This classification which is texture based can be applied to only single band imagery at this time. The first results are very encouraging and reach conclusions similar to those obtained with more time consuming classifiers. The signature of each class is well expressed for the Landsat picture. Misclasifications occur with the SIR-A or Seasat images.

Rebillard, PH.↗
NASA NTRS1994

A comparison of spectral decorrelation techniques and performance evaluation metrics for a wavelet-based, multispectral data compression algorithm

Future space-based, remote sensing systems will have data transmission requirements that exceed available downlinks necessitating the use of lossy compression techniques for multispectral data. In this paper, we describe several algorithms for lossy compression of multispectral data which combine spectral decorrelation techniques with an adaptive, wavelet-based, image compression algorithm to exploit both spectral and spatial correlation. We compare the performance of several different spectral decorrelation techniques including wavelet transformation in the spectral dimension. The performance of each technique is evaluated at compression ratios ranging from 4:1 to 16:1. Performance measures used are visual examination, conventional distortion measures, and multispectral classification results. We also introduce a family of distortion metrics that are designed to quantify and predict the effect of compression artifacts on multi spectral classification of the reconstructed data.

Matic, Roy M.↗
NASA NTRS1986

Hard X-ray imaging and the relative contribution of thermal and nonthermal emission in flares

The question of whether the impulsive 25 to 100 keV X-ray emission from solar flares is thermal or nonthermal has been a long-standing controversy. Both thermal and nonthermal (beam) models have been developed and applied to the hard X-ray data. It now seems likely that both thermal and nonthermal emission have been observed at hard X-ray energies. The Hinotori classification scheme, for example, is an attempt to associate the thermal-nonthermal characteristics of flare hard X-ray emission with other flare properties. From a theoretical point of view, it is difficult to generate energetic, nonthermal electrons without dumping an equal or greater amount of energy into plasma heating. On the other hand, any impulsive heating process will invariably generate at least some nonthermal particles. Hence, strictly speaking, although thermal or nonthermal emission may dominate the hard X-ray emission in a given energy range for a given flare, there is no such thing as a purely thermal or nonthermal flare mechanism.

Holman, G. D.↗
NASA NTRS1982

Geology and image processing

Digital image processing for geological applications will be integrated with geographic information systems and data base management systems. While multiband data sets from radar and multispectral scanners will make extreme demands on memory, bus and processor architectures, it is expected that array processors and VLSI/VHSIC dedicated function chips will allow the use of fast Fourier transform and classification algorithms. It is anticipted that, as processor power increases, the weakest link of a processing system will become the analyst who uses it. Human engineering of systems is therefore recommended for the most effective utilization of remotely sensed geologic data.

Daily, M.↗
NASA NTRS1987

Imaging radar polarimetry - A status report

The development of imaging radar polarimetry at JPL is considered. Advances in the correlation of polarimetric SAR and in the synthesis of arbitrary polarization are discussed. The capabilities of the polarization workstation are described. Various applications for polarimetric SAR data include: the identification of scatter, the evaluation of scattering theories, the measurement of the roughness of geologic targets, the classification of forest stands, and the characterization of trees within a particular stand. The development and testing of the DC-8 SAR and the SIR-C system are examined.

Held, Daniel N.↗
NASA NTRS1988

Extension of a drought monitoring and vegetation classification methodology to the western Sahel

Biomass of growing vegetation over large semiarid regions can be estimated by digital manipulation of data from the AVHRR on NOAA polar-orbiting satellites. Here, the African Sahel is classified using a methodology which incorporates both the normalized difference and CAUSE procedures for the monitoring of vegetation during drought conditions. Preliminary analysis of color IR photographs taken on Space Shuttle missions indicates that such photographs can be digitized, registered to maps and other images, and utilized to fill temporal gaps in the historical record of data from unmanned satellites.

Mohler, Robert R. J.↗
NASA NTRS2015

Characterization of Apollo Regolith by X-Ray and Electron Microbeam Techniques: An Analog for Future Sample Return Missions

The Apollo missions collected 382 kg of rock and regolith from the Moon; approximately 1/3 of the sample mass collected was regolith. Lunar regolith consists of well mixed rocks, minerals, and glasses less than 1-centimeter n size. The majority of most surface regolith samples were sieved into less than 1, 1-2, 2-4, and 4-10- millimiter size fractions; a portion of most samples was re-served unsieved. The initial characterization and classification of most Apollo regolith particles was done primarily by binocular microscopy. Optical classification of regolith is difficult because (1) the finest fraction of the regolith coats and obscures the textures of the larger particles, and (b) not all lithologies or minerals are uniquely identifiable optically. In recent years, we have begun to use more modern x-ray beam techniques [1-3], coupled with high resolution 3D optical imaging techniques [4] to characterize Apollo and meteorite samples as part of the curation process. These techniques, particularly in concert with SEM imaging of less than 1-millimeter regolith grain mounts, allow for the rapid characterization of the components within a regolith.

Zeigler, Ryan A.↗
NASA NTRS1993

Nuclear and large-scale outflow in NGC 1808

NGC 1808 has been studied via deep broad-band and H-alpha images and longslit spectroscopy around the Na I D and H-alpha lines. In particular, Na I is seen blueshifted in absorption and redshifted in emission, providing incontrovertible proof of outflow. B-R images show that the dust plumes associated with the outflow reach about 3 kpc or more above the plane. The morphology of the outflow is complex. Nuclear emission and absorption line profiles show pronounced blue wings similar to those seen in far-IR luminous galaxies (FIRGs), and indicate nuclear outflow velocities up to 700 km/s. The classification of NGC 1808 as a Seyfert 2 is reviewed and dismissed; rather, on the basis of line profiles and ratios and the presence of the 'superwind', NGC 1808 is probably an example of the FIRG phenomenon.

Phillips, Andrew C.↗
NASA NTRS1992

Adaptive fuzzy leader clustering of complex data sets in pattern recognition

A modular, unsupervised neural network architecture for clustering and classification of complex data sets is presented. The adaptive fuzzy leader clustering (AFLC) architecture is a hybrid neural-fuzzy system that learns on-line in a stable and efficient manner. The initial classification is performed in two stages: a simple competitive stage and a distance metric comparison stage. The cluster prototypes are then incrementally updated by relocating the centroid positions from fuzzy C-means system equations for the centroids and the membership values. The AFLC algorithm is applied to the Anderson Iris data and laser-luminescent fingerprint image data. It is concluded that the AFLC algorithm successfully classifies features extracted from real data, discrete or continuous.

Newton, Scott C.↗
NASA NTRS1993

Optimal band selection for dimensionality reduction of hyperspectral imagery

Hyperspectral images have many bands requiring significant computational power for machine interpretation. During image pre-processing, regions of interest that warrant full examination need to be identified quickly. One technique for speeding up the processing is to use only a small subset of bands to determine the 'interesting' regions. The problem addressed here is how to determine the fewest bands required to achieve a specified performance goal for pixel classification. The band selection problem has been addressed previously Chen et al., Ghassemian et al., Henderson et al., and Kim et al.. Some popular techniques for reducing the dimensionality of a feature space, such as principal components analysis, reduce dimensionality by computing new features that are linear combinations of the original features. However, such approaches require measuring and processing all the available bands before the dimensionality is reduced. Our approach, adapted from previous multidimensional signal analysis research, is simpler and achieves dimensionality reduction by selecting bands. Feature selection algorithms are used to determine which combination of bands has the lowest probability of pixel misclassification. Two elements required by this approach are a choice of objective function and a choice of search strategy.

Stearns, Stephen D.↗
NASA NTRS2004

Lunar and Planetary Science XXXV: Image Processing and Earth Observations

The titles in this section include: 1) Expansion in Geographic Information Services for PIGWAD; 2) Modernization of the Integrated Software for Imagers and Spectrometers; 3) Science-based Region-of-Interest Image Compression; 4) Topographic Analysis with a Stereo Matching Tool Kit; 5) Central Avra Valley Storage and Recovery Project (CAVSARP) Site, Tucson, Arizona: Floodwater and Soil Moisture Investigations with Extraterrestrial Applications; 6) ASE Floodwater Classifier Development for EO-1 HYPERION Imagery; 7) Autonomous Sciencecraft Experiment (ASE) Operations on EO-1 in 2004; 8) Autonomous Vegetation Cover Scene Classification of EO-1 Hyperion Hyperspectral Data; 9) Long-Term Continental Areal Reduction Produced by Tectonic Processes.

Source record↗