Search NASA⌕ Search

SEARCH · Search NASA

Results for “Selective 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 217 records · Page 12

A Deterministic Self-Organizing Map Approach and its Application on Satellite Data based Cloud Type Classification

A self-organizing map (SOM) is a type of competitive artificial neural network, which projects the high dimensional input space of the training samples into a low dimensional space with the topology relations preserved. This makes SOMs supportive of organizing and visualizing complex data sets and have been pervasively used among numerous disciplines with different applications. Notwithstanding its wide applications, the self-organizing map is perplexed by its inherent randomness, which produces dissimilar SOM patterns even when being trained on identical training samples with the same parameters every time, and thus causes usability concerns for other domain practitioners and precludes more potential users from exploring SOM based applications in a broader spectrum. Motivated by this practical concern, we propose a deterministic approach as a supplement to the standard self-organizing map. In accordance with the theoretical design, the experimental results with satellite cloud data demonstrate the effective and efficient organization as well as simplification capabilities of the proposed approach.

Initialization method↗

Impact of Thematic Mapper Sensor Characteristics on Classification Accuracy

A three factor (spectral, spatial, and radiometric resolution), two level (TM and MSS) analysis of variance (ANOVA) approach allowed evaluation of the effects of each factor individually and in all possible combinations. Digital classification accuracy was used as the figure of merit. Nine study sites in Washington, D.C. each of approximately 256 x 256 TM pixels, were randomly selected from the full scene for analysis. These results strongly suggest that the quantization level improvements and the addition of new spectral bands in the visible and middle IR regions (both afforded by the TM sensor design) can result in improved capabilities to accurately delineate land cover categories using a per point Gaussian maximum likelihood classifier. On the other hand, results indicate that the increase in spatial resolution to 30m does not significantly enhance classification accuracy. The spatial result points to an inherent limitation of a per point classifier and to the need to improve data analysis techniques to handle high spatial resolution data.

Williams, D. L.↗

Generating Ground Reference Data for a Global Impervious Surface Survey

We are engaged in a project to produce a 30m impervious cover data set of the entire Earth for the years 2000 and 2010 based on the Landsat Global Land Survey (GLS) data set. The GLS data from Landsat provide an unprecedented opportunity to map global urbanization at this resolution for the first time, with unprecedented detail and accuracy. Moreover, the spatial resolution of Landsat is absolutely essential to accurately resolve urban targets such as buildings, roads and parking lots. Finally, with GLS data available for the 1975, 1990, 2000, and 2005 time periods, and soon for the 2010 period, the land cover/use changes due to urbanization can now be quantified at this spatial scale as well. Our approach works across spatial scales using very high spatial resolution commercial satellite data to both produce and evaluate continental scale products at the 30m spatial resolution of Landsat data. We are developing continental scale training data at 1m or so resolution and aggregating these to 30m for training a regression tree algorithm. Because the quality of the input training data are critical, we have developed an interactive software tool, called HSegLearn, to facilitate the photo-interpretation of high resolution imagery data, such as Quickbird or Ikonos data, into an impervious versus non-impervious map. Previous work has shown that photo-interpretation of high resolution data at 1 meter resolution will generate an accurate 30m resolution ground reference when coarsened to that resolution. Since this process can be very time consuming when using standard clustering classification algorithms, we are looking at image segmentation as a potential avenue to not only improve the training process but also provide a semi-automated approach for generating the ground reference data. HSegLearn takes as its input a hierarchical set of image segmentations produced by the HSeg image segmentation program [1, 2]. HSegLearn lets an analyst specify pixel locations as being either positive or negative examples, and displays a classification of the study area based on these examples. For our study, the positive examples are examples of impervious surfaces and negative examples are examples of non-impervious surfaces. HSegLearn searches the hierarchical segmentation from HSeg for the coarsest level of segmentation at which selected positive example locations do not conflict with negative example locations and labels the image accordingly. The negative example regions are always defined at the finest level of segmentation detail. The resulting classification map can be then further edited at a region object level using the previously developed HSegViewer tool [3]. After providing an overview of the HSeg image segmentation program, we provide a detailed description of the HSegLearn software tool. We then give examples of using HSegLearn to generate ground reference data and conclude with comments on the effectiveness of the HSegLearn tool.

Tilton, James C.↗

Impact of thematic mapper sensor characteristics on classification accuracy

A three factor (spectral, spatial, and radiometric resolution), two level (TM and MSS) analysis of variance (ANOVA) approach allowed evaluation of the effects of each factor individually and in all possible combinations. Digital classification accuracy was used as the figure of merit. Nine study sites in Washington, DC, each of approximately 256 x 256 TM pixels, were randomly selected from the full scene for analysis. These results strongly suggest that the quantization level improvements and the addition of new spectral bands in the visible and middle IR regions (both afforded by the TM sensor design) can result in improved capabilities to accurately delineate land cover categories using a per point Gaussian maximum likelihood classifier. On the other hand, results indicate that the increase in spatial resolution to 30 m does not significantly enhance classification accuracy. The spatial result points to an inherent limitation of a per point classifier and to the need to improve data analysis techniques to handle high spatial resolution data.

Williams, D. L.↗

On the application of multifrequency polarimetric radar observations for sea-ice classification

The use of multifrequency polarimetric radar imagery to enhance the ability to separate different sea-ice types using single-frequency, single-polarization synthetic aperture radar (SAR) data is investigated. Backscatter characteristics of six radiometrically and polarimetrically distinct sea-ice types are selected in an unsupervised range-dependent analysis of multifrequency polarimetric SAR data using the maximum a posteriori (MAP) polarimetric classifier. Maximum ice discrimination is achieved with combined C- and L-band full polarimetry, and collocated passive microwave imagery suggests greater than 90 percent classification accuracy. C-band VV-pol alone achieves only 68 percent relative accuracy because it confuses multiyear and rough compressed first year ice. L-band, relative classification accuracy is 75 percent, 83 percent, and 85 percent, using HH-pol, HH- and VV-combined, or the full polarimetry, respectively. P-band is less accurate. Combinations of two frequencies at a single polarization show the greatest improvement over a single channel.

Rignot, Eric↗

Simulation techniques for estimating error in the classification of normal patterns

Methods of efficiently generating and classifying samples with specified multivariate normal distributions were discussed. Conservative confidence tables for sample sizes are given for selective sampling. Simulation results are compared with classified training data. Techniques for comparing error and separability measure for two normal patterns are investigated and used to display the relationship between the error and the Chernoff bound.

Whitsitt, S. J.↗

Basic forest cover mapping using digitized remote sensor data and automated data processing techniques

Remote sensing equipment and automatic data processing techniques were employed as aids in the institution of improved forest resource management methods. On the basis of automatically calculated statistics derived from manually selected training samples, the feature selection processor of LARSYS selected, upon consideration of various groups of the four available spectral regions, a series of channel combinations whose automatic classification performances (for six cover types, including both deciduous and coniferous forest) were tested, analyzed, and further compared with automatic classification results obtained from digitized color infrared photography.

Coggeshall, M. E.↗

An empirical study of scanner system parameters

The selection of the current combination of parametric values (instantaneous field of view, number and location of spectral bands, signal-to-noise ratio, etc.) of a multispectral scanner is a complex problem due to the strong interrelationship these parameters have with one another. The study was done with the proposed scanner known as Thematic Mapper in mind. Since an adequate theoretical procedure for this problem has apparently not yet been devised, an empirical simulation approach was used with candidate parameter values selected by the heuristic means. The results obtained using a conventional maximum likelihood pixel classifier suggest that although the classification accuracy declines slightly as the IFOV is decreased this is more than made up by an improved mensuration accuracy. Further, the use of a classifier involving both spatial and spectral features shows a very substantial tendency to resist degradation as the signal-to-noise ratio is decreased. And finally, further evidence is provided of the importance of having at least one spectral band in each of the major available portions of the optical spectrum.

Landgrebe, D.↗

Status report: Data management program algorithm evaluation activity at Marshall Space Flight Center

An algorithm evaluation activity was initiated to study the problems associated with image processing by assessing the independent and interdependent effects of registration, compression, and classification techniques on LANDSAT data for several discipline applications. The objective of the activity was to make recommendations on selected applicable image processing algorithms in terms of accuracy, cost, and timeliness or to propose alternative ways of processing the data. As a means of accomplishing this objective, an Image Coding Panel was established. The conduct of the algorithm evaluation is described.

Jayroe, R. R., Jr.↗

Studies of BL Lacertae objects with the Einstein X-ray observatory - The absolute volume density

It is estimated that the local volume density of BL Lac objects which emit greater than 10 to the 44th ergs/s in the 0.5-4.5 keV band is about 10 to the -7th/cu Mpc. This is based on identifications of bright X-ray sources, and the fact that Einstein X-ray observations detect BL Lac objects over a wide, continuous range of flux up to the thresholds of the all-sky X-ray surveys. Since this density is of the same order of magnitude as the local density of Seyfert galaxies, or local density of optically selected quasars, emitting X-rays at the same luminosity, we argue that the difference between these particular astronomical classifications is not solely due to the orientation of a relativistic beam.

Schwartz, D. A.↗

Mapping land use changes in the carboniferous region of Santa Catarina, report 2

The techniques applied to MSS-LANDSAT data in the land-use mapping of Criciuma region (Santa Catarina state, Brazil) are presented along with the results of a classification accuracy estimate tested on the resulting map. The MSS-LANDSAT data digital processing involves noise suppression, features selection and a hybrid classifier. The accuracy test is made through comparisons with aerial photographs of sampled points. The utilization of digital processing to map the classes agricultural lands, forest lands and urban areas is recommended, while the coal refuse areas should be mapped visually.

Valeriano, D. D.↗

Identification of USSR Indicator Regions

Potential indicator regions were determined by comparing the statistics for barley and wheat at the lowest administrative levels for which published statistics were available. Fourteen were selected for review based on their relative abundances of wheat and barely. These potential indicator regions were grouped according to three conditions that could affect labeling and classification accuracies: (1) high-barley content; (2) presence of barley and spring wheat; and (3) presence of barley and winter wheat. Each region was further evaluated based on the availability of crop calendars, LANDSAT acquisitions, and ancillary data. Based on the relative abundance of wheat and barley and the availability of data, three indicator regions were recommended. Within each region, individual oblasts and/or krays were selected according to segment availability and segment acquisition histories for potential barley separation.

Disler, J.↗

Europa Luminescence Microscope

The Europa Luminescence Microscope (ELM) is an automated fluorescence and dark-field mi-croscope designed to meet key objectives defined in the NASA Europa Lander Study Report, includ-ing the identification and characterization of morphological biosignatures. ELM’s heritage stems from a 2U cubesat fluorescence microscope, the Fluorescence Analysis for In-situ Research (FLAIR) im-ager, designed and built at NASA Ames Research Center, for the autonomous study of microbial bi-ology in low Earth orbit. For the ELM implementation, a sample is autonomously manipulated with a microfluidic system using in-line filter sets to capture successively smaller particles on 10, 1.0, and 0.1 µm pore-size filters for imaging. For darkfield imaging, ELM uses ultraviolet and visible light to image organic and inorganic structures with submicron resolution. The ability to detect structural and chemical biosignatures as small as 0.2 µm in size is achieved by imaging native fluorescence and us-ing fluorescence microscopy stains to identify key molecular and structural indicators of microbial life (proteins, lipids, nucleic acids). To excite fluorescence, ELM uses LEDs with wavelengths centered near 265, 370, 470, and 530 nm and five emission bands. The use of multiple excitation and emission wavelengths for native fluorescence imaging not only enables the detection of different molecular species, but also their rough classification. Excitation at 265 nm allows for the detection of smaller polyaromatic hydrocarbons (PAHs; 1-5 rings), aromatic amino acids, and proteins with little to no interference from mineral fluorescence, given proper emission band selection. 370 and 470 nm light excites increasingly larger PAH structures (e.g., coronene) and larger aromatic biomolecules that may be present (e.g., protective pigments). Similarly, inorganic fluorescence can be characterized and sep-arated from organic fluorescence, allowing the recognition and in some cases classification, of miner-als and other abiotic particles. ELM is based upon work supported by the NASA COLDTech and ICEE-2 programs.

Microscope↗

Use of Land Use Land Cover Change Mapping Products in Aiding Coastal Habitat Conservation and Restoration Efforts of the Mobile Bay NEP

The Mobile Bay region has undergone significant land use land cover change (LULC) over the last 35 years, much of which is associated with urbanization. These changes have impacted the region s water quality and wildlife habitat availability. In addition, much of the region is low-lying and close to the Gulf, which makes the region vulnerable to hurricanes, climate change (e.g., sea level rise), and sometimes man-made disasters such as the Deepwater Horizon (DWH) oil spill. Land use land cover change information is needed to help coastal zone managers and planners to understand and mitigate the impacts of environmental change on the region. This presentation discusses selective results of a current NASA-funded project in which Landsat data over a 34-year period (1974-2008) is used to produce, validate, refine, and apply land use land cover change products to aid coastal habitat conservation and restoration needs of the Mobile Bay National Estuary Program (MB NEP). The project employed a user defined classification scheme to compute LULC change mapping products for the entire region, which includes the majority of Mobile and Baldwin counties. Additional LULC change products have been computed for select coastal HUC-12 sub-watersheds adjacent to either Mobile Bay or the Gulf of Mexico, as part of the MB NEP watershed profile assessments. This presentation will include results of additional analyses of LULC change for sub-watersheds that are currently high priority areas, as defined by MB NEP. Such priority sub-watersheds include those that are vulnerable to impacts from the DWH oil spill, as well as sub-watersheds undergoing urbanization. Results demonstrating the nature and permanence of LULC change trends for these higher priority sub-watersheds and results characterizing change for the entire 34-year period and at approximate 10-year intervals across this period will also be presented. Future work will include development of value-added coastal habitat quality assessment products that will be used by the MB NEP and its partners in the planning of coastal conservation and restoration activities.

Spruce, Joseph P.↗

Aircraft Fault Detection and Classification Using Multi-Level Immune Learning Detection

This work is an extension of a recently developed software tool called MILD (Multi-level Immune Learning Detection), which implements a negative selection algorithm for anomaly and fault detection that is inspired by the human immune system. The immunity-based approach can detect a broad spectrum of known and unforeseen faults. We extend MILD by applying a neural network classifier to identify the pattern of fault detectors that are activated during fault detection. Consequently, MILD now performs fault detection and identification of the system under investigation. This paper describes the application of MILD to detect and classify faults of a generic transport aircraft augmented with an intelligent flight controller. The intelligent control architecture is designed to accommodate faults without the need to explicitly identify them. Adding knowledge about the existence and type of a fault will improve the handling qualities of a degraded aircraft and impact tactical and strategic maneuvering decisions. In addition, providing fault information to the pilot is important for maintaining situational awareness so that he can avoid performing an action that might lead to unexpected behavior - e.g., an action that exceeds the remaining control authority of the damaged aircraft. We discuss the detection and classification results of simulated failures of the aircraft's control system and show that MILD is effective at determining the problem with low false alarm and misclassification rates.

Wong, Derek↗

Antarctic Meteorite Classification and Petrographic Database

The Antarctic Meteorite collection, which is comprised of over 18,700 meteorites, is one of the largest collections of meteorites in the world. These meteorites have been collected since the late 1970's as part of a three-agency agreement between NASA, the National Science Foundation, and the Smithsonian Institution [1]. Samples collected each season are analyzed at NASA s Meteorite Lab and the Smithsonian Institution and results are published twice a year in the Antarctic Meteorite Newsletter, which has been in publication since 1978. Each newsletter lists the samples collected and processed and provides more in-depth details on selected samples of importance to the scientific community. Data about these meteorites is also published on the NASA Curation website [2] and made available through the Meteorite Classification Database allowing scientists to search by a variety of parameters

Todd, Nancy S.↗

Antarctic Meteorite Classification and Petrographic Database Enhancements

The Antarctic Meteorite collection, which is comprised of over 18,700 meteorites, is one of the largest collections of meteorites in the world. These meteorites have been collected since the late 1970 s as part of a three-agency agreement between NASA, the National Science Foundation, and the Smithsonian Institution [1]. Samples collected each season are analyzed at NASA s Meteorite Lab and the Smithsonian Institution and results are published twice a year in the Antarctic Meteorite Newsletter, which has been in publication since 1978. Each newsletter lists the samples collected and processed and provides more in-depth details on selected samples of importance to the scientific community. Data about these meteorites is also published on the NASA Curation website [2] and made available through the Meteorite Classification Database allowing scientists to search by a variety of parameters. This paper describes enhancements that have been made to the database and to the data and photo acquisition process to provide the meteorite community with faster access to meteorite data concurrent with the publication of the Antarctic Meteorite Newsletter twice a year.

Todd, N. S.↗

LACIE performance predictor FOC users manual

The LACIE Performance Predictor (LPP) is a computer simulation of the LACIE process for predicting worldwide wheat production. The simulation provides for the introduction of various errors into the system and provides estimates based on these errors, thus allowing the user to determine the impact of selected error sources. The FOC LPP simulates the acquisition of the sample segment data by the LANDSAT Satellite (DAPTS), the classification of the agricultural area within the sample segment (CAMS), the estimation of the wheat yield (YES), and the production estimation and aggregation (CAS). These elements include data acquisition characteristics, environmental conditions, classification algorithms, the LACIE aggregation and data adjustment procedures. The operational structure for simulating these elements consists of the following key programs: (1) LACIE Utility Maintenance Process, (2) System Error Executive, (3) Ephemeris Generator, (4) Access Generator, (5) Acquisition Selector, (6) LACIE Error Model (LEM), and (7) Post Processor.

Source record↗