Search NASA⌕ Search

SEARCH · Search NASA

Results for “classifiers”

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 307 records · Page 17
All sourcesNASA NTRSDOE OSTI
NASA NTRS1975

Water quality indicators obtainable from aircraft and Landsat images and their use in classifying lakes

Equations describing the interaction of sunlight and skylight with the surface of a lake, particles in the water to the depth where light is extinguished, and lake bottom are presented, and the use of aircraft and Landsat images to derive water quality indicators on the basis of these interactions is discussed. A very clear, deep lake with a backscatter signal similar to that of distilled water is used as a reference standard. The degree of turbidity of other target lakes is determined by comparing their residual radiance with the clear lake standard and with the residual radiance of a lake whose turbidity has been determined from water samples. The relative and absolute strengths of residual radiance are used to determine the type and concentration of suspended material, respectively. Oil slicks are characterized by an increased specular reflectance component, decreased signal from the underlying water, and added backscatter signal from the oil volume.

Scherz, J. P.↗
NASA NTRS1976

Classifying and monitoring water quality by use of satellite imagery

A technique is developed to eliminate the atmosphere and surface noise effects on Landsat signals of water bodies by manipulating the total signal from Landsat in such a way that only the volume reflectance is left as a residual. With the Landsat signal from a lake and the known volume reflectance for its clear water it is possible to eliminate the surface and atmospheric effects and have residual signals that are indicative only of the type and concentration of the material in other lakes. Laboratory values are more precise than field values because in the field one must contend with indirect skylight and wave action which can be removed in the laboratory. The volume reflectance of distilled water or a very clear lake approaching distilled water was determined in the laboratory by the use of the Bendix radiant power measuring instrument. The Bendix multispectral data analysis system provided a color categorized image of several hundred lakes in a Wisconsin area. These lakes were categorized for tannin and nontannin waters and for the degrees of algae, silt, weeds, and bottom effects present.

Scherz, J. P.↗
NASA NTRS1975

The use of unsupervised clustering as a classifier for LACIE MSS data

The author has identified the following significant results. This classification method appears to give accurate field center results and to give practical, statistically consistent and accurate estimates of crop proportions. The accuracy of this method is attributable to certain qualities of the particular clustering algorithm. These qualities are freedom from assumptions about Gaussian data, and the continual updating of distribution estimates, including updating the number of modes. This method is relatively tolerant of errors in the determination of crop type, as crop identity is used only for identifying clusters, and not for computing signatures.

Pentland, A. P.↗
NASA NTRS1977

Test of spectral/spatial classifier

The author has identified the following significant results. The supervised ECHO processor (which utilizes class statistics for object identification) successfully exploits the redundancy of states characteristic of sampled imagery of ground scenes to achieve better classification accuracy, reduce the number of classifications required, and reduce the variability of classification results. The nonsupervised ECHO processor (which identifies objects without the benefit of class statistics) successfully reduces the number of classifications required and the variability of the classification results.

Landgrebe, D. A.↗
NASA NTRS1979

Evaluation of three techniques for classifying urban land cover patterns using LANDSAT MSS data

Three computer quantitative techniques for determining urban land cover patterns are evaluated. The techniques examined deal with the selection of training samples by an automated process, the overlaying of two scenes from different seasons of the year, and the use of individual pixels as training points. Evaluation is based on the number and type of land cover classes generated and the marks obtained from an accuracy test. New Orleans, Louisiana and its environs form the study area.

Baumann, P. R.↗
NASA NTRS1980

Computer classified Landsat data used as a forest stratifier

Results of two forest stratification projects are presented to show that Landsat data, when combined with guided clustering techniques, can provide detailed stratification of forest environment. It is shown that conifer species groupings, vegetative cover classes, and three size classes can be discriminated with accuracies ranging from 83 to 91%.

Fox, L., III↗
NASA NTRS1983

Classifying Particles By Acoustic Levitation

Separation technique well suited to material processing. Apparatus with rectangular-cross-section chamber used to measure equilibrium positions of low-density spheres in gravitational field. Vertical acoustic forces generated by two opposing compression drivers exciting fundamental plane-wave mode at 1.2 kHz. Additional horizontal drivers centered samples along vertical axis. Applications in fusion-target separation, biological separation, and manufacturing processes in liquid or gas media.

Barmatz, Martin B.↗
NASA NTRS1982

The evaluation of a semi-automated procedure for classifying corn and soybeans without ground data

Since the launch of Landsat 1 in 1973, research has been conducted with the objective to develop technology which would make it possible to achieve large area crop estimates on the basis of Landsat Multispectral Sensor (MSS) data without the benefit of ground observed training data. The present investigation is concerned with the evaluation of a technology which was developed to produce estimates of corn and soybean acreage in the central U.S. Corn Belt (Iowa, Illinois, and Indiana). A description of the employed technique is provided and details regarding the test of the developed technology are discussed. The obtained results show that considerable progress has been made toward creating an automatic, self-adapting procedure which has favorable bias and variance characteristics.

Metzler, M. D.↗
NASA NTRS1984

Classifying northern forests using Thematic Mapper Simulator data

Thematic Mapper Simulator data were collected over a 23,200 hectare forested area near Baxter State Park in north-central Maine. Photointerpreted ground reference information was used to drive a stratified random sampling procedure for waveband discriminant analyses and to generate training statistics and test pixel accuracies. Stepwise discriminant analyses indicated that the following bands best differentiated the thirteen level II - III cover types (in order of entry): near infrared (0.77 to 0.90 micron), blue (0.46 0.52 micron), first middle infrared (1.53 to 1.73 microns), second middle infrared (2.06 to 2.33 microsn), red (0.63 to 0.69 micron), thermal (10.32 to 12.33 microns). Classification accuracies peaked at 58 percent for thirteen level II-III land-cover classes and at 65 percent for ten level II classes.

Nelson, R. F.↗
NASA NTRS1986

Secure Disposal Container for Classified Papers

Meshing steel combs retain papers when container overturned. Comblike shutters installed on hinges near deflectors. If container is upright, combs hang vertically and out of way. When container is tipped or overturned, gravity forces one or both of combs to fall over opening. When this happens, teeth intermesh and container opening covered, preventing its contents from falling out.

Collins, Earl R., Jr.↗
NASA NTRS1989

Optical neural net for classifying imaging spectrometer data

The problem of determining the composition of an unknown input mixture from its measured spectrum, given the spectra of a number of elements, is studied. The Hopfield minimization procedure was used to express the determination of the compositions as a problem suitable for solution by neural nets. A mathematical description of the problem was developed and used as a basis for a neural network solution and an optical implementation.

Barnard, Etienne↗