Image detection through bipolar correlation
Image detection in pattern recognition through bipolar correlation, discussing reference generating algorithms and digital simulation results
Arcese, A.↗
SEARCH · Search NASA
Results for “Pattern Recognition”
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.
Soil photographic mapping Periodic report, 1 Jan. - 30 Jun. 1970
Pattern recognition and soil mapping for soil classification by remote sensors
Source record↗
Preliminary design of an automatic device for the location of the pole star and/or true pole of Mars
Automatic pattern recognition system to locate Martian pole star for unmanned surface vehicle navigation
Rieback, D. J.↗
A linguistic approach to telemetry decommutation
Telemetry decommutation system using linguistic and statistical methods in pattern recognition
Kulick, J. H.↗
Holographic data processing
Holography utilization to data processing, discussing factors affecting recording and matched filters creation for pattern recognition
Jenkins, R. W.↗
Skylab earth resources experiment package
Skylab earth resources experimental equipment, describing sensing and recording instrumentation for electromagnetic spectral pattern recognition studies
Armitage, P. J.↗
Crop surveys from multiband satellite photography using digital techniques
Crop surveys from multiband and multibase satellite photography during Apollo 9 mission, using statistical multispectral pattern recognition digital techniques
Anuta, P. E.↗
The applications of remote sensing to corn blight detection and crop yield forecasting
Photography revealed the widespread and variable effects of southern corn leaf blight in Indiana. Three levels of severity of the infection could be discerned from good quality color and color infrared photography. As many as five severity levels appeared to be detectable and classifiable with multispectral scanner data and pattern recognition analysis. These conclusions are preliminary in nature, however, having been obtained from a limited amount of good quality scanner data collected over a small geographic area.
Macdonald, R. B.↗
Interactive display/graphics systems for remote sensor data analysis
A color-television display system and interactive graphics equipment on-line to an IBM 360/44 computer are used to develop a variety of interactive displays which aid in analyzing remote sensor data. These interactive displays are used to: (1) analyze data from a multispectral scanner; (2) develop automatic pattern recognition systems based on multispectral scanner measurements; and (3) analyze data from non-imaging sensors such as the infrared radiometer and microwave scatterometer.
Eppler, W. G.↗
Crime prediction modeling
A study of techniques for the prediction of crime in the City of Los Angeles was conducted. Alternative approaches to crime prediction (causal, quasicausal, associative, extrapolative, and pattern-recognition models) are discussed, as is the environment within which predictions were desired for the immediate application. The decision was made to use time series (extrapolative) models to produce the desired predictions. The characteristics of the data and the procedure used to choose equations for the extrapolations are discussed. The usefulness of different functional forms (constant, quadratic, and exponential forms) and of different parameter estimation techniques (multiple regression and multiple exponential smoothing) are compared, and the quality of the resultant predictions is assessed.
Source record↗
Visual orientation performances of desert ants (Cataglyphis bicolor) toward astromenotactic directions and horizon landmarks
Experimental data, on the visual orientation of desert ants toward astromenotactic courses and horizon landmarks involving the cooperation of different direction finding systems, are given. Attempts were made to: (1) determine if the ants choose a compromise direction between astromenotactic angles and the direction toward horizon landmarks when both angles compete with each other or whether they decide alternatively; (2) analyze adaptations of the visual system to the special demands of direction finding by astromenotactic orientation or pattern recognition; and (3) determine parameters of visual learning behavior. Results show separate orientation mechanisms are responsible for the orientation of the ant toward astromenotactic angles and horizon landmarks. If both systems compete with each other, the ants switch over from one system to the other and do not perform a compromise direction.
Wehner, R.↗
Summary of 1971 land remote sensing investigations
Techniques to provide land use up-date information using remotely sensed data and automatic data processing technology are being developed. The approach utilizes multispectral scanners, the associated data analysis station, and the pattern recognition programs to identify and classify land surface characteristics, including wetlands, and to convert these data to demonstration type experiments in the various disciplines.
Mooneyhan, D. W.↗
A first-look machine analysis of ERTS-1 data
There are no author-identified significant results in this report. The preliminary analysis of a black and white image of channel 5 data together with tapes from the multispectral scanner is discussed. Four sub-projects based on the initial analysis are discussed. The sub-projects are the analysis by multispectral pattern recognition techniques of the full frame and two particular subframes and a study of the data quality. The procedures for conducting the study and the limitations in analyzing the data are examined. Methods for improving the analysis of the frames by first and second iteration are presented.
Landgrebe, D. A.↗
Detection of southern corn leaf blight by remote sensing techniques.
Multispectral photographic and scanner data were collected over western Indiana in August and September 1970, to determine the detectability of southern corn leaf blight by remote sensing. Measurements were made at altitudes of 3000 to 7000 ft. Color, color IR, and multiband black and white photography were collected at altitudes from 3000 to 60,000 ft. Six levels of infection based on the amount of leaf damage were identified in the fields. Three levels of infection were detected with color IR photography by standard photo-interpretive techniques. Up to five levels of infection were distinguished by applying automatic pattern recognition techniques to the multispectral scanner data. The results illustrate the potential of remote sensing techniques in the detection of crop diseases.
Bauer, M. E.↗
Interactive display/graphics systems for remote sensor data analysis.
Using a color-television display system and interactive graphics equipment on-line to an IBM 360/44 computer, investigators at the Manned Spacecraft Center have developed a variety of interactive displays which aid in analyzing remote sensor data. This paper describes how such interactive displays are used to: (1) analyze data from a multispectral scanner, (2) develop automatic pattern recognition systems based on multispectral scanner measurements, and (3) analyze data from nonimaging sensors such as the infrared radiometer and microwave scatterometer.
Eppler, W. G.↗
Effects of compression and random noise on multispectral data.
Two problem areas are often encountered in the use of multispectral scanner data: (1) large quantities of man and machine time are required to analyze and store the volumes of data gathered and (2) the quality of the data is usually reduced by the introduction of unwanted random noise. This paper will present some effects of data compression and random noise on multispectral data, particularly as they apply to pattern recognition and picture quality.
Ready, P. J.↗
Mapping soil types from multispectral scanner data.
Multispectral remote sensing and computer-implemented pattern recognition techniques were used for automatic ?mapping' of soil types. This approach involves subjective selection of a set of reference samples from a gray-level display of spectral variations which was generated by a computer. Each resolution element is then classified using a maximum likelihood ratio. Output is a computer printout on which the researcher assigns a different symbol to each class. Four soil test areas in Indiana were experimentally examined using this approach, and partially successful results were obtained.
Kristof, S. J.↗
Reflectance of vegetation, soil, and water
There are no author-identified significant results in this report. This report deals with the selection of the best channels from the 24-channel aircraft data to represent crop and soil conditions. A three-step procedure has been developed that involves using univariate statistics and an F-ratio test to indicate the best 14 channels. From the 14, the 10 best channels are selected by a multivariate stochastic process. The third step involves the pattern recognition procedures developed in the data analysis plan. Indications are that the procedures in use are satsifactory and will extract the desired information from the data.
Wiegand, C. L.↗