Search NASA⌕ Search

SEARCH · Search NASA

Results for “Feature extraction”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
NASA NTRS2011

Optimization of Adaboost Algorithm for Sonar Target Detection in a Multi-Stage ATR System

JPL has developed a multi-stage Automated Target Recognition (ATR) system to locate objects in images. First, input images are preprocessed and sent to a Grayscale Optical Correlator (GOC) filter to identify possible regions-of-interest (ROIs). Second, feature extraction operations are performed using Texton filters and Principal Component Analysis (PCA). Finally, the features are fed to a classifier, to identify ROIs that contain the targets. Previous work used the Feed-forward Back-propagation Neural Network for classification. In this project we investigate a version of Adaboost as a classifier for comparison. The version we used is known as GentleBoost. We used the boosted decision tree as the weak classifier. We have tested our ATR system against real-world sonar images using the Adaboost approach. Results indicate an improvement in performance over a single Neural Network design.

Adaboost↗
NASA NTRS2010

Autonomous Exploration for Gathering Increased Science

The Autonomous Exploration for Gathering Increased Science System (AEGIS) provides automated targeting for remote sensing instruments on the Mars Exploration Rover (MER) mission, which at the time of this reporting has had two rovers exploring the surface of Mars (see figure). Currently, targets for rover remote-sensing instruments must be selected manually based on imagery already on the ground with the operations team. AEGIS enables the rover flight software to analyze imagery onboard in order to autonomously select and sequence targeted remote-sensing observations in an opportunistic fashion. In particular, this technology will be used to automatically acquire sub-framed, high-resolution, targeted images taken with the MER panoramic cameras. This software provides: 1) Automatic detection of terrain features in rover camera images, 2) Feature extraction for detected terrain targets, 3) Prioritization of terrain targets based on a scientist target feature set, and 4) Automated re-targeting of rover remote-sensing instruments at the highest priority target.

Bornstein, Benjamin J.↗
NASA NTRS1997

Iterative edge- and wavelet-based image registration of AVHRR and GOES satellite imagery

Most automatic registration methods are either correlation-based, feature-based, or a combination of both. Examples of features which can be utilized for automatic image registration are edges, regions, corners, or wavelet-extracted features. In this paper, we describe two proposed approaches, based on edge or edge-like features, which are very appropriate to highlight regions of interest such as coastlines. The two iterative methods utilize the Normalized Cross-Correlation of edge and wavelet features and are applied to such problems as image-to-map registration, landmarking, and channel-to-channel co-registration, utilizing test data, AVHRR data, as well as GOES image data.

LeMoigne, Jacqueline↗
NASA NTRS1981

Optical recognition of statistical patterns

Optical implementation of the Fukunaga-Koontz transform (FKT) and the Least-Squares Linear Mapping Technique (LSLMT) is described. The FKT is a linear transformation which performs image feature extraction for a two-class image classification problem. The LSLMT performs a transform from large dimensional feature space to small dimensional decision space for separating multiple image classes by maximizing the interclass differences while minimizing the intraclass variations. The FKT and the LSLMT were optically implemented by utilizing a coded phase optical processor. The transform was used for classifying birds and fish. After the F-K basis functions were calculated, those most useful for classification were incorporated into a computer generated hologram. The output of the optical processor, consisting of the squared magnitude of the F-K coefficients, was detected by a T.V. camera, digitized, and fed into a micro-computer for classification. A simple linear classifier based on only two F-K coefficients was able to separate the images into two classes, indicating that the F-K transform had chosen good features. Two advantages of optically implementing the FKT and LSLMT are parallel and real time processing.

Lee, S. H.↗
NASA NTRS2003

Using X-band Weather Radar Measurements to Monitor the Integrity of Digital Elevation Models for Synthetic Vision Systems

Synthetic Vision Systems (SVS) provide pilots with displays of stored geo-spatial data representing terrain, obstacles, and cultural features. As comprehensive validation is impractical, these databases typically have no quantifiable level of integrity. Further, updates to the databases may not be provided as changes occur. These issues limit the certification level and constrain the operational context of SVS for civil aviation. Previous work demonstrated the feasibility of using a realtime monitor to bound the integrity of Digital Elevation Models (DEMs) by using radar altimeter measurements during flight. This paper describes an extension of this concept to include X-band Weather Radar (WxR) measurements. This enables the monitor to detect additional classes of DEM errors and to reduce the exposure time associated with integrity threats. Feature extraction techniques are used along with a statistical assessment of similarity measures between the sensed and stored features that are detected. Recent flight-testing in the area around the Juneau, Alaska Airport (JNU) has resulted in a comprehensive set of sensor data that is being used to assess the feasibility of the proposed monitor technology. Initial results of this assessment are presented.

Young, Steve↗
NASA NTRS1991

Analysis of SSME inspection imagery using AI approaches

The automated analysis of SSME injector assemblies has been investigated for the cases of LOX post surface defects and injector-baffle deterioration. Defects are isolated via 2D feature extraction from borescope and camera images; temporal-frequency transforms are then used to create a multiresolution set of feature vectors representing image contents. The potential flaws thus discriminated are then segmented and classified according to known categories. AI is applied in the form of a blackboard architecture that is controlled by a rule-based production system.

Finegan, Michael K., Jr.↗
NASA NTRS1989

Optical linear discriminant functions

The use of computer generated holograms to implement feature extraction operations has been achieved. The optical realization and use of multiple linear discriminant functions on a high-dimensionality feature space for large class pattern recognition is described and initial experimental results are provided.

Casasent, David↗
NASA NTRS2007

Fusing Image Data for Calculating Position of an Object

A computer program has been written for use in maintaining the calibration, with respect to the positions of imaged objects, of a stereoscopic pair of cameras on each of the Mars Explorer Rovers Spirit and Opportunity. The program identifies and locates a known object in the images. The object in question is part of a Moessbauer spectrometer located at the tip of a robot arm, the kinematics of which are known. In the program, the images are processed through a module that extracts edges, combines the edges into line segments, and then derives ellipse centroids from the line segments. The images are also processed by a feature-extraction algorithm that performs a wavelet analysis, then performs a pattern-recognition operation in the wavelet-coefficient space to determine matches to a texture feature measure derived from the horizontal, vertical, and diagonal coefficients. The centroids from the ellipse finder and the wavelet feature matcher are then fused to determine co-location. In the event that a match is found, the centroid (or centroids if multiple matches are present) is reported. If no match is found, the process reports the results of the analyses for further examination by human experts.

Huntsberger, Terrance↗
NASA NTRS1985

Basalts of Mars: Constraints on Volatile Evolution

The mineralogy of relatively unweathered rocks on Mars place important constraints on models of planetary oxidation state, volcanism and associated outgassing, accretion and associated volatile inventory, and geochemical changes over time. Reflectance spectra (300 to 2500 nm) provide direct mineralogic information about the surface materials. Spectra measured using Earth-based telescopes were analyzed by a multiple high-order derivative spectroscopy technique. Nine areas, measured during the 1978 opposition, were analyzed by the technique. Each contained suites of well-defined absorption bands. These bands can be interpreted in terms of constituent mineralogy by the technique of Adams. Among the features extracted from the spectra were bands attributed to iron oxides. Other bands can be attributed to silicates within chemically unweathered rocks/fines. Absorption features suggest the presence of Mg-olivine and plagioclase feldspar.

Huguenin, R. L.↗
NASA NTRS1972

Earth resources data processor

The recent development of manned and unmanned space vehicles has brought about an almost unprecedented advance in studies concerned with remotely sensed earth observations. With this advance comes an unprecedented amount of data. The problem arises of how to efficiently analyze and compress unmanageable amounts of data into manageable amounts of useful information. A recently developed computer program is proposed as a partial solution to the above problem. The computer program is designed to determine the ground scene location and distribution of features extracted from remotely sensed earth observation data without human involvement in the data processing or a priori knowledge of ground truth. Human involvement and judgement are reserved for identification of the features presented in the compressed data.

Phillips, M. R.↗
NASA NTRS1976

Classification improvement by optimal dimensionality reduction when training sets are of small size

A computer simulation was performed to test the conjecture that, when the sizes of the training sets are small, classification in a subspace of the original data space may give rise to a smaller probability of error than the classification in the data space itself; this is because the gain in the accuracy of estimation of the likelihood functions used in classification in the lower dimensional space (subspace) offsets the loss of information associated with dimensionality reduction (feature extraction). A number of pseudo-random training and data vectors were generated from two four-dimensional Gaussian classes. A special algorithm was used to create an optimal one-dimensional feature space on which to project the data. When the sizes of the training sets are small, classification of the data in the optimal one-dimensional space is found to yield lower error rates than the one in the original four-dimensional space.

Starks, S. A.↗
NASA NTRS1990

Real-time image processing II; Proceedings of the Meeting, Orlando, FL, Apr. 16-18, 1990

The present conference discusses topics in the fields of feature extraction and implementation, filter and correlation algorithms, optical correlators, high-level algorithms, and digital image processing for ranging and remote driving. Attention is given to a nonlinear filter derived from topological image features, IR image segmentation through iterative thresholding, orthogonal subspaces for correlation masking, composite filter trees and image recognition via binary search, and features of matrix-coherent optical image processing. Also discussed are multitarget tracking via hybrid joint transform correlator, binary joint Fourier transform correlator considerations, global image processing operations on parallel architectures, real-time implementation of a differential range finder, and real-time binocular stereo range and motion detection.

Juday, Richard D.↗
NASA NTRS1994

Unsupervised texture image segmentation by improved neural network ART2

We here propose a segmentation algorithm of texture image for a computer vision system on a space robot. An improved adaptive resonance theory (ART2) for analog input patterns is adapted to classify the image based on a set of texture image features extracted by a fast spatial gray level dependence method (SGLDM). The nonlinear thresholding functions in input layer of the neural network have been constructed by two parts: firstly, to reduce the effects of image noises on the features, a set of sigmoid functions is chosen depending on the types of the feature; secondly, to enhance the contrast of the features, we adopt fuzzy mapping functions. The cluster number in output layer can be increased by an autogrowing mechanism constantly when a new pattern happens. Experimental results and original or segmented pictures are shown, including the comparison between this approach and K-means algorithm. The system written in C language is performed on a SUN-4/330 sparc-station with an image board IT-150 and a CCD camera.

Wang, Zhiling↗
NASA NTRS1992

Feature detection in satellite images using neural network technology

A feasibility study of automated classification of satellite images is described. Satellite images were characterized by the textures they contain. In particular, the detection of cloud textures was investigated. The method of second-order gray level statistics, using co-occurrence matrices, was applied to extract feature vectors from image segments. Neural network technology was employed to classify these feature vectors. The cascade-correlation architecture was successfully used as a classifier. The use of a Kohonen network was also investigated but this architecture could not reliably classify the feature vectors due to the complicated structure of the classification problem. The best results were obtained when data from different spectral bands were fused.

Augusteijn, Marijke F.↗
NASA NTRS2001

Road Extraction from AVIRIS Using Spectral Mixture and Q-Tree Filter Techniques

Accurate road location and condition information are of primary importance in road infrastructure management. Additionally, spatially accurate and up-to-date road networks are essential in ambulance and rescue dispatch in emergency situations. However, accurate road infrastructure databases do not exist for vast areas, particularly in areas with rapid expansion. Currently, the US Department of Transportation (USDOT) extends great effort in field Global Positioning System (GPS) mapping and condition assessment to meet these informational needs. This methodology, though effective, is both time-consuming and costly, because every road within a DOT's jurisdiction must be field-visited to obtain accurate information. Therefore, the USDOT is interested in identifying new technologies that could help meet road infrastructure informational needs more effectively. Remote sensing provides one means by which large areas may be mapped with a high standard of accuracy and is a technology with great potential in infrastructure mapping. The goal of our research is to develop accurate road extraction techniques using high spatial resolution, fine spectral resolution imagery. Additionally, our research will explore the use of hyperspectral data in assessing road quality. Finally, this research aims to define the spatial and spectral requirements for remote sensing data to be used successfully for road feature extraction and road quality mapping. Our findings will facilitate the USDOT in assessing remote sensing as a new resource in infrastructure studies.

Gardner, Margaret E.↗
NASA NTRS1991

Optical implementation of neocognitron and its applications to radar signature discrimination

A feature-extraction-based optoelectronic neural network is introduced. The system implementation approach applies the principle of the neocognitron paradigm first introduced by Fukushima et al. (1983). A multichannel correlator is used as a building block of a generic single layer of the neocognitron for shift-invariant feature correlation. Multilayer processing is achieved by iteratively feeding back the output of the feature correlator to the input spatial light modulator. Successful pattern recognition with intraclass fault tolerance and interclass discrimination is achieved using this optoelectronic neocognitron. Detailed system analysis is described. Experimental demonstration of radar signature processing is also provided.

Chao, Tien-Hsin↗
NASA NTRS2009

Processing Electromyographic Signals to Recognize Words

A recently invented speech-recognition method applies to words that are articulated by means of the tongue and throat muscles but are otherwise not voiced or, at most, are spoken sotto voce. This method could satisfy a need for speech recognition under circumstances in which normal audible speech is difficult, poses a hazard, is disturbing to listeners, or compromises privacy. The method could also be used to augment traditional speech recognition by providing an additional source of information about articulator activity. The method can be characterized as intermediate between (1) conventional speech recognition through processing of voice sounds and (2) a method, not yet developed, of processing electroencephalographic signals to extract unspoken words directly from thoughts. This method involves computational processing of digitized electromyographic (EMG) signals from muscle innervation acquired by surface electrodes under a subject's chin near the tongue and on the side of the subject s throat near the larynx. After preprocessing, digitization, and feature extraction, EMG signals are processed by a neural-network pattern classifier, implemented in software, that performs the bulk of the recognition task as described.

Jorgensen, C. C.↗