SEARCH · Engineering Papers
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.
MATHPAC image-analysis library is collection of general-purpose mathematical and statistical routines and special-purpose data-analysis and pattern-recognition routines for image analysis. MATHPAC library consists of Linear Algebra, Optimization, Statistical-Summary, Densities and Distribution, Regression, and Statistical-Test packages.
A comprehensive study has been undertaken to determine the extent to which ERTS-1 data could be used to detect, identify (classify), locate and measure features of applications interest in the disciplines of Agriculture and Forestry. The study areas included: six counties in five states in which were located examples of the most important crops and practices of American agriculture; and a portion of the Sam Houston National Forest, a typical Gulf coastal plain pine forest. The investigation utilized conventional image interpretation and computer-aided (spectral pattern recognition) analysis using both image products and computer compatible tapes. The emphasis was generally upon the computer-aided techniques. It was concluded that ERTS-1 data can be used to detect, identify, locate and measure a wide array of features of interest in agriculture and forestry.
A method of recognizing or classifying patterns is based on an artificial immune system (AIS), which includes an algorithm and a computational model of nonlinear dynamics inspired by the behavior of a biological immune system. The method has been proposed as the theoretical basis of the computational portion of a star-tracking system aboard a spacecraft. In that system, a newly acquired star image would be treated as an antigen that would be matched by an appropriate antibody (an entry in a star catalog). The method would enable rapid convergence, would afford robustness in the face of noise in the star sensors, would enable recognition of star images acquired in any sensor or spacecraft orientation, and would not make an excessive demand on the computational resources of a typical spacecraft. Going beyond the star-tracking application, the AIS-based pattern-recognition method is potentially applicable to pattern- recognition and -classification processes for diverse purposes -- for example, reconnaissance, detecting intruders, and mining data.
The general problem of computer vision has been investigated for more that 20 years and is still one of the most challenging fields in artificial intelligence. Indeed, taking a look at the human visual system can give us an idea of the complexity of any solution to the problem of visual recognition. This general task can be decomposed into a whole hierarchy of problems ranging from pixel processing to high level segmentation and complex objects recognition. Contrasting an image at different representations provides useful information such as edges. An example of low level signal and image processing using the theory of wavelets is introduced which provides the basis for multiresolution representation. Like the human brain, we use a multiorientation process which detects features independently in different orientation sectors. So, images of the same orientation but of different resolutions are contrasted to gather information about an image. An interesting image representation using energy zero crossings is developed. This representation is shown to be experimentally complete and leads to some higher level applications such as edge and corner finding, which in turn provides two basic steps to image segmentation. The possibilities of feedback between different levels of processing are also discussed.
Image understanding concepts and models, image understanding systems and applications, advanced digital processors and software tools, and advanced man-machine interfaces are among the topics discussed. Particular papers are presented on such topics as neural networks for computer vision, object-based segmentation and color recognition in multispectral images, the application of image algebra to image measurement and feature extraction, and the integration of modeling and graphics to create an infrared signal processing test bed.
An optical neural network based on the neocognitron paradigm is introduced. A novel aspect of the architecture design is shift-invariant multichannel Fourier optical correlation within each processing layer. Multilayer processing is achieved by feeding back the ouput of the feature correlator interatively to the input spatial light modulator and by updating the Fourier filters. By training the neural net with characteristic features extracted from the target images, successful pattern recognition with intraclass fault tolerance and interclass discrimination is achieved. A detailed system description is provided. Experimental demonstrations of a two-layer neural network for space-object discrimination is also presented.
The issues of image compression and pattern classification have been a primary focus of researchers among a variety of fields including signal and image processing, pattern recognition, data classification, etc. These issues depend on finding an efficient representation of the source data. In this paper we collate our earlier results where we introduced the application of the. Hilbe.rt scan to a principal component algorithm (PCA) with Adaptive Principal Component Extraction (APEX) neural network model. We apply these technique to medical imaging, particularly image representation and compression. We apply the Hilbert scan to the APEX algorithm to improve results
Abstract Imaging Cherenkov detectors form the backbone of particle identification (PID) at the future Electron Ion Collider (EIC). Currently all the designs for the first EIC detector proposal use a dual Ring Imaging CHerenkov (dRICH) detector in the hadron endcap, a Detector for Internally Reflected Cherenkov (DIRC) light in the barrel, and a modular RICH (mRICH) in the electron endcap. These detectors involve optical processes with many photons that need to be tracked through complex surfaces at the simulation level, while for reconstruction they rely on pattern recognition of ring images. This proceeding summarizes ongoing efforts and possible applications of AI for imaging Cherenkov detectors at EIC. In particular we will provide the example of the dRICH for the AI-assisted design and of the DIRC for simulation and particle identification from complex patterns and discuss possible advantages of using AI.
An optical neural network based upon the Neocognitron paradigm (K. Fukushima et al. 1983) is introduced. A novel aspect of the architectural design is shift-invariant multichannel Fourier optical correlation within each processing layer. Multilayer processing is achieved by iteratively feeding back the output of the feature correlator to the input spatial light modulator and updating the Fourier filters. By training the neural net with characteristic features extracted from the target images, successful pattern recognition with intra-class fault tolerance and inter-class discrimination is achieved. A detailed system description is provided. Experimental demonstration of a two-layer neural network for space objects discrimination is also presented.
Improved resolution could make satellite remote sensing data more useful for surveys of natural vegetation. Although improved satellite/sensor systems appear to be several years away, one potential interim solution to the problem of achieving greater resolution without sacrificing spectral sensitivity is through the merging of Landsat RBV and MSS data. This paper describes the results of a study performed to obtain a preliminary evaluation of the usefulness of two types of products that can be made by merging Landsat RBV and MSS data. The products generated were a false color composite image and a computer recognition map. Of these two products, the false color composite image appears to be the most useful.
The Magellan data set constitutes an example of the large volumes of data that today's instruments can collect, providing more detail of Venus than was previously available from Pioneer Venus, Venera 15/16, or ground-based radar observations put together. However, data analysis technology has not kept pace with data collection and storage technology. Due to the sheer size of the data, complete and comprehensive scientific analysis of such large volumes of image data is no longer feasible without the use of computational aids. Our progress towards developing a pattern recognition system for aiding in the detection and cataloging of small-scale natural features in large collections of images is reported. Combining classical image processing, machine learning, and a graphical user interface, the detection of the 'small-shield' volcanoes (less than 15km in diameter) that constitute the most abundant visible geologic feature in the more that 30,000 synthetic aperture radar (SAR) images of the surface of Venus are initially targeted. Our eventual goal is to provide a general, trainable tool for locating small-scale features where scientists specify what to look for simply by providing examples and attributes of interest to measure. This contrasts with the traditional approach of developing problem specific programs for detecting Specific patterns. The approach and initial results in the specific context of locating small volcanoes is reported. It is estimated, based on extrapolating from previous studies and knowledge of the underlying geologic processes, that there should be on the order of 10(exp 5) to 10(exp 6) of these volcanoes visible in the Magellan data. Identifying and studying these volcanoes is fundamental to a proper understanding of the geologic evolution of Venus. However, locating and parameterizing them in a manual manner is forbiddingly time-consuming. Hence, the development of techniques to partially automate this task were undertaken. The primary constraints for this particular problem are that the method must be reasonably robust and fast. Unlike most geological features, the small volcanoes of Venus can be ascribed to a basic process that produces features with a short list of readily defined characteristics differing significantly from other surface features on Venus. For pattern recognition purposes the relevant criteria include (1) a circular planimetric outline, (2) known diameter frequency distribution from preliminary studies, (3) a limited number of basic morphological shapes, and (4) the common occurrence of a single, circular summit pit at the center of the edifice.
There are two main algorithmic approaches to autonomous driving systems: (1) An end-to-end system in which a single deep neural network learns to map sensory input directly into appropriate warning and driving responses. (2) A mediated hybrid recognition system in which a system is created by combining independent modules that detect each semantic feature. While some researchers believe that deep learning can solve any problem, others believe that a more engineered and symbolic approach is needed to cope with complex environments with less data. Deep learning alone has achieved state-of-the-art results in many areas, from complex gameplay to predicting protein structures. In particular, in image classification and recognition, deep learning models have achieved accuracies as high as humans. But sometimes it can be very difficult to debug if the deep learning model doesn't work. Deep learning models can be vulnerable and are very sensitive to changes in data distribution. Generalization can be problematic. It's usually hard to prove why it works or doesn't. Deep learning models can also be vulnerable to adversarial attacks. Here, we combine deep learning-based object recognition and tracking with an adaptive neurosymbolic network agent, called the Non-Axiomatic Reasoning System (NARS), that can adapt to its environment by building concepts based on perceptual sequences. We achieved an improved intersection-over-union (IOU) object recognition performance of 0.65 in the adaptive retraining model compared to IOU 0.31 in the COCO data pre-trained model. We improved the object detection limits using RADAR sensors in a simulated environment, and demonstrated the weaving car detection capability by combining deep learning-based object detection and tracking with a neurosymbolic model.
NASA depends on advanced, ultra-sensitive photoreceivers and photodetectors to provide high-data communications and pinpoint image-detection and -recognition capabilities from great distances. In 2003, Epitaxial Technologies LLC was awarded a Small Business Innovation Research (SBIR) contract from Goddard Space Flight Center to address needs for advanced sensor components. Epitaxial developed a photoreciever capable of single proton sensitivity that is also smaller, lighter, and requires less power than its predecessor. This receiver operates in several wavelength ranges; will allow data rate transmissions in the terabit range; and will enhance Earth-based missions for remote sensing of crops and other natural resources, including applications for fluorescence and phosphorescence detection. Widespread military and civilian applications are anticipated, especially through enhancing fiber optic communications, laser imaging, and laser communications.
With increased sensor data rates, and limited downlink capability, NASA missions have increased demands for onboard processing for applications ranging from synthetic aperture radar (SAR) data reduction to hyperspectral image processing and recognition, and even artificial intelligence (AI). Graphics Processor Units (GPUs) offer an attractive processing architecture for many of the applications due to their massive parallelism. As no radiation hardened GPU devices currently exist, any near term GPU-based onboard processors must use commercially available devices. To address this need NASA GSFC is collaborating with Cubic Aerospace Incorporated to, (a) characterize the capability of GPUs to meet the demands of a candidate onboard processing application, thereby demonstrating their ability to improve mission performance, reduce spacecraft SWaP, and potentially enable new missions, and (b) evaluate the radiation tolerance of capable COTS GPU devices to determine their suitability for spaceflight applications and understand any mitigations that are needed. A candidate onboard processing image has been prototyped and evaluated on a commercial GPU board and has demonstrated significantly increased processing throughput. Radiation tests for commercial GPU devices are planned for early fiscal year 2019.
Elemental abundances (C6, N7, O8, Na11, Mg12, Al3, P15, S16, Cl17, K19, Ca20, Ti22, Mn25, Fe26, and Ni28) were obtained for a set of terrestrial fossils and the rock matrix surrounding them. Principal Component Analysis extracted five factors accounting for the 92.5% of the data variance, i.e. information content, of the elemental abundance data. Hierarchical Cluster Analysis provided unsupervised sample classification distinguishing fossil from matrix samples on the basis of either raw abundances or PCA input that agreed strongly with visual classification. A stochastic, non-linear Artificial Neural Network produced a Bayesian probability of correct sample classification. The results provide a quantitative probabilistic methodology for discriminating terrestrial fossils from the surrounding rock matrix using chemical information. To demonstrate the applicability of these techniques to the assessment of meteoritic samples or in situ extraterrestrial exploration, we present preliminary data on samples of the Orgueil meteorite. In both systems an elemental signature produces target classification decisions remarkably consistent with morphological classification by a human expert using only structural (visual) information. We discuss the possibility of implementing a complexity analysis metric capable of automating certain image analysis and pattern recognition abilities of the human eye using low magnification optical microscopy images and discuss the extension of this technique across multiple scales.
BACKGROUND: Pitfalls of the flow convergence (FC) method, including 2-dimensional imaging of the 3-dimensional (3D) geometry of the FC surface, can lead to erroneous quantification of mitral regurgitation (MR). This limitation may be mitigated by the use of real-time 3D color Doppler echocardiography (CE). Our objective was to validate a real-time 3D navigation method for MR quantification. METHODS: In 12 sheep with surgically induced chronic MR, 37 different hemodynamic conditions were studied with real-time 3DCE. Using real-time 3D navigation, the radius of the largest hemispherical FC zone was located and measured. MR volume was quantified according to the FC method after observing the shape of FC in 3D space. Aortic and mitral electromagnetic flow probes and meters were balanced against each other to determine reference MR volume. As an initial clinical application study, 22 patients with chronic MR were also studied with this real-time 3DCE-FC method. Left ventricular (LV) outflow tract automated cardiac flow measurement (Toshiba Corp, Tokyo, Japan) and real-time 3D LV stroke volume were used to quantify the reference MR volume (MR volume = 3DLV stroke volume - automated cardiac flow measurement). RESULTS: In the sheep model, a good correlation and agreement was seen between MR volume by real-time 3DCE and electromagnetic (y = 0.77x + 1.48, r = 0.87, P <.001, delta = -0.91 +/- 2.65 mL). In patients, real-time 3DCE-derived MR volume also showed a good correlation and agreement with the reference method (y = 0.89x - 0.38, r = 0.93, P <.001, delta = -4.8 +/- 7.6 mL). CONCLUSIONS: real-time 3DCE can capture the entire FC image, permitting geometrical recognition of the FC zone geometry and reliable MR quantification.
Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification and recognition. Mathematically, ResNet architectures can be interpreted as forward Euler discretizations of a nonlinear initial value problem whose time-dependent control variables represent the weights of the neural network. Hence, training a ResNet can be cast as an optimal control problem of the associated dynamical system. For similar time-dependent optimal control problems arising in engineering applications, parallel-in-time methods have shown notable improvements in scalability. This paper demonstrates the use of those techniques for efficient and effective training of ResNets. The proposed algorithms replace the classical (sequential) forward and backward propagation through the network layers with a parallel nonlinear multigrid iteration applied to the layer domain. This adds a new dimension of parallelism across layers that is attractive when training very deep networks. From this basic idea, we derive multiple layer-parallel methods. The most efficient version employs a simultaneous optimization approach where updates to the network parameters are based on inexact gradient information in order to speed up the training process. Finally, using numerical examples from supervised classification, we demonstrate that the new approach achieves a training performance similar to that of traditional methods, but enables layer-parallelism and thus provides speedup over layer-serial methods through greater concurrency.
The author has identified the following significant results. A summary of the significant results of the studies completed during the July-August, 1973 period includes: (1) ERTS-1 image brightness contrasts can be related to important contrasts in rangeland and forest vegetation communities of the Laramie Basin. (2) Stereoscopic viewing is essential for correct structural interpretation in outcrop patterns in some areas. (3) Complex fracture patterns which may have exerted a controlling influence on intrusive activity in the Absaroka Mountains can be mapped from ERTS. (4) Volcanic lithologies of the Yellowstone region are often differentiated on the basis of their textures, and cannot be successfully mapped by photogeologic interpretation of ERTS-1 imagery. Ground spectral readings confirm a general lack of contrast between these lithologies in the four ERTS-1 MSS bands. (5) Major dune fields can be recognized and defined from ERTS-1 image interpretations and recognition of differences in stabilizing plant communities (some of which may be mappable from ERTS-1) yields information about migration history of the dune fields.