SEARCH · Search NASA
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.
This paper develops a procedure for an autonomous Martian rover to classify objects into obstacles and non-obstacles. These so called 'objects' are actually models generated by the Terrain Modeling and Edge Detection schemes. The classification process is performed using a set of object parameters which distinguish unobstructive objects from obstacles.
In this study we present a novel method of land surface classification using surface-reflected GPS signals in combination with digital imagery. Two GPS-derived classification features are merged with visible image data to create terrain-moisture (TM) classes, defined here as visibly identifiable terrain or landcover classes containing a surface/soil moisture component. As compared to using surface imagery alone, classification accuracy is significantly improved for a number of visible classes when adding the GPS-based signal features. Since the strength of the reflected GPS signal is proportional to the amount of moisture in the surface, use of these GPS features provides information about the surface that is not obtainable using visible wavelengths alone. Application areas include hydrology, precision agriculture, and wetlands mapping.
The impact of charge-coupled device (CCD) processors on future instrumentation was investigated. The CCD devices studied process sampled analog data and are referred to as OP-SAPS - operational sampled analog processors. Preliminary studies into various architectural configurations for systems composed of OP-SAPS show that they have potential in such diverse applications as pattern recognition and automatic control. It appears probable that OP-SAPS may be used to construct computing structures which can serve as special peripherals to large-scale computer complexes used in real time flight simulation. The research was limited to the following benchmark programs: (1) face recognition, (2) voice command and control, (3) terrain classification, and (4) terrain identification. A small amount of effort was spent on examining a method by which OP-SAPS may be used to decrease the limiting ground sampling distance encountered in remote sensing from satellites.
Two algorithms processing polarimetric synthetic-aperture-radar data found effective in assigning various parts of SAR images to classes representing different types of terrain. Partially automate interpretation of SAR imagery, reducing amount of photointerpretation needed and putting whole interpretation process on more quantitative and systematic basis. First algorithm implements Bayesian classification scheme "supervised" by use of training data. Second algorithm implements classification procedure unsupervised.
The normalized polarimetric classifier (NPC) which uses only the relative magnitudes and phases of the polarimetric data is proposed for discrimination of terrain elements. The probability density functions (PDFs) of polarimetric data are assumed to have a complex Gaussian distribution, and the marginal PDF of the normalized polarimetric data is derived by adopting the Euclidean norm as the normalization function. The general form of the distance measure for the NPC is also obtained. It is demonstrated that for polarimetric data with an arbitrary PDF, the distance measure of NPC will be independent of the normalization function selected even when the classifier is mistrained. A complex Gaussian distribution is assumed for the polarimetric data consisting of grass and tree regions. The probability of error for the NPC is compared with those of several other single-feature classifiers. The classification error of NPCs is shown to be independent of the normalization function.
The possibility of improving the accuracy of terrain classification by preprocessing spectral data was investigated. Terrain maps were made using the following techniques: 1) preprocessing by scan angle function transformation, using the computer-selected best set of three channels; and 2) preprocessing by ratio transformation, using the specified ERTS data channels, simulated by fitting the spectral response of each of the 12 data channels to the ERTS channels by a set of weighting coefficients. By using a simple technique during printout, the maps were produced in color. The normalized scan angle function transformation resulted in the most accurate classification. The best ratio transformation for the Yellowstone Park data was the ratio of each channel to the sum of all channels. A supervised training program involving maximum likelihood decision for selecting the best spectrometer channels and similar techniques for digitizing the data of the analog magnetic tapes were used. Cloud shadows were recognized in addition to eight classes of terrain. Preprocessing of data resulted in more accurate maps, required fewer training areas (hence less preparation and computer time), and enabled much of the area formerly classified as shadow to be reclassified according to actual terrain type.
TIR cameras can be used for day/night Unmanned Ground Vehicle (UGV) autonomous navigation when stealth is required. The quality of uncooled TIR cameras has significantly improved over the last decade, making them a viable option at low speed Limiting factors for stereo ranging with uncooled LWIR cameras are image blur and low texture scenes TIR perception capabilities JPL has explored includes: (1) single and dual band TIR terrain classification (2) obstacle detection (pedestrian, vehicle, tree trunks, ditches, and water) (3) perception thru obscurants
The author has identified the following significant results. For the exploitation of the ERTS-1 images, both multispectral and spatial pattern recognition techniques are important. A multispectral recognition software program was successfully tested. A technique for the generation of resource boundaries has been successfully combined with terrain recognition software resulting in a regionalized terrain classification system. Digital registration of multispectral images has been achieved. Also, photointerpretation results from one test site are reported and the development of spatial terrain signatures from optical diffraction patterns is described.
In preparation for the launch of SIR-C/X-SAR and design studies for future orbital SAR, a program has made considerable progress in the development of an SAR terrain classifier and algorithms for quantification of biophysical attributes. The goal of this program is to produce a generalized software package for terrain classification and estimation of biophysical attributes and to make this package available to the larger scientific community. The basic elements of the SAR (Synthetic Aperture Radar) terrain classifier are outlined. An SAR image is calibrated with respect to known system and processor gains and external targets (if available). A Level 1 classifier operates on the data to differentiate: urban features, surfaces and tall and short vegetation. Level 2 classifiers further subdivide these classes on the basis of structure. Finally, biophysical and geophysical inversions are applied to each class to estimate attributes of interest. The process used to develop the classifiers and inversions is shown. Radar scattering models developed from theory and from empirical data obtained by truck-mounted polarimeters and the JPL AirSAR are validated. The validated models are used in sensitivity studies to understand the roles of various scattering sources (i.e., surface trunk, branches, etc.) in determining net backscatter. Model simulations of sigma (sup o) as functions of the wave parameters (lambda, polarization and angle of incidence) and the geophysical and biophysical attributes are used to develop robust classifiers. The classifiers are validated using available AirSAR data sets. Specific estimators are developed for each class on the basis of the scattering models and empirical data sets. The candidate algorithms are tested with the AirSAR data sets. The attributes of interest include: total above ground biomass, woody biomass, soil moisture and soil roughness.
An algorithm that performs sparse linear discriminant analysis (Sparse-LDA) finds near-optimal solutions in far less time than the prior art when specialized to binary classification (of 2 classes). Sparse-LDA is a type of feature- or variable- selection problem with numerous applications in statistics, machine learning, computer vision, computational finance, operations research, and bio-informatics. Because of its combinatorial nature, feature- or variable-selection problems are NP-hard or computationally intractable in cases involving more than 30 variables or features. Therefore, one typically seeks approximate solutions by means of greedy search algorithms. The prior Sparse-LDA algorithm was a greedy algorithm that considered the best variable or feature to add/ delete to/ from its subsets in order to maximally discriminate between multiple classes of data. The present algorithm is designed for the special but prevalent case of 2-class or binary classification (e.g. 1 vs. 0, functioning vs. malfunctioning, or change versus no change). The present algorithm provides near-optimal solutions on large real-world datasets having hundreds or even thousands of variables or features (e.g. selecting the fewest wavelength bands in a hyperspectral sensor to do terrain classification) and does so in typical computation times of minutes as compared to days or weeks as taken by the prior art. Sparse LDA requires solving generalized eigenvalue problems for a large number of variable subsets (represented by the submatrices of the input within-class and between-class covariance matrices). In the general (fullrank) case, the amount of computation scales at least cubically with the number of variables and thus the size of the problems that can be solved is limited accordingly. However, in binary classification, the principal eigenvalues can be found using a special analytic formula, without resorting to costly iterative techniques. The present algorithm exploits this analytic form along with the inherent sequential nature of greedy search itself. Together this enables the use of highly-efficient partitioned-matrix-inverse techniques that result in large speedups of computation in both the forward-selection and backward-elimination stages of greedy algorithms in general.
Supervised and unsupervised classification techniques are developed and used to classify the earth terrain components from SAR polarimetric images of San Francisco Bay and Traverse City, Michigan. The supervised techniques include the Bayes classifiers, normalized polarimetric classification, and simple feature classification using discriminates such as the absolute and normalized magnitude response of individual receiver channel returns and the phase difference between receiver channels. An algorithm is developed as an unsupervised technique which classifies terrain elements based on the relationship between the orientation angle and the handedness of the transmitting and receiving polariation states. It is found that supervised classification produces the best results when accurate classifier training data are used, while unsupervised classification may be applied when training data are not available.
Fully-polarimetric synthetic aperture radar (PolSAR) data contain a rich body of elementary scattering physics information that is critically valuable for a broad range of applications and scientific purposes. However, there is a lack of available high-resolution (< 0.3048-m) data available for PolSAR phenomenology research. This article introduces a high-resolution PolSAR data set collected and provided by Sandia National Laboratories (SNL). The data sets were collected to support studying high-resolution scattering physics from different types of clutter and applications such as polarimetric-based terrain classification.
ERTS-1 applications in water depth calculation, terrain classification, land use mapping, water pollution, and mineral exploration
An algorithm for locating gray level and/or texture edges in digitized pictures is presented. The algorithm is based on the concept of hypothesis testing. The digitized picture is first subdivided into subsets of picture elements, e.g., 2 x 2 arrays. The algorithm then compares the first- and second-order statistics of adjacent subsets; adjacent subsets having similar first- and/or second-order statistics are merged into blobs. By continuing this process, the entire picture is segmented into blobs such that the picture elements within each blob have similar characteristics. The boundaries between the blobs comprise the boundaries. The algorithm always generates closed boundaries. The algorithm was developed for multispectral imagery of the earth's surface. Application of this algorithm to various image processing techniques such as efficient coding, information extraction (terrain classification), and pattern recognition (feature selection) are included.
The author has identified the following significant results. The capability of mapping ponds over a very large area was demonstrated, with multidate, multiframe LANDSAT imagery. A small double sample of aircraft data made it possible to adjust a LANDSAT large area census. Terrain classification was improved by using multitemporal LANDSAT data. Waterfowl production was estimated, using remotely determined pond data, in conjunction with FWS estimates of breeding population. Relative waterfowl habitat quality was characterized on a section by section basis.
A navigation system for Mars rovers in very rough terrain has been designed, implemented, and tested on a research rover in Mars analog terrain. This navigation system consists of several technologies that are integrated to increase the capabilities compared to current rover navigation algorithms. These technologies include: goodness maps and terrain triage, terrain classification, remote slip prediction, path planning, high-fidelity traversability analysis (HFTA), and slip-compensated path following. The focus of this paper is not on the component technologies, but rather on the integration of these components. Results from the onboard integration of several of the key technologies described here are shown. Additionally, the results from independent demonstrations of several of these technologies are shown. Future work will include the demonstration of the entire integrated system described here.
The objective of this paper is three-fold: 1) to describe the engineering challenges in the surface mobility of the Mars 2020 Rover mission that are considered in the landing site selection processs, 2) to introduce new automated traversability analysis capabilities, and 3) to present the preliminary analysis results for top candidate landing sites. The analysis capabilities presented in this paper include automated terrain classification, automated rock detection, digital elevation model (DEM) generation, and multi-ROI (region of interest) route planning. These analysis capabilities enable to fully utilize the vast volume of high-resolution orbiter imagery, quantitatively evaluate surface mobility requirements for each candidate site, and reject subjectivity in the comparison between sites in terms of engineering considerations. The analysis results supported the discussion in the Second Landing Site Workshop held in August 2015, which resulted in selecting eight candidate sites that will be considered in the third workshop.
Deep learning has quickly become a necessity for selfdriving vehicles on Earth. In contrast, the self-driving vehicles on Mars, including NASA’s latest rover, Perseverance, which is planned to land on Mars in February 2021, are still driven by classical machine vision systems. Deep learning capabilities, such as semantic segmentation and object recognition, would substantially benefit the safety and productivity of ongoing and future missions to the red planet. To this end, we created the first large-scale dataset, AI4Mars, for training and validating terrain classification models for Mars, consisting of ~326K semantic segmentation full image labels on 35K images from Curiosity, Opportunity, and Spirit rovers, collected through crowdsourcing. Each image was labeled by ~10 people to ensure greater quality and agreement of the crowdsourced labels. It also includes ~1.5K validation labels annotated by the rover planners and scientists from NASA’s MSL (Mars Science Laboratory) mission, which operates the Curiosity rover, and MER (Mars Exploration Rovers) mission, which operated the Spirit and Opportunity rovers. We trained a DeepLabv3 model on the AI4Mars training dataset and achieved over 96% overall classification accuracy on the test set. The dataset is made publicly available.1