Search NASA⌕ Search

Engineering topics

Thompson, David R.

Publications and source records attributed to Thompson, David R..

120 records · Page 7
All sourcesNASA NTRSDOE OSTI
NASA NTRS2011

Efficient Spectral Endmember Detection Onboard the EO-1 Spacecraft

Spaceflight and planetary exploration place severe constraints on the available bandwidth for downlinking large hyperspectral images. In addition, communications with spacecraft often occur intermittently, so mission-relevant hyperspectral data must wait for analysis on the ground before it can inform spacecraft activity planning. Onboard endmember detection can help alleviate these problems. It enables novelty detection and target identification for scheduling follow-up activities such as additional observation by narrow field of view instruments. Additionally, endmember analysis can facilitate data summary for downlink. This work describes a planned experiment of selective downlink by the EO-1 autonomous spacecraft. Here an efficient superpixel endmember detection algorithm keeps to the limited computational constraints of the flight processor. Tests suggest the procedure could enable significant improvements in downlink efficiency.

Endmember Detection↗
NASA NTRS2011

Metric Learning for Hyperspectral Image Segmentation

We present a metric learning approach to improve the performance of unsupervised hyperspectral image segmentation. Unsupervised spatial segmentation can assist both user visualization and automatic recognition of surface features. Analysts can use spatially-continuous segments to decrease noise levels and/or localize feature boundaries. However, existing segmentation methods use tasks-agnostic measures of similarity. Here we learn task-specific similarity measures from training data, improving segment fidelity to classes of interest. Multiclass Linear Discriminate Analysis produces a linear transform that optimally separates a labeled set of training classes. The defines a distance metric that generalized to a new scenes, enabling graph-based segmentation that emphasizes key spectral features. We describe tests based on data from the Compact Reconnaissance Imaging Spectrometer (CRISM) in which learned metrics improve segment homogeneity with respect to mineralogical classes.

Compact Reconnaissance Imaging Spectrometer (CRISM↗
NASA NTRS2011

Fast Image Texture Classification Using Decision Trees

Texture analysis would permit improved autonomous, onboard science data interpretation for adaptive navigation, sampling, and downlink decisions. These analyses would assist with terrain analysis and instrument placement in both macroscopic and microscopic image data products. Unfortunately, most state-of-the-art texture analysis demands computationally expensive convolutions of filters involving many floating-point operations. This makes them infeasible for radiation- hardened computers and spaceflight hardware. A new method approximates traditional texture classification of each image pixel with a fast decision-tree classifier. The classifier uses image features derived from simple filtering operations involving integer arithmetic. The texture analysis method is therefore amenable to implementation on FPGA (field-programmable gate array) hardware. Image features based on the "integral image" transform produce descriptive and efficient texture descriptors. Training the decision tree on a set of training data yields a classification scheme that produces reasonable approximations of optimal "texton" analysis at a fraction of the computational cost. A decision-tree learning algorithm employing the traditional k-means criterion of inter-cluster variance is used to learn tree structure from training data. The result is an efficient and accurate summary of surface morphology in images. This work is an evolutionary advance that unites several previous algorithms (k-means clustering, integral images, decision trees) and applies them to a new problem domain (morphology analysis for autonomous science during remote exploration). Advantages include order-of-magnitude improvements in runtime, feasibility for FPGA hardware, and significant improvements in texture classification accuracy.

Thompson, David R.↗
NASA NTRS2011

Feature Acquisition with Imbalanced Training Data

This work considers cost-sensitive feature acquisition that attempts to classify a candidate datapoint from incomplete information. In this task, an agent acquires features of the datapoint using one or more costly diagnostic tests, and eventually ascribes a classification label. A cost function describes both the penalties for feature acquisition, as well as misclassification errors. A common solution is a Cost Sensitive Decision Tree (CSDT), a branching sequence of tests with features acquired at interior decision points and class assignment at the leaves. CSDT's can incorporate a wide range of diagnostic tests and can reflect arbitrary cost structures. They are particularly useful for online applications due to their low computational overhead. In this innovation, CSDT's are applied to cost-sensitive feature acquisition where the goal is to recognize very rare or unique phenomena in real time. Example applications from this domain include four areas. In stream processing, one seeks unique events in a real time data stream that is too large to store. In fault protection, a system must adapt quickly to react to anticipated errors by triggering repair activities or follow- up diagnostics. With real-time sensor networks, one seeks to classify unique, new events as they occur. With observational sciences, a new generation of instrumentation seeks unique events through online analysis of large observational datasets. This work presents a solution based on transfer learning principles that permits principled CSDT learning while exploiting any prior knowledge of the designer to correct both between-class and withinclass imbalance. Training examples are adaptively reweighted based on a decomposition of the data attributes. The result is a new, nonparametric representation that matches the anticipated attribute distribution for the target events.

Thompson, David R.↗
NASA NTRS2011

Superpixel-Augmented Endmember Detection for Hyperspectral Images

Superpixels are homogeneous image regions comprised of several contiguous pixels. They are produced by shattering the image into contiguous, homogeneous regions that each cover between 20 and 100 image pixels. The segmentation aims for a many-to-one mapping from superpixels to image features; each image feature could contain several superpixels, but each superpixel occupies no more than one image feature. This conservative segmentation is relatively easy to automate in a robust fashion. Superpixel processing is related to the more general idea of improving hyperspectral analysis through spatial constraints, which can recognize subtle features at or below the level of noise by exploiting the fact that their spectral signatures are found in neighboring pixels. Recent work has explored spatial constraints for endmember extraction, showing significant advantages over techniques that ignore pixels relative positions. Methods such as AMEE (automated morphological endmember extraction) express spatial influence using fixed isometric relationships a local square window or Euclidean distance in pixel coordinates. In other words, two pixels covariances are based on their spatial proximity, but are independent of their absolute location in the scene. These isometric spatial constraints are most appropriate when spectral variation is smooth and constant over the image. Superpixels are simple to implement, efficient to compute, and are empirically effective. They can be used as a preprocessing step with any desired endmember extraction technique. Superpixels also have a solid theoretical basis in the hyperspectral linear mixing model, making them a principled approach for improving endmember extraction. Unlike existing approaches, superpixels can accommodate non-isometric covariance between image pixels (characteristic of discrete image features separated by step discontinuities). These kinds of image features are common in natural scenes. Analysts can substitute superpixels for image pixels during endmember analysis that leverages the spatial contiguity of scene features to enhance subtle spectral features. Superpixels define populations of image pixels that are independent samples from each image feature, permitting robust estimation of spectral properties, and reducing measurement noise in proportion to the area of the superpixel. This permits improved endmember extraction, and enables automated search for novel and constituent minerals in very noisy, hyperspatial images. This innovation begins with a graph-based segmentation based on the work of Felzenszwalb et al., but then expands their approach to the hyperspectral image domain with a Euclidean distance metric. Then, the mean spectrum of each segment is computed, and the resulting data cloud is used as input into sequential maximum angle convex cone (SMACC) endmember extraction.

Thompson, David R.↗
NASA NTRS2010

Sparse Superpixel Unmixing for Hyperspectral Image Analysis

Software was developed that automatically detects minerals that are present in each pixel of a hyperspectral image. An algorithm based on sparse spectral unmixing with Bayesian Positive Source Separation is used to produce mineral abundance maps from hyperspectral images. A superpixel segmentation strategy enables efficient unmixing in an interactive session. The algorithm computes statistically likely combinations of constituents based on a set of possible constituent minerals whose abundances are uncertain. A library of source spectra from laboratory experiments or previous remote observations is used. A superpixel segmentation strategy improves analysis time by orders of magnitude, permitting incorporation into an interactive user session (see figure). Mineralogical search strategies can be categorized as supervised or unsupervised. Supervised methods use a detection function, developed on previous data by hand or statistical techniques, to identify one or more specific target signals. Purely unsupervised results are not always physically meaningful, and may ignore subtle or localized mineralogy since they aim to minimize reconstruction error over the entire image. This algorithm offers advantages of both methods, providing meaningful physical interpretations and sensitivity to subtle or unexpected minerals.

Castano, Rebecca↗
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 NTRS2009

Flightspeed Integral Image Analysis Toolkit

The Flightspeed Integral Image Analysis Toolkit (FIIAT) is a C library that provides image analysis functions in a single, portable package. It provides basic low-level filtering, texture analysis, and subwindow descriptor for applications dealing with image interpretation and object recognition. Designed with spaceflight in mind, it addresses: Ease of integration (minimal external dependencies) Fast, real-time operation using integer arithmetic where possible (useful for platforms lacking a dedicated floatingpoint processor) Written entirely in C (easily modified) Mostly static memory allocation 8-bit image data The basic goal of the FIIAT library is to compute meaningful numerical descriptors for images or rectangular image regions. These n-vectors can then be used directly for novelty detection or pattern recognition, or as a feature space for higher-level pattern recognition tasks. The library provides routines for leveraging training data to derive descriptors that are most useful for a specific data set. Its runtime algorithms exploit a structure known as the "integral image." This is a caching method that permits fast summation of values within rectangular regions of an image. This integral frame facilitates a wide range of fast image-processing functions. This toolkit has applicability to a wide range of autonomous image analysis tasks in the space-flight domain, including novelty detection, object and scene classification, target detection for autonomous instrument placement, and science analysis of geomorphology. It makes real-time texture and pattern recognition possible for platforms with severe computational restraints. The software provides an order of magnitude speed increase over alternative software libraries currently in use by the research community. FIIAT can commercially support intelligent video cameras used in intelligent surveillance. It is also useful for object recognition by robots or other autonomous vehicles

Thompson, David R.↗
NASA NTRS2009

Sparse Superpixel Unmixing for Exploratory Analysis of CRISM Hyperspectral Images

Fast automated analysis of hyperspectral imagery can inform observation planning and tactical decisions during planetary exploration. Products such as mineralogical maps can focus analysts' attention on areas of interest and assist data mining in large hyperspectral catalogs. In this work, sparse spectral unmixing drafts mineral abundance maps with Compact Reconnaissance Imaging Spectrometer (CRISM) images from the Mars Reconnaissance Orbiter. We demonstrate a novel "superpixel" segmentation strategy enabling efficient unmixing in an interactive session. Tests correlate automatic unmixing results based on redundant spectral libraries against hand-tuned summary products currently in use by CRISM researchers.

Image Segmentation↗