Data and Image Processing
Data and Image Processing
Algorithms, Data Analysis, Data Processing
Pour: A Framework for Periodic, On-Demand, and User-Specified Information Reconciliation
Pour is a general-purpose information service framework for periodic, on-demand, and user-specified information reconciliation. The technology is designed to accommodate a wide variety of information types with support for high-volume, low-frequency periodic updates, user-specified updates, and automatic updates collected on demand when needed.
Open Source
Visual Environment for Remote Virtual Exploration (VERVE), Version 2
VERVE is a 3D visualization system that provides situational awareness, science analysis tools, and data understanding capabilities for robotics researchers and exploration science operations. The technology is highly modular and extensible and includes a 3D scene-graph database, an interactive 3D viewer, and associated graphical user interfaces to OSGI plugin-based applications.
Open Source
PixelLearn is a tool for classifying the pixels in scientific image data sets. Based on one or more images on the same grid, the tool uses cutting-edge clustering algorithms to automatically find structures in the image, or to label individual classes and use supervised classification methods to extend the labels to the rest of the image.
U.S. Government Purpose Release
Kodiak: A Software Library for Verifying Nonlinear Arithmetic Statements
Kodiak is a software implementation of an algorithm for verifying expressions involving nonlinear real arithmetic. It includes an optimizer for nonlinear real functions, a solver for nonlinear inequalities, and an application programming interface (API) for integrating other software verification tools.
Open Source
Scalable Gaussian Process Regression
Block GP is a Gaussian Process regression framework for multimodal data, that can be an order of magnitude more scalable than existing state-of-the-art nonlinear regression algorithms. The framework builds local Gaussian Processes on semantically meaningful partitions of the data and provides higher prediction accuracy than a single global model with very high confidence. The method relies on approximating the covariance matrix of the entire input space by smaller covariance matrices that can be modeled independently, and can therefore be parallelized for faster execution.
Open Source
Ground and Space Radar Volume Matching and Comparison Software
This software enables easy comparison of ground- and space-based radar observations for validation purposes. It can be accessed at:
Open Source
Spatial Resolution Verification Tool (SRVT)
An automated Spatial Resolution Verification Tool (SRVT) was developed to rapidly determine the spatial resolution characteristics of remotely sensed aerial and satellite imagery. Most current methods for assessing spatial resolution characteristics of imagery rely on pre-deployed engineered targets and are performed only at selected times within pre-selected scenes. The SRVT addresses these insufficiencies by finding uniform, high-contrast edges from urban scenes and then using these edges to determine standard estimators of spatial resolution, such as the modulation transfer function (MTF) and the relative edge response (RER). Developed using the MATLAB programming language and environment, this automated software algorithm assesses every image in an acquired data set, using edges found within each image, and in many cases eliminating the need for dedicated edge targets. SRVT automatically identifies high-contrast, uniform edges and calculates the MTF and RER of each image, and when possible, within sections of an image, so that the variation of spatial resolution characteristics across the image can be analyzed. The automated algorithm is capable of quickly verifying the spatial resolution quality of all images within a data set, enabling the appropriate use of those images in a number of applications. The SRVT has been validated against traditional techniques using IKONOS and QuickBird satellite imagery.
U.S. Government Purpose Release
Land Surface Temperature MODIS Visualization (LaSTMoV)
Extreme heat causes and exacerbates a number of health problems, leading to hospitalization and death in some cases. The problem of severe heat is notably felt in Maricopa County, Arizona, where the socially disadvantaged and physically vulnerable are especially susceptible to the effects of extreme heat. Several organizations, including the Arizona Department of Health Services and the Phoenix Heat Relief Network, are working to create more effectively placed cooling centers and heat warning systems to aid those with the highest risk of exposure. This project created a Python tool using Aqua Moderate Resolution Imaging Spectrometer (MODIS) land surface temperature parameters to generate heat maps that reference demographics data on extreme heat days.
Open Source
Kodiak's Boolean Checker Software Module
Kodiak is a software implementation of a branch-and-bound algorithm for rigorous approximations of expressions involving nonlinear real arithmetic. It includes an optimizer for nonlinear real functions, a solver for nonlinear inequalities, and an Application Programming Interface (API) to integrate directly with other software verification tools. Kodiak's Boolean Checker Software Module is an implementation of a general mixed boolean/real expression checker that is integrated into Kodiak's global optimization solver.
Open Source
View more software
Stay up to date, follow NASA's Technology Transfer Program on:
facebook twitter linkedin youtube
Facebook Logo Twitter Logo Linkedin Logo Youtube Logo