Abstract: Techniques for improving the quality of images captured by a remote sensing overhead platform such as a satellite. Sensor shifting is employed in an open-loop fashion to compensate for relative motion of the remote sensing overhead platform to the Earth. Control signals are generated for the sensor shift mechanism by an orbital motion compensation calculation that uses the predicted ephemeris (including orbit dynamics) and image geometry (overhead platform to target). Optionally, the calculation may use attitude and rate errors that are determined from on-board sensors.

Abstract: Techniques for atmospheric compensation in satellite imagery that include converting an image including an array of radiance values to an array of surface reflectance values. The conversion is performed in an automated fashion by identifying one or more portions of the image for which the surface reflectance can be estimated and determining the Aerosol Optical Depth (AOD) by iteratively comparing the radiance value captured by the image sensor to a calculated radiance value (based on the known surface reflectance, historical values for other atmospheric parameters, and the AOD) and adjusting the AOD until the calculated radiance value is substantially the same as the captured radiance value.

Abstract: Techniques for automatically determining, on a pixel by pixel basis, whether imagery includes ground images or is obscured by cloud cover. The techniques include training a Neural Network, making an initial determination of cloud or ground by using the Neural Network, and performing a max-flow, min-cut operation on the image to determine whether each pixel is a cloud or ground imagery.

Abstract: A system and methods for muddy water detection using normalized semantic layers, wherein a spectrum analyzer isolates spectrum bands within an image to produce a set of three normalized differential index images from which a composite color image is created, from which a power band is computed, from which a two-color image is produced, and then filters image components within the two-color representation based on defined criteria.

Abstract: A system for modular image mining and search, comprising a plurality of image capture devices, a search engine, an indexing engine, a database, and user interface software. A plurality of image capture devices capture images and store them to a database. The indexing engine indexes images to create image data for each image with associated metadata and stores the information to the database. The interface software is used to request search queries via a search engine. The search engine accesses the image data to find images or parts of images that satisfy the search query.

Abstract: A system for automated mosaic-based vector editing comprising a mosaic imaging server that assembles image tiles to form larger image mosaics while correcting the image tiles for tonality and other visual characteristics, a vector analysis server that analyzes vector information, a routing calculation server that calculates routes from the vector information, and a rendering engine that produces visualizations from the routing information, and a method for image mosaic creation and correction.

Abstract: A system for automated geospatial image analysis comprising a deep learning model that receives orthorectified geospatial images, pre-labeled to demarcate objects of interest. The module presents marked geospatial images and a second set of unmarked, optimized, training geospatial images to a convolutional neural network. This process may be repeated so that an image analysis software module can detect multiple object types or categories. The image analysis software module receives orthorectified geospatial images from one or more geospatial image caches. Using a multi-scale sliding window submodule, image analysis software scans geospatial images, detects objects present and geospatially locates them.

Abstract: A system and various methods for processing an image to produce a hierarchical image representation model, segment the image model using shape criteria to produce positive and negative training data sets as well as a search-space data set comprising shapes matched to a search query provided as input, and using the training data sets to train a machine learning model to improve recognition of shapes that are similar to an input query without being exact matches, to improve object recognition.

Abstract: A system for simplified generation of systems for analysis of satellite images to geolocate one or more objects of interest. A plurality of training images labeled for a study object or objects with irrelevant features loaded into a preexisting feature identification subsystem causes automated generation of models for the study object. This model is used to parameterize pre-engineered machine learning elements that are running a preprogrammed machine learning protocol. Training images with the study are used to train object recognition filters. This filter is used to identify the study object in unanalyzed images. The system reports results in a requestor's preferred format.

Abstract: A system for large-scale crowd sourcing of map data cleanup and correction, comprising an application server that generates image data, sends image data to a user device, receives tagging data provided by the device user, and provides tags to a crowdsourced search and locate server based on tagging data from a user device, a crowdsourced search and locate server that receives tags from an application server, computes agreement and disagreement values and performs expectation-maximization analysis, and a map data server that stores and provides map data, and a method for estimating location and quality of a set of geolocation data.

Abstract: A system for semi-automated feature extraction comprising an image analysis server that receives and initializes a plurality of raster images, a feature extraction server that identifies and extracts image features, a mosaic server that assembles mosaics from multiple images, and a rendering engine that provides visual representations of images for review by a human user, and a method for generating a cost raster utilizing the system of the invention.

Abstract: A system for vector extraction comprising a vector extraction engine stored and operating on a network-connected computing device that loads raster images from a database stored and operating on a network-connected computing device, identifies features in the raster images, and computes a vector based on the features, and methods for feature and vector extraction.

Abstract: A system for automated tonal balancing, comprising a rectification server that groups and processes images for use in tone-matching and provides them to a tone-matching server, that then performs tone-matching operations on the images and provides them as output for review or storage, and methods for tonal balancing using the system of the invention.

Abstract: A system for automated vector updating, comprising a database that stores raster and vector information, and a vector processing server that algorithmically processes vectors for updates, and methods for algorithm-based vector updating.

Abstract: A crowdsourced search and locate platform has been developed and put into practice. A plurality of geospatial images of a geographical region of interest are presented to a plurality of participants in an internet mediated crowdsourcing campaign for the purpose of identifying and tagging specific features of interest to the campaign administrator. An algorithm of the invention, CrowdRank, monitors the identification accuracy of the participants both absolute and compared to other participants calculating a score used to weight each identification made by that user. CrowdRank also chooses images to maximize campaign efficiency and calculates the confidence level of each feature identification.

Abstract: A system for broad area geospatial object recognition, identification, classification, location and quantification, comprising an image manipulation module to create synthetically-generated images to imitate and augment an existing quantity of orthorectified geospatial images; together with a deep learning module and a convolutional neural network serving as an image analysis module, to analyze a large corpus of orthorectified geospatial images, identify and demarcate a searched object of interest from within the corpus, locate and quantify the identified or classified objects from the corpus of geospatial imagery available to the system. The system reports results in a requestor's preferred format.

Abstract: A system for advanced vector editing, comprising a vector analysis server that analyzes vector information, a routing calculation server that calculates routes from the vector information, and a rendering engine that produces visualizations from the routing information, and several methods for advanced vector editing in two- and three-dimensional visualizations.

Abstract: A database for creating orthomosaics, where the database is tailored to retrieve the most recent imagery for each pixel, in an efficient manner that partitions the orthomosaic into sufficiently small chunks that can each be quickly processed.

Abstract: A system for incorporating geographical data into a map-related system, adding objects being tracked while moving within a specific geographic area and automatically analyzing their movement characteristics; wherein the tracking is done by visual means from a sky-borne platform.

Abstract: Techniques for automatically determining, on a pixel by pixel basis, whether imagery includes ground images or is obscured by cloud cover. The techniques include training a cloud dictionary and a ground dictionary, determining whether a given pixel is best represented by “words” from the cloud dictionary or “words” from the ground dictionary to make an initial determination of cloud or ground, and performing a max-flow, min-cut operation on the image to determine whether each pixel is a cloud or ground imagery.