Abstract: Systems and methods are provided for generating sets of candidates comprising images and places within a threshold geographic proximity based on geographic information associated with each of the plurality of images and geographic information associated with each place. For each set of candidates, the systems and methods generate a similarity score based on a similarity between text extracted from each image and a place name, and the geographic information associated with each image and each place. For each place with an associated image as a potential match, the systems and methods generate a name similarity score based on matching the extracted text of the image to the place name, and store an image as place data associated with a place based on determining that the name similarity score for the extracted text associated with the image is higher than a second predetermined threshold.

Abstract: Systems and methods are provided for generating sets of candidates comprising images and places within a threshold geographic proximity based on geographic information associated with each of the plurality of images and geographic information associated with each place. For each set of candidates, the systems and methods generate a similarity score based on a similarity between text extracted from each image and a place name, and the geographic information associated with each image and each place. For each place with an associated image as a potential match, the systems and methods generate a name similarity score based on matching the extracted text of the image to the place name, and store an image as place data associated with a place based on determining that the name similarity score for the extracted text associated with the image is higher than a second predetermined threshold.

Abstract: Systems and methods are provided for generating sets of candidates comprising images and places within a threshold geographic proximity based on geographic information associated with each of the plurality of images and geographic information associated with each place. For each set of candidates, the systems and methods generate a similarity score based on a similarity between text extracted from each image and a place name, and the geographic information associated with each image and each place. For each place with an associated image as a potential match, the systems and methods generate a name similarity score based on matching the extracted text of the image to the place name, and store an image as place data associated with a place based on determining that the name similarity score for the extracted text associated with the image is higher than a second predetermined threshold.

Abstract: A system classifies a compressed image or predicts likelihood values associated with a compressed image. The system partially decompresses compressed JPEG image data to obtain blocks of discrete cosine transform (DCT) coefficients that represent the image. The system may apply various transform functions to the individual blocks of DCT coefficients to resize the blocks so that they may be input together into a neural network for analysis. Weights of the neural network may be trained to accept transformed blocks of DCT coefficients which may be less computationally intensive than accepting raw image data as input.

Abstract: Example systems and methods improve a location detection process. A system accesses image data and image metadata, whereby the image data captures images of a plurality of objects from different views, each image having corresponding image metadata. The system then detects each object in the plurality of objects in the image data. A plurality of rays in three-dimensional space is generated, whereby each ray of the plurality of rays is generated based on the detected objects and the corresponding image metadata. The system predicts object locations using the generated rays based on a probabilistic triangulation of the rays. The networked system updates map data using the predicted object locations. The updating includes adding objects at their predicted object locations to the map data. The map data is used to generate a map.

Abstract: Systems and methods are provided for generating sets of candidates comprising images and places within a threshold geographic proximity based on geographic information associated with each of the plurality of images and geographic information associated with each place. For each set of candidates, the systems and methods generate a similarity score based on a similarity between text extracted from each image and a place name, and the geographic information associated with each image and each place. For each place with an associated image as a potential match, the systems and methods generate a name similarity score based on matching the extracted text of the image to the place name, and store an image as place data associated with a place based on determining that the name similarity score for the extracted text associated with the image is higher than a second predetermined threshold.

Abstract: A system classifies a compressed image or predicts likelihood values associated with a compressed image. The system partially decompresses compressed JPEG image data to obtain blocks of discrete cosine transform (DCT) coefficients that represent the image. The system may apply various transform functions to the individual blocks of DCT coefficients to resize the blocks so that they may be input together into a neural network for analysis. Weights of the neural network may be trained to accept transformed blocks of DCT coefficients which may be less computationally intensive than accepting raw image data as input.

Abstract: A system identifies areas of interest (e.g., locations of text or objects) in an image in a way that reduces memory requirements, computer processing requirements, and computation time. The system analyzes a downscaled version of an input image using a convolutional neural network that has been trained to recognize areas of interest in coarse, low resolution, images. Based on the output of the coarse neural network, the system predicts particular segments of the image that are most likely to include areas of interest. A second convolutional neural network that has been trained to identify areas of interest in fine, high resolution images analyzes only those segments of the image that the coarse neural network selected for further examination. A reconstruction of the analysis locates likely areas of interest for the whole image.

Abstract: A system for performing global-scale damage detection using satellite imagery, comprising a damage detection server that receives and analyzes image data to identify objects within an image via a curated computational method, and a curation interface that enables a user to curate image information for use in object identification, and a method for a curated computational method for performing global scale damage detection.

Abstract: Utilities (e.g., systems, methods, etc.) for automatically generating high resolution population density estimation data sets through manipulation of low resolution population density estimation data sets with high resolution overhead imagery data (e.g., such as overhead imagery data acquired by satellites, aircrafts, etc. of celestial bodies). Stated differently, the present utilities make use of high resolution overhead imagery data to determine how to distribute the population density of a large, low resolution cell (e.g., 1000m) among a plurality of smaller, high resolution cells (e.g., 100m) within the larger cell.

Abstract: A system for automatically characterizing areas of interest (e.g., urban areas, forests, and/or other compound structures) in high resolution overhead imagery through manipulation of a dictionary of visual words. The pixels of an input overhead image are initially clustered into a plurality of hierarchically-arranged connected components of a first hierarchical data structure. Image descriptors (e.g., shape, spectral, etc.) of the connected components are then clustered into a plurality of hierarchically-arranged nodes of a second hierarchical data structure. The nodes at a particular level in the second hierarchical data structure become a dictionary of visual words. Subsets of the visual words may be used to label the cells of a grid over the geographic area as falling into one of a number of areas of interest. Categorization information from the grid may be mapped into a resultant image whereby pixels depict their respective type of area of interest.

Abstract: A system for automatically characterizing areas of interest (e.g., urban areas, forests, and/or other compound structures) in high resolution overhead imagery through manipulation of a dictionary of visual words. The pixels of an input overhead image are initially clustered into a plurality of hierarchically-arranged connected components of a first hierarchical data structure. Image descriptors (e.g., shape, spectral, etc.) of the connected components are then clustered into a plurality of hierarchically-arranged nodes of a second hierarchical data structure. The nodes at a particular level in the second hierarchical data structure become a dictionary of visual words. Subsets of the visual words may be used to label the cells of a grid over the geographic area as falling into one of a number of areas of interest. Categorization information from the grid may be mapped into a resultant image whereby pixels depict their respective type of area of interest.

Abstract: Utilities (e.g., systems, methods, etc.) for automatically generating high resolution population density estimation data sets through manipulation of low resolution population density estimation data sets with high resolution overhead imagery data (e.g., such as overhead imagery data acquired by satellites, aircrafts, etc. of celestial bodies). Stated differently, the present utilities make use of high resolution overhead imagery data to determine how to distribute the population density of a large, low resolution cell (e.g., 1000 m) among a plurality of smaller, high resolution cells (e.g., 100 m) within the larger cell.

Abstract: A system for performing global-scale damage detection using satellite imagery, comprising a damage detection server that receives and analyzes image data to identify objects within an image via a curated computational method, and a curation interface that enables a user to curate image information for use in object identification, and a method for a curated computational method for performing global scale damage detection.

Abstract: A system for automatically extracting interesting structures or areas (e.g., built-up structures such as buildings, tents, etc.) from HR/VHR satellite imagery data using corresponding LR satellite imagery data. The system breaks down HR/VHR input satellite images into a plurality of components (e.g., groups of pixels), organizes the components into a first hierarchical data structure (e.g., a Max-Tree), generates a second hierarchical data structure (e.g., a KD-Tree) from feature elements (e.g., spectral and shape characteristics) of the components, uses LR satellite imagery data to categorize components as being of interest or not, uses the feature elements of the categorized components to train the second data structure to be able to classify all components of the first data structure as being of interest or not, classifies the components of the first data structure with the trained second data structure, and then maps components classified as being of interest into a resultant image.

Abstract: Utilities (e.g., systems, methods, etc.) for automatically generating high resolution population density estimation data sets through manipulation of low resolution population density estimation data sets with high resolution overhead imagery data (e.g., such as overhead imagery data acquired by satellites, aircrafts, etc. of celestial bodies). Stated differently, the present utilities make use of high resolution overhead imagery data to determine how to distribute the population density of a large, low resolution cell (e.g., 1000 m) among a plurality of smaller, high resolution cells (e.g., 100 m) within the larger cell.

Abstract: A system for automatically characterizing areas of interest (e.g., urban areas, forests, and/or other compound structures) in high resolution overhead imagery through manipulation of a dictionary of visual words. The pixels of an input overhead image are initially clustered into a plurality of hierarchically-arranged connected components of a first hierarchical data structure. Image descriptors (e.g., shape, spectral, etc.) of the connected components are then clustered into a plurality of hierarchically-arranged nodes of a second hierarchical data structure. The nodes at a particular level in the second hierarchical data structure become a dictionary of visual words. Subsets of the visual words may be used to label the cells of a grid over the geographic area as falling into one of a number of areas of interest. Categorization information from the grid may be mapped into a resultant image whereby pixels depict their respective type of area of interest.

Abstract: Utilities (e.g., systems, methods, etc.) for automatically generating high resolution population density estimation data sets through manipulation of low resolution population density estimation data sets with high resolution overhead imagery data (e.g., such as overhead imagery data acquired by satellites, aircrafts, etc. of celestial bodies). Stated differently, the present utilities make use of high resolution overhead imagery data to determine how to distribute the population density of a large, low resolution cell (e.g., 1000 m) among a plurality of smaller, high resolution cells (e.g., 100 m) within the larger cell.

Abstract: A system for automatically extracting interesting structures or areas (e.g., built-up structures such as buildings, tents, etc.) from HR/VHR satellite imagery data using corresponding LR satellite imagery data. The system breaks down HR/VHR input satellite images into a plurality of components (e.g., groups of pixels), organizes the components into a first hierarchical data structure (e.g., a Max-Tree), generates a second hierarchical data structure (e.g., a KD-Tree) from feature elements (e.g., spectral and shape characteristics) of the components, uses LR satellite imagery data to categorize components as being of interest or not, uses the feature elements of the categorized components to train the second data structure to be able to classify all components of the first data structure as being of interest or not, classifies the components of the first data structure with the trained second data structure, and then maps components classified as being of interest into a resultant image.