Abstract: Methods, devices and system for designing and deploying one or more data processing pipelines on an embedded system. These data processing pipelines may be deployed without requiring the application running on the embedded system to be rebuilt, redeployed, or halted.

Abstract: Methods and systems for detecting and geolocating features in satellite-captured images include an edge device (e.g., satellite, etc.) receiving from a mission operations center (MOC) an acquisition context and a transformation for mapping pixel coordinates to geographic coordinates and storing the acquisition context and transformation in onboard memory. The edge device may capture one or more images, detect one or more features in the one or more captured images, process the detected features by filtering noise and clustering contiguous features, apply the transformation to the pixel coordinates of the processed detected features to determine geographic coordinates of the detected features, generate geolocation data for the detected features based on the geographic coordinates, and transmit the geolocation data and associated metadata over a low-bandwidth link.

Abstract: The system and methods of the various embodiments enable better capturing of images of objects that are moving relative to a camera. A computing system may be configured to capture a frame containing a target object, generate at least two candidate object bounding boxes for the target object, and determine a candidate object feature vector for the part of the frame contained within each candidate object bounding box. The computing system may compute the distance between each candidate object feature vector and a target object feature vector, selecting the candidate object bounding box associated with the candidate object feature vector that is closest to the target object feature vector, generate partial image statistics on the part of the frame contained within the selected candidate object bounding box, and provide the partial image statistics as input to an AX algorithm that controls the camera.

Abstract: Methods, devices and system for designing and deploying one or more data processing pipelines on an embedded system. These data processing pipelines may be deployed without requiring the application running on the embedded system to be rebuilt, redeployed, or halted.

Abstract: Methods, devices and system for updating a neural network on an edge device that has low-bandwidth uplink capability include a centralized site/device that is configured to train and send the neural network to the edge device. In response, the centralized site/device may receive neural network information from the edge device that includes all or portions of a dataset, output activations, and/or overall inference result that is collected or generated in the edge device. The centralized site/device may use the received neural network information to update all or a part of the trained neural network, generate updated neural network information based on the updated neural network, and send the updated neural network information to the edge device.