Abstract: An imager such as a camera or other suitable device capable of identifying objects, including vehicles, using a variety of techniques. In one form the imager is a roadside camera situated to capture passing vehicles and identify the vehicles. The identification can be accomplished using license plate readers, etc., and can also include the identification of the type of vehicle, color, configuration, etc. The object imaged by the roadside camera can be matched with the object captured using an airborne or orbital imager. Such matching permits the object to be labelled in the images captured from the airborne or orbital imagers, using either the identification of the object or a characteristic of the object. Labelling the object also permits training of a data-driven model using images from the airborne or orbital imagers so that subsequent identification of the objects can be made using the airborne or orbital images with or without the terrestrial based imager.

Abstract: A machine learning model can be developed and deployed to detect a water-based vessel, such as a maritime vessel, using acoustic data collected from sensors structured to detect sound traveling in water caused by operation of the water-based vessel. Information received from satellite tracking of vessels (either transponder based signals or imagery of a body of water having the vessels) can be used as a label to train the machine learning model to discern acoustic signatures related to the labelled vessel. The acoustic data is collected from a water-based platform, such as a buoy, which includes one or more acoustic sensors. Other sensor types can also be used to train the data-based model on other aspects of the vessel, such as radar, infrared, electro-optical, and/or lidar. The buoys can be mounted to the seafloor or permitted to be free floating of the type that can either maneuver itself or be required to be repositioned from time to time. More than one buoy can be used to collect data.