| CPC G05D 1/106 (2019.05) [G05D 1/0094 (2013.01); G05D 1/104 (2013.01); G06V 20/17 (2022.01); B64U 10/13 (2023.01); B64U 2101/00 (2023.01); B64U 2101/10 (2023.01); B64U 2101/30 (2023.01)] | 3 Claims |
|
1. A method comprising
performing one or more monitoring actions by a drone at one or more locations during a mission comprising a plurality of mission requirements, wherein the mission requirements require the drone to fly in a particular pattern over a designated area to identify objects of interest;
identifying, via the drone, one or more vehicles at one or more locations based on image data captured by the drone;
forwarding, via the drone, the image data to a ground station;
performing, via the ground station, with machine-learning models to determine whether the one or more vehicles are above a threat threshold and require additional action by the drone based on an image analysis of the image data including the one or more vehicles being paired with stored image data of known vehicles associated with the threat threshold;
receiving, via the drone, a mission update from the ground station comprising additional mission objectives, wherein the mission update comprises additional flying patterns to identify a candidate object which is predicted to be present within a predefined area between the one or more vehicles based on the machine-learning models determining a likelihood of a presence of the candidate object;
determining a range of additional locations for the drone to perform one or more new monitoring actions comprising additional image captures and communication signal monitoring
performing the one or more new monitoring actions by the drone; and
performing an image analysis of the additional image captures to identify the candidate object.
|