Systems and methods for detecting and classifying drone signals

A non-transitory computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:

• obtaining one or more radio frequency (RF) snapshots, wherein the RF snapshots include a set of signals from an RF source of a first RF source type;
• determining, using the RF snapshots, that a signal of the set of signals is of a first type;
• generating a first training data set based on (i) the one or more RF snapshots and (ii) the determined first signal type of the set of signals;
• annotating the first training data set to generate an annotated first training data set, wherein annotations of the first training data set indicate a particular signal type of RF signals emitted by the first RF source type that is configured to generate RF signals of the first signal type;
• generating a detection and classification model trained to detect the particular signal type of RF signals based on the annotated first training data set;
• and
• providing the trained detection and classification model to a sensor engine to detect and classify one or more new signals from an RF source of the first RF source type using the trained detection and classification model.

A system, comprising:

• one or more processors;
• and
• machine-readable media interoperably coupled with the one or more processors and storing one or more instructions that, when executed by the one or more processors, perform operations comprising:
• obtaining one or more radio frequency (RF) snapshots, wherein the RF snapshots include a set of signals from an RF source of a first RF source type;
• determining, using the RF snapshots, that a signal of the set of signals is of a first type;
• generating a first training data set based on (i) the one or more RF snapshots and (ii) the determined first signal type of the set of signals;
• annotating the first training data set to generate an annotated first training data set, wherein annotations of the first training data set indicate a particular signal type of RF signals emitted by the first RF source type that is configured to generate RF signals of the first signal type;
• generating a detection and classification model trained to detect the particular signal type of RF signals based on the annotated first training data set;
• and
• providing the trained detection and classification model to a sensor engine to detect and classify one or more new signals from an RF source of the first RF source type using the trained detection and classification model.