Claims:1. A drone classification device, comprising:
a radio signal receiver configured to receive a radio signal; and
a radio signal analyzer configured to:
determine physical characteristics of the received radio signal;
compare the determined physical characteristics of the received radio signal with a plurality of reference characteristics, each reference characteristics describing a drone class of a plurality of drone classes; and
classify a drone into a drone class of a plurality of drone classes depending on a result of the comparison.

2. The drone classification device of claim 1,
wherein the physical characteristics comprise at least one of a group of physical characteristics comprising:
a carrier frequency of the received radio signal;
locations of peaks in a spectral correlation function of the received radio signal;
a characteristic time of using a first carrier frequency in the received radio signal before switching to a different second carrier frequency;
a frequency shift in the received radio signal caused by motions of the drone.

3. The drone classification device of claim 1,
wherein the determining physical characteristics comprises at least one of a group of processes performed on the received radio signal, the group comprising:
creating a spectral correlation function;
creating a periodogram;
autocorrelating the received radio signal;
creating a spectrogram;
applying a wavelet transform;
applying a time smoothing algorithm;
creating a spectral kurtosis; and
creating a power cepstrum.

4. The drone classification device of claim 1,
wherein a carrier frequency of the received radio signal is in a range from about 2 GHz to about 6 GHz, for example between 2.4 GHz and 2.5 GHz or between 5.725 GHz and 5.875 GHz.

5. The drone classification device of claim 1, further comprising:
a radio signal reader configured to extract communication data frame information from the received radio signal and to combine the extracted information with the assigned drone classification.

6. The drone classification device of claim 1,
wherein the radio signal analyzer is configured to apply a machine learning model for comparing the determined physical characteristics with the plurality of reference characteristics.

7. The drone classification device of claim 1,
wherein the received radio signal is a cyclostationary radio signal.

8. The drone classification device of claim 1,
wherein the plurality of drone classes include at least one of a group of classes comprising:
a manufacturer;
a series;
a model; and
a type.

9. The drone classification device of claim 1,
wherein the radio signal comprises at least one of a group of radio signals comprising:
a radio signal transmitted to a drone;
a radio signal transmitted by the drone; and
a radio signal transmitted to and reflected by the drone.

10. A method of classifying drones, the method comprising:
receiving a radio signal;
determining physical characteristics of the received radio signal;
comparing the determined physical characteristics of the received radio signal a plurality of reference characteristics, each reference characteristics describing a drone class of a plurality of drone classes; and
classifying a drone into a drone class of a plurality of drone classes depending on a result of the comparison.

11. The method of claim 10,
wherein the physical characteristics comprise at least one of a group of physical characteristics comprising:
a carrier frequency of the received radio signal;
locations of peaks in a spectral correlation function of the received radio signal;
a characteristic time of using a first carrier frequency in the received radio signal before switching to a different second carrier frequency;
a frequency shift in the received radio signal caused by motions of the drone.

12. The method of claim 10,
wherein the determining physical characteristics comprises at least one of a group of processes performed on the received radio signal, the group comprising:
creating a spectral correlation function;
creating a periodogram;
autocorrelating the received radio signal;
creating a spectrogram;
applying a wavelet transform;
applying a time smoothing algorithm;
creating a spectral kurtosis; and
creating a power cepstrum.

13. The method of claim 10,
wherein a carrier frequency of the received radio signal is in a range from about 2 GHz to about 6 GHz, for example between 2.4 GHz and 2.5 GHz or between 5.725 GHz and 5.875 GHz.

14. The method of claim 10, further comprising:
extracting communication data frame information from the received radio signal; and
combining the extracted information with the assigned drone classification.

15. The method of claim 10,
applying a machine learning model for comparing the determined physical characteristics with the plurality of reference characteristics.

16. The method of claim 10,
wherein the received radio signal is a cyclostationary radio signal.

17. The method of claim 10,
wherein the drone class comprises at least one of a group of drone classes, the group comprising:
a manufacturer;
a series;
a model; and
a type.

18. The method of claim 10,
wherein the radio signal comprises at least one of a group of radio signals comprising:
a radio signal transmitted to a drone;
a radio signal transmitted by the drone; and
a radio signal transmitted to and reflected by the drone

19. A non-transitory machine-readable storage medium having instructions encoded thereon that, when executed by one or more processors, cause one or more processors to:
receive a radio signal;
determine physical characteristics of the received radio signal;
compare the determined physical characteristics of the received radio signal a plurality of reference characteristics, each reference characteristics describing a drone class of a plurality of drone classes; and
classify a drone into a drone class of a plurality of drone classes depending on a result of the comparison.

, Description:
[0001] The present application claims priority to U.S. Non-Provisional Patent Application No. 17/352,522 filed June 21, 2021 and titled “DRONE CLASSIFICATION DEVICE AND METHOD OF CLASSIFYING DRONES” the entire disclosure of which is hereby incorporated by reference.

Technical Field
[0002] Various embodiments relate generally to a watchdog circuit, to a system-on-chip, to a method of operating a watchdog circuit, and to a method of operating a system-on-chip.
Background
[0003] A presence of a drone in a certain area may be known or suspected. However, a class of the drone, e.g., manufacturer, type, etc., may be unknown.

Brief Description of the Drawings
[0004] In the drawings, like reference characters generally refer to the same parts throughout the different views. The drawings are not necessarily to scale, emphasis instead generally being placed upon illustrating the principles of the invention. In the following description, various embodiments of the invention are described with reference to the following drawings, in which:
FIG. 1 shows a schematic illustration of a drone classification device in accordance with various embodiments receiving radio signals from a drone and/or signals directed at a drone;
FIG. 2A shows a schematic illustration of an analysis performed in a radio signal analyzer included in the drone classification device in accordance with various embodiments, and FIG. 2B displays the results graphically ;
each of FIG. 3A to FIG. 3C shows a power spectrum of a radio signal created as part of an analysis performed in a radio signal analyzer included in the drone classification device in accordance with various embodiments;
each of FIG. 4A and FIG. 4B shows an autocorrelation of a radio signal created as part of an analysis performed in a radio signal analyzer included in the drone classification device in accordance with various embodiments;
FIG. 5 shows a flow diagram of a method of classifying drones in accordance with various embodiments; and
FIG. 6 shows a table listing encoded/transmitted information extracted from WiFi data packets sent to or by drones.

Description
[0005] The following detailed description refers to the accompanying drawings that show, by way of illustration, specific details and embodiments in which the invention may be practiced.
[0006] The word "exemplary" is used herein to mean "serving as an example, instance, or illustration". Any embodiment or design described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments or designs.
[0007] The term “drone” as used herein refers to an unmanned, remote controlled vehicle, for example an unmanned aerial vehicle (UAV).
[0008] Various aspects of the disclosure are provided for devices, and various aspects of the disclosure are provided for methods. It will be understood that basic properties of the devices also hold for the methods and vice versa. Therefore, for sake of brevity, duplicate description of such properties may have been omitted.
[0009] In various embodiments, detecting/identifying and classifying drones based on their unique RF signatures may make use of cyclostationary radio frequency (RF) signal analysis and signal processing algorithms. .
[0010] In various embodiments, the RF signature characterized by modulation and protocol (for example without actually decoding the protocol) may serve as a basis for identifying a drone.
[0011] More specifically, rather than extracting information encoded in the RF signal, classifying a drone may include executing an analysis of physical properties of the RF signal itself, and comparing a result of the analysis to physical properties of known references, for which a drone classification, e.g., a manufacturer and/or a model, type, year, etc., may be known.
[0012] Drone Detection and Classification (DDC) may in various embodiments refer to algorithms, e.g. MATLAB algorithms, and models, e.g. Python models, designed for detecting and classifying drones based on RF signal features that may be characteristic for a modulation and a protocol used by the drones in communication, for example in communication with a control device.