# US 9,697,850 B2 · Drone detection and classification methods and apparatus

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 9,697,850 B2
- Document ID: US9697850B2
- Status: Granted
- Kind: B2
- Application number: 14/950,593
- Filed: 2015-11-24
- Published: 2016-04-28
- Granted: 2017-07-04
- Earliest claimed: 2014-04-22
- Assignees: Droneshield, LLC
- Applicants: DroneShield, LLC
- Inventors: Brian Hearing; John Franklin
- Web page: https://patentgrep.com/patent/US9697850B2

## CPC

- G10L 25/51: for comparison or discrimination
- G01H 1/00: Measuring {characteristics of} vibrations in solids by using direct conduction to the detector (G01H9/00, G01H11/00 take precedence)
- G01S 3/80: using ultrasonic, sonic or infrasonic waves
- G01S 5/18: using ultrasonic, sonic or infrasonic waves
- G10L 19/00: Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis (in musical instruments G10H)
- G10L 25/18: the extracted parameters being spectral information of each sub-band
- G10L 25/54: for retrieval
- H04R 29/00: Monitoring arrangements; Testing arrangements {(for hearing aids H04R25/30; detection of loudspeaker connection H04R5/04; sound-field adaptation dependent on speaker detection H04S7/308)}
- H04R 2410/00: Microphones
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G01H: MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- H04R: LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS (producing sounds with frequency not determined by supply frequency G10K)

## Abstract

A system, method, and apparatus for drone detection and classification are disclosed. An example method includes receiving a sound signal in a microphone and recording, via a sound card, a digital sound sample of the sound signal, the digital sound sample having a predetermined duration. The method also includes processing, via a processor, the digital sound sample into a feature frequency spectrum. The method further includes applying, via the processor, broad spectrum matching to compare the feature frequency spectrum to at least one drone sound signature stored in a database, the at least one drone sound signature corresponding to a flight characteristic of a drone model. The method moreover includes, conditioned on matching the feature frequency spectrum to one of the drone sound signatures, transmitting, via the processor, an alert.

## Claims

### Claim 1

An apparatus for creating a drone signature library comprising:
a microphone configured to receive a sound signal from a drone;
a sound card configured to record a digital sound sample of the sound signal; and
a sample processor configured to:
partition the digital sound sample into a predetermined number of segments having a specified duration,
convert each of the segments into a vector of frequency amplitudes by applying a frequency domain transformation to the segments,
form a composite frequency vector by averaging the vectors,
determine a drone component within the composite frequency vector,
receive drone information indicative of a type of the drone,
associate the drone information with the drone component of the composite frequency vector,
store information related to the drone component of the composite frequency vector and the drone information to the drone signature library, and
use the information related to the drone component and the drone information for detection of drones.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the sound signal is generated by at least one of a sound machine, a user device operating an application configured to cause the user device to generate the sound signal, and a drone.

### Claim 3 (depends on 1)

The apparatus of claim 1, wherein the identifier specifies at least one of a drone type, a drone class, and a drone flight characteristic.

### Claim 4 (depends on 3)

The apparatus of claim 3, wherein the drone flight characteristic includes at least one of retreating, advancing, sideways translating, rotating, hovering, inverting, ascending, and descending; and
wherein the drone type includes at least one of a brand name, a model name, a part number, and a rotor configuration.

### Claim 5 (depends on 1)

The apparatus of claim 1, wherein the calibration processor is configured to:
determine at least one of (i) tuning parameters, and (ii) calibration filters for different sound signals;
combine the at least one of (i) and (ii) for the different sound signals into at least one of an average tuning parameter and an average calibration filter; and
apply the at least one of an average tuning parameter and an average calibration filter to the sample processor.

### Claim 6 (depends on 5)

The apparatus of claim 5, wherein the different sound signals are generated by a sound machine according to a predetermined routine and are configured to account for particular tones.

### Claim 7 (depends on 1)

The apparatus of claim 1, wherein the at least one of the tuning parameter and the calibration filter is configured to at least one of:
shift a frequency of a subsequent digital sound sample,
filter a component from a subsequent digital sound sample,
shift a phase of a subsequent digital sound sample,
shift a frequency peak within a subsequent digital sound sample or a subsequent measured composite frequency vector, and
smooth a frequency peak within a subsequent digital sound sample or a subsequent measured composite frequency vector.

### Claim 8 (depends on 1)

The apparatus of claim 1, wherein the calibration processor is configured to be activated after the microphone is placed in a location to detect drones.

### Claim 9 (depends on 1)

The apparatus of claim 1, wherein the calibration processor is configured to receive from a management server, via a network, the calibration frequency vector.

### Claim 10 (depends on 1)

The apparatus of claim 1, wherein the sample processor is configured to:
smooth the vectors of each of the segments using a filter; and
form the measured composite frequency vector by averaging the smoothed vectors.

### Claim 11 (depends on 1)

The apparatus of claim 1, wherein the predetermined number of segments are equal-sized and non-overlapping.

### Claim 12

A drone detection apparatus comprising:
a microphone configured to receive a sound signal that is related to a drone;
a sound card configured to record a measured digital sound sample of the sound signal; and
a calibration processor configured to:
receive an identifier that is related to the digital sound sample,
select a calibration digital sound sample stored in a memory that corresponds to the received identifier,
determine differences between the measured digital sound sample and the calibration digital sound sample,
determine a tuning parameter based on the determined differences, and
calibrate a sample processor using the tuning parameter for identifying a drone from subsequent sound signals recorded by the microphone.

### Claim 13 (depends on 12)

The apparatus of claim 12, wherein at least one of:
(i) the sound signal includes background noise, and
(ii) the sound signal is affected by an environmental characteristic.

### Claim 14 (depends on 13)

The apparatus of claim 13, wherein the calibration processor is configured to calibrate the sample processor to at least one of compensate for the background noise and compensate for the environmental characteristic.

### Claim 15 (depends on 12)

The apparatus of claim 12, wherein the calibration processor is configured to calibrate the sample processor by causing the sample processor to apply the tuning parameter to the subsequent sound signals.

### Claim 16 (depends on 12)

The apparatus of claim 12, wherein the calibration processor is configured to calibrate the sample processor by causing the sample processor to apply the tuning parameter to frequency signatures related to drones.

### Claim 17 (depends on 12)

The apparatus of claim 12, wherein the calibration processor is configured to:
determine a calibration filter based on the determined differences between the measured digital sound sample and the calibration digital sound sample; and
calibrate the sample processor using the calibration filter.

### Claim 18

A method for calibrating a drone detection device comprising:
(i) receiving, in a microphone, a sound signal that is representative of a drone;
(ii) recording, via a sound card, a digital sound sample of the sound signal;
(iii) partitioning, via a processor, the digital sound sample into a predetermined number of segments having a specified duration;
(iv) converting, via the processor, each of the segments into a vector of frequency amplitudes by determining an absolute value of a Fast Fourier Transform applied to the respective segment;
(vi) receiving, in the processor, an identifier that is related to the sound signal;
(vii) selecting, via the processor, a calibration frequency vector stored in a memory that corresponds to the received identifier;
(viii) determining, via the processor, a difference between the calibration frequency vector and each of the vectors of frequency amplitudes;
(ix) determining, via the processor, a tuning parameter based on the determined differences; and
(x) applying, via the processor, the tuning parameter for compensation when sound signals are recorded by the microphone.

### Claim 19 (depends on 18)

The method of claim 18,
wherein step (iv) includes:
smoothing, via the processor, the vectors of each of the segments using a filter, and
averaging, via the processor, the smoothed vectors to form a measured composite frequency vector;
wherein step (viii) includes determining, via the processor, a difference between the calibration frequency vector and the measured composite frequency vector; and
wherein step (ix) includes determining, via the processor, the tuning parameter based on the determined difference between the calibration frequency vector and the measured composite frequency vector.

### Claim 20 (depends on 18)

The method of claim 18, wherein steps (i) to (ix) are repeated for at least one of different flight characteristics of a drone and different types of drones, and
wherein the step (x) further includes:
averaging the tuning parameter based on each iteration of steps (i) to (ix), and
applying the averaged tuning parameter for the detection of drones.

### Claim 21 (depends on 20)

The method of claim 20, wherein the sound signal for each iteration of steps (i) to (ix) is generated according to a predetermined routine and includes predetermined tones known to be affected by environmental characteristics.

### Claim 22 (depends on 21)

The method of claim 21, wherein the predetermined routine is operated by an application operating on a user device, and wherein the method further comprises, for each sound signal within the predetermined routine, transmitting the corresponding identifier from the application to the processor.

### Claim 23 (depends on 18)

The method of claim 18, wherein the identifier is generated acoustically and provided in conjunction with the sound signal.

### Claim 24 (depends on 18)

The method of claim 18, wherein the sound signal is representative of a sound emitted by a drone.