IP Library Granted Patent US 11,369,106
Granted Patent B2
US 11,369,106 · App. 16/382,498 · Granted Jun 28, 2022

Automatic animal detection and deterrent system

Inventor: Charles Hartman King (Birmingham, AL)
A01M29/00A01M29/10A01M29/16A01M29/18A01M31/002G06K9/6256G06K9/6262G06N3/08G06N20/00G06V20/52
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,369,106
App. No.
16/382,498
Granted
Jun 28, 2022
Kind
B2
Abstract

This disclosure provides a method of detecting and deterring a target animal from a target area. A target area is positioned within the field of vision of a video camera connected to a computer processing system. An animal identification computer program using convolution neural networks and deep learning computer programs and camera images rapidly detects a target animal. The animal identification computer program is trained to identify target animals accurately using a learning algorithm and related machine learning technology. The time to deploy a deterrent against a target animal from the instant of detection is 2 seconds or less so that little or no time is available to the target animal to damage the target area.

Claims (41)

1. A method of detecting and deterring a target animal from a target area, comprising:

1) placing the target area within the field of vision of a camera, wherein the camera is connected to a computer processing system;

2) running an animal identification computer program using convolution neural networks and deep learning computer programs with camera images from the camera to detect a target animal;

3) verifying if a target animal is in the field of view of the camera;

4) recording the target animal with the camera if the target animal is in the field of view of the camera;

5) arming one or more deterrents and setting a target location;

6) deploying the deterrent to cause the target animal to leave the target area;

7) training the animal identification computer program to identify target animals using a learning algorithm;

8) training the learning algorithm with training data sets;

9) validating the training of the learning algorithm with validation data sets; and

10) creating the training data sets and the validation data sets by gathering target animal image data in a target area, building image data sets for target animals and for target areas from the image data, and annotating or labeling images in the data sets so that the data sets may be entered into the learning algorithm.

2. The method of claim 1 , further comprising stopping the recording after step 6 and saving the recording to a file in the computer.

3. The method of claim 1 , further comprising repeating steps 3 through 6 if the target animal has not left the target area after deploying the deterrent.

4. The method of claim 1 , further comprising continuing to perform step 3 until a target animal is in the field of view of the camera.

5. A method of detecting and deterring a target animal from a target area, comprising:

1) placing the target area within the field of vision of a camera, wherein the camera is connected to a computer processing system;

2) running an animal identification computer program using convolution neural networks and deep learning computer programs with camera images from the camera to detect a target animal, wherein the animal identification computer program is trained to identify target animals using a learning algorithm;

3) verifying if a target animal is in the field of view of the camera;

4) recording the target animal with the camera if the target animal is in the field of view of the camera;

5) arming one or more deterrents and setting a target location;

6) deploying the deterrent to cause the target animal to leave the target area;

7) stopping the recording after step 6 and saving the recording to a file in the computer;

8) training the learning algorithm with training data sets;

9) validating the training of the learning algorithm with validation data sets; and

10) creating the training data sets and the validation data sets by gathering target animal image data in a target area, building image data sets for target animals and for target areas from the image data, and annotating or labeling images in the data sets so that the data sets may be entered into the learning algorithm.

6. The method of claim 5 , further comprising repeating steps 3 through 6 if the target animal has not left the target area after deploying the deterrent.

7. The method of claim 5 , further comprising continuing to perform step 3 until a target animal is in the field of view of the camera.

8. A method of detecting and deterring a target animal from a target area, comprising:

1) placing the target area within the field of vision of a camera, wherein the camera is connected to a computer processing system;

2) running an animal identification computer program using convolution neural networks and deep learning computer programs with camera images from the camera to detect a target animal, wherein the animal identification computer program is trained to identify target animals using a learning algorithm;

3) verifying if a target animal is in the field of view of the camera;

4) recording the target animal with the camera if the target animal is in the field of view of the camera;

5) arming one or more deterrents and setting a target location;

6) deploying the deterrent to cause the target animal to leave the target area;

7) stopping the recording after step 6 and saving the recording to a file in the computer;

8) repeating steps 3 through 6 if the target animal has not left the target area after deploying the deterrent;

9) continuing to perform step 3 until a target animal is in the field of view of the camera;

10) training the learning algorithm with training data sets;

11) validating the training of the learning algorithm with validation data sets; and

12) creating the training data sets and the validation data sets by gathering target animal image data in a target area, building image data sets for target animals and for target areas from the image data, and annotating or labeling images in the data sets so that the data sets may be entered into the learning algorithm.

9. The method of claim 8 , wherein the time from performing step 3 to performing step 6 is 0.25 to 2 seconds.

Assignments (4)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 14, 2025
From: ANIMAL DETERRENT SOLUTIONS, LLC
To: WESTERN ROBOTICS LLC
Reel/Frame 072079/0292 →
SECURITY INTEREST Recorded Jul 11, 2024
From: ANIMAL DETERRENT SOLUTIONS LLC
To: TALLGRASS TECHNOLOGY PARTNERS, LLC
Reel/Frame 068107/0025 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 7, 2023
From: WESTERN ROBOTICS LLC
To: ANIMAL DETERRENT SOLUTIONS LLC
Reel/Frame 063261/0983 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 29, 2023
From: KING, CHARLES HARTMAN
To: WESTERN ROBOTICS LLC
Reel/Frame 063142/0790 →
Continuity (1)
Related Publication 20200323193A1 · Oct 15, 2020