Alerting system for automatically detecting, categorizing, and locating animals using computer aided image comparisons

• US 20160026895A1
• Filed: 07/20/2015
• Published: 01/28/2016
• Est. Priority Date: 07/23/2014
• Status: Active Grant

• Current Assignee: Metecs LLC
• Original Assignee: Metecs LLC
• Inventors: Huffman, Robert Kenneth, Jordan, Daniel David, Zalkin, Chadwick Jason
• Granted Patent: US 9,750,238 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: A01K 29/005 Monitoring or measuring activity, e.g. detecting heat or mating
• CPC Class Codes: A01M 31/002 Detecting animals in a given area
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources
• CPC Class Codes: H04N 7/188 Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position signal generation from motion picture films H04N5/253

Abstract

Described are systems for (a) monitoring real-time animal activity in an area of interest using computer aided image comparison of a real-time image of the area and reference images of animals of interest and (b) providing informed alerts to a user.

Claims

1. A system for (a) monitoring real-time animal activity in an area of interest using computer aided image comparison of a real-time image of the area and reference images of animals of interest and (b) providing informed alerts to a user regarding animal type in said area.

2. The system of claim 1 wherein the system comprises:

a camera mounted in a remote area of interest;

a computer operated microprocessor that is connected to the camera;

wherein, the microprocessor is loaded with reference images of animals;

wherein, the camera is configured to continuously feed real time images of the remote area of interest to the microprocessor;

wherein the microprocessor is configured to (a) construct a static reference background image from said continuous feed of real time images, to (b) programatically compare the continuous feed of real-time images of the area to the static reference background image to identify any incongruity in the real-time images, and to (c) compare said reference images of animals of interest to the incongruities to determine whether any incongruity in the real time image is an animal of interest.

3. The system of claim 2, wherein the microprocessor is configured with programming language and wireless communication hardware so that:

if, after comparison, the incongruities have a match with the reference images, then a wireless signal alerts a user and,

if the detected animal is relevant, the user is notified of the animal'"'"'s presence and activity in the area.

4. The system of claim 2, wherein the camera is connected wirelessly to the computer operated microprocessor.

5. A system comprising:

a camera mounted in a remote area;

a microprocessor connected to the camera;

a wireless communication unit connected to the microprocessor;

wherein the camera is configured to capture images or videos of the area of interest and load those images to the microprocessor;

wherein, the microprocessor (a) is pre-loaded with references images of animals of interest, (b) is continually learning the appearance or background of the area in a static state by a constant photo or video feed from the camera, and (c) is configured to compare the images or video images taken by the camera with the reference images to determine the type, size, and color of animals entering the area of interest; and

,

wherein the wireless communication unit is configured for sending alerts regarding the animal'"'"'s information.

6. The system of claim 5 wherein the microprocessor features computer code in the form of computer image comparison algorithms for comparing images or video from the camera with reference images of animals of interest.

7. The system of claim 6 wherein the computer code comprises a high level logic flowchart as follows:

(1) an image of the static state background or appearance of the area is learned;

(2) reference images of animals of interest and a static image of the area of interest may be input and stored in the microprocessor;

(3) with the reference images stored on the microprocessor, the camera feeds real-time images to the microprocessor;

(4) if a match is found, the object in the real-time image is designated as the animal of the type corresponding to the reference image and categorized, wherein when a positive match occurs with one of the reference images, additional processing will occur, including sending a wireless signal to alert the user that an animal of interest has been spotted at the area of interest.

8. The system of claim 6 wherein learning the static background image or appearance of the area of interest is accomplished via

(a) delivering a video or photo stream is delivered by the camera to the microprocessor,

(b) the microprocessor measures the frame-to-frame foreground, as calculated from a simple frame subtraction wherein the subtraction is done in rectangular subsections of the scene, which has been portioned into a grid of configurable size so that each subsection of the grid is compared to the corresponding subsection in the next frame of the photo or video stream, and when that section of the grid has very little variance, that subsection is considered complete and the image in that subsection is stored as the static background for that subsection, and

(c), when all subsections of the grid have a completed static image, the full static background is stitched together from all the background subsections and stored in the microprocessor.

9. The system of claim 6 wherein the microprocessor is configured to learn the static background image of the area of interest via (1) splitting the frames of a photo or video stream into a grid, (2) processing the photo or video stream for minor variance in each grid section, (3) storing each grid section with minor variance, and (4) stitching a static background together with the stored grid sections with minor variance.

10. The system of claim 8 wherein the real-time images of the area of interest that are loaded on the microprocessor from the camera are compared so that overlapping aspects of the reference image and real-time image are subtracted from each other to identify incongruities between the images and wherein if any incongruities are identified, then the incongruity is compared with the reference images of animals to determine whether the incongruity matches the reference images.

11. The system of claim 10 wherein the microprocessor is a smartphone.