IP Library Granted Patent US 11,227,382
Granted Patent B2
US 11,227,382 · App. 16/245,743 · Granted Jan 18, 2022

Change detection system

Inventors: Ara Victor Nefian (San Francisco, CA); Hrant Khachatryan (Yerevan, AM); Hovnatan Karapetyan (Yerevan, AM); Naira Hovakymian (Champaign, IL)
Assignee: Intelinair, Inc.
G06T7/001G06K9/00657G06K9/6212G06T5/002G06T5/20G06T5/50G06T7/0002G06T7/0012G06T7/10G06T7/11G06T7/136G06T7/74G06T2207/10024G06T2207/10032G06T2207/20021G06T2207/30188
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 11,227,382
App. No.
16/245,743
Granted
Jan 18, 2022
Kind
B2
Abstract

A change detection system including an image analysis unit that analyzes an image gathered from an image gathering unit, a change detection unit that detects changes in a plurality of images taken over a predetermined time, where the change detection unit modifies the image to indicate areas where a change has occurred.

Claims (28)

1. A change detection system including:

an image analysis unit configured to analyze an image gathered from an image gathering unit affixed to an airplane or drone;

a change detection unit configured to detect changes in a plurality of images taken over a predetermined time,

wherein,

the change detection unit separates each image into a plurality of tiles of a predetermined size,

an Otsu binary thresholding is applied to each pixel in each tile,

a vegetation mask having an analog value greater than 0 is assigned to each pixel based on the Otsu binary thresholding with pixels not assigned to vegetation being assigned a value of 0, and

the image analysis unit is configured to perform a pixel by pixel analysis of each pixel with a vegetation mask greater then 0 in each tile and to compare each pixel to a corresponding pixel stored over a predetermined period of time to determine a deviation in each pixel over time, and

the change detection unit modifies the image to indicate areas where a change has occurred.

2. The change detection system of claim 1 , wherein the change detection unit calculates a normalized differential vegetation index for each image gathered.

3. The change detection system of claim 1 , wherein the change detection unit calculates a soil adjusted vegetation index for each image gathered.

4. The change detection system of claim 1 , wherein the change detection unit performs a Gaussian blur to each tile.

5. The change detection system of claim 1 , wherein the change detection unit applies a local statistics method to each tile.

6. The change detection system of claim 1 , wherein each tile is a square.

7. The change detection system of claim 6 , wherein each square is 25 pixels by 25 pixels.

8. A change detection unit including a processor and a memory with a program being executed in the memory, the program performing the steps of:

analyzing an image gathered from an image gathering unit;

separating by the change detection unit each image into a plurality of tiles of a predetermined size,

applying an Otsu binary thresholding to each pixel in each tile,

assigning a vegetation mask having an analog value greater than 0 to each pixel based on the Otsu binary thresholding with pixels not assigned to vegetation being assigned a value of 0, and

performing a pixel by pixel analysis of each pixel with a vegetation mask greater then 0 in each tile and compare each pixel to a corresponding pixel stored over a predetermined period of time to determine a deviation in each pixel over time

wherein the change detection unit modifies the image to indicate areas where a change has occurred.

9. The method of claim 8 , including the step of calculating a normalized differential vegetation index for each image gathered.

10. The method of claim 8 , including the step of calculating a soil adjusted vegetation index for each image gathered.

11. The change detection system of claim 8 , wherein the change detection unit performs a Gaussian blur to each tile.

12. The change detection system of claim 8 , wherein the change detection unit applies a local statistics method to each tile.

13. The change detection system of claim 8 , wherein each tile is a square.

14. The method of claim 13 , wherein each square is 25 pixels by 25 pixels.

Assignments (1)
SECURITY INTEREST Recorded Mar 9, 2022
From: INTELINAIR, INC.
To: MCKINSEY & COMPANY, INC. UNITED STATES
Reel/Frame 059206/0843 →
Continuity (2)
Provisional Application 62616159 · Jan 11, 2018
Related Publication 20190213731A1 · Jul 11, 2019
Cited By (1)
US 12,430,734