# US 2024/0005491 A1 · Anomaly Detection System

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

- Number: US 2024/0005491 A1
- Document ID: US20240005491A1
- Status: Published application
- Kind: A1
- Application number: 18/230,834
- Filed: 2023-08-07
- Published: 2024-01-04
- Earliest claimed: 2018-01-11
- Assignees: Intelinair, Inc.
- Applicants: Intelinair, Inc.
- Inventors: Ara Victor Nefian; Hrant Khachatryan; Hovnatan Karapetyan; Naira Hovakymian
- Web page: https://patentgrep.com/patent/US20240005491A1

## CPC

- G06T 7/0012: {Biomedical image inspection}
- G06T 5/20: using local operators
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 5/70: Denoising; Smoothing
- G06T 7/0002: {Inspection of images, e.g. flaw detection}
- G06T 7/001: {using an image reference approach}
- G06T 7/10: Segmentation; Edge detection (motion-based segmentation G06T7/215)
- G06T 7/11: Region-based segmentation
- G06T 7/136: involving thresholding
- G06T 7/74: {involving reference images or patches}
- G06V 20/188: {Vegetation}
- G06T 2207/10024: Color image
- G06T 2207/10032: Satellite or aerial image; Remote sensing
- G06T 2207/20021: Dividing image into blocks, subimages or windows
- G06T 2207/30188: Vegetation; Agriculture
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

An image analysis system including an image gathering unit that gathers a high-altitude image having multiple channels, an image analysis unit that segments the high-altitude image into a plurality of equally size tiles and determines an index value based on at least one channel of the image where the image analysis unit identifies areas containing anomalies in each image.

## Claims

### Claim 1

An image analysis system including:
an image capture unit that captures at least one a high-altitude image having multiple channels;
an image analysis unit operating in the memory of a computer that segments the high-altitude image into a plurality of tiles with each tile having a same pixel width and a same pixel height as an adjacent tile and determines an index value based on at least one channel of the image,
wherein
the image analysis unit performs a pixel by pixel analysis of the pixels in each tile to calculate a mean value for each tile,
the image analysis unit applies a Gaussian distribution of the image pixel values to identify outlying values, and
the image analysis unit normalizes the image after applying the Gaussian distribution and calculates a mean and standard deviation values of each pixel, and
the image analysis unit identifies areas containing anomalies in each image by analyzing the mean value for each area connected to identified anomalies to determine areas where anomalies exist, and
a score is assigned to each identified anomaly and an anomaly rectangle is placed on the image to identify areas where anomalies are identified.

### Claim 2 (depends on 1)

The image analysis system of claim 1, wherein the index determined is a normal differential vegetation index for a segment of the captured image.

### Claim 3 (depends on 1)

The image analysis system of claim 1, wherein the index determined is a soil adjusted vegetation index for a segment of the captured image.

### Claim 4 (depends on 1)

The image analysis system of claim 1, wherein the image analysis unit masks the segment of the image using a confidence mask based on the index value.

### Claim 5 (depends on 1)

The image analysis system of claim 1, wherein the image analysis unit applies a box averaging threshold to the segment of the normalized image.

### Claim 6 (depends on 5)

The image analysis system of claim 5, wherein the image analysis unit calculates a mean for each pixel in the applied box.

### Claim 7 (depends on 6)

The image analysis system of claim 6, wherein the image analysis unit removes pixels from the segment of the image that have a calculated mean below a predetermined threshold.

### Claim 8 (depends on 7)

The image analysis system of claim 7, wherein the image analysis unit calculates a score for each of the remaining pixels and draws a rectangle around groups of pixels based on the scores of each pixel.

### Claim 9

An image analysis unit including a processor and a memory with a method of analyzing an image performed in the memory, the method including the steps of:
gathering a high-altitude image having multiple channels via an image capture unit;
segmenting the high-altitude image into a plurality of tiles with each tile having a same pixel width and a same pixel height as an adjacent tile via an image analysis unit;
determining an index value based on at least one channel of the image via the image analysis unit;
applying a Gaussian distribution of the image pixel values to identify outlying values, and
normalizing the image after applying the Gaussian distribution and calculates a mean and standard deviation values of each pixel,
identifying areas containing anomalies in each image via the image analysis unit by analyzing the mean value for each area connected to identified anomalies to determine areas where anomalies exist, and
assigning a score to each identified anomaly and placing an anomaly rectangle on the image to identify areas where anomalies are identified.

### Claim 10 (depends on 9)

The method of claim 9, wherein the index determined is a normal differential vegetation index for a segment of the captured image.

### Claim 11 (depends on 9)

The method of claim 9, wherein the index determined is a soil adjusted vegetation index for a segment of the captured image.

### Claim 12 (depends on 9)

The method of claim 9, wherein the step of identifying anomalies includes masking the segment of the image using a confidence mask based on the index value.

### Claim 13 (depends on 12)

The method of claim 12, wherein the step of identifying anomalies includes applying a box averaging threshold to the segment of the normalized image.

### Claim 14 (depends on 13)

The method of claim 13, wherein the step of identifying anomalies includes calculating a mean for each pixel in the applied box.

### Claim 15 (depends on 14)

The method of claim 14, wherein the step of identifying anomalies includes removing pixels from the segment of the image that have a calculated mean below a predetermined threshold.

### Claim 16 (depends on 15)

The method of claim 15, wherein the step of identifying anomalies includes calculating a score for each of the remaining pixels and drawing a rectangle around groups of pixels based on the scores of each pixel.
