# US 2026/0073681 A1 · Apparatus and method for processing high-altitude images

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

- Number: US 2026/0073681 A1
- Document ID: US20260073681A1
- Status: Published application
- Kind: A1
- Application number: 19/323,809
- Filed: 2025-09-09
- Published: 2026-03-12
- Earliest claimed: 2024-09-12
- Assignees: Near Space Labs, Inc.
- Applicants: Near Space Labs, Inc.
- Inventors: Alexandra Moseguí Saladié; Ignasi Lluch i Cruz; Albert Caubet; Asa Jonas Ivry Block; Hripsime Matevosyan
- Web page: https://patentgrep.com/patent/US20260073681A1

## CPC

- G06V 20/17: taken from planes or by drones
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 5/60: using machine learning, e.g. neural networks
- G06T 5/77: Retouching; Inpainting; Scratch removal
- G06V 20/13: Satellite images
- G06T 2207/10024: Color image
- G06T 2207/10032: Satellite or aerial image; Remote sensing
- G06T 2207/30181: Earth observation
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

In an embodiment, an apparatus for processing of high-altitude images is presented. An apparatus for processing high-altitude images may include a processor and a memory communicatively coupled to the processor. A memory may contain instructions configuring a processor to obtain image data. A processor may be configured to perform image processing on image data specific to an atmosphere associated with the image data. A processor may be configured to remove, through application of a machine learning model, obscure image data from processed image data to generate viable images. A processor may be configured to geolocate viable images based on obtained georeference data to generate geolocated image data. A processor may be configured to mosaic geolocated image data to produce a georeferenced map.

## Claims

### Claim 1

An apparatus for processing high-altitude images, comprising:
a processor; and
a memory communicatively coupled to the processor, the memory containing instructions configuring the processor to:
obtain high-altitude image data;
perform image processing on the image data specific to an atmospheric location associated with the image data;
remove, through application of a machine learning model, obscure image data from the processed image data to generate viable images;
geolocate the viable images based on obtained georeference data to generate geolocated image data; and
mosaic the geolocated image data to produce a georeferenced map.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the image processing includes color correction.

### Claim 3 (depends on 1)

The apparatus of claim 1, wherein the obscure image data includes images with an amount of blur and the processor is further configured to:
detect blur in the processed image data through application of the machine learning model; and
discard the detected blurred image data from further processing.

### Claim 4 (depends on 1)

The apparatus of claim 1, wherein the obscure image data includes images with a cloud and the processor is configured to:
detect clouds in the processed image data through the machine learning model; and
discard image data of the processed image data based on the detected clouds from further processing.

### Claim 5 (depends on 1)

The apparatus of claim 1, wherein the processor is configured to geolocate the image data through an indirect georeferencing method.

### Claim 6 (depends on 1)

The apparatus of claim 1, wherein the processor is configured to geolocate the image data through global positioning system (GPS) coordinates.

### Claim 7 (depends on 1)

The apparatus of claim 1, wherein the image data is obtained from an imaging device positioned within the stratosphere.

### Claim 8 (depends on 1)

The apparatus of claim 1, wherein the atmospheric location is an altitude range of about 30,000 feet to about 100,000 feet.

### Claim 9 (depends on 1)

The apparatus of claim 1, wherein the processor is further configured to geolocate the image data through comparison of two or more viable images to each other.

### Claim 10 (depends on 1)

The apparatus of claim 1, wherein the processor is further configured to mosaic the geolocated image data by combining at least two overlapping images of the geolocated image data.

### Claim 11

A computer-implemented method of processing high-altitude images, comprising:
obtaining high-altitude image data;
performing image processing on the image data specific to an atmospheric location associated with the image data;
removing, through application of a machine learning model, obscure image data from the processed image data to generate viable images;
geolocating the viable images based on obtained georeference data to generate geolocated image data; and
mosaicking the geolocated image data to produce a georeferenced map.

### Claim 12 (depends on 11)

The method of claim 11, wherein the imaging process comprises color correcting the image data.

### Claim 13 (depends on 11)

The method of claim 11, further comprising:
detecting blur in the processed image data through a blur detection machine learning model; and
discarding image data of the processed image data based on the detected blur.

### Claim 14 (depends on 11)

The method of claim 11, further comprising:
detecting at least a cloud in the processed image data through a cloud detection machine learning model; and
discarding image data of the processed image data based on the detected clouds.

### Claim 15 (depends on 11)

The method of claim 11, wherein geolocating the image data comprising utilizing an indirect georeferencing method.

### Claim 16 (depends on 11)

The method of claim 11, wherein geolocating the image data comprising utilizing Global Positioning System (GPS) coordinates.

### Claim 17 (depends on 11)

The method of claim 11, wherein the image data is obtained from an imaging device positioned within the stratosphere.

### Claim 18 (depends on 11)

The method of claim 11, wherein the atmospheric location is an altitude range of about 30,000 feet to about 100,000 feet.

### Claim 19 (depends on 11)

The method of claim 11, wherein geolocating the image data comprising comparing two or more images of the processed image data to each other.

### Claim 20

A non-transitory computer readable medium containing instructions that, when executed by a processor, cause the processor to perform the steps of:
obtaining high-altitude image data;
performing image processing on the image data specific to an atmospheric location associated with the image data;
removing, through application of a machine learning model, obscure image data from the processed image data to generate viable images;
geolocating the viable images based on obtained georeference data to generate geolocated image data; and
mosaicking the geolocated image data to produce a georeferenced map.
