# US 2019/0356864 A1 · High speed image registration system and methods of use

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

- Number: US 2019/0356864 A1
- Document ID: US20190356864A1
- Status: Published application
- Kind: A1
- Application number: 15/982,404
- Filed: 2018-05-17
- Published: 2019-11-21
- Earliest claimed: 2018-05-17
- Assignees: Lockheed Martin Corporation
- Applicants: Lockheed Martin Corporation
- Inventors: Alexander M. Elhage
- Web page: https://patentgrep.com/patent/US20190356864A1

## CPC

- H04N 5/265: Mixing
- G06T 3/4038: Image mosaicing, e.g. composing plane images from plane sub-images
- G06T 7/248: {involving reference images or patches}
- G06T 7/33: using feature-based methods
- H04N 5/44504: {Circuit details of the additional information generator, e.g. details of the character or graphics signal generator, overlay mixing circuits}
- G06T 2207/20221: Image fusion; Image merging
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

The invention is directed to systems and methods for image capturing technologies and, more particularly, to a high speed image registration system and respective processes to achieve high quality images. The method is implemented in a computing device and includes: capturing a first image of an object and identifying interest points; capturing a second image of the object and identifying regions of interest associated with the identified interest points of the first image, in addition to any areas not captured in the first image; identifying interest points in the second image within the regions of interest of the second image; matching interest points between the first image and the second image; aligning the matched interest points between the first image and the second image; and blending together the first image and the second image using the aligned similar interest points to form a single image of the object.

## Claims

### Claim 1

A method implemented in a computing device, comprising:
capturing a first image of an object and identifying interest points;
capturing a second image of the object and identifying regions of interest associated with the identified interest points of the first image, in addition to any areas not captured in the first image;
identifying interest points in the second image within the regions of interest of the second image;
matching interest points between the first image and the second image;
aligning the matched interest points between the first image and the second image; and
blending together the first image and the second image using the aligned similar interest points to form a single image of the object.

### Claim 2 (depends on 1)

The method of claim 1, further comprising using a travel speed of the object as it passes a camera to predict the interest regions associated with the identified points of interest of the first image.

### Claim 3 (depends on 2)

The method of claim 2, further comprising using a capture rate of the camera to predict the regions of interest associated with the identified interest points of the first image.

### Claim 4 (depends on 3)

The method of claim 3, wherein the interest points of the first image and the second image are corners of the first image and the second image.

### Claim 5 (depends on 3)

The method of claim 3, further comprising extracting descriptors of the matched similar interest points of the second image.

### Claim 6 (depends on 1)

The method of claim 1, further comprising searching an entire first frame of the first image for the interest points.

### Claim 7 (depends on 6)

The method of claim 6, wherein the identifying the interest points of the second image comprises searching only the regions of interest of the second image to find the interest points of the second image associated with the interest points of the first image.

### Claim 8 (depends on 7)

The method of claim 7, wherein the regions of interest of the second image associated with the identified interest points of the first image are predicted based on a known or estimated travel speed of the object as it passes a camera and a capture rate of the camera.

### Claim 9 (depends on 8)

The method of claim 8, wherein the regions of interest associated with the identified interest points of the first image encompasses an area smaller than an entirety of the first image or the second image.

### Claim 10

A computer program product comprising program code embodied in a computer-readable storage medium, the program code is readable/executable by a computing device to perform the following steps:
identifying corner points in a first captured image of an object;
identifying regions of interest in a second captured image of the object which correspond with the corner points of the first captured image;
identifying corner points in the second image within the regions of interest of the second image;
aligning matched corner points between the first image and the second image; and
blending together the first image and the second image using the aligned matched corner points to create a single image of the object.

### Claim 11 (depends on 10)

The computer program product of claim 10, wherein the regions of interest are predicted based on a known or estimate travel speed of the object as it passes a camera and a capture rate of the camera.

### Claim 12 (depends on 10)

The computer program product of claim 10, wherein the corners points of the first image substantially match to the corner points of the second image in the regions of interest.

### Claim 13 (depends on 12)

The computer program product of claim 12, further comprising extracting descriptors of the corner points in the second image.

### Claim 14 (depends on 12)

The computer program product of claim 12, further comprising searching an entire first frame of the first image for the corner points and only the regions of interest in the second frame for the corner points.

### Claim 15 (depends on 14)

The computer program product of claim 14, wherein the regions of interest in the second frame include areas that were not captured by a camera in the first frame.

### Claim 16 (depends on 15)

The computer program product of claim 15, wherein the regions of interest associated with second image is an area smaller than the first image.

### Claim 17 (depends on 15)

The computer program product of claim 15, wherein the regions of interest associated with second image is an area smaller than the second image.

### Claim 18 (depends on 1)

A system comprising:
a CPU, a computer readable memory and a computer readable storage medium; and
program instructions to perform the method steps of claim 1;
wherein the program instructions are stored on the computer readable storage medium.

### Claim 19 (depends on 18)

The system of claim 18, wherein the identifying the interest points of the second image comprises searching only the regions of interest of the second image.

### Claim 20 (depends on 19)

The system of claim 19, wherein the regions of interest of the second image associated with the identified interest points of the first image are predicted based on a known or estimated travel speed of the object as it passes a camera and a capture rate of the camera.
