# US 2025/0157003 A1 · Method and a device for stitching image data

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

- Number: US 2025/0157003 A1
- Document ID: US20250157003A1
- Status: Published application
- Kind: A1
- Application number: 18/945,145
- Filed: 2024-11-12
- Published: 2025-05-15
- Earliest claimed: 2023-11-14
- Assignees: Axis AB
- Applicants: Axis AB
- Inventors: Mikael MURSTAM; Johan STENING
- Web page: https://patentgrep.com/patent/US20250157003A1

## CPC

- G06T 3/4038: Image mosaicing, e.g. composing plane images from plane sub-images
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 7/11: Region-based segmentation
- G06T 7/20: Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51)
- G06T 7/90: Determination of colour characteristics
- G06V 10/764: using classification, e.g. of video objects
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- H04N 23/698: for achieving an enlarged field of view, e.g. panoramic image capture
- G06T 2207/20221: Image fusion; Image merging
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

A method of stitching image data from one or more image sensors arranged to acquire image data depicting at least partly overlapping views of a scene comprises obtaining sets of image data representing a blending region; dividing each set of image data into portions of different interest levels; for each portion of image data, determining one or more image frequency bands based on the interest level of the portion, and obtaining image data of the determined one or more image frequency bands from the portion of image data; and blending the first set of image data and the second set of image data by multi-band blending, wherein only the obtained image data of the determined one or more image frequency bands are blended for each portion of image data.

## Claims

### Claim 1

A method of generating stitched image data for an application, wherein the image data is acquired by one or more image sensors arranged to acquire image data depicting at least partly overlapping views of a scene, the method comprising:
obtaining a first set of image data and a second set of image data, wherein each set of image data represents a blending region,
defining different levels of interest for image data of different spatial regions or of different color components of a color space depending on an application for which the stitched image data is generated,
dividing each set of image data into portions of different defined interest levels corresponding to a same plurality of spatial regions of the blending region or corresponding to a same plurality of color components, for each portion of image data:
determining one or more image frequency bands for the portion in view of the interest level of the portion, and
obtaining image data of the determined one or more image frequency bands from the portion of image data,
blending the first set of image data and the second set of image data by multi-band blending, wherein only the obtained image data of the determined one or more image frequency bands are blended for each portion of image data, thereby generating stitched image data for the blending region for the application.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the step of determining one or more image frequency bands comprises selecting one or more image frequency bands from a fixed set of image frequency bands.

### Claim 3 (depends on 1)

The method according to claim 1, wherein the sets of image data are divided into portions corresponding to a same plurality of spatial regions of the blending region, and comprises:
performing image segmentation on the sets of image data, and
dividing the sets of image data into spatial portions corresponding to segmented regions of different defined interest levels.

### Claim 4 (depends on 3)

The method according to claim 3, wherein the image segmentation is performed using a background model.

### Claim 5 (depends on 3)

The method according to claim 3, wherein the image segmentation is performed using an image classification algorithm or image recognition algorithm.

### Claim 6 (depends on 1)

The method according to claim 1, wherein the sets of image data are divided into portions corresponding to a same plurality of spatial regions of the blending region, the method further comprising:
performing motion analysis on the sets of image data and dividing the sets of image data into spatial regions corresponding to different motion levels having different defined interest levels.

### Claim 7 (depends on 1)

The method according to claim 1, wherein the sets of image data are divided into a plurality of spatial regions, the method further comprising:
receiving information from a predictive coding process indicating coding parameter values for the sets of image data, and
dividing the sets of image data into spatial regions corresponding to different coding parameters having different defined interest levels.

### Claim 8 (depends on 1)

The method according to claim 1, wherein the sets of image data are divided into a plurality of spatial regions, the method further comprising:
analyzing the sets of image data to determine the image frequency content, and
dividing the sets of image data into spatial regions with different dominant frequencies having different defined interest levels.

### Claim 9 (depends on 1)

The method according to claim 1, wherein the sets of image data are divided into a same plurality of color components, wherein the color components are Y, Cb, and Cr of the YCbCr color space.

### Claim 10 (depends on 1)

The method according to claim 1, wherein the sets of image data are divided into a plurality of portions based on a user-defined division.

### Claim 11 (depends on 1)

The method according to claim 1, wherein the sets of image data are divided into a plurality of regions, the method further comprising:
determining a historic division of the sets of image data in previous sets of image data representing the same image region, and
dividing the sets of image data into a plurality of portions according to the historic division.

### Claim 12

A method of generating a sequence of stitched images, comprising:
obtaining a first image sequence and a second image sequence from a plurality of image sensors arranged to acquire image data depicting at least partly overlapping views of a scene,
for temporally corresponding sets of image data:
obtaining a first set of image data and a second set of image data, wherein each set of image data represents a blending region,
defining different levels of interest for image data of different spatial regions or of different color components of a color space depending on an application for which the stitched image data is generated,
dividing each set of image data into portions of different defined interest levels corresponding to a same plurality of spatial regions of the blending region or corresponding to a same plurality of color components, for each portion of image data:
determining one or more image frequency bands for the portion in view of the interest level of the portion, and
obtaining image data of the determined one or more image frequency bands from the portion of image data,
blending the first set of image data and the second set of image data by multi-band blending, wherein only the obtained image data of the determined one or more image frequency bands are blended for each portion of image data, thereby generating stitched image data for the blending region for the application, and
generating a sequence of stitched images based on the first image sequence, the second image sequence and the generated stitched image data for the blending region.

### Claim 13

A device for generating stitched image data for an application, wherein the image data is acquired by one or more image sensors arranged to acquire image data depicting at least partly overlapping views of a scene, the device comprising:
an image data obtainer arranged to obtain a first set of image data and a second set of image data, wherein each set of image data represents a blending region,
a divider arranged to divide each set of image data into portions of different defined interest levels corresponding to a same plurality of spatial regions of the blending region or corresponding to a same plurality of color components, wherein different levels of interest for image data of different spatial regions or of different color components of a color space are defined depending on an application for which the stitched image data is generated,
an image frequency obtainer that is adapted to, for each portion of image data:
determine one or more image frequency bands for the portion in view of the interest level of the portion, and
obtain image data of the determined one or more image frequency bands from the portion of image data,
a blender adapted to blend the first set of image data and the second set of image data by multi-band blending, wherein only the obtained image data of the determined one or more image frequency bands are blended for each portion of image data, thereby generating stitched image data for the blending region for the application.

### Claim 14 (depends on 13)

The device according to claim 13, further including a surveillance camera adapted to provide a live stream of panoramic video.
