# US 2022/0036111 A1 · Method and device for associating panoramic image with point of interest, electronic device and storage medium

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

- Number: US 2022/0036111 A1
- Document ID: US20220036111A1
- Status: Published application
- Kind: A1
- Application number: 17/451,304
- Filed: 2021-10-18
- Published: 2022-02-03
- Earliest claimed: 2020-12-25
- Assignees: Beijing Baidu Netcom Science Technology Co., Ltd.
- Applicants: Beijing Baidu Netcom Science Technology Co., Ltd
- Inventors: Guocai Bai; Jiankang Xin
- Web page: https://patentgrep.com/patent/US20220036111A1

## CPC

- G06V 20/63: {Scene text, e.g. street names}
- G06T 3/4038: Image mosaicing, e.g. composing plane images from plane sub-images
- G06T 7/0002: {Inspection of images, e.g. flaw detection}
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06V 20/635: {Overlay text, e.g. embedded captions in a TV programme}
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30168: Image quality inspection
- G06V 30/10: Character recognition
- G06V 2201/07: Target detection
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

This application provides a method and a device for associating a panoramic image with a point of interest, an electronic device and a storage medium. A specific implementation solution is as follows: performing text recognition on a panoramic image associated with a target point of interest, and determining target text information; acquiring a set of panoramic images including the target text information among a plurality of panoramic images associated with the target point of interest; acquiring a panoramic screenshot corresponding to each panoramic image in the set of panoramic images to acquire a set of panoramic screenshots, where one panoramic image is formed by splicing a plurality of panoramic screenshots; and determining a target panoramic screenshot in the set of panoramic screenshots, and associating the target panoramic screenshot with the target point of interest, where the target panoramic screenshot includes the target text information.

## Claims

### Claim 1

A method for associating a panoramic image with a point of interest, comprising:
performing text recognition on a panoramic image associated with a target point of interest, and determining target text information;
acquiring a set of panoramic images comprising the target text information among a plurality of panoramic images associated with the target point of interest;
acquiring a panoramic screenshot corresponding to each panoramic image in the set of panoramic images to acquire a set of panoramic screenshots, wherein one panoramic image is formed by stitching a plurality of panoramic screenshots together; and
determining a target panoramic screenshot in the set of panoramic screenshots, and associating the target panoramic screenshot with the target point of interest, wherein the target panoramic screenshot comprises the target text information.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the determining the target panoramic screenshot in the set of panoramic screenshots comprises:
acquiring a score value of each panoramic screenshot in the set of panoramic screenshots based on a preset scoring rule, and determining the target panoramic screenshot in the set of panoramic screenshots based on the score value.

### Claim 3 (depends on 1)

The method according to claim 1, wherein the determining the target panoramic screenshot in the set of panoramic screenshots comprises:
acquiring an image parameter of each panoramic screenshot in the set of panoramic screenshots, wherein the image parameter comprises at least one of following items: image brightness, image contrast, a display position of the target text information in the panoramic screenshot, a display size of the target text information in the panoramic screenshot, and angle information corresponding to the panoramic screenshot;
acquiring a score value of each panoramic screenshot based on a preset scoring model, wherein the preset scoring model is a network model of which an input is the image parameter and an output is the score value; and
determining the panoramic screenshot having a highest score value as the target panoramic screenshot.

### Claim 4 (depends on 1)

The method according to claim 1, wherein the associating the target panoramic screenshot with the target point of interest comprises:
acquiring a target panoramic image corresponding to the target panoramic screenshot;
acquiring angle information of the target panoramic screenshot based on the target panoramic image and the target panoramic screenshot, wherein the angle information of the target panoramic screenshot comprises at least one of following items: a pitch angle, a roll angle, and a yaw angle of the target panoramic screenshot relative to the target panoramic image; and
associating the angle information of the target panoramic screenshot with the target point of interest.

### Claim 5 (depends on 1)

The method according to claim 1, further comprising: displaying the target panoramic screenshot, in the case of receiving a trigger operation for the target point of interest.

### Claim 6

A device for associating a panoramic image with a point of interest, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the memory stores thereon an instruction that is executable by the at least one processor, and when executing the instruction, the at least one processor is configured to:
perform text recognition on a panoramic image associated with a target point of interest, and determine target text information;
acquire a set of panoramic images comprising the target text information among a plurality of panoramic images associated with the target point of interest;
acquire a panoramic screenshot corresponding to each panoramic image in the set of panoramic images to acquire a set of panoramic screenshots, wherein one panoramic image is formed by stitching a plurality of panoramic screenshots together; and
determine a target panoramic screenshot in the set of panoramic screenshots, and associate the target panoramic screenshot with the target point of interest, wherein the target panoramic screenshot comprises the target text information.

### Claim 7 (depends on 6)

The device according to claim 6, wherein the at least one processor is further configured to:
acquire a score value of each panoramic screenshot in the set of panoramic screenshots based on a preset scoring rule, and determine the target panoramic screenshot in the set of panoramic screenshots based on the score value.

### Claim 8 (depends on 6)

The device according to claim 6, wherein the at least one processor is further configured to:
acquire an image parameter of each panoramic screenshot in the set of panoramic screenshots, wherein the image parameter comprises at least one of following items: image brightness, image contrast, a display position of the target text information in the panoramic screenshot, a display size of the target text information in the panoramic screenshot, and angle information corresponding to the panoramic screenshot;
acquire a score value of each panoramic screenshot based on a preset scoring model, wherein the preset scoring model is a network model of which an input is the image parameter and an output is the score value; and
determine the panoramic screenshot having a highest score value as the target panoramic screenshot.

### Claim 9 (depends on 6)

The device according to claim 6, wherein the at least one processor is further configured to:
acquire a target panoramic image corresponding to the target panoramic screenshot;
acquire angle information of the target panoramic screenshot based on the target panoramic image and the target panoramic screenshot, wherein the angle information of the target panoramic screenshot comprises at least one of following items: a pitch angle, a roll angle, and a yaw angle of the target panoramic screenshot relative to the target panoramic image; and
associate the angle information of the target panoramic screenshot with the target point of interest.

### Claim 10 (depends on 6)

The device according to claim 6, wherein the at least one processor is further configured to:
display the target panoramic screenshot, in the case of receiving a trigger operation for the target point of interest.

### Claim 11

A non-transitory computer-readable storage medium having stored a computer instruction thereon, wherein the computer instruction is configured to cause a computer to perform following steps:
performing text recognition on a panoramic image associated with a target point of interest, and determining target text information;
acquiring a set of panoramic images comprising the target text information among a plurality of panoramic images associated with the target point of interest;
acquiring a panoramic screenshot corresponding to each panoramic image in the set of panoramic images to acquire a set of panoramic screenshots, wherein one panoramic image is formed by stitching a plurality of panoramic screenshots together; and
determining a target panoramic screenshot in the set of panoramic screenshots, and associating the target panoramic screenshot with the target point of interest, wherein the target panoramic screenshot comprises the target text information.

### Claim 12 (depends on 11)

The non-transitory computer-readable storage medium according to claim 11, wherein when determining the target panoramic screenshot in the set of panoramic screenshots, the computer instruction is further configured to cause the computer to perform following steps:
acquiring a score value of each panoramic screenshot in the set of panoramic screenshots based on a preset scoring rule, and determining the target panoramic screenshot in the set of panoramic screenshots based on the score value.

### Claim 13 (depends on 11)

The non-transitory computer-readable storage medium according to claim 11, wherein when determining the target panoramic screenshot in the set of panoramic screenshots, the computer instruction is further configured to cause the computer to perform following steps:
acquiring an image parameter of each panoramic screenshot in the set of panoramic screenshots, wherein the image parameter comprises at least one of following items: image brightness, image contrast, a display position of the target text information in the panoramic screenshot, a display size of the target text information in the panoramic screenshot, and angle information corresponding to the panoramic screenshot;
acquiring a score value of each panoramic screenshot based on a preset scoring model, wherein the preset scoring model is a network model of which an input is the image parameter and an output is the score value; and
determining the panoramic screenshot having a highest score value as the target panoramic screenshot.

### Claim 14 (depends on 11)

The non-transitory computer-readable storage medium according to claim 11, wherein when associating the target panoramic screenshot with the target point of interest, the computer instruction is further configured to cause the computer to perform following steps:
acquiring a target panoramic image corresponding to the target panoramic screenshot;
acquiring angle information of the target panoramic screenshot based on the target panoramic image and the target panoramic screenshot, wherein the angle information of the target panoramic screenshot comprises at least one of following items: a pitch angle, a roll angle, and a yaw angle of the target panoramic screenshot relative to the target panoramic image; and
associating the angle information of the target panoramic screenshot with the target point of interest.

### Claim 15 (depends on 11)

The non-transitory computer-readable storage medium according to claim 11, wherein the computer instruction is further configured to cause the computer to perform following steps:
displaying the target panoramic screenshot, in the case of receiving a trigger operation for the target point of interest.
