# US 2020/0402259 A1 · Image calibrating method and related monitoring camera system

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

- Number: US 2020/0402259 A1
- Document ID: US20200402259A1
- Status: Published application
- Kind: A1
- Application number: 16/671,187
- Filed: 2019-11-01
- Published: 2020-12-24
- Earliest claimed: 2019-06-21
- Assignees: Vivotek Inc.
- Applicants: Vivotek Inc.
- Inventors: Cheng-Chieh Liu
- Web page: https://patentgrep.com/patent/US20200402259A1

## CPC

- G06T 7/80: Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
- G06T 7/292: Multi-camera tracking
- H04N 7/18: Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- G06T 2207/10012: Stereo images
- G06T 2207/30196: Human being; Person
- G06T 2207/30204: Marker
- G06T 2207/30232: Surveillance
- G06T 2207/30241: Trajectory
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

An image calibrating method is applied to a first monitoring image and a second monitoring image partly overlapped with each other. The image calibrating method includes detecting a plurality of first marking points and second marking points about a target object on the first monitoring image and the second monitoring image, computing a first trace and a second trace formed by the first marking points and the second marking points, setting a plurality of first estimating points and second estimating points on stretching sections on the first trace and the second respectively within the second monitoring image and the first monitoring image, and utilizing the first marking points and the second estimating points and/or the first estimating points and the second marking points to compute a shift between the first monitoring image and the second monitoring image.

## Claims

### Claim 1

An image calibrating method applied to a monitoring camera system having a first monitoring camera and a second monitoring camera, a first monitoring image acquired by the first monitoring camera being partly overlapped with a second monitoring image acquired by the second monitoring camera, the image calibrating method comprising:
detecting a plurality of first marking points about a target object within the first monitoring image and a plurality of second marking points about the target object within the second monitoring image;
computing a first trace formed by the plurality of first marking points and a second trace formed by the plurality of second marking points;
setting a plurality of first estimating points on a stretching section of the first trace within the second monitoring image;
setting a plurality of second estimating points on a stretching section of the second trace within the first monitoring image; and
utilizing the plurality of first marking points and the plurality of second estimating points and/or further utilizing the plurality of first estimating points and the plurality of second marking points to compute a shift between the first monitoring image and the second monitoring image.

### Claim 2 (depends on 1)

The image calibrating method of claim 1, wherein the plurality of first marking points is sieved via regression analysis to generate the first trace.

### Claim 3 (depends on 1)

The image calibrating method of claim 1, wherein computing the first trace formed by the plurality of first marking points comprises:
setting a virtual line;
computing distances between the virtual line and each of the plurality of first marking points;
selecting at least two first marking points having the distance smaller than a threshold; and
generating the first trace by the at least two first marking points.

### Claim 4 (depends on 1)

The image calibrating method of claim 1, wherein a difference between one interval between any two adjacent first marking points and another interval between other two adjacent first marking points of the plurality of first marking points is smaller than a reference value.

### Claim 5 (depends on 4)

The image calibrating method of claim 4, wherein a difference between one interval between any two adjacent first marking points of the plurality of first marking points and another interval between any two adjacent first estimating points of the plurality of first estimating points is smaller than the reference value.

### Claim 6 (depends on 1)

The image calibrating method of claim 1, wherein the first trace and the second trace are straight lines, or curves with a curvature conforming to a specific condition.

### Claim 7 (depends on 1)

The image calibrating method of claim 1, wherein the shift is computed via the plurality of first marking points adjusted by a first weighting and the plurality of second estimating points adjusted by a second weighting, and the first weighting is greater than or equal to the second weighting.

### Claim 8 (depends on 1)

The image calibrating method of claim 1, wherein the plurality of first marking points and the plurality of second estimating points are divided into a first tracing group and a second tracing group, the first tracing group is consisted of at least one first marking point and at least one second estimating point close to a center of the first monitoring image, the second tracing group is consisted of at least one first marking point and at least one second estimating point close to a boundary of the first monitoring image, the shift is computed via the first tracing group adjusted by a first weighting and the second tracing group adjusted by a second weighting, and the first weighting is greater than or equal to the second weighting.

### Claim 9 (depends on 1)

The image calibrating method of claim 1, wherein at least one first marking point selected from the plurality of first marking points and at least one second estimating point selected from the plurality of second estimating points are utilized to compute the shift.

### Claim 10 (depends on 1)

The image calibrating method of claim 1, further comprising:
utilizing the first trace and the second trace to compute rotation of the first monitoring image and the second monitoring image;
wherein the image calibrating method executes rotary amendment via the rotation and then executes computation and amendment of the shift.

### Claim 11

A monitoring camera system, comprising:
a first monitoring camera adapted to acquire a first monitoring image;
a second monitoring camera adapted to acquire a second monitoring image partly overlapped with the first monitoring image; and
an operation processor electrically connected to the first monitoring camera and the second monitoring camera for acquiring the first monitoring image and the second monitoring image, the operation processor being adapted to detect a plurality of first marking points about a target object within the first monitoring image and a plurality of second marking points about the target object within the second monitoring image, compute a first trace formed by the plurality of first marking points and a second trace formed by the plurality of second marking points, set a plurality of first estimating points on a stretching section of the first trace within the second monitoring image, set a plurality of second estimating points on a stretching section of the second trace within the first monitoring image, and utilize the plurality of first marking points and the plurality of second estimating points and/or further utilize the plurality of first estimating points and the plurality of second marking points for computing a shift between the first monitoring image and the second monitoring image.

### Claim 12 (depends on 11)

The monitoring camera system of claim 11, wherein the plurality of first marking points is sieved via regression analysis to generate the first trace.

### Claim 13 (depends on 11)

The monitoring camera system of claim 11, wherein the operation processor is further adapted to set a virtual line, compute distances between the virtual line and each of the plurality of first marking points, select at least two first marking points having the distance smaller than a threshold, and generate the first trace by the at least two first marking points.

### Claim 14 (depends on 11)

The monitoring camera system of claim 11, wherein a difference between one interval between any two adjacent first marking points and another interval between other two adjacent first marking points of the plurality of first marking points is smaller than a reference value.

### Claim 15 (depends on 14)

The monitoring camera system of claim 14, wherein a difference between one interval between any two adjacent first marking points of the plurality of first marking points and another interval between any two adjacent first estimating points of the plurality of first estimating points is smaller than the reference value.

### Claim 16 (depends on 11)

The monitoring camera system of claim 11, wherein the shift is computed via the plurality of first marking points adjusted by a first weighting and the plurality of second estimating points adjusted by a second weighting, and the first weighting is greater than or equal to the second weighting.

### Claim 17 (depends on 11)

The monitoring camera system of claim 11, wherein the plurality of first marking points and the plurality of second estimating points are divided into a first tracing group and a second tracing group, the first tracing group is consisted of at least one first marking point and at least one second estimating point close to a center of the first monitoring image, the second tracing group is consisted of at least one first marking point and at least one second estimating point close to a boundary of the first monitoring image, the shift is computed via the first tracing group adjusted by a first weighting and the second tracing group adjusted by a second weighting, and the first weighting is greater than or equal to the second weighting.

### Claim 18 (depends on 11)

The monitoring camera system of claim 11, wherein at least one first marking point selected from the plurality of first marking points and at least one second estimating point selected from the plurality of second estimating points are utilized to compute the shift.

### Claim 19 (depends on 11)

The monitoring camera system of claim 11, wherein the operation processor is further adapted to utilize the first trace and the second trace to compute rotation of the first monitoring image and the second monitoring image, the image calibrating method executes rotary amendment via the rotation and then executes computation and amendment of the shift.

### Claim 20

A monitoring camera system, comprising:
a first monitoring camera adapted to acquire a first monitoring image and receive a second monitoring image partly overlapped with the first monitoring image, wherein the first monitoring camera comprises an operation processor adapted to detect a plurality of first marking points about a target object within the first monitoring image and a plurality of second marking points about the target object within the second monitoring image, compute a first trace formed by the plurality of first marking points and a second trace formed by the plurality of second marking points, set a plurality of first estimating points on a stretching section of the first trace within the second monitoring image, set a plurality of second estimating points on a stretching section of the second trace within the first monitoring image, and utilize the plurality of first marking points and the plurality of second estimating points and/or further utilize the plurality of first estimating points and the plurality of second marking points for computing a shift between the first monitoring image and the second monitoring image.
