# US 12,118,750 B1 · System and method for calibrating a camera and object tracking system using a calibrated camera

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

- Number: US 12,118,750 B1
- Document ID: US12118750B1
- Status: Granted
- Kind: B1
- Application number: 18/595,592
- Filed: 2024-03-05
- Granted: 2024-10-15
- Earliest claimed: 2024-03-05
- Assignees: Rapsodo Pte. Ltd.
- Applicants: Rapsodo Pte. Ltd.
- Inventors: Evgeny Lipunov; Botan Yildirim; Xu Dejiang; Aditya Vishwanath; Sivaprakash Natesan; Yasar Burak Savak; Batuhan Okur
- Web page: https://patentgrep.com/patent/US12118750B1

## 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
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- H04N 17/002: {for television cameras}
- H04N 23/60: Control of cameras or camera modules
- G06T 2207/30204: Marker
- G06T 2207/30241: Trajectory
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

A method for calibrating a camera without the decomposition of camera parameters into extrinsic and intrinsic components is provided. Further, there is provided a method for tracking an object in motion comprising capturing one or more image frames of an object in motion, using one or more calibrated cameras that have been calibrated according to a calibration method that generates and uses a respective transformation matrix for mapping three-dimensional (3D) real world model features to corresponding two-dimensional (2D) image features. The tracking method further comprises determining, using a hardware processor, motion characteristics of the object in motion based on the captured one or more image frames from each one or more calibrated cameras, the determining of the motion characteristics based on implicit intrinsic camera parameters and implicit extrinsic camera parameters of the respective transformation matrix from each respective one or more calibrated cameras.

## Claims

### Claim 1

A method of calibrating a camera comprising:
obtaining an initial transformation matrix (Hk) by performing a discrete linear transform (DLT) to recover 11 DoF representing initial implicit camera parameters, the initial transformation matrix (Hk) for transforming pixel coordinates (qk) relating to a reference camera image object in a 2D camera field of view (FOV) of the camera with corresponding known real world location coordinates in a 3D global reference space;
aligning a calibration image to the reference camera image object in the 3D global reference space by applying one or more corrections (HΔ) to said initial transformation matrix (Hk); and
building an updated transformation matrix (Hk+1) based on said aligning of the calibration image to the reference camera image object and applying one or more corrections (HΔ) to said initial transformation matrix (Hk) thereby updating implicit extrinsic camera parameters,
wherein the camera is calibrated without decomposing a plurality of camera parameters into explicit extrinsic and explicit intrinsic camera parameters.

### Claim 2 (depends on 1)

The method as claimed in claim 1, wherein the plurality of camera parameters include extrinsic and intrinsic camera parameters.

### Claim 3 (depends on 1)

The method as claimed in claim 1, further comprising: modifying one or more implicit extrinsic camera parameters through an affine correction, said affine correction recovering 6 DoF representing said implicit extrinsic camera parameters.

### Claim 4 (depends on 1)

The method as claimed in claim 1, further comprising:
applying said updated transformation matrix (Hk+1) to a 3D model to obtain pixel coordinates (qk+1) relating to the reference camera image object;
comparing said pixel coordinates (qk+1) against the transformed pixel coordinates (qn) evaluated with respect to the reference camera image object;
determining whether a difference between the obtained pixel coordinates (qk+1) and the transformed pixel coordinates (qk) is above a threshold; and
responsive to determining that the difference between the obtained pixel coordinates (qk+1) and transformed pixel coordinates (qk) is above the threshold, repeating said aligning the calibration image, said building the one or more corrections (HΔ) and said applying said one or more corrections (HΔ) to said initial transformation matrix (Hk) to further update the transformation matrix (Hk+1).

### Claim 5 (depends on 4)

The method as claimed in claim 4, wherein said threshold being a distance corresponding to a pre-determined number of pixel coordinates.

### Claim 6 (depends on 1)

The method as claimed in claim 1, wherein the updating of implicit extrinsic camera parameters is performed without altering implicit intrinsic camera parameters.