# US 12,118,778 B2 · Machine vision-based method and system for locating objects within a scene containing the objects

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

- Number: US 12,118,778 B2
- Document ID: US12118778B2
- Status: Granted
- Kind: B2
- Application number: 17/491,975
- Filed: 2021-10-01
- Published: 2023-04-06
- Granted: 2024-10-15
- Earliest claimed: 2021-10-01
- Assignees: Liberty Robotics Inc.
- Applicants: Liberty Reach Inc.
- Inventors: G. Neil Haven
- Web page: https://patentgrep.com/patent/US12118778B2

## CPC

- G06V 20/10: Terrestrial scenes (scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59)
- G06T 7/593: from stereo images
- G06T 7/75: {involving models}
- G06V 10/60: relating to illumination properties, e.g. using a reflectance or lighting model
- G06V 10/751: {Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching}
- G06V 20/64: Three-dimensional [3D] objects
- H04N 13/239: using two two-dimensional [2D] image sensors having a relative position equal to or related to the interocular distance (H04N13/243 takes precedence)
- H04N 13/254: in combination with electromagnetic radiation sources for illuminating objects
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

A machine vision-based method and system for locating an object within a scene are provided. The method includes uniformly illuminating a target surface of the object within the scene with light having an intensity within a relatively narrow range of wavelengths such that the light overwhelms the intensity of ambient light within the narrow range to obtain reflected, backscattered illumination. The method also includes sensing brightness of the surface due to a diffuse component of the backscattered illumination to obtain brightness information. Backscattered illumination from the target surface is inspected to obtain geometric information. Rotationally and positionally invariant surface albedo of the object is computed based on the brightness and geometric information. The surface albedo and the geometric information may then be used by a matching algorithm.

## Claims

### Claim 1

A machine vision-based method of locating an object within a scene, the method comprising:
uniformly illuminating, a target surface of the object within the scene with light having an intensity within a narrow range of wavelengths such that the light overwhelms an intensity of ambient light within the narrow range to obtain reflected, backscattered illumination;
sensing brightness of the target surface due to a diffuse component of the backscattered illumination to obtain brightness information;
inspecting the backscattered illumination from the target surface to obtain geometric information;
computing rotation invariant and position invariant surface albedo of the object based on the brightness information and the geometric information; and
processing the surface albedo with a matching algorithm to match to a model using surface geometry or the surface albedo in order to obtain a location of both a model and the object within the scene.

### Claim 2 (depends on 1)

The method as claimed in claim 1, wherein the inspecting is performed by a 3D sensor such as an active stereo sensor.

### Claim 3 (depends on 1)

The method as claimed in claim 1, wherein the computing includes steps of providing a location of all sources of light which illuminates the scene, providing the individual contribution of the all sources of light to the sense brightness and providing the diffuse component of the backscattered illumination from the all sources of light.

### Claim 4 (depends on 1)

The method as claimed in claim 1, wherein the narrow range of wavelengths lies in the near infrared region of the light spectrum.

### Claim 5 (depends on 1)

The method as claimed in claim 1, wherein the light is polarized.

### Claim 6 (depends on 1)

The method as claimed in claim 1, wherein the surface albedo is normalized to distance variations and orientation variations of the object within the scene.

### Claim 7 (depends on 1)

The method as claimed in claim 1, further comprising filtering out a non-scattered component of the light.

### Claim 8 (depends on 1)

The method as claimed in claim 1, wherein the surface albedo is not a function of either object position or rotation within the scene.