# US 11,900,649 B2 · Methods, systems, articles of manufacture and apparatus to generate digital scenes

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

- Number: US 11,900,649 B2
- Document ID: US11900649B2
- Status: Granted
- Kind: B2
- Application number: 17/851,508
- Filed: 2022-06-28
- Published: 2023-01-12
- Granted: 2024-02-13
- Earliest claimed: 2018-03-30
- Assignees: Movidius Limited
- Applicants: Movidius Limited
- Inventors: Kevin Lee; Anton Shmatov; Jonathan Byrne; David Moloney
- Web page: https://patentgrep.com/patent/US11900649B2

## CPC

- G06V 10/56: relating to colour
- G06T 17/20: Finite element generation, e.g. wire-frame surface description, {tesselation}
- G06T 19/00: Manipulating three-dimensional [3D] models or images for computer graphics
- G06V 10/7753: {Incorporation of unlabelled data, e.g. multiple instance learning [MIL]}
- G06V 20/13: Satellite images
- G06V 20/17: taken from planes or by drones
- G06V 20/53: {Recognition of crowd images, e.g. recognition of crowd congestion}
- G06V 20/653: {by matching three-dimensional models, e.g. conformal mapping of Riemann surfaces}
- G06T 2219/004: Annotating, labelling
- G06V 2201/12: Acquisition of 3D measurements of objects
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Methods, systems, articles of manufacture and apparatus to generate digital scenes are disclosed. An example apparatus to generate labelled models includes a map builder to generate a three-dimensional (3D) model of an input image, a grouping classifier to identify a first zone of the 3D model corresponding to a first type of grouping classification, a human model builder to generate a quantity of placeholder human models corresponding to the first zone, a coordinate engine to assign the quantity of placeholder human models to respective coordinate locations of the first zone, the respective coordinate locations assigned based on the first type of grouping classification, a model characteristics modifier to assign characteristics associated with an aspect type to respective ones of the quantity of placeholder human models, and an annotation manager to associate the assigned characteristics as label data for respective ones of the quantity of placeholder human models.

## Claims

### Claim 1

An apparatus to annotate models, comprising:
interface circuitry to obtain object models;
machine readable instructions; and
programmable circuitry to be programmed by the machine readable instructions to at least:
assign a quantity of the object models to coordinate locations of a map;
set an orientation of the quantity of the object models based on a co-dependency classification of respective ones of the quantity of the object models;
set an alignment of the respective ones of the quantity of the object models based on a variation factor; and
generate metadata corresponding to the respective ones of the quantity of the object models, the metadata containing the orientation and the alignment of the respective ones of the quantity of the object models.

### Claim 2 (depends on 1)

The apparatus as defined in claim 1, wherein the programmable circuitry is to label the respective ones of the quantity of the object models with the metadata.

### Claim 3 (depends on 1)

The apparatus as defined in claim 1, wherein the programmable circuitry is to assign an aspect type to the respective ones of the quantity of the object models.

### Claim 4 (depends on 3)

The apparatus as defined in claim 3, wherein the aspect type includes at least one of gender metadata, age metadata, height metadata or pose metadata.

### Claim 5 (depends on 3)

The apparatus as defined in claim 3, wherein the programmable circuitry is to assign a characteristic of the aspect type.

### Claim 6 (depends on 5)

The apparatus as defined in claim 5, wherein the characteristic of the aspect type includes at least one of a female type, a male type, an age value or a pose type.

### Claim 7 (depends on 1)

The apparatus as defined in claim 1, wherein the quantity of the object models includes human models.

### Claim 8

A non-transitory computer readable medium comprising computer readable instructions to cause programmable circuitry to at least:
assign object models to coordinate locations of a data structure;
assign an orientation of the object models based on a co-dependency classification of respective ones of the object models;
assign an alignment of the respective ones of the object models based on a variation factor; and
generate metadata corresponding to the respective ones of the object models, the metadata containing the orientation and the alignment of the respective ones of the object models.

### Claim 9 (depends on 8)

The computer readable medium as defined in claim 8, wherein the instructions are to cause the programmable circuitry to label the respective ones of the object models with the metadata.

### Claim 10 (depends on 8)

The computer readable medium as defined in claim 8, wherein the instructions are to cause the programmable circuitry to assign an aspect type to the respective ones of the object models.

### Claim 11 (depends on 10)

The computer readable medium as defined in claim 10, wherein the instructions are to cause the programmable circuitry to set the aspect type as at least one of a gender type, an age type, a height type, or a pose type.

### Claim 12 (depends on 11)

The computer readable medium as defined in claim 11, wherein the instructions are to cause the programmable circuitry to assign a characteristic of the aspect type.

### Claim 13 (depends on 12)

The computer readable medium as defined in claim 12, wherein the instructions are to cause the programmable circuitry to assign the characteristic of the aspect type as at least one of a female characteristic of the gender type, a male characteristic of the gender type, or an age value of the age type.

### Claim 14 (depends on 12)

The computer readable medium as defined in claim 12, wherein the instructions are to cause the programmable circuitry to assign the object models to the data structure corresponding to a map.

### Claim 15

A method to annotate models, comprising:
assigning, by executing an instruction with processor circuitry, a quantity of object models to coordinate locations of a map data structure;
arranging, by executing an instruction with the processor circuitry, an orientation of the quantity of the object models based on a co-dependency classification of respective ones of the quantity of the object models;
arranging, by executing an instruction with the processor circuitry, an alignment of the respective ones of the quantity of the object models based on a variation factor; and
generating, by executing an instruction with the processor circuitry, metadata corresponding to the respective ones of the quantity of the object models, the metadata containing the orientation and the alignment of the respective ones of the quantity of the object models.

### Claim 16 (depends on 15)

The method as defined in claim 15, further including labeling the respective ones of the quantity of the object models with the metadata.

### Claim 17 (depends on 15)

The method as defined in claim 15, further including assigning an aspect type to the respective ones of the quantity of the object models.

### Claim 18 (depends on 17)

The method as defined in claim 17, wherein the aspect type includes at least one of gender metadata, age metadata, height metadata or pose metadata.

### Claim 19 (depends on 18)

The method as defined in claim 18, further including assigning a characteristic of the aspect type.

### Claim 20 (depends on 19)

The method as defined in claim 19, wherein the characteristic of the aspect type includes at least one of a female type, a male type, an age value or a pose type.

### Claim 21 (depends on 15)

The method as defined in claim 15, wherein the quantity of the object models includes human models.