# US 2023/0267682 A1 · Three-dimensional modeling

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

- Number: US 2023/0267682 A1
- Document ID: US20230267682A1
- Status: Published application
- Kind: A1
- Application number: 18/024,145
- Filed: 2020-09-02
- Published: 2023-08-24
- Earliest claimed: 2020-09-02
- Assignees: Telefonaktiebolaget LM Ericsson (publ)
- Applicants: Telefonaktiebolaget LM Ericsson (publ)
- Inventors: Volodya GRANCHAROV; Manish SONAL; Steven COMBES
- Web page: https://patentgrep.com/patent/US20230267682A1

## CPC

- G06T 7/174: involving the use of two or more images
- G06T 17/05: Geographic models
- G06T 7/11: Region-based segmentation
- G06T 7/194: involving foreground-background segmentation
- G06T 7/73: using feature-based methods
- G06T 7/97: {Determining parameters from multiple pictures (depth or shape recovery from multiple images G06T7/55; stereo camera calibration G06T7/85)}
- G06T 2200/04: involving 3D image data
- G06T 2207/10004: Still image; Photographic image
- G06T 2207/10016: Video; Image sequence
- G06T 2207/10028: Range image; Depth image; 3D point clouds
- G06T 2207/10032: Satellite or aerial image; Remote sensing
- G06T 2207/30184: Infrastructure
- G06T 2207/30244: Camera pose
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A method (1200) for producing a reduced point cloud comprising an object of interest (OOI) from an original point cloud comprising the OOI. The method includes obtaining (s1202) the original point cloud; obtaining (s1204) a set of N images, each of the N images comprising an image of the OOI from a unique position relative to the OOI; for each one of the N images, defining (s1206) an area of interest in the image that obtaining a set of N images, each of the N images that includes the OOI, thereby defining N areas of interest; for each point included in the original point cloud, determining (s1208), for each one of the N areas of interest, whether the point is located in the area of interest; for each point included in the original point cloud, determining (s1210) a first metric for the point based on the total number of the N areas of interest in which the point is determined to be located; and for each point included in the set of points, determining (s1212) whether or not to include the point in the reduced point cloud based on the first metric for the point.

## Claims

### Claim 1

A method for producing a reduced point cloud comprising an object of interest (OOI) from an original point cloud comprising the OOI, the method comprising:
obtaining the original point cloud, the original point cloud comprising a set of points, each point having a location in a three-dimensional (3D) space;
obtaining a set of N images, each of the N images comprising an image of the OOI from a unique position relative to the OOI;
for each one of the N images, defining an area of interest in the image that includes the OOI, thereby defining N areas of interest;
for each point included in the set of points, determining, for each one of the N areas of interest, whether the point is located in the area of interest;
for each point included in the set of points, determining a first metric for the point based on the total number of the N areas of interest in which the point is determined to be located; and
for each point included in the set of points, determining whether or not to include the point in the reduced point cloud based on the first metric for the point.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
for each point included in the set of points, determining whether the first metric for the point satisfies a first threshold condition and adding the point to the reduced point cloud as a result of determining that the first metric for the point satisfies the first threshold condition.

### Claim 3 (depends on 2)

The method of claim 2, wherein
determining the first metric, m1, for a particular point included in the set of points comprises calculating m1=Cin/N, where Cin is a value equal to the total number of the N areas of interest in which the particular point is determined to be located, and
determining whether m1 satisfies the first threshold condition comprising determining whether m1 is greater than a threshold.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
for each point included in the reduced point cloud, determining, for each one of the N areas of interest, whether the point is within a threshold distance of a lower edge of the area of interest.

### Claim 5 (depends on 4)

The method of claim 4, further comprising:
for each point included in the reduced point cloud, determining a second metric for the point based on the total number of the N areas of interest for which the point is determined to be within the threshold distance of the lower edge of the area of interest;
for each point included in the reduced point cloud for which the second metric satisfies a threshold condition, using the point to determine a plane; and
removing from the reduced point cloud all of the points in the reduce point cloud that are positioned below the determined plane.

### Claim 6 (depends on 1)

The method of claim 1, wherein the step of determining, for each one of the N areas of interest, whether the point is located in the area of interest comprises:
obtaining 3D location information specifying the location of the point in the 3D space;
obtaining camera pose information identifying a camera pose associated with the one of the N images;
obtaining intrinsic camera information, the intrinsic camera information comprising focal length information identifying a focal length;
based on the 3D location information, the camera pose information, and the intrinsic camera information, obtaining two-dimensional (2D) location information indicating the location of the point in the one of the N images; and
using the obtained 2D location information to determine whether the point is within the area of interest corresponding to the one of the N images.

### Claim 7 (depends on 6)

The method of claim 6, wherein
the area of interest has a center point located at the coordinates Cu and Cv,
the area of interest has a width of W,
the area of interest has a height of H,
the 2D location information consists of a pair of coordinates u,v,
the step of using the obtained 2D location information to determine whether the point is within the area of interest corresponding to the one of the N images comprises:
determining if |Cu−u|≤W/2; and
determining if |Cv−v|≤H/2.

### Claim 8 (depends on 1)

The method of claim 1, wherein the step of obtaining a set of N images comprises flying an aerial vehicle equipped with a camera on a path that circles the OOI, and, while the drone is flying on the path, operating the camera to obtain the N images.

### Claim 9 (depends on 8)

The method of claim 8, wherein the aerial vehicle is an unmanned aerial vehicle, UAV.

### Claim 10 (depends on 1)

A non-transitory computer readable storage medium storing a computer program comprising instructions which when executed by processing circuitry of a modeling apparatus causes the modeling apparatus to perform the method of claim 1.

### Claim at position 11

11-13. (canceled)

### Claim 14

A modeling apparatus , the modeling apparatus comprising:
processing circuitry ; and
a memory, the memory containing instructions executable by the processing circuitry, wherein the modeling apparatus is configured to perform a method for producing a reduced point cloud comprising an object of interest (OOI ) from an original point cloud comprising the OOI, the method comprising:
obtaining the original point cloud, the original point cloud comprising a set of points, each point having a location in a three-dimensional (3D) space;
obtaining a set of N images, each of the N images comprising an image of the OOI from a unique position relative to the OOI;
for each one of the N images, defining an area of interest in the image that includes the OOI, thereby defining N areas of interest;
for each point included in the set of points, determining, for each one of the N areas of interest, whether the point is located in the area of interest;
for each point included in the set of points, determining a first metric for the point based on the total number of the N areas of interest in which the point is determined to be located; and
for each point included in the set of points, determining whether or not to include the point in the reduced point cloud based on the first metric for the point.

### Claim 15 (depends on 14)

The modeling apparatus of claim 14, wherein the method further comprises:
for each point included in the set of points, determining whether the first metric for the point satisfies a first threshold condition and adding the point to the reduced point cloud as a result of determining that the first metric for the point satisfies the first threshold condition.

### Claim 16 (depends on 15)

The modeling apparatus of claim 15, wherein
determining the first metric, m1, for a particular point included in the set of points comprises calculating m1=Cin/N, where Cin is a value equal to the total number of the N areas of interest in which the particular point is determined to be located, and
determining whether m1 satisfies the first threshold condition comprising determining whether m1 is greater than a threshold.

### Claim 17 (depends on 14)

The modeling apparatus of claim 14, wherein the method further comprises:
for each point included in the reduced point cloud, determining, for each one of the N areas of interest, whether the point is within a threshold distance of a lower edge of the area of interest.

### Claim 18 (depends on 17)

The modeling apparatus of claim 17, wherein the method further comprises:
for each point included in the reduced point cloud, determining a second metric for the point based on the total number of the N areas of interest for which the point is determined to be within the threshold distance of the lower edge of the area of interest;
for each point included in the reduced point cloud for which the second metric satisfies a threshold condition, using the point to determine a plane; and
removing from the reduced point cloud all of the points in the reduce point cloud that are positioned below the determined plane.

### Claim 19 (depends on 14)

The modeling apparatus of claim 14, wherein the step of determining, for each one of the N areas of interest, whether the point is located in the area of interest comprises:
obtaining 3D location information specifying the location of the point in the 3D space;
obtaining camera pose information identifying a camera pose associated with the one of the N images;
obtaining intrinsic camera information, the intrinsic camera information comprising focal length information identifying a focal length;
based on the 3D location information, the camera pose information, and the intrinsic camera information, obtaining two-dimensional (2D) location information indicating the location of the point in the one of the N images; and
using the obtained 2D location information to determine whether the point is within the area of interest corresponding to the one of the N images.

### Claim 20 (depends on 19)

The modeling apparatus of claim 19, wherein
the area of interest has a center point located at the coordinates Cu and Cv,
the area of interest has a width of W,
the area of interest has a height of H,
the 2D location information consists of a pair of coordinates u,v,
the step of using the obtained 2D location information to determine whether the point is within the area of interest corresponding to the one of the N images comprises:
determining if |Cu−u|≤W/2; and
determining if |Cv−v|≤H/2.

### Claim 21 (depends on 14)

The modeling apparatus of claim 14, wherein the step of obtaining a set of N images comprises flying an aerial vehicle equipped with a camera on a path that circles the OOI, and, while the drone is flying on the path, operating the camera to obtain the N images.

### Claim 22 (depends on 21)

The modeling apparatus of claim 21, wherein the aerial vehicle is an unmanned aerial vehicle, UAV.