# US 2021/0241518 A1 · Methods and apparatus to detect collision of a virtual camera with objects in three-dimensional volumetric model

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

- Number: US 2021/0241518 A1
- Document ID: US20210241518A1
- Status: Published application
- Kind: A1
- Application number: 17/054,078
- Filed: 2018-12-24
- Published: 2021-08-05
- Earliest claimed: 2018-12-24
- Assignees: Intel Corporation
- Applicants: Intel Corporation
- Inventors: Xiaofeng Tong; Qiang Li; Wenlong Li; Yikai Fang; Ofer Shkedi
- Web page: https://patentgrep.com/patent/US20210241518A1

## CPC

- G06T 15/20: Perspective computation
- H04N 7/181: {for receiving images from a plurality of remote sources}
- G06T 17/00: Three-dimensional [3D] modelling for computer graphics
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- H04N 23/60: Control of cameras or camera modules
- G06T 2210/12: Bounding box
- G06T 2210/21: Collision detection, intersection
- G06V 2201/12: Acquisition of 3D measurements of objects
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Methods and apparatus to detect collision of a virtual camera with objects in a three-dimensional volumetric model are disclosed herein. An example virtual camera system disclosed herein includes cameras to obtain images of a scene in an environment. The example virtual camera system also includes a virtual camera generator to create a 3D volumetric model of the scene based on the images, identify a 3D location of a virtual camera to be disposed in the 3D volumetric model, and detect whether a collision occurs between the virtual camera and one or more objects in the 3D volumetric model.

## Claims

### Claim 1

A virtual camera system comprising:
cameras to obtain images of a scene in an environment; and
a virtual camera generator to:
create a 3D volumetric model of the scene based on the images;
identify a 3D location of a virtual camera to be disposed in the 3D volumetric model; and
detect whether a collision occurs between the virtual camera and one or more objects in the 3D volumetric model.

### Claim 2 (depends on 1)

The virtual camera system of claim 1, wherein the virtual camera generator is to detect whether a collision occurs by:
projecting the virtual camera into the images in which the 3D location of the virtual camera appears;
determining, for respective ones of the images, whether an overlap occurs between the virtual camera and an object in the respective image; and
comparing a number of the images with overlaps to a threshold.

### Claim 3 (depends on 2)

The virtual camera system of claim 2, wherein the virtual camera generator is to determine whether an overlap occurs by:
computing a camera boundary box around the virtual camera in the images in which the virtual camera appears;
computing an object boundary box around each object in the images in which the virtual camera appears; and
determining whether there is an overlap between the camera boundary box and at least one of the object boundary boxes in the respective images.

### Claim 4 (depends on 1)

The virtual camera system of claim 1, wherein the 3D location is a first 3D location, and wherein, if the virtual camera generator detects a collision, the virtual camera generator is to at least one of generate an alert or select a second 3D location for the virtual camera.

### Claim 5 (depends on 1)

The virtual camera system of claim 1, further including a display, wherein, if the virtual camera generator does not detect a collision, the virtual camera generator is to:
generate an image of the scene in the 3D volumetric model from the 3D location of the virtual camera; and
cause the display to present the generated image of the scene.

### Claim 6 (depends on 1)

The virtual camera system of claim 1, wherein the environment is a sports arena including a playing field, and the scene is a moment during a game occurring on the playing field.

### Claim 7 (depends on 6)

The virtual camera system of claim 6, wherein the cameras are disposed around the sports arena and directed at various locations of the playing field.

### Claim 8

A non-transitory computer readable storage medium comprising instructions that, when executed, cause at least one processor to at least:
create a three-dimensional (3D) volumetric model of a scene in an environment based on a set of images of the scene;
identify a 3D location of a virtual camera to be disposed in the 3D volumetric model; and
detect whether a collision occurs between the virtual camera at the 3D location and one or more objects in the 3D volumetric model.

### Claim 9 (depends on 8)

The non-transitory computer readable storage medium of claim 8, wherein the instructions, when executed, cause the at least one processor to detect whether a collision occurs by:
projecting the virtual camera into the images in which the 3D location of the virtual camera appears;
determining, for respective ones of the images, whether an overlap occurs between the virtual camera and an object in the respective image; and
comparing a number of the images with overlaps to a threshold.

### Claim 10 (depends on 9)

The non-transitory computer readable storage medium of claim 9, wherein the instructions, when executed, cause the at least processor to determine whether an overlap occurs by:
computing a camera boundary box around the virtual camera in the images in which the virtual camera appears;
computing an object boundary box around each object in the images in which the virtual camera appears; and
determining whether there is an overlap between the camera boundary box and at least one of the object boundary boxes in the respective images.

### Claim 11 (depends on 8)

The non-transitory computer readable storage medium of claim 8, wherein the 3D location is a first 3D location, and wherein, if a collision is detected, the instructions, when executed, cause the at least one processor to at least one of generate an alert or select a second 3D location for the virtual camera.

### Claim 12 (depends on 8)

The non-transitory computer readable storage medium of claim 8, wherein, if a collision is not detected, the instructions, when executed, cause the at least one processor to:
generate an image of the scene in the 3D volumetric model from the 3D location of the virtual camera; and
cause a display to present the generated image of the scene.

### Claim 13 (depends on 8)

The non-transitory computer readable storage medium of claim 8, wherein the environment is a sports arena including a playing field, and the scene is a moment during a game occurring on the playing field.

### Claim 14 (depends on 13)

The non-transitory computer readable storage medium of claim 13, wherein the set of images are obtained by a respective set of cameras disposed around the sports arena and directed at various locations of the playing field.

### Claim 15

A method to improve viewing a scene in a three-dimensional (3D) volumetric model, the method comprising:
creating, by executing an instruction with at least one processor, a 3D volumetric model of a scene in an environment based on a set of images of the scene;
identifying, by executing an instruction with the at least one processor, a 3D location of a virtual camera to be disposed in the 3D volumetric model; and
detecting, by executing an instruction with the at least one processor, whether a collision occurs between the virtual camera at the 3D location and one or more objects in the 3D volumetric model.

### Claim 16 (depends on 15)

The method of claim 15, wherein the detecting of whether a collision occurs includes:
projecting the virtual camera into the images in which the 3D location of the virtual camera appears;
determining, for respective ones of the images, whether an overlap occurs between the virtual camera and an object in the respective image; and
comparing a number of the images with overlaps to a threshold.

### Claim 17 (depends on 16)

The method of claim 16, wherein the determining of whether an overlap occurs includes:
computing a camera boundary box around the virtual camera in the images in which the virtual camera appears;
computing an object boundary box around each object in the images in which the virtual camera appears; and
determining whether there is an overlap between the camera boundary box and at least one of the object boundary boxes in the respective images.

### Claim 18 (depends on 15)

The method of claim 15, wherein the 3D location is a first 3D location, further including, if a collision is detected, at least one of generating an alert or selecting a second 3D location for the virtual camera.

### Claim 19 (depends on 15)

The method of claim 15, further including, if a collision is not detected:
generating, by executing an instruction with the at least one processor, an image of the scene in the 3D volumetric model from the 3D location of the virtual camera; and
displaying the generated image of the scene.

### Claim 20 (depends on 15)

The method of claim 15, wherein the environment is a sports arena including a playing field, and the scene is a moment during a game occurring on the playing field.

### Claim 21 (depends on 20)

The method of claim 20, further including obtaining the set of images from a respective set of cameras disposed around the sports arena and directed at various locations of the playing field.

### Claim 22

An apparatus comprising:
means for obtaining a set of images of a scene in an environment; and
means for processing, the processing means to:
create a 3D volumetric model of the scene based on the images;
identify a 3D location of a virtual camera to be disposed in the 3D volumetric model; and
detect whether a collision occurs between the virtual camera and one or more objects in the 3D volumetric model.

### Claim 23 (depends on 22)

The apparatus of claim 22, wherein the processing means is to detect whether a collision occurs by:
projecting the virtual camera into the images in which the 3D location of the virtual camera appears;
determining, for respective ones of the images, whether an overlap occurs between the virtual camera and an object in the respective image; and
comparing a number of the images with overlaps to a threshold.

### Claim 24 (depends on 23)

The apparatus of claim 23, wherein the processing means is to determine whether an overlap occurs by:
computing a camera boundary box around the virtual camera in the images in which the virtual camera appears;
computing an object boundary box around each object in the images in which the virtual camera appears; and
determining whether there is an overlap between the camera boundary box and at least one of the object boundary boxes in the respective images.

### Claim 25 (depends on 22)

The apparatus of claim 22, further including means for displaying, wherein the 3D location is a first 3D location,
wherein, if the processing means detects a collision, the processing means is to at least one of generate an alert or select a second 3D location for the virtual camera, and
wherein, if the processing means does not detect a collision, the processing means is to generate an image of the scene in the 3D volumetric model from the 3D location of the virtual camera, and the display means is to present the generated image of the scene.