- Number
- 11272081
- Published
- 2022-03-08
- Filed
- 2018-05-03
- Assignee
- DISNEY ENTERPRISES, INC.
- Inventors
- Chapman; Steven M., Patel; Mehul, Popp; Joseph
- CPC
- H04N21/854; G06T11/00; G06T11/65; H04N5/2228; H04N5/272; H04N21/41422; H04N21/4223
- Verdict
- Low Notable software
- Source
- Google Patents · FreePatentsOnline
The keeper's note
Real-time video compositing technique (VFX/AR).
Abstract
Systems, devices, and methods are disclosed for compositing real-time, real-world video with virtual objects. An electronic device includes circuitry coupled to a memory storing instructions that, when executed, cause the circuitry to receive video of a given video capture region. The circuitry is caused to receive location information and camera information from the unmanned vehicle. The circuitry is caused to obtain a representation of a location of interest corresponding to the location of the unmanned vehicle. The circuitry is caused to display the representation. The circuitry is caused to obtain virtual objects. The circuitry is caused to place the virtual objects into the representation. The circuitry is caused to render the virtual objects and the video to generate a rendered video including rendered virtual objects in at least one frame of the video. The circuitry is caused to send the rendered video.
Background
BACKGROUND (1) Scouting film locations may require photographers or videographers to capture a given environment without much input from a filmmaker. For example, the location may be remote, or the filmmaker may not have seen a scout's suggested location yet. The photos and videos may be captured and processed without considering the context for a scene in a movie, wasting time and money to scout the given environment. SUMMARY (2) Embodiments of the present disclosure include systems, methods, and devices, capable of compositing real-time, real-world video with virtual objects, as well as interconnected processors and/or circuitry, to render virtual objects to appear in a rendered video of a real-world location, including in some examples, by using video, location information, and camera information from an unmanned vehicle along with virtual object data to determine whether virtual objects will appear in the rendered video. (3) In accordance with aspects of the present disclosure, a server system composites real-time, real-world video with virtual objects. The server system includes a non-transitory computer-readable medium coupled to logic circuitry. The non-transitory computer-readable medium stores instructions that, when executed, cause the logic circuitry to perform a number of operations. One such operation is to receive video of a given video capture region from an unmanned vehicle via a camera. Another such operation is to receive location information and camera info
Claims
1. A server system for compositing real-time, real-world video with a virtual object, the server system comprising: a non-transitory computer-readable medium operatively coupled to circuitry and storing instructions that, when executed cause the circuitry to: receive location information and camera information from an unmanned vehicle including a camera; obtain a map representation of a location of interest, wherein the location of interest comprises a location of the unmanned vehicle; determine a video capture region within the map representation, based on the location information and the camera information; receive video of the video capture region from the unmanned vehicle via the camera; display the map representation on a graphical user interface; place the virtual object into the map representation at an object position based on a user input selecting the virtual object, wherein the virtual object comprises a story planning visualization for filming of visual media; in response to the object position in the map representation being within the video capture region, render the video to generate a rendered video, wherein the virtual object is rendered in at least one frame of the rendered video; based on an elevation of the unmanned vehicle, updating the virtual object to transition between a top view of the virtual object and an elevation view or perspective view of the virtual object. ||
8. A method for compositing real-time, real-world video with a virtual object, comprising: receiving location information and camera information from an unmanned vehicle including a camera; obtaining a map representation of a location of interest, wherein the location of interest comprises a location of the unmanned vehicle; determining a video capture region within the map representation, based on the location information and the camera information; receiving video of the video capture region from the unmanned vehicle via the camera; displaying the map representation on a graphical user interface; placing the virtual object into the map representation at an object position based on a user input selecting the virtual object, wherein the virtual object comprises a story planning visualization for filming of visual media; in response to the object position in the map representation being within the video capture region, rendering the video to generate a rendered video, wherein the virtual object is rendered in at least one frame of the rendered video; based on an elevation of the unmanned vehicle, updating the virtual object to transition between a top view of the virtual object and an elevation view or perspective view of the virtual object. ||
14. A server system for compo siting real-time, real-world video with a virtual object, the server system comprising: a receiver configured to receive incoming signals; a transmitter configured to send outgoing signals; a graphical user interface; circuitry coupled to the transmitter, the receiver, and the graphical user interface; and a non-transitory computer-readable medium operatively coupled to the circuitry and storing instructions that, when executed cause the circuitry to: receive, using the receiver, location information and camera information from an unmanned vehicle including a camera; obtain a map representation of a location of interest, wherein the location of interest comprises a location of the unmanned vehicle; determine a video capture region within the map representation, based on the location information and the camera information; receive, using the receiver, video of the video capture region from the unmanned vehicle via the camera; display the map representation on the graphical user interface; place the virtual object into the map representation at an object position based on a user input selecting the virtual object, wherein the virtual object comprises a story planning visualization for filming of visual media; in response to the object position in the map representation being within the video capture region, render the video to generate a rendered video, wherein the virtual object is rendered in at least one frame of the video; based on an elevation of the unmanned vehicle, updating the virtual object to transition between a top view of the virtual object and an elevation view or perspective view of the virtual object.