Real-time video compositing technique (VFX/AR, granted).
Systems and methods for compositing real-world video with a virtual object are disclosed. In one embodiment the system includes a processor; and a computer-readable non-transitory storage medium, the medium encoded with instructions that when executed cause the processor to perform operations including receiving video of a video capture region from a camera coupled to an unmanned vehicle; obtaining a map representation of the video capture region; placing the virtual object into the map representation; rendering the video with the virtual object to generate a rendered video; displaying the rendered video; and 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.
CROSS REFERENCE TO RELATED APPLICATIONS (1) This application claims the benefit of priority pursuant to 35 U.S.C. § 120 of U.S. patent application Ser. No. 15/970,783, filed 3 May 2018, U.S. Pat. No. 11,272,081 entitled “Systems and Methods for Real-Time Compositing of Video Content,” which is hereby incorporated by reference herein in its entirety. BACKGROUND (2) 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 (3) A system for compositing real-world video with a virtual object is disclosed. In one embodiment the system includes a processor; and a computer-readable non-transitory storage medium, the medium encoded with instructions that when executed cause the processor to perform operations including receiving video of a video capture region from a camera coupled to an unmanned vehicle; obtaining a map representation of the video capture region; displaying the map representation on a graphical user interface; placing the virtual object into the map representation; rendering the video with the virtual object to generate a rendered video; displaying the rendered video; and based on an elevation of the unmanned vehic
1. A system for compositing real-world video with a virtual object comprising: a processor; and a computer-readable non-transitory storage medium, the computer-readable non-transitory storage medium encoded with instructions that when executed cause the processor to perform operations comprising: receiving video of a video capture region from a camera coupled to an unmanned vehicle and an orientation of the camera during capture of the video; obtaining a map representation of the video capture region; placing the virtual object into the map representation; rendering the video with the virtual object to generate a rendered video; displaying the rendered video; receiving an updated orientation of the camera; and based on a change to an elevation of the unmanned vehicle and the updated orientation of the camera, updating the virtual object in the rendered video to transition between a first representation of the virtual object at a first elevation of the unmanned vehicle and a second representation of the virtual object at a second elevation of the unmanned vehicle, wherein the virtual object appears to be two dimensional in the first representation and three dimensional in the second representation. ||
13. A method for compositing real-time, real-world video with a virtual object, comprising: receiving video of a video capture region from a camera coupled to an unmanned vehicle and an orientation of the camera during capture of the video; obtaining a map representation of the video capture region; placing the virtual object into the map representation; rendering the video with the virtual object to generate a rendered video; displaying the rendered video; receiving an updated orientation of the camera; and based on a change to an elevation of the unmanned vehicle and the updated orientation of the camera, updating the virtual object in the rendered video to transition between a first representation of the virtual object at a first elevation of the unmanned vehicle and a second representation of the virtual object at a second elevation of the unmanned vehicle, wherein the virtual object appears to be two dimensional in the first representation and three dimensional in the second representation. ||
20. A system for compositing real-world video with a virtual object comprising: an unmanned vehicle; a processor configured to: receive video of a video capture region from a camera coupled to the unmanned vehicle and an orientation of the camera during capture of the video; obtain a map representation of the video capture region; place the virtual object into the map representation; render the video with the virtual object to generate a rendered video; display the rendered video; receive an updated orientation of the camera; and based on a change to an elevation of the unmanned vehicle and the updated orientation of the camera, update the virtual object to transition between a first representation of the virtual object at a first elevation of the unmanned vehicle and a second representation of the virtual object at a second elevation of the unmanned vehicle, wherein the virtual object appears to be two dimensional in the first representation and three dimensional in the second representation.