Systems and methods for providing real-time composite video from multiple source devices featuring augmented reality elements
Systems and methods for superimposing the human elements of video generated by computing devices, wherein a first user device and second user device capture and transmit video to a central server which analyzes the video to identify and extract human elements, superimpose these human elements upon one another, adds in at least one augmented reality element, and then transmits the newly created superimposed video back to at least one of the user devices.
1. A computer-implemented method of superimposing video carried out by a processor, the method comprising the steps of:
receiving a first live video from a first user device, the first live video including video of a first human element of a first user captured by a rear facing camera of the first user device;
receiving a second video from a second user device, the second video including video of a second user;
identifying and extracting the first human element of the first user from the first live video using a detection algorithm;
combining the first human element of the first user and a portion or all of the second video to create a superimposed video including the first human element of the first user captured by the rear facing camera of the first user device from the first live video and a second human element of the second user from the second video; and
displaying the superimposed video on a front facing display of the first user device, the displayed superimposed video including the extracted first human element of the first user captured by the rear facing camera of the first user device;
wherein the first user is simultaneously viewing the front facing display of the first user device displaying the superimposed video while the video of the first human element of the first user is being captured by the rear facing camera of the first user device;
wherein the location of the extracted first human element captured by the rear facing camera of the first user device and displayed on the second user device within the superimposed video is directly controlled by the position of the first human element relative to the location of the rear facing camera of the first user device; and
further wherein the first user moves the first human element into a chosen position relative to the second human element in the superimposed video.
2. The computer-implemented method of superimposing video of claim 1 , wherein in response to real-time movement by the first human element of the first user relative to the first user device, contact is simulated between the first human element of the first user and the second human element of the second user in the superimposed video.
3. The computer-implemented method of superimposing video of claim 2 , wherein, in response to simulated contact between the first human element of the first user and the second human element of the second user in the superimposed video, the first user device provides a haptic response.
4. The computer-implemented method of superimposing video of claim 3 , wherein, in response to simulated contact between the first human element of the first user and the second human element of the second user in the superimposed video, the second user device provides a haptic response.
5. The computer-implemented method of superimposing video of claim 2 , wherein the first user aligns the position of the first human element of the first user to simulate contact with the second human element of the second user in the superimposed video while viewing the position of the first human element of the first user and the second human element of the second user on the front facing display of the first user device to selectively induce a haptic response in at least one of the first user device and the second user device.
6. The computer-implemented method of superimposing video of claim 1 , further comprising the step of:
identifying and extracting a first non-human element from the first live video using a detection algorithm; and
wherein the step of combining the first human element of the first user and a portion or all of the second video to create a superimposed video including the first human element of the first user captured by the rear facing camera of the first user device from the first live video and a second human element of the second user from the second video further includes:
combining the first non-human element from the first live video with the first human element of the first user and a portion or all of the second video to create a superimposed video including the first non-human element captured by the rear facing camera of the first user device from the first live video, the first human element of the first user captured by the rear facing camera of the first user device from the first live video and a second human element of the second user from the second video.
7. The computer-implemented method of superimposing video of claim 6 , wherein, in response to movement of the first human element of the first user relative to the first user device, each of the first non-human element and the first human element of the first user obscures at least a portion of the second human element of the second user in the superimposed video.
8. The computer-implemented method of superimposing video of claim 1 , wherein, in response to movement of the first human element of the first user relative to the first user device, the first human element of the first user obscures at least a portion of the second human element of the second user in the superimposed video.
9. The computer-implemented method of superimposing video of claim 1 , wherein the second user views a video on the front facing screen of the second device that is a real-time combination of some part of the first live video including the first human element of the first user taken from the rear facing camera of the first device and some part of the second live video including the second human element of the second user taken from the front facing camera of the second device.
10. The computer-implemented method of superimposing video of claim 1 , wherein the second video is pre-recorded.
11. A computer-implemented system for superimposing video, comprising:
a first user device featuring a camera, processor, memory, and networking interface;
a second user device featuring a camera, processor, memory, and networking interface;
wherein one of the first user device's processor and the second user device's processor:
receives a first live video from a first user device, the first live video including video of a first human element of a first user captured by a rear facing camera of the first user device, and a second video from a second user device, the second video including video of a second user;
identifies and extracts a first human element of the first user from the first live video using a detection algorithm;
combines the first human element of the first user and a portion or all of the second video to create a superimposed video including the first human element of the first user captured by the rear facing camera of the first user device from the first live video and a second human element of the second user captured by the front facing camera of the second user device from the second video; and
displaying the superimposed video on the front facing display of the first user device, the displayed superimposed video including the extracted first human element of the first user captured by the rear facing camera of the first user device;
wherein the first user is simultaneously viewing the front facing display of the first user device displaying the superimposed video while the video of the first human element of the first user is being captured by the rear facing camera of the first user device;
wherein the location of the extracted first human element captured by the rear facing camera of the first user device and displayed on the second user device within the superimposed video is directly controlled by the position of the first human element relative to the location of the rear facing camera of the first user device; and
further wherein the first user moves the first human element into a chosen position relative to the second human element in the superimposed video.
12. The computer-implemented system for superimposing video of claim 11 , wherein in response to real-time movement by the first human element of the first user relative to the first user device, contact is simulated between the first human element of the first user and the second human element of the second user in the superimposed video.
13. The computer-implemented system of superimposing video of claim 12 , wherein, in response to simulated contact between the first human element of the first user and the second human element of the second user in the superimposed video, the first user device provides a haptic response.
14. The computer-implemented system of superimposing video of claim 13 , wherein, in response to simulated contact between the first human element of the first user and the second human element of the second user in the superimposed video, the second user device provides a haptic response.
15. The computer-implemented system of superimposing video of claim 12 , wherein the first user aligns the position of the first human element of the first user to simulate contact with the second human element of the second user in the superimposed video while viewing the position of the first human element of the first user and the second human element of the second user on the front facing display of the first user device to selectively induce a haptic response in at least one of the first user device and the second user device.
16. The computer-implemented system of superimposing video of claim 11 , further wherein one of the first user device's processor and the second user device's processor further:
identifies and extracts a first non-human element from the first live video using a detection algorithm; and
combines the first non-human element from the first live video with the first human element of the first user and a portion or all of the second video to create a superimposed video including the first non-human element captured by the rear facing camera of the first user device from the first live video, the first human element of the first user captured by the rear facing camera of the first user device from the first live video and a second human element of the second user from the second video.
17. The computer-implemented system of superimposing video of claim 16 , wherein, in response to movement of the first human element of the first user relative to the first user device, each of the first non-human element and the first human element of the first user obscures at least a portion of the second human element of the second user in the superimposed video.
18. The computer-implemented system for superimposing video of claim 11 , wherein in response to movement of the first human element of the first user relative to the first user device, the first human element of the first user obscures at least a portion of the second human element of the second user in the transmitted superimposed video.
19. The computer-implemented system of superimposing video of claim 11 , wherein the second user views a video on the front facing screen of the second device that is a real-time combination of some part of the first live video including the first human element of the first user taken from the rear facing camera of the first device and some part of the second live video including the second human element of the second user taken from the front facing camera of the second device.
20. The computer-implemented system for superimposing video of claim 11 , wherein the second video is pre-recorded.