Systems and methods for real-time efficient navigation of video streams
AssigneeFuji Xerox Co., Ltd.
InventorsLaurent Denoue, Scott Carter, Matthew L. Cooper
Life of this patent
Estimating the term…
Abstract
Described are systems and methods that allow a video conference participant to efficiently review semantically meaningful events within the video streams shared by their peers. Because participants are engaged in real-time communication, it is important to provide tools that let them quickly jump back to past events that were shown previously, not requiring them to manipulate a standard video timeline. Our techniques thus find meaningful events in the video stream such as scrolling pages, moving windows, typing text, etc. Using these techniques, a participant can then easily go back to e.g. the last PDF page shown by a peer, while still listening to the live audio.
Claims21
A computer-implemented method performed in a computerized system comprising a central processing unit, a display device, a network interface and a memory, the computer-implemented method comprising:
- a. using the network interface to receive a live video stream from a remote computerized system, the live video stream comprising a plurality of frames;
- b. displaying the received live video stream on the display device;
- c. using the central processing unit to identify a plurality of semantically significant events in the received live video stream;
- d. associating each of the identified plurality of semantically significant events with a respective keyframe from the live video stream;
- e. using the memory to store information on the identified plurality of semantically significant events and the associated keyframes;
- f. generating a navigable graphical user interface on the display device, the navigable graphical user interface displaying user-selectable representations of the keyframes from the live video stream;
- and
- g. in response to detection of an instruction from a user in connection with the navigable graphical user interface, displaying a keyframe associated with one of the identified plurality of semantically significant events on the display device, wherein the keyframe is displayed on the display device in addition to, or replacing the displayed received live video stream and wherein the one of the identified plurality of semantically significant events is a past event previously displayed to the user as a part of the live video stream.
A non-transitory computer-readable medium embodying a set of computer-executable instructions, which, when executed in a computerized system comprising a central processing unit, a display device, a network interface and a memory, cause the computerized system to perform a method comprising:
- a. using the network interface to receive a live video stream from a remote computerized system, the live video stream comprising a plurality of frames;
- b. displaying the received live video stream on the display device;
- c. using the central processing unit to identify a plurality of semantically significant events in the received live video stream;
- d. associating each of the identified plurality of semantically significant events with a respective keyframe from the live video stream;
- e. using the memory to store information on the identified plurality of semantically significant events and the associated keyframes;
- f. generating a navigable graphical user interface on the display device, the navigable graphical user interface displaying user-selectable representations of the keyframes from the live video stream;
- and
- g. in response to detection of an instruction from a user in connection with the navigable graphical user interface, displaying a keyframe associated with one of the identified plurality of semantically significant events on the display device, wherein the keyframe is displayed on the display device in addition to, or replacing the displayed received live video stream and wherein the one of the identified plurality of semantically significant events is a past event previously displayed to the user as a part of the live video stream.
A computerized system comprising a central processing unit, a display device, a network interface and a memory storing a set of instructions, the set of instructions comprising instructions for:
- a. using the network interface to receive a live video stream from a remote computerized system, the live video stream comprising a plurality of frames;
- b. displaying the received live video stream on the display device;
- c. using the central processing unit to identify a plurality of semantically significant events in the received live video stream;
- d. associating each of the identified plurality of semantically significant events with a respective keyframe from the live video stream;
- e. using the memory to store information on the identified plurality of semantically significant events and the associated keyframes;
- f. generating a navigable graphical user interface on the display device, the navigable graphical user interface displaying user-selectable representations of the keyframes from the live video stream;
- and
- g. in response to detection of an instruction from a user in connection with the navigable graphical user interface, displaying a keyframe associated with one of the identified plurality of semantically significant events on the display device, wherein the keyframe is displayed on the display device in addition to, or replacing the displayed received live video stream and wherein the one of the identified plurality of semantically significant events is a past event previously displayed to the user as a part of the live video stream.
A computer-implemented method performed in a computerized system comprising a central processing unit, a display device, a network interface and a memory, the computer-implemented method comprising:
- a. using the network interface to receive a live video stream from a remote computerized system, the live video stream comprising a plurality of frames;
- b. displaying the received live video stream on the display device;
- c. using the central processing unit to identify a plurality of semantically significant events in the received live video stream;
- d. associating each of the identified plurality of semantically significant events with a respective keyframe;
- e. using the memory to store information on the identified plurality of semantically significant events and the associated keyframes;
- f. in response to detection of an instruction from a user, displaying a keyframe associated with one of the identified plurality of semantically significant events on the display device, wherein the keyframe is displayed on the display device in addition to, or replacing the displayed received live video stream and wherein the one of the identified plurality of semantically significant events is a past event previously displayed to the user as a part of the live video stream;
- g. generating a second live video stream using a feed from a camera or a desktop activity based on a selection received from the user;
- h. displaying a suggestion to the user to select the desktop activity if a predetermined desktop activity is detected or displaying a suggestion to the user to select the feed from the camera if a predetermined desktop activity is not detected;
- and
- i. transmitting the generated second live video stream to the remote computerized system using the network interface.
Dependencies are inferred from the claim text.