Method for triggering events in a video

• US 10,283,162 B2
• Filed: 06/25/2014
• Issued: 05/07/2019
• Est. Priority Date: 02/05/2014
• Status: Active Grant

• Current Assignee: Avatar Merger Sub II, LLC
• Original Assignee: Avatar Merger Sub II, LLC
• Inventors: Shaburova, Elena, Shaburov, Victor
• Primary Examiner(s): Tran, Thai Q
• Assistant Examiner(s): Mesa, Jose M
• Application Number:
  US14/314,343
• Publication Number:
  US 20150221338A1
• Time in Patent Office: 1,777 Days
• Field of Search: 386271
• CPC Class Codes: G06F 3/011 Arrangements for interaction with the human body, e.g. for user immersion in virtual reality blind teaching G09B21/00
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06T 11/001 Texturing; Colouring; Generation of texture or colour inpainting G06T5/77
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06T 13/40 of characters, e.g. humans, animals or virtual beings
• CPC Class Codes: G06T 17/20 Finite element generation, e.g. wire-frame surface description, tesselation
• CPC Class Codes: G06T 19/20 Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10021 Stereoscopic video; Stereoscopic image sequence
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/20036 Morphological image processing
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 5/77 Retouching; Inpainting; Scratch removal
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/251 involving models
• CPC Class Codes: G06T 7/33 using feature-based methods
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 10/40 Extraction of image or video features
• CPC Class Codes: G06V 10/42 Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
• CPC Class Codes: G06V 10/467 Encoded features or binary features, e.g. local binary patterns [LBP]
• CPC Class Codes: G06V 10/56 : relating to colour
• CPC Class Codes: G06V 10/60 : relating to illumination properties, e.g. using a reflectance or lighting model
• CPC Class Codes: G06V 20/40 : in video content extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44
• CPC Class Codes: G06V 20/46 : Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
• CPC Class Codes: G06V 40/167 : using comparisons between temporally consecutive images
• CPC Class Codes: G06V 40/168 : Feature extraction; Face representation
• CPC Class Codes: G06V 40/171 : Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships
• CPC Class Codes: G06V 40/174 : Facial expression recognition
• CPC Class Codes: G06V 40/20 : Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: G11B 27/031 : Electronic editing of digitised analogue information signals, e.g. audio or video signals
• CPC Class Codes: H04N 5/262 : Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
• CPC Class Codes: H04N 9/79 : Processing of colour television signals in connection with recording

Abstract

A computer implemented method of triggering events in a video, the method comprising: providing a list of objects with their states and corresponding events in video such that each state from the list triggers at least one event of the corresponding events, wherein each object from the list has at least one state triggering at least one event of the corresponding events from the list in video; detecting at least one object from the list that at least partially and at least occasionally is presented in frames of the video; tracking the at least one object and its state; triggering at least one event of the corresponding events from the list in video in case the state of the at least one object matches with one of its states from the list.

Claims

1. A computer-implemented method for triggering events in a video, the method being performed in connection with a computerized system comprising a processing unit and a memory, the method comprising:

providing a list comprising a set of objects, a set of object states associated with the set of objects, and a set of events, wherein the set of objects are associated with one or more images of a user and each object from the set of objects has at least one object state triggering at least one event from the set of events in the video and each object state is associated with at least one point of an object of the set of objects;

detecting a face of the user within frames of the video, the face including a set of landmark points corresponding to facial features;

aligning a mesh with the face of the user, the mesh containing a set of feature reference points, each feature reference point corresponding to a landmark point of the set of landmark points;

detecting at least one object from the list that at least partially and at least occasionally is presented in frames of the video, the at least one object including at least a portion of the set of feature reference points, the portion of the set of feature reference points aligned with one or more points of the at least one object;

tracking the at least one object across two or more frames, the at least one object having a first object state;

identifying a change in the first object state of the at least one object to a second object state, the change from the first object state to the second object state corresponding to movement of a first portion of landmark points relative to one or more feature reference points of the mesh, indicating movement of the first portion of landmark points on the face of the user, while a second portion of landmark points remain aligned with corresponding feature reference points of the mesh;

determining that the second object state of the at least one object matches a state from the set of object states; and

in response to determining the match, triggering at least one event of the set of events in the video, the at least one event modifying the one or more images of the user by;

selecting a visualization from a plurality of visualizations associated with the at least one event; and

replacing at least a portion of the face, associated with the feature reference point within the frames of the video, with the selected visualization to modify the video, the feature reference point corresponding to the at least one point moved by the change from the first object state to the second object state.

2. The computer-implemented method of claim 1, wherein the second object state comprises a facial gesture, and wherein the plurality of visualizations includes a plurality of animal depictions.

3. The computer-implemented method of claim 1, wherein the set of object states comprises a plurality of facial gestures, wherein each of the plurality of facial gestures is associated with a different animal depiction of a plurality of animal depictions.

4. The computer-implemented method of claim 1, further comprising:

tracking the at least one object and its state after triggering one event of the set of events in the video; and

removing the triggered event from the video in case of detecting change of the state of the at least one object.

5. The computer-implemented method of claim 4, wherein the triggered event is removed from the video in case of detecting a state of the at least one object, such that the state of the at least one object corresponds to its pre-triggering state, the pre-triggering state being defined as an average state based on at least one state prior to the state that triggered the event.

6. The computer-implemented method of claim 4, wherein the triggered event is removed from the video in case of detecting change of the state of the at least one object from a current state to another state opposite to the current state.

7. The computer-implemented method of claim 1, further comprising:

after triggering the at least one event, removing the selected visualization from the video after an amount of time.

8. The computer-implemented method of claim 1, wherein the objects from the list include a human'"'"'s face and parts of a human body.

9. The computer implemented method of claim 1, wherein the video comprises a real-time video stream.

10. A computer implemented method for triggering events in a video, the method being performed in connection with a computerized system comprising a processing unit and a memory, the method comprising:

providing a list comprising a set of objects, a set of object states associated with the set of objects, and a set of events, wherein the set of objects are associated with one or more images of a user and each object from the set of objects has at least one object state triggering at least one event from the set of events in the video and each object state is associated with at least one point of an object of the set of objects;

detecting a face of the user within frames of the video, the face including a set of landmark points corresponding to facial features;

aligning a mesh with the face of the user, the mesh containing a set of feature reference points, each feature reference point corresponding to a landmark point of the set of landmark points;

detecting at least one object from the list that at least partially and at least occasionally is presented in frames of the video, the at least one object including at least a portion of the set of feature reference points, the portion of the set of feature reference points aligned with one or more points of the at least one object;

tracking the at least one object having a first object state across two or more frames;

identifying a change in the first object state of the at least one object to a second object state, the change from the first object state to the second object state corresponding to movement of a first portion of landmark points relative to one or more feature reference points of the mesh, indicating movement of the first portion of landmark points on the face of the user, while a second portion of landmark points remain aligned with corresponding feature reference points of the mesh;

determining the second object state of the at least one object matches a state from the set of object states; and

in response to determining the match, triggering one random event from the list in video, the random event modifying the one or more images of the user and the mesh aligned with the face of the user by;

selecting a visualization from a plurality of visualizations associated with the random event; and

replacing at least a portion of the face, associated with at least one feature reference point of the set of feature reference points within the frames of the video, with the selected visualization to modify the video.

11. A computer-implemented method of triggering events in a video which frames comprise images of a user and one or more objects associated with the images of the user, the method being performed in connection with a computerized system comprising a processing unit and a memory, the method comprising:

providing a list comprising a set of pieces of information and a set of events, wherein each piece of information from the set of pieces of information triggers at least one event from the set of events in the video, and wherein each event from the set of events modifies an object of the one or more objects associated with the images of the user;

detecting a face of the user within frames of the video, the face including a set of landmark points corresponding to facial features;

aligning a mesh with the face of the user, the mesh containing a set of feature reference points, each feature reference point corresponding to a landmark point of the set of landmark points;

identifying a change in the first object state of the at least one object to a second object state, the change from the first object state to the second object state corresponding to movement of a first portion of landmark points relative to one or more feature reference points of the mesh, indicating movement of the first portion of landmark points on the face of the user, while a second portion of landmark points remain aligned with corresponding feature reference points of the mesh;

determining the information relating to the user matches at least one of the pieces of information from the set of pieces of information; and

in response to identifying the information, triggering at least one event from the set of events in video, the at least one event modifying at least one object of the one or more objects associated with the images of the user by;

selecting a visualization from a plurality of visualizations associated with the at least one event; and

replacing at least a portion of the face, associated with at least one feature reference point of the set of feature reference points within the frames of the video, with the selected visualization to modify the video.

12. A mobile computerized system comprising a central processing unit and a memory, the memory storing instructions for:

providing a list comprising a set of objects, a set of object states associated with the set of objects, and a set of events, wherein the set of objects are associated with one or more images of a user and each object from the set of objects has at least one object state triggering at least one event from the set of events in the video and each object state is associated with at least one point of an object of the set of objects;

detecting a face of the user within frames of the video, the face including a set of landmark points corresponding to facial features;

aligning a mesh with the face of the user, the mesh containing a set of feature reference points, each feature reference point corresponding to a landmark point of the set of landmark points;

detecting at least one object from the list that at least partially and at least occasionally is presented in frames of the video, the at least one object including at least a portion of the set of feature reference points, the portion of the set of feature reference points aligned with one or more points of the at least one object;

tracking the at least one object having a first object state across two or more frames;

identifying a change in the first object state of the at least one object to a second object state, the change from the first object state to the second object state corresponding to movement of a first portion of landmark points relative to one or more feature reference points of the mesh, indicating movement of the first portion of landmark points on the face of the user, while a second portion of landmark points remain aligned with corresponding feature reference points of the mesh;

determining the second object state of the at least one object matches a state from the set of object states; and

in response to determining the match, triggering at least one event of the set of events in the video, the at least one event modifying the one or more images of the user by;

selecting a visualization from a plurality of visualizations associated with the at least one event; and

replacing at least a portion of the face, associated with the feature reference point within the frames of the video, with the selected visualization to modify the video, the feature reference point corresponding to the at least one point moved by the change from the first object state to the second object state.

13. The mobile computerized system of claim 12, wherein the events in the set of events are selected from a group including modification of the at least one object, modification of at least one part of the at least one object, masking of the at least one object, adding at least one new object into the frames of the video, and using visual filters for the at least one object.

14. The mobile computerized system of claim 12, wherein the at least one event of the set of events is triggered in the video after a time delay.

15. The mobile computerized system of claim 12, wherein the memory further stores instructions for:

tracking the at least one object and its state after triggering one event of the set of events in the video; and

removing the triggered event from the video in case of detecting change of the state of the at least one object.

16. The mobile computerized system of claim 15, wherein the triggered event is removed from the video in case of detecting a state of the at least one object, such that the state of the at least one object corresponds to its pre-triggering state, the pre-triggering state being defined as an average state based on at least one state prior to the state that triggered the event.

17. The mobile computerized system of claim 15, wherein the triggered event is removed from the video in case of detecting change of the state of the at least one object from the current state to another state opposite to the current state.

18. The mobile computerized system of claim 12, wherein the memory further stores instructions for:

after triggering the at least one event, removing the selected visualization from the video after an amount of time.