SYSTEMS AND METHODS FOR CREATING TARGET MOTION, CAPTURING MOTION, ANALYZING MOTION, AND IMPROVING MOTION
First Claim
1. A computer-readable storage medium storing instructions that, when executed by a computing system, cause the computing system to perform operations for creating a video combination, the operations comprising:
- obtaining a target video by one or more of;
manual selection of the target video;
orautomatic selection of the target video by;
receiving a target category;
identifying one or more first target videos showing an expert with target physical characteristics that correspond to subject physical characteristics of a subject, the subject physical characteristics either specified by a user or determined through automatic analysis of a subject video;
identifying one or more second target videos showing an expert with target motions that correspond to subject motions determined through automatic analysis of the subject video; and
selecting a target video that A) matches the target category, B) is one of the first target videos, and C) is one of the second target videos;
wherein the selected target video has been modified to have at least a background portion made transparent; and
wherein the selected target video is associated with camera positioning data indicating one or more camera locations;
obtaining a subject video by;
providing guidance to position one or more cameras based on the camera positioning data associated with the selected target video; and
receiving the subject video captured using the one or more cameras positioned according to the guidance;
adjusting spatial aspects of the target video or of the subject video such that particular spatial aspects of the target video corresponding to spatial aspects of the subject video, wherein the adjusting the spatial aspects comprises;
identifying a first size of a first identified object, in the subject video, comprising a body part or a piece of equipment; and
adjusting a second size of at least a portion of the target video, including a second identified object corresponding to the first identified object;
to align with the first size;
identifying synchronization points between the target video and the subject video, wherein each synchronization point identifies a temporal correspondence of motions or objects between the target video and the subject video, based on one or more of;
manual selections of one or more of the synchronization points;
automatic selection of points where a location of an identified object in the target video corresponds to a location of a corresponding identified object in the subject video;
automatic selection of points where a motion identified in the target video correspond to a motion identified object in the subject video;
automatic selection of points where a timing of sounds from the target video correspond to timing of sounds from the subject video;
automatic selection of points by a machine learning model that was trained using a set of training videos corresponding to the target category with marked synchronization points;
orany combination thereof;
adjusting playback of one or more segments of the target video or of the subject video such that at least a first synchronization point in the target video is displayed at the same time as a corresponding synchronization point in the subject video during playback;
modifying the target video to create a version of the target video with at least a portion of the expert displayed as an outline or partially transparent;
creating the video combination to facilitate comparison of the target video with the subject video by overlaying the version of the target video with the subject video; and
facilitating comparison, in the video combination, between the version of the target video and the subject video by performing one or more of;
in response to a viewpoint selection, changing a viewpoint of the target video and changing a viewpoint of the subject view;
automatically identifying that a deviation between the expert in the target video and the subject in the subject video is above a threshold deviation amount, and in response, displaying a deviation indication or playing a sound;
extrapolating motions of the subject to correspond to motions of the expert and, based on the extrapolating, providing an expected performance difference;
identifying aspects of motions of the subject which would benefit from an equipment change and providing a suggestion of the equipment change;
orany combination thereof.
0 Assignments
0 Petitions
Accused Products
Abstract
The present technology enables viewing, analyzing, and improve a variety of motions for a subject by facilitating comparison to a target video. Motions can include activities such as walking, athletic activities, and educational activities. The comparison can be accomplished by adjusting spatial aspects of a target and subject video to match. The comparison can also include identifying synchronization points, between the videos, that identify a temporal correspondence between of motions or objects in the videos and adjusting playback of one or more segments in the videos so corresponding synchronization points are displayed at the same time during playback. A version of one of the videos can be provided as an outline or as partially transparent, which can be overlaid with the other video to create a video combination for playback.
100 Citations
20 Claims
-
1. A computer-readable storage medium storing instructions that, when executed by a computing system, cause the computing system to perform operations for creating a video combination, the operations comprising:
-
obtaining a target video by one or more of; manual selection of the target video;
orautomatic selection of the target video by; receiving a target category; identifying one or more first target videos showing an expert with target physical characteristics that correspond to subject physical characteristics of a subject, the subject physical characteristics either specified by a user or determined through automatic analysis of a subject video; identifying one or more second target videos showing an expert with target motions that correspond to subject motions determined through automatic analysis of the subject video; and selecting a target video that A) matches the target category, B) is one of the first target videos, and C) is one of the second target videos; wherein the selected target video has been modified to have at least a background portion made transparent; and wherein the selected target video is associated with camera positioning data indicating one or more camera locations; obtaining a subject video by; providing guidance to position one or more cameras based on the camera positioning data associated with the selected target video; and receiving the subject video captured using the one or more cameras positioned according to the guidance; adjusting spatial aspects of the target video or of the subject video such that particular spatial aspects of the target video corresponding to spatial aspects of the subject video, wherein the adjusting the spatial aspects comprises; identifying a first size of a first identified object, in the subject video, comprising a body part or a piece of equipment; and adjusting a second size of at least a portion of the target video, including a second identified object corresponding to the first identified object;
to align with the first size;identifying synchronization points between the target video and the subject video, wherein each synchronization point identifies a temporal correspondence of motions or objects between the target video and the subject video, based on one or more of; manual selections of one or more of the synchronization points; automatic selection of points where a location of an identified object in the target video corresponds to a location of a corresponding identified object in the subject video; automatic selection of points where a motion identified in the target video correspond to a motion identified object in the subject video; automatic selection of points where a timing of sounds from the target video correspond to timing of sounds from the subject video; automatic selection of points by a machine learning model that was trained using a set of training videos corresponding to the target category with marked synchronization points;
orany combination thereof; adjusting playback of one or more segments of the target video or of the subject video such that at least a first synchronization point in the target video is displayed at the same time as a corresponding synchronization point in the subject video during playback; modifying the target video to create a version of the target video with at least a portion of the expert displayed as an outline or partially transparent; creating the video combination to facilitate comparison of the target video with the subject video by overlaying the version of the target video with the subject video; and facilitating comparison, in the video combination, between the version of the target video and the subject video by performing one or more of; in response to a viewpoint selection, changing a viewpoint of the target video and changing a viewpoint of the subject view; automatically identifying that a deviation between the expert in the target video and the subject in the subject video is above a threshold deviation amount, and in response, displaying a deviation indication or playing a sound; extrapolating motions of the subject to correspond to motions of the expert and, based on the extrapolating, providing an expected performance difference; identifying aspects of motions of the subject which would benefit from an equipment change and providing a suggestion of the equipment change;
orany combination thereof.
-
-
2. A method for creating a video combination, the method comprising:
-
obtaining a target video and a subject video; adjusting spatial aspects of the target video or of the subject video such that particular spatial aspects of the target video correspond to spatial aspects of the subject video; identifying synchronization points between the target video and the subject video, wherein an individual synchronization point identifies a temporal correspondence of motions or objects between the target video and the subject video; adjusting playback of one or more segments of the target video or of the subject video such that at least a first synchronization point in the target video is displayed at the same time as a corresponding synchronization point in the subject video during playback; and creating the video combination to facilitate comparison of the target video with the subject video by either; overlaying a version of the target video on a version of the subject video;
oroverlaying the version of the subject video on the version of the target video. - View Dependent Claims (3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13)
-
-
14. A system for creating a video combination, the system comprising:
-
one or more processors; and a memory storing instructions that, when executed by a computing system, cause the computing system to perform operations comprising; obtaining a target video and a subject video; identifying synchronization points between the target video and the subject video, wherein an individual synchronization point identifies a temporal correspondence of motions or objects between the target video and the subject video; adjusting playback of one or more segments of the target video or of the subject video such that at least a first synchronization point in the target video is displayed at the same time as a corresponding synchronization point in the subject video during playback; and creating the video combination to facilitate comparison of the target video with the subject video by causing concurrent display of a version of the target video with a version of the subject video. - View Dependent Claims (15, 16, 17, 18, 19, 20)
-
Specification