Generating instance-based summary videos for fixed-field videos using machine-learned classifiers
A media detection system receives a video corresponding to a fixed field of view. The media detection system may receive user input indicating one or more object types to identify or a subset of the video within which to identify objects. The media detection system applies one or more machine-learned classifiers to frames of the video and creates a summary video that includes the background of the video and identified instances for simultaneous playback within the fixed field of view. The media detection system may also identify instances of objects in a live video stream and use the identified instances to respond to user questions. The media detection system applies a language model to questions to identify the subject matter of the questions, identifies content within the live video stream associated with the subject matter, and uses the identified content to respond to the user's question.
1 . A computer-implemented method, the method comprising:
receiving a video corresponding to a fixed field of view such that a background of the video is consistent for an above-threshold portion of the video;
applying one or more machine-learned classifiers to frames of the video, each classifier configured to identify instances of an object type associated with the classifier as each instance of the object type moves within the fixed field of view of the video;
receiving a selection of the identified instances of one or more object types; and
generating a summary video comprising the background of the video within the fixed field of view, the selected instances of the one or more object types for simultaneous playback within the fixed field of view, and, for each selected instance of the selected instances of the one or more object types, a label displayed adjacent to the selected instance identifying 1) the object type associated with the selected instance, and 2) a timestamp identifying when the selected instance first appeared in the received video, wherein each label is configured to move within the summary video in conjunction with the associated selected instance.
2 . The computer-implemented method of claim 1 , wherein each instance of the object type is associated with a first set of timestamps, the first set of timestamps corresponding to times at which the instance appears in the video.
3 . The computer-implemented method of claim 2 , wherein each instance of the object type is associated with a second set of timestamps, the second set of timestamps corresponding to times at which the instance appears in the summary video, and wherein simultaneous playback comprises playing movement of each instance such that the first set of timestamps maps to the second set of timestamps.
4 . The computer-implemented method of claim 3 , wherein simultaneous playback comprises playing movement of each instance at a same time, such that the second set of timestamps are the same for each instance in the summary video.
5 . The computer-implemented method of claim 1 , wherein receiving the selection of instances of one or more object types comprises receiving the selection from a user.
6 . The computer-implemented method of claim 1 , wherein receiving the selection of instances of one or more object types comprises receiving the selection of all instances of the one or more object types.
7 . The computer-implemented method of claim 1 , wherein receiving the selection of instances of one or more object types comprises receiving the selection of less than all instances of the one or more object types.
8 . The computer-implemented method of claim 1 , wherein the label uniquely identifies each instance of the object type.
9 . A non-transitory computer-readable storage medium storing executable computer instructions that when executed by a hardware processor are configured to cause the hardware processor to perform steps comprising:
receiving a video corresponding to a fixed field of view such that a background of the video is consistent for an above-threshold portion of the video;
applying one or more machine-learned classifiers to frames of the video, each classifier configured to identify instances of an object type associated with the classifier as each instance of the object type moves within the fixed field of view of the video;
receiving a selection of the identified instances of one or more object types; and
generating a summary video comprising the background of the video within the fixed field of view, the selected instances of the one or more object types for simultaneous playback within the fixed field of view, and, for each selected instance of the selected instances of the one or more object types, a label displayed adjacent to the selected instance identifying 1) the object type associated with the selected instance, and 2) a timestamp identifying when the selected instance first appeared in the received video, wherein each label is configured to move within the summary video in conjunction with the associated selected instance.
10 . The non-transitory computer-readable storage medium of claim 9 , wherein each instance of the object type is associated with a first set of timestamps, the first set of timestamps corresponding to times at which the instance appears in the video.
11 . The non-transitory computer-readable storage medium of claim 10 , wherein each instance of the object type is associated with a second set of timestamps, the second set of timestamps corresponding to times at which the instance appears in the summary video, and wherein simultaneous playback comprises playing movement of each instance such that the first set of timestamps maps to the second set of timestamps.
12 . The non-transitory computer-readable storage medium of claim 11 , wherein simultaneous playback comprises playing movement of each instance at a same time, such that the second set of timestamps are the same for each instance in the summary video.
13 . The non-transitory computer-readable storage medium of claim 9 , wherein instructions for receiving the selection of instances of one or more object types comprise instructions for receiving the selection from a user.
14 . The non-transitory computer-readable storage medium of claim 9 , wherein instructions for receiving the selection of instances of one or more object types comprise instructions for receiving the selection of all instances of the one or more object types.
15 . The non-transitory computer-readable storage medium of claim 9 , wherein instructions for receiving the selection of instances of one or more object types comprise instructions for receiving the selection of less than all instances of the one or more object types.
16 . The non-transitory computer-readable storage medium of claim 9 , wherein the label uniquely identifies each instance of the object type.
17 . A system, comprising:
a computer processor; and
a non-transitory memory storing executable computer instructions that when executed by the computer processor are configured to cause the computer processor to perform steps comprising:
receiving a video corresponding to a fixed field of view such that a background of the video is consistent for an above-threshold portion of the video;
applying one or more machine-learned classifiers to frames of the video, each classifier configured to identify instances of an object type associated with the classifier as each instance of the object type moves within the fixed field of view of the video;
receiving a selection of the identified instances of one or more object types; and
generating a summary video comprising the background of the video within the fixed field of view, the selected instances of the one or more object types for simultaneous playback within the fixed field of view, and, for each selected instance of the selected instances of the one or more object types, a label displayed adjacent to the selected instance identifying 1) the object type associated with the selected instance, and 2) a timestamp identifying when the selected instance first appeared in the received video, wherein each label is configured to move within the summary video in conjunction with the associated selected instance.
18 . The system of claim 17 , wherein each instance of the object type is associated with a first set of timestamps, the first set of timestamps corresponding to times at which the instance appears in the video.
19 . The system of claim 18 , wherein each instance of the object type is associated with a second set of timestamps, the second set of timestamps corresponding to times at which the instance appears in the summary video, and wherein simultaneous playback comprises playing movement of each instance such that the first set of timestamps maps to the second set of timestamps.
20 . The system of claim 19 , wherein simultaneous playback comprises playing movement of each instance at the same time, such that the second set of timestamps are the same for each instance in the summary video.