Using user-triggered video recordings and/or user-exported video recordings as a basis to identify future videos of interest
Video analytics may be performed on user-triggered video recording to generate metadata that describes what was found in the user-triggered video recording. A subsequent video stream may be analyzed, thereby generating metadata associated with the subsequent video stream. The metadata associated with the subsequent video stream may be compared with the metadata associated with the user-triggered recording. When the metadata associated with the subsequent video stream matches the metadata associated one or more of the user-triggered video recordings in accordance with one or more matching criteria, an inquiry is outputted to an operator soliciting whether a user-triggered video recording should be initiated for the subsequent video stream. The method includes receiving from the operator a response to the inquiry indicating whether to initiate a user-triggered video recording of the subsequent video stream, and if so, initiating a user-triggered video recording of the subsequent video stream.
1 . A method for using user-triggered video recordings to find subsequent video streams of interest, the method comprising:
for at least some of the user-triggered video recordings:
performing video analytics on the corresponding user-triggered video recording to find one or more events, objects and/or characteristics within the corresponding user-triggered video recording;
generating metadata that corresponds to the one or more events, objects and/or characteristics found within the corresponding user-triggered video recording, including a time of day that the corresponding event, object and/or characteristic was captured in the respective video recording;
associating the metadata with the corresponding user-triggered video recording;
receiving a subsequent video stream, wherein for the subsequent video stream:
performing video analytics on the subsequent video stream to find one or more events, objects and/or characteristics within the subsequent video stream;
generating metadata that describes the one or more events, objects and/or characteristics found within the subsequent video stream, including a time of day that the corresponding event, object and/or characteristic was captured in the subsequent video stream;
compare the metadata associated with the subsequent video stream to the metadata associated one or more of the user-triggered video recordings;
when the metadata associated with the subsequent video stream matches the metadata associated one or more of the user-triggered video recordings in accordance with one or more matching criteria, outputting an inquiry to an operator soliciting from the operator whether a user-triggered video recording should be initiated for the subsequent video stream, wherein the one or more matching criteria comprise a matching time of day that the respective one or more events, objects and/or characteristics were captured; and
receiving from the operator a response to the inquiry indicating whether to initiate a user-triggered video recording of the subsequent video stream, and if so, initiating a user-triggered video recording of the subsequent video stream, and if not, not initiating a user-triggered video recording of the subsequent video stream.
2 . The method of claim 1 , wherein the subsequent video stream comprises a live-video stream.
3 . The method of claim 1 , wherein the one or more events, objects and/or characteristics comprise one or more of:
one or more facial characteristics of a detected person suitable for facial recognition;
one or more clothing characteristics of a detected person;
a gender;
an estimated age;
an overall number of people;
a crowd density;
an interaction between two or more inanimate objects;
an interaction between a person and an inanimate object;
a presence of smoke;
a presence of flame;
a noise;
a noise level;
a scream; and
a video characteristic of being blurry, at least partially blocked, too dark, too light, or not stable.
4 . The method of claim 3 , wherein the one or more matching criteria comprise one or more matching events, objects and/or characteristics.
5 . The method of claim 3 , wherein the one or more matching criteria comprise a combination of two or more matching events, objects and/or characteristics.
6 . The method of claim 1 , wherein one or more of the matching criteria are learned over time using machine learning.
7 . The method of claim 1 , wherein the metadata associated with the subsequent video stream is compared to the metadata associated one or more of the user-triggered video recordings using a crawler.
8 . The method of claim 1 , wherein the one or more events, objects and/or characteristics comprise an overall number of people.
9 . The method of claim 1 , wherein the one or more events, objects and/or characteristics comprise an interaction between a person and an inanimate object.
10 . The method of claim 1 , wherein the one or more events, objects and/or characteristics comprise a presence of smoke or a presence of flame.
11 . The method of claim 1 , wherein the one or more events, objects and/or characteristics comprise a noise level.
12 . The method of claim 1 , wherein the one or more events, objects and/or characteristics comprise a video characteristic of being blurry, at least partially blocked, too dark, too light, or not stable.
13 . A method for using stored video recordings, at least some of the stored video recordings including user-triggered video recordings and/or user-exported video recordings, to find other videos of interest, the method comprising:
for each of the user-triggered video recordings and/or user-exported video recordings:
performing video analytics on the corresponding user-triggered video recording and/or the corresponding user-exported video recording to find one or more events, objects and/or characteristics within the corresponding user-triggered video recording and/or the corresponding user-exported video recording;
generating metadata that describes the one or more found events, objects and/or characteristics, including a time of day that the corresponding event, object and/or characteristic was captured in the respective video recording;
associating the metadata with the corresponding user-triggered video recording and/or the corresponding user-exported video recording;
receiving a subsequent video stream, wherein for the subsequent video stream:
performing video analytics on the subsequent video stream to find one or more events, objects and/or characteristics within the subsequent video stream;
generating metadata that describes the one or more events, objects and/or characteristics found within the subsequent video stream, including a time of day that the corresponding event, object and/or characteristic was captured in the subsequent video stream;
compare the metadata associated with the subsequent video stream to the metadata associated one or more of the user-triggered video recordings and/or one or more user-exported video recordings;
when the metadata associated with the subsequent video stream matches the metadata associated one or more of the user-triggered video recordings and/or one or more user-exported video recordings in accordance with one or more matching criteria, outputting an inquiry to an operator soliciting from the operator whether a user-triggered video recording should be initiated for the subsequent video stream, wherein the one or more matching criteria include a matching time of day that the respective one or more events, objects and/or characteristics were captured; and
receiving from the operator a response to the inquiry indicating whether to initiate a user-triggered video recording of the subsequent video stream, and if so, initiating a user-triggered video recording of the subsequent video stream, and if not, not initiating a user-triggered video recording of the subsequent video stream.
14 . The method of claim 13 , wherein at least one of the other videos comprise a live-streaming video.
15 . The method of claim 13 , wherein at least one of the other videos comprise a previously recorded video.
16 . The method of claim 13 , further comprising displaying at least part of the videos of interest for review by an operator.
17 . The method of claim 13 , wherein performing video analytics comprises identifying one or more objects and classifying one or more of the identified objects into one of a plurality of object classifications.
18 . A method for using user-triggered video recordings to find subsequent video streams of interest, the method comprising:
for at least some of the user-triggered video recordings:
performing video analytics on the corresponding user-triggered video recording to find one or more events, objects and/or characteristics within the corresponding user-triggered video recording;
generating metadata that corresponds to the one or more events, objects and/or characteristics found within the corresponding user-triggered video recording;
associating the metadata with the corresponding user-triggered video recording;
receiving a subsequent video stream, wherein for the subsequent video stream:
performing video analytics on the subsequent video stream to find one or more events, objects and/or characteristics within the subsequent video stream;
generating metadata that describes the one or more events, objects and/or characteristics found within the subsequent video stream;
compare the metadata associated with the subsequent video stream to the metadata associated one or more of the user-triggered video recordings;
when the metadata associated with the subsequent video stream matches the metadata associated one or more of the user-triggered video recordings in accordance with one or more matching criteria, outputting an inquiry to an operator soliciting from the operator whether a user-triggered video recording should be initiated for the subsequent video stream, wherein the one or more matching criteria comprise a crowd density; and
receiving from the operator a response to the inquiry indicating whether to initiate a user-triggered video recording of the subsequent video stream, and if so, initiating a user-triggered video recording of the subsequent video stream, and if not, not initiating a user-triggered video recording of the subsequent video stream.