Computing system with video-tagging anomaly detection feature
View Patent ↗In one aspect, an example method includes (i) receiving, by a computing system, first data indicating a first extent of temporal portions of video content that have a particular characteristic; (ii) receiving, by the computing system, second data indicating a second extent of temporal portions of the video content that have the particular characteristic; (iii) determining, by the computing system, that the received first data lacks a threshold extent of similarity with the received second data; and (iv) responsive to determining that the received first data lacks the threshold extent of similarity with the received second data, performing, by the computing system, an action.
1. A method comprising:
receiving, by a computing system, first tagging data indicating a first extent of temporal portions of video content that are suitable for having a digital video-effect (DVE) of a particular DVE type applied thereto, wherein the first tagging data is generated by a first video-broadcast system (VBS) via a first tagging station based on first user input received via a first user terminal;
receiving, by the computing system, second tagging data indicating a second extent of temporal portions of the video content that are suitable for having a DVE of the particular DVE type applied thereto, wherein the second tagging data is generated by a second video-broadcast system (VBS) via a second tagging station based on second user input received via a second user terminal;
determining, by the computing system, that the received first tagging data lacks a threshold extent of similarity with the received second tagging data;
responsive to determining that the received first tagging data lacks the threshold extent of similarity with the received second tagging data, performing, by the computing system, an action, wherein performing the action comprises using the received first tagging data and the received second tagging data to generate a best guess estimate of tagging data for the video content;
using by the computing system, the generated best guess estimated tagging data to selectively apply a DVE of the particular DVE type to a temporal portion of the video content, thereby modifying the video content; and
transmitting, by the computing, the modified video content to an end-user device.
2. The method of claim 1 , wherein determining that the received first tagging data lacks the threshold extent of similarity with the received second tagging data comprises determining that there is a mismatch, by more than a threshold amount, in time markers for a frame of a temporal portion of the video content.
3. The method of claim 1 , wherein the first VBS is connected with the second VBS via a wide-area network, and wherein receiving the second tagging data comprises receiving the second tagging data via the wide-area network.
4. A non-transitory computer-readable medium having stored thereon program instructions that upon execution by a processor, cause performance of a set of acts comprising:
receiving, by a computing system, first tagging data indicating a first extent of temporal portions of a video content that are suitable for having a digital video-effect (DVE) of a particular DVE type applied thereto, wherein the first tagging data is generated by a first video-broadcast system (VBS) via a first tagging station based on first user input received via a first user terminal;
receiving, by the computing system, second tagging data indicating a second extent of temporal portions of the video content that are suitable for having a DVE of the particular DVE type applied thereto, wherein the second tagging data is generated by a second video-broadcast system (VBS) via a second tagging station based on second user input received via a second user terminal;
determining, by the computing system, that the received first tagging data lacks a threshold extent of similarity with the received second tagging data;
responsive to determining that the received first tagging data lacks the threshold extent of similarity with the received second tagging data, performing, by the computing system, an action, wherein performing the action composes using the received first tagging data and the received second tagging data to generate a best guess estimate of tagging data for the video content;
using, by the computing system, the generated best guess estimated tagging data to selectively apply a DVE of the particular DVE type to a temporal portion of the video content, thereby modifying the video content, and
transmitting, by the computing, the modified video content to an end-user device.
5. The non-transitory computer-readable medium of claim 4 , wherein determining that the received first tagging data lacks the threshold extent of similarity with the received second tagging data comprises determining that there is a mismatch, by more than a threshold amount, in time markers for a frame of a temporal portion of the video content.
6. The non-transitory computer-readable medium of claim 4 ,
wherein the first VBS is connected with the second VBS via a wide-area network, and wherein receiving the second tagging data comprises receiving the second tagging data via the wide-area network.
7. A computing system configured for performing a set of acts comprising:
receiving, by the computing system, first tagging data indicating a first extent of temporal portions of video content that are suitable for having a digital video-effect (DVE) of a particular DVE type applied thereto, wherein the first tagging data is generated by a first video-broadcast system (VBS) via a first tagging station based on first user input received via a first user terminal;
receiving, by the computing system, second tagging data indicating a second extent of temporal portions of the video content that are suitable for having a DVE of the particular DVE type applied thereto, wherein the second tagging data is generated by a second video-broadcast system (VBS) via a second tagging station based on second user input received via a second user terminal;
determining, by the computing system, that the received first tagging data lacks a threshold extent of similarity with the received second tagging data;
responsive to determining that the received first tagging data lacks the threshold extent of similarity with the received second tagging data, performing, by the computing system, an action, wherein performing the action comprises using the received first tagging data and the received second tagging data to generate a best guess estimate of tagging data for the video content;
using, by the computing system, the generated best guess estimated tagging data to selectively apply a DVE of the particular DVE type to a temporal portion of the video, content, thereby modifying the video content; and
transmitting, by the computing, the modified video content to an end-user device.
8. The computing system of claim 7 , wherein determining that the received first tagging data lacks the threshold extent of similarity with the received second tagging data comprises determining that there is a mismatch, by more than a threshold amount, in time markers for a frame of a temporal portion of the video content.
9. The computing system of claim 7 , wherein the first VBS is connected with the second VBS via a wide-area network, and wherein receiving the second tagging data comprises receiving the second tagging data via the wide-area network.