LIVE VIDEO ANOMALY DETECTION

• US 20190327183A1
• Filed: 04/20/2018
• Published: 10/24/2019
• Est. Priority Date: 04/20/2018
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Ward, Brett, Delaney, Mark, Chakra, Al, Grant, Robert H.
• Granted Patent: US 11,044,206 B2
• Time in Patent Office: Days
• CPC Class Codes: G06V 20/41 Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items segmenting video sequences G06V20/49
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: H04L 47/726 Reserving resources in multiple paths to be used simultaneously by balancing the load H04L47/125
• CPC Class Codes: H04L 47/80 Actions related to the user profile or the type of traffic
• CPC Class Codes: H04L 47/822 Collecting or measuring resource availability data
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04L 67/63 Routing a service request depending on the request content or context

Abstract

Embodiments of the invention include computer-implemented methods, computer program products and systems for live video anomaly detection. The embodiments include detecting live stream data, determining an activity from the live stream data, and receiving contextual data associated with the live stream data. The embodiments also include prompting a user to redirect the live stream data from a first channel based on the activity and the contextual data, and redirecting, responsive to the prompt, the live stream data to a different channel and simultaneously maintaining the live stream data on the first channel.

Claims

1. A computer-implemented method for live video anomaly detection, comprising:

detecting live stream data;

determining an activity from the live stream data;

receiving contextual data associated with the live stream data; and

redirecting the live stream data from a first channel, based on the activity and the contextual data, to a different channel and simultaneously maintaining the live stream data on the first channel.

2. The computer-implemented method of claim 1, further comprises prompting a user to redirect the live stream data from the first channel, wherein the prompt includes an option to record the live stream data, an option to redirect the live stream data a different channel, or an option to ignore the redirection.

3. The computer-implemented method of claim 1, wherein a previously recorded portion of the live stream data is included in the redirection.

4. The computer-implemented method of claim 1, further comprises selecting a redirection channel based at least in part on the activity.

5. The method of claim 4, wherein the redirection channel is based on a frequent contact list of a user device.

6. The computer-implemented method of claim 1, further comprises determining a tolerance level for the activity based at least in part on a user profile for a user recording the live stream data and providing a prompt based on comparing the activity to the tolerance level.

7. The computer-implemented method of claim 6, wherein the tolerance level is based on social media information for a user.

8. The computer-implemented method of claim 1, wherein the contextual data includes location data, crowd sourced data, historical data, and time data.

9. The method of claim 1, wherein additional contextual information is collected from devices external to a recording device collecting the live stream data including performing facial recognition of the live stream data.

10. A system for live video anomaly detection, comprising:

one or more processors; and

at least one memory, the memory including instructions that, upon execution by at least one of the one or more processors, cause the system to perform a method for analyzing and prioritizing incoming user messages, the method comprising;

detecting, detection unit, live stream data;

determining an activity from the live stream data;

receiving contextual data associated with the live stream data; and

redirecting the live stream data from a first channel, based on the activity and the contextual data, to a different channel and simultaneously maintaining the live stream data on the first channel.

11. The system of claim 10, further comprises prompting a user to redirect the live stream data from the first channel, wherein the prompt includes an option to record the live stream data, an option to redirect the live stream data a different channel, or an option to ignore the redirection.

12. The system of claim 10, wherein a previously recorded portion of the live stream data is included in the redirection.

13. The system of claim 10, further comprises selecting a redirection channel based at least in part on the activity.

14. The system of claim 10, further comprises determining a tolerance level for an activity based at least in part on a user profile for a user recording the live stream data and providing a prompt based on comparing the activity to the tolerance level.

15. The system of claim 14, wherein the contextual data includes location data, crowd sourced data, historical data, and time data, and wherein the tolerance level is based on social media information for a user.

16. A computer program product for live video anomaly detection, the computer program product comprising:

a computer readable storage medium having stored thereon program instructions executable by a processor to cause the processor to;

detecting, detection unit, live stream data;

determining an activity from the live stream data;

receiving contextual data associated with the live stream data; and

redirecting the live stream data from a first channel, based on the activity and the contextual data, to a different channel and simultaneously maintaining the live stream data on the first channel.

17. The computer program product of claim 16, further comprises prompting a user to redirect the live stream data from the first channel, wherein the prompt includes an option to record the live stream data, an option to redirect the live stream data to a different channel, or an option to ignore the redirection.

18. The computer program product of claim 16, wherein a previously recorded portion of the live stream data is included in the redirection.

19. The computer program product of claim 16, wherein the instructions are further executable by the processor to cause the processor to determine a tolerance level for an activity based at least in part on a user profile for a user recording the live stream data and providing a prompt based on comparing the activity to the tolerance level.

20. The computer program product of claim 19, wherein the contextual data includes location data, crowd sourced data, historical data, and time data, and wherein the tolerance level is based on a social media information for the user.