Live video anomaly detection

Patent metadata

Field	Value
Publication number	US-11044206-B2
Application number	US-201815957958-A
Country	US
Kind code	B2
Filing date	Apr 20, 2018
Priority date	Apr 20, 2018
Publication date	Jun 22, 2021
Grant date	Jun 22, 2021

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.

First claim

What is claimed is:

1. A computer-implemented method for live video anomaly detection, comprising:
detecting live stream data recorded using an image capturing device of a user device;
determining an activity from the live stream data;
receiving contextual data associated with the live stream data, wherein the contextual data comprises location data, crowd sourced data, historical data, and time data;
automatically redirecting the live stream data recorded using the image capturing device of the user device from a first channel, based on detecting an anomaly in the activity and the contextual data, to a different unrelated external channel and simultaneously maintaining the live stream data on the first channel; and
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 to the user device recording the live stream data to redirect the live stream data based on the contextual data and comparing the activity to the tolerance level, wherein the contextual data further comprises facial expression data.

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 to 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 computer-implemented 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 , wherein the tolerance level is based on social media information for a user.

7. The computer-implemented 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.

8. 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 live stream data recorded using an image capturing device of a user device;
determining an activity from the live stream data;
receiving contextual data associated with the live stream data, wherein the contextual data includes location data, crowd sourced data, historical data, and time data; and
automatically redirecting the live stream data recorded using the image capturing device of the user device from a first channel, based on detecting an anomaly in the activity and the contextual data, to a different unrelated external channel and simultaneously maintaining the live stream data on the first channel; and
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 to the user device recording the live stream data to redirect the live stream data based on the contextual data and comparing the activity to the tolerance level, wherein the tolerance level is based on social media information for a user.

9. The system of claim 8 , 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.

10. The system of claim 8 , wherein a previously recorded portion of the live stream data is included in the redirection.

11. The system of claim 8 , further comprises selecting a redirection channel based at least in part on the activity.

12. 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 live stream data recorded using an image capturing device of a user device;
determining an activity from the live stream data;
receiving contextual data associated with the live stream data, wherein the contextual data includes location data, crowd sourced data, historical data, and time data;
automatically redirecting the live stream data recorded using the image capturing device of the user device from a first channel, based on detecting an anomaly in the activity and the contextual data, to a different unrelated external channel and simultaneously maintaining the live stream data on the first channel; and
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 to the user device recording the live stream data to redirect the live stream data based on the contextual data and comparing the activity to the tolerance level, wherein the tolerance level is based on a social media information for the user.

13. The computer program product of claim 12 , 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.

14. The computer program product of claim 12 , wherein a previously recorded portion of the live stream data is included in the redirection.

Assignees

• IBM

Inventors

• Ward Brett
• Delaney Mark
• Chakra Al
• Grant Robert H

Classifications

• H04L67/306 Primary

  User profiles · CPC title

• H04L67/63

  Routing a service request depending on the request content or context · CPC title

• H04L67/535

  Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34) · CPC title

• G06V20/41

  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 title

• G06V20/52

  Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) · CPC title