Emergency alert message detection on electronic device based on audio-video information

Patent metadata

Field	Value
Publication number	US-12034524-B2
Application number	US-202217735725-A
Country	US
Kind code	B2
Filing date	May 3, 2022
Priority date	May 3, 2022
Publication date	Jul 9, 2024
Grant date	Jul 9, 2024

Abstract

An electronic device and method for emergency alert message detection based on audio-video information is disclosed. The electronic device receives first media content received over a first broadcast channel. The electronic device renders second media content, which is different from the first media content. The electronic device further detects, from the received first media content, a set of objects associated with a geo-location corresponding to the electronic device. The set of objects corresponds to an emergency at the geo-location. The electronic device further detects an emergency alert audio in the received first media content. The electronic device further extracts an emergency alert message received over a second broadcast channel associated with the geo-location based on the detected set of objects and the emergency alert audio in the received first media content. The electronic device further renders an emergency alert signal associated with the emergency alert message.

First claim

What is claimed is:

1. An electronic device, comprising:
circuitry configured to:
receive first media content over a first broadcast channel;
control a display device associated with the electronic device to render second media content, wherein the second media content is different from the first media content;
detect, from the received first media content, a set of objects associated with a geo-location corresponding to the electronic device, wherein the set of objects corresponds to an emergency at the geo-location;
detect an emergency alert audio in the received first media content;
determine a static display portion in at least one image frame of the received first media content based on the detected set of objects, wherein the static display portion corresponds to a portion of the at least one image frame in which a rate of change of pixel location of the detected set of objects is less than a threshold value;
extract an emergency alert message received over a second broadcast channel associated with the geo-location, based on the detected set of objects, the determined static display portion, and the detected emergency alert audio in the received first media content; and
control an output of an emergency alert signal associated with the extracted emergency alert message.

2. The electronic device according to claim 1 , wherein the circuitry is further configured to:
determine a discontinuity in the received first media content based on the detected set of objects, wherein the extraction of the emergency alert message is further based on the determined discontinuity.

3. The electronic device according to claim 1 , wherein the circuitry is further configured to:
apply a machine learning model on a set of audio samples related to the emergency alert audio in the received first media content; and
determine a discontinuity in the received first media content based on an application of the machine learning model on the set of audio samples, wherein the extraction of the emergency alert message is further based on the determined discontinuity.

4. The electronic device according to claim 1 , wherein the circuitry is further configured to control the display device to render, in a single-view mode, the emergency alert signal that is associated with the emergency alert message received from the second broadcast channel.

5. The electronic device according to claim 1 , wherein the circuitry is further configured to:
control the electronic device to switch from the first broadcast channel to the second broadcast channel, for the extraction of the emergency alert message; and
control the display device to render the emergency alert signal from the second broadcast channel along with the second media content in a composite-view mode.

6. The electronic device according to claim 5 , wherein in the composite-view mode, the circuitry is further configured to output audio content associated with the emergency alert signal from the second broadcast channel and concurrently output video content associated with the second media content.

7. The electronic device according to claim 5 , wherein in the composite-view mode, the circuitry is further configured to output at least one of text content or video content associated with the emergency alert signal from the second broadcast channel and concurrently output audio content associated with the second media content.

8. The electronic device according to claim 1 , wherein the first media content corresponds to at least one of over-the-air (OTA) media content, a television (TV) broadcast content, a satellite TV content, or a cable TV content.

9. The electronic device according to claim 1 , wherein the second media content corresponds to at least one of over-the-top (OTT) media content, streaming media content, media content stored on the electronic device, or media content received from an Internet.

10. The electronic device according to claim 1 , wherein the circuitry is further configured to:
apply a machine learning model on a set of image frames in the received first media content, wherein the machine learning model is trained to detect the set of objects, related to the emergency, from the first media content; and
detect the set of objects from the received first media content based on an application of the machine learning model on the set of image frames in the received first media content.

11. The electronic device according to claim 1 , wherein the circuitry is further configured to:
apply a machine learning model on a set of audio samples in the received first media content to determine textual content related to the set of audio samples, wherein the machine learning model is trained to convert audio samples to corresponding textual information;
determine a context associated with the determined textual content based on the geo-location associated with the electronic device; and
detect the set of objects from the received first media content further based on the determined context.

12. The electronic device according to claim 1 , wherein the circuitry is further configured to:
determine the geo-location corresponding to the electronic device based on at least one of a user input or a location sensor associated with the electronic device; and
determine, based on the determined geo-location, the second broadcast channel from a plurality of broadcast channels received by the electronic device.

13. The electronic device according to claim 1 , wherein the circuitry is further configured to:
monitor the second broadcast channel to detect the emergency alert audio, based on the electronic device being in an idle mode; and
control the output of the emergency alert signal associated with the extracted emergency alert message based on the monitored second broadcast channel.

14. A method, comprising:
in an electronic device:
receiving first media content over a first broadcast channel;
controlling a display device associated with the electronic device to render second media content, wherein the second media content is different from the first media content;
detecting, from the received first media content, a set of objects associated with a geo-location corresponding to the electronic device, wherein the set of objects correspond to an emergency at the geo-location;
detecting an emergency alert audio in the received first media content;
determining a static display portion in at least one image frame of the received first media content based on the detected set of objects, wherein the static display portion corresponds to a portion of the at least one image frame in which a rate of change of pixel location of the detected set of objects is less than a threshold value;
extracting an emergency alert message received over a second broadcast channel associated with the geo-location, based on the detected set of objects, and the determined static display portion, and the detected emergency alert audio in the received first media content; and
controlling an output of an emergency alert signal associated with the extracted emergency alert message.

15. The method according to claim 14 , further comprising controlling the display device, in a single-view mode, to render the emergency alert signal that is associated with the emergency alert message received from the second broadcast channel.

16. The method according to claim 14 , further comprising:
controlling the electronic device to switch from the first broadcast channel to the second broadcast channel, for the extraction of the emergency alert message; and
controlling the display de

Assignees

• Sony Group Corp

Inventors

• Shintani Peter
• Goldberg Adam
• Pineda Loren

Classifications

• H04N21/814

  comprising emergency warnings (arrangements specially adapted for emergency or urgency in broadcast systems H04H20/59; arrangements for providing alarms, notifications, alerts to substation in data switching networks H04L12/1895) · CPC title

• H04H60/70

  using geographical information, e.g. maps, charts or atlases · CPC title

• G06N20/00

  Machine learning · CPC title

• H04H60/51

  of receiving stations · CPC title

• H04W4/02

  Services making use of location information · CPC title