System and method for sound based surveillance

Patent metadata

Field	Value
Publication number	US-10163313-B2
Application number	US-201715457747-A
Country	US
Kind code	B2
Filing date	Mar 13, 2017
Priority date	Mar 14, 2016
Publication date	Dec 25, 2018
Grant date	Dec 25, 2018

Abstract

A system and method to detect an event by analyzing sound signals received from a plurality of configured sensors. The sensors can be fixed or mobile and sensor activity is tracked in a sensor map. The frame analyzer of the system compares sound signals received from the sensors and applies knowledge data to determine if any deviation observed can be determined to be an uncharacteristic event. A rule data set comprising priority data, type of event, location is applied to the output of the frame analyzer to determine if the uncharacteristic sound observed is an event. On detection of an event, alerts are issued to appropriate authority. Further, sound frame and contextual data associated with the event are stored to serve as continuous learning for the system.

First claim

What is claimed is:

1. A system to detect events by monitoring sound signals of an environment, wherein the system comprises:
a processor; and
a memory coupled to the processor, wherein the memory has a plurality of modules stored therein that are executable by the processor, the plurality of modules comprising:
a receiver to receive input signals from a configured sensor network, wherein the input signals comprises a combination of sound signals and location data of the environment;
a frame analyzer to create and compare sound frames for predefined time intervals from the input signals received by the receiver;
a context builder to associate contextual information and apply at least one rule from a rule builder to the sound frames to determine the context, wherein the rule builder comprises a configured rule data having rule elements of location, time, sound attributes and a priority;
an alert generator to flag an event, generate alerts and communicate with authorities regarding the event;
an action logger to record the at least one sound associated with the event and contextual information associated with the event in the central server; and
a central server to store at least one sound frame and contextual information of the event, for continual learning.

2. The system as claimed in claim 1 , wherein the configured sensor network comprises a network of fixed and mobile sensors, wherein the mobile sensors further comprise wearable devices affixed to an object being monitored in the environment.

3. The system as claimed in claim 1 , wherein the receiver on receiving input signals from the configured sensor network, creates a sensor map to indicate sound activity of a cluster of sensors in monitored zone of the environment.

4. The system as claimed in claim 1 , wherein the frame analyzer compares adjacent set of sound frames (F 1 , F 2 , . . . FN) comprising knowledge data (K) to determine deviation in sound signals and time (t) of occurrence.

5. The system as claimed in claim 1 , wherein the configured rule data can be modified or re-configured based on observed sound signals.

6. The system as claimed in claim 1 , wherein the alert generator signals an alert on the sensor map generated by the receiver.

7. A computer-implemented method to detect events by monitoring sound signals of an environment, wherein the method comprises:
receiving, by a receiver, at least one input signal from a configured sensor network;
creating and analysing sound frames, by a frame analyzer for the at least one input signal received by the receiver, wherein creating and analysing sound frames comprises generating a set of sound frames and comparing adjacent set of sound frames with knowledge data set over time (t) to determine an event;
associating a contextual data set, by a context builder to the sound frames to determine an event;
generating at least one alert, by an alert generator to flag an event;
recording details of an event, by an event logger to record time, place, type and priority of an event for continuous learning; and
storing at least one sound frame and associated contextual data, by a central server for continual learning.

8. The computer implemented method as claimed in claim 7 , wherein the at least one input signals comprises a combination of sound signals and location data.

9. The computer implemented method as claimed in claim 7 , wherein the receiving of input signals by the receiver further comprises creation of a sensor map to indicate monitored zone of the environment indicating sound activity of a cluster of networked sensors.

10. The computer implemented method as claimed claim 7 , wherein associating of a contextual data set comprises superimposing contextual data set, wherein the contextual data set further comprises a schedule, time of the day, priority, sound activity from sensor map and application of at least one rule to the sound frames being compared.

11. The computer implemented method, as claimed in claim 10 , wherein the application of at least one rule further comprises creating of a rule data, wherein the rule data further comprises at least one of schedule, location, time of the day, sound attributes and assigning of a priority.

12. The computer implemented method as claimed in claim 7 , wherein, generating an alert comprises indicating an alert on the sensor map for a cluster of sensors and communicating to authorities via communication means.

13. A computer program product comprising a non-transitory computer readable medium having a computer readable program embodied therein, wherein the computer readable program, when executed on a computing device causes the computing device to:
receive at least one input signal from a configured sensor network;
create and analyse sound frames for the at least one input signal received, wherein creating and analysing sound frames comprises generating a set of sound frames and comparing adjacent set of sound frames with knowledge data set over time (t) to determine an event;
associate a contextual data set to determine an event;
generate at least one alert to flag an event;
record details of an event pertaining to time, place, type and priority of an event for continuous learning; and
store at least one sound frame by a central server for continual learning.

Assignees

• Tata Consultancy Services Ltd

Inventors

• Subramanian Sivakumar
• Kopparapu Sunil Kumar

Classifications

• G08B21/0438

  Sensor means for detecting · CPC title

• G08B3/10

  using electric transmission; using electromagnetic transmission · CPC title

• G08B13/1672 Primary

  using sonic detecting means, e.g. a microphone operating in the audio frequency range · CPC title

• G08B21/0423

  detecting deviation from an expected pattern of behaviour or schedule · CPC title

• G08B21/02

  Alarms for ensuring the safety of persons · CPC title