Conversation surveillance apparatus, control method, and computer readable medium

Patent metadata

Field	Value
Publication number	US-12456302-B2
Application number	US-202018014942-A
Country	US
Kind code	B2
Filing date	Jul 8, 2020
Priority date	Jul 8, 2020
Publication date	Oct 28, 2025
Grant date	Oct 28, 2025

Abstract

A conversation surveillance apparatus ( 2000 ) detects a plurality of persons (a human group ( 40 )) who have a conversation within a predetermined distance in a surveillance area ( 10 ) from video data ( 32 ). The conversation surveillance apparatus ( 2000 ) determines the duration of the conversation held by the human group ( 40 ) and puts the determined duration of the conversation into a storage device in association with identification information of the human group ( 40 ). The conversation surveillance apparatus ( 2000 ) determines whether the total duration of the conversations held by the human group ( 40 ) within a predetermined period of time is equal to or larger than a threshold using the information stored in the storage device.

First claim

What is claimed is:

1. A conversation surveillance apparatus comprising:
at least one memory storing instructions; and
at least one processor that is configured to execute the instructions to:
detect a plurality of persons who have a conversation within a predetermined distance in a surveillance area from video data;
perform a first determination to determine a duration of the conversation had by the plurality of persons;
put the determined duration of the conversation in association with identification information of the plurality of persons into a storage device; and
perform a second determination to determine whether or not a total duration of the conversations of the plurality of persons within a predetermined period of time is equal to or larger than a threshold using the information stored in the storage device,
wherein the first determination includes determining the duration of the conversation had by the plurality of persons using audio data generated by a microphone provided in a mobile robot that moves in the surveillance area, and
wherein the identification information of the plurality of persons is defined using sound features of a voice of each of the plurality of persons; and
based on the total duration being larger than the threshold, outputting a countermeasure.

2. The conversation surveillance apparatus according to claim 1 , wherein the at least one processor is configured to further to acquire the video data from each of a plurality of cameras that capture places different from each other in the surveillance area.

3. The conversation surveillance apparatus according to claim 1 , wherein the at least one processor is configured further to acquire the video data from a camera provided in a mobile robot that moves in the surveillance area.

4. The conversation surveillance apparatus according to claim 1 ,
wherein the first determination includes determining the duration of the conversation had by the plurality of persons using video data generated by the camera provided in a mobile robot that moves in the surveillance area, and
wherein the identification information of the plurality of persons is defined using image features of a face of each of the plurality of persons.

5. The conversation surveillance apparatus according to claim 1 , wherein the second determination includes: acquiring a plurality of the durations of the conversations associated with the identification information of the plurality of persons from the storage device; and determining whether or not a sum of the acquired durations of the conversations is equal to or larger than the threshold.

6. The conversation surveillance apparatus according to claim 1 , wherein the second determination includes: computing a sum of a duration of a conversation that the plurality of persons are currently having and one or more durations of the conversations that are stored in the storage device in association with the identification information of the plurality of persons; and determining whether or not the computed sum is equal to or larger than the threshold.

7. The conversation surveillance apparatus according to claim 1 ,
wherein the at least one processor is configured further to determine using video data, whether or not the plurality of persons are taking predetermined measures to prevent an infectious disease, and
wherein the second determination includes computing for the plurality of persons, the total duration of only the conversations that are had in a state in which the predetermined measures are not being taken.

8. A control method executed by a computer, the control method comprising:
detecting a plurality of persons who have a conversation within a predetermined distance in a surveillance area from video data;
performing a first determination to determine a duration of the conversation had by the plurality of persons;
putting the determined duration of the conversation in association with identification information of the plurality of persons into a storage device;
performing a second determination to determine whether or not a total duration of the conversations of the plurality of persons within a predetermined period of time is equal to or larger than a threshold using the information stored in the storage device; and
wherein the first determination includes determining the duration of the conversation had by the plurality of persons using audio data generated by a microphone provided in a mobile robot that moves in the surveillance area, and
wherein the identification information of the plurality of persons is defined using sound features of a voice of each of the plurality of persons; and
based on the total duration being larger than the threshold, outputting a countermeasure.

9. A non-transitory computer readable medium storing a program, the program causing a computer to execute:
detecting a plurality of persons who have a conversation within a predetermined distance in a surveillance area from video data;
performing a first determination to determine a duration of the conversation had by the plurality of persons;
putting the determined duration of the conversation in association with identification information of the plurality of persons into a storage device;
performing a second determination to determine whether or not a total duration of the conversations of the plurality of persons within a predetermined period of time is equal to or larger than a threshold using the information stored in the storage device; and
wherein the first determination includes determining the duration of the conversation had by the plurality of persons using audio data generated by a microphone provided in a mobile robot that moves in the surveillance area, and
wherein the identification information of the plurality of persons is defined using sound features of a voice of each of the plurality of persons; and
based on the total duration being larger than the threshold, outputting a countermeasure.

Assignees

• Nec Corp

Inventors

• Funada Junichi
• Mizumoto Hisashi

Classifications

• G10L25/57

  for processing of video signals · 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

• G10L25/51

  for comparison or discrimination · CPC title

• G16H10/60

  for patient-specific data, e.g. for electronic patient records · CPC title

• G06V20/53 Primary

  Recognition of crowd images, e.g. recognition of crowd congestion · CPC title