CN109151393A - A kind of sound fixation and recognition method for detecting - Google Patents

A kind of sound fixation and recognition method for detecting Download PDF

Info

Publication number
CN109151393A
CN109151393A CN201811170560.6A CN201811170560A CN109151393A CN 109151393 A CN109151393 A CN 109151393A CN 201811170560 A CN201811170560 A CN 201811170560A CN 109151393 A CN109151393 A CN 109151393A
Authority
CN
China
Prior art keywords
sound source
sound
microphone array
detecting
monitor camera
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201811170560.6A
Other languages
Chinese (zh)
Inventor
柯浩伟
郭俊峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Elink Smart Co Ltd
Original Assignee
Shenzhen Elink Smart Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Elink Smart Co Ltd filed Critical Shenzhen Elink Smart Co Ltd
Priority to CN201811170560.6A priority Critical patent/CN109151393A/en
Publication of CN109151393A publication Critical patent/CN109151393A/en
Pending legal-status Critical Current

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00Television systems
    • H04N7/18Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/18Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using ultrasonic, sonic, or infrasonic waves
    • G01S5/22Position of source determined by co-ordinating a plurality of position lines defined by path-difference measurements
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L21/00Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02Speech enhancement, e.g. noise reduction or echo cancellation
    • G10L21/0208Noise filtering
    • G10L21/0216Noise filtering characterised by the method used for estimating noise
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L21/00Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02Speech enhancement, e.g. noise reduction or echo cancellation
    • G10L21/0208Noise filtering
    • G10L21/0216Noise filtering characterised by the method used for estimating noise
    • G10L2021/02161Number of inputs available containing the signal or the noise to be suppressed
    • G10L2021/02166Microphone arrays; Beamforming

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Quality & Reliability (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
  • Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)

Abstract

The present invention provides a kind of sound fixation and recognition method for detecting, include the following steps, S1: preparation is integrated with the holder monitor camera of solid space microphone array, and the sound detecting/warning function of the holder monitor camera is opened, sampling processing is carried out using sound source (voice or noise) of the solid space microphone array to environment;S2: after holder monitor camera acquires sound source information somewhither, sound source information is analyzed and determined by built-in speech sample recognizer;S3: solid space microphone array is detected using the position that voice signal energy power issues sound source, and quickly carry out sound source position positioning, in actual application, identification is detected in the auditory localization of the application, image push alarm can be instantaneously captured, the quick pickup of microphone array analyzes and determines sound source, and can effectively shield noise signal, precision is high, good application effect.

Description

A kind of sound fixation and recognition method for detecting
[technical field]
The present invention relates to voice recognition detection technology field more particularly to a kind of identification precision height, intelligence degree are high Sound fixation and recognition method for detecting.
[background technique]
PTZ camera only passes through human motion into camera views at present, and humanoid alarm of setting out cannot actively be sentenced Disconnected situation of the people outside camera picture, it is that very well, how could preferably be directed to camera shooting that this, which results in Product Experience effect not, The defect of machine passive triggering human body alarm, carries out the identification of active pickup within the scope of designated space, judges position of human body, actively touches Hair alarm, well solves the problem of video camera cannot actively trigger alarm, is that those skilled in the art often consider the problems of.
Based on this, those skilled in the art have carried out a large amount of research and development and experiment, the obtaining mode of sound from environment, letter The various aspects such as breath tupe, which are started with, to be improved and improves, and achieves preferable achievement.
[summary of the invention]
To overcome the problems of prior art, the present invention provides a kind of identification precision height, and intelligence degree is high Sound fixation and recognition method for detecting.
The scheme that the present invention solves technical problem is to provide a kind of sound fixation and recognition method for detecting, includes the following steps,
S1: preparation is integrated with the holder monitor camera of solid space microphone array, and opens the holder monitoring camera The sound detecting/warning function of machine is carried out at sampling using sound source (voice or noise) of the solid space microphone array to environment Reason;
S2: after holder monitor camera acquires sound source information somewhither, pass through built-in speech sample and identify calculation Method analyzes and determines sound source information;
S3: solid space microphone array is detected using the position that voice signal energy power issues sound source, and Quickly carry out sound source position positioning;
S4: after sound source position determines in step S3, the internal control component of holder monitor camera sends control life It enables control camera turn to sound source position direction, and picture at this is captured, it further will be in the image information of shooting Report cloud server;
S5: corresponding informance is pushed to customer mobile terminal position by cloud server photographing information based on the received.
Preferably, the solid space microphone array of holder monitor camera includes 360 ° of horizontal annular in the step S1 Microphone array is combined with vertical ring-shaped 360 ° of microphone arrays.
Preferably, it in the step S2, after holder monitor camera collects sound source information, synchronizes be directed to and be somebody's turn to do The noise reduction process of sound source information distinguishes the sound of noise and human body sending in environment, shields noise signal.
Preferably, between 360 ° of microphone arrays of the horizontal annular and vertical ring-shaped 360 ° of microphone arrays respectively include etc. Four microphones away from setting;And four microphone connecting lines of 360 ° of microphone arrays of horizontal annular and vertical ring-shaped 360 ° of wheats Four microphone connecting line square crossings of gram wind array have same center.
Preferably, in the step S4, while holder monitor camera captures sound source position, pass through alarm Issue alarm sound.
Compared with prior art, a kind of sound fixation and recognition method for detecting of the present invention is integrated with three-dimensional sky by using preparation Between microphone array holder monitor camera, and the sound detecting/warning function of the holder monitor camera is opened, using vertical Body space microphone array carries out sampling processing to the sound source (voice or noise) of environment, when holder monitor camera collects certain After the sound source information at place, sound source information is analyzed and determined by built-in speech sample recognizer, finally realization sound The fixation and recognition of sound, in actual application, identification is detected in the auditory localization of the application, can instantaneously capture image push report Alert, the quick pickup of microphone array analyzes and determines sound source, and can effectively shield noise signal, and precision is high, application effect It is good.
[Detailed description of the invention]
Fig. 1 is a kind of flow diagram of sound fixation and recognition method for detecting of the present invention.
[specific embodiment]
To make the purpose of the present invention, technical solution and advantage are more clearly understood, with reference to the accompanying drawings and embodiments, to this Invention is further elaborated.It should be appreciated that specific embodiment described herein is used only for explaining the present invention, not For limiting the invention.
Referring to Fig. 1, a kind of sound fixation and recognition method for detecting 1 of the present invention includes the following steps,
S1: preparation is integrated with the holder monitor camera of solid space microphone array, and opens the holder monitoring camera The sound detecting/warning function of machine is carried out at sampling using sound source (voice or noise) of the solid space microphone array to environment Reason;
S2: after holder monitor camera acquires sound source information somewhither, pass through built-in speech sample and identify calculation Method analyzes and determines sound source information;
S3: solid space microphone array is detected using the position that voice signal energy power issues sound source, and Quickly carry out sound source position positioning;
S4: after sound source position determines in step S3, the internal control component of holder monitor camera sends control life It enables control camera turn to sound source position direction, and picture at this is captured, it further will be in the image information of shooting Report cloud server;
S5: corresponding informance is pushed to customer mobile terminal position by cloud server photographing information based on the received.
The application is integrated with the holder monitor camera of solid space microphone array by using preparation, and opens the cloud The sound detecting/warning function of platform monitor camera, using solid space microphone array to the sound source (voice or noise) of environment Sampling processing is carried out, after holder monitor camera acquires sound source information somewhither, passes through built-in speech sample and identifies Algorithm analyzes and determines sound source information, final to realize that localization of sound identifies, in actual application, the sound source of the application Positioning detecting identification can instantaneously capture image push alarm, and the quick pickup of microphone array analyzes and determines sound source, and can have The shielding noise signal of effect, precision is high, good application effect.
Preferably, the solid space microphone array of holder monitor camera includes 360 ° of horizontal annular in the step S1 Microphone array is combined with vertical ring-shaped 360 ° of microphone arrays.
Preferably, it in the step S2, after holder monitor camera collects sound source information, synchronizes be directed to and be somebody's turn to do The noise reduction process of sound source information distinguishes the sound of noise and human body sending in environment, shields noise signal.
Preferably, between 360 ° of microphone arrays of the horizontal annular and vertical ring-shaped 360 ° of microphone arrays respectively include etc. Four microphones away from setting;And four microphone connecting lines of 360 ° of microphone arrays of horizontal annular and vertical ring-shaped 360 ° of wheats Four microphone connecting line square crossings of gram wind array have same center.
Preferably, in the step S4, while holder monitor camera captures sound source position, pass through alarm Issue alarm sound.
The present invention is a kind of sound fixation and recognition method for detecting, is mainly used in the alarm detecting of household PTZ camera On.Solid space microphone array is integrated in PTZ camera, and sound source is carried out by special speech sample recognizer It analyzes and determines, quickly carries out localization of sound source position, and candid photograph image is carried out to picture at this and reports cloud.
Mainly comprise the steps that microphone array passes through the sound source (people to environment when opening sound detecting/warning function Sound, noise etc.) it is sampled, noise is filtered out, analyzes and determines sound source, precise positioning position of human body rapidly.Camera pan-tilt rotation To sound source position, candid photograph alarm is carried out to picture, cloud is reported to, is then pushed in user hand.
In PTZ camera integrated microphone array, it can be determined that in space the position of sound source, is quickly identified, thus Effectively quick positioning video picture position, instantaneously captures image alarm.
(2) 360 ° of microphone arrays of horizontal annular are combined with vertical ring-shaped 360 ° of microphone arrays, and comprehensive no dead angle is fixed Sound source in the environment of position.Level of microphone array is placed on the scene of desktop primarily directed to PTZ camera, when sound source is in level It is issued under environment, judgement sound source position can be identified by level of microphone array;Vertical microphone array primarily directed to PTZ camera mounts or lifts scene, can combine microphone array by horizontal+vertical and judge sound source position to analyze identification It sets.(as shown in figure)
(3) microphone array detect principle: under level environment, when people said in short, if in 8 MIC MIC1 this When it is nearest apart from sound source.The voice signal energy that so MIC1 is sampled is most strong, and the voice signal energy that MIC3 is sampled is most weak, The voice signal energy that MIC2, MIC4 are sampled is between MIC1 and MIC3.Again by special algorithm, can thus identify quickly Judge the position that sound issues.Similarly, the sound in solid space is also to be analyzed in this way.(as shown in Figure 2)
(4) when someone makes a sound in the environment of setting, the microphone array in PTZ camera passes through sampled voice Identification technology analyzes and determines rapidly, precise positioning position of human body.Camera pan-tilt turns to sound source position, grabs to picture Alarm is clapped, cloud is reported to, is then pushed in user mobile phone.(as shown in Figure 3)
(5) noise reduction process is carried out by particular algorithm, the sound of noise and human body sending in environment is distinguished, is shielded Cover noise signal.
Compared with prior art, a kind of sound fixation and recognition method for detecting 1 of the present invention is integrated with solid by using preparation The holder monitor camera of space microphone array, and the sound detecting/warning function of the holder monitor camera is opened, it utilizes Solid space microphone array carries out sampling processing to the sound source (voice or noise) of environment, when holder monitor camera collects After the sound source information in somewhere, sound source information is analyzed and determined by built-in speech sample recognizer, it is final to realize Localization of sound identifies, in actual application, identification is detected in the auditory localization of the application, can instantaneously capture image push report Alert, the quick pickup of microphone array analyzes and determines sound source, and can effectively shield noise signal, and precision is high, application effect It is good.
The embodiments of the present invention described above are not intended to limit the scope of the present invention.It is any in the present invention Spirit and principle within made modifications, equivalent substitutions and improvements etc., should be included in claim protection model of the invention Within enclosing.

Claims (5)

1. a kind of sound fixation and recognition method for detecting, it is characterised in that: include the following steps,
S1: preparation is integrated with the holder monitor camera of solid space microphone array, and opens the holder monitor camera Sound detecting/warning function carries out sampling processing using sound source (voice or noise) of the solid space microphone array to environment;
S2: after holder monitor camera acquires sound source information somewhither, pass through built-in speech sample recognizer pair Sound source information is analyzed and determined;
S3: solid space microphone array is detected using the position that voice signal energy power issues sound source, and quickly Carry out sound source position positioning;
S4: after sound source position determines in step S3, the internal control component of holder monitor camera sends control command control Camera processed turns to sound source position direction, and captures to picture at this, and the image information of shooting is further reported cloud Hold server;
S5: corresponding informance is pushed to customer mobile terminal position by cloud server photographing information based on the received.
2. a kind of sound fixation and recognition method for detecting as described in claim 1, it is characterised in that: holder is supervised in the step S1 The solid space microphone array for controlling video camera includes 360 ° of microphone arrays of horizontal annular and vertical ring-shaped 360 ° of microphone array Column combination.
3. a kind of sound fixation and recognition method for detecting as described in claim 1, it is characterised in that: in the step S2, work as cloud After platform monitor camera collects sound source information, the noise reduction process carried out for the sound source information is synchronized, making an uproar in environment The sound that sound and human body issue distinguishes, and shields noise signal.
4. a kind of sound fixation and recognition method for detecting as claimed in claim 2, it is characterised in that: 360 ° of wheats of the horizontal annular Gram wind array and vertical ring-shaped 360 ° of microphone arrays respectively include four microphones of spaced set;And 360 ° of horizontal annular Four microphone connecting lines of microphone array are vertical with four microphone connecting lines of vertical ring-shaped 360 ° of microphone arrays to be handed over Fork has same center.
5. a kind of sound fixation and recognition method for detecting as described in claim 1, it is characterised in that: in the step S4, holder While monitor camera captures sound source position, alarm sound is issued by alarm.
CN201811170560.6A 2018-10-09 2018-10-09 A kind of sound fixation and recognition method for detecting Pending CN109151393A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811170560.6A CN109151393A (en) 2018-10-09 2018-10-09 A kind of sound fixation and recognition method for detecting

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811170560.6A CN109151393A (en) 2018-10-09 2018-10-09 A kind of sound fixation and recognition method for detecting

Publications (1)

Publication Number Publication Date
CN109151393A true CN109151393A (en) 2019-01-04

Family

ID=64810875

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811170560.6A Pending CN109151393A (en) 2018-10-09 2018-10-09 A kind of sound fixation and recognition method for detecting

Country Status (1)

Country Link
CN (1) CN109151393A (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109658654A (en) * 2019-01-14 2019-04-19 刘萍 Scene orientation monitor supervision platform
CN111050130A (en) * 2019-12-12 2020-04-21 深圳市大拿科技有限公司 Camera control method and device and storage medium
CN111627178A (en) * 2020-06-30 2020-09-04 深圳市联丰科技有限公司 Sound identification positioning warning system and method thereof
CN112788482A (en) * 2021-03-01 2021-05-11 北京电信易通信息技术股份有限公司 Microphone array positioning and holder linkage method and device
CN113075614A (en) * 2021-03-17 2021-07-06 武汉创现科技有限公司 Sound source direction-finding device for cruise device, cruise device and intelligent garbage can
CN113099099A (en) * 2019-12-23 2021-07-09 中移物联网有限公司 Camera holder, electronic equipment and camera driving method
CN113365200A (en) * 2021-06-07 2021-09-07 杭州纳奇思科技有限公司 Self-adaptive abnormal sound source detection device and detection method
CN114422935A (en) * 2022-03-16 2022-04-29 荣耀终端有限公司 Audio processing method, terminal and computer readable storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101771814A (en) * 2009-12-29 2010-07-07 天津市亚安科技电子有限公司 Pan and tilt camera with sound identification and positioning function
CN204442410U (en) * 2015-02-13 2015-07-01 上海赢谊电子设备有限公司 The intelligent home device that a kind of sound is auxiliary
CN105045122A (en) * 2015-06-24 2015-11-11 张子兴 Intelligent household natural interaction system based on audios and videos
CN105263093A (en) * 2015-10-12 2016-01-20 深圳东方酷音信息技术有限公司 Omnibearing audio acquisition apparatus, omnibearing audio editing apparatus, and omnibearing audio acquisition and editing system
CN106328156A (en) * 2016-08-22 2017-01-11 华南理工大学 Microphone array voice reinforcing system and microphone array voice reinforcing method with combination of audio information and video information

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101771814A (en) * 2009-12-29 2010-07-07 天津市亚安科技电子有限公司 Pan and tilt camera with sound identification and positioning function
CN204442410U (en) * 2015-02-13 2015-07-01 上海赢谊电子设备有限公司 The intelligent home device that a kind of sound is auxiliary
CN105045122A (en) * 2015-06-24 2015-11-11 张子兴 Intelligent household natural interaction system based on audios and videos
CN105263093A (en) * 2015-10-12 2016-01-20 深圳东方酷音信息技术有限公司 Omnibearing audio acquisition apparatus, omnibearing audio editing apparatus, and omnibearing audio acquisition and editing system
CN106328156A (en) * 2016-08-22 2017-01-11 华南理工大学 Microphone array voice reinforcing system and microphone array voice reinforcing method with combination of audio information and video information

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109658654A (en) * 2019-01-14 2019-04-19 刘萍 Scene orientation monitor supervision platform
CN111050130A (en) * 2019-12-12 2020-04-21 深圳市大拿科技有限公司 Camera control method and device and storage medium
CN113099099A (en) * 2019-12-23 2021-07-09 中移物联网有限公司 Camera holder, electronic equipment and camera driving method
CN111627178A (en) * 2020-06-30 2020-09-04 深圳市联丰科技有限公司 Sound identification positioning warning system and method thereof
CN112788482A (en) * 2021-03-01 2021-05-11 北京电信易通信息技术股份有限公司 Microphone array positioning and holder linkage method and device
CN112788482B (en) * 2021-03-01 2021-07-30 北京电信易通信息技术股份有限公司 Microphone array positioning and holder linkage method and device
CN113075614A (en) * 2021-03-17 2021-07-06 武汉创现科技有限公司 Sound source direction-finding device for cruise device, cruise device and intelligent garbage can
CN113365200A (en) * 2021-06-07 2021-09-07 杭州纳奇思科技有限公司 Self-adaptive abnormal sound source detection device and detection method
CN114422935A (en) * 2022-03-16 2022-04-29 荣耀终端有限公司 Audio processing method, terminal and computer readable storage medium
CN114422935B (en) * 2022-03-16 2022-09-23 荣耀终端有限公司 Audio processing method, terminal and computer readable storage medium

Similar Documents

Publication Publication Date Title
CN109151393A (en) A kind of sound fixation and recognition method for detecting
US9491553B2 (en) Method of audio signal processing and hearing aid system for implementing the same
WO2017125094A1 (en) Body fall smart control system and method therefor
CN102737480B (en) Abnormal voice monitoring system and method based on intelligent video
JP5043940B2 (en) Video surveillance system and method combining video and audio recognition
CN105578058A (en) Shooting control method and device for intelligent robot and robot
JP6135880B2 (en) Audio processing method, audio processing system, and storage medium
CN105894702A (en) Invasion detecting alarming system based on multi-camera data combination and detecting method thereof
CN104135645A (en) Video surveillance system and method for face tracking and capturing
CN110633612B (en) Monitoring method and system for inspection robot
CN108353148A (en) Nolo flight quality testing examining system and nolo flight object detecting method
CN107450729A (en) Robot interactive method and device
CN109551500A (en) Supervisory control of robot alarm system
CN104349040B (en) For the camera base and its method in video conferencing system
WO2017147827A1 (en) Image acquisition method
CN110933478A (en) Security protection system
CN110634506A (en) Voice data processing method and device
CN105516692A (en) Intelligent equipment for Internet of Things
WO2019225147A1 (en) Airborne object detection device, airborne object detection method, and airborne object detection system
CN109194916B (en) Movable shooting system with image processing module
JP2007156689A (en) Light source position detection device and face recognition device using the same and self-propelled robot
US10880655B2 (en) Method for operating a hearing apparatus system, and hearing apparatus system
CN109104667A (en) A kind of control method of intelligent sound, system and intelligent sound
CN105718921A (en) Method capable of realizing robot intelligent emotion recording
CN108986407A (en) A kind of safety monitoring system and method for old solitary people

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20190104