CN106779091B - A Periodic Vibration Signal Localization Method Based on ELM and Reach Distance - Google Patents
A Periodic Vibration Signal Localization Method Based on ELM and Reach Distance Download PDFInfo
- Publication number
- CN106779091B CN106779091B CN201611205044.3A CN201611205044A CN106779091B CN 106779091 B CN106779091 B CN 106779091B CN 201611205044 A CN201611205044 A CN 201611205044A CN 106779091 B CN106779091 B CN 106779091B
- Authority
- CN
- China
- Prior art keywords
- fundamental frequency
- vibration signal
- fbed
- distance
- periodic vibration
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000000737 periodic effect Effects 0.000 title claims abstract description 33
- 230000004807 localization Effects 0.000 title claims abstract description 9
- 238000000605 extraction Methods 0.000 claims abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 13
- 238000004364 calculation method Methods 0.000 claims description 14
- 239000000284 extract Substances 0.000 claims description 9
- 230000003595 spectral effect Effects 0.000 claims description 7
- 238000001228 spectrum Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 6
- 230000001419 dependent effect Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000001154 acute effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 230000001568 sexual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a kind of periodic vibration signal localization methods based on transfinite learning machine and arrival distance.The present invention includes the following steps: step 1, based on known accurate fundamental frequency and arrival distance, obtains training range prediction model.Step 2 obtains the unknown fundamental frequency collected at 3 or more nodes in the same period respectively and reaches the periodic vibration signal of distance；Step 3, the periodic vibration signal at any node carry out accurate fundamental frequency fiExtraction, and carry out based on obtained accurate fundamental frequency the extraction of FBED feature vector；Step 4, to periodic vibration signal at any node, extraction obtains FBED characteristic vector W, carries out distance estimations to characteristic vector W using trained ELM prediction model, obtains corresponding range estimation di；Step 5, the estimated coordinates for calculating vibration source.The present invention realizes high-precision distance estimations and the speed with the training and real-time estimation being exceedingly fast under single node, reduces the cost of sensor network laying.
Description
Technical field
The invention belongs to field of signal processing, are related to a kind of periodic vibration signal based on transfinite learning machine and arrival distance
Localization method.
Background technique
Traditional high precision nonlinear regression estimation algorithm such as support vector machines (SVM), error back propagation (BP) nerve
Network and now popular deep learning algorithm, relatively slow, unsuitable field application that there are model trainings and real-time estimation speed
The application problem of environment.
Traditional vibration source positioning is realized based on multisensor array node based on the deflection positioning for reaching time delay
Scheme, however it is applied to there are problems that following 2 when earth's surface periodic vibration reaches distance detection:
1. the calculating that traditional locating scheme reaches time delay is necessarily dependent upon more accurate velocity of wave, however vibration wave is in different Jie
Velocity of wave has certain difference when propagating in quality table, will cause greatly to the array positioning mode dependent on accurate delay inequality
Error influences precision；
2. multisensor array node is more demanding to sensor and support circuit, cost is larger, pushes away without large area
Wide condition；
3. single multisensor array node is only able to achieve the estimation at vibration source arrival direction angle, need 2 or more it is more
Sensor array node realizes that direction intersects the plane coordinates that just can determine that vibration source, therefore considerably increases the laying of sensor
Cost, sexual valence are relatively low.
The present invention is based on learning machine intelligent algorithm and the arrival Distance positioning methods of transfiniting, and propose a kind of for the vibration of earth's surface period
The method of source coordinate setting.The method is estimated based on learning machine (Extreme Learning Machine, ELM) progress distance that transfinites
High-precision distance estimations and the speed with the training and real-time estimation being exceedingly fast under single node may be implemented in meter.Furthermore it is based on arriving
The estimation of 1 vibrating sensor realization arrival distance is only needed up to single-sensor node in the locating scheme of distance, and it is non-traditional
It needs multiple vibrating sensors to realize the estimation of arrival direction in locating scheme in array node, reduces sensor network laying
Cost, reduce this method popularization difficulty.
Summary of the invention
In view of the deficiencies of the prior art, it is an object of the present invention to provide a kind of weeks based on transfinite learning machine and arrival distance
Phase vibration signal localization method.
The technical solution adopted by the present invention to solve the technical problems includes the following steps:
Step 1 obtains training range prediction model
It 1.1, is L for any one piece of data length based on known accurate fundamental frequency and arrival distancefKnown fundamental frequency and arrive
Up to the periodic vibration signal of distance, FBED is carried out based on known accurate fundamental frequency
(FrequencyBandEnergyDistribution) extraction of feature vector；
1.2, it acquires periodic vibration signal under different distance and constructs corresponding standard FBED feature vector library；
1.3, the FBED feature vector of distance is reached based on calibration using learning machine (ELM) algorithm training range prediction of transfiniting
Model.
Step 2, the node P for obtaining 3 or more in the same period respectivelyiIt is collected at (i=1,2,3 ...)
Unknown fundamental frequency and the periodic vibration signal S for reaching distancei(n), n=1,2 ..., Lf, data length is all Lf, sample frequency be
Fs；
Step 3 is directed to any node PiPeriodic vibration signal S at (i=1,2,3 ...)i(n), accurate fundamental frequency f is carried outi
Extraction, and based on obtained accurate fundamental frequency fiCarry out the extraction of FBED feature vector；
3.1, it is based on common fundamental frequency extraction algorithm, as autocorrelation sequence method, average amplitude difference method or Cepstrum Method carry out base
Frequency, which extracts, obtains fundamental frequency estimation valueAnd match immediate accurate fundamental frequency fi；
3.2, accurate fundamental frequency is based on from periodic vibration signal Si(n) it is extracted on and obtains FBED characteristic vector W.
Step 4, to any node PiLocate periodic vibration signal Si(n), it extracts and obtains FBED characteristic vector W, using training
ELM prediction model to characteristic vector W carry out distance estimations, obtain corresponding range estimation di；
Step 5, the estimated coordinates for calculating vibration source, it is specific as follows: based on periodic vibration signal S at any 3 nodesi
(n), the vibration is calculated in the range estimation respectively obtained by ELM prediction model, the positioning mode for being then based on arrival distance
The estimated coordinates in dynamic source；
The calculating of vibration source estimated coordinates is as follows:
Setting any 3 nodes is respectively P1(x1,y1)、P2(x2,y2)、P3(x3,y3), and the estimated coordinates of vibration source are
(x, y), the then formula based on the positioning mode for reaching distance are as follows:
Wherein
Wherein, d1、d2、d3It respectively refers to for node P1(x1,y1)、P2(x2,y2)、P3(x3,y3) at obtained range estimation,
And γ1、γ2Intermediate variable when to calculate；
FBED characteristic vector pickup process in the step 1.1 and step 3.2 be it is identical, treatment process is base
Mr. Yu's fundamental frequency ffd, extract NbTie up FBED feature vectorSpecific formula for calculation group is as follows:
1) dimension NbDetermine formula:
2) i-th of frequency band upper and lower limits [fL(i),fR(i)] calculation formula:
Conflict additionally due to frequency range may have with half spectral limit of PSD (f), so to fR(Nb) have one it is modified
Operation:
fR(Nb)=min [Fs/2,fR(Nb)]；
3) feature vector before normalizingCalculation formula:
Power spectral density (Power Spectral Density) sequence of PSD (f) segment signal thus herein, as one
The common Digital Signal Processing frequency-domain analysis object of kind, has many general calculation methods, details are not described herein again；
4) FBED feature vectorCalculation formula it is as follows:
The FBED feature vector is existing more stable FBED
(FrequencyBandEnergyDistribution) feature vector, can also using other include reach range information away from
From feature, the validity of subsequent processes is had no effect on.
Due to using existing general fundamental frequency extraction algorithm and fundamental frequency matching process in the step 3.1, so
It can select specific scheme according to demand herein, have no effect on the validity of subsequent processes.
The present invention has the beneficial effect that:
The method be based on transfinite learning machine (Extreme Learning Machine, ELM) carry out distance estimations can be real
High-precision distance estimations and the speed with the training and real-time estimation being exceedingly fast under existing single node.
Furthermore based on single-sensor node in the locating scheme for reaching distance only need 1 vibrating sensor realize reach away from
From estimation, and multiple vibrating sensors is needed to realize the estimations of arrival directions, drop in non-traditional locating scheme in array node
The cost that low sensor network is laid reduces the difficulty of this method popularization.
Detailed description of the invention
Fig. 1 reaches distance estimations and localization method flow diagram
Specific embodiment
It elaborates with reference to the accompanying drawings and detailed description to the present invention.
As shown in Figure 1, a kind of periodic vibration signal localization method based on transfinite learning machine and arrival distance, specifically includes
Following steps:
Step 1 obtains training range prediction model
It 1.1, is L for any one piece of data length based on known accurate fundamental frequency and arrival distancefKnown fundamental frequency and arrive
Up to the periodic vibration signal of distance, FBED is carried out based on known accurate fundamental frequency
(FrequencyBandEnergyDistribution) extraction of feature vector；
1.2, it acquires periodic vibration signal under different distance and constructs corresponding standard FBED feature vector library；
1.3, the FBED feature vector of distance is reached based on calibration using learning machine (ELM) algorithm training range prediction of transfiniting
Model.
Step 2, the node P for obtaining 3 or more in the same period respectivelyiIt is collected at (i=1,2,3 ...)
Unknown fundamental frequency and the periodic vibration signal S for reaching distancei(n), n=1,2 ..., Lf, data length is all Lf, sample frequency be
Fs；
Step 3 is directed to any node PiPeriodic vibration signal S at (i=1,2,3 ...)i(n), accurate fundamental frequency f is carried outi
Extraction, and based on obtained accurate fundamental frequency fiCarry out the extraction of FBED feature vector；
3.1, it is based on common fundamental frequency extraction algorithm, as autocorrelation sequence method, average amplitude difference method or Cepstrum Method carry out base
Frequency, which extracts, obtains fundamental frequency estimation valueAnd match immediate accurate fundamental frequency fi；
3.2, accurate fundamental frequency is based on from periodic vibration signal Si(n) it is extracted on and obtains FBED characteristic vector W.
Step 4, to any node PiLocate periodic vibration signal Si(n), it extracts and obtains FBED characteristic vector W, using training
ELM prediction model to characteristic vector W carry out distance estimations, obtain corresponding range estimation di；
Step 5, the estimated coordinates for calculating vibration source, it is specific as follows: based on periodic vibration signal S at any 3 nodesi
(n), the vibration is calculated in the range estimation respectively obtained by ELM prediction model, the positioning mode for being then based on arrival distance
The estimated coordinates in dynamic source；
The calculating of vibration source estimated coordinates is as follows:
Setting any 3 nodes is respectively P1(x1,y1)、P2(x2,y2)、P3(x3,y3), and the estimated coordinates of vibration source are
(x, y), the then formula based on the positioning mode for reaching distance are as follows:
Wherein
Wherein, d1、d2、d3It respectively refers to for node P1(x1,y1)、P2(x2,y2)、P3(x3,y3) at obtained range estimation,
And γ1、γ2Intermediate variable when to calculate；
FBED characteristic vector pickup process in the step 1.1 and step 3.2 be it is identical, treatment process is base
Mr. Yu's fundamental frequency ffd, extract NbTie up FBED feature vectorSpecific formula for calculation group is as follows:
1) dimension NbDetermine formula:
2) i-th of frequency band upper and lower limits [fL(i),fR(i)] calculation formula:
Conflict additionally due to frequency range may have with half spectral limit of PSD (f), so to fR(Nb) have one it is modified
Operation:
fR(Nb)=min [Fs/2,fR(Nb)]；
3) feature vector before normalizingCalculation formula:
Power spectral density (Power Spectral Density) sequence of PSD (f) segment signal thus herein, as one
The common Digital Signal Processing frequency-domain analysis object of kind, has many general calculation methods, details are not described herein again；
4) FBED feature vectorCalculation formula:
The FBED feature vector is existing more stable FBED
(FrequencyBandEnergyDistribution) feature vector, can also using other include reach range information away from
From feature, the validity of subsequent processes is had no effect on.
In step 3.1, the data length Lf that common fundamental frequency extraction algorithm usually requires to obtain in step 2 is included at least
2 or more practical fundamental frequency cycles, to guarantee to extract to obtain fundamental frequency information therein.
It is understood that the essence of FBED distance feature vector is periodic vibration signal power spectrum in step 1.1 and 3.2
The compression expression form of degree.It is basic according to being that (a) is based on energy in periodic vibration signal and concentrates on as 2 of distance feature
Near fundamental frequency integral multiple；(b) with the variation of propagation distance (reaching distance), the decaying of the different frequency ingredient of periodic vibration signal
Degree is different.It using each fundamental frequency integral multiple is frequency range center in formula in note 1 of the present invention, cover width is base
The frequency range of frequency size.In fact each frequency bands Band can be selected wide according to demand to reach different anti-broadband noise and base
The effect of frequency evaluated error.
Positioning in step 5, which can according to need, does into one each vibration source estimated coordinates that all 3 combination of nodes obtain
Step integration, to reach more preferably locating effect.The present invention is shown by taking least 3 node as an example based on the positioning side for reaching distance
Method, so no longer being repeated with regard to this.In addition, 3 vibrating sensors need not point-blank in 3 node locatings, and preferably exist
Earth's surface Triangle-Profile at an acute angle simultaneously guarantees reasonable spacing, to guarantee that distance estimations error is smaller and vibration source to all directions
Locating effect is close.
Claims (2)
1. a kind of periodic vibration signal localization method based on transfinite learning machine and arrival distance, it is characterised in that including walking as follows
It is rapid:
Step 1 obtains training range prediction model
It 1.1, is L for any one piece of data length based on known accurate fundamental frequency and arrival distancefKnown fundamental frequency and reach away from
From periodic vibration signal, the extraction of FBED feature vector is carried out based on known accurate fundamental frequency；
1.2, it acquires periodic vibration signal under different distance and constructs corresponding standard FBED feature vector library；
1.3, the FBED feature vector of distance is reached based on calibration using the learning machine algorithm training range prediction model that transfinites；
Step 2 obtains the unknown fundamental frequency collected at 3 or more nodes in the same period respectively and reaches distance
Periodic vibration signal Si(n), n=1,2 ..., Lf, data length is all Lf, sample frequency Fs；
Step 3 is directed to any node PiThe periodic vibration signal S at placei(n), accurate fundamental frequency f is carried outiExtraction, wherein i=1,2,
3..., and based on obtained accurate fundamental frequency fiCarry out the extraction of FBED feature vector；
3.1, it is based on fundamental frequency extraction algorithm, fundamental frequency is carried out and extracts acquisition fundamental frequency estimation valueAnd match immediate accurate fundamental frequency
fi；
3.2, accurate fundamental frequency is based on from periodic vibration signal Si(n) it is extracted on and obtains FBED characteristic vector W；
Step 4, to any node PiLocate periodic vibration signal Si(n), it extracts and obtains FBED characteristic vector W, utilization is trained
ELM prediction model carries out distance estimations to characteristic vector W, obtains corresponding range estimation di；
Step 5, the estimated coordinates for calculating vibration source, it is specific as follows: based on periodic vibration signal S at any 3 nodesi(n), lead to
The range estimation that ELM prediction model respectively obtains is crossed, the vibration source is calculated in the positioning mode for being then based on arrival distance
Estimated coordinates；
The calculating of vibration source estimated coordinates is as follows:
Setting any 3 nodes is respectively P1(x1,y1)、P2(x2,y2)、P3(x3,y3), and the estimated coordinates of vibration source be (x,
Y), then the formula based on the positioning mode for reaching distance is as follows:
Wherein
Wherein, d1、d2、d3It respectively refers to for node P1(x1,y1)、P2(x2,y2)、P3(x3,y3) at obtained range estimation, and
γ1、γ2Intermediate variable when to calculate.
2. a kind of periodic vibration signal localization method based on transfinite learning machine and arrival distance according to claim 1,
It is characterized by:
FBED characteristic vector pickup process in the step 1.1 and step 3.2 be it is identical, treatment process is based on base
Frequency ffd, extract NbTie up FBED feature vectorSpecific formula for calculation group is as follows:
1) dimension NbDetermine formula:
2) i-th of frequency band upper and lower limits [fL(i),fR(i)] calculation formula:
Conflict additionally due to frequency range has with half spectral limit of power spectrum degree series PSD (f), so to fR(Nb) there is one
Modified operation:
fR(Nb)=min [Fs/2,fR(Nb)]；FsFor sample frequency；
3) feature vector before normalizingCalculation formula:
4) FBED feature vectorCalculation formula:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611205044.3A CN106779091B (en) | 2016-12-23 | 2016-12-23 | A Periodic Vibration Signal Localization Method Based on ELM and Reach Distance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611205044.3A CN106779091B (en) | 2016-12-23 | 2016-12-23 | A Periodic Vibration Signal Localization Method Based on ELM and Reach Distance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106779091A CN106779091A (en) | 2017-05-31 |
| CN106779091B true CN106779091B (en) | 2019-02-12 |
Family
ID=58918935
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611205044.3A Active CN106779091B (en) | 2016-12-23 | 2016-12-23 | A Periodic Vibration Signal Localization Method Based on ELM and Reach Distance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106779091B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110176129B (en) * | 2018-10-31 | 2022-05-03 | 广东小天才科技有限公司 | Underwater safety detection method based on double cameras and wearable equipment |
| CN110287514B (en) * | 2019-05-10 | 2023-03-28 | 杭州电子科技大学 | Ultrahigh-speed collision source intelligent positioning method based on vibration signal processing |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104799852A (en) * | 2015-05-19 | 2015-07-29 | 北京工业大学 | Method for extracting movement imagination electroencephalogram characteristics based on ultralimit learning machine self encoding |
| CN104914870A (en) * | 2015-07-08 | 2015-09-16 | 中南大学 | Ridge-regression-extreme-learning-machine-based local path planning method for outdoor robot |
| CN105426447A (en) * | 2015-11-09 | 2016-03-23 | 北京工业大学 | Relevance feedback method based on transfinite learning machine |
| CN105701506A (en) * | 2016-01-12 | 2016-06-22 | 杭州电子科技大学 | Improved method based on extreme learning machine (ELM) and sparse representation classification |
| CN105809247A (en) * | 2016-02-25 | 2016-07-27 | 中国石油大学(华东) | Over-limit learning machine modeling method based on conjugate gradient method |
| CN105852885A (en) * | 2016-03-23 | 2016-08-17 | 陕西师范大学 | N400 evoked potential lie detection method based on improved extreme learning machine |
| CN105919584A (en) * | 2016-06-23 | 2016-09-07 | 电子科技大学 | Heart rate estimation method and device for wearable heart rate monitoring equipment |
-
2016
- 2016-12-23 CN CN201611205044.3A patent/CN106779091B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104799852A (en) * | 2015-05-19 | 2015-07-29 | 北京工业大学 | Method for extracting movement imagination electroencephalogram characteristics based on ultralimit learning machine self encoding |
| CN104914870A (en) * | 2015-07-08 | 2015-09-16 | 中南大学 | Ridge-regression-extreme-learning-machine-based local path planning method for outdoor robot |
| CN105426447A (en) * | 2015-11-09 | 2016-03-23 | 北京工业大学 | Relevance feedback method based on transfinite learning machine |
| CN105701506A (en) * | 2016-01-12 | 2016-06-22 | 杭州电子科技大学 | Improved method based on extreme learning machine (ELM) and sparse representation classification |
| CN105809247A (en) * | 2016-02-25 | 2016-07-27 | 中国石油大学(华东) | Over-limit learning machine modeling method based on conjugate gradient method |
| CN105852885A (en) * | 2016-03-23 | 2016-08-17 | 陕西师范大学 | N400 evoked potential lie detection method based on improved extreme learning machine |
| CN105919584A (en) * | 2016-06-23 | 2016-09-07 | 电子科技大学 | Heart rate estimation method and device for wearable heart rate monitoring equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106779091A (en) | 2017-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105263113B (en) | A kind of WiFi location fingerprints map constructing method and its system based on crowdsourcing | |
| CN107102296A (en) | A Sound Source Localization System Based on Distributed Microphone Array | |
| CN109188362A (en) | A kind of microphone array auditory localization signal processing method | |
| CN102305925A (en) | Robot continuous sound source positioning method | |
| CN106019215B (en) | Nested array direction of arrival angle method of estimation based on fourth-order cumulant | |
| CN105929389A (en) | Direct locating method based on external radiation source time delay and Doppler frequency | |
| CN104535965A (en) | Parallelized sound source positioning system based on embedded GPU system and method | |
| CN108828501B (en) | Method for real-time tracking and positioning of mobile sound source in indoor sound field environment | |
| US20120195436A1 (en) | Sound Source Position Estimation Apparatus, Sound Source Position Estimation Method, And Sound Source Position Estimation Program | |
| CN108231085A (en) | A kind of sound localization method and device | |
| CN107707324A (en) | A kind of acoustical signal delay time estimation method based on phase difference and maximal possibility estimation | |
| CN104749557B (en) | A kind of RF tag localization method and system | |
| CN106779091B (en) | A Periodic Vibration Signal Localization Method Based on ELM and Reach Distance | |
| CN103760520A (en) | Monolingual sound source DOA estimation method based on AVS and sparse representation | |
| CN103969508B (en) | A kind of Electric Power Harmonic Analysis method high-accuracy in real time and device | |
| CN103792513A (en) | Thunder positioning system and method | |
| CN109459745A (en) | A method of moving acoustic sources speed is estimated using radiated noise | |
| CN110221249A (en) | Compressed sensing based broadband sound source localization method | |
| CN108089702B (en) | A method and system for human-body sensory interaction based on ultrasound | |
| CN115166632B (en) | Method and device for determining sound source direction, storage medium and electronic device | |
| CN110515034A (en) | An acoustic signal azimuth measurement system and method | |
| Liu et al. | Research on acoustic source localization using time difference of arrival measurements | |
| CN103778288B (en) | Ant colony optimization-based near field sound source localization method under non-uniform array noise condition | |
| CN105891776B (en) | Direct method reaching time-difference localization method based on MDS models | |
| CN108957389A (en) | A kind of real number field multi channel signals method for estimating target azimuth |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |