CN109448389A - A kind of vehicle whistle intelligent detecting method - Google Patents
A kind of vehicle whistle intelligent detecting method Download PDFInfo
- Publication number
- CN109448389A CN109448389A CN201811406108.5A CN201811406108A CN109448389A CN 109448389 A CN109448389 A CN 109448389A CN 201811406108 A CN201811406108 A CN 201811406108A CN 109448389 A CN109448389 A CN 109448389A
- Authority
- CN
- China
- Prior art keywords
- signal
- whistle
- vehicle
- sound
- indicate
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
Abstract
The present invention provides a kind of vehicle whistle intelligent detecting methods, receive acoustical signal with air sonar sensor array, amplify filtering to the signal received and sample;The classification of vehicle whistle signal and ambient noise is realized by trained support vector machines;Change signal incident angle θ by way of mechanical scanning, estimates the direction of sound-source signal;The positioning of illegal vehicle is realized by Wave beam forming positioning, is then collected evidence by the candid photograph that high-definition camera carries out illegal vehicle.The present invention can monitor the voice signal on road in real time, accurately identify whistle sound, and position in real time according to the vehicle whistle sound of acquisition.
Description
Technical field
The invention belongs to field of signal processing, are related to the reasons such as machine learning, sonar Wave beam forming, acoustical signal processing positioning
By.
Background technique
With the rapid development of auto industry, automobile annual growth rate is higher and higher, concern of the people for noise of blowing a whistle
More and more closely.Show the noise source in city 70% in traffic noise according to relevant information, and vehicle whistle is made an uproar in traffic noise
Sound occupies very big specific gravity.The normal life and rest of vehicle whistle noise jamming people even influences the body and mind of people when serious
Health, such as cause cardiovascular disease, endocrine system disease.Furthermore vehicle whistle noise can cause study and work efficiency to reduce, produce
Quality decline even becomes the social factors of instability under given conditions.In recent years, the people are to vehicle whistle noise pollution
The demand of improvement is more more and more intense, and the complaint to disturb residents about whistle that various regions traffic police is accepted is also in an endless stream.Many cities exist
All set up the region of no tooting in each section.But since illegal whistle event scene evidence taking itself is more difficult, it is difficult to differentiate etc. because
Element, various regions traffic police are difficult to carry out scene evidence taking punishment to illegal whistle event, this brings to the improvement of each city noise pollution
Very big difficulty.
Array signal process technique has been widely used in communication, radar, sonar, medicine, Speech processing etc. at present
Numerous areas, since the eighties in last century, array signal process technique is widely used in the research of sound source Passive Positioning,
What is such as carried on submarine is used to visit latent broadside-sonar, and the microphone array of localization of sound source is used in video conference room,
The acoustic sensor array etc. of anti-sniper hand is used in military affairs.Sonic transducer equipment for Passive Positioning is in ocean mainly with water
Listening device basic matrix is representative, and is mainly arranged in air with the microphone array of various formations as representative, they passively receive sound
Information, being filtered using array signal process technique to signal is enhanced, and obtains signal characteristic, calculates transmission direction.Sound transmission
Multipath effect causes containing other reflection signals in addition to signal source in received signal, these are reached by multipath transmisstion
Signal and original signal correlation are very high, are difficult to be filtered out, and a degree of deviation can be brought to calculated result.
Summary of the invention
For overcome the deficiencies in the prior art, the present invention provides a kind of intelligent detecting method based on air Sonar system,
Voice signal on road can be monitored in real time, accurately identify whistle sound, and real according to the vehicle whistle sound of acquisition
Shi Dingwei, cooperation high-definition camera are accurately captured whistle vehicle, while can also enroll the speaker sound of whistle vehicle as card
According to, by technological means to whistle vehicle capture, auxiliary traffic police department law enforcement evidence obtaining.
The technical solution adopted by the present invention to solve the technical problems the following steps are included:
The first step receives acoustical signal, the signal x that i-th of sonic transducer receives with air sonar sensor arrayi(t)
=hi(t)*s(t)+ni(t), i=1,2 ..., N, wherein hiIt (t) is that environment impulse between sound source and i-th of sonic transducer is rung
It answers, s (t) represents original signal, ni(t) ambient noise is represented;
Second step amplifies filtering to the signal received and samples;
Third step realizes the classification of vehicle whistle signal and ambient noise by trained support vector machines;It is optimal
Classify curve yi=wxi+ b, i=1...n, wherein w is optimal classification line slope, and b is optimal classification line intercept;At this time optimal
Change classification problem to be converted to
In formula, ξiIndicate the relaxation factor with elastic telescopic, C indicates penalty coefficient;
4th step, calculates the output power of Beam-former, changes signal incident angle θ by way of mechanical scanning and looks for
To angle corresponding to output power spectrum peak, the direction of sound-source signal is estimated;
5th step realizes the positioning of illegal vehicle by Wave beam forming positioning, is then carried out by high-definition camera separated
The candid photograph of method vehicle is collected evidence.
The second step carries out two-stage amplification to the signal of acquisition, and the first order amplifies 10 times, the gain of second level amplification
It is adjusted between 1,2,5,10 times.
In the third step, framing windowing process is carried out to signal is received, extracts the following five classes sound letter for receiving signal
Number feature;
(1) sub-belt energyWherein Y (ω) indicates to receive the Fourier transformation of signal, and n, m are respectively indicated
Pay close attention to the initial frequency and cutoff frequency of frequency band;
(2) sub-belt energy varianceWherein SiIndicate the frequency of i-th of subband of constant bandwidth
Domain normalized energy;
(3) the total kurtosis of frequency bandWherein δ is the standard deviation of sample data,Indicate the equal of Y (ω)
Value
(4) subband kurtosis mean valueWherein KiIndicate the kurtosis of i-th of subband;
(5) short-time average zero-crossing rateWherein w (n)
It is window function;
Vehicle whistle acoustical signal is denoted as ui=1, ambient noise signal is denoted as ui=-1, then have
Wherein xiFor the feature vector for receiving the composition of five acoustical signal features corresponding to signal in third step, w is optimal classification line
Slope matrix, b are the bias term of optimal classification line;Construction decision function w makes ui(wxi+ b) establishment of > 1;
Calculate training sample xiEuclidean distance between hyperplane | uiyi|/| | w | |, all training datas are all satisfied |
uiyi|/| | w | | >=δ, wherein δ is interval, with season δ | | w | |=1;Then solving optimal hyperlane is exactly to find the w for meeting above formula
The European norm of minimum, then be converted into following optimization problem:
In formula, ξiIndicate the relaxation factor with elastic telescopic, C indicates penalty coefficient;
Several training samples are taken to repeat this step, being divided into training sample by hyperplane has whistle sound and environment to make an uproar
Sound obtains trained support vector machines.
The relaxation factor ξiThe value in 0 to 1 range;The value of penalty coefficient C is 100 or 200.
In 4th step Wave beam forming output end power spectrum P (θ)=E [| y (t, θ) |2]=wH(θ) Rw (θ), formula
In, t is the time, and w is weighting matrix, and array element receives covariance matrix R=E [X (t) X of signalH(t)];N number of sound is sensed
The array of device composition, kth packet snap is interior to receive data matrixAssuming that number of snapshots are K,
Total covariance matrix
The beneficial effects of the present invention are: can monitor in real time to the voice signal on road, whistle sound is accurately identified
Sound, and positioned in real time according to the vehicle whistle sound of acquisition, cooperation high-definition camera can be accurately captured whistle vehicle, simultaneously also
The speaker sound of whistle vehicle can be enrolled as evidence.Whistle vehicle is captured by technological means, assists traffic police department
Law enforcement evidence obtaining solves the pain spot that traffic police administers illegal whistle event Difficult Law-enforcement, evidence obtaining is more difficult.
Illegal whistle frequency can be effectively reduced by installing illegal whistle capturing system, it is dirty to administer vehicle whistle noise
Dye has far reaching significance for construction green, civilization, harmonious society.Present invention employs newest machine learning and artificial intelligence
Energy technology, artificial intelligence technology is successfully applied in intelligent transportation field, pushed the technology in fields such as security protection, monitoring
Application and development.
Detailed description of the invention
Fig. 1 is flow chart of the method for the present invention;
Fig. 2 is sensor of the invention array scheme of installation
Fig. 3 is pretreatment circuit diagram of the invention;
Fig. 4 is support vector machines optimal classification schematic diagram of the invention;
Fig. 5 is Wave beam forming location simulation result schematic diagram of the invention.
Specific embodiment
Present invention will be further explained below with reference to the attached drawings and examples, and the present invention includes but are not limited to following implementations
Example.
It blows a whistle the problem that evidence obtaining is difficult and discrimination is low for traffic offence, it is proposed by the present invention based on air Sonar system
Steps are as follows for intelligent detecting method:
Step 1: air sonar sensor receives signal
It selects MEMS grades of microphones as array element, builds 16 yuan of planar arrays, be mounted on light pole platform.Air-borne sound
Mainly it is made of the microphone of certain amount and certain formation, sonar passively receives the acoustic information in monitoring area,
Under multi-path environment, sound can be regarded as sound field environment to sound source by the process that number of ways propagates successively arrival sonic transducer
The process of signal filtering, then the signal x that i-th of sonic transducer receivesi(t) it can indicate are as follows:
xi(t)=hi(t)*s(t)+ni(t), i=1,2 ..., N (1)
* indicates convolution algorithm, h in formulai(t) it is environment impulse response between sound source and i-th of sonic transducer.ni(t) generation
Table ambient noise, the ambient noise between different sonic transducers can be relevant.Environment impulse response hi(t) it is more to contain sound source
All information that diameter is propagated receive signal xi(t) not only include original signal s (t), be also superimposed by number of ways propagate,
Several back waves and ambient noise after decaying.
Step 2: pretreatment
One piece of signal pre-processing module major design of system has the pre-amplification circuit of filter function, for microphone
The signal of acquisition carries out simple amplification filtering processing.Pretreatment circuit amplifier section is made of two-stage amplifying circuit, the first order
Amplifying circuit amplifies 10 times, and the low-pass filter of cutoff frequency is adjusted, to avoid noise saturation, the increasing of second level amplifying circuit
It is beneficial then can be adjusted between 1,2,5,10 times.The chip of amplifier selects MC33204, and the entire circuit that pre-processes is powered using 5V, selected
It uses 2.5V as the bias voltage of signal, it is as shown in Figure 3 to pre-process circuit diagram.
Step 3: signal acquisition
The Passive Positioning System that the present invention designs is 16 yuan of battle arrays, it is therefore desirable to the capture card in 16 channels.16 channels are adopted
Truck type selecting should consider the elements such as sampling rate, transmission mode, stability, hardware cost.
This sound source Passive Positioning System is because what is acquired is the synchronization signal of 16 array element, 16 channel data capture cards
Sample frequency be not easy with sampling precision excessively high, otherwise can bring huge operand to array signal processing, it is negative to increase system
Load, the sampling rate highest of capture card should not be higher than 16 no more than 20480Hz, sampling resolution here.
Capture card collects after signal there is still a need for PC machine terminal is transferred to, at present the transmission mode of mainstream have serial ports transmission,
First two data transfer mode is compared in USB transmission, network interface transmission etc., and network interface transmission is in transmission range, transmission stability and in real time
Property on all have some superiority, therefore this system selection using network interface transmission acquisition signal mode.
The Ethernet data capture card of the country certain capture card producer model HK_NET6360_16AD is finally selected to make herein
For the signal acquisition unit of this system, which realizes 16 road synchronous acquisitions using the AD sampling A/D chip in double 8 channels, use with
The signal transmission form netted very much,
Step 4: the signal detection based on support vector machines
By the classification method based on support vector machines, classify to line spectrum class signal and common environmental noise, to reach
To the effect of signal detection.One " optimizing classification line " can not have been searched out to two class samples according to the principle of linear separability
It is distinguished completely, and the thinking of " approximately linear can point support vector machines " classification is to allow to classify that there are mistakes for the classification of curve
Situation, but it is all restricted to the geometric distance of mistake points and this distance classification line.Assuming that optimal classification curve can use formula
It indicates.
yi=wxi+ b, i=1...n (2)
Optimization classification problem at this time is as shown in Equation 3:
In formula, ξiIndicate the relaxation factor with elastic telescopic, the value in 0 to 1 range;C indicates punishment system
Number.They are used to adjust together the quantity and deviation of wrong misclassified gene.The experience value of constant C is generally 100 or 200.
As shown in figure 4, can always search out two straight line S1, S2 parallel to each other, this two straight lines can be respectively by two classes
Sample separates, and distance is maximum between two parallel lines, and the middle line of two parallel lines is then " the optimization classification to be found at this time
Line ".The classification of vehicle whistle signal and ambient noise is realized by trained support vector machines.
Step 5: Wave beam forming Passive Positioning
It determines after having whistle voice signal, auditory localization is carried out by Wave beam forming, N number of sonic transducer, which is constituted, receives battle array
Column, to per reception signal x all the wayi(t) it only needs to choose certain weighing vector wi(θ) is weighted summation again and can be obtained by
The output y (t, θ) of basic matrix.Assuming that echo signal is narrow band signal, signal center frequency f, then the input of Wave beam forming can be with
It indicates are as follows:
The sampled data of all array elements and the vector of complex weighting coefficients are expressed as:
X (t)=[x1(t) x2(t) … xN(t)]T (9)
W (θ)=[w1(θ) w(θ) … wN(θ)]T (10)
Then the form of Wave beam forming output inner product of vectors can indicate are as follows:
Y (t, θ)=wH(θ) x (t)=xH(t)w(θ) (11)
In formula, subscript " * " indicates that complex conjugation operator, subscript " T " indicate that the transposition of vector or matrix, subscript " H " indicate
The complex conjugate transposition of vector or matrix.
The power spectrum of Wave beam forming output end can indicate are as follows:
P (θ)=E [| y (t, θ) |2]=wH(θ)Rw(θ) (12)
The output power for calculating conventional beamformer changes θ and finds output power spectrum by way of mechanical scanning
Angle corresponding to peak value, so that it may estimate the direction of sound-source signal.Matrix R is defined as the covariance square that array element receives signal
Battle array indicates are as follows:
R=E [X (t) XH(t)] (13)
For the array of N number of sonic transducer composition, data matrix X (k) is received in kth packet snap are as follows:
Assuming that number of snapshots are K, total covariance matrix can be indicated are as follows:
Sound source theoretically should be (0 °, 0 °) with respect to the drift angle of planar array centre normal, using 3000Hz simple signal as sound source,
The plane conventional beamformer emulation of 16 yuan of battle arrays is carried out under conditions of received signal to noise ratio is 0dB, simulation result is as shown in Figure 5.
Step 6: capturing license plate
The positioning of illegal vehicle is realized by Wave beam forming positioning, and illegal vehicle is then carried out by high-definition camera
Capture evidence obtaining.
Claims (5)
1. a kind of vehicle whistle intelligent detecting method, it is characterised in that the following steps are included:
The first step receives acoustical signal, the signal x that i-th of sonic transducer receives with air sonar sensor arrayi(t)=hi
(t)*s(t)+ni(t), i=1,2 ..., N, wherein hiIt (t) is environment impulse response between sound source and i-th of sonic transducer, s
(t) original signal, n are representedi(t) ambient noise is represented;
Second step amplifies filtering to the signal received and samples;
Third step realizes the classification of vehicle whistle signal and ambient noise by trained support vector machines;Optimal classification
Curve yi=wxi+ b, i=1...n, wherein w is optimal classification line slope, and b is optimal classification line intercept;Optimization at this time
Class problem is converted to
In formula, ξiIndicate the relaxation factor with elastic telescopic, C indicates penalty coefficient;
4th step, calculates the output power of Beam-former, changed by way of mechanical scanning signal incident angle θ find it is defeated
Angle corresponding to spectrum peak out estimates the direction of sound-source signal;
5th step realizes the positioning of illegal vehicle by Wave beam forming positioning, then carries out illegal vehicle by high-definition camera
Candid photograph evidence obtaining.
2. vehicle whistle intelligent detecting method according to claim 1, it is characterised in that: the second step is to acquisition
Signal carries out two-stage amplification, and the first order amplifies 10 times, and the gain of second level amplification is adjusted between 1,2,5,10 times.
3. vehicle whistle intelligent detecting method according to claim 1, it is characterised in that: in the third step, docking
The collection of letters number carries out a framing windowing process, extracts the following five classes acoustical signal feature for receiving signal;
(1) sub-belt energyWherein Y (ω) indicates to receive the Fourier transformation of signal, and n, m respectively indicate concern
The initial frequency and cutoff frequency of frequency band;
(2) sub-belt energy varianceWherein SiIndicate the frequency domain normalizing of i-th of subband of constant bandwidth
Change energy;
(3) the total kurtosis of frequency bandWherein δ is the standard deviation of sample data,Indicate the mean value of Y (ω);
(4) subband kurtosis mean valueWherein KiIndicate the kurtosis of i-th of subband;
(5) short-time average zero-crossing rateWherein w (n) is window
Function;
Vehicle whistle acoustical signal is denoted as ui=1, ambient noise signal is denoted as ui=-1, then haveWherein
xiFor the feature vector for receiving the composition of five acoustical signal features corresponding to signal in third step, w is the slope of optimal classification line
Matrix, b are the bias term of optimal classification line;Construction decision function w makes ui(wxi+ b) establishment of > 1;
Calculate training sample xiEuclidean distance between hyperplane | uiyi|/| | w | |, all training datas are all satisfied | uiyi
|/| | w | | >=δ, wherein δ is interval, with season δ | | w | |=1;Then solving optimal hyperlane is exactly to find the w for meeting above formula
Minimum European norm, then be converted into following optimization problem:
In formula, ξiIndicate the relaxation factor with elastic telescopic, C indicates penalty coefficient;
Several training samples are taken to repeat this step, being divided into training sample by hyperplane has whistle sound and ambient noise,
Obtain trained support vector machines.
4. vehicle whistle intelligent detecting method according to claim 3, it is characterised in that: the relaxation factor ξiIt is arrived 0
Value in 1 range;The value of penalty coefficient C is 100 or 200.
5. vehicle whistle intelligent detecting method according to claim 1, it is characterised in that: wave beam shape in the 4th step
At output end power spectrum P (θ)=E [| y (t, θ) |2]=wH(θ) Rw (θ), in formula, t is the time, and w is weighting matrix, and array element connects
Covariance matrix R=E [X (t) X of the collection of letters numberH(t)];For the array of N number of sonic transducer composition, number is received in kth packet snap
According to matrixAssuming that number of snapshots are K, total covariance matrix
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811406108.5A CN109448389B (en) | 2018-11-23 | 2018-11-23 | Intelligent detection method for automobile whistling |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811406108.5A CN109448389B (en) | 2018-11-23 | 2018-11-23 | Intelligent detection method for automobile whistling |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109448389A true CN109448389A (en) | 2019-03-08 |
CN109448389B CN109448389B (en) | 2021-09-10 |
Family
ID=65554222
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811406108.5A Active CN109448389B (en) | 2018-11-23 | 2018-11-23 | Intelligent detection method for automobile whistling |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109448389B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110136745A (en) * | 2019-05-08 | 2019-08-16 | 西北工业大学 | A kind of vehicle whistle recognition methods based on convolutional neural networks |
CN111243283A (en) * | 2019-09-27 | 2020-06-05 | 杭州爱华仪器有限公司 | Automatic recognition device and method for whistling vehicle based on acoustic array |
CN113205830A (en) * | 2021-05-08 | 2021-08-03 | 南京师范大学 | Automobile whistle recognition method based on subband spectral entropy method and PSO-GA-SVM |
CN114355289A (en) * | 2022-03-19 | 2022-04-15 | 深圳市烽火宏声科技有限公司 | Sound source positioning method, sound source positioning device, storage medium and computer equipment |
CN115234849A (en) * | 2022-06-14 | 2022-10-25 | 哈尔滨理工大学 | Pipeline leakage position positioning method based on acoustic signal processing |
CN116990755A (en) * | 2023-09-22 | 2023-11-03 | 海宁市微纳感知计算技术有限公司 | Method and system for positioning whistle sound source, electronic equipment and readable storage medium |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101377885A (en) * | 2007-08-28 | 2009-03-04 | 凌子龙 | Electronic workstation for obtaining evidence of vehicle peccancy whistle and method thereof |
CN102044244A (en) * | 2009-10-15 | 2011-05-04 | 华为技术有限公司 | Signal classifying method and device |
CN102760444A (en) * | 2012-04-25 | 2012-10-31 | 清华大学 | Support vector machine based classification method of base-band time-domain voice-frequency signal |
US20150154868A1 (en) * | 2012-07-27 | 2015-06-04 | Tomer Neuner | Intelligent state determination |
CN104916289A (en) * | 2015-06-12 | 2015-09-16 | 哈尔滨工业大学 | Quick acoustic event detection method under vehicle-driving noise environment |
CN105277921A (en) * | 2015-09-23 | 2016-01-27 | 浙江大学 | Passive acoustic source localization method based on intelligent mobile phone |
CN105810212A (en) * | 2016-03-07 | 2016-07-27 | 合肥工业大学 | Train whistle recognizing method for complex noise environment |
CN106487929A (en) * | 2016-12-09 | 2017-03-08 | 庄耿华 | A kind of vehicle-mounted rule-breaking vehicle is blown a whistle automatic detection and evidence-obtaining system |
CN106875678A (en) * | 2017-01-23 | 2017-06-20 | 上海良相智能化工程有限公司 | A kind of vehicle whistle law enforcement evidence-obtaining system |
CN108091345A (en) * | 2017-12-27 | 2018-05-29 | 东南大学 | A kind of ears speech separating method based on support vector machines |
CN108417036A (en) * | 2018-05-07 | 2018-08-17 | 北京中电慧声科技有限公司 | Vehicle whistle sound localization method and device in intelligent transportation system |
-
2018
- 2018-11-23 CN CN201811406108.5A patent/CN109448389B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101377885A (en) * | 2007-08-28 | 2009-03-04 | 凌子龙 | Electronic workstation for obtaining evidence of vehicle peccancy whistle and method thereof |
CN102044244A (en) * | 2009-10-15 | 2011-05-04 | 华为技术有限公司 | Signal classifying method and device |
CN102760444A (en) * | 2012-04-25 | 2012-10-31 | 清华大学 | Support vector machine based classification method of base-band time-domain voice-frequency signal |
US20150154868A1 (en) * | 2012-07-27 | 2015-06-04 | Tomer Neuner | Intelligent state determination |
CN104916289A (en) * | 2015-06-12 | 2015-09-16 | 哈尔滨工业大学 | Quick acoustic event detection method under vehicle-driving noise environment |
CN105277921A (en) * | 2015-09-23 | 2016-01-27 | 浙江大学 | Passive acoustic source localization method based on intelligent mobile phone |
CN105810212A (en) * | 2016-03-07 | 2016-07-27 | 合肥工业大学 | Train whistle recognizing method for complex noise environment |
CN106487929A (en) * | 2016-12-09 | 2017-03-08 | 庄耿华 | A kind of vehicle-mounted rule-breaking vehicle is blown a whistle automatic detection and evidence-obtaining system |
CN106875678A (en) * | 2017-01-23 | 2017-06-20 | 上海良相智能化工程有限公司 | A kind of vehicle whistle law enforcement evidence-obtaining system |
CN108091345A (en) * | 2017-12-27 | 2018-05-29 | 东南大学 | A kind of ears speech separating method based on support vector machines |
CN108417036A (en) * | 2018-05-07 | 2018-08-17 | 北京中电慧声科技有限公司 | Vehicle whistle sound localization method and device in intelligent transportation system |
Non-Patent Citations (2)
Title |
---|
刘若澜: "音频场景检测机制的设计与实施", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
张铁成: "基于麦克风阵列的声音识别与定位算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110136745A (en) * | 2019-05-08 | 2019-08-16 | 西北工业大学 | A kind of vehicle whistle recognition methods based on convolutional neural networks |
CN111243283A (en) * | 2019-09-27 | 2020-06-05 | 杭州爱华仪器有限公司 | Automatic recognition device and method for whistling vehicle based on acoustic array |
CN113205830A (en) * | 2021-05-08 | 2021-08-03 | 南京师范大学 | Automobile whistle recognition method based on subband spectral entropy method and PSO-GA-SVM |
CN113205830B (en) * | 2021-05-08 | 2024-05-07 | 南京师范大学 | Automobile whistle identification method based on subband spectral entropy method and PSO-GA-SVM |
CN114355289A (en) * | 2022-03-19 | 2022-04-15 | 深圳市烽火宏声科技有限公司 | Sound source positioning method, sound source positioning device, storage medium and computer equipment |
CN114355289B (en) * | 2022-03-19 | 2022-06-10 | 深圳市烽火宏声科技有限公司 | Sound source positioning method, sound source positioning device, storage medium and computer equipment |
CN115234849A (en) * | 2022-06-14 | 2022-10-25 | 哈尔滨理工大学 | Pipeline leakage position positioning method based on acoustic signal processing |
CN116990755A (en) * | 2023-09-22 | 2023-11-03 | 海宁市微纳感知计算技术有限公司 | Method and system for positioning whistle sound source, electronic equipment and readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109448389B (en) | 2021-09-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109448389A (en) | A kind of vehicle whistle intelligent detecting method | |
CN107644650B (en) | Improved sound source positioning method based on progressive serial orthogonalization blind source separation algorithm and implementation system thereof | |
CN110010147A (en) | A kind of method and system of Microphone Array Speech enhancing | |
CN106846803B (en) | Traffic event detection device and method based on audio frequency | |
Liu et al. | Wavoice: A noise-resistant multi-modal speech recognition system fusing mmwave and audio signals | |
CN101593522B (en) | Method and equipment for full frequency domain digital hearing aid | |
CN111044973B (en) | MVDR target sound source directional pickup method for microphone matrix | |
CN102682765B (en) | Expressway audio vehicle detection device and method thereof | |
CN111445920B (en) | Multi-sound source voice signal real-time separation method, device and pickup | |
CN111429939B (en) | Sound signal separation method of double sound sources and pickup | |
CN101430882B (en) | Method and apparatus for restraining wind noise | |
CN106328156A (en) | Microphone array voice reinforcing system and microphone array voice reinforcing method with combination of audio information and video information | |
CN108389586A (en) | A kind of long-range audio collecting device, monitoring device and long-range collection sound method | |
CN106782590A (en) | Based on microphone array Beamforming Method under reverberant ambiance | |
CN102819009A (en) | Driver sound localization system and method for automobile | |
CN104916289A (en) | Quick acoustic event detection method under vehicle-driving noise environment | |
CN108597505A (en) | Audio recognition method, device and terminal device | |
CN109741609B (en) | Motor vehicle whistling monitoring method based on microphone array | |
CN107167770A (en) | A kind of microphone array sound source locating device under the conditions of reverberation | |
CN103854660A (en) | Four-microphone voice enhancement method based on independent component analysis | |
CN112363112B (en) | Sound source positioning method and device based on linear microphone array | |
CN102426837B (en) | Robustness method used for voice recognition on mobile equipment during agricultural field data acquisition | |
CN109884591A (en) | A kind of multi-rotor unmanned aerial vehicle acoustical signal Enhancement Method based on microphone array | |
CN109741759A (en) | A kind of acoustics automatic testing method towards specific birds species | |
CN112394324A (en) | Microphone array-based remote sound source positioning method and system |
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 |