CN105046880B - A kind of method that intelligent mobile terminal carries out hazards monitoring and early warning based on Doppler effect - Google Patents
A kind of method that intelligent mobile terminal carries out hazards monitoring and early warning based on Doppler effect Download PDFInfo
- Publication number
- CN105046880B CN105046880B CN201510283722.7A CN201510283722A CN105046880B CN 105046880 B CN105046880 B CN 105046880B CN 201510283722 A CN201510283722 A CN 201510283722A CN 105046880 B CN105046880 B CN 105046880B
- Authority
- CN
- China
- Prior art keywords
- mrow
- mobile terminal
- sound wave
- early warning
- msub
- 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.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0438—Sensor means for detecting
- G08B21/0469—Presence detectors to detect unsafe condition, e.g. infrared sensor, microphone
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO 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
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/02—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems using reflection of acoustic waves
- G01S15/50—Systems of measurement, based on relative movement of the target
- G01S15/52—Discriminating between fixed and moving objects or between objects moving at different speeds
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO 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
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/02—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems using reflection of acoustic waves
- G01S15/50—Systems of measurement, based on relative movement of the target
- G01S15/58—Velocity or trajectory determination systems; Sense-of-movement determination systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO 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
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/88—Sonar systems specially adapted for specific applications
- G01S15/93—Sonar systems specially adapted for specific applications for anti-collision purposes
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Acoustics & Sound (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Gerontology & Geriatric Medicine (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Emergency Alarm Devices (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides a kind of method that intelligent mobile terminal carries out hazards monitoring and early warning based on Doppler effect, current research is seldom directed to use with the potential danger detection that smart machine is brought, and the existing method based on image and extras has its intrinsic limitation and deficiency.The present invention judges whether user is in away line state first with accelerometer data, surrounding environment is monitored in real time using sound Doppler effect and sound ranging afterwards, environmental information is judged whether by grader potentially dangerous, and danger is subjected to early warning according to danger classes, the presence of warning consumers risk in time, with convenience, real-time, accuracy, it is user friendly, the features such as low in energy consumption.Test result indicates that, the present invention has high accuracy and real-time, can carry out early warning to danger in time.It is believed that the present invention can play the characteristics of it is convenient, efficient, accurate, long-term and universal application is obtained in mobile hazard detection field and guide field.
Description
Technical field
The invention belongs to signal transacting, grader and sensor field, and in particular to a kind of intelligent mobile terminal is based on many
It is general to strangle the method that effect carries out hazards monitoring and early warning.
Background technology
Continuous progressive and science and technology with society is maked rapid progress, and the life style of people is constantly changed.With
Smart mobile phone is simple to operate with its for the high-performance intelligent mobile terminal of new generation of representative, and the features such as being easy to carry gives people life
Great convenience in work, in this case, people are also gradually stepped up for the degree of dependence of smart machine.On the other hand, just
It is that dependence to mobile phone causes many people to be all absorbed in mobile phone whenever and wherever possible, is also played during trip in hand, from
And it is easy to ignore potential hazards in surrounding environment due to diverting one's attention, and potential safety hazard is produced, is gently then fallen, it is heavy then occur car
Misfortune.Therefore how to be prevented effectively from due to playing mobile phone to cause to divert one's attention and occurring unexpected is urgent problem to be solved.
Traditional Environment Obstacles detection method is based primarily upon ranging technology, including laser ranging, infrared distance measuring, ultrasonic wave
Ranging etc..Such Environment Obstacles detection technique precision is high, identification is accurate, belongs to precise distance measurement, is widely used in military field, industry
Measurement and control area etc..But above ranging technology needs that specific sensor and corresponding hardware supported, cost are high, be not easy to
Body is carried, and is not suitable for the use of personal and family.
Detection of obstacles application is also occurred in that on smart machine, it is main to include two kinds of solutions.The first is direct
Ambient image is obtained by the rear camera of smart machine and then judges to whether there is in environment using computer vision technique
Barrier.This method can be judged environmental risk factors with more accurate, but its own is to equipment posture, ambient light
Source brightness and line of sight direction have very high requirement, are typically only capable to detect the barrier in bright light environments on specific direction, and
And resource consumption is big during detection, real-time is low.Be for second by smart machine additionally one laser range finder of increase or
Ultrasonic wave module obtains environmental information, is handled on smart machine, obtains the distance of barrier.This method precision is high, but
It is to need extra hardware device, portability is low.
The content of the invention
In order to solve the problems of the prior art, the present invention proposes that one kind judges to walk line state, and base using accelerometer
Ambient condition information is obtained in sound Doppler effect and sound ranging, the danger classes that combining classification device is obtained carries out early warning,
Evade people because the intelligent mobile terminal for the potential safety hazard for causing to divert one's attention to produce using mobile phone is endangered based on Doppler effect
Danger monitoring and the method for early warning.
In order to realize the above object the technical solution adopted in the present invention is:Comprise the following steps:
1) state-detection:Judge whether user is in walking states, and whether use intelligent mobile terminal equipment;
2) environmental monitoring:The time difference t of detection transmitting sound wave and reflection sound wave, calculates the distance between sound source and barrier
S, when sound source carries out relative motion with user, the acoustic vibration frequency generation frequency different from the frequency that sound source is sent that user receives
Move, the frequency shift (FS) of contrast transmitting sound wave and reflection sound wave, you can mobile object and intelligent mobile terminal in detection surrounding environment
Speed of related movement between equipment, so as to judge whether occur dangerous;
3) danger classes classification and early warning:Danger signal is determined whether by support vector machine classifier, if dangerous
Signal, then judge that dangerous degree carries out early warning and obtained after threat data, it is empty to build vector using KNN algorithms by KNN algorithms
Between model degree of danger is classified and to user's early warning.
Described step 1) in judge whether user is using according to whether lighting for intelligent mobile terminal equipment screen
Mobile phone, lights expression and uses, non-lit up to represent to be not used.
Described step 1) in judge that people is using the regular vibration of the accelerometer data of intelligent mobile terminal equipment
It is no in walking, accelerometer data microvibration near 0 under static state, data can be to shake by a relatively large margin when on foot
It is dynamic.
Described step 2) in intelligent mobile terminal equipment periodic transmission particular amplitude, frequency and sample rate sound wave,
The time difference t of detection transmitting sound wave and reflection sound wave, sound wave spread speed v=332m/s in atmosphere, so as to obtain intelligent sliding
The distance between dynamic terminal device and barrier S is:
Described step 2) in intelligent mobile terminal equipment and barrier have relative motion, the reflection sound wave and hair received
Penetrating sound wave has frequency shift (FS), and the aerial spread speed of sound wave is v=332m/s, and f is the original transmitted frequency of sound wave, is occurred
The reflection sound wave frequency of frequency displacement is f ', then user and the relative velocity v of barrier0Drawn by following formula:
Wherein ,+represent that both have close relative motion ,-represent that both have remote relative motion.
Described step 2) transmitting sound wave and reflection sound wave detection in using Butterworth LPF reduce around
Ambient noise obtains reflection sound wave.
Described step 3) in obtain threat data after, KNN algorithms are classified using vector space model, identical category
Data similarity is high, predicts that the possibility of unknown categorical data is classified by the similarity with known class data is calculated, utilizes
Hamming distances calculate Hamming distances and K in classification minimum distance, you can endangered as distance metric by majority voting
Dangerous grade.
Described step 3) obtain after danger classes, shaken according to danger classes classification is different with different intelligent mobile terminal
Intensity is to user's early warning.
Described step 3) in need Training Support Vector Machines grader, by Doppler frequency shift, obstacle distance, motion shape
State, movement velocity input grader are trained to adjust classifier parameters, when rate of accuracy reached of the grader in certain distance
Deconditioning after to threshold value.
Described SVMs builds higher-dimension hyperplane to be classified, and training grader finds optimal hyperlane, seeks
Looking for optimal hyperlane is minimized under constraints | w |, w is hyperplane method vector:
Meet yi(wxi- b) >=1, wherein 1=1 ..., n;
Use non-negative Lagrange's multiplier αiSolve:
Utilize Quadratic Programming Solution:
Corresponding xiIt is exactly supporting vector, these supporting vectors are on edge and meet yi(wxi- b)=1.
Compared with prior art, the present invention judges that user walks line state using accelerometer, and based on sound Doppler effect
Surrounding environment should be monitored in real time with sound distance-finding method, environmental information is classified using sorter model, according to danger etc.
Level carries out early warning, on the basis of special equipment is not increased additionally, realizes and is easy to carry, accuracy in detection is high, real-time is good,
It is user friendly, the features such as low in energy consumption, surrounding environment danger early warning is provided to be absorbed in the people of intelligent mobile terminal in time, and can
With further simple and reliable guide service is provided for the crowd that has visual function disorder.
Further, judge whether user uses intelligent mobile terminal using whether lighting for device screen, light table
Show and use, it is non-lit up to represent to be not used;People's body when on foot can rise and fall with paces, be shaken within the specific limits
It is dynamic.The regular vibration of accelerometer data can be for judging whether people is walking.The purpose of state-detection is to select to use
Family needs the state of risk prediction, other when etching system in a dormant state, to reduce the consumption of electricity.
Further, environmental monitoring can launch sound wave and gather reflection sound wave, and general principle is detection transmitting sound wave and anti-
The time difference of sound wave is penetrated, the distance between sound source and barrier can be calculated.Doppler effect is that sound source carries out phase with observer
During to motion, the acoustic vibration frequency generation frequency displacement different from the frequency that sound source is sent that observer receives, contrast transmitting sound wave
With the frequency shift (FS) of reflection sound wave, you can the speed of related movement in detection surrounding environment between mobile object and smart machine,
So as to judge whether occur dangerous.
Further, the noise in environment is removed using Butterworth LPF, so as to obtain reflection sound wave and carry
High accuracy.
Further, in daily life, the security threat caused by the motor vehicle of fast running is far above fixed obstacle
Threaten, on the other hand, barrier closely is also more dangerous than slightly remote barrier, so the present invention sets three kinds of danger
Dangerous grade:It is high, medium and low.The potential danger of motor vehicle in traveling is high-grade, and the fixed obstacle within 3 meters is middle grade,
Fixed obstacle within 5 meters is inferior grade.Different degrees of is dangerous with different shockproofness prompting users, and higher grade,
Vibrations are stronger.The classification of danger classes is realized by two steps.
Brief description of the drawings
Fig. 1 is system overall flow figure;
Fig. 2 is walking states overhaul flow chart;
Fig. 3 is the vibrorecord of walking states;
Fig. 4 is that Doppler and sound ranging carry out environment measuring flow chart.
Embodiment
Below in conjunction with the accompanying drawings and specific embodiment the present invention is further illustrated.
Referring to Fig. 1, the present invention comprises the following steps:
1) state-detection:Judge whether user is in walking states, and whether use intelligent mobile terminal equipment;
2) environmental monitoring:The time difference t of detection transmitting sound wave and reflection sound wave, calculates the distance between sound source and barrier
S, when sound source carries out relative motion with user, the acoustic vibration frequency generation frequency different from the frequency that sound source is sent that user receives
Move, the frequency shift (FS) of contrast transmitting sound wave and reflection sound wave, you can mobile object and intelligent mobile terminal in detection surrounding environment
Speed of related movement between equipment, so as to judge whether occur dangerous;
3) danger classes classification and early warning:Danger signal is determined whether by support vector machine classifier, if dangerous
Signal, then judge that dangerous degree carries out early warning and obtained after threat data, it is empty to build vector using KNN algorithms by KNN algorithms
Between model degree of danger is classified and to user's early warning.
Referring to Fig. 2 and Fig. 3, state-detection judges whether user is in walking states and whether uses equipment, when
User when walking using mobile phone when need carry out danger early warning.Judge whether user makes using whether lighting for device screen
With mobile phone, light expression and use, it is non-lit up to represent to be not used.People's body when on foot can rise and fall with paces, certain
In the range of vibrated.The regular vibration of accelerometer data can be for judging whether people is walking.The mesh of state-detection
Be select user need the state of risk prediction, other when etching system in a dormant state, to reduce the consumption of electricity.
Referring to Fig. 4, environmental monitoring can launch sound wave and gather reflection sound wave, and general principle is detection transmitting sound wave and anti-
The time difference of sound wave is penetrated, the distance between sound source and barrier can be calculated.Doppler effect is that sound source carries out phase with observer
During to motion, acoustic vibration frequency that observer receives is different from the frequency that sound source is sent to occur frequency displacement, contrast launch sound wave with
The frequency shift (FS) of reflection sound wave, you can the speed of related movement in detection surrounding environment between mobile object and smart machine, from
And judge whether occur dangerous., it is necessary to remove the noise in environment using bandpass filter after voice data is obtained,
So as to obtain reflection sound wave and improve the degree of accuracy.Two kinds of present invention detection is dangerous close:The active of motor vehicle in traveling is leaned on
It is near passive close with fixed barrier.Motor vehicle speed in traveling is very fast, if the frequency rise expression machine of reflection sound wave
Motor-car is just close to people, if the frequency reduction of reflection sound wave represents motor vehicle from people.Due to the hair during motor-driven vehicle going
Motivation and tire and the frequency that pavement friction is produced are relatively low, and the present invention launches 1500Hz sound using smart machine, receive
Its reflection sound wave.If motor vehicle speed is 15m/s, the Doppler frequency shift of generation is about Δ f=67Hz, easily detection.Due to
The potential danger of motor vehicle around user in any direction appearance traveling is all very high, as long as being approached so detecting by motor vehicle
Early warning just is carried out to user.For fixed obstacle, the average speed of people's walking is generally 1.5m/s, the Doppler now occurred
Frequency displacement Δ f=1.5Hz, frequency change is smaller, it is not easy to detect, so obtaining the distance of barrier using distance measuring method.People
In outdoor walking, ranging can mainly detect the barrier of four direction all around, in order to distinguish whether barrier is in
In front of user, the present invention retains the historical information of the obstacle distance detected, by the distance of newest detection and historical information ratio
Compared with.If one group of range information is held essentially constant, illustrate that it represents user and the distance of the barrier similar to wall, because
Advancing for user, so wall is in the left side or the right of user, the two directions are all without causing danger.If one group
Range information becomes larger, and illustrates user away from this barrier, and this barrier in after one's death, does not result in danger
Danger.If one group of range information is tapered into, illustrate that user is just moving closer to the barrier, now need to user's early warning.This
The barrier that user or so and rear are rejected by this method is invented, barrier and the early warning in front is only focused on.
Danger classes classification determines dangerous degree.In daily life, the safe prestige caused by the motor vehicle of fast running
The side of body is far above the threat of fixed obstacle, and on the other hand, barrier closely is also more dangerous than slightly remote barrier,
So the present invention sets three kinds of danger classes:It is high, medium and low.The potential danger of motor vehicle in traveling is high-grade, within 3 meters
Fixed obstacle be that fixed obstacle within middle grade, 5 meters is inferior grade.Different degrees of danger is strong with different vibrations
Degree reminds user, and higher grade, shakes stronger.The classification of danger classes is realized by two steps.Pass through SVMs point first
Class device determines whether danger signal, and because SVMs is typically used as two-value classification, filtering out dangerous signal can be with
The efficiency of raising system.If dangerous signal, judge that dangerous degree carries out early warning by KNN algorithms.
Specific implementation step is as follows:
Step 1: state-detection:
1. user installation hazards monitoring system;
2. system dormancy;
If 3. screen is lighted, jumping to 4, otherwise jumping to 2;
4. background thread is waken up, accelerometer data is collected;
5. accelerometer data is removed into denoising by low pass filter;
6. judged whether by sliding window in walking;
7. if it is determined that user jumps to 8 in walking, otherwise jump to 2;
If 8. screen is closed, jumping to 2, otherwise jumping to step 2.
Step 2: environmental monitoring:
1. original sound data is launched and gathered:Launch fixed frequency, amplitude and sample rate using smart machine audio amplifier
Sound wave, while collecting sound wave using sound receiver;
2. bandpass filtering:The sonic data of collection is subjected to noise reduction by Butterworth filter, transmitting sound wave is obtained
Reflection sound wave;
3. extracting doppler information and range information, step 3 is jumped to.
Step 3: danger classes is classified:
1. carry out Experiment Training grader before system issue;
2. by Doppler frequency shift, obstacle distance, motion state, movement velocity input grader are trained and divided with adjusting
Class device parameter;
3. deconditioning after rate of accuracy reached of the grader in certain distance is to threshold value;
4. be judged as danger for being classified device, high, medium and low three danger etc. is classified as using KNN algorithms
Level;
5. vibrations early warning is carried out to user according to different danger classes.
The present invention is specifically included:
1. state-detection
Device screen lights wake-up system, collects accelerometer data.Body can rise and fall with paces when on foot, show
It is the vibration of numerical value on accelerometer data.Referring to Fig. 3, accelerometer numerical value microvibration near 0 under static state,
Numerical value can be to vibrate by a relatively large margin when on foot;
Using this feature, it is 20 to set sliding window size, first that numerical value is negative to remove plus the absolute value of minimum value
Number, the average value M and variance S in calculation window afterwards.If M < 3S, are judged as walking line state.
2. bandpass filtering noise reduction
The recorder of existing smart mobile phone all has decrease of noise functions, and because model is different, noise reduction is also not quite similar.Sound
Ripple detection environment needs to reduce the ambient noise of surrounding, and the present invention selects Butterworth filter, is characterized in passband
Frequency response curve it is most smooth, do not rise and fall, it is zero that suppressed frequency band, which is gradually reduced,.
Butterworth LPF can use square representing the formula of frequency for following amplitude:
Wherein n represents the exponent number of wave filter.The present invention is from 3 exponent numbers as wave filter, now suppressed frequency band fall off rate
It hurry up, meet filtering requirements.Ambient noise is generally high-frequency noise, and people around speaks noise for 500-700Hz, and detection frequency of sound wave exists
1500Hz or so, therefore present invention design Butterworth digital band-pass filter, band connection frequency 1200-1600Hz, the stopband upper limit
Frequency 1700Hz, stopband lower frequency limit 1100Hz, pass band damping are less than 1dB, and stopband maximum attenuation is more than 20dB, sample rate
2000Hz.By bandpass filter, most of noise can be filtered out, to obtain target sound waves.The intensity (amplitude) of sound wave exists
Being propagated in air to decay, and unifrequency sound is compared with long-distance communications, and sound pressure level L decay (acoustic pressure takes log) is substantially line
Property, i.e.,
L=as
Wherein s is distance, and a is attenuation coefficient, can be tabled look-up and obtained according to temperature humidity frequency.By detecting acoustic pressure and frequency
Rate, can obtain reflection sound wave.
3. sound ranging
The sound wave of smart machine periodic transmission particular amplitude, frequency and sample rate, detection transmitting sound wave and reflection sound wave
Time difference t, sound wave spread speed v=332m/s in atmosphere, can be with the distance between computational intelligence equipment and barrier S
For:
4. Doppler effect
When Doppler effect refers to that smart machine and barrier have relative motion, the reflection sound wave received and transmitting sound wave
There is certain frequency shift (FS) phenomenon.General principle is if user has relative velocity v with barrier0, sound wave is aerial
Spread speed is v=332m/s, and f is the original transmitted frequency of the sound wave, then the reflection sound wave frequency f' for occurring frequency displacement is:
Wherein ,+represent that both have close relative motion ,-represent that both have remote relative motion.
Relative velocity v between smart machine and barrier0For:
Wherein ,-represent that both have close relative motion ,+represent that both have remote relative motion.
5. Training Support Vector Machines grader
SVMs builds one or more higher-dimension hyperplane to be classified, and hyperplane is classification boundaries.Classification
Device training is exactly to find optimal hyperlane.Find optimal hyperlane be under constraints minimize | w |, w be hyperplane method to
Amount:
Meet yi(wxi- b) >=1, wherein i=1 ..., n.
Use non-negative Lagrange's multiplier αiSolve:
Utilize Quadratic Programming Solution:
Corresponding xiIt is exactly supporting vector, these supporting vectors are on edge and meet
yi(wxi- b)=1
6. carry out danger classes classification using KNN
Obtain after threat data, its degree of danger is classified using KNN.KNN is classified using vector space model,
The data similarity of identical category is high.Unknown categorical data can be predicted by the similarity with known class data is calculated
May classification.Distance metric is used as by the use of Hamming distances.Hamming distances are calculated with K in classification (by evolving by majority voting
Algorithm obtains K for 3) individual minimum distance, you can obtain danger classes belong to it is high, medium and low which kind of, and according to classification it is different with
Different shockproofnesses are to user's early warning.
Claims (9)
1. a kind of method that intelligent mobile terminal carries out hazards monitoring and early warning based on Doppler effect, it is characterised in that including
Following steps:
1) state-detection:Judge whether user is in walking states, and whether use intelligent mobile terminal equipment;
2) environmental monitoring:The time difference t of detection transmitting sound wave and reflection sound wave, calculates the distance between sound source and barrier S, sound
When source carries out relative motion with user, the acoustic vibration frequency generation frequency displacement different from the frequency that sound source is sent that user receives is right
Than the frequency shift (FS) of transmitting sound wave and reflection sound wave, you can in detection surrounding environment mobile object and intelligent mobile terminal equipment it
Between speed of related movement so that judge whether i.e. by it is dangerous occur;
3) danger classes classification and early warning:Danger signal is determined whether by support vector machine classifier, if dangerous signal,
Then judge that dangerous degree carries out early warning and obtained after threat data by KNN algorithms, KNN algorithms are divided using vector space model
Class, the data similarity of identical category is high, and unknown categorical data is predicted by the similarity with known class data is calculated
May classification, by the use of Hamming distances as distance metric, by majority voting calculate Hamming distances with classification K minimum away from
From, you can danger classes is obtained, and to user's early warning.
2. a kind of intelligent mobile terminal according to claim 1 carries out the side of hazards monitoring and early warning based on Doppler effect
Method, it is characterised in that:Described step 1) in judge user whether just according to whether lighting for intelligent mobile terminal equipment screen
Mobile phone is being used, expression is being lighted and uses, it is non-lit up to represent to be not used.
3. a kind of intelligent mobile terminal according to claim 2 carries out the side of hazards monitoring and early warning based on Doppler effect
Method, it is characterised in that:Described step 1) in sentenced using the regular vibration of the accelerometer data of intelligent mobile terminal equipment
Whether disconnected people is in walking.
4. a kind of intelligent mobile terminal according to claim 1 carries out the side of hazards monitoring and early warning based on Doppler effect
Method, it is characterised in that:Described step 2) in intelligent mobile terminal equipment periodic transmission particular amplitude, frequency and sample rate
The time difference t, sound wave spread speed v=332m/s in atmosphere, so as to obtain intelligence of sound wave, detection transmitting sound wave and reflection sound wave
Can the distance between mobile terminal device and barrier S be:
5. a kind of intelligent mobile terminal according to claim 4 carries out the side of hazards monitoring and early warning based on Doppler effect
Method, it is characterised in that:Described step 2) in intelligent mobile terminal equipment and barrier have relative motion, the reflected sound received
Ripple has frequency shift (FS) with transmitting sound wave, and the aerial spread speed of sound wave is v=332m/s, and f is the original transmitted frequency of sound wave
Rate, the reflection sound wave frequency for occurring frequency displacement is f ', then user and the relative velocity v of barrier0Drawn by following formula:
Wherein ,+represent that both have close relative motion ,-represent that both have remote relative motion.
6. a kind of intelligent mobile terminal according to claim 5 carries out the side of hazards monitoring and early warning based on Doppler effect
Method, it is characterised in that:Described step 2) transmitting sound wave and reflection sound wave detection in using Butterworth LPF drop
Low ambient noise obtains reflection sound wave.
7. a kind of intelligent mobile terminal according to claim 1 carries out the side of hazards monitoring and early warning based on Doppler effect
Method, it is characterised in that:Described step 3) obtain after danger classes, moved eventually with different intelligent according to danger classes classification is different
Shockproofness is held to user's early warning.
8. a kind of intelligent mobile terminal according to claim 7 carries out the side of hazards monitoring and early warning based on Doppler effect
Method, it is characterised in that:Described step 3) in need Training Support Vector Machines grader, by Doppler frequency shift, obstacle distance,
Motion state, movement velocity input grader are trained to adjust classifier parameters, when standard of the grader in certain distance
True rate reaches deconditioning after threshold value.
9. a kind of intelligent mobile terminal according to claim 8 carries out the side of hazards monitoring and early warning based on Doppler effect
Method, it is characterised in that:Described SVMs builds higher-dimension hyperplane to be classified, and training grader finds optimal super flat
Face, finding optimal hyperlane is minimized under constraints | w |, w is hyperplane method vector:
<mrow>
<mi>arg</mi>
<mi> </mi>
<msub>
<mi>min</mi>
<mrow>
<mi>w</mi>
<mo>,</mo>
<mi>b</mi>
</mrow>
</msub>
<mfrac>
<mrow>
<mo>|</mo>
<mo>|</mo>
<mi>w</mi>
<mo>|</mo>
<msup>
<mo>|</mo>
<mn>2</mn>
</msup>
</mrow>
<mn>2</mn>
</mfrac>
</mrow>
Meet yi(wxi- b) >=1, wherein i=1 ..., n;
Use non-negative Lagrange's multiplier αiSolve:
<mrow>
<mi>arg</mi>
<mi> </mi>
<msub>
<mi>min</mi>
<mrow>
<mi>w</mi>
<mo>,</mo>
<mi>b</mi>
</mrow>
</msub>
<msub>
<mi>max</mi>
<mrow>
<mi>&alpha;</mi>
<mo>&GreaterEqual;</mo>
<mn>0</mn>
</mrow>
</msub>
<mo>{</mo>
<mfrac>
<mn>1</mn>
<mn>2</mn>
</mfrac>
<mo>|</mo>
<mo>|</mo>
<mi>w</mi>
<mo>|</mo>
<msup>
<mo>|</mo>
<mn>2</mn>
</msup>
<mo>-</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
<mo>&lsqb;</mo>
<msub>
<mi>y</mi>
<mi>i</mi>
</msub>
<mrow>
<mo>(</mo>
<msub>
<mi>wx</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mi>b</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mn>1</mn>
<mo>&rsqb;</mo>
<mo>}</mo>
</mrow>
Utilize Quadratic Programming Solution:
<mrow>
<mi>w</mi>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
<msub>
<mi>y</mi>
<mi>i</mi>
</msub>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
</mrow>
Corresponding xiIt is exactly supporting vector, these supporting vectors are on edge and meet yi(wxi- b)=1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510283722.7A CN105046880B (en) | 2015-05-28 | 2015-05-28 | A kind of method that intelligent mobile terminal carries out hazards monitoring and early warning based on Doppler effect |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510283722.7A CN105046880B (en) | 2015-05-28 | 2015-05-28 | A kind of method that intelligent mobile terminal carries out hazards monitoring and early warning based on Doppler effect |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105046880A CN105046880A (en) | 2015-11-11 |
CN105046880B true CN105046880B (en) | 2017-10-20 |
Family
ID=54453390
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510283722.7A Expired - Fee Related CN105046880B (en) | 2015-05-28 | 2015-05-28 | A kind of method that intelligent mobile terminal carries out hazards monitoring and early warning based on Doppler effect |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105046880B (en) |
Families Citing this family (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105761423B (en) * | 2016-02-04 | 2018-04-06 | 合肥联宝信息技术有限公司 | Detect the device and method of the behavior of the user of hand-held electronic equipment |
US9919647B2 (en) * | 2016-05-02 | 2018-03-20 | Ford Global Technologies, Llc | Intuitive haptic alerts |
CN107437322A (en) * | 2016-05-25 | 2017-12-05 | 北京京东尚科信息技术有限公司 | Mobile terminal, mobile terminal hazards monitoring device and method |
CN106161786A (en) * | 2016-06-28 | 2016-11-23 | 李玉婷 | A kind of walking uses mobile phone householder method and device |
CN106254667A (en) * | 2016-08-24 | 2016-12-21 | 维沃移动通信有限公司 | A kind of method of prompting and mobile terminal |
CN106534523A (en) * | 2016-10-28 | 2017-03-22 | 维沃移动通信有限公司 | Mobile terminal danger early-warning method, and mobile terminal |
TWI633323B (en) * | 2017-07-28 | 2018-08-21 | 宏碁股份有限公司 | Distance detection device and distance detection method thereof |
CN107544803B (en) * | 2017-08-31 | 2020-08-21 | 努比亚技术有限公司 | Ultrasonic wave-based on-off screen control method and device and readable storage medium |
CN107526072B (en) * | 2017-08-31 | 2021-09-21 | 努比亚技术有限公司 | Displacement calculation method and device based on ultrasonic waves and computer-readable storage medium |
CN107610528A (en) * | 2017-10-09 | 2018-01-19 | 上海闻泰电子科技有限公司 | The dangerous system for prompting of road conditions and equipment |
CN107908275A (en) * | 2017-11-30 | 2018-04-13 | 北京小米移动软件有限公司 | Control method, mobile terminal and the storage medium of mobile terminal |
CN108562890B (en) * | 2017-12-29 | 2023-10-03 | 努比亚技术有限公司 | Method and device for calibrating ultrasonic characteristic value and computer readable storage medium |
CN108196544A (en) * | 2018-01-02 | 2018-06-22 | 联想(北京)有限公司 | A kind of information processing method and information processing equipment |
CN111724643A (en) * | 2018-06-21 | 2020-09-29 | 林泽和 | Blind person directional training device and method for simulating outdoor danger avoidance based on Doppler effect |
TWI672679B (en) * | 2018-08-22 | 2019-09-21 | 香港商冠捷投資有限公司 | Handheld electronic device and object distance sensing module |
CN109507678B (en) * | 2018-11-26 | 2023-02-03 | 广东小天才科技有限公司 | Reminding method, system, equipment and storage medium for road surface danger avoidance |
CN109637089A (en) * | 2019-01-08 | 2019-04-16 | 合肥鑫晟光电科技有限公司 | The method for early warning and device of user security |
CN109949541B (en) * | 2019-04-03 | 2020-12-11 | 新沂市锡沂高新材料产业技术研究院有限公司 | Intelligent trip early warning system |
CN110175570A (en) * | 2019-05-28 | 2019-08-27 | 联想(北京)有限公司 | A kind of information indicating method and system |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100582679C (en) * | 2008-04-22 | 2010-01-20 | 东南大学 | Broad domain all-optical fiber disturbance sensing network system self-adapting disturbance signal processing recognition device |
CN102523323A (en) * | 2011-12-27 | 2012-06-27 | 东莞华贝电子科技有限公司 | Mobile terminal and barrier alarm method |
CN103152483B (en) * | 2013-03-04 | 2015-07-08 | 广东欧珀移动通信有限公司 | Method and device for monitoring approaching object by using mobile device |
CN104378494A (en) * | 2013-08-16 | 2015-02-25 | 联想移动通信科技有限公司 | Reminding method and mobile terminal |
CN104280736A (en) * | 2014-09-24 | 2015-01-14 | 天津三星电子有限公司 | Mobile terminal and prompting method |
-
2015
- 2015-05-28 CN CN201510283722.7A patent/CN105046880B/en not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
CN105046880A (en) | 2015-11-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105046880B (en) | A kind of method that intelligent mobile terminal carries out hazards monitoring and early warning based on Doppler effect | |
US9618611B2 (en) | Personal radar assistance | |
US10036809B2 (en) | Real-time warning for distracted pedestrians with smartphones | |
US9488724B2 (en) | Method for multi-mode obstacle detection using radar, and apparatus for same | |
Wen et al. | We help you watch your steps: Unobtrusive alertness system for pedestrian mobile phone users | |
CN108371545B (en) | Human body arm action sensing method based on Doppler radar | |
CN105677039A (en) | Method, device and wearable device for gesture-based driving status detection | |
CN104135911A (en) | Activity classification in a multi-axis activity monitor device | |
CN105049589A (en) | Handset device used for improving personal safety and early warning method | |
CN203786851U (en) | Novel pickup alarm | |
CN105632187B (en) | Low-power consumption curb parking detection method based on geomagnetic sensor network | |
Li et al. | Auto++ detecting cars using embedded microphones in real-time | |
US20170154521A1 (en) | Methods and systems for providing personal emergency alerts and context aware activity notifications | |
CN109965889B (en) | Fatigue driving detection method by using smart phone loudspeaker and microphone | |
CN112163280B (en) | Method, device and equipment for simulating automatic driving scene and storage medium | |
WO2018086471A1 (en) | Navigation method and device, terminal and storage medium | |
CN107305772A (en) | For providing the method for sound detection information, device and vehicle including the device | |
CN108279671A (en) | Environment perception method, device based on Terahertz and computer readable storage medium | |
KR102060286B1 (en) | Radar object detection threshold value determination method using image information and radar object information generation device using the same | |
CN112595728B (en) | Road problem determination method and related device | |
US20210270936A1 (en) | Method and apparatus of radar-based activity detection | |
CN113449711A (en) | Micro Doppler image sign language perception identification method based on direction density characteristics | |
CN111638522B (en) | Proximity detection method and electronic device | |
KR20160044528A (en) | Influence of line of sight for driver safety | |
CN106203282A (en) | A kind of fingerprint image processing method and terminal |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20171020 Termination date: 20210528 |