CN106686341A - Interactive vehicle-mounted intelligent terminal system and monitoring method - Google Patents
Interactive vehicle-mounted intelligent terminal system and monitoring method Download PDFInfo
- Publication number
- CN106686341A CN106686341A CN201510746944.8A CN201510746944A CN106686341A CN 106686341 A CN106686341 A CN 106686341A CN 201510746944 A CN201510746944 A CN 201510746944A CN 106686341 A CN106686341 A CN 106686341A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- module
- barrier
- distance
- straight line
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses an interactive vehicle-mounted intelligent terminal system and a monitoring method. The system comprises a vehicle-mounted terminal and a plurality of double-camera systems. The vehicle-mounted terminal comprises a core processor, a voice broadcasting module, and a display module. The core processor comprises a video collection module which is used for obtaining a video image; a data processing module which is used for obtaining image data from the video image, and calculating the distance between a vehicle and an obstacle and the size of the obstacle according to the image data when the vehicle is at a running stage; or calculating the distance between the vehicle and a lane line according to the image data when the vehicle is at a backing-up stage; and a voice broadcast module which is used for broadcasting the size of the obstacle and the distance between the vehicle and the obstacle when the vehicle is at the running stage or broadcasting the distance between the vehicle and the lane line according to the image data when the vehicle is at the backing-up stage. The beneficial effects of the invention are that the method can achieve the voice broadcasting of the size of the obstacle and the distance between the obstacle and the vehicle, and also can achieve the effective communication with a driver.
Description
Technical field
The present invention relates to communication technical field, more particularly, it relates to a kind of interactive vehicle intelligent terminal system and monitoring method.
Background technology
At present, with the propulsion and the improvement of people's living standards of urbanization, car owning amount constantly rises, the traffic safety of automobile, and peripheral vehicle environmental monitoring problem increasingly causes the concern of masses.Driver obtains and the more interactive mode of hommization to the real time information of vehicle-surroundings environment during in order to solve vehicle driving, and people take many means.Wherein, the equipment such as drive recorder, vehicle-mounted pick-up head system, are that driver's acquisition peripheral vehicle environmental information is made that certain contribution.
Existing vehicle-mounted terminal system be embodied as and performance in terms of, remain in all many defects：Main performance is as follows：1) existing vehicle-mounted pick-up head system is mainly fixed on the tailstock or Chinese herbaceous peony mostly for the application in terms of vehicle backing backsight monitoring, and its visible angle is little, also needs by rearview mirror and driver；2) existing vehicle-mounted pick-up head system does not also have the application of motion detection peripheral obstacle, and its intellectuality also needs to improve；3) existing car-mounted terminal broadcasting system mainly also focuses on the report of moving traffic environment, for intelligentized vehicle-surroundings can or the report of environmental information be still unsatisfactory for.
The content of the invention
The technical problem to be solved in the present invention is, for the drawbacks described above of prior art, there is provided a kind of to realize when driving carrying out vehicle periphery omnibearing video monitoring and the interactive vehicle intelligent terminal system and monitoring method to the intelligent interaction of vehicle-surroundings environment.
The technical solution adopted for the present invention to solve the technical problems is：Construct a kind of interactive vehicle intelligent terminal system, it includes that a car-mounted terminal, multiple dual camera systems, the dual camera system are separately mounted to Chinese herbaceous peony, the tailstock and car side, the car-mounted terminal includes core processor and the voice broadcast module being connected with the core processor respectively and display module, wherein：The core processor includes：
Video acquisition module：It is connected with each dual camera system, for obtaining video image and being shown by the display module；
Data processing module, is connected with the video acquisition module, for obtaining view data from the video image, and when vehicle is in the traveling stage according to the distance and barrier size between described image data calculating vehicle and barrier；Or calculate the distance between vehicle and parking stall line according to described image data when vehicle is in the reversing stage；
The voice broadcast module is connected with the data processing module, and for reporting barrier size and the distance between vehicle and barrier when vehicle is in the traveling stage, or the distance between vehicle and parking stall line is reported when vehicle is in the reversing stage.
In above-mentioned interactive vehicle intelligent terminal system, the car-mounted terminal also includes：
Voice input module, for receiving the voice signal of driver's input；
Sound identification module, is connected with the voice input module and is identified for the voice signal to receiving；
The core processor also includes speech processing module, it is connected with the sound identification module and the data processing module respectively, and for being analyzed to obtain operator demand to the speech recognition signal received from the sound identification module, and from calling system data in the data processing module obtaining corresponding driver's information needed and be reported by the voice broadcast module.
In above-mentioned interactive vehicle intelligent terminal system, the core processor also includes cloud service module, for receiving the view data in the data processing module, and described image data is presented eventually through user terminal.
In above-mentioned interactive vehicle intelligent terminal system, the car-mounted terminal also includes the communication module being connected with the data processing module, for vehicle when by external impact, sends information to the user terminal.
In above-mentioned interactive vehicle intelligent terminal system, the interactive vehicle intelligent terminal system also includes the power module for power supply.
A kind of monitoring method is also provided, based on above-mentioned interactive vehicle intelligent terminal system, the monitoring method includes：
S1, by dual camera system obtain video image；
S2, view data is obtained from the video image, and distance and barrier size between vehicle and barrier are calculated when vehicle is in the traveling stage, or the distance between vehicle and parking stall line is calculated when vehicle is in the reversing stage；
S3, when vehicle is in the traveling stage distance between voice broadcast barrier size and vehicle and barrier, or the distance between voice broadcast vehicle and parking stall line when vehicle is in attached section of reversing.
In above-mentioned monitoring method, when vehicle is in the traveling stage, step S2 includes：
The view data of S21, foundation barrier P dual camera systems corresponding to the acquisition of the position relationship of vehicle；
S22, the vector representation for setting two straight lines L1 and L2 are as follows：L1=r1+tv1And L2=r2+sv2；
Wherein：Straight line L1 is projected to the straight line formed between the point on the camera perspective plane by the photocentre and barrier P of one of camera in corresponding dual camera system；Straight line L2 is projected to the straight line formed between the point on the camera perspective plane by the photocentre and barrier P of another camera；The amount of being biased towards,It is unit direction vector；S and t are parametric variables；
S23, distances of the barrier P apart from vehicle is calculated, computational methods are as follows：If A is straight line L1On point, coordinate be (x1+m1t,y1+n1t,z1+p1t)；
B is straight line L2On point, coordinate be (x2+m2s,y2+n2s,z2+p2s)；
If the distance of A to B is d, then
d2=[(x1+m1t)-(x2+m2s)]2+[(y1+n1t)-(y2+n2s)]2+[(z1+p1t)-(z2+p2s)]2, it meets equation below：
Calculate and causeWithS and t values it is as follows：
Wherein：C=m1m2+n1n2+p1p2,
E=m2(x2-x1)+n1(y2-y1)+p1(z2-z1), f=m1(x1-x2)+n1(y1-y2)+p1(z1-z2)
S and t are substituted into respectively straight line L1With straight line L2Parametric equation obtain intersection point coordinate be (x1+m1t,y1+n1t,z1+p1T) with (x2+m2s,y2+n2s,z2+p2s)；
The distance between barrier P and vehicle are：
In above-mentioned monitoring method, the monitoring method also includes：
Receive the voice signal of driver's input；
Voice signal to receiving is identified；
To speech recognition signal analysis to obtain operator demand, and from data processing module calling system data obtaining corresponding driver's information needed.
Implement the interactive vehicle intelligent terminal system and monitoring method of the present invention, have the advantages that：The system adopts dual camera system, and it is separately mounted to Chinese herbaceous peony, the tailstock and car side, can omnibearing video monitoring be carried out to vehicle periphery to check outside vehicle environment, and by the data acquisition module in core processor by the transmission of video images for getting to data processing module, data processing module is analyzed to the view data for getting and processes and calculate barrier size and its distance between vehicle when vehicle is in the traveling stage, reported by voice broadcast module simultaneously, to help driver to avoid bumping against or abrading people around or thing.
Description of the drawings
Below in conjunction with drawings and Examples, the invention will be further described, in accompanying drawing：
Fig. 1 is a kind of structured flowchart of interactive vehicle intelligent terminal system embodiment of the present invention；
Fig. 2 is a kind of workflow diagram of interactive vehicle intelligent terminal system embodiment of the present invention；
Fig. 3 is barrier P space projection schematic diagrames；
Fig. 4 is the schematic flow sheet of the size that a kind of interactive vehicle intelligent terminal system embodiment of the present invention calculates barrier P.
Specific embodiment
In order to be more clearly understood to the technical characteristic of the present invention, purpose and effect, the specific embodiment that accompanying drawing describes the present invention in detail is now compareed.
As shown in Figure 1, for a kind of structured flowchart of interactive vehicle intelligent terminal system embodiment of the present invention, in the present embodiment, the interactive vehicle intelligent terminal system includes a car-mounted terminal (not shown), multiple dual camera systems 10, the car-mounted terminal is arranged on vehicle interior, multiple dual camera systems 10 are separately mounted to Chinese herbaceous peony, the tailstock and car side, to carry out omnibearing video monitoring to vehicle periphery, the dual camera system 10 is equipped with compact hardware circuit with stabilized power source supply and video acquisition, so that vehicle can also obtain stably clear accessible video flowing during Fast marching.Especially, the car-mounted terminal specifically includes core processor 11 and the voice broadcast module 12 that is connected with the core processor 11 respectively and display module 13, and core processor 11 includes video acquisition module 111 and data processing module 112 again.
Video acquisition module 111 is connected with each dual camera system 10, to complete acquisition of the external camera to video image；Data processing module 112 is connected with the video acquisition module 111, and it is mainly used in that view data is obtained from video image and these data are processed, including finds range and survey size and carry out fusion treatment etc. to video image.Specifically, as shown in Figure 2, when vehicle is in the traveling stage, retrieve for examination vehicle periphery panorama monitoring video image, retrieve for examination the video image collected installed in all dual camera systems of Chinese herbaceous peony, car side and the tailstock, if it was found that there is barrier, data processing module 111 calculates the distance between vehicle and barrier and barrier size according to acquired view data；When vehicle is in the reversing stage, the video image that the dual camera system installed in car side and the tailstock is collected is retrieved for examination, the distance between vehicle and parking stall line are calculated according to acquired view data.
Voice broadcast module 12 is connected with data processing module 112, it is used for when vehicle is in the traveling stage, have outside vehicle barrier when monitoring, system automatic information broadcast is being reminded, simultaneously the barrier size and distance away from the car are reported, to help driver to avoid people around or thing are bumped against or abrade；When vehicle is in reversing stage warehouse-in, the distance between voice broadcast vehicle and parking stall line, as shown in Figure 2.
Above-mentioned display module 13 is connected with video acquisition module 111, is mainly useful in vehicular motion showing the video image of surrounding enviroment, and it directly can directly be shown using the liquid crystal indicator of vehicle interior, be simple liquid crystal apparatus；Also can be shown using touch display device.
Especially, above-mentioned data processing module 112 is to recognize that location algorithm calculates the distance between the distance between barrier and vehicle and vehicle and parking stall line by intelligent video, it is based on the realization of bionic binocular positioning mode, multiple dual camera systems realize the measurement with vehicle distances and article size by algorithm by the form for positioning two-by-two.
Here as a example by calculating the distance between barrier and vehicle when vehicle was expert at into the stage, it is understandable that, when barrier and vehicle are close, or when in the detectable scope of camera, data processing module 112 can be processed the view data for getting, and according to barrier before vehicle periphery, afterwards, it is left, right direction, to calculate the dual camera camera system 10 with a distance from vehicle respective direction, such as camera detects the barrier in vehicle front, then the view data acquired in 112 pairs of dual camera systems for being arranged on Chinese herbaceous peony of data processing module is processed, calculate this and be arranged on the distance between dual camera system and barrier of Chinese herbaceous peony, i.e. only with the distance between one dual camera system of calculating and barrier, the installation direction of the dual camera system is identical from car direction with the barrier for detecting.
Specifically, the process of the range finding of data processing module 112 is as follows：
First, if barrier is P, dual camera head system C is projected toiPoint coordinates on perspective plane is pi；To some camera Ci, it is determined that photocentre OiWith the point p of perspective plane (on image)i, then it is possible to project to piThe set of spatial point be at straight line Oi-piOn；That is P is necessarily in straight line Oi-piOn, this straight line is referred to as polar curve.
To dual camera system, spatial point P must be in straight line Oi-pi(i=1,2) on, that is, calculate all straight line Oi-pi(i=1,2) intersection point.Actually due to the generation of error, possible straight line Oi-piDeviation can occur, cause these straight lines all not intersect.As shown in figure 3, straight line p1p2It is two straight line L1And L2Most short vertical line, its distance as two straight lines distance, here straight line L1 the straight line formed between the point on the camera perspective plane is projected to by the photocentre and barrier P of one of camera in corresponding dual camera system；Straight line L2 is projected to the straight line formed between the point on the camera perspective plane by the photocentre and barrier P of another camera.
Consider that deviation is small, if two straight line antarafacials；To straight line L1For, the physical location of spatial point should be near the intersection point p of most short vertical line1；In the same manner, for straight line L2, the physical location of spatial point should be near the intersection point p of most short vertical line2.To n bar straight lines, each straight line has n-1 intersection point, and these intersection points reflect the information of the physical location of spatial point, is rational using the physical location of these information estimation space points, and simplest method is exactly the central point for taking these intersection points.The intersection point for seeking two straight lines is thus converted into the intersection point for seeking the most short vertical line of two straight lines, in the present embodiment, the intersection point of two straight lines is to being unique.
The most short vertical line of two straight lines, is the beeline of two Points on Straight Line, then by the beeline between the point for finding two straight lines, can obtain the position of intersection point.
The intersection point for seeking two straight lines is thus converted into the problem for seeking two straight line beelines, intersection point point is found by extremum method in the present embodiment.
If the vector representation of two straight lines L1 and L2 is as follows：L1=r1+tv1And L2=r2+sv2, whereinThe amount of being biased towards,It is unit direction vector；S and t are parametric variables；
If A is straight line L1On point, coordinate be (x1+m1t,y1+n1t,z1+p1t)；
B is straight line L2On point, coordinate be (x2+m2s,y2+n2s,z2+p2s)；
If the distance of A to B is d, then
d2=[(x1+m1t)-(x2+m2s)]2+[(y1+n1t)-(y2+n2s)]2+[(z1+p1t)-(z2+p2s)]2
The value of s and t is now sought so that d2Value it is minimum, that is, ask so that d2Single order local derviation be 0, second order local derviation more than 0 s and t values, it meets equation below：
Due toWithThen d2Only minimum of a value, does not have maximum；Calculate and causeWithS and t values it is as follows：
Wherein,
C=m1m2+n1n2+p1p2,
E=m2(x2-x1)+n1(y2-y1)+p1(z2-z1), f=m1(x1-x2)+n1(y1-y2)+p1(z1-z2)
S and t are substituted into respectively straight line L1With straight line L2Parametric equation obtain intersection point coordinate be (x1+m1t,y1+n1t,z1+p1T) with (x2+m2s,y2+n2s,z2+p2s)；The approximation of two straight-line intersections, as physical locations of the barrier P in space coordinates can be obtained according to the two intersection point coordinates afterwards, this approximation is to take the midrange between two intersection points.That is barrier P actual coordinates of spatial point in the dual camera system are：
And camera photocentre is space initial point, i.e., (0,0,0).So as to the distance between the distance between, barrier P and the dual camera system namely barrier P and vehicle are：
It is understood that when vehicle is in the reversing stage, needing to calculate the distance between dual camera system 10 and parking stall line after car here, its calculating process is similar to the above, simply parking stall line is regarded as into P points and is calculated, and will not be described here.
Additionally, the measurement of the outer article size of car takes the method for the existing feedback background segment method based on self adaptation blocks of pixels to realize.Its calculating process is as shown in Figure 4, the dual camera system 10 of vehicle side is detected after barrier P, due to the travel speed disunity of the movement velocity or vehicle itself of barrier P, therefore the view data of barrier P is read in units of 1 frame, the image of acquisition is processed in the short period of time, obtain initial point and X, the information of Y-axis of barrier P, finally, by existing algorithm-determine the block diagram size of barrier P, the i.e. size of barrier P based on the feedback background segment method of self adaptation blocks of pixels.
Especially, the system can also recognize the voice messaging of driver by introducing speech recognition technology, realize effectively being linked up between the car-mounted terminal and driver.
Specifically, above-mentioned car-mounted terminal also includes voice input module 14, sound identification module 15, and accordingly, above-mentioned core processor 11 also includes speech processing module 113, and voice input module 14, sound identification module 15 and speech processing module 113 are sequentially connected.Voice input module 14 receives the voice signal of driver's input and is sent to sound identification module 15, sound identification module 15 is used for the voice signal to receiving and is identified, realize the identification to driver's voice signal, complete exchanging between driver, speech processing module 113 is also connected with data processing module 112, it is mainly used in obtaining the information after speech recognition, speech recognition signal is analyzed to obtain operator demand, and from calling system data in data processing module 112 completing corresponding instruction, obtain corresponding driver's information needed and voice broadcast is carried out by voice broadcast module 12, realize and exchanging between driver.
Therefore, in the present embodiment, voice broadcast module 12 mainly completes two kinds of voice broadcast, a kind of information passively obtained for driver, the such as information of system intialization, report the information of barrier size and distance away from the car, or the information between vehicle and parking stall line etc., one secure threshold can also be set in data processing module 112, when extraneous barrier is less than the secure threshold with a distance from vehicle, i.e., voice broadcast warning message when barrier closes on；Another kind is the information of driver's active obtaining, as above-mentioned driver sends phonetic order, needs the information of systems response reply.
Especially, above-mentioned sound identification module 15 adopts adaptive voice recognizer, it is in DTW (Dynamic Time Warping, dynamic time consolidation) on the basis of algorithm, give the extracting method of speech terminals detection operation and MFCC (Mel Frequency Cepstrum Coefficient, Mel frequency cepstral coefficients) parameter.
In the speech recognition process, its end points monitoring process is divided into：Two steps of pretreatment and differentiation.Wherein pretreatment adopts the methods such as amplitude normalization, framing and the elimination low-frequency disturbance of input signal to implement.Low-frequency disturbance is eliminated by single order high-pass filter, its transmission function is 1-0.9375z-1, the function can eliminate 50Hz and 60Hz Hz noises.
The Mel parameters that this algorithm is adopted, it can to a certain extent simulate processing procedure and result of the human ear to voice.In the case where there is interchannel noise, MFCC can effectively improve the discrimination of isolated word, and Mel frequencies such as following formula is represented：
fMEL=1127 × log (1+f/700), f are sample frequency.
In the speech recognition process, MFCC cepstrum coefficients extracting method is a link crucial in speech recognition technology, and its computational methods is described as follows：
Carry out sub-frame processing to the above-mentioned voice signal for receiving, preemphasis and plus Hamming window, obtain frequency spectrum using Short Time Fourier Transform；
With M Mel band-pass filter, calculate and obtain energy spectrum, the energy being superimposed in each filter band obtains k-th filter output power spectrum x ' (k)；In this process, its process for obtaining output power spectrum is prior art, and here is no longer specifically described；
The output of each wave filter is taken the logarithm, the log power spectrum of frequency band is obtained, anti-discrete cosine function calculating is carried out to each log power spectrum, obtain L MFCC coefficient, the computational methods of the MFCC coefficients are as follows：
Above-mentioned n is the natural number more than or equal to 1, is L in the present embodiment, and the numerical value of L is 16, but does not make this restriction.
In the present embodiment, the core processor 11 in said system adopts 64 4 core LTE flat computer platforms SOC of Lian Fa sections, and its model is preferably MT8735, but does not make this restriction.
Preferably, above-mentioned core processor 11 also includes the cloud service module 114 being connected with data processing module 112, presented for the view data in receiving data processing module 112 and by user terminal, by the Cloud Server 114 so that driver is not under the scene of vehicle interior, driver can pass through user terminal Telnet to check corresponding data, the system data includes the view data gathered by all dual cameras, and by these data vehicle environmental situation is checked.Above-mentioned user terminal includes the equipment such as PC, mobile phone, PAD.
Preferably, above-mentioned car-mounted terminal also includes the communication module 16 being connected with data processing module 112, the communication module 16 mainly completes the transmission of information by common carrier network, the 4G/3G communication modules of Huawei and the SIM of three big operator's one (movement/UNICOM/telecommunications) can be adopted in the present embodiment, but do not make this restriction.Caused in driving procedure or during vehicle is unmanned by the communication module 16, when the vehicle runs into urgent emergency case, such as traffic accident, be stolen or from damage, traffic or driver just can be sent information to by preset scheme by telecommunication carrier networks by the built-in communication module 16.
In the interactive vehicle intelligent terminal system of the present embodiment, the system also includes power module (not shown), for powering to whole system, is mainly shown as two ways：One is after vehicle start-up, directly 12V vehicle powers to be carried out to work for whole system after voltage stabilizing and reduced output voltage；Two is after vehicle non-started state or accident flameout state, to be powered by its internal battery, is mainly powered to communication module 16 and cloud service module 114.
The present invention also provides a kind of monitoring method, is realized based on above-mentioned interactive vehicle intelligent terminal system, and the monitoring method includes：
S1, video acquisition module 111 obtain video image by multiple dual camera systems；In this step, this multiple dual camera system is separately mounted to Chinese herbaceous peony, the tailstock and car side, to carry out omnibearing video monitoring to vehicle periphery；
S2, data processing module 112 obtain view data from the video image, and distance and barrier size between vehicle and barrier are calculated when vehicle is in the traveling stage, or the distance between vehicle and parking stall line is calculated when vehicle is in the reversing stage；
S3, when vehicle is in the traveling stage voice broadcast barrier size and distance away from the car, or the distance between voice broadcast vehicle and parking stall line when vehicle is in the reversing stage.
Above-mentioned S2 is specifically included：
The view data of S21, foundation barrier P dual camera systems corresponding to the acquisition of the position relationship of vehicle；In this step, it is the front, rear, left and right direction according to barrier in vehicle periphery, to calculate the dual camera camera system 10 with a distance from barrier respective direction, such as camera detects the barrier in vehicle front, then the view data acquired in 112 pairs of dual cameras for being arranged on Chinese herbaceous peony of data processing module is processed, that is to say, that what is obtained in this step is mounted in the view data of the dual camera of Chinese herbaceous peony.
S22, the vector representation for setting two straight lines L1 and L2 are as follows：L1=r1+tv1And L2=r2+sv2；
Wherein：Straight line L1 is projected to the straight line formed between the point on the camera perspective plane by the photocentre and barrier P of one of camera in corresponding dual camera system；Straight line L2 is projected to the straight line formed between the point on the camera perspective plane by the photocentre and barrier P of another camera；The amount of being biased towards,It is unit direction vector；S and t are parametric variables；
S23, distances of the barrier P apart from vehicle is calculated, computational methods are as follows：If A is straight line L1On point, coordinate be (x1+m1t,y1+n1t,z1+p1t)；
B is straight line L2On point, coordinate be (x2+m2s,y2+n2s,z2+p2s)；
If the distance of A to B is d, then
d2=[(x1+m1t)-(x2+m2s)]2+[(y1+n1t)-(y2+n2s)]2+[(z1+p1t)-(z2+p2s)]2, it meets equation below：
Calculate and causeWithS and t values it is as follows：
S and t are substituted into respectively straight line L1With straight line L2Parametric equation obtain intersection point coordinate be (x1+m1t,y1+n1t,z1+p1T) with (x2+m2s,y2+n2s,z2+p2s)；
The approximation of two straight-line intersections, as physical locations of the barrier P in space coordinates can be obtained according to the two intersection point coordinates afterwards, this approximation is to take the midrange between two intersection points.That is barrier P actual coordinates of spatial point in camera are：And camera photocentre is space initial point, i.e., (0,0,0).So as to the distance between, barrier P and camera are：
It is understood that when vehicle is in the reversing stage, needing to calculate the distance between dual camera system 10 and parking stall line after car here, its calculating process is similar to the above, simply parking stall line is regarded as into P points and is calculated, and will not be described here.
The present invention also by speech recognition technology, can recognize the voice messaging of driver, realize effectively being linked up and driver between, and, in this, above-mentioned monitoring method also includes for it：
Receive the voice signal of driver's input；
Voice signal to receiving is identified；
To speech recognition signal analysis to obtain operator demand, and from data processing module calling system data obtaining corresponding driver's information needed.
It is above-mentioned the voice signal that receives is identified during include MFCC coefficient extracting methods, it is a link crucial in speech recognition algorithm, and the MFCC coefficient extracting methods include：
Carry out sub-frame processing to the above-mentioned voice signal for receiving, preemphasis and plus Hamming window, obtain frequency spectrum using Short Time Fourier Transform；
With M Mel band-pass filter, calculate and obtain energy spectrum, the energy being superimposed in each filter band obtains k-th filter output power spectrum x ' (k)；
The output of each wave filter is taken the logarithm, the log power spectrum of frequency band is obtained, anti-discrete cosine function calculating is carried out to each log power spectrum, obtain L MFCC coefficient, the computational methods of the MFCC coefficients are as follows：
Above-mentioned n is the natural number more than or equal to 1, is L in the present embodiment, and the numerical value of L is 16, but does not make this restriction.
Embodiments of the invention are described above in conjunction with accompanying drawing; but the invention is not limited in above-mentioned specific embodiment; above-mentioned specific embodiment is only schematic; rather than it is restricted; one of ordinary skill in the art is under the enlightenment of the present invention; in the case of without departing from present inventive concept and scope of the claimed protection, many forms can be also made, these are belonged within the protection of the present invention.
Claims (8)
1. a kind of interactive vehicle intelligent terminal system, it is characterised in that it includes a car-mounted terminal, many
Individual dual camera system, the dual camera system are separately mounted to Chinese herbaceous peony, the tailstock and car side, described
Car-mounted terminal is including core processor and the voice broadcast module being connected with the core processor respectively and shows
Show module, wherein：The core processor includes：
Video acquisition module：It is connected with each dual camera system, for obtaining video image and leading to
Cross the display module to show；
Data processing module, is connected with the video acquisition module, for obtaining from the video image
View data, and when vehicle is in the traveling stage according to described image data calculate vehicle and barrier it
Between distance and barrier size；Or calculated according to described image data when vehicle is in the reversing stage
The distance between vehicle and parking stall line；
The voice broadcast module is connected with the data processing module, and for being in traveling rank in vehicle
The distance between barrier size and vehicle and barrier are reported during section, or the reversing stage is in vehicle
When report the distance between vehicle and parking stall line.
2. interactive vehicle intelligent terminal system according to claim 1, it is characterised in that described
Car-mounted terminal also includes：
Voice input module, for receiving the voice signal of driver's input；
Sound identification module, is connected and for the voice for receiving with the voice input module
Signal is identified；
The core processor also includes speech processing module, respectively with the sound identification module and described
Data processing module connects, and for entering to the speech recognition signal received from the sound identification module
Row analysis is to obtain operator demand and right to obtain from calling system data in the data processing module
Driver's information needed for answering simultaneously is reported by the voice broadcast module.
3. interactive vehicle intelligent terminal system according to claim 1, it is characterised in that described
Core processor also includes cloud service module, for receiving the view data in the data processing module,
And be presented described image data eventually through user terminal.
4. interactive vehicle intelligent terminal system according to claim 3, it is characterised in that described
Car-mounted terminal also includes the communication module being connected with the data processing module, for vehicle by outside
During shock, the user terminal is sent information to.
5. interactive vehicle intelligent terminal system according to claim 1, it is characterised in that described
Interactive vehicle intelligent terminal system also includes the power module for power supply.
6. a kind of usage right requires the interactive vehicle intelligent terminal described in any one of 1～claim 5
The monitoring method of system, it is characterised in that the monitoring method includes：
S1, by dual camera system obtain video image；
S2, view data is obtained from the video image, and car is calculated when vehicle is in the traveling stage
With the distance between barrier and barrier size, or calculate vehicle when vehicle is in the reversing stage
The distance between with parking stall line；
S3, vehicle be in the traveling stage when between voice broadcast barrier size and vehicle and barrier
Distance, or the distance between voice broadcast vehicle and parking stall line when vehicle is in attached section of reversing.
7. monitoring method according to claim 6, it is characterised in that be in the traveling stage in vehicle
When, step S2 includes：
The picture number of S21, foundation barrier P dual camera systems corresponding to the acquisition of the position relationship of vehicle
According to；
S22, the vector representation for setting two straight lines L1 and L2 are as follows：L1=r1+tv1And L2=r2+sv2；
Wherein：Straight line L1 is the photocentre and barrier P of one of camera in corresponding dual camera system
Project to the straight line formed between the point on the camera perspective plane；Straight line L2 is the light of another camera
The heart and barrier P project to the straight line formed between the point on the camera perspective plane； It is skew
Vector, It is unit direction vector； S and t are parametric variables；
S23, distances of the barrier P apart from vehicle is calculated, computational methods are as follows：If A is straight line L1On
Point, coordinate is (x1+m1t,y1+n1t,z1+p1t)；
B is straight line L2On point, coordinate be (x2+m2s,y2+n2s,z2+p2s)；
If the distance of A to B is d, then
d2=[(x1+m1t)-(x2+m2s)]2+[(y1+n1t)-(y2+n2s)]2+[(z1+p1t)-(z2+p2s)]2, it meets equation below：
Calculate and causeWithS and t values it is as follows：
Wherein： C=m1m2+n1n2+p1p2,
E=m2(x2-x1)+n1(y2-y1)+p1(z2-z1), f=m1(x1-x2)+n1(y1-y2)+p1(z1-z2)
S and t are substituted into respectively straight line L1With straight line L2Parametric equation obtain the coordinate of intersection point and be
(x1+m1t,y1+n1t,z1+p1T) with (x2+m2s,y2+n2s,z2+p2s)；
The distance between barrier P and vehicle are：
8. monitoring method according to claim 6, it is characterised in that the monitoring method is also wrapped
Include：
Receive the voice signal of driver's input；
Voice signal to receiving is identified；
Speech recognition signal is analyzed to obtain operator demand, and the calling system from data processing module
Data are obtaining corresponding driver's information needed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510746944.8A CN106686341A (en) | 2015-11-05 | 2015-11-05 | Interactive vehicle-mounted intelligent terminal system and monitoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510746944.8A CN106686341A (en) | 2015-11-05 | 2015-11-05 | Interactive vehicle-mounted intelligent terminal system and monitoring method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106686341A true CN106686341A (en) | 2017-05-17 |
Family
ID=58858819
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510746944.8A Pending CN106686341A (en) | 2015-11-05 | 2015-11-05 | Interactive vehicle-mounted intelligent terminal system and monitoring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106686341A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107277445A (en) * | 2017-06-29 | 2017-10-20 | 深圳市元征科技股份有限公司 | A kind of mobile unit |
| CN109754415A (en) * | 2017-11-02 | 2019-05-14 | 郭宇铮 | A kind of vehicle-mounted panoramic solid sensory perceptual system based on multiple groups binocular vision |
| CN110108289A (en) * | 2018-02-01 | 2019-08-09 | 上海博泰悦臻网络技术服务有限公司 | Automobile navigation method, Vehicular navigation system, car-mounted terminal and vehicle |
| CN110310387A (en) * | 2019-06-25 | 2019-10-08 | 三明学院 | A kind of intelligent travelling crane recorder, system and vehicle based on the identification of YOLO image |
| CN110459217A (en) * | 2019-08-21 | 2019-11-15 | 中国第一汽车股份有限公司 | A kind of vehicle-mounted answering method, system, vehicle and storage medium |
| CN111081243A (en) * | 2019-12-20 | 2020-04-28 | 大众问问(北京)信息科技有限公司 | Feedback mode adjusting method, device and equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103507759A (en) * | 2012-06-27 | 2014-01-15 | 比亚迪股份有限公司 | Vehicle-mounted device, system and method for recording and informing vehicle owner of vehicle abnormal information |
| CN103608248A (en) * | 2011-11-25 | 2014-02-26 | Senul株式会社 | Mobile-combined user interactive black box for vehicle, and operating method thereof |
| CN103685524A (en) * | 2013-12-16 | 2014-03-26 | 中国科学院深圳先进技术研究院 | Intelligent vehicle-mounted terminal system |
| CN103692974A (en) * | 2013-12-16 | 2014-04-02 | 广州中国科学院先进技术研究所 | Vehicle driving safety pre-warning method and system based on environmental monitoring |
| CN104695311A (en) * | 2014-12-31 | 2015-06-10 | 广东光阵光电科技有限公司 | On-board monitoring method and system for road condition |
| CN205232353U (en) * | 2015-11-05 | 2016-05-11 | 深圳市祈飞科技有限公司 | Interactive intelligent terminal system |
-
2015
- 2015-11-05 CN CN201510746944.8A patent/CN106686341A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103608248A (en) * | 2011-11-25 | 2014-02-26 | Senul株式会社 | Mobile-combined user interactive black box for vehicle, and operating method thereof |
| CN103507759A (en) * | 2012-06-27 | 2014-01-15 | 比亚迪股份有限公司 | Vehicle-mounted device, system and method for recording and informing vehicle owner of vehicle abnormal information |
| CN103685524A (en) * | 2013-12-16 | 2014-03-26 | 中国科学院深圳先进技术研究院 | Intelligent vehicle-mounted terminal system |
| CN103692974A (en) * | 2013-12-16 | 2014-04-02 | 广州中国科学院先进技术研究所 | Vehicle driving safety pre-warning method and system based on environmental monitoring |
| CN104695311A (en) * | 2014-12-31 | 2015-06-10 | 广东光阵光电科技有限公司 | On-board monitoring method and system for road condition |
| CN205232353U (en) * | 2015-11-05 | 2016-05-11 | 深圳市祈飞科技有限公司 | Interactive intelligent terminal system |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107277445A (en) * | 2017-06-29 | 2017-10-20 | 深圳市元征科技股份有限公司 | A kind of mobile unit |
| CN107277445B (en) * | 2017-06-29 | 2020-05-12 | 深圳市元征科技股份有限公司 | Vehicle-mounted equipment |
| CN109754415A (en) * | 2017-11-02 | 2019-05-14 | 郭宇铮 | A kind of vehicle-mounted panoramic solid sensory perceptual system based on multiple groups binocular vision |
| CN110108289A (en) * | 2018-02-01 | 2019-08-09 | 上海博泰悦臻网络技术服务有限公司 | Automobile navigation method, Vehicular navigation system, car-mounted terminal and vehicle |
| CN110310387A (en) * | 2019-06-25 | 2019-10-08 | 三明学院 | A kind of intelligent travelling crane recorder, system and vehicle based on the identification of YOLO image |
| CN110459217A (en) * | 2019-08-21 | 2019-11-15 | 中国第一汽车股份有限公司 | A kind of vehicle-mounted answering method, system, vehicle and storage medium |
| CN110459217B (en) * | 2019-08-21 | 2022-03-08 | 中国第一汽车股份有限公司 | Vehicle-mounted question and answer method, system, vehicle and storage medium |
| CN111081243A (en) * | 2019-12-20 | 2020-04-28 | 大众问问(北京)信息科技有限公司 | Feedback mode adjusting method, device and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106686341A (en) | Interactive vehicle-mounted intelligent terminal system and monitoring method | |
| CN107985225B (en) | Method for providing sound tracking information, sound tracking apparatus and vehicle having the same | |
| CN108226854B (en) | Apparatus and method for providing visual information of rear vehicle | |
| CN110889351B (en) | Video detection method, device, terminal equipment and readable storage medium | |
| US11237241B2 (en) | Microphone array for sound source detection and location | |
| CN205232353U (en) | Interactive intelligent terminal system | |
| CN100466011C (en) | Electric evidence obtaining for vehicle breaking rule to whistle, electric policeman system and evidence obtaining method | |
| CN112771858A (en) | Camera assessment techniques for automated vehicles | |
| CN116901975B (en) | Vehicle-mounted AI security monitoring system and method thereof | |
| KR102051136B1 (en) | Artificial intelligence dashboard robot base on cloud server for recognizing states of a user | |
| CN106202193A (en) | The method of road image acquisition of information, Apparatus and system | |
| CN113808418A (en) | Road condition information display system, method, vehicle, computer device and storage medium | |
| CN109637148B (en) | Vehicle-mounted whistling monitoring system, method, storage medium and equipment | |
| CN101377885A (en) | Electronic workstation for obtaining evidence of vehicle peccancy whistle and method thereof | |
| Pepe et al. | Detecting road surface wetness using microphones and convolutional neural networks | |
| CN113829994B (en) | Early warning method and device based on car external whistling, car and medium | |
| CN210258307U (en) | AI intelligent auxiliary driving terminal equipment based on 4G audio and video transmission technology | |
| CN108932503A (en) | The recognition methods of Chinese herbaceous peony obstacle and device, storage medium, terminal under bad weather | |
| CN111780869A (en) | Multi-camera single-microphone array automobile whistle detection equipment | |
| WO2022179124A1 (en) | Image restoration method and apparatus | |
| CN116486351A (en) | Driving early warning method, device, equipment and storage medium | |
| CN113997863B (en) | Data processing method and device and vehicle | |
| CN110855733B (en) | Vehicle introduction method, system, server and vehicle | |
| CN209044894U (en) | A kind of Visual retrieval parking assistance system | |
| US20200005806A1 (en) | Call quality improvement system, apparatus and method |
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 |