CN107886751A - A kind of car-mounted terminal real-time road early warning system - Google Patents
A kind of car-mounted terminal real-time road early warning system Download PDFInfo
- Publication number
- CN107886751A CN107886751A CN201711081209.5A CN201711081209A CN107886751A CN 107886751 A CN107886751 A CN 107886751A CN 201711081209 A CN201711081209 A CN 201711081209A CN 107886751 A CN107886751 A CN 107886751A
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- road condition
- image
- msup
- 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
- 238000012545 processing Methods 0.000 claims abstract description 33
- 230000006837 decompression Effects 0.000 claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 7
- 230000006835 compression Effects 0.000 claims abstract description 5
- 238000007906 compression Methods 0.000 claims abstract description 5
- 230000009466 transformation Effects 0.000 claims description 23
- 239000011159 matrix material Substances 0.000 claims description 17
- 238000005070 sampling Methods 0.000 claims description 13
- 238000012216 screening Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 5
- 230000000903 blocking effect Effects 0.000 claims description 2
- 238000012937 correction Methods 0.000 claims description 2
- 230000009191 jumping Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 9
- 230000005540 biological transmission Effects 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Atmospheric Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Processing (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a kind of car-mounted terminal real-time road early warning system, the system includes camera, image processing module, decompression module, cloud computing platform and terminal device, and the camera is used to capture current road conditions image；Described image processing module is used to be compressed road conditions image, store, and the road conditions image transmitting after compression is handled by wireless network to decompression module carries out decompression operations；The cloud computing platform is used to analyze and process the road conditions image that decompression obtains, and obtains current road condition data；The terminal device is used to provide the user current traffic information according to the road condition data that cloud computing platform provides, and facilitates user according to traffic information travel route planning；And terminal device connects with the prior-warning device on car, when front gets congestion, also early warning, prompting changing route actively can be sent to driver.
Description
Technical Field
The invention relates to the technical field of automobiles, in particular to a real-time road condition early warning system for a vehicle-mounted terminal.
Background
With the rapid development of economy and the acceleration of urbanization process, the traffic contradiction is increasingly prominent, and the normal life of people is seriously influenced by the traffic jam problem. The traffic condition information is real-time traffic information, which reflects the traffic condition of the road in a specific area and the recent change trend. The traffic road condition information not only can provide basis for traffic guidance of traffic management departments, but also provides help for drivers and ordinary travelers to reasonably select routes. Therefore, the collection, processing, reporting and publishing of the traffic road condition information can help to solve the increasingly serious traffic jam problem at present.
The camera needs to gather a large amount of real-time traffic road conditions information every day, because the shared space of these videos is big, can appear the flow loss big in the transmission, transmission speed is low, the real-time poor scheduling problem, gives people to go out and brings a great deal of inconvenience, how to realize carrying out quick transmission and timely processing to these video information is a problem that needs to solve urgently.
Disclosure of Invention
Aiming at the problems, the invention aims to provide a vehicle-mounted terminal real-time road condition early warning system.
The purpose of the invention is realized by adopting the following technical scheme:
a real-time road condition early warning system of a vehicle-mounted terminal is characterized by comprising a camera, an image processing module, a decompression module, a cloud computing platform and terminal equipment, wherein the camera is used for snapshotting current road condition information and acquiring a current road condition image; the image processing module is used for compressing and storing the road condition image, and transmitting the processed road condition image to the decompression module through a wireless network for decompression; the cloud computing platform is used for comprehensively managing the road condition images obtained through decompression; the terminal equipment is used for providing current road condition information for the user, and the user can conveniently plan a travel route according to the road condition information.
The invention has the beneficial effects that: the user can acquire the real-time road condition information of the vehicle-mounted terminal through the system, the path is changed in time according to the road condition information, traffic jam is reduced, the terminal equipment is connected with the early warning device on the vehicle, and when congestion occurs in the front side, early warning prompt can be actively sent to a driver to remind the driver of changing the path.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.
Fig. 1 is a frame configuration diagram of the present invention.
Reference numerals:
a camera 1; an image processing module 2; a decompression module 3; a cloud computing platform 4; a terminal device 5; a receiver 6; a central processing unit 7; a storage unit 8; a wireless communication unit 9.
Detailed Description
The invention is further described in connection with the following application scenarios.
Referring to fig. 1, the real-time road condition early warning system of the vehicle-mounted terminal in the embodiment is characterized by comprising a camera 1, an image processing module 2, a decompression module 3, a cloud computing platform 4 and a terminal device 5, wherein the camera 1 is used for capturing current road condition information and acquiring a current road condition image; the image processing module 2 is used for compressing and storing the road condition image, and transmitting the processed road condition image to the decompression module 3 through a wireless network for decompression; the cloud computing platform 4 is used for analyzing and processing the road condition images obtained by decompression to obtain current road condition data; the terminal device 5 is used for providing current road condition information for the user according to the road condition data provided by the cloud computing platform 4, and the user can plan a travel route according to the road condition information conveniently.
Preferably, a camera 1 is installed on the road every 50 kilometers, and the camera 1 is used for capturing road condition images and sending the captured road condition images to the receiver 6 through a wireless network.
Preferably, referring to fig. 1, the image processing module 2 comprises a receiver 6, a central processing unit 7, a storage unit 8, and a wireless communication unit 9, which are connected in sequence. The receiver 6 is used for receiving road condition images captured by the camera; the central processing unit 7 is configured to perform denoising processing on the road condition image to remove random noise in the road condition image to obtain a denoised road condition image, and compress the denoised road condition image; the storage unit 8 is used for storing the compressed road condition image; the wireless communication unit 9 is configured to transmit the compressed road condition image to the decompression module.
Preferably, the Discrete Cosine Transform (DCT) is to perform discrete cosine transform on an image, convert the image from a spatial domain to a frequency domain, process a transform coefficient in the frequency domain, and perform inverse transform on the image from the frequency domain to the spatial domain, thereby achieving the purpose of removing image noise.
Preferably, the non-downsampling contourlet transform is performed by non-downsampling using a pyramid (NSP) and a non-downsampling direction filter bank (NSDFB), the NSP can remove downsampling in the LP decomposition process, perform corresponding upsampling on the filter, and perform similar multi-scale decomposition by using a two-channel non-downsampling filter; the NSDFB is formed by removing a sampling process in the DFB and performing corresponding upsampling on the filter, and after the directional filter bank is subjected to proper upsampling, the directional filter can be partially covered on a band-pass band of the tower-type filter well, so that the phenomenon of frequency aliasing can be overcome, and the NSDFB has translation invariance.
Preferably, the central processing unit 7 is configured to remove random noise in the road condition image, perform blocking preprocessing on the road condition image after being denoised to obtain image blocks, and perform sparse transformation on the image blocks to obtain a series of road condition subimage blocks, which specifically includes:
1) preprocessing the collected road condition image in advance, removing interference factors in the road condition image to obtain a new road condition image, wherein the size of the road condition image is NxN, and preprocessing the road condition image in advance by adopting a Discrete Cosine Transform (DCT) method;
2) with new road condition image pixel point xaSetting a square area with the size of R multiplied by R as a retrieval range for the center, and utilizing a selection function to carry out retrieval on pixel points x in the retrieval rangebMaking a pre-selection when F (N)a,Nb) Greater than a selected threshold τ (x)a) Then the pixel point is the pixel point xaTraversing all the pixel points in the search range to obtain a pixel point xaSimilar set of (U)aThe selection function is:
wherein N isa、NbRespectively is defined as pixel point xaAnd NbAn image block of size M × M centered; mu.sa、σaAre respectively NaMean and standard deviation of the gray values of (1), mub、σbIs NbMean and standard deviation of the gray values of (2), σijIs NaAnd Nbα, β and gamma are adjustment factors and satisfy α + β + gamma is 1, C1、C2And C3For the correction factor, which is primarily intended to ensure that the selection function is meaningful, σFiAnd σFjAre respectively NaAnd NbOf the frequency domain coefficients of (a) is the standard deviation of the gray values of the frequency domain coefficients of (a), σFijIs a block N of pixelsaAnd a pixel block NbThe covariance of the frequency domain coefficients of (a);
3) calculate the similarity set UaAll similar points x inaAnd carrying out weighted average on all pixel points in the retrieval range to obtain a pixel point x to be estimatedaThe weight calculation formula of the denoised estimated value is as follows:
pixel point xaThe calculation formula of the denoising estimation value is as follows:
wherein,is a block N of pixelsaAnd a pixel block NbThe Euclidean distance weighted by Gauss, kappa is the standard deviation of the Gaussian kernel of the road condition image, h is the filter coefficient, and omega is the pixel point xaSearch range centered on, w (x)a,xb) As a weight, by xaAnd xbImage block N of size M centeredaAnd NbSimilarity between them, and 0w (x)a,xb)≤1，y(xa) Is a pixel point xaThe denoised estimate of, y (x)b) For searching range pixel point xbThe denoised estimate of (2);
4) traversing all pixel points in the new road condition image to obtain denoising estimated values of all pixel points in the new road condition image, and replacing the gray values of the corresponding pixel points in the new road condition image with the denoising estimated values obtained by calculation so as to obtain a road condition image X to be processed after secondary denoising;
5) the road condition image to be processed is divided into a group of sub image blocksWherein x isjRepresenting the column vector form of the jth sub-image block, N being the size of the road condition image, S being the size of the sub-image block, then carrying out sparse transformation on the sub-image blocks by adopting non-subsampled contourlet transformation to obtain a series of road condition sub-image blocks
Has the advantages that: the road condition image collected by the camera 1 is subjected to denoising processing twice, so that random noise in the road condition image can be effectively removed, the recognition degree of the denoised image is improved, and meanwhile, in the secondary denoising, the weight coefficient is corrected by using the selection function, and the random noise can be adaptively filtered. This reduces the data processing amount for the subsequent perception compression processing image, improves the compression rate, and saves the memory space. The road condition image to be processed is subjected to sparse processing by adopting non-subsampled contourlet transformation, so that the main characteristics of the road condition image can be described by using minimum information, the memory space is saved, and the data processing speed is improved.
Preferably, the central processing unit 7 is further configured to perform observation projection on the road condition sub image block to obtain a sampling value of the road condition sub image block, specifically:
1) using the following system of equations, a set of sequences is generatedThe self-defined equation set is as follows:
2) slave sequenceIn turn, a set of numbers at equal intervals to form a new sequence, the length of the new sequence being S2；
3) Arranging and combining the new sequences according to the row sequence to obtain a projection matrix phi with the size of S multiplied by SBNormalizing the projection matrix to obtain a new projection matrix phiB＇；
4) By using phiB' compressing the road condition sub-image block to obtain sample values of the road condition sub-image block, specifically:
yj＝ΦB＇xj′
wherein, yjSampling values of the jth road condition sub-image block; x is the number ofj' is the jth road condition subimage block.
Has the advantages that: the road condition sub-image blocks are directly sampled, observed and projected, the processing method does not need to store a measurement matrix phi of the whole road condition image during storage, and the road condition sub-image blocks are observed and projected, so that the operation storage space is greatly reduced, and the compression speed of the road condition image is accelerated; the coding operation is not required to be carried out after the whole sparse road condition image is measured, each road condition sub-image block can be independently processed, and the real-time performance is ensured.
Preferably, the decompression module 3 is configured to perform iterative reconstruction on the sampling values of the road condition sub-image blocks to obtain iterative values of the road condition sub-image blocks, and combine the iterative values of all the road condition sub-image blocks to obtain a complete reconstructed image, which specifically includes:
1) by usingObtaining an initial iteration value of the jth sub image block in the road condition image, wherein,representing the initial iteration value, phi, of the jth sub-image blockB＇TIs phiBThe transposed matrix ofjSampling values of the jth road condition sub-image block;
2) filtering the road condition sub-image blocks to obtainWherein i is an iterative algebra;filtering image blocks of the jth road condition sub-image block obtained by filtering;
3) by usingProjection formula pairPerforming projection calculation to obtain
Wherein,the j image block is obtained by iterating the i times of post projection; phiB＇TProjection matrix phi for image blockBThe transposed matrix ofjSampling values of the jth road condition sub-image block;
4) obtained by projection using sparse matrix psiCarrying out sparse transformation, screening the transformation coefficient obtained by the sparse transformation by using a screening function, if the absolute value w is more than or equal to tau, obtaining a new transformation coefficient by using a threshold function calculation, otherwise, setting the transformation coefficient to zero, wherein tau is a self-defined screening value, and finally carrying out sparse inverse transformation to obtain the new transformation coefficientThe custom filter function is:
wherein the sparse matrix psi is a selected one of the matrices,for the screening function, w is the transform coefficient, wpIs the parent coefficient of the transform coefficient w, τ is the convergence control coefficient, f is the estimate of the transform coefficient w, σwIs the edge mean square error of the 3 x 3 neighborhood estimate of the coefficient of variation w,the estimated value of the j image block obtained by the sparse inverse transformation is obtained;
5) using pairs of iterative functionsPerforming iterative processing to obtainIteration value ofThe defined iteration function is:
6) calculating residual error D(i)If | D(i+1)-D(i)|10-4Then outputOtherwise, jumping to step 2, and performing iterative calculation until | D is satisfied(i+1)-D(i)|10-4Output the iteration valueWherein, the calculation formula of the residual error is as follows:
7) traversing the sampling values of all the image blocks, carrying out iterative reconstruction to obtain iterative values of all the image blocks, and realizing reconstruction of the whole road condition image by using the obtained iterative values to obtain a reconstructed image of the road condition image.
Claims (6)
1. A real-time road condition early warning system of a vehicle-mounted terminal is characterized by comprising a camera, an image processing module, a decompression module, a cloud computing platform and terminal equipment, wherein the camera is used for capturing a current road condition image; the image processing module is used for compressing and storing the road condition image, and transmitting the road condition image after compression processing to the decompression module through a wireless network for decompression operation; the cloud computing platform is used for analyzing and processing the road condition images obtained by decompression to obtain current road condition data; the terminal device is used for providing current road condition information for the user according to the road condition data provided by the cloud computing platform, and the user can plan a travel route conveniently according to the road condition information.
2. The real-time road condition early warning system of the vehicle-mounted terminal as claimed in claim 1, wherein the image processing module comprises a receiver, a central processing unit, a storage unit and a wireless communication unit, the receiver is used for receiving road condition images captured by the camera; the central processing unit is used for denoising the road condition image to remove random noise in the road condition image to obtain a denoised road condition image on one hand, and compressing the denoised road condition image on the other hand; the storage unit is used for storing the compressed road condition image; the wireless communication unit is used for transmitting the compressed road condition image to the decompression module.
3. The real-time road condition early warning system of the vehicle-mounted terminal as claimed in claim 2, wherein the terminal device is further connected to an early warning system on the vehicle, and when traffic jam occurs, the early warning system sends out an early warning to remind a user to adjust a route and plan a path again.
4. The system as claimed in claim 3, wherein the central processing unit is configured to remove random noise in the road condition image, perform blocking preprocessing on the road condition image after being denoised to obtain image blocks, and perform sparse transformation on the image blocks to obtain a series of road condition sub-image blocks, specifically:
1) preprocessing the collected road condition image in advance, removing interference factors in the road condition image to obtain a new road condition image, wherein the size of the road condition image is NxN, and preprocessing the road condition image in advance by adopting a Discrete Cosine Transform (DCT) method;
2) with new road condition image pixel point xaSetting a square area with the size of R multiplied by R as a retrieval range for the center, and utilizing a selection function to carry out retrieval on pixel points x in the retrieval rangebMaking a pre-selection when F (N)a,Nb) Greater than a selected threshold τ (x)a) Then the pixel point is the pixel point xaTraversing all the pixel points in the search range to obtain a pixel point xaSimilar set of (U)aThe selection function is:
<mrow> <mi>F</mi> <mrow> <mo>(</mo> <msub> <mi>N</mi> <mi>a</mi> </msub> <mo>,</mo> <msub> <mi>N</mi> <mi>b</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <msup> <mrow> <mo>&lsqb;</mo> <mfrac> <mrow> <msqrt> <mrow> <mn>2</mn> <msub> <mi>&mu;</mi> <mi>a</mi> </msub> <msub> <mi>&mu;</mi> <mi>b</mi> </msub> </mrow> </msqrt> <mo>+</mo> <msub> <mi>C</mi> <mn>1</mn> </msub> </mrow> <mrow> <msub> <mi>&mu;</mi> <mi>a</mi> </msub> <mo>+</mo> <msub> <mi>&mu;</mi> <mi>b</mi> </msub> <mo>+</mo> <msub> <mi>C</mi> <mn>1</mn> </msub> </mrow> </mfrac> <mo>&rsqb;</mo> </mrow> <mi>&alpha;</mi> </msup> <msup> <mrow> <mo>&lsqb;</mo> <mfrac> <mrow> <msqrt> <mrow> <mn>2</mn> <msub> <mi>&sigma;</mi> <mi>a</mi> </msub> <msub> <mi>&sigma;</mi> <mi>b</mi> </msub> </mrow> </msqrt> <mo>+</mo> <msub> <mi>C</mi> <mn>2</mn> </msub> </mrow> <mrow> <msub> <mi>&sigma;</mi> <mi>a</mi> </msub> <mo>+</mo> <msub> <mi>&sigma;</mi> <mi>b</mi> </msub> <mo>+</mo> <msub> <mi>C</mi> <mn>2</mn> </msub> </mrow> </mfrac> <mo>&rsqb;</mo> </mrow> <mi>&beta;</mi> </msup> <msup> <mrow> <mo>&lsqb;</mo> <mfrac> <mrow> <msqrt> <mrow> <mn>2</mn> <msub> <mi>&sigma;</mi> <mrow> <mi>F</mi> <mi>i</mi> <mi>j</mi> </mrow> </msub> </mrow> </msqrt> <mo>+</mo> <msub> <mi>C</mi> <mn>3</mn> </msub> </mrow> <mrow> <msub> <mi>&sigma;</mi> <mrow> <mi>F</mi> <mi>i</mi> </mrow> </msub> <mo>+</mo> <msub> <mi>&sigma;</mi> <mrow> <mi>F</mi> <mi>j</mi> </mrow> </msub> <mo>+</mo> <msub> <mi>C</mi> <mn>3</mn> </msub> </mrow> </mfrac> <mo>&rsqb;</mo> </mrow> <mi>&gamma;</mi> </msup> <mo>;</mo> </mrow>
wherein N isa、NbRespectively is defined as pixel point xaAnd NbAn image block of size M × M centered; mu.sa、σaAre respectively NaMean and standard deviation of the gray values of (1), mub、σbIs NbMean and standard deviation of the gray values of (2), σijIs NaAnd Nbα, β and gamma are adjustment factors and satisfy α + β + gamma is 1, C1、C2And C3For the correction factor, which is primarily intended to ensure that the selection function is meaningful, σFiAnd σFjAre respectively NaAnd NbOf the frequency domain coefficients of (a) is the standard deviation of the gray values of the frequency domain coefficients of (a), σFijIs a block N of pixelsaAnd a pixel block NbThe covariance of the frequency domain coefficients of (a);
3) calculate the similarity set UaAll similar points x inaThen, carrying out weighted average on all pixel points in the retrieval range to obtain a pixel point x to be estimatedaThe weight calculation formula of the denoised estimated value is as follows:
<mrow> <mi>w</mi> <mrow> <mo>(</mo> <msub> <mi>x</mi> <mi>a</mi> </msub> <mo>,</mo> <msub> <mi>x</mi> <mi>b</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mn>0</mn> </mtd> <mtd> <mrow> <mi>F</mi> <mrow> <mo>(</mo> <msub> <mi>N</mi> <mi>a</mi> </msub> <mo>,</mo> <msub> <mi>N</mi> <mi>b</mi> </msub> <mo>)</mo> </mrow> <mo><</mo> <mi>&tau;</mi> <mrow> <mo>(</mo> <msub> <mi>x</mi> <mi>a</mi> </msub> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mi>exp</mi> <mrow> <mo>(</mo> <mo>-</mo> <mfrac> <mrow> <mo>|</mo> <mo>|</mo> <mi>v</mi> <mrow> <mo>(</mo> <msub> <mi>N</mi> <mi>a</mi> </msub> <mo>)</mo> </mrow> <mo>-</mo> <mi>v</mi> <mrow> <mo>(</mo> <msub> <mi>N</mi> <mi>b</mi> </msub> <mo>)</mo> </mrow> <mo>|</mo> <msubsup> <mo>|</mo> <mrow> <mn>2</mn> <mo>,</mo> <mi>&kappa;</mi> </mrow> <mn>2</mn> </msubsup> </mrow> <msup> <mi>h</mi> <mn>2</mn> </msup> </mfrac> <mo>)</mo> </mrow> <mo>&times;</mo> <mi>F</mi> <mrow> <mo>(</mo> <msub> <mi>N</mi> <mi>a</mi> </msub> <mo>,</mo> <msub> <mi>N</mi> <mi>b</mi> </msub> <mo>)</mo> </mrow> </mrow> </mtd> <mtd> <mrow> <mi>F</mi> <mrow> <mo>(</mo> <msub> <mi>N</mi> <mi>a</mi> </msub> <mo>,</mo> <msub> <mi>N</mi> <mi>b</mi> </msub> <mo>)</mo> </mrow> <mo>&GreaterEqual;</mo> <mi>&tau;</mi> <mrow> <mo>(</mo> <msub> <mi>x</mi> <mi>a</mi> </msub> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> </mtable> </mfenced> </mrow>
pixel point xaThe calculation formula of the denoising estimation value is as follows:
<mrow> <mi>y</mi> <mrow> <mo>(</mo> <msub> <mi>x</mi> <mi>a</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mfrac> <mn>1</mn> <mrow> <msub> <mi>&Sigma;</mi> <msub> <mi>x</mi> <mi>b</mi> </msub> </msub> <mi>w</mi> <mrow> <mo>(</mo> <msub> <mi>x</mi> <mi>a</mi> </msub> <mo>,</mo> <msub> <mi>x</mi> <mi>b</mi> </msub> <mo>)</mo> </mrow> </mrow> </mfrac> <munder> <mo>&Sigma;</mo> <mrow> <msub> <mi>x</mi> <mi>b</mi> </msub> <mo>&Subset;</mo> <mi>&Omega;</mi> </mrow> </munder> <mi>w</mi> <mrow> <mo>(</mo> <msub> <mi>x</mi> <mi>a</mi> </msub> <mo>,</mo> <msub> <mi>x</mi> <mi>b</mi> </msub> <mo>)</mo> </mrow> <mi>y</mi> <mrow> <mo>(</mo> <msub> <mi>x</mi> <mi>b</mi> </msub> <mo>)</mo> </mrow> </mrow>
wherein,is a block N of pixelsaAnd a pixel block NbThe Euclidean distance is weighted by Gauss, kappa is the standard deviation of the Gaussian kernel of the road condition image, h is the filter coefficient, and omega isBy pixel point xaSearch range centered on, w (x)a,xb) As a weight, by xaAnd xbImage block N of size M centeredaAnd NbThe similarity between the two is determined, and 0 is more than or equal to w (x)a,xb)≤1；y(xa) Is a pixel point xaThe denoised estimate of, y (x)b) For searching range pixel point xbThe denoised estimate of (2);
4) traversing all pixel points in the new road condition image to obtain denoising estimated values of all pixel points in the new road condition image, and replacing the gray values of the corresponding pixel points in the new road condition image with the denoising estimated values obtained by calculation so as to obtain a road condition image X to be processed after secondary denoising;
5) the road condition image to be processed is divided into a group of sub image blocksWherein x isjRepresenting the column vector form of the jth sub-image block, N being the size of the road condition image, S being the size of the sub-image block, then carrying out sparse transformation on the sub-image blocks by adopting non-subsampled contourlet transformation to obtain a series of road condition sub-image blocks
5. The real-time road condition early warning system of the vehicle-mounted terminal as claimed in claim 4, wherein the central processing unit is further configured to perform observation and projection on the road condition sub-image block to obtain the sampling values of the road condition sub-image block, specifically:
1) using the following system of equations, a set of sequences is generatedThe self-defined equation set is as follows:
2) slave sequenceIn turn, a set of numbers at equal intervals to form a new sequence, the length of the new sequence being S2；
3) Arranging and combining the new sequences according to the row sequence to obtain a projection matrix phi with the size of S multiplied by SBNormalizing the projection matrix to obtain a new projection matrix phiB＇；
4) By using phiB' compressing the road condition sub-image block to obtain sample values of the road condition sub-image block, specifically:
yj＝ΦB＇xj′
wherein, yjSampling values of the jth road condition sub-image block; x is the number ofj' is the jth road condition subimage block.
6. The real-time road condition early warning system of the vehicle-mounted terminal as claimed in claim 5, wherein the decompression module is configured to perform iterative reconstruction on the sampling values of the road condition sub-image blocks to obtain iterative values of the road condition sub-image blocks, and combine the iterative values of all the road condition sub-image blocks to obtain a complete reconstructed image, specifically:
1) by usingObtaining an initial iteration value of the jth sub image block in the road condition image, wherein,representing the initial iteration value, phi, of the jth sub-image blockB＇TIs phiBThe transposed matrix ofjSampling values of the jth road condition sub-image block;
2) filtering the road condition sub-image blocks to obtainWherein i is an iterative algebra;filtering image blocks of the jth road condition sub-image block obtained by filtering;
3) by usingProjection formula pairPerforming projection calculation to obtain
Wherein,the j image block is obtained by iterating the i times of post projection; phiB＇TProjection matrix phi for image blockBThe transposed matrix ofjSampling values of the jth road condition sub-image block;
4) obtained by projection using sparse matrix psiCarrying out sparse transformation, screening the transformation coefficient obtained by the sparse transformation by using a screening function, if the absolute value w is more than or equal to tau, obtaining a new transformation coefficient by using a threshold function calculation, otherwise, setting the transformation coefficient to zero, wherein tau is a self-defined screening value, and finally carrying out sparse inverse transformation to obtain the new transformation coefficientThe custom filter function is:
<mrow> <mo>&dtri;</mo> <mo>=</mo> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mfrac> <mrow> <mi>w</mi> <msqrt> <mrow> <msup> <mi>w</mi> <mn>2</mn> </msup> <mo>+</mo> <msubsup> <mi>w</mi> <mi>p</mi> <mn>2</mn> </msubsup> </mrow> </msqrt> <mo>-</mo> <mi>&tau;</mi> <mfrac> <mrow> <msqrt> <mn>3</mn> </msqrt> <msup> <mi>f</mi> <mn>2</mn> </msup> </mrow> <msub> <mi>&sigma;</mi> <mi>w</mi> </msub> </mfrac> <mi>w</mi> </mrow> <msqrt> <mrow> <msup> <mi>w</mi> <mn>2</mn> </msup> <mo>+</mo> <msubsup> <mi>w</mi> <mi>p</mi> <mn>2</mn> </msubsup> </mrow> </msqrt> </mfrac> </mtd> <mtd> <mrow> <mrow> <mo>|</mo> <mi>w</mi> <mo>|</mo> </mrow> <mo>&GreaterEqual;</mo> <mi>&tau;</mi> </mrow> </mtd> </mtr> <mtr> <mtd> <mn>0</mn> </mtd> <mtd> <mrow> <mi>o</mi> <mi>t</mi> <mi>h</mi> <mi>e</mi> <mi>r</mi> <mi>s</mi> </mrow> </mtd> </mtr> </mtable> </mfenced> </mrow>
wherein the sparse matrix psi is a selected one of the matrices,for the screening function, w is the transform coefficient, wpIs the parent coefficient of the transform coefficient w, τ is the convergence control coefficient, f is the estimate of the transform coefficient w, σwIs the edge mean square error of the 3 x 3 neighborhood estimate of the coefficient of variation w,the estimated value of the j image block obtained by the sparse inverse transformation is obtained;
5) using pairs of iterative functionsPerforming iterative processing to obtainIteration value ofThe defined iteration function is:
6) calculating residual error D(i)If | D(i+1)-D(i)|＜10-4Then outputOtherwise, jumping to step 2, and performing iterative calculation until | D is satisfied(i+1)-D(i)|＜10-4Output the iteration valueWherein, the calculation formula of the residual error is as follows:
<mrow> <msup> <mi>D</mi> <mrow> <mo>(</mo> <mi>i</mi> <mo>)</mo> </mrow> </msup> <mo>=</mo> <mfrac> <mn>1</mn> <msqrt> <mi>N</mi> </msqrt> </mfrac> <mo>|</mo> <mo>|</mo> <msup> <mi>X</mi> <mrow> <mo>(</mo> <mi>i</mi> <mo>)</mo> </mrow> </msup> <mo>-</mo> <msup> <mover> <mover> <mi>X</mi> <mo>^</mo> </mover> <mo>^</mo> </mover> <mrow> <mo>(</mo> <mi>i</mi> <mo>)</mo> </mrow> </msup> <mo>|</mo> <msub> <mo>|</mo> <mn>2</mn> </msub> </mrow>
7) traversing the sampling values of all the image blocks, carrying out iterative reconstruction to obtain iterative values of all the image blocks, and realizing reconstruction of the whole road condition image by using the obtained iterative values to obtain a reconstructed image of the road condition image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711081209.5A CN107886751B (en) | 2017-11-07 | 2017-11-07 | Real-time road condition early warning system of vehicle-mounted terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711081209.5A CN107886751B (en) | 2017-11-07 | 2017-11-07 | Real-time road condition early warning system of vehicle-mounted terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107886751A true CN107886751A (en) | 2018-04-06 |
| CN107886751B CN107886751B (en) | 2020-12-25 |
Family
ID=61779068
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711081209.5A Active CN107886751B (en) | 2017-11-07 | 2017-11-07 | Real-time road condition early warning system of vehicle-mounted terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107886751B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107692392A (en) * | 2017-11-07 | 2018-02-16 | 韦彩霞 | A kind of safety helment warning device for site safety operation |
| CN108846372A (en) * | 2018-06-27 | 2018-11-20 | 肖鑫茹 | A kind of intelligent transportation system |
| CN109017557A (en) * | 2018-06-20 | 2018-12-18 | 上海科世达-华阳汽车电器有限公司 | A kind of vehicle road condition detection system and autonomous driving vehicle |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101344991A (en) * | 2008-09-03 | 2009-01-14 | 华为技术有限公司 | Method, device and system for providing road information |
| CN103489312A (en) * | 2013-09-22 | 2014-01-01 | 江苏大学 | A Method of Collecting Traffic Flow Information Based on Image Compression |
| US8666180B2 (en) * | 2009-12-04 | 2014-03-04 | Stc.Unm | System and methods of compressed sensing as applied to computer graphics and computer imaging |
| CN106448266A (en) * | 2016-10-27 | 2017-02-22 | 深圳市元征软件开发有限公司 | Vehicle driving warning method, vehicle driving warning device and vehicle driving warning system |
-
2017
- 2017-11-07 CN CN201711081209.5A patent/CN107886751B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101344991A (en) * | 2008-09-03 | 2009-01-14 | 华为技术有限公司 | Method, device and system for providing road information |
| US8666180B2 (en) * | 2009-12-04 | 2014-03-04 | Stc.Unm | System and methods of compressed sensing as applied to computer graphics and computer imaging |
| CN103489312A (en) * | 2013-09-22 | 2014-01-01 | 江苏大学 | A Method of Collecting Traffic Flow Information Based on Image Compression |
| CN106448266A (en) * | 2016-10-27 | 2017-02-22 | 深圳市元征软件开发有限公司 | Vehicle driving warning method, vehicle driving warning device and vehicle driving warning system |
Non-Patent Citations (1)
| Title |
|---|
| 沈萍萍，余勤: "基于离散余弦变换的非局部均值图像去噪算法", 《计算机工程与设计》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107692392A (en) * | 2017-11-07 | 2018-02-16 | 韦彩霞 | A kind of safety helment warning device for site safety operation |
| CN107692392B (en) * | 2017-11-07 | 2019-12-10 | 南京万和消防科技有限公司 | A safety helmet warning device for building site safety work |
| CN109017557A (en) * | 2018-06-20 | 2018-12-18 | 上海科世达-华阳汽车电器有限公司 | A kind of vehicle road condition detection system and autonomous driving vehicle |
| CN108846372A (en) * | 2018-06-27 | 2018-11-20 | 肖鑫茹 | A kind of intelligent transportation system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107886751B (en) | 2020-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110223511A (en) | A kind of automobile roadside is separated to stop intelligent monitoring method and system | |
| CN111652804B (en) | Super-resolution reconstruction method based on expansion convolution pyramid and bottleneck network | |
| CN107886751B (en) | Real-time road condition early warning system of vehicle-mounted terminal | |
| CN105069796B (en) | SAR image segmentation method based on small echo both scatternets | |
| CN111951195A (en) | Image enhancement method and device | |
| CN107292851A (en) | A kind of BM3D image denoising methods converted based on pseudo- 3D | |
| CN105160647A (en) | Panchromatic multi-spectral image fusion method | |
| CN103106660B (en) | Synthetic aperture radar (SAR) image quality evaluation method based on contrast sensitivity characteristics | |
| CN114419605B (en) | Visual enhancement method and system based on spatial alignment feature fusion of multi-networked vehicles | |
| CN101551902A (en) | A characteristic matching method for compressing video super-resolution based on learning | |
| CN113624223A (en) | Indoor parking lot map construction method and device | |
| CN104517126A (en) | Air quality assessment method based on image analysis | |
| CN113191325A (en) | Image fusion method, system and application thereof | |
| CN116993933A (en) | Live-action map construction method, device and equipment under emergency scene and storage medium | |
| US9268791B2 (en) | Method and apparatus for image processing and computer readable medium | |
| CN117079261A (en) | Campus vehicle cross-domain tracking method, system, equipment and storage medium | |
| CN100465661C (en) | Multispectral and Panchromatic Image Fusion Method Based on Hypercomplex Pivot Component Weighting | |
| CN112907972A (en) | Road vehicle flow detection method and system based on unmanned aerial vehicle and computer readable storage medium | |
| CN113989474B (en) | Infrared small target intelligent identification method based on progressive hierarchical fusion network | |
| CN111524079A (en) | Multispectral remote sensing image panchromatic sharpening method based on component replacement and low-pass filtering | |
| CN114677329A (en) | Pit edge image target detection system based on mobile edge calculation | |
| CN118679493A (en) | Image processing method and image processing apparatus | |
| CN107692392B (en) | A safety helmet warning device for building site safety work | |
| CN111353982B (en) | Depth camera image sequence screening method and device | |
| CN117544863A (en) | Information acquisition method and system based on recorder and recorder |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201119 Address after: B603, 6th floor, building 1, No. 36, North Third Ring Road East, Dongcheng District, Beijing 100010 Applicant after: Mushroom car Union Information Technology Co.,Ltd. Address before: No. 44, people's East Road, Yulin, the Guangxi Zhuang Autonomous Region, the Guangxi Zhuang Autonomous Region Applicant before: Gong Tuting |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |