CN117972629A - Parking space state detection method and system based on fusion filtering - Google Patents
Parking space state detection method and system based on fusion filtering Download PDFInfo
- Publication number
- CN117972629A CN117972629A CN202410132060.2A CN202410132060A CN117972629A CN 117972629 A CN117972629 A CN 117972629A CN 202410132060 A CN202410132060 A CN 202410132060A CN 117972629 A CN117972629 A CN 117972629A
- Authority
- CN
- China
- Prior art keywords
- parking space
- state
- target parking
- geomagnetic
- signal
- 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
- 238000001914 filtration Methods 0.000 title claims abstract description 78
- 230000004927 fusion Effects 0.000 title claims abstract description 58
- 238000001514 detection method Methods 0.000 title claims abstract description 56
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 19
- 239000011159 matrix material Substances 0.000 claims description 28
- 108010076504 Protein Sorting Signals Proteins 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 2
- 230000007704 transition Effects 0.000 claims description 2
- 230000008859 change Effects 0.000 abstract description 12
- 230000005291 magnetic effect Effects 0.000 abstract description 12
- 230000000694 effects Effects 0.000 abstract description 7
- 230000005294 ferromagnetic effect Effects 0.000 description 3
- 238000009499 grossing Methods 0.000 description 3
- 230000001052 transient effect Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Abstract
The invention relates to the technical field of parking space state detection, in particular to a parking space state detection method and system based on fusion filtering. According to the invention, the geomagnetic original signal of the geomagnetic sensor at the target parking space is subjected to fusion filtering processing based on the combination of wavelet denoising and Kalman filtering, so that the method has better effect than the traditional method which only uses wavelet denoising, can filter most of external interference, has smoother signal curve and has better continuity. The data of the fusion filtering signal obtained by processing can be rapidly increased or reduced when the parking space state changes, and the sliding standard deviation sequence change amplitude calculated based on the fusion filtering signal can be increased by one order of magnitude, so that the magnetic field strength change condition can be reflected more, and the erroneous judgment and the missed judgment caused by threshold selection can be effectively reduced by carrying out threshold judgment based on the sliding standard deviation sequence. The invention solves the problems of poor signal filtering processing effect and low detection accuracy in the existing method.
Description
Technical Field
The invention relates to the technical field of parking space state detection, in particular to a parking space state detection method, which comprises the following steps: 1. a parking space state detection method based on fusion filtering, 2, a parking space state detection system based on fusion filtering.
Background
The parking space state detection technology, as the name implies, is used for detecting the use condition of the parking space, thereby effectively optimizing the utilization and management of parking resources and reducing traffic jams and environmental pollution.
A more common device today than conventional vehicle detection devices is a geomagnetic sensor. The geomagnetic sensor has the advantages of low cost, easiness in installation and strong anti-interference capability, and whether a vehicle exists or not can be judged through the magnetic field intensity collected by the geomagnetic sensor. In particular, this is because the vehicle is composed of a large amount of ferromagnetic substances, and the vehicle may have a regular influence on the environmental magnetic field when passing through the geomagnetic sensor detection area. Therefore, in the current detection using a geomagnetic sensor, a threshold value is generally set to determine the collected geomagnetic signal so as to realize the detection. However, there are two problems with this threshold determination method: 1, geomagnetic signals acquired by a geomagnetic sensor are processed by a traditional wavelet denoising method, so that a filtering signal is difficult to achieve a better smoothing effect; 2, because the vehicles are of various types and have different influence degrees on the environmental magnetic field, the situation of misjudgment or missed judgment can be easily detected by directly selecting the threshold value according to the geomagnetic signal, and the detection accuracy is influenced.
Disclosure of Invention
Based on the above, it is necessary to provide a parking space state detection method and system based on fusion filtering, aiming at the problems of poor signal filtering processing effect and low detection accuracy in the existing method.
The invention is realized by adopting the following technical scheme:
In a first aspect, the invention discloses a parking space state detection method based on fusion filtering, which comprises the following steps:
Step one, continuously acquiring geomagnetic original signals of a geomagnetic sensor at a target parking space from an initial time t 1 to a current time t K, and forming a geomagnetic original signal sequence G= [ G 1,...,gk,...,gK ]; wherein g k represents the geomagnetic original signal at t k; k is [1, K ];
Step two, fusion filtering processing based on combination of wavelet denoising and Kalman filtering is carried out on the G to obtain a fusion filtering signal sequence Wherein/>Representing the fused filtered signal at t k;
The second step comprises the following steps:
Step 2.1, performing wavelet denoising on the G to obtain a wavelet denoising signal sequence G' = [ G 1′,...,gk′,...,g′K];g′k represents a wavelet denoising signal at t k;
step 2.2, calculating an observed noise variance R based on G, G';
Step 2.3, kalman filtering is performed based on G' and R to obtain
Step three, based onCalculating a sliding standard deviation sequence sigma i, and judging the state of the target parking space according to a judgment rule according to sigma i;
wherein, the judging rule comprises:
If the state of the target parking space at t 1 is that the parking space is idle and the state of the target parking space at [ t 1,tK ] is changed for an even number of times, the state of the target parking space at t K is that the target parking space is idle; if the state of the target parking space at t 1 is that the parking space is idle and the state of the target parking space at [ t 1,tK ] is changed in the odd number of vehicle positions, the state of the target parking space at t K is that the parking space is in a vehicle;
If the state of the target parking space at t 1 is that the parking space is available and the state of the target parking space at [ t 1,tK ] is changed for an even number of times, the state of the target parking space at t K is that the parking space is available; if the state of the target parking space at t 1 is that the parking space is available and the state of the target parking space at [ t 1,tK ] is changed for an odd number of times, the state of the target parking space at t K is that the target parking space is idle;
If σ i exceeds a preset standard deviation threshold σ d and the duration T 0 exceeds a preset time threshold T d, the state of the target parking space is changed; if not, the state of the target parking space is unchanged.
The parking space state detection method based on fusion filtering realizes the method or the process according to the embodiment of the disclosure.
In a second aspect, the present invention discloses a parking space state detection system based on fusion filtering, which uses the parking space state detection method based on fusion filtering of the first aspect.
The parking space state detection system based on fusion filtering comprises: the parking space state judgment system comprises a signal acquisition unit, a filtering processing unit, a sliding standard deviation calculation unit and a parking space state judgment unit.
The signal acquisition unit is used for continuously acquiring geomagnetic original signals of the geomagnetic sensor at the target parking space from an initial time t 1 to a current time t K and forming a geomagnetic original signal sequence G= [ G 1,...,gk,...,gK ]. The filtering processing unit is used for carrying out fusion filtering processing on G based on the combination of wavelet denoising and Kalman filtering to obtain a fusion filtering signal sequenceThe sliding standard deviation calculation unit is used for being based on/>The sliding standard deviation sequence σ i is calculated. The parking space state judging unit is used for judging the state of the target parking space according to the sigma i and the judging rule.
Such fusion filtering-based parking space state detection systems implement methods or processes according to embodiments of the present disclosure.
In a third aspect, a readable storage medium is disclosed. The readable storage medium has stored therein computer program instructions which, when read and executed by a processor, perform the steps of the fusion filtering based parking space state detection method of the first aspect.
The invention also discloses a computer terminal comprising a memory, a processor and a computer program stored on the memory and executable on the processor. The processor, when executing a program, implements the steps of the fusion filtering-based parking space state detection method of the first aspect.
Compared with the prior art, the invention has the following beneficial effects:
1, the geomagnetic original signal of the geomagnetic sensor at the target parking space is subjected to fusion filtering processing based on the combination of wavelet denoising and Kalman filtering, so that the method has better effect than the traditional method which only uses wavelet denoising processing, can filter most of external interference, has smoother signal curve and has better continuity.
2, The data of the fusion filtering signal obtained by processing can be rapidly increased or reduced when the parking space state changes, and the sliding standard deviation sequence change amplitude calculated based on the fusion filtering signal can be increased by one order of magnitude, so that the magnetic field strength change condition can be reflected more, and the misjudgment and missed judgment caused by threshold selection can be effectively reduced by carrying out threshold judgment based on the sliding standard deviation sequence; in addition, the sliding standard deviation sequence can effectively inhibit the fluctuation noise in a small range, and improve the anti-interference capability of detection.
Drawings
Fig. 1 is a flowchart of a parking space state detection method based on fusion filtering in embodiment 1 of the present invention;
FIG. 2 is a data flow diagram of the fusion filtering process of FIG. 1;
FIG. 3 is a flowchart illustrating the operation of the judgment rule in embodiment 1 of the present invention;
FIG. 4 is a comparison chart of geomagnetic original signal sequence, wavelet denoising signal sequence and fusion filtering signal sequence in embodiment 3 of the present invention;
FIG. 5 is a comparison chart of the fusion filtering signal sequence and sliding standard deviation sequence in the embodiment 3 of the present invention;
fig. 6 is a comparison chart of sliding standard deviation sequences and parking space states in embodiment 3 of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It is noted that when an element is referred to as being "mounted to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "disposed on" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "secured to" another element, it can be directly secured to the other element or intervening elements may also be present.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "or/and" as used herein includes any and all combinations of one or more of the associated listed items.
Example 1
Referring to fig. 1, fig. 1 is a flowchart of a parking space state detection method based on fusion filtering in embodiment 1. The object of the detection method is a target parking space on which a geomagnetic sensor is mounted.
Referring to fig. 1, the detection method includes the steps of:
Step one, continuously acquiring geomagnetic original signals of a geomagnetic sensor at a target parking space from an initial time t 1 to a current time t K, and forming a geomagnetic original signal sequence G= [ G 1,...,gk,...,gK ]; wherein g k represents the geomagnetic original signal at t k; k is [1, K ].
In general, the geomagnetic sensor can perform signal acquisition according to a set acquisition period T 0, where for any acquisition time, original signals (including noise) of the geomagnetic axes of x, y and z are acquired and integrated into a signal g.
Step two, fusion filtering processing based on combination of wavelet denoising and Kalman filtering is carried out on the G to obtain a fusion filtering signal sequenceWherein/>Representing the fused filtered signal at t k.
Referring to fig. 2, step two includes:
And 2.1, performing wavelet denoising on the G to obtain a wavelet denoising signal sequence G '= [ G 1′,...,gk′,...,g′K];gk' represents a wavelet denoising signal at t k.
The wavelet denoising can effectively filter noise to achieve the purpose of smoothing signals, but the signal characteristics can be greatly weakened. Since the processing steps of the wavelet denoising are not improved in comparison with the existing method in this embodiment 1, only a simple description will be given here:
the wavelet basis function used for wavelet denoising is Daubechies wavelet;
threshold for wavelet denoising Wherein σ represents the estimated standard deviation of G, and K represents the signal length of G;
the soft threshold function used for wavelet denoising is: Wherein w T is a wavelet coefficient after thresholding; w is the wavelet coefficient before thresholding; t is the threshold used for wavelet denoising.
And 2.2, calculating the observed noise variance R based on G, G'.
Specifically, G, G' is firstly subjected to difference to obtain observation noise, and then the observation noise variance R is calculated.
The process can be formulated as:
Wherein v j is observation noise at t j, v j＝gj-g′j; to observe the noise mean value,/>
Step 2.3, kalman filtering is performed based on G' and R to obtain
The Kalman filtering is combined with wavelet denoising, so that the effects of noise filtering, signal smoothing and the like can be achieved, and meanwhile, the filtered signal is ensured to have the signal characteristics of the original signal.
The Kalman filtering is divided into two processes of updating observation and updating system state, wherein the updating observation is to estimate the state of the next moment through the estimated value of the previous moment, the current state and the covariance priori estimated value. Updating the system state is to update and correct the system state according to the measured value at the current moment and to perform posterior estimation on the current state.
Specifically, step 2.3 includes:
2.3.1, constructing a geomagnetic state observation equation and a covariance matrix prediction equation, and calculating:
in the method, in the process of the invention, Geomagnetic state prediction at t h; p h-1 is the prediction covariance matrix at t h-1; /(I)Predicting a prediction covariance matrix at t h; a is a geomagnetic state transition matrix, and generally 1 is taken; b is a control input matrix, generally taking 0; q is the variance matrix of the input white noise at t h.
Step 2.3.2, constructing a Kalman gain matrix calculation equation and a covariance matrix update equation, and calculating the Kalman gain matrix calculation equation and the covariance matrix update equation:
Wherein K h is a Kalman gain matrix at t h; p h is the prediction covariance matrix at t h; the observed noise variance matrix when R is t h; h is geomagnetic observation matrix, and generally takes 1.
Step 2.3.4, constructing a geomagnetic state update equation, and calculating:
in the method, in the process of the invention, A fused filtered signal at t h; g h is the actual measurement at t h.
Step three, based onAnd calculating a sliding standard deviation sequence sigma i, and judging the state of the target parking space according to the judgment rule according to sigma i.
First, σ i has a calculation formula:
wherein D is the length of the sliding window; For/> A signal with a middle sequence number i; /(I)For the signal mean value corresponding to the sliding window,/>
Then, if σ i is obtained, it is determined whether the target parking space has changed:
If σ i exceeds a preset standard deviation threshold σ d and the duration T 0 exceeds a preset time threshold T d, the state of the target parking space is changed; if not, the state of the target parking space is unchanged. Wherein sigma d∈[25,35];Td＝N*T0;N∈[3,5],T0 is the signal acquisition period of the geomagnetic sensor at the target parking space. In this example 1, σ d is 30 and N is 3.
The reason why the double judgment condition is considered to be set is that: although the method uses the sliding standard deviation as a data judgment basis, the fluctuation caused by signal noise and the like can be eliminated; however, if the signal transient change caused by the non-vehicle appears in the target parking space, the signal transient change caused by the non-vehicle is regarded as the vehicle driving in and out or can cause erroneous judgment, so that not only the fact that sigma i exceeds the preset standard deviation threshold sigma d but also the fact that the duration time T 0 exceeds the preset time threshold T d is considered, and the signal transient change caused by the non-vehicle can be filtered out, and the detection accuracy is ensured.
Then, the judgment rule is set as:
If the state of the target parking space at t 1 is that the parking space is idle and the state of the target parking space at [ t 1,tK ] is changed for an even number of times, the state of the target parking space at t K is that the target parking space is idle; if the state of the target parking space at t 1 is that the parking space is free and the state of the odd number of vehicle positions is changed at [ t 1,tK ] together, the state of the target parking space at t K is that the parking space is available.
If the state of the target parking space at t 1 is that the parking space is available and the state of the target parking space at [ t 1,tK ] is changed for an even number of times, the state of the target parking space at t K is that the parking space is available; if the state of the target parking space at t 1 is that the parking space is available and the state of the target parking space at [ t 1,tK ] is changed by an odd number of times, the state of the target parking space at t K is that the target parking space is free.
Referring to fig. 3, a flow chart illustrating the operation of the rule is shown. It should be noted that, the state of the target parking space at the initial time t 1 may be set according to the actual situation, and may be set manually during the initialization of the geomagnetic sensor, or may be set automatically after the situation of the target parking space is captured by the camera.
Example 2
Embodiment 2 discloses a parking space state detection system based on fusion filtering, which uses the parking space state detection method based on fusion filtering of embodiment 1.
The parking space state detection system based on fusion filtering comprises: the parking space state judgment system comprises a signal acquisition unit, a filtering processing unit, a sliding standard deviation calculation unit and a parking space state judgment unit.
The signal acquisition unit is configured to continuously acquire a geomagnetic raw signal of the geomagnetic sensor at the target parking space from an initial time t 1 to a current time t K, and to compose a geomagnetic raw signal sequence g= [ G 1,...,gk,...,gK ]. The filtering processing unit is configured to perform fusion filtering processing on G based on combination of wavelet denoising and Kalman filtering to obtain a fusion filtering signal sequenceThe sliding standard deviation calculation unit is configured to be based on/>The sliding standard deviation sequence σ i is calculated. The parking space state judging unit is configured to judge the state of the target parking space according to the judging rule based on sigma i.
Example 3
This embodiment 3 discloses a specific application example of the detection method of embodiment 1, and compares it with the conventional threshold judgment method.
In this embodiment 3, a geomagnetic sensor is installed at a parking space, and an initial time state is set to be idle, and then geomagnetic original signals of a 5-wheel vehicle driving-in and driving-out process are continuously collected after the initial time. Wherein, the 1 st wheel, the 3 rd wheel and the 4 th wheel adopt ferromagnetic vehicles; the 2 nd and 5 th wheels adopt weak magnetic vehicles.
First, the geomagnetic raw signal is processed in the manner of step 2, and the result is shown in fig. 4. It can be seen that:
1.1, even if wavelet denoising treatment is carried out, the corresponding signal change amplitude of the ferromagnetic vehicles and the weakly magnetic vehicles is not affected: the influence of the strong magnetic vehicle on the magnetic field intensity is larger (the signal change amplitude of the 1 st wheel, the 3 rd wheel and the 4 th wheel is larger), and the influence of the weak magnetic vehicle on the magnetic field intensity is smaller (the signal change amplitude of the 2 nd wheel and the 5 th wheel is smaller); when the threshold is selected according to the wavelet denoising signal, if a larger threshold is selected, the weak magnetic vehicle is missed. And the wavelet denoising signal also has small-amplitude fluctuation (the reason is caused by signal noise) when the parking space state is not changed, if a smaller threshold value is selected, the situation of misjudgment can be generated. This is consistent with the problems mentioned in the background.
1.2, Compared with the process of denoising by using only wavelets, the fusion filtering process has better effect: the fusion filtering signal is smoother and has better continuity.
Then, a sliding standard deviation sequence is calculated based on the fused filtered signal sequence, and the result is referred to fig. 5. It can be seen that:
2.1, the fusion filtering signal sequence and the sliding standard deviation sequence can correspond to each other, and the state change of the parking space can be intuitively reflected: when a vehicle enters or exits a parking space, the sliding standard deviation sequence shows a rapid increasing trend, and the amplitude change is more severe; and when the vehicle is stably parked in the parking space or no vehicle is present in the parking space, the sliding standard deviation sequence becomes 0 and remains stable.
The sliding standard deviation sequence almost does not fluctuate when the parking space state is unchanged, so that the fluctuation noise in a small range can be effectively restrained, and the anti-interference capability of detection is improved.
2.2, The order of magnitude of the fusion filtering signal is only 10 -1, and the order of magnitude of the sliding standard deviation can reach 10, so that the space for selecting the threshold value is much larger and more reasonable.
Finally, parking space state judgment is performed based on the sliding standard deviation sequence, and the result is shown in fig. 6. It can be seen that when the low position is 0, the parking space is idle; when the lower position is 1, the parking place is indicated to be on; the result is also consistent with the judgment rule, verifying the feasibility of the method of example 1.
In this example 3, in-situ monitoring was also performed, and 120 vehicle entrance or exit events were detected by using the detection method of example 1 and the conventional threshold detection method, respectively, and the detection accuracy was compared, as shown in table 1.
Table 1 comparison of detection accuracy
It can be seen that the detection method of embodiment 1 can improve the detection accuracy compared to the conventional threshold detection method.
Example 4
Embodiment 4 discloses a readable storage medium having stored therein computer program instructions which, when read and executed by a processor, perform the steps of the fusion filtering based parking space state detection method of embodiment 1.
When the method of embodiment 1 is applied, the application may be performed in the form of software, such as a program designed to be independently executable on a computer-readable storage medium, which may be a usb disk, designed as a U-shield, through which the program of the entire method is designed to be started by external triggering.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The present embodiment 4 also provides a computer terminal including a memory, a processor, and a computer program stored on the memory and executable on the processor. The steps of the parking space state detection method based on fusion filtering of embodiment 1 are implemented when the processor executes the program.
When the method of embodiment 1 is applied, the application can be performed in the form of software, such as a program designed to run independently, and the program is installed on a computer terminal, where the computer terminal can be a computer, a smart phone, a control system, other internet of things equipment, and the like. The method of embodiment 1 may also be designed as an embedded running program, and installed on a computer terminal, such as a single chip microcomputer.
The above examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (10)
1. The parking space state detection method based on fusion filtering is characterized by comprising the following steps of:
Step one, continuously acquiring geomagnetic original signals of a geomagnetic sensor at a target parking space from an initial time t 1 to a current time t K, and forming a geomagnetic original signal sequence G= [ G 1,...,gk,...,gK ]; wherein g k represents the geomagnetic original signal at t k; k is [1, K ];
Step two, fusion filtering processing based on combination of wavelet denoising and Kalman filtering is carried out on the G to obtain a fusion filtering signal sequence Wherein/>Representing the fused filtered signal at t k;
The second step comprises the following steps:
Step 2.1, performing wavelet denoising on the G to obtain a wavelet denoising signal sequence G '= [ G' 1,...,g′k,...,g′K];g′k represents a wavelet denoising signal at t k;
step 2.2, calculating an observed noise variance R based on G, G';
Step 2.3, kalman filtering is performed based on G' and R to obtain
Step three, based onCalculating a sliding standard deviation sequence sigma i, and judging the state of the target parking space according to a judgment rule according to sigma i;
wherein, the judging rule comprises:
If the state of the target parking space at t 1 is that the parking space is idle and the state of the target parking space at [ t 1,tK ] is changed for an even number of times, the state of the target parking space at t K is that the target parking space is idle; if the state of the target parking space at t 1 is that the parking space is idle and the state of the target parking space at [ t 1,tK ] is changed in the odd number of vehicle positions, the state of the target parking space at t K is that the parking space is in a vehicle;
If the state of the target parking space at t 1 is that the parking space is available and the state of the target parking space at [ t 1,tK ] is changed for an even number of times, the state of the target parking space at t K is that the parking space is available; if the state of the target parking space at t 1 is that the parking space is available and the state of the target parking space at [ t 1,tK ] is changed for an odd number of times, the state of the target parking space at t K is that the target parking space is idle;
If σ i exceeds a preset standard deviation threshold σ d and the duration T 0 exceeds a preset time threshold T d, the state of the target parking space is changed; if not, the state of the target parking space is unchanged.
2. The fusion filtering-based parking space state detection method according to claim 1, wherein the state of the target parking space at the initial time t 1 is set according to the actual situation.
3. The parking space state detection method based on fusion filtering according to claim 1, wherein in step 2.1, the wavelet basis function used for wavelet denoising is Daubechies wavelet;
threshold for wavelet denoising Wherein σ represents the estimated standard deviation of G, and K represents the signal length of G;
the soft threshold function used for wavelet denoising is: Wherein w T is a wavelet coefficient after thresholding; w is the wavelet coefficient before thresholding; t is the threshold used for wavelet denoising.
4. The method for detecting a parking space state based on fusion filtering according to claim 3, wherein in step 2.2,
Wherein v j is observation noise at t j, v j＝gj-g′j; to observe the noise mean value,/>
5. The fusion filtering-based parking space state detection method according to claim 4, wherein step 2.3 comprises:
2.3.1, constructing a geomagnetic state observation equation and a covariance matrix prediction equation, and calculating:
in the method, in the process of the invention, Geomagnetic state prediction at t h; p h-1 is the prediction covariance matrix at t h-1; /(I)Predicting a prediction covariance matrix at t h; a is geomagnetic state transition matrix; b is a control input matrix; the variance matrix of the input white noise when Q is t h;
step 2.3.2, constructing a Kalman gain matrix calculation equation and a covariance matrix update equation, and calculating the Kalman gain matrix calculation equation and the covariance matrix update equation:
Wherein K h is a Kalman gain matrix at t h; p h is the prediction covariance matrix at t h; the observed noise variance matrix when R is t h; h is geomagnetic observation matrix;
Step 2.3.4, constructing a geomagnetic state update equation, and calculating:
in the method, in the process of the invention, A fused filtered signal at t h; g h is the actual measurement at t h.
6. The fusion filtering-based parking space state detection method according to claim 1, wherein in the third step,
Wherein D is the length of the sliding window; For/> A signal with a middle sequence number i; /(I)For the signal mean value corresponding to the sliding window,
7. The fusion filtering-based parking space state detection method according to claim 1, wherein in the third step,
σd∈[25,35]；
T d＝N*T0; wherein N epsilon [3,5], T 0 is the signal acquisition period of the geomagnetic sensor at the target parking space.
8. A fusion filter-based parking space state detection system, characterized in that it uses the fusion filter-based parking space state detection method according to any one of claims 1 to 7;
the parking space state detection system based on fusion filtering comprises:
A signal acquisition unit for continuously acquiring geomagnetic raw signals of the geomagnetic sensor at the target parking space from an initial time t 1 to a current time t K, and composing a geomagnetic raw signal sequence g= [ G 1,...,gk,...,gK ];
a filtering processing unit for performing fusion filtering processing based on combination of wavelet denoising and Kalman filtering on G to obtain a fusion filtering signal sequence
A sliding standard deviation calculation unit for calculating a sliding standard deviation based on the sliding standard deviationCalculating a sliding standard deviation sequence sigma i;
And
And the parking space state judging unit is used for judging the state of the target parking space according to the sigma i and the judging rule.
9. A readable storage medium, wherein computer program instructions are stored in said readable storage medium, which, when read and executed by a processor, perform the steps of the fusion filtering based parking space state detection method according to any one of claims 1-8.
10. A computer terminal comprising a memory, a processor, and a computer program stored on the memory and executable on the processor; the processor, when executing a program, implements the steps of the fusion filtering-based parking space state detection method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410132060.2A CN117972629A (en) | 2024-01-30 | 2024-01-30 | Parking space state detection method and system based on fusion filtering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410132060.2A CN117972629A (en) | 2024-01-30 | 2024-01-30 | Parking space state detection method and system based on fusion filtering |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117972629A true CN117972629A (en) | 2024-05-03 |
Family
ID=90847256
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410132060.2A Pending CN117972629A (en) | 2024-01-30 | 2024-01-30 | Parking space state detection method and system based on fusion filtering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117972629A (en) |
-
2024
- 2024-01-30 CN CN202410132060.2A patent/CN117972629A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107884757B (en) | Constant false alarm target detection method and device and vehicle | |
| WO2017118510A1 (en) | Method, computer program and device for reducing an interference of temporary communication resources used for a wireless communication between a vehicle key and a vehicle | |
| DE102012211616B4 (en) | TRAFFIC DENSITY ESTIMATE | |
| DE102012217157A1 (en) | Vehicle mode for a car wash | |
| DE102013227199B4 (en) | Apparatus and method for removing noise from an ultrasound system | |
| CN112009470B (en) | Vehicle running control method, device, equipment and storage medium | |
| US11636002B2 (en) | Information processing device and information processing method | |
| CN109696665B (en) | Method, device and equipment for processing measurement data of ultrasonic sensor | |
| CN117972629A (en) | Parking space state detection method and system based on fusion filtering | |
| CN112070802B (en) | Target tracking method, device, equipment and computer readable storage medium | |
| CN111706199B (en) | Vehicle window position judging method and device, vehicle, equipment and medium | |
| CN112560689A (en) | Parking space detection method and device, electronic equipment and storage medium | |
| CN109991627B (en) | Narrow-band interference suppression method and module | |
| CN108169094B (en) | Filter screen cleanliness detection method, sensor and air treatment equipment | |
| CN111177878A (en) | Method, device and terminal for screening derivative simulation scenes | |
| CN116363542A (en) | Off-duty event detection method, apparatus, device and computer readable storage medium | |
| JP2019159622A (en) | Vehicle detection device, vehicle detection method, and vehicle detection program | |
| CN109995458B (en) | Narrow-band interference suppression method and module | |
| KR100772380B1 (en) | An extended method of noise-adaptive motion detection | |
| CN111350437A (en) | Vehicle window position judging method and device, vehicle, equipment and medium | |
| CN110987945A (en) | Defect detection method, defect detection device and detection method of touch display panel | |
| US20230254473A1 (en) | Apparatus for improving an impact detecting performance of a built-in camera, system having the same, and method thereof | |
| CN110852192B (en) | Method and device for determining noise data, storage medium, terminal and vehicle | |
| CN117553695B (en) | Method and device for calculating vehicle height and computer storage medium | |
| CN116453065B (en) | Road surface foreign matter throwing identification method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication |