Highway vehicle positioning point association method and device

Abstract

The invention provides an expressway vehicle positioning point association method and device, and the method comprises the steps: obtaining a vehicle vibration signal in a target monitoring region, carrying out the framing calculation of the vehicle vibration signal, obtaining a corresponding root-mean-square sequence, determining a peak value of the root-mean-square sequence through a peak value searching algorithm, and obtaining a positioning point of the expressway vehicle. Obtaining first positioning information that the target vehicle passes through the target monitoring area, combining second positioning information located in an association area with the first positioning information by using a nearest neighbor association method, and determining target positioning information that the target vehicle passes through the target monitoring area; the associated area is an area adjacent to the target monitoring area. Accurate positioning of road vehicles is realized by applying a peak value search algorithm in a root-mean-square sequence, and at the same time, a nearest neighbor association method is combined, and the positioning information of adjacent areas is used for supplementation, so that necessary association range support is provided for association of the positioning information.

Description

Technical Field

[0001] The present invention relates to the technical field of signal processing, and in particular, to a method and device for associating vehicle positioning points on highways. Background Art

[0002] Distributed fiber optic vibration sensing technology is based on the Rayleigh scattering principle. When light of a certain intensity is injected into an optical fiber, about one-thousandth of the Rayleigh scattering echo will be received, and these echoes will bring back the vibration information of the glass lattice in the optical fiber. Any external vibration wave will affect the glass lattice in the optical fiber, causing the lattice to vibrate at the same frequency. By demodulating and analyzing this vibration information and passing through a series of algorithms such as noise reduction, analysis, and restoration, the vibration information in the vibration area can be collected and analyzed, and the position of the vibration area can be determined. In highway vehicle detection, the application of fiber optic grating sensing technology has gradually become an effective detection means. Through the vibration signals sensed by fiber optic sensors, it is possible to achieve high-precision monitoring of the minute vibrations generated when a vehicle passes by. However, there is currently no relevant research on associating vehicle positioning points on highways based on distributed fiber optic vibration sensing. For the problem of extracting vehicle trajectories on highways based on distributed fiber optic vibration sensing, existing technologies mainly rely on image processing means rather than directly providing solutions from the characteristics of vibration sensing signals. This processing flow may lead to errors or omissions in the final trajectory extraction results due to the influence of image resolution and external environmental interference, and thus it is difficult to be widely used. Summary of the Invention

[0003] In view of this, the present invention proposes a method and device for associating vehicle positioning points on highways.

[0004] The technical solution of the present invention is realized as follows: In a first aspect of the present invention, a method for associating vehicle positioning points on highways is provided, including:

[0005] Obtaining vehicle vibration signals within a target monitoring area;

[0006] Performing frame-by-frame calculation on the vehicle vibration signals to obtain a corresponding root mean square sequence, and using a peak search algorithm to determine the peak of the root mean square sequence, so as to obtain first positioning information of the target vehicle passing through the target monitoring area;

[0007] Using the nearest neighbor association method to combine second positioning information within an association area with the first positioning information to determine target positioning information of the target vehicle passing through the target monitoring area; the association area is an area adjacent to the target monitoring area, and the second positioning information is the positioning information of the target vehicle determined based on the vehicle vibration signals monitored within the association area.

[0008] Based on the above technical solutions, preferably, obtaining the vehicle vibration signal in the target monitoring area includes:

[0009] Using a UWFBG sensing array and an unbalanced Michelson interferometer to obtain the vehicle vibration signal in the target monitoring area.

[0010] Based on the above technical solutions, preferably, performing frame-by-frame calculation on the vehicle vibration signal to obtain the corresponding root mean square sequence includes using the following formula to determine the root mean square sequence:

[0011]

[0012] where N represents the frame length, x[n] is each frame signal after frame division, n is the frame number, and RMS represents the root mean square value of the signal.

[0013] Based on the above technical solutions, preferably, using the peak search algorithm to determine the peak of the root mean square sequence to obtain the first positioning information of the target vehicle passing through the target monitoring area includes using the following formula to determine the peak of the root mean square sequence:

[0014] {1 < i < n} ∧ {R[i - 1] ≤ R[i]} ∧ {R[i] > R[i + 1]};

[0015] where R[i] is the root mean square sequence, n is the total number of the root mean square sequence, and ∧ represents the intersection.

[0016] Based on the above technical solutions, preferably, using the nearest neighbor association method to combine the second positioning information in the association area with the first positioning information to determine the target positioning information of the target vehicle passing through the target monitoring area includes using the following formula to determine the association area in combination with the first positioning information:

[0017]

[0018] where (y n , x n ) is the first positioning information, and a, b, and c are the acceleration, speed, and position parameters of the trajectory corresponding to the positioning information;

[0019] Based on the first positioning information, the acceleration, the speed, and the position parameters, obtain the motion trajectory of the target vehicle, and determine the association area based on the motion trajectory.

[0020] Based on the above technical solutions, preferably, using the nearest neighbor association method to combine the second positioning information in the association area with the first positioning information to determine the target positioning information of the target vehicle passing through the target monitoring area includes:

[0021] Obtain the second positioning information corresponding to the positioning points within the associated area;

[0022] Use the nearest neighbor association method to select the target positioning point closest to the center of the associated area from the positioning points in the associated area, and determine the second positioning information corresponding to the target positioning point as the target positioning information.

[0023] Based on the above technical solutions, preferably, after using the nearest neighbor association method to combine the second positioning information within the associated area with the first positioning information to determine the target positioning information of the target vehicle passing through the target monitoring area, the method further includes:

[0024] When it is detected that the current positioning information fails to be associated with new positioning information at least M times in N consecutive association processes, determine that the current positioning information is invalid; the current positioning information is any example of the positioning information in the target positioning information.

[0025] Even more preferably, a second aspect of the present invention provides a freeway vehicle positioning point association device, including: a data acquisition module, a frame-by-frame search module, and an information determination module; wherein,

[0026] The data acquisition module is configured to acquire the vehicle vibration signal within the target monitoring area;

[0027] The frame-by-frame search module is configured to perform frame-by-frame calculation on the vehicle vibration signal to obtain the corresponding root mean square sequence, and use the peak search algorithm to determine the peak of the root mean square sequence to obtain the first positioning information of the target vehicle passing through the target monitoring area;

[0028] The information determination module is configured to use the nearest neighbor association method to combine the second positioning information within the associated area with the first positioning information to determine the target positioning information of the target vehicle passing through the target monitoring area; the associated area is an area adjacent to the target monitoring area, and the second positioning information is the positioning information of the target vehicle determined based on the vehicle vibration signal monitored within the associated area.

[0029] Even more preferably, a third aspect of the present invention provides an electronic device, including a processor and a memory; the memory stores a computer program, wherein the computer program, when executed by the processor, implements the freeway vehicle positioning point association method described in the first aspect.

[0030] Even more preferably, a fourth aspect of the present invention provides a computer storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the freeway vehicle positioning point association method described in the first aspect.

[0031] A method and device for associating vehicle positioning points on highways according to the present invention have the following beneficial effects compared with the prior art:

[0032] 1. Convert the vehicle vibration signal into a root mean square sequence, and apply a peak search algorithm in the root mean square sequence to determine the peak of the root mean square sequence. The peak can reflect the time point when the vehicle passes by, thus achieving precise positioning of the vehicle on the road surface. At the same time, using the nearest neighbor association method, combined with the currently known positioning information and the association area, predict the trajectory of the target vehicle and determine the positioning information of the target vehicle, providing the necessary association range support for the association of positioning information.

[0033] 2. Adopt the signal framing theory and root mean square value calculation to concentrate the energy of the road surface vibration signal, cut the continuous vibration signal into multiple shorter signal segments, so as to more accurately capture and analyze the characteristics of the road surface vibration signal. By calculating the root mean square value, further quantify the energy of the road surface vibration signal, improving the accuracy and reliability of obtaining the position of the vehicle on the highway.

[0034] 3. Based on the validity judgment, further ensure the reliability of the output of valid positioning information. Through the validity judgment, reduce the influence of false positioning information on the final positioning result. The positioning information association result successfully achieves the association goal of valid positioning information, can accurately reflect the trajectory information of the vehicle on the highway pavement, and successfully realizes the accurate mapping from the road surface vibration signal to the vehicle trajectory. Brief Description of the Drawings

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0036] Figure 1 It is a schematic flowchart of a method for associating vehicle positioning points on highways provided by an embodiment of the present invention;

[0037] Figure 2 It is a schematic structural diagram of a distributed acoustic wave sensing system based on a UWFBG array provided by an embodiment of the present invention;

[0038] Figure 3 It is a schematic diagram of the application scenario of the distributed acoustic wave sensing system provided by an embodiment of the present invention;

[0039] Figure 4 It is a schematic diagram of the intensity distribution of vehicle vibration signals provided by an embodiment of the present invention;

[0040] Figure 5Enhanced comparison chart of the original waveform of the vehicle vibration signal and the vehicle target signal after matched filtering provided by the embodiment of the present invention;

[0041] Figure 6 Schematic diagram of the signal framing principle provided by the embodiment of the present invention;

[0042] Figure 7 Schematic diagram of the root mean square sequence and positioning result of a certain measurement area of three channels within a certain time period provided by the embodiment of the present invention;

[0043] Figure 8 Schematic diagram of the positioning result of the vehicle provided by the embodiment of the present invention;

[0044] Figure 9 Schematic diagram of the nearest neighbor association of highway vehicle positioning information provided by the embodiment of the present invention;

[0045] Figure 10 Schematic diagram of the associated result of highway pavement vehicle positioning information provided by the embodiment of the present invention;

[0046] Figure 11 Schematic diagram of the process of determining the vehicle trajectory by using the highway vehicle positioning point association method provided by the embodiment of the present invention;

[0047] Figure 12 Schematic diagram of the nearest neighbor association of highway vehicle positioning information provided by the embodiment of the present invention

[0048] Figure 13 Schematic diagram of the structure of an electronic device provided by the embodiment of the present invention. Detailed implementation manners

[0049] Next, in combination with the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0050] In some embodiments, as Figure 1 shown, Figure 1 Schematic diagram of the process of a highway vehicle positioning point association method provided by the embodiment of the present invention; A highway vehicle positioning point association method provided by the present invention includes:

[0051] S110, obtaining the vehicle vibration signal within the target monitoring area.

[0052] Here, the target monitoring area can be the sensing area that can perceive the road surface vibration signals when multiple optical cable measurement areas laid under the highway road surface are organized in a certain arrangement. The optical cable measurement area is a distributed vibration sensor composed of an ultra-weak fiber array (UWFBG) based on fiber optic sensing technology laid under the highway road surface. These vibration sensors can be used to collect the vibration signals of vehicles passing through this sensing area.

[0053] In some embodiments, S110, obtaining the vehicle vibration signals in the target monitoring area includes:

[0054] Using the UWFBG sensing array and the unbalanced Michelson interferometer to obtain the vehicle vibration signals in the target monitoring area.

[0055] The UWFBG sensing array, that is, the ultra-weak fiber Bragg grating sensing array, is mainly used for distributed and quasi-distributed perception of external information. The unbalanced Michelson interferometer uses the method of amplitude splitting to generate two light beams to achieve interference and form different interference patterns.

[0056] In an alternative embodiment, please refer to Figure 2 , Figure 2 which is the structural schematic diagram of the distributed acoustic wave sensing system based on the UWFBG array provided by the embodiment of the present invention; this system is mainly composed of two parts: an unbalanced Michelson interferometer and a UWFBG sensing array. Among them, the unbalanced Michelson interferometer is composed of two Faraday mirrors, a 3*3 coupler, and a delay optical fiber with a length of L. The working principle of the DAS system is that a narrow linewidth laser is used as the light source, and the continuous light emitted by it is modulated into an optical pulse sequence by an electro-optic modulator (EOM), then amplified by an erbium-doped fiber amplifier (EDFA), and injected into the UWFBG sensing array. The UWFBG sensing array is composed of n fiber Bragg gratings, and their intervals are all L. The pulsed light reflected from the UWFBG sensing array enters the unbalanced Michelson interferometer through two circulators. In the unbalanced Michelson interferometer, the delay optical fiber is used to make up the optical path difference between adjacent ultra-weak fiber Bragg gratings, and the phase change caused by the change of the optical pulse between adjacent ultra-weak fiber Bragg gratings in the fiber is demodulated to recover the amplitude of the time-domain vehicle vibration signal. Finally, the three-way light of the 3*3 coupler is collected by three photodetectors and converted into an electrical signal through the photoelectric conversion process, that is, the original vehicle vibration signal.

[0057] Combined with the characteristics of vehicle driving on the highway, the deployment scheme of the distributed acoustic wave sensing system based on the UWFBG array can refer to Figure 3 , Figure 3Schematic diagram of the application scenario of the distributed acoustic wave sensing system provided by the embodiment of the present invention. The optical cables are evenly arranged on the upper base surface below each lane of the highway, and each lane is independently monitored by the corresponding optical cable channel. Figure 2 The sensor system and Figure 3 The deployment scenarios shown are combined. Figure 3 For example, the layout of channel 1, channel 2 and channel 3 can correspond to the lanes, and each channel is equipped with multiple sensors connected in series to form a sensor array. The distance between each sensor is L, and the value of L can be determined according to the sensing distance of the sensor and the range of the target detection area. The pulse emitted by the narrow linewidth laser is reflected by the sensor array and passes through two circulators into the unbalanced Michelson interferometer. After the laser pulse is reflected by the sensor array, it carries the modulation information of the sensor array, and the photoelectric conversion is completed by the photodetector to obtain an electrical signal, and the intensity or phase change of the electrical signal reflects the modulation information of the sensor array.

[0058] In one example, the distribution of vibration intensity in the optical cable monitoring area obtained during a certain period of time can be referred to as Figure 4 , Figure 4 A schematic diagram of the distribution of vehicle vibration signal intensity provided in an embodiment of the present invention; the trajectories of multiple vehicles are shown as bright white segments. Bright white segments represent strong signals, which usually correspond to direct reflections of target vehicles. In contrast, darker lines are the accompanying effects caused by interference from adjacent lanes during the data acquisition phase, and these lines should be regarded as interference to the current lane. The interference may be caused by: the reflection signal of the vehicle in the adjacent lane is weak, but still captured by the sensor; the limitation of the sensor resolution causes the signal of the adjacent lane to be aliased to the current lane; interference caused by environmental noise or multipath effects (such as road surface reflections). The positioning of the vehicle in the sensing area is achieved based on the data collected in a single measurement area. Here, a single measurement area is a series of sensors in a single lane that can capture vehicle motion information in a specific area. By analyzing the brightness, shape and position of the vehicle trajectory, the exact position of the vehicle in the current lane can be determined.

[0059] In another example, see Figure 5 , Figure 5Schematic diagram of the relationship between road surface vibration intensity and time provided by an embodiment of the present invention; the relationship between the highway road surface vibration intensity and time in a certain measurement area of three channels within a certain time period is described. When a vehicle passes through this measurement area, there is a large amplitude, and the corresponding interference shows a weak change trend. Here, an amplitude threshold can be set, and signals greater than this threshold are identified as vehicle signals, while signals less than this threshold are identified as interference signals. Considering that vehicle signals may contain higher frequency components, while interference signals tend to be concentrated in a lower frequency range, vehicle signals and interference signals can also be separated in the frequency domain through Fourier transform or wavelet transform, or a machine learning algorithm can be used to train a model to automatically identify vehicle signals and interference signals.

[0060] S120, perform frame-by-frame calculation on the vehicle vibration signal to obtain the corresponding root mean square sequence, and use the peak search algorithm to determine the peak of the root mean square sequence to obtain the first positioning information of the target vehicle passing through the target monitoring area.

[0061] In some embodiments, S120, performing frame-by-frame calculation on the vehicle vibration signal to obtain the corresponding root mean square sequence includes using the following formula to determine the root mean square sequence:

[0062]

[0063] where N represents the frame length, x[n] is each frame signal after frame division, n is the frame number, and RMS represents the root mean square value of the signal.

[0064] After frame division and calculation of the root mean square value, the original vehicle vibration signal can be characterized by the root mean square sequence. The root mean square sequence concentrates the energy of the vehicle vibration signal, and its rising and falling trends are very obvious, which can correspond to the process of the vehicle entering and leaving this measurement area.

[0065] In an example, please refer to Figure 6 , Figure 6 Schematic diagram of the signal frame division principle provided by an embodiment of the present invention; through signal frame division, complex continuous signals can be simplified into a series of short signal segments that are easy to process, thus facilitating subsequent feature extraction and analysis. The frame length refers to the duration of each frame signal, and the frame shift is the time interval between adjacent frames. The frame length should be long enough to capture the main features of the signal, but not too long so that the signal characteristics change. An appropriate frame length can ensure that the characteristics of the speech signal remain relatively stable during this period. The frame shift should be balanced according to the continuity of the signal and the computational efficiency. A smaller frame shift means a higher overlap degree between frames, which helps to capture more fine signal changes, but will increase the computational amount, while a larger frame shift can reduce the computational amount. In Figure 6Among them, the frame length is 4 data points and the frame shift is 0.5. In the data processing of this embodiment, the frame length can be set to 0.1 times the sampling rate, and the frame shift is set to 0.5. After selecting the frame length and the frame shift, the continuous signal is segmented according to the frame length and the frame shift, a window function is applied to each frame of the signal, and the windowed signal is further processed, so that the required features can be extracted.

[0066] In some embodiments, in S120, a peak search algorithm is used to determine the peak of the root mean square sequence, and the first positioning information of the target vehicle passing through the target monitoring area is obtained, including using the following formula to determine the peak of the root mean square sequence:

[0067] {1 < i < n} ∧ {R[i - 1] ≤ R[i]} ∧ {R[i] > R[i + 1]};

[0068] Wherein, R[i] is the root mean square sequence, n is the total number of the root mean square sequence, and ∧ represents the intersection. Here, by taking the intersection of {1 < i < n}, R[i - 1] ≤ R[i] and R[i] > R[i + 1], the intersection of the three is used to determine the peak of the root mean square sequence.

[0069] Exemplarily, please refer to Figure 7 , Figure 7 is a schematic diagram of the root mean square sequence and the positioning result of a certain measurement area of three channels within a certain time period provided by the embodiment of the present invention; applying the peak search algorithm to the root mean square sequence can locate the time point when the vehicle passes through this measurement area. The root mean square value can be used to reflect the vibration or impact of the vehicle. When the vehicle passes through the measurement area, the vibration signal generated by it will be captured by the sensor and converted into an electrical signal, and then the root mean square value sequence is calculated. Due to the vibration and impact of the vehicle, obvious peaks may appear in the root mean square value. Therefore, through the peak search algorithm, the time points when these peaks appear can be located, so as to determine the time when the vehicle passes through the measurement area. As Figure 7 shown, the peak appears near 51s.

[0070] Generalizing the above positioning process to the measurement areas of the entire target monitoring area can obtain the vehicle positioning result in the target monitoring area. Please refer to Figure 8 , Figure 8 is a schematic diagram of the vehicle positioning result provided by the embodiment of the present invention. Due to noise or other interference factors, some false peaks may be generated. Therefore, it is necessary to screen the peaks according to the actual situation to determine which peaks are valid, that is, the time points that truly represent the vehicle passing through the measurement area. As Figure 8As shown, since the sensors in the target monitoring area can only capture the instantaneous information when a vehicle passes by, each positioning point only represents the position of the target vehicle at a certain time point. This information is isolated in time and space and cannot directly reflect the complete driving trajectory of the vehicle. To generate effective target positioning information, it is necessary to associate the positioning information belonging to the same vehicle. This can not only restore the complete driving trajectory of the vehicle but also be used for the calculation and analysis of parameters such as vehicle speed, acceleration, and driving direction. Despite the existence of some false positioning points, the positioning results of the vehicles can still accurately reflect the time points when each vehicle passes through the target monitoring area.

[0071] S130. Use the nearest neighbor association method to combine the second positioning information located within the association area with the first positioning information to determine the target positioning information of the target vehicle passing through the target monitoring area; the association area is the area adjacent to the target monitoring area, and the second positioning information is the positioning information of the target vehicle determined based on the vehicle vibration signals monitored within the association area.

[0072] In some embodiments, S130. Use the nearest neighbor association method to combine the second positioning information located within the association area with the first positioning information to determine the target positioning information of the target vehicle passing through the target monitoring area, including using the following formula to determine the association area in combination with the first positioning information:

[0073]

[0074] where, (y n , x n ) is the first positioning information, and a, b, and c are the acceleration, speed, and position parameters of the trajectory corresponding to the positioning information;

[0075] Based on the first positioning information, acceleration, speed, and position parameters, obtain the motion trajectory of the target vehicle, and determine the association area based on the motion trajectory.

[0076] The above formula can be transformed. Let The above formula can be simplified to obtain: y = Xm; where, m = (X T X) -1 X T y. Thus, based on the existing multiple groups of positioning information, the values of a, b, and c can be calculated, and the acceleration, speed, and position parameters of the trajectory corresponding to the corresponding positioning points can be determined.

[0077] Exemplarily, reference can be made to Figure 9 , Figure 9Schematic diagram of nearest neighbor association of highway vehicle positioning information provided by embodiments of the present invention; here, for each driving state (such as acceleration, deceleration, constant speed), two parallel lines are drawn, and the slopes of these two lines reflect the speed and acceleration of the vehicle in that state. The distance between the parallel lines can be adjusted according to the accuracy of the positioning information and the stability of the vehicle driving. The area between the two parallel lines is defined as the association range. If the positioning points of the vehicle fall within this range, they are considered to be consecutive positioning information belonging to the same vehicle. When the driving state of the vehicle changes (such as from acceleration to constant speed, or from constant speed to deceleration), the slopes and positions of the parallel lines will be adjusted accordingly to reflect the new speed and acceleration. The speed and acceleration parameters can be calculated by analyzing the existing positioning information in the positioning information. Specifically, the average speed of the vehicle can be calculated by analyzing the time interval and distance difference between adjacent positioning points. By analyzing the rate of change of speed over time, the acceleration of the vehicle can be calculated.

[0078] In some embodiments, in S130, using the nearest neighbor association method to combine the second positioning information located within the association area with the first positioning information to determine the target positioning information of the target vehicle passing through the target monitoring area, includes:

[0079] Obtain the second positioning information corresponding to the positioning points within the association area;

[0080] Using the nearest neighbor association method, select the target positioning point closest to the center of the association area from the positioning points within the association area, and determine the second positioning information corresponding to the target positioning point as the target positioning information.

[0081] In this embodiment, after determining the acceleration, speed, and position parameters, combining the trend of the positioning points in the current positioning information, multiple association areas that the target will pass through in the future can be delimited. Among all the possible positioning points that fall within the association area, select the positioning point closest to the center of the association area as the target positioning point, and thus obtain the target positioning information.

[0082] In some embodiments, after S130, using the nearest neighbor association method to combine the second positioning information located within the association area with the first positioning information to determine the target positioning information of the target vehicle passing through the target monitoring area, further includes:

[0083] In the case where it is detected that in the current positioning information, at least M times of new positioning information cannot be associated in N consecutive association processes, determine that the current positioning information is invalid; the current positioning information is any example of the positioning information in the target positioning information.

[0084] In this embodiment, the effective positioning information of multiple channels can be accurately derived, and the false positioning points of each channel do not affect the final positioning point association result. Within the sensing and monitoring area of the highway, the positioning information generated after the validity judgment can accurately describe the current traffic conditions on the road surface, that is, an accurate mapping from vehicle vibration signals to vehicle driving trajectories is realized.

[0085] By performing a validity judgment on the positioning results of each channel, obviously unreasonable positioning points are eliminated, such as by setting thresholds, using statistical methods or machine learning algorithms. On this basis, the continuity and consistency characteristics of the vehicle driving trajectory are used to perform correlation analysis on the multi-channel positioning results. By comparing the positioning information at different time points and different sensor channels, inconsistent false positioning points are identified and excluded. In one example, please refer to Figure 10 , Figure 10 is a schematic diagram of the association result of vehicle positioning information on the highway road surface provided by the embodiment of the present invention; under the current experimental section, through a large amount of data analysis, it can be determined that N can take the value of 7 and M can take the value of 5.

[0086] In an alternative embodiment, please refer to Figure 11 , Figure 11 is a schematic flowchart of determining the vehicle trajectory using the highway vehicle positioning point association method provided by the embodiment of the present invention; the distributed fiber optic vibration sensor can continuously monitor vibration signals along the fiber optic, and is suitable for the monitoring requirements of long distances and large ranges such as highways. When a vehicle passes by, a specific vibration signal will be generated on the fiber optic. After obtaining the vehicle vibration signals in each measurement area of the highway using the distributed fiber optic vibration sensor, signal framing and root mean square value calculation are performed. Framing processing helps to reduce the complexity of data processing and makes subsequent signal analysis more efficient. Furthermore, the root mean square peak is determined by finding the peak of the root mean square sequence. On this basis, using the nearest neighbor association of vehicle positioning information, candidate positioning information is generated. After validity judgment, invalid positioning information is discarded, and effective positioning information is output to describe the vehicle trajectory.

[0087] In some embodiments, please refer to Figure 12 , Figure 12 is a schematic structural diagram of a highway vehicle positioning point association device provided by the embodiment of the present invention. The present invention provides a highway vehicle positioning point association device 1200, including: a data acquisition module 1210, a framing search module 1220, and an information determination module 1230; wherein,

[0088] The data acquisition module 1210 is configured to acquire vehicle vibration signals within the target monitoring area;

[0089] The frame-by-frame search module 1220 is configured to perform frame-by-frame calculation on the vehicle vibration signal to obtain the corresponding root-mean-square sequence, and use the peak search algorithm to determine the peak of the root-mean-square sequence, so as to obtain the first positioning information of the target vehicle passing through the target monitoring area;

[0090] The information determination module 1230 is configured to use the nearest neighbor association method to combine the second positioning information located in the association area with the first positioning information to determine the target positioning information of the target vehicle passing through the target monitoring area; the association area is an area adjacent to the target monitoring area, and the second positioning information is the positioning information of the target vehicle determined based on the vehicle vibration signal monitored in the association area.

[0091] In some embodiments, the data acquisition module 1210 is specifically configured as follows:

[0092] Use the UWFBG sensing array and the unbalanced Michelson interferometer to obtain the vehicle vibration signal in the target monitoring area.

[0093] In some embodiments, the frame-by-frame search module 1220 is specifically configured to determine the root-mean-square sequence using the following formula:

[0094]

[0095] where N represents the frame length, x[n] is each frame signal after frame division, n is the frame number, and RMS represents the root-mean-square value of the signal.

[0096] In some embodiments, the frame-by-frame search module 1220 is specifically configured to determine the peak of the root-mean-square sequence using the following formula:

[0097] {1 < i < n} ∧ {R[i - 1] ≤ R[i]} ∧ {R[i] > R[i + 1]};

[0098] where R[i] is the root-mean-square sequence, n is the total number of the root-mean-square sequence, and ∧ represents the intersection. Here, by taking the intersection of {1 < i < n}, R[i - 1] ≤ R[i] and R[i] > R[i + 1], the intersection of the three is determined as the peak of the root-mean-square sequence.

[0099] In some embodiments, the information determination module 1230 is specifically configured to combine the second positioning information located in the association area with the first positioning information using the following formula:

[0100]

[0101] where (y n , x n ) is the first positioning information, and a, b, and c are the acceleration, speed, and position parameters of the trajectory corresponding to the positioning information;

[0102] Based on the first positioning information, acceleration, speed, and position parameters, obtain the motion trajectory of the target vehicle, and determine the associated area based on the motion trajectory.

[0103] In some embodiments, the information determination module 1230 is specifically configured to:

[0104] Obtain the second positioning information corresponding to the positioning points within the associated area;

[0105] Use the nearest neighbor association method to select the target positioning point closest to the center of the associated area from the positioning points in the associated area, and determine the second positioning information corresponding to the target positioning point as the target positioning information.

[0106] In some embodiments, the highway vehicle positioning point association device further includes a verification module; the verification module is specifically configured to:

[0107] When it is detected that the current positioning information fails to associate with new positioning information at least M times in N consecutive association processes, determine that the current positioning information is invalid; the current positioning information is any one of the positioning information in the target positioning information.

[0108] It should be noted that the highway vehicle positioning point association method provided in the embodiments of the present application and the highway vehicle positioning point association method provided in the embodiments of the present application are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned highway vehicle positioning point association method, and the repeated parts will not be elaborated.

[0109] In some embodiments, please refer to Figure 13 , Figure 13 is a schematic structural diagram of an electronic device provided in an embodiment of the present application. An electronic device 1300 provided in an embodiment of the present application includes a processor 1310 and a memory 1320; the memory 1320 stores a computer program, and when the computer program is executed by the processor, the above-mentioned highway vehicle positioning point association method is implemented.

[0110] Specifically, the processor 1310 may include, for example, a general microprocessor, an instruction set processor, and / or a related chipset and / or a dedicated microprocessor (such as an application specific integrated circuit (ASIC)), and so on. The processor 1310 may also include on-board memory for caching purposes. The processor 1310 may be a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiments of the present application.

[0111] The memory 1320 can be, for example, any medium capable of containing, storing, transmitting, propagating, or transporting instructions. For example, the memory 1320 may include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, components, or propagation media. Specific examples of the memory 1320 include: magnetic storage devices such as magnetic tapes or hard disk drives (HDDs); optical storage devices such as compact discs (CD-ROMs); it can also be, for example, random access memory (RAM) or flash memory; and / or wired / wireless communication links.

[0112] The present application also provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the above-described freeway vehicle positioning point association method. The computer-readable medium can be included in the device / apparatus / system described in the above embodiments; or it can exist separately without being assembled into the device / apparatus / system. The above computer-readable medium carries one or more programs, which, when the one or more programs are executed, implement the method according to the embodiments of the present application.

[0113] According to an embodiment of the present application, the computer-readable medium can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer-readable storage medium can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, device, or component. In the present application, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries the computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate, or transport a program for use by or in conjunction with an instruction execution system, device, or component. The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wired, optical fiber cable, radio frequency signal, etc., or any suitable combination of the above.

[0114] Those skilled in the art will understand that the features recited in the various embodiments and / or claims of this application can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly recited in this application. In particular, without departing from the spirit and teachings of this application, the features recited in the various embodiments and / or claims of this application can be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of this application. Therefore, the scope of this application should not be limited to the above embodiments, but should be determined not only by the appended claims, but also by the equivalents of the appended claims. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for associating vehicle positioning points on an expressway, characterized in that, Including: Obtain vehicle vibration signals within a target monitoring area; Perform frame-by-frame calculation on the vehicle vibration signals to obtain a corresponding root mean square sequence, and use a peak search algorithm to determine the peak of the root mean square sequence, so as to obtain the first positioning information of the target vehicle passing through the target monitoring area; Use the nearest neighbor association method to combine the second positioning information located within the association area with the first positioning information to determine the target positioning information of the target vehicle passing through the target monitoring area; the association area is an area adjacent to the target monitoring area, and the second positioning information is the positioning information of the target vehicle determined based on the vehicle vibration signals monitored within the association area.

2. The highway vehicle positioning point association method according to claim 1, characterized in that, The obtaining of the vehicle vibration signals within the target monitoring area includes: Use a UWFBG sensing array and an unbalanced Michelson interferometer to obtain vehicle vibration signals within the target monitoring area.

3. The freeway vehicle positioning point association method according to claim 1, characterized in that, The performing of frame-by-frame calculation on the vehicle vibration signals to obtain a corresponding root mean square sequence includes using the following formula to determine the root mean square sequence: where N represents the frame length, x[n] is each frame of the signal after frame division, n is the frame number, and RMS represents the root mean square value of the signal.

4. The method for associating highway vehicle positioning points according to claim 1, wherein, The using of the peak search algorithm to determine the peak of the root mean square sequence and obtain the first positioning information of the target vehicle passing through the target monitoring area includes using the following formula to determine the peak of the root mean square sequence: {1 < i < n} ∧ {R[i - 1] ≤ R[i]} ∧ {R[i] > R[i + 1]}; where R[i] is the root mean square sequence, n is the total number of the root mean square sequence, and ∧ represents the intersection.

5. The method for associating highway vehicle positioning points according to claim 1, characterized in that, The using of the nearest neighbor association method to combine the second positioning information located within the association area with the first positioning information to determine the target positioning information of the target vehicle passing through the target monitoring area includes using the following formula to determine the association area in combination with the first positioning information: Among them, (y n , x n ) is the first positioning information, and a, b, and c are the acceleration, velocity, and position parameters of the corresponding trajectory; Based on the first positioning information, the acceleration, the speed, and the position parameters, obtain the motion trajectory of the target vehicle, and determine the association area based on the motion trajectory.

6. The method for associating highway vehicle positioning points according to claim 5, wherein, The using of the nearest neighbor association method to combine the second positioning information located within the association area with the first positioning information to determine the target positioning information of the target vehicle passing through the target monitoring area includes: Obtain the second positioning information corresponding to the positioning points within the association area; Use the nearest neighbor association method to select the target positioning point closest to the center of the association area from the positioning points within the association area, and determine the second positioning information corresponding to the target positioning point as the target positioning information.

7. The method for associating highway vehicle positioning points according to claim 1, wherein After using the nearest neighbor association method to combine the second positioning information located within the association area with the first positioning information to determine the target positioning information of the target vehicle passing through the target monitoring area, the method further includes: When it is detected that the current positioning information fails to be associated with new positioning information at least M times in N consecutive association processes, determine that the current positioning information is invalid; the current positioning information is any example of the target positioning information.

8. An associated device for vehicle positioning points on an expressway, characterized in that, Including: A data acquisition module, a frame-by-frame search module, and an information determination module; where The data acquisition module is configured to acquire vehicle vibration signals within a target monitoring area; The frame division and peak search module is configured to perform frame division calculation on the vehicle vibration signals to obtain corresponding root mean square sequences, and use a peak search algorithm to determine the peaks of the root mean square sequences, thereby obtaining first positioning information of the target vehicle passing through the target monitoring area; The information determination module is configured to combine second positioning information located within an association area with the first positioning information by using a nearest neighbor association method to determine target positioning information of the target vehicle passing through the target monitoring area; the association area is an area adjacent to the target monitoring area, and the second positioning information is positioning information of the target vehicle determined based on vehicle vibration signals monitored within the association area.

9. An electronic device, comprising a processor and a memory; the memory stores a computer program, wherein, The computer program, when executed by the processor, implements the highway vehicle positioning point association method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that, A computer program is stored thereon, wherein the computer program, when executed by the processor, implements the highway vehicle positioning point association method according to any one of claims 1 to 7.

Images