A vehicle continuous tracking method, device and electronic device based on grating array

Abstract

The present invention relates to a vehicle continuous tracking method, device and electronic device based on a grating array, belonging to the field of intelligent traffic signal processing technology, wherein the method comprises: obtaining a vehicle vibration positioning signal based on an ultra-weak fiber Bragg grating array, and extracting the vibration energy corresponding to the vehicle vibration positioning signal; constructing a vehicle motion model according to the vibration energy of the vehicle; obtaining observation data of multiple vehicles according to the vehicle motion model, and predicting the running state of a single vehicle in a preset monitoring area according to the observation data, and obtaining a motion trajectory prediction result of each vehicle; based on the motion trajectory prediction result of each vehicle, determining the tracking continuity of multiple vehicles according to the correlation between the observation data and the vehicle. The present invention solves the technical problem in the prior art that only positioning and identifying vehicles is difficult to fully and accurately reflect real-time traffic conditions.

Description

Technical Field

[0001] The invention relates to the technical field of intelligent traffic signal processing, and in particular to a vehicle continuous tracking method, device and electronic equipment based on a grating array. Background Art

[0002] Real-time highway traffic monitoring systems play an important role in road traffic management and planning, early warning of traffic violations, relieving traffic congestion, and preventing fatal road traffic accidents. Traditional traffic vehicle monitoring technologies mainly include radar, lidar, camera, GPS, and wireless sensor networks. However, these technologies have monitoring blind spots, are sensitive to weather and environmental factors, and are relatively expensive, and cannot meet the needs of long-distance continuous traffic monitoring on highways. In recent years, with the rapid development of distributed fiber optic sensing technology, distributed acoustic sensing (DAS), as a dynamic vibration sensing technology, has been widely used to measure and collect vibration positioning signals caused by vehicles. However, the intensity of the backward Rayleigh scattered light of DAS is weak in the long-distance transmission of optical fiber signals, resulting in relatively low signal-to-noise ratio and accuracy. In addition, due to the limitations of the fiber preparation process and demodulation method, large-scale multiplexing of gratings over long distances cannot be achieved.

[0003] Compared with DAS, grating arrays have the advantages of high signal-to-noise ratio, high spatial resolution, fast sensing response and dynamic measurement, and provide a new way for long-distance continuous traffic monitoring on highways. However, due to the complex traffic environment and multi-source noise interference on highways, it is difficult to fully and accurately reflect the real-time traffic conditions by only locating and identifying vehicles. Summary of the invention

[0004] In view of this, it is necessary to provide a vehicle continuous tracking method, device and electronic equipment based on a grating array to solve the technical problem in the prior art that only the vehicle is located and identified, and it is difficult to fully and accurately reflect the real-time traffic conditions.

[0005] In order to solve the above problems, the present invention provides a vehicle continuous tracking method based on a grating array, comprising:

[0006] Obtaining a vehicle vibration positioning signal based on an ultra-weak fiber Bragg grating array, and extracting the vibration energy corresponding to the vehicle vibration positioning signal;

[0007] Construct a vehicle motion model based on the vibration energy of the vehicle;

[0008] Obtain observation data of multiple vehicles according to the vehicle motion model, and predict the running state of a single vehicle in a preset monitoring area according to the observation data to obtain the motion trajectory prediction result of each vehicle;

[0009] Based on the motion trajectory prediction results of each vehicle, the tracking continuity of multiple vehicles is determined according to the correlation between the observation data and the vehicles.

[0010] In a possible implementation, constructing a vehicle motion model according to the vibration energy of the vehicle includes:

[0011] According to the vibration energy of the vehicle, the vehicle motion model is constructed using the preset nonlinear constant turning rate and speed method.

[0012] In a possible implementation, the acquisition of observation data of multiple vehicles according to the vehicle motion model, and prediction of the running state of a single vehicle in a preset monitoring area according to the observation data to obtain a motion trajectory prediction result of each vehicle includes:

[0013] The preset adaptive extended Kalman filter method is used to predict the operating state of a single vehicle based on the observed data to obtain the motion trajectory prediction result of each vehicle.

[0014] In a possible implementation, the step of determining the tracking continuity of multiple vehicles based on the motion trajectory prediction result of each vehicle and the correlation between the observation data and the vehicle includes:

[0015] The preset joint probability data association method is used to match the correlation between the observed data and each vehicle to determine the trajectory of the vehicle.

[0016] In a possible implementation, the method of using a preset joint probability data association method to match the correlation between the observation data and each vehicle to determine the trajectory of the vehicle includes:

[0017] Preprocess the vibration positioning signal obtained at time k to obtain a target positioning signal;

[0018] A preset joint probability data association method is used to compare the target positioning signal with the predicted value of the operating state of a single vehicle;

[0019] If the target positioning signal is within the tracking gate of any single vehicle, the target positioning signal is successfully associated with the predicted value of the running state of the single vehicle, and the target positioning data is determined to be the motion data of the corresponding single vehicle;

[0020] The single vehicle corresponding to the target positioning data is set as the target vehicle, and the preset adaptive extended Kalman filter method is used to update the motion state of the target vehicle to determine the continuous trajectory of the target vehicle.

[0021] In a possible implementation, the comparing the target positioning signal with the predicted value of the running state of a single vehicle by using a preset joint probability data association method further includes:

[0022] If the target positioning signal is not within the tracking gate of any single vehicle, the target positioning signal fails to be associated with the predicted value of the running state of the single vehicle. The target positioning signal is used as the initial state of the vehicle, and the preset adaptive extended Kalman filter method is used to perform initial processing on the vehicle's motion state.

[0023] In a possible implementation, after comparing the target positioning signal with the predicted value of the running state of a single vehicle by using a preset joint probability data association method, the method further includes:

[0024] The vehicle track management strategy is updated based on the comparison result between the target positioning signal and the predicted value of the operating status of a single vehicle.

[0025] In a second aspect, the present invention further provides a vehicle continuous tracking device based on a grating array, comprising:

[0026] An acquisition module, used to acquire a vehicle vibration positioning signal based on an ultra-weak fiber Bragg grating array, and extract vibration energy corresponding to the vehicle vibration positioning signal;

[0027] A motion model building module, used to build a vehicle motion model according to the vibration energy of the vehicle;

[0028] The prediction module is used to obtain the observation data of multiple vehicles according to the vehicle motion model, and predict the running state of a single vehicle in a preset monitoring area according to the observation data to obtain the motion trajectory prediction result of each vehicle;

[0029] The association module is used to determine the tracking continuity of multiple vehicles based on the motion trajectory prediction results of each vehicle and the association between the observation data and the vehicles.

[0030] In a third aspect, the present invention further provides an electronic device, comprising: a processor and a memory;

[0031] The memory stores a computer-readable program executable by the processor;

[0032] When the processor executes the computer-readable program, the steps in the vehicle continuous tracking method based on the grating array as described above are implemented.

[0033] In a fourth aspect, the present invention further provides a computer-readable storage medium storing one or more programs, wherein the one or more programs can be executed by one or more processors to implement the steps in the grating array-based vehicle continuous tracking method as described above.

[0034] The beneficial effects of the present invention are: firstly, a vehicle vibration positioning signal based on an ultra-weak fiber Bragg grating array is obtained, and the vibration energy corresponding to the vehicle vibration positioning signal is extracted; then, a vehicle motion model is constructed according to the vibration energy of the vehicle; thereby, observation data of multiple vehicles are obtained according to the vehicle motion model, and the running state of a single vehicle in a preset monitoring area is predicted according to the observation data, and the motion trajectory prediction result of each vehicle is obtained; finally, based on the motion trajectory prediction result of each vehicle, the tracking continuity of multiple vehicles is determined according to the correlation between the observation data and the vehicle. The present invention obtains a continuous and stable vehicle driving trajectory by predicting, estimating and associating vehicle status information between frames, which can support the extraction of multiple key traffic parameter information, and can continuously and stably track vehicles in different complex traffic scenarios, which can well meet the needs of real-time vehicle monitoring on highways. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A method flow chart of an embodiment of a vehicle continuous tracking method based on a grating array provided by the present invention;

[0036] Figure 2 A schematic diagram of an embodiment of a vehicle vibration sensing system based on a grating array in the vehicle continuous tracking method based on a grating array provided by the present invention;

[0037] Figure 3 A schematic diagram of the principle of the adaptive extended Kalman filter method in the vehicle continuous tracking method based on the grating array provided by the present invention;

[0038] Figure 4 A flowchart of an embodiment of step S103 in the vehicle continuous tracking method based on a grating array provided by the present invention;

[0039] Figure 5 A schematic diagram of a multi-target tracking scenario in the vehicle continuous tracking method based on a grating array provided by the present invention;

[0040] Figure 6 is a schematic diagram of an embodiment of a vehicle continuous tracking device based on a grating array provided by the present invention;

[0041] Figure 7 It is a schematic diagram of the operating environment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0042] The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0043] On highways, vehicles are dynamic and move at high speeds, and traditional single target tracking methods may not be able to effectively handle the tracking of multiple vehicles. In order to achieve accurate vehicle monitoring and tracking in such complex environments, it is necessary to combine advanced tracking algorithms and data association techniques.

[0044] A specific embodiment of the present invention discloses a vehicle continuous tracking method based on a grating array, see Figure 1 ,include:

[0045] S101, obtaining a vehicle vibration positioning signal based on an ultra-weak fiber Bragg grating array, and extracting vibration energy corresponding to the vehicle vibration positioning signal;

[0046] S102, constructing a vehicle motion model according to the vibration energy of the vehicle;

[0047] S103, obtaining observation data of multiple vehicles according to the vehicle motion model, and predicting the running state of a single vehicle in a preset monitoring area according to the observation data to obtain a motion trajectory prediction result of each vehicle;

[0048] S104: Based on the motion trajectory prediction result of each vehicle and according to the correlation between the observation data and the vehicle, determine the tracking continuity of multiple vehicles.

[0049] In this embodiment, firstly, a vehicle vibration positioning signal based on an ultra-weak fiber Bragg grating array is obtained, and the vibration energy corresponding to the vehicle vibration positioning signal is extracted; then, a vehicle motion model is constructed according to the vibration energy of the vehicle; thus, the observation data of multiple vehicles are obtained according to the vehicle motion model, and the running state of a single vehicle in a preset monitoring area is predicted according to the observation data, and the motion trajectory prediction result of each vehicle is obtained; finally, based on the motion trajectory prediction result of each vehicle, the tracking continuity of multiple vehicles is determined according to the correlation between the observation data and the vehicle. The present invention predicts and estimates the vehicle state information between frames and correlates and matches to obtain a continuous and stable vehicle driving trajectory, which can support the extraction of a variety of key traffic parameter information, such as the total number of vehicles, average speed, traffic flow and density, driving direction, headway and spacing, etc. Moreover, the vehicle can be continuously and stably tracked in different complex traffic scenarios, which can well meet the needs of real-time vehicle monitoring on highways.

[0050] The vibrations generated by the vehicle during driving will affect the structure with a certain frequency and intensity. In step S101, these vibration signals are captured by the UWFBG array, and the vibration energy of the vehicle in different frequency bands can be calculated. This information can be used to locate and track the movement trajectory of the vehicle. Among them, the ultraweak fiber Bragg gratings (UWFBGs) are manufactured by an online writing system, in which the ultraviolet light emitted by the 248nm excimer laser passes through the phase mask at a fixed period and irradiates the drawn optical fiber.

[0051] In a specific embodiment, a vehicle vibration sensing system based on a grating array is deployed, such as Figure 2 As shown. The highway vehicle vibration sensing system based on UWFBG array includes: four parallel optical cables buried 30cm underground at the center of the four lanes, with a grating spacing of 5m, so as to achieve lane-level vehicle monitoring. The lanes where the four UWFBG arrays are located are defined as lane I, lane II, lane III and lane IV. The monitoring center consists of a demodulator and a server. The vibration generated by the vehicle during driving can be captured in real time by the UWFBG array sensor network, and the real-time vibration response is transmitted to the demodulator for demodulation at a sampling frequency of 1kHz. The server receives the demodulated vibration data for real-time analysis.

[0052] In step S102, in order to reflect the real motion state of the vehicle, such as the real-time position, real-time speed and acceleration of the vehicle, and to predict the state change information of the vehicle at the next moment, a motion model of the vehicle is constructed. Specifically, the motion model of the vehicle can be established through models such as a constant acceleration model, a constant turning rate and speed model, a nonlinear dynamic model and a motion equation combination model.

[0053] In some embodiments, considering the complex traffic behaviors of vehicles such as lane changing and overtaking in an actual highway environment, and the vehicle speed and lane changing angular velocity are basically constant in a relatively short period of time, this embodiment selects nonlinear CTRV to model the vehicle, thereby achieving accurate estimation and prediction of the real-time motion state of the vehicle.

[0054] Specifically, the embodiment of the present invention can also obtain the effective energy information of the vehicle by performing vehicle positioning based on the vibration signal collected by the UWFBG array. Therefore, the sixth energy parameter introduced on the basis of the traditional CTRV state vector is expressed as follows:

[0055]

[0056] in, Indicated in The state vector of the vehicle at time and They represent the lane the vehicle is in and the real-time mileage position in meters. Indicates the real-time speed of the vehicle. The yaw angle indicates the vehicle's direction of travel. is the estimated angular velocity, is the real-time vibration energy of the vehicle.

[0057] In step S103, in the context of the vehicle motion model, observation data refers to actual data about the vehicle state collected by various sensors and measuring devices. These data are used to estimate the current state of the vehicle and are the basis for state prediction. The observation data includes but is not limited to the vehicle's speed data, position data, acceleration data, observation distance data, and direction data.

[0058] The preset monitoring area refers to a geographical area where a system or device is designated as requiring real-time monitoring and data collection in a specific scenario. In this embodiment, a grating array is arranged in the predicted monitoring area.

[0059] It should be further explained that a nonlinear motion model, machine learning method or filtering method can be used to predict the running state of a single vehicle based on the observed data to obtain the motion trajectory prediction result of each vehicle. In this embodiment, an adaptive extended Kalman filter method is used.

[0060] Specifically, see Figure 3 ,By utilizing the measurement information obtained from the vehicle positioning of the UWFBG array, the new information and residuals are recursively calculated to continuously adjust and correct the noise covariance matrix and, thus achieving the optimal estimation of the vehicle state.

[0061] In some embodiments, the prediction result of the motion trajectory of each vehicle is based on the correlation between the observation data and the vehicle to determine the tracking continuity of multiple vehicles. Data association algorithm, multi-target tracking algorithm, graph model and network flow method can be used. In this embodiment, the joint probability data association method is used, please refer to Figure 4 ,include:

[0062] S401, preprocessing the vibration positioning signal obtained at time k to obtain a target positioning signal;

[0063] S402, using a preset joint probability data association method to compare the target positioning signal with the predicted value of the running state of a single vehicle;

[0064] S403, if the target positioning signal is within the tracking gate of any single vehicle, the target positioning signal is successfully associated with the predicted value of the running state of the single vehicle, and the target positioning data is determined to be the motion data of the corresponding single vehicle;

[0065] S404: Set the single vehicle corresponding to the target positioning data as the target vehicle, and use a preset adaptive extended Kalman filter method to update the motion state of the target vehicle to determine the continuous trajectory of the target vehicle.

[0066] Before step S401, the method also includes obtaining the vehicle positioning result of the UWFBG array at the moment, and performing energy non-maximum suppression preprocessing to remove false positioning information caused by vehicles with larger mass in adjacent lanes, thereby obtaining processed measurement data.

[0067] Among them Figure 5 In the multi-target tracking scenario shown in the figure, the joint probabilistic data association law assumes that Shared moments A measurement falls within the target tracking gate and is called a valid measurement. The effective measurement set at time can be expressed as:

[0068]

[0069] From 1 to The cumulative set of valid measurements in all target tracking gates at the moment can be expressed as:

[0070]

[0071] JPDA uses a confirmation matrix to describe the association between valid measurements and each target tracking gate, which is defined as follows:

[0072]

[0073] in, Indicates the serial number of the valid measurement, Indicates the serial number of the target vehicle, The value is 0 or 1. Indicates measurement Fell into the target Inside the tracking door, The opposite is true. Indicates that there is no target. The first column of is set to 1, because each measurement may be caused by false alarm or clutter, such as Figure 5 Shown in the lower right corner.

[0074] By splitting the confirmation matrix, we can get several feasible matrices, which are recorded as , and its corresponding event is called a feasible joint event. At the same time, the splitting needs to meet two conditions: 1) Each measurement can only come from one target or clutter; 2) Each target can only produce one measurement at most. Assume for The set of all feasible joint events at a certain moment is the event space. is the number of joint events, expressed as follows:

[0075]

[0076] in, For the joint events, indicating A possible match between an effective measurement and each target. Therefore, the feasible matrix can be expressed as:

[0077] in, Indicated in Joint event measurement From the goal ,otherwise .

[0078] According to Bayes' rule, The cumulative set of all valid measurements at the moment As a condition, the joint event The conditional probability is expressed as follows:

[0079]

[0080] in, is the normalization constant, is the clutter density, For the goal The detection probability, It is a measurement-related indicator, indicating that the measurement Is it related to the real target? It is the target detection indicator, indicating that the target Is it related to measurement? for The amount of clutter in For and target Associated actual measurements obey Gaussian distribution (this paper represents the dimension of measurement), is expressed as follows:

[0081]

[0082] in, for Time measurement With the goal The new breath between The target The corresponding innovation covariance matrix.

[0083] Finally, considering all joint events, we can get Time measurement With the goal Related events , and the corresponding association probability can be calculated by the following formula:

[0084]

[0085] It is worth noting that the above gives This means that there is no measurement or target. association, and also indicates that all measurements and targets The associated probabilities must sum to 1.

[0086] Furthermore, the method of comparing the target positioning signal with the predicted value of the running state of a single vehicle by using a preset joint probability data association method further includes:

[0087] If the target positioning signal is not within the tracking gate of any single vehicle, the target positioning signal fails to be associated with the predicted value of the running state of the single vehicle. The target positioning signal is used as the initial state of the vehicle, and the preset adaptive extended Kalman filter method is used to perform initial processing on the vehicle's motion state.

[0088] Furthermore, if the existing target vehicle is not successfully associated with any valid target positioning signal, the vehicle track is in a lost state, and relevant conditions are judged for it, so that the track is deleted.

[0089] In some embodiments, after comparing the target positioning signal with the predicted value of the running state of a single vehicle using a preset joint probability data association method, the method further includes:

[0090] The vehicle track management strategy is updated based on the comparison result between the target positioning signal and the predicted value of the operating status of a single vehicle.

[0091] In this embodiment, vehicle track management plays an important role in the vehicle tracking process. By performing operations such as track initiation, maintenance and deletion on each tracked vehicle, false vehicles and vehicles that have gone out of the positioning range can be effectively eliminated during vehicle positioning, thereby ensuring the reliability, stability and effectiveness of the tracking method. The following track management strategy is designed:

[0092] 1) For the start of the new target vehicle’s track, if the vehicle can be associated with the target positioning signal within a continuous range of multiple frames, the vehicle’s track start is considered successful;

[0093] 2) For the track maintenance of the existing target vehicle, reset its lost frames to 0 after each status update. If the vehicle meets the starting threshold frame number, its track start is marked as successful;

[0094] For vehicles in the lost state, determine whether the vehicle track is successfully started. If not, it is considered a false vehicle and the track is deleted directly. If successful, and the number of frames lost by the vehicle is less than the specified threshold, it is considered that there may be a vehicle missed detection in the current frame. In order to maintain the continuity of the vehicle track, continue to predict its state. If the number of frames lost by the vehicle is greater than the threshold, it is considered that the vehicle has left the highway and the track is deleted.

[0095] Based on the above-mentioned vehicle continuous tracking method based on grating array, the embodiment of the present invention also provides a vehicle continuous tracking device based on grating array, please refer to Figure 6 ,include:

[0096] An acquisition module 610 is used to acquire a vehicle vibration positioning signal based on an ultra-weak fiber Bragg grating array and extract vibration energy corresponding to the vehicle vibration positioning signal;

[0097] A motion model building module 620 is used to build a vehicle motion model according to the vibration energy of the vehicle;

[0098] Prediction module 630, used to obtain observation data of multiple vehicles according to the vehicle motion model, and predict the running state of a single vehicle in a preset monitoring area according to the observation data to obtain a motion trajectory prediction result of each vehicle;

[0099] The association module 640 is used to determine the tracking continuity of multiple vehicles based on the motion trajectory prediction result of each vehicle and the association between the observation data and the vehicle.

[0100] like Figure 7 As shown, based on the above-mentioned vehicle continuous tracking method based on the grating array, the present invention also provides an electronic device, which can be a computing electronic device such as a mobile terminal, a desktop computer, a notebook, a palm computer, and a server. The electronic device includes a processor 710, a memory 720, and a display 730. Figure 7 Only some components of the electronic device are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0101] In some embodiments, the memory 720 may be an internal storage unit of the electronic device, such as a hard disk or memory of the electronic device. In other embodiments, the memory 720 may also be an external storage electronic device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory 720 may also include both an internal storage unit of the electronic device and an external storage electronic device. The memory 720 is used to store application software and various types of data installed in the electronic device, such as program codes installed in the electronic device. The memory 720 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a vehicle continuous tracking program 740 based on a grating array is stored on the memory 720, and the vehicle continuous tracking program 740 based on a grating array can be executed by the processor 710, thereby realizing the vehicle continuous tracking method based on a grating array in each embodiment of the present application.

[0102] In some embodiments, the processor 710 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 720, such as executing a vehicle continuous tracking method based on a grating array.

[0103] In some embodiments, the display 730 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 730 is used to display information of the vehicle continuous tracking electronic device based on the grating array and to display a visual user interface. The components 710-730 of the electronic device communicate with each other through a system bus.

[0104] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0105] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A vehicle continuous tracking method based on a grating array, characterized in that: include: Obtaining a vehicle vibration positioning signal based on an ultra-weak fiber Bragg grating array, and extracting the vibration energy corresponding to the vehicle vibration positioning signal; According to the vibration energy corresponding to the vehicle vibration positioning signal, the vehicle motion model is constructed using a nonlinear constant turning rate and speed model: in, Indicated in The state vector of the vehicle at time and They represent the lane the vehicle is in and the real-time mileage position in meters. Indicates the real-time speed of the vehicle. is the yaw angle, indicating the direction of vehicle travel. is the estimated angular velocity, is the real-time vibration energy of the vehicle; Obtain observation data of multiple vehicles according to the vehicle motion model, and predict the running state of a single vehicle in a preset monitoring area according to the observation data to obtain the motion trajectory prediction result of each vehicle; The trajectory tracking result of each vehicle is determined according to the correlation between the motion trajectory prediction result of each vehicle and the vehicle vibration positioning signal.

2. The vehicle continuous tracking method based on grating array according to claim 1, characterized in that: The method of obtaining observation data of multiple vehicles according to the vehicle motion model and predicting the running state of a single vehicle in a preset monitoring area according to the observation data to obtain a motion trajectory prediction result of each vehicle includes: The preset adaptive extended Kalman filter method is used to predict the operating state of a single vehicle based on the observed data to obtain the motion trajectory prediction result of each vehicle.

3. The vehicle continuous tracking method based on grating array according to claim 1, characterized in that: The step of determining the trajectory tracking result of each vehicle according to the correlation between the motion trajectory prediction result of each vehicle and the vehicle vibration positioning signal comprises: A preset joint probability data association method is used to match the correlation between the vehicle vibration positioning signal and each vehicle to determine the vehicle trajectory of each vehicle.

4. The vehicle continuous tracking method based on grating array according to claim 3 is characterized in that: The method of using a preset joint probability data association method to match the correlation between the vehicle vibration positioning signal and each vehicle to determine the vehicle trajectory of each vehicle includes: Preprocess the vibration positioning signal obtained at time k to obtain a target positioning signal; A preset joint probability data association method is used to compare the target positioning signal with the predicted value of the operating state of a single vehicle; If the target positioning signal is within the tracking gate of any single vehicle, the target positioning signal is successfully associated with the predicted value of the running state of the single vehicle, and the target positioning data is determined to be the motion data of the corresponding single vehicle; The single vehicle corresponding to the target positioning data is set as the target vehicle, and the preset adaptive extended Kalman filter method is used to update the motion state of the target vehicle to determine the continuous trajectory of the target vehicle.

5. The vehicle continuous tracking method based on grating array according to claim 4, characterized in that: The method of comparing the target positioning signal with the predicted value of the running state of a single vehicle by using a preset joint probability data association method further includes: If the target positioning signal is not within the tracking gate of any single vehicle, the target positioning signal fails to be associated with the predicted value of the running state of the single vehicle. The target positioning signal is used as the initial state of the vehicle, and the preset adaptive extended Kalman filter method is used to perform initial processing on the vehicle's motion state.

6. The vehicle continuous tracking method based on grating array according to claim 4, characterized in that: After comparing the target positioning signal with the predicted value of the running state of a single vehicle using a preset joint probability data association method, it also includes: The vehicle track management strategy is updated based on the comparison result between the target positioning signal and the predicted value of the operating status of a single vehicle.

7. A vehicle continuous tracking device based on a grating array, characterized in that: include: An acquisition module, used to acquire a vehicle vibration positioning signal based on an ultra-weak fiber Bragg grating array, and extract vibration energy corresponding to the vehicle vibration positioning signal; The motion model building module is used to build the vehicle motion model using a nonlinear constant turning rate and speed model based on the vibration energy corresponding to the vehicle vibration positioning signal: in, Indicated in The state vector of the vehicle at time and They represent the lane the vehicle is in and the real-time mileage position in meters. Indicates the real-time speed of the vehicle. is the yaw angle, indicating the direction of vehicle travel. is the estimated angular velocity, is the real-time vibration energy of the vehicle; The prediction module is used to obtain the observation data of multiple vehicles according to the vehicle motion model, and predict the running state of a single vehicle in a preset monitoring area according to the observation data to obtain the motion trajectory prediction result of each vehicle; The correlation module is used to determine the trajectory tracking result of each vehicle according to the correlation between the motion trajectory prediction result of each vehicle and the vehicle vibration positioning signal.

8. An electronic device, characterized in that: include: Processor and memory; The memory stores a computer-readable program executable by the processor; When the processor executes the computer-readable program, the steps in the vehicle continuous tracking method based on the grating array are implemented as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in the vehicle continuous tracking method based on the grating array as described in any one of claims 1-6.

Images