Data association method and apparatus

Abstract

The application discloses a data association method and device, comprising: acquiring at least one second vehicle, a first measurement parameter collected at a first time by a first vehicle, a first predicted value of a motion parameter of each second vehicle at the first time and a second predicted value of a measurement value of the motion parameter; calculating a first score for representing the association degree of the first measurement parameter and each second vehicle according to a first residual, and calculating a second score for representing the association degree of the first measurement parameter and each second vehicle according to a second residual; calculating a target score for representing the association degree of the first measurement parameter and each second vehicle according to the first score and the second score corresponding to each second vehicle; and determining the target association degree of the first measurement parameter and each second vehicle according to the target score. The measurement data is accurately matched to the target object belonging to it.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and more specifically to a data association method and apparatus. Background Technology

[0002] Data association is the process of establishing relationships between multiple radar measurements and existing data at a given moment to determine whether these measurements originate from the same target. Ultimately, it aims to correctly pair the measurement data with existing data, matching the measurement data to its corresponding target object. Data association is a critical issue in radar data processing. Incorrect data association will result in an incorrect measurement being matched to the target object. For vehicle-mounted radar, this mismatch can lead to inaccurate estimations of the target vehicle's trajectory or heading, resulting in flawed decision-making.

[0003] Current data association schemes typically involve obtaining a measurement data point, calculating the distance between that measurement data and multiple target objects, and then identifying the closest target object as the target object associated with that measurement data. This approach results in low data association accuracy. Summary of the Invention

[0004] The purpose of this application is to provide a data association method and apparatus to quickly and accurately associate measurement data with target objects, accurately match measurement data to the target objects to which it belongs, and improve the accuracy of the association between measurement data and known data.

[0005] The technical solution of this application is as follows:

[0006] Firstly, a data association method is provided, which includes:

[0007] The system acquires at least one second vehicle detected by the first vehicle, as well as first measurement parameters collected within the associated threshold of the first vehicle at a first time, and a first predicted value of the motion parameters of each second vehicle at the first time and a second predicted value of the measured values ​​of the motion parameters of each second vehicle at the first time, wherein the coordinate system in which the first predicted value is located is a rectangular coordinate system and the coordinate system in which the second predicted value is located is a polar coordinate system.

[0008] Calculate the first residual of the first measurement parameter and the second predicted value corresponding to each second vehicle in the polar coordinate system, and the second residual of the first measurement parameter and the first predicted value corresponding to each second vehicle in the rectangular coordinate system.

[0009] Based on the first residual, a first score is calculated to characterize the correlation between the first measurement parameter and each of the second vehicles, and a second score is calculated based on the second residual to characterize the correlation between the first measurement parameter and each of the second vehicles.

[0010] Based on the first score and the second score corresponding to each second vehicle, a target score is calculated to characterize the correlation between the first measurement parameter and each second vehicle.

[0011] Based on the target score, the correlation degree between the first measurement parameter and the target of each second vehicle is determined.

[0012] Secondly, a data association device is provided, the device comprising:

[0013] The first acquisition module is used to acquire at least one second vehicle detected by the first vehicle, as well as first measurement parameters collected within the associated threshold of the first vehicle at a first time, and a first predicted value of the motion parameters of each second vehicle at the first time and a second predicted value of the measured values ​​of the motion parameters of each second vehicle at the first time, wherein the coordinate system in which the first predicted value is located is a rectangular coordinate system and the coordinate system in which the second predicted value is located is a polar coordinate system.

[0014] The first calculation module is used to calculate the first residual of the first measurement parameter and the second predicted value corresponding to each second vehicle in the polar coordinate system, and the second residual of the first measurement parameter and the first predicted value corresponding to each second vehicle in the rectangular coordinate system.

[0015] The second calculation module is used to calculate a first score representing the correlation between the first measurement parameter and each second vehicle based on the first residual, and to calculate a second score representing the correlation between the first measurement parameter and each second vehicle based on the second residual.

[0016] The third calculation module is used to calculate a target score that characterizes the correlation between the first measurement parameter and each second vehicle based on the first score and the second score corresponding to each second vehicle.

[0017] The first determining module is used to determine the correlation degree between the first measurement parameter and the target of each second vehicle based on the target score.

[0018] Thirdly, embodiments of this application provide an electronic device, which includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the steps of any of the data association methods described in the embodiments of this application.

[0019] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, and when the program or instructions are executed by a processor, the steps of any of the data association methods described in embodiments of this application are implemented.

[0020] Fifthly, embodiments of this application provide a computer program product in which instructions, when executed by a processor of an electronic device, enable the electronic device to perform the steps of any of the data association methods described in embodiments of this application.

[0021] The technical solutions provided by the embodiments of this application bring at least the following beneficial effects:

[0022] In this embodiment, by acquiring at least one second vehicle detected by the first vehicle, and the first measurement parameters collected within the association threshold of the first vehicle at the first time, as well as the first predicted value of the motion parameters of each second vehicle at the first time and the second predicted value of the measured values ​​of the motion parameters of each second vehicle at the first time, a first residual in the polar coordinate system and a second residual in the rectangular coordinate system are calculated for the first measurement parameters and the second predicted values ​​corresponding to each second vehicle. Based on the first residual, a first score characterizing the association degree between the first measurement parameters and each second vehicle is calculated, and based on the second residual, a score characterizing the association degree between the first measurement parameters and each second vehicle is calculated. A second score is calculated to represent the correlation between a measurement parameter and each second vehicle. Based on the first and second scores corresponding to each second vehicle, a target score is calculated to characterize the correlation between the first measurement parameter and each second vehicle. Based on the target score, the target correlation between the first measurement parameter and each second vehicle is determined. In this way, when determining the correlation between the first measurement parameter and each second vehicle, multiple dimensions of the second vehicle's parameters are considered, rather than just the distance between the first measurement parameter and each second vehicle. This improves the accuracy of determining the correlation between the first measurement parameter and each second vehicle, accurately matching the first measurement parameter to its corresponding second vehicle, and improving the accuracy of associating the first measurement parameter with each known second vehicle.

[0023] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0024] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application, and do not constitute an undue limitation of this application.

[0025] Figure 1 This is a flowchart illustrating a data association method provided in the first aspect of this application;

[0026] Figure 2 This is a schematic diagram illustrating the correspondence between the rectangular coordinate system and the polar coordinate system involved in the first aspect of the embodiment of this application;

[0027] Figure 3 This is a flowchart illustrating a data association method provided in the first aspect of this application;

[0028] Figure 4 This is a schematic diagram of a scenario involving an application data association method according to the first aspect of this application;

[0029] Figure 5 This is a schematic diagram of the structure of a data association device provided in the second aspect embodiment of this application;

[0030] Figure 6 This is a schematic diagram of the structure of an electronic device provided in the third aspect of this application. Detailed Implementation

[0031] To enable those skilled in the art to better understand the technical solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0032] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples consistent with some aspects of this application as detailed in the appended claims.

[0033] As described in the background section, existing technologies suffer from low accuracy in determining data correlation. To address this issue, this application provides a data correlation method and apparatus. The method involves acquiring at least one second vehicle detected by a first vehicle, first measurement parameters collected within the correlation threshold of the first vehicle at a first time, and first predicted values ​​of motion parameters for each second vehicle at the first time and second predicted values ​​of the measured motion parameters for each second vehicle at the first time. It then calculates a first residual in polar coordinates between the first measurement parameters and the second predicted values ​​for each second vehicle, and a second residual in Cartesian coordinates between the first measurement parameters and the first predicted values ​​for each second vehicle. Based on the first residuals, it calculates the correlation between the first measurement parameters and each second vehicle. The system calculates a first score for the correlation between the first measurement parameter and each second vehicle, based on the second residual. Then, it calculates a second score based on the first and second scores for each second vehicle, and a target score for the correlation between the first measurement parameter and each second vehicle. Based on the target score, the target correlation between the first measurement parameter and each second vehicle is determined. This approach considers multiple dimensions of the second vehicle's parameters when determining the correlation, rather than simply looking at the distance between the first measurement parameter and each second vehicle. This improves the accuracy of determining the correlation between the first measurement parameter and each second vehicle, accurately matching the first measurement parameter to its corresponding second vehicle, and enhancing the accuracy of associating the first measurement parameter with each known second vehicle.

[0034] The data association method provided in this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0035] Figure 1 This is a flowchart illustrating a data association method provided in an embodiment of this application, as shown below. Figure 1 As shown, the data association method provided in this application embodiment may include steps 110-150.

[0036] Step 110: Obtain at least one second vehicle detected by the first vehicle, and the first measurement parameters collected within the associated threshold of the first vehicle at the first time, as well as the first predicted value of the motion parameters of each second vehicle at the first time and the second predicted value of the measured values ​​of the motion parameters of each second vehicle at the first time, wherein the coordinate system of the first predicted value is a rectangular coordinate system and the coordinate system of the second predicted value is a polar coordinate system.

[0037] The first vehicle may be equipped with sensors, including but not limited to lidar or millimeter-wave radar. These sensors can detect at least one second vehicle near the first vehicle and acquire motion parameters of each vehicle within an associated threshold of the first vehicle.

[0038] The second vehicle can be a vehicle detected by the sensors of the first vehicle that is near the first vehicle.

[0039] The first moment can be any moment after the current time.

[0040] The first measurement parameter may be a motion parameter collected by the sensors of the first vehicle within the associated threshold of the first vehicle at the first moment, that is, the first measurement parameter is obtained based on the sensors on the first vehicle.

[0041] It should be noted that at the first moment, the sensors of the first vehicle can collect multiple motion parameters within the associated threshold of the first vehicle. The first measurement parameter can be one of the multiple motion parameters. For ease of subsequent description, this application embodiment will only use one motion parameter as an example for illustration. For each of the multiple motion parameters that the sensors of the first vehicle can collect within the associated threshold of the first vehicle at the first moment, the same processing method as the first measurement parameter can be used to determine the second vehicle that matches it.

[0042] For a given second vehicle, the first predicted value for that second vehicle can be the motion parameters of that second vehicle at the first moment, predicted based on its trajectory before the current time.

[0043] For a given second vehicle, the second predicted value for that second vehicle can be the measured value of the motion parameters of the second vehicle at the first moment, which is predicted based on the trajectory of the second vehicle before the current time. In other words, the second predicted value is the measured value of the second vehicle measured by the sensor at the first moment.

[0044] In some embodiments of this application, for a certain second vehicle, the motion parameters of the second vehicle can be a multi-dimensional vector, specifically, the motion parameters can be... Where x represents the position information of the second vehicle in the lateral direction, y represents the position information of the second vehicle in the longitudinal direction, and v x For the second vehicle's lateral speed information, v y The velocity information of the second vehicle in the longitudinal direction is given, and the coordinate system in which this motion parameter is located is a Cartesian coordinate system.

[0045] For a specific second vehicle, when the sensor measures the motion parameters of the second vehicle, the measured values ​​of the motion parameters acquired by the sensor are in a polar coordinate system. That is, the measured values ​​of the motion parameters are in a polar coordinate system. Therefore, the coordinate system of the first predicted value is also a Cartesian coordinate system, and the coordinate system of the second predicted value is a polar coordinate system. The measured values ​​of the motion parameters are affected by measurement noise. It can be assumed that the measured value in the polar coordinate system can be expressed as Z = [R, v] r ,θ], where R is the radial distance of the second vehicle relative to the first vehicle, θ is the azimuth angle of the second vehicle relative to the first vehicle, v r The radial Doppler velocity of the second vehicle relative to the first vehicle is given.

[0046] Step 120: Calculate the first residual of the first measurement parameter and the second predicted value corresponding to each second vehicle in the polar coordinate system, and the second residual of the first measurement parameter and the first predicted value corresponding to each second vehicle in the rectangular coordinate system.

[0047] The first residual for each second vehicle can be the residual between the first measurement parameter and the second predicted value corresponding to the second vehicle in the polar coordinate system.

[0048] For each second vehicle, the second residual can be the residual between the first motion parameter and the first predicted value corresponding to the second vehicle in a Cartesian coordinate system.

[0049] In some embodiments of this application, for each second vehicle, the first residual Δυ1 in polar coordinates between the first measurement parameter and the second predicted value corresponding to the second vehicle can be calculated according to the following formula (1):

[0050]

[0051] Where Z is the first measurement parameter, Z pre This is the second predicted value for a given vehicle.

[0052] In some embodiments of this application, for each second vehicle, the second residual Δυ2 in a rectangular coordinate system of the first measurement parameter and the first predicted value corresponding to the second vehicle can be calculated according to the following formula (2):

[0053]

[0054] in, The first measurement parameter, For a given vehicle, the first predicted value is v in formula (2). r It is the sum of the lateral and longitudinal velocity information of the second vehicle in a Cartesian coordinate system.

[0055] In some embodiments of this application, since the first measurement parameter is a value in a polar coordinate system and the first predicted value is a value in a rectangular coordinate system, in order to accurately obtain the second parameter, step 120 calculates the second residual of the first measurement parameter and the first predicted value corresponding to each second vehicle in the rectangular coordinate system, which may specifically include:

[0056] Based on the first measurement parameter and the pre-set correspondence between the polar coordinate system and the rectangular coordinate system, determine the parameter value of the first measurement parameter in the rectangular coordinate system;

[0057] Calculate the parameter value of the first measurement parameter in the rectangular coordinate system and the second residual of the first predicted value corresponding to each second vehicle in the rectangular coordinate system.

[0058] In some embodiments of this application, it can be based on, as follows Figure 2 The correspondence between the rectangular coordinate system and the polar coordinate system shown can be obtained from the following formula (3): the correspondence between the polar coordinate system where the sensor measurement value is located and the rectangular coordinate system where the vehicle's motion parameters are located.

[0059]

[0060]

[0061] v r =v y ×cosθ+v x ×sinθ

[0062] In some embodiments of this application, by substituting the first measurement parameter into the above formula (3), the parameter value of the first measurement parameter in the rectangular coordinate system as shown in the following formula (4) can be obtained:

[0063]

[0064] After obtaining the parameter value of the first measurement parameter in the rectangular coordinate system as shown in formula (4), the parameter value of the first measurement parameter in the rectangular coordinate system and the second residual of the first predicted value of the second vehicle in the rectangular coordinate system can be calculated according to the above formula (2) for each second vehicle.

[0065] In the embodiments of this application, the parameter value of the first measurement parameter in the rectangular coordinate system is determined according to the first measurement parameter and the pre-set correspondence between the polar coordinate system and the rectangular coordinate system. In this way, the parameter value of the first measurement parameter in the rectangular coordinate system and the second residual of the first predicted value corresponding to each second vehicle in the rectangular coordinate system can be accurately obtained.

[0066] Step 130: Based on the first residual, calculate the first score to characterize the correlation between the first measurement parameter and each second vehicle, and based on the second residual, calculate the second score to characterize the correlation between the first measurement parameter and each second vehicle.

[0067] The first score and the second score can both be used to characterize the correlation between the first measurement parameter and each second vehicle.

[0068] In some embodiments of this application, a first score characterizing the correlation between the first measurement parameter and each second vehicle can be calculated based on the first residual, and a second score characterizing the correlation between the first measurement parameter and each second vehicle can be calculated based on the second residual.

[0069] In some embodiments of this application, in order to accurately obtain the first score, step 130 above calculates the first score, based on the first residual, to characterize the correlation between the first measurement parameter and each second vehicle. Specifically, this may include:

[0070] Calculate the prediction covariance for each second vehicle based on the second predicted value for each second vehicle.

[0071] Based on the predicted covariance, the first residual, and the first correction coefficient of the scoring function, a first score is calculated to characterize the correlation between the first measurement parameter and each second vehicle, wherein the first correction coefficient is determined based on the sensor.

[0072] In some embodiments of this application, for each second vehicle, the prediction covariance S corresponding to the second vehicle can be calculated according to the following formula (5) based on the second predicted value corresponding to the second vehicle:

[0073]

[0074] For each second vehicle, based on the predicted covariance, the first residual, and the first correction coefficient of the scoring function obtained from formula (5) above, the first score f1, which characterizes the correlation between the first measurement parameter and the second vehicle, can be calculated according to the following formula (6):

[0075]

[0076] Here, α is the first correction coefficient, which is used to adjust the first residual or predict the abnormal changes in covariance. This correction coefficient is related to the characteristics of the sensor and generally takes a value in the range of α∈[1,3].

[0077] Obviously, the score function (Equation 7) established shows that the smaller the residual Δυ1 and the prediction covariance S, the higher the score of the track evaluation function, which indicates that the track matches the measurement better.

[0078] In the embodiments of this application, by calculating the prediction covariance corresponding to each second vehicle based on the second predicted value corresponding to each second vehicle, and based on the prediction covariance, the first residual and the first correction coefficient of the scoring function, the first score used to characterize the correlation between the first measurement parameter and each second vehicle can be accurately obtained.

[0079] In some embodiments of this application, motion parameters may include component parameters of each motion dimension, such as the motion parameters described above. The parameters v = (v_x, y_y) have position dimension components and velocity dimension components, respectively. x v y ).

[0080] To accurately determine the second score, step 130 above calculates a second score, based on the second residual, to characterize the correlation between the first measurement parameter and each second vehicle. Specifically, this may include:

[0081] Based on the second residual, the component difference values ​​of the component parameters of each second vehicle in each motion dimension are obtained;

[0082] For each second vehicle, based on the driving state of the second vehicle in each motion dimension at the first moment, a second correction coefficient is determined to correct the component differences of the second vehicle in each motion dimension.

[0083] For each second vehicle, the third residual is calculated based on the second correction coefficients corresponding to each motion dimension of the second vehicle and the component differences of each motion dimension.

[0084] Based on the third residual corresponding to each second vehicle, a second score is determined to characterize the correlation between the first measurement parameter and each second vehicle.

[0085] Specifically, for each second vehicle, the component difference of the component parameters of each motion dimension corresponding to the second vehicle can be the difference of the component parameters of the second vehicle in each motion dimension.

[0086] The second correction factor can be a correction factor that corrects the component differences in each motion dimension of the second vehicle.

[0087] The third residual can be calculated based on the second correction coefficients corresponding to each motion dimension of the second vehicle, and the component differences of each motion dimension.

[0088] In some embodiments of this application, for each second vehicle, the component difference of the component parameters of the second vehicle in each motion dimension can be obtained from the second residual obtained according to the above formula (2). The component difference of the component parameters of the second vehicle in each motion dimension is the component difference in the above formula (2).

[0089] Then, for each second vehicle, based on the driving state of the second vehicle in each motion dimension at the first moment, the second correction coefficient for correcting the component differences in each motion dimension of the second vehicle can be determined. Based on the second correction coefficients corresponding to each motion dimension of the second vehicle and the component differences in each motion dimension, the third residual d shown in the following formula (7) can be obtained:

[0090] d = a × d x +b×d y +c×d v +g (7)

[0091] Where a, b, and c are the second correction coefficients for correcting the component differences in each motion dimension, and g is another correction coefficient, which will be described in detail in the following embodiments.

[0092] After obtaining the third residual, for each second vehicle, a second score f2, characterizing the correlation between the first measurement parameter and each second vehicle, can be obtained based on the third residual corresponding to that second vehicle, according to the following formula (8):

[0093] f2=β×(κ-d)+γ (8)

[0094] The values ​​of β, κ, and γ are all related to the characteristics of the sensors on the first vehicle. Specifically, in general, β∈[0.002, 0.5], κ∈[1.0, 100.0], and γ∈[0.0, 1.5].

[0095] In the embodiments of this application, the component difference values ​​of the component parameters of each second vehicle in each motion dimension are obtained according to the second residual. For each second vehicle, a second correction coefficient is determined to correct the component difference values ​​of each motion dimension of the second vehicle according to the driving state of the second vehicle in each motion dimension at the first moment. For each second vehicle, a third residual is calculated according to the second correction coefficient corresponding to each motion dimension of the second vehicle and the component difference values ​​of each motion dimension. Based on the third residual corresponding to each second vehicle, a second score used to characterize the correlation between the first measurement parameter and each second vehicle can be accurately determined.

[0096] In some embodiments of this application, when the motion parameters include component parameters of the position dimension and component parameters of the velocity dimension, the component differences of the component parameters of each motion dimension may include the component differences of the position dimension and the component differences of the velocity dimension. v The position dimension component difference here can include the first position component difference of the second vehicle in the first direction and the second position component difference in the second direction. The first and second directions can be the lateral and longitudinal directions, respectively. The first position component difference can be the position dimension component difference of the second vehicle in the first direction, and the second position component difference can be the position dimension component difference of the second vehicle in the second direction. If the first direction is the lateral direction and the second direction is the longitudinal direction, then the first position component difference is d. x The component difference at the second position is d. y .

[0097] If we take the first direction as the horizontal direction and the second direction as the vertical direction, then the difference of the first position component is d. x The component difference at the second position is d. y For example.

[0098] The step of determining a second correction coefficient to correct the component differences of the second vehicle in each motion dimension based on the driving state of the second vehicle in each motion dimension at the first moment can specifically include:

[0099] Given that the second vehicle's driving state at the first moment is determined to be lateral movement in the first direction, the range of the second correction coefficient for correcting the difference in the first position component is determined to be [0.5, 0.95].

[0100] If it is determined that the distance between the second vehicle and the first vehicle at the first moment is less than a preset distance threshold, or the size of the second vehicle is greater than a preset size threshold, the range of the second correction coefficient for correcting the difference of the second position component is determined to be [0.35, 0.85].

[0101] Given that the second vehicle is in the Doppler region at the first moment, the range of the second correction coefficient for correcting the component differences in the velocity dimension is determined to be [0.15, 0.55].

[0102] The preset distance threshold can be a pre-set threshold for the distance between the first vehicle and the second vehicle at the first moment. This preset distance threshold can be set by the user according to their needs, and is not limited in this embodiment.

[0103] The preset size threshold can be a threshold value for the size of the second vehicle that can be set in advance. This preset size threshold can be set by the user according to their needs, and is not limited in this embodiment.

[0104] In some embodiments of this application, if it is determined that the driving state of the second vehicle at the first moment is lateral movement in the first direction, it is necessary to reduce the influence of lateral deviation on the score. That is, the range of the second correction coefficient for correcting the difference of the first position component can be set to [0.5, 0.95]. Otherwise, the range of the second correction coefficient for correcting the difference of the first position component can be set to 1.0.

[0105] If it is determined that the distance between the second vehicle and the first vehicle at the first moment is less than a preset distance threshold, or the size of the second vehicle is greater than a preset size threshold, that is, if the second vehicle is relatively close to the first vehicle or the size of the second vehicle is relatively large (if the size of the second vehicle is relatively large, it indicates that the extended attribute of the second vehicle is obvious), then it is necessary to reduce the impact of longitudinal deviation on the score. That is, the range of the second correction coefficient for correcting the difference of the second position component can be set to [0.35, 0.85]. Otherwise, the second correction coefficient for correcting the difference of the second position component can be set to 0.0.

[0106] If it is determined that the second vehicle is in the Doppler region at the first moment, then it is necessary to reduce the impact of speed deviation on the score. In this case, the range of the second correction coefficient for correcting the component difference of the speed dimension can be set to [0.15, 0.55]. Otherwise, the second correction coefficient for correcting the component difference of the speed dimension can be set to 1.0.

[0107] In the embodiments of this application, by determining the second correction coefficient for correcting the component differences of the second vehicle in each motion dimension based on the driving state of the second vehicle in each motion dimension at the first moment, the correction coefficient can be accurately determined.

[0108] In some embodiments of this application, after determining the second correction coefficient for correcting the component differences in each motion dimension of the second vehicle, the method described above may further include:

[0109] The state coefficients of the second vehicle are determined based on the motion state of the second vehicle at the first moment and the predicted motion state of the second vehicle at the first moment.

[0110] For each second vehicle, based on the second correction coefficients corresponding to each motion dimension of the second vehicle and the component differences of each motion dimension, the third residual is calculated, including:

[0111] For each second vehicle, the third residual is calculated based on the second correction coefficient and state coefficient corresponding to each motion dimension of the second vehicle, as well as the component difference of each motion dimension.

[0112] The state coefficient can be determined based on the motion state of the second vehicle at the first moment and the predicted motion state of the second vehicle at the first moment. The state coefficient can be g in the above formula (7).

[0113] In some embodiments of this application, the state coefficient of the second vehicle can be determined based on whether the motion state of the second vehicle at the first moment is consistent with the predicted motion state of the second vehicle at the first moment. For example, if the motion state of the second vehicle at the first moment is inconsistent with the predicted motion state of the second vehicle at the first moment, the state coefficient can be set to g∈[0.25, 0.55]; otherwise, the state coefficient is set to 0.0.

[0114] In the embodiments of this application, when determining the third residual, the state coefficient of the second vehicle can also be set, so that the first measurement parameter and each second vehicle can be managed from more dimensions, further improving the accuracy of the association between the first measurement parameter and each second vehicle.

[0115] Step 140: Calculate the target score, which characterizes the correlation between the first measurement parameter and each second vehicle, based on the first score and the second score corresponding to each second vehicle.

[0116] The target score can be a score used to characterize the correlation between the first measurement parameter and each second vehicle.

[0117] In some embodiments of this application, for each second vehicle, a target score can be calculated based on the first score and the second score corresponding to the second vehicle to characterize the correlation between the first measurement parameter and the second vehicle. Specifically, the target score can be determined by the sum of the first score and the second score, or the target score can be obtained by weighted calculation of the first score and the second score. The specific calculation method can be selected by the user according to their needs and is not limited in the embodiments of this application.

[0118] In some embodiments of this application, in order to accurately determine the correlation between the first measurement parameter and each second vehicle, step 140 may specifically include:

[0119] For each second vehicle, the type of the second vehicle is determined based on the distance between the second vehicle and the first vehicle, and the detection results of the second vehicle within a preset detection cycle.

[0120] Determine the additional score for each second vehicle based on its type;

[0121] Based on the additional score, and the first and second scores corresponding to each second vehicle, a target score is calculated to characterize the correlation between the first measurement parameter and each second vehicle.

[0122] The preset detection cycle can be the detection cycle of the sensors in the first vehicle.

[0123] Additional points can be awarded based on the type of each second vehicle, with each second vehicle receiving an additional point.

[0124] In some embodiments of this application, the detection result of the second vehicle within a preset detection period may be that the second vehicle can be detected a few times and the second vehicle cannot be detected a few times within the preset detection period, or it may be other detection results, which are not limited in the embodiments of this application.

[0125] In some embodiments of this application, for each second vehicle, a target score fk characterizing the correlation between the first measurement parameter and the second vehicle can be obtained according to the following formula (9), based on the additional score and the first and second scores corresponding to the second vehicle:

[0126] fk=f1+f2+f3 (9)

[0127] Here, f3 represents the additional score. The determination of this additional score will be described in more detail in later embodiments.

[0128] In the embodiments of this application, when matching the first measurement parameter with each second vehicle, in addition to referring to the first score and the second score mentioned above, the characteristics of the vehicle can also be referenced to determine the additional score of the vehicle. In this way, the first measurement parameter is matched with each second vehicle from multiple dimensions, which improves the accuracy of matching the first measurement parameter with each second vehicle.

[0129] In some embodiments of this application, determining the type of the second vehicle based on the distance between the second vehicle and the first vehicle, and the detection results of the second vehicle within a preset detection period, may specifically include:

[0130] If it is determined that the distance between the second vehicle and the first vehicle is less than a preset distance threshold at the current time, or if it is predicted that the distance between the second vehicle and the first vehicle will be less than a preset distance threshold within a preset period after the current time, the type of the second vehicle is determined to be the first type.

[0131] If no second vehicle is detected within a predetermined number of consecutive detection cycles within a predetermined detection cycle, or if the number of times the second vehicle is detected within a predetermined detection cycle is less than a predetermined number, then the type of the second vehicle is determined to be the second type.

[0132] The preset distance threshold can be a pre-set threshold between the first vehicle and the second vehicle. Within this threshold, it is indicated that the second vehicle poses a safety hazard to the first vehicle.

[0133] The preset time period can be a pre-set period of time after the current time, such as half an hour after the current time.

[0134] The first type of vehicle can be a vehicle that poses a safety hazard to the first vehicle if the second vehicle is involved.

[0135] In some embodiments of this application, the preset number can be a pre-set detection cycle in which the second vehicle is not detected for three consecutive detection cycles. For example, if the second vehicle is not detected for three consecutive detection cycles, the type of the second vehicle is determined to be the second type.

[0136] In some embodiments of this application, the preset number of times can be a threshold for the number of times the second vehicle is detected within a preset detection period. If the number of times the second vehicle is detected within the preset detection period is less than the threshold, the type of the second vehicle is determined to be the second type.

[0137] The second type of vehicle can be either in the emerging or disappearing phase. "Emerging" here refers to the sudden appearance of another vehicle among the second vehicles continuously being collected by the first vehicle; in this case, the new vehicle is considered to be in the emerging phase by the first vehicle. "Disappearing" here refers to the sudden disappearance of a vehicle from the first vehicle's detection range among the second vehicles continuously being collected; in this case, the vehicle is considered to be in the disappearing phase by the first vehicle.

[0138] In some embodiments of this application, for a certain second vehicle, if the distance between the second vehicle and the first vehicle is less than a preset distance threshold, such as less than 1 meter, it indicates that the vehicle may be at risk of colliding with the first vehicle. In this case, the vehicle's trajectory is determined to be a CIPV trajectory, and the second vehicle can be determined to be a first type of vehicle.

[0139] In some embodiments of this application, for a certain second vehicle, if the second vehicle is currently located 5 meters to the left of the first vehicle, but based on the tracks of the first and second vehicles, it is predicted that after 10 minutes, the distance between the second and first vehicles will be less than 1 meter, then the second vehicle is determined to be a vehicle that poses a safety hazard to the first vehicle, and thus the second vehicle is determined to be a key vehicle within the functional area, and thus the second vehicle can be determined to be a vehicle of the first type.

[0140] In some embodiments of this application, for a certain second vehicle, if it is determined that the second vehicle is not detected three times consecutively within a preset detection period of the first vehicle's sensor, it is indicated that the second vehicle is a vehicle in the extinction stage. If it is determined that the second vehicle is detected less than 10 times within the preset detection period, it is indicated that the second vehicle is a vehicle in the nascent stage. Therefore, the type of the second vehicle is determined to be the second type.

[0141] In the embodiments of this application, if the distance between the second vehicle and the first vehicle at the current time is less than a preset distance threshold, or if it is predicted that the distance between the second vehicle and the first vehicle will be less than the preset distance threshold within a preset period after the current time, the type of the second vehicle can be determined to be of the first type. If the second vehicle is not detected within a preset number of consecutive detection cycles within a preset detection cycle, or if the number of times the second vehicle is detected within a preset detection cycle is less than a preset number, the type of the second vehicle can be determined to be of the second type. In this way, the type of the second vehicle can be accurately determined.

[0142] In some embodiments of this application, determining the additional score for each second vehicle based on its type may specifically include:

[0143] For each second vehicle, if the type of the second vehicle is determined to be the first type, the second vehicle is assigned a first score, where the first score is a positive number;

[0144] For each second vehicle, if the type of the second vehicle is determined to be the second type, the second vehicle is assigned a second score, where the first score is a negative number;

[0145] Based on the first and second scores corresponding to each second vehicle, determine the additional score for each second vehicle.

[0146] In some embodiments of this application, for each second vehicle, if the type of the second vehicle is a first type, points can be added to the second vehicle. For example, the range of the first score of the vehicle can be f31∈(1.5, 3.75). If the type of the second vehicle is a second type, points can be deducted from the second vehicle. For example, the range of the first score of the vehicle can be f32∈(-3.75, -1.5). Then, the first score and the second score are added together according to the following formula (10) to obtain the additional score f3:

[0147] f3=f31+f32 (10)

[0148] Among them, f31 is the first score and f32 is the second score.

[0149] In the embodiments of this application, the additional score of the second vehicle can be determined by adding and subtracting points according to the type of the second vehicle.

[0150] Step 150: Based on the target score, determine the correlation between the first measurement parameter and the target of each second vehicle.

[0151] The target correlation degree can be the correlation degree between the first measurement parameter and each second vehicle, that is, whether the first measurement parameter is a measurement parameter of the second vehicle.

[0152] In some embodiments of this application, the second vehicle with the highest target score can be determined as the second vehicle that matches the first measurement parameter, based on the target score corresponding to each second vehicle.

[0153] In some embodiments of this application, to more clearly understand the solutions of the embodiments of this application, another implementation of the data association method is provided, such as... Figure 3 As shown, the data association method may include the following steps 310-350.

[0154] Step 310: Obtain the residual between each second vehicle and the first measurement parameter collected within the associated threshold of the first vehicle at the first time.

[0155] Step 310 may include the process of steps 110-120 in the above embodiments, namely, determining the first residual of the first measurement parameter and the second predicted value corresponding to each second vehicle in the polar coordinate system, and the second residual of the first measurement parameter and the first predicted value corresponding to each second vehicle in the rectangular coordinate system.

[0156] Step 320: Based on the first residual, calculate the first score to characterize the correlation between the first measurement parameter and each second vehicle.

[0157] Step 330: Based on the second residual, calculate the second score, which characterizes the correlation between the first measurement parameter and each second vehicle.

[0158] Steps 320-330 above are the same as step 130 in the above embodiment, and will not be repeated here.

[0159] Step 340: Determine the additional score for each second vehicle.

[0160] Step 340 is consistent with the process of adding points for each second vehicle in the above embodiments, and will not be described again here.

[0161] Step 350: Determine the target score for each second vehicle.

[0162] In step 350, the target score for each second vehicle can be obtained according to the first score, the second score, and the additional score, in accordance with the above formula (9).

[0163] Then, based on the target score, the correlation between the first measurement parameter and the target of each second vehicle can be determined.

[0164] In some embodiments of this application, to more clearly understand the solutions of the embodiments of this application, a specific example is now used to illustrate the data association method provided by the embodiments of this application:

[0165] refer to Figure 4 , Figure 4 The two second vehicles collected by the first vehicle are vehicle 1 and vehicle 2. The first vehicle also collected a measurement parameter p1, which is the first measurement parameter in the above embodiment.

[0166] The predicted values ​​of the motion parameters of vehicle 1 at the first moment (i.e., the first predicted value) and the predicted values ​​of the measured values ​​of the motion parameters of vehicle 1 at the first moment (i.e., the second predicted value) are as follows:

[0167]

[0168] Z pre1 =[R p1 θ p1 v rp1 = [5.4433, 0.1261, 2.983]

[0169] The predicted values ​​of the motion parameters of vehicle 2 at the first moment (i.e., the first predicted value) and the predicted values ​​of the measured values ​​of the motion parameters of vehicle 2 at the first moment (i.e., the second predicted value) are as follows:

[0170]

[0171] Z pre1 =[R p1 θ p1 v rpl = [6.0398, 0.2828, 2.783]

[0172] The measurement parameter p1 is Z = [R, θ, v] = [7.2245, 0.1438, 3.733]. Based on this measurement parameter p1, the parameter value of the measurement parameter p1 in the rectangular coordinate system can be obtained by formula (4) as Z = [x, y] = [1.035, 7.15].

[0173] According to formula (1), the first residuals of the measurement parameter p1 and the second predicted values ​​of vehicle 1 and vehicle 2 in the polar coordinate system are as follows:

[0174]

[0175]

[0176] According to formula (2), the second residuals of the measurement parameter p1 and the first predicted values ​​of vehicle 1 and vehicle 2 in the rectangular coordinate system are as follows:

[0177]

[0178]

[0179] If the first correction coefficient of the scoring function is set to α = 1.5, then the first scores of vehicle 1 and vehicle 2 can be obtained from formula (6) as f11 = 3.7459 and f21 = 3.9586 respectively.

[0180] If the second correction coefficients for correcting the component differences of each motion dimension of vehicle 1 and vehicle 2 are set as follows: a = 1.0, b = 0.75, c = 0.25, g = 0.0, then according to formula (7), the third residuals corresponding to vehicle 1 and vehicle 2 are d1 = 1.85 and d2 = 1.9, respectively.

[0181] If the parameters β = 0.5, κ = 2.0, and γ = 0.1 in formula (8) are set, then according to formula (8), the second scores of vehicle 1 and vehicle 2 can be obtained as f12 = 0.175 and f22 = 0.15, respectively.

[0182] If vehicle 1's track is a CIPV track and vehicle 2's track is a non-CIPV track, and both vehicle 1 and vehicle 2 are tracks in normal development, meaning that vehicle 1 and vehicle 2 are neither vehicles in the extinction phase nor newly created vehicles, then the additional scores for vehicle 1 and vehicle 2 can be obtained as follows: f13 = 1.5 and f23 = 0.0, respectively.

[0183] Calculate the target scores for vehicle 1 and vehicle 2 respectively:

[0184] f1z=f11+f12+f13=3.7459+0.175+1.5=5.4209

[0185] f2z=f21+f22+f23=3.9586+0.15+0.0=4.1086

[0186] Based on the target scores of vehicle 1 and vehicle 2, it can be seen that vehicle 1 has a higher target score, therefore the measurement parameter p1 is matched with vehicle 1.

[0187] It should be noted that the values ​​in the above examples are exemplary values ​​and not limitations. That is, the values ​​in the above examples are only examples in the embodiments of this application. In actual application, the values ​​of the above parameters can be determined according to the actual situation.

[0188] It should be noted that the data association method provided in this application embodiment can be executed by a data association device or a control module in the data association device for executing the data association method.

[0189] Based on the same inventive concept as the data association method described above, this application also provides a data association device. The following is in conjunction with... Figure 5 The data association apparatus provided in the embodiments of this application will be described in detail.

[0190] Figure 5 This is a schematic diagram of the structure of a data association device according to an exemplary embodiment.

[0191] like Figure 5 As shown, the data association device 500 may include:

[0192] The first acquisition module 510 is used to acquire at least one second vehicle detected by the first vehicle, as well as first measurement parameters collected within the associated threshold of the first vehicle at a first time, and a first predicted value of the motion parameters of each second vehicle at the first time and a second predicted value of the measured values ​​of the motion parameters of each second vehicle at the first time, wherein the coordinate system in which the first predicted value is located is a rectangular coordinate system and the coordinate system in which the second predicted value is located is a polar coordinate system.

[0193] The first calculation module 520 is used to calculate the first residual of the first measurement parameter and the second predicted value corresponding to each second vehicle in the polar coordinate system, and the second residual of the first measurement parameter and the first predicted value corresponding to each second vehicle in the rectangular coordinate system.

[0194] The second calculation module 530 is used to calculate a first score representing the correlation between the first measurement parameter and each second vehicle based on the first residual, and to calculate a second score representing the correlation between the first measurement parameter and each second vehicle based on the second residual.

[0195] The third calculation module 530 is used to calculate, based on the first score and the second score corresponding to each second vehicle, a target score that characterizes the correlation between the first measurement parameter and each second vehicle.

[0196] The first determining module 540 is used to determine the target correlation degree between the first measurement parameter and each of the second vehicles based on the target score.

[0197] In the embodiments of this application, by acquiring at least one second vehicle detected by the first vehicle, and the first measurement parameters collected within the association threshold of the first vehicle at a first time, and the first predicted value of the motion parameters of each second vehicle at the first time and the second predicted value of the measured values ​​of the motion parameters of each second vehicle at the first time, a first residual in the polar coordinate system and the second predicted value corresponding to each second vehicle corresponding to the first measurement parameters are calculated, and a second residual in the rectangular coordinate system is calculated. Based on the first residual, a first score for characterizing the association degree between the first measurement parameters and each second vehicle is calculated, and a score for characterizing the association degree between the first measurement parameters and each second vehicle is calculated based on the second residual. The second score of the correlation between the first measurement parameter and each second vehicle is calculated. Based on the first score and the second score corresponding to each second vehicle, a target score is calculated to characterize the correlation between the first measurement parameter and each second vehicle. Based on the target score, the target correlation between the first measurement parameter and each second vehicle is determined. In this way, when determining the correlation between the first measurement parameter and each second vehicle, multiple dimensions of the second vehicle's parameters are taken into account, rather than just looking at the distance between the first measurement parameter and each second vehicle. This improves the accuracy of determining the correlation between the first measurement parameter and each second vehicle, accurately matching the first measurement parameter to its corresponding second vehicle, and improving the accuracy of associating the first measurement parameter with each known second vehicle.

[0198] In some embodiments of this application, the first computing module 520 may specifically be used for:

[0199] Based on the first measurement parameter and the pre-set correspondence between the polar coordinate system and the rectangular coordinate system, the parameter value of the first measurement parameter in the rectangular coordinate system is determined;

[0200] Calculate the parameter value of the first measurement parameter in the Cartesian coordinate system and the second residual of the first predicted value corresponding to each second vehicle in the Cartesian coordinate system.

[0201] In some embodiments of this application, the first measurement parameter is obtained based on sensors on the first vehicle; the second calculation module 530 may specifically include:

[0202] The first calculation unit is used to calculate the prediction covariance corresponding to each of the second vehicles based on the second prediction value corresponding to each of the second vehicles.

[0203] The second calculation unit is used to calculate a first score, which characterizes the correlation between the first measurement parameter and each of the second vehicles, based on the predicted covariance, the first residual, and a first correction coefficient of the scoring function, wherein the first correction coefficient is determined based on the sensor.

[0204] In some embodiments of this application, the motion parameters include component parameters of each motion dimension; the second calculation module 530 may specifically include:

[0205] The first determining unit is used to obtain the component difference value of the component parameters of each second vehicle in each motion dimension based on the second residual.

[0206] The second determining unit is used to determine, for each of the second vehicles, a second correction coefficient for correcting the component differences in each motion dimension of the second vehicle based on the driving state of the second vehicle in each motion dimension at the first moment.

[0207] The third calculation unit is used to calculate the third residual for each of the second vehicles based on the second correction coefficients corresponding to each motion dimension of the second vehicle and the component differences of each motion dimension.

[0208] The third determining unit is used to determine a second score, based on the third residual corresponding to each second vehicle, to characterize the correlation between the first measurement parameter and each second vehicle.

[0209] In some embodiments of this application, the component differences of the component parameters of each motion dimension include component differences of the position dimension and component differences of the velocity dimension. The component differences of the position dimension include the first position component difference of the second vehicle in the first direction and the second position component difference in the second direction. The first direction is the lateral direction and the second direction is the longitudinal direction.

[0210] The second determining unit is specifically used for:

[0211] If the second vehicle is determined to be moving laterally in the first direction at the first moment, the range of the second correction coefficient for correcting the difference of the first position component is determined to be [0.5, 0.95].

[0212] If it is determined that the distance between the second vehicle and the first vehicle at the first moment is less than a preset distance threshold, or the size of the second vehicle is greater than a preset size threshold, the range of the second correction coefficient for correcting the difference of the second position component is determined to be [0.35, 0.85].

[0213] If it is determined that the second vehicle is in the Doppler region at the first moment, the range of the second correction coefficient for correcting the component difference of the velocity dimension is determined to be [0.15, 0.55].

[0214] In some embodiments of this application, the second computing module 530 may specifically include:

[0215] The fourth determining unit is used to determine the state coefficient of the second vehicle based on the motion state of the second vehicle at the first moment and the predicted motion state of the second vehicle at the first moment.

[0216] The third computing unit is specifically used for:

[0217] For each of the second vehicles, a third residual is calculated based on the second correction coefficients corresponding to each motion dimension of the second vehicle, the state coefficients, and the component differences of each motion dimension.

[0218] In some embodiments of this application, the third computing module 530 may specifically include:

[0219] The fifth determining unit is used to determine the type of the second vehicle for each second vehicle based on the distance between the second vehicle and the first vehicle, and the detection results of the second vehicle within a preset detection period;

[0220] The sixth determining unit is used to determine an additional score for each of the second vehicles based on the type of each second vehicle;

[0221] The fourth calculation unit is used to calculate, based on the additional score and the first score and the second score corresponding to each second vehicle, a target score that characterizes the correlation between the first measurement parameter and each second vehicle.

[0222] In some embodiments of this application, the fifth determining unit is specifically used for:

[0223] If it is determined that the distance between the second vehicle and the first vehicle is less than a preset distance threshold at the current time, or if it is predicted that the distance between the second vehicle and the first vehicle will be less than the preset distance threshold within a preset period after the current time, then the type of the second vehicle is determined to be the first type.

[0224] If the second vehicle is not detected within a predetermined number of consecutive detection cycles within a predetermined detection cycle, or if the number of times the second vehicle is detected within a predetermined detection cycle is less than a predetermined number, then the type of the second vehicle is determined to be the second type.

[0225] In some embodiments of this application, the sixth determining unit is specifically used for:

[0226] For each of the second vehicles, if the type of the second vehicle is determined to be the first type, a first score is assigned to the second vehicle, wherein the first score is a positive number;

[0227] For each of the second vehicles, if the type of the second vehicle is determined to be the second type, a second score is assigned to the second vehicle, wherein the first score is a negative number;

[0228] Based on the first score and the second score corresponding to each second vehicle, an additional score is determined for each second vehicle.

[0229] The data association apparatus provided in this application embodiment can be used to execute the data association methods provided in the above method embodiments. Its implementation principle and technical effect are similar, and for the sake of brevity, it will not be described in detail here.

[0230] Based on the same inventive concept, embodiments of this application also provide an electronic device.

[0231] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. For example... Figure 6 As shown, the electronic device may include a processor 1001 and a memory 1002 storing computer programs or instructions.

[0232] Specifically, the processor 1001 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of the present invention.

[0233] Memory 1002 may include mass storage for data or instructions. For example, and not limitingly, memory 1002 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 1002 may include removable or non-removable (or fixed) media. Where appropriate, memory 1002 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 1002 is non-volatile solid-state memory. Memory may include read-only memory (ROM), random-access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, a memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described in the data association method provided in the above embodiments.

[0234] The processor 1001 implements any of the data association methods described in the above embodiments by reading and executing computer program instructions stored in the memory 1002.

[0235] In one example, the electronic device may also include a communication interface 1003 and a bus 1010. For example, Figure 6 As shown, the processor 1001, memory 1002, and communication interface 1003 are connected through bus 1010 and complete communication with each other.

[0236] The communication interface 1003 is mainly used to realize communication between various modules, devices, units and / or devices in the embodiments of the present invention.

[0237] Bus 1010 includes hardware, software, or both, that couples components of an electronic device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 1010 may include one or more buses. While specific buses are described and illustrated in embodiments of the invention, the invention contemplates any suitable bus or interconnect.

[0238] The electronic device can execute the data association method in the embodiments of the present invention, thereby achieving... Figure 1 and Figure 3 Describe the data association method.

[0239] Furthermore, in conjunction with the data association methods in the above embodiments, this invention can be implemented using a readable storage medium. This readable storage medium stores program instructions, which, when executed by a processor, implement any of the data association methods described in the above embodiments.

[0240] In addition, in conjunction with the data association methods in the above embodiments, the present invention can provide a computer program product in which the instructions are executed by the processor of an electronic device, enabling the electronic device to execute any of the data association methods in the above embodiments.

[0241] It should be clarified that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of the present invention.

[0242] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this invention are programs or code segments used to perform the required tasks. The programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0243] It should also be noted that the exemplary embodiments mentioned in this invention describe methods or systems based on a series of steps or apparatus. However, this invention is not limited to the order of the steps described above; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0244] The aspects of this application have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by dedicated hardware performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0245] The above description is merely a specific embodiment of the present invention. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the protection scope of the present invention.

Claims

1. A data association method, characterized in that, The method includes: The system acquires at least one second vehicle detected by the first vehicle, as well as first measurement parameters collected within the associated threshold of the first vehicle at a first time, and a first predicted value of the motion parameters of each second vehicle at the first time and a second predicted value of the measured values ​​of the motion parameters of each second vehicle at the first time, wherein the coordinate system in which the first predicted value is located is a rectangular coordinate system and the coordinate system in which the second predicted value is located is a polar coordinate system. Calculate the first residual of the first measurement parameter and the second predicted value corresponding to each second vehicle in the polar coordinate system, and the second residual of the first measurement parameter and the first predicted value corresponding to each second vehicle in the rectangular coordinate system. Based on the first residual, a first score is calculated to characterize the correlation between the first measurement parameter and each of the second vehicles, and a second score is calculated based on the second residual to characterize the correlation between the first measurement parameter and each of the second vehicles. Based on the first score and the second score corresponding to each second vehicle, a target score is calculated to characterize the correlation between the first measurement parameter and each second vehicle. Based on the target score, the correlation degree between the first measurement parameter and the target of each second vehicle is determined.

2. The method according to claim 1, characterized in that, Calculate the second residuals of the first measurement parameter and the first predicted value corresponding to each of the second vehicles in the Cartesian coordinate system, including: Based on the first measurement parameter and the pre-set correspondence between the polar coordinate system and the rectangular coordinate system, the parameter value of the first measurement parameter in the rectangular coordinate system is determined; Calculate the parameter value of the first measurement parameter in the Cartesian coordinate system and the second residual of the first predicted value corresponding to each second vehicle in the Cartesian coordinate system.

3. The method according to claim 1, characterized in that, The first measurement parameter is obtained based on sensors on the first vehicle; The step of calculating a first score, based on the first residual, to characterize the correlation between the first measurement parameter and each of the second vehicles includes: Calculate the prediction covariance for each of the second vehicles based on the second prediction value for each of the second vehicles; Based on the predicted covariance, the first residual, and the first correction coefficient of the scoring function, a first score is calculated to characterize the correlation between the first measurement parameter and each of the second vehicles, wherein the first correction coefficient is determined based on the sensor.

4. The method according to claim 1, characterized in that, The motion parameters include component parameters for each motion dimension; Based on the second residual, a second score is calculated to characterize the correlation between the first measurement parameter and each of the second vehicles, including: Based on the second residual, the component difference values ​​of the component parameters of each second vehicle in each motion dimension are obtained; For each of the second vehicles, based on the driving state of the second vehicle in each motion dimension at the first moment, a second correction coefficient is determined to correct the component differences of the second vehicle in each motion dimension. For each of the second vehicles, a third residual is calculated based on the second correction coefficients corresponding to each motion dimension of the second vehicle and the component differences of each motion dimension. Based on the third residual corresponding to each second vehicle, a second score is determined to characterize the correlation between the first measurement parameter and each second vehicle.

5. The method according to claim 4, characterized in that, The component differences of the component parameters of each motion dimension include the component differences of the position dimension and the component differences of the velocity dimension. The component differences of the position dimension include the first position component difference of the second vehicle in the first direction and the second position component difference in the second direction. The first direction is the lateral direction and the second direction is the longitudinal direction. The step of determining the second correction parameter for correcting the component differences in each motion dimension of the second vehicle based on the driving state of the second vehicle in each motion dimension at the first moment includes: If the second vehicle is determined to be moving laterally in the first direction at the first moment, the range of the second correction coefficient for correcting the difference of the first position component is determined to be [0.5, 0.95]. If it is determined that the distance between the second vehicle and the first vehicle at the first moment is less than a preset distance threshold, or the size of the second vehicle is greater than a preset size threshold, the range of the second correction coefficient for correcting the difference of the second position component is determined to be [0.35, 0.85]. If it is determined that the second vehicle is in the Doppler region at the first moment, the range of the second correction coefficient for correcting the component difference of the velocity dimension is determined to be [0.15, 0.55].

6. The method according to claim 4, characterized in that, After determining the second correction coefficient for correcting the component differences in each dimension of motion of the second vehicle, the method further includes: Based on the motion state of the second vehicle at the first moment and the predicted motion state of the second vehicle at the first moment, the state coefficient of the second vehicle is determined; For each of the second vehicles, the third residual is calculated based on the second correction coefficients corresponding to each motion dimension of the second vehicle and the component differences of each motion dimension, including: For each of the second vehicles, a third residual is calculated based on the second correction coefficients corresponding to each motion dimension of the second vehicle, the state coefficients, and the component differences of each motion dimension.

7. The method according to claim 1, characterized in that, The step of calculating a target score to characterize the correlation between the first measurement parameter and each second vehicle based on the first score and the second score corresponding to each second vehicle includes: For each second vehicle, the type of the second vehicle is determined based on the distance between the second vehicle and the first vehicle, and the detection results of the second vehicle within a preset detection period; Determine additional points for each second vehicle based on its type; Based on the additional score, and the first score and the second score corresponding to each second vehicle, a target score is calculated to characterize the correlation between the first measurement parameter and each second vehicle.

8. The method according to claim 7, characterized in that, The step of determining the type of the second vehicle based on the distance between the second vehicle and the first vehicle, and the detection results of the second vehicle within a preset detection period, includes: If it is determined that the distance between the second vehicle and the first vehicle is less than a preset distance threshold at the current time, or if it is predicted that the distance between the second vehicle and the first vehicle will be less than the preset distance threshold within a preset period after the current time, then the type of the second vehicle is determined to be the first type. If the second vehicle is not detected within a predetermined number of consecutive detection cycles within a predetermined detection cycle, or if the number of times the second vehicle is detected within a predetermined detection cycle is less than a predetermined number, then the type of the second vehicle is determined to be the second type.

9. The method according to claim 8, characterized in that, Based on the type of each second vehicle, determine the additional score for each second vehicle, including: For each of the second vehicles, if the type of the second vehicle is determined to be the first type, a first score is assigned to the second vehicle, wherein the first score is a positive number; For each of the second vehicles, if the type of the second vehicle is determined to be the second type, a second score is assigned to the second vehicle, wherein the first score is a negative number; Based on the first score and the second score corresponding to each second vehicle, an additional score is determined for each second vehicle.

10. A data association device, characterized in that, The device includes: The first acquisition module is used to acquire at least one second vehicle detected by the first vehicle, as well as first measurement parameters collected within the associated threshold of the first vehicle at a first time, and a first predicted value of the motion parameters of each second vehicle at the first time and a second predicted value of the measured values ​​of the motion parameters of each second vehicle at the first time, wherein the coordinate system in which the first predicted value is located is a rectangular coordinate system and the coordinate system in which the second predicted value is located is a polar coordinate system. The first calculation module is used to calculate the first residual of the first measurement parameter and the second predicted value corresponding to each second vehicle in the polar coordinate system, and the second residual of the first measurement parameter and the first predicted value corresponding to each second vehicle in the rectangular coordinate system. The second calculation module is used to calculate a first score representing the correlation between the first measurement parameter and each second vehicle based on the first residual, and to calculate a second score representing the correlation between the first measurement parameter and each second vehicle based on the second residual. The third calculation module is used to calculate a target score that characterizes the correlation between the first measurement parameter and each second vehicle based on the first score and the second score corresponding to each second vehicle. The first determining module is used to determine the correlation degree between the first measurement parameter and the target of each second vehicle based on the target score.

Images