A method, device and electronic device for determining data association threshold

Abstract

The present invention discloses a method, device and electronic device for determining a data association threshold, which obtains target data of the nth target at the current moment, wherein the target data includes a target type recognition result, a target motion state parameter and a target heading angle, determines a position threshold in the data association threshold based on the target type recognition result and a preset spatial position scaling factor, and determines a Doppler speed threshold in the data association threshold based on the target motion state parameter and the target heading angle, combined with a preset Doppler speed threshold scaling factor. In the data association process, the present invention can adaptively set the data association threshold based on the target type recognition result, the target motion state parameter and the target heading angle, combined with the spatial position scaling factor and the Doppler speed threshold scaling factor. The entire association threshold setting process is relatively flexible, and refers to the actual working conditions of the target. Compared with traditional methods, it is more widely applicable and has strong engineering practice significance.

Description

Technical Field

[0001] The present invention relates to the technical field of target tracking, and more particularly to a method, device and electronic device for determining a data association threshold. Background Art

[0002] In a single-target clutter-free environment, there is only one target measurement value within the detection range of the environmental perception sensor (such as radar). At this time, the data processing does not have a data association link and only involves tracking problems. In the case of multiple targets and complex scenes on the actual road, there are many target measurement values ​​within the detection range of the environmental perception sensor, and the number of measurement values ​​is uncertain. At this time, the data association problem will be involved. The data association problem is to establish a matching relationship between the measurement value of the environmental perception sensor at a certain moment and the existing target data to determine whether these measurement values ​​come from the same target, and finally achieve the correct pairing of the measurement value and the target. Data association is one of the key issues in the data processing of environmental perception sensors. If the data association is incorrect, then the wrong data association will associate an erroneous measurement value with the tracking track. For environmental perception sensors, the wrong target measurement value matching may cause errors in the estimation of the target vehicle's motion trajectory or heading, which in turn leads to decisions with serious deviations.

[0003] In order to solve the problem of matching the target detected by the environmental perception sensor with the track, the data association algorithm is currently used to associate and pair the N measurement values ​​from the environmental perception sensor with the known M tracks, so that the measurement set of a track comes from the same target with the highest probability. The data association threshold (also known as the association area, association gate) used by the data association algorithm in the prior art is an area established with the target prediction value as the center, which delineates the range in which the measurement value of the tracked target may appear. The measurement value that falls within the data association threshold is the candidate measurement value, and data association is the processing of these candidate measurement values.

[0004] Common data association thresholds include elliptical thresholds, rectangular thresholds, etc. However, no matter what shape the data association threshold is, its specific threshold setting is a fixed threshold threshold set in theory. For example, in actual engineering applications, in order to pursue faster computing speed, Euclidean distance or new information weighting is usually selected to set the data association threshold. Obviously, in traditional data association algorithms, the method for determining the data association threshold is relatively idealized, has no obvious engineering practice significance, and cannot cover complex and changeable actual working conditions. Summary of the invention

[0005] In view of this, the present invention discloses a method, device and electronic device for determining a data association threshold, so as to realize adaptively setting the data association threshold based on target type recognition results, target motion state parameters and target heading angle in the data association process, combined with a spatial position scaling factor and a Doppler velocity threshold scaling factor.

[0006] A method for determining a data association threshold, comprising:

[0007] Obtaining target data of the nth target at the current moment, the target data including: target type recognition result, target motion state parameters and target heading angle;

[0008] Determine a position threshold in a data association threshold based on the target type recognition result and a preset spatial position scaling factor;

[0009] Based on the target motion state parameter and the target heading angle, combined with a preset Doppler velocity threshold scaling factor, a Doppler velocity threshold in the data association threshold is determined.

[0010] Optionally, the determining a position threshold in a data association threshold based on the target type recognition result and a preset spatial position scaling factor includes:

[0011] Determine the target size corresponding to the target type recognition result from a target type and size parameter correspondence table;

[0012] The position threshold is determined based on the target size and a preset spatial position scaling factor.

[0013] Optionally, determining the position threshold based on the target size and a preset spatial position scaling factor includes:

[0014] When the data association threshold is a rectangular threshold, the target size includes: target width W and target length L, and the expression of the position threshold is as follows:

[0015] ;

[0016] ;

[0017] In the formula, represents the horizontal position threshold, represents the vertical position threshold, Represents the spatial horizontal position scaling factor, Indicates the spatial longitudinal position scaling factor.

[0018] Optionally, after determining the position threshold in the data association threshold based on the target type recognition result and a preset spatial position scaling coefficient, the method further includes:

[0019] Obtain the valid measurement values ​​of all measurement points within the detection range of the environmental perception sensor at the current moment;

[0020] According to the target heading angle, the position threshold is rotated to a direction corresponding to the target heading to obtain a target position threshold;

[0021] Based on the target position threshold and the valid measurement values ​​of all measurement points obtained, the spatial position threshold constraint condition is determined as follows:

[0022] ;

[0023] In the formula, represents the target heading angle, represents the slope of the constraint line obtained based on the target heading angle at the current moment, Represents the spatial lateral coordinate of the i-th valid measurement value among all valid measurement values ​​within the detection range of the environmental perception sensor at the current moment, Represents the spatial longitudinal coordinate of the i-th valid measurement value among all valid measurement values ​​within the detection range of the environment perception sensor at the current moment; represents the horizontal position threshold, Indicates the vertical position threshold, x n Indicates the spatial horizontal coordinate of the nth target at the current moment, y n represents the spatial longitudinal coordinate of the nth target at the current moment, wherein the target motion state parameters include: x n and n .

[0024] Optionally, determining the Doppler velocity threshold in the data association threshold based on the target motion state parameter and the target heading angle in combination with a preset Doppler velocity threshold scaling factor includes:

[0025] Determine a plurality of pseudo-Doppler velocity values ​​of velocity information of the nth target at a data association threshold at a current moment based on the target motion state parameter and the target heading angle, wherein the target motion state parameter includes the velocity information;

[0026] A Doppler velocity threshold in the data association threshold is determined based on the plurality of pseudo-Doppler velocity values ​​and the Doppler velocity threshold scaling factor.

[0027] Optionally, the determining, based on the target motion state parameter and the target heading angle, a plurality of pseudo-Doppler velocity values ​​of the velocity information of the nth target at a data association threshold at a current moment includes:

[0028] According to the target heading angle, the position threshold is rotated to a direction corresponding to the target heading to obtain a target position threshold of the data association threshold;

[0029] Determine the pseudo-Doppler velocity value of the velocity information of the nth target at the corner point of the target position threshold at the current moment, and the expression of the pseudo-Doppler velocity value is as follows:

[0030] ;

[0031] In the formula, represents the pseudo-Doppler velocity value, represents the spatial lateral velocity of the nth target at the current moment, represents the spatial longitudinal velocity of the nth target at the current moment, x i Represents the horizontal coordinate of the i-th corner point, y i represents the ordinate of the i-th corner point, wherein the target motion state parameters include and .

[0032] Optionally, determining the Doppler velocity threshold in the data association threshold based on the multiple pseudo-Doppler velocity values ​​and the Doppler velocity threshold scaling factor comprises:

[0033] The Doppler velocity threshold is determined according to the following formula, and the expression of the Doppler velocity threshold is as follows:

[0034] ;

[0035] In the formula, represents the Doppler velocity threshold, represents the Doppler velocity threshold scaling factor, represents the maximum pseudo-Doppler velocity, Indicates the minimum pseudo-Doppler velocity.

[0036] Optionally, after determining the Doppler speed threshold in the data association threshold based on the target motion state parameter and the target heading angle in combination with a preset Doppler speed threshold scaling factor, the method further includes:

[0037] The Doppler velocity prediction value of the nth target at the current moment is determined according to the target motion state parameter. The expression of the Doppler velocity prediction value is as follows:

[0038] ;

[0039] In the formula, represents the Doppler velocity prediction value, represents the spatial lateral velocity of the nth target at the current moment, represents the spatial longitudinal velocity of the nth target at the current moment, x n Indicates the spatial horizontal coordinate of the nth target at the current moment, y n Represents the spatial longitudinal coordinate of the nth target at the current moment, wherein the target motion state parameters include: , 、x n and n ;

[0040] According to the Doppler velocity prediction value and the valid measurement values ​​of all measurement points within the detection range of the environment perception sensor at the current moment, the Doppler constraint threshold is determined as follows:

[0041] ;

[0042] In the formula, represents the Doppler velocity threshold, It represents the Doppler velocity of the ith valid measurement value among all valid measurement values ​​within the detection range of the environment perception sensor at the current moment.

[0043] A device for determining a data association threshold, comprising:

[0044] A data acquisition unit, used to acquire target data of the nth target at the current moment, wherein the target data includes: target type recognition result, target motion state parameters and target heading angle;

[0045] A position threshold determination unit, configured to determine a position threshold in a data association threshold based on the target type recognition result and a preset spatial position scaling factor;

[0046] The speed threshold determination unit is used to determine the Doppler speed threshold in the data association threshold based on the target motion state parameter and the target heading angle in combination with a preset Doppler speed threshold scaling factor.

[0047] An electronic device, comprising: a memory and a processor;

[0048] The memory is used to store at least one instruction;

[0049] The processor is used to execute the at least one instruction to implement the above-mentioned method for determining the data association threshold.

[0050] As can be seen from the above technical solutions, the present invention discloses a method, device and electronic device for determining a data association threshold, obtains the target data of the nth target at the current moment, the target data includes a target type recognition result, a target motion state parameter and a target heading angle, determines the position threshold in the data association threshold based on the target type recognition result and a preset spatial position scaling factor, and determines the Doppler speed threshold in the data association threshold based on the target motion state parameter and the target heading angle, combined with a preset Doppler speed threshold scaling factor. In the data association process, the present invention can adaptively set the data association threshold based on the target type recognition result, the target motion state parameter and the target heading angle, combined with the spatial position scaling factor and the Doppler speed threshold scaling factor. The entire association threshold setting process is relatively flexible, and refers to the actual working conditions of the target. Compared with traditional methods, it is more widely applicable and has strong engineering practice significance. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the disclosed drawings without paying creative work.

[0052] Figure 1 A flow chart of a method for determining a data association threshold disclosed in an embodiment of the present invention;

[0053] Figure 2 A schematic diagram of an extended target size identifier and tracking points disclosed in an embodiment of the present invention;

[0054] Figure 3 A schematic diagram of a basic threshold rotation of the nth target space at the current moment disclosed in an embodiment of the present invention;

[0055] Figure 4 A schematic diagram of an associated constraint area after rotation based on a target heading angle at the current moment disclosed in an embodiment of the present invention;

[0056] Figure 5 A schematic diagram of an embodiment of an n-th target association threshold disclosed in an embodiment of the present invention;

[0057] Figure 6 A schematic diagram of the structure of a device for determining a data association threshold disclosed in an embodiment of the present invention;

[0058] Figure 7 The present invention is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] The embodiment of the present invention discloses a method, device and electronic device for determining a data association threshold, which obtains target data of the nth target at the current moment, wherein the target data includes a target type recognition result, a target motion state parameter and a target heading angle, determines a position threshold in the data association threshold based on the target type recognition result and a preset spatial position scaling factor, and determines a Doppler speed threshold in the data association threshold based on the target motion state parameter and the target heading angle, combined with a preset Doppler speed threshold scaling factor. In the data association process, the present invention can adaptively set the data association threshold based on the target type recognition result, the target motion state parameter and the target heading angle, combined with the spatial position scaling factor and the Doppler speed threshold scaling factor. The entire association threshold setting process is relatively flexible, and refers to the actual working conditions of the target. Compared with traditional methods, it is more widely applicable and has strong engineering practice significance.

[0061] See also Figure 1 , a flow chart of a method for determining a data association threshold disclosed in an embodiment of the present invention, the method is applied in the data association matching stage of target tracking data, the method comprising:

[0062] Step S101, obtaining target data of the nth target at the current moment.

[0063] Target data includes: target type recognition results, target motion state parameters and target heading angle.

[0064] The nth target mentioned in this application refers to any target, and the value of n is a positive integer.

[0065] In practical applications, the target type recognition result can be determined by a vehicle-mounted sensor (such as a vehicle-mounted radar), and the vehicle-mounted sensor can distinguish and classify the detected targets. For example, the target type recognition result is a heavy truck.

[0066] The target motion state parameter in this application can be expressed as: n =[x n ,y n ,v xn ,v yn ], where x n Indicates the spatial horizontal coordinate of the nth target at the current moment, y nrepresents the spatial longitudinal coordinate of the nth target at the current moment, v xn represents the spatial lateral velocity of the nth target at the current moment, v yn It represents the spatial longitudinal velocity of the nth target at the current moment, where n is a positive integer.

[0067] Target heading angle express.

[0068] Among them, when the nth target is a target with a certain size, for example, the nth target is a rectangle, the target width is W, and the target length is L, it can be assumed that the tracking point is at the center point of the target, such as Figure 2 At point P shown in n Indicates the speed direction of the target, that is, the target's heading information.

[0069] Step S102: determining a position threshold in a data association threshold based on the target type recognition result and a preset spatial position scaling factor.

[0070] In practical applications, there is a strong correlation between the position threshold in the data association threshold and the target size. This application determines the target size corresponding to the target type recognition result from the target type and size parameter correspondence table, and then determines the position threshold based on the target size and the preset spatial position scaling factor.

[0071] The spatial position scaling factor describes the ratio of the change in the spatial length or size of the same object in different observation reference systems, reflecting the degree of size change of the object under different conditions.

[0072] In the process of data association, data from multiple sensors with different scanning cycles are involved, and these data may correspond to thousands of targets. The overlapping scanning coverage of multiple sensors leads to data duplication, and the data may also include false alarm traces and residual traces from previous moments. In order to limit the number of tracks and clutter, an association gate needs to be set.

[0073] The association gate is a subspace defined in the Euclidean space, which is used to filter the sensor observations that are closest to the estimated predicted values. Observations with large errors will not fall within the test threshold, so there is no need to perform test association, which allows for efficient and accurate feature storage and update. The types of association gates are roughly divided into four categories: rectangular threshold, elliptical threshold, annular threshold, and truncated fan threshold.

[0074] Taking the data association threshold as a rectangular threshold as an example, the target size includes: target width W and target length L, and the expression of the position threshold is as follows:

[0075] (1);

[0076] (2);

[0077] In the formula, represents the horizontal position threshold, represents the vertical position threshold, Represents the spatial horizontal position scaling factor, Indicates the spatial longitudinal position scaling factor.

[0078] Considering the influence of measurement noise and random errors, the spatial longitudinal position scaling factor And the spatial lateral position scaling factor Usually it gradually increases with distance, so the spatial longitudinal position scaling factor And the spatial lateral position scaling factor Generally, any value between [1.1 and 1.5] can be used to meet the association requirements.

[0079] Step S103: Determine the Doppler velocity threshold in the data association threshold based on the target motion state parameter and the target heading angle in combination with a preset Doppler velocity threshold scaling factor.

[0080] The Doppler speed threshold is a critical value set for the target speed measured based on the Doppler effect when detecting or tracking a target. When the target speed exceeds or falls below this critical value, corresponding alarms, recording or other processing actions may be triggered.

[0081] In multi-sensor data association, Doppler velocity thresholds can be used to screen potential targets. By setting different Doppler velocity thresholds, different types of targets can be distinguished. For example, fast-moving targets (such as aircraft, missiles) and slow-moving targets (such as pedestrians, vehicles) may have different Doppler velocity thresholds.

[0082] The Doppler velocity threshold itself is a critical value set according to the target velocity measured by the Doppler effect when performing target detection or tracking. Different types of targets may have different velocity ranges, so different Doppler velocity thresholds are required. The Doppler velocity threshold scaling factor can scale the Doppler velocity threshold to adapt to different application scenarios or target characteristics.

[0083] In summary, the present invention discloses a method for determining a data association threshold, obtaining target data of the nth target at the current moment, the target data including target type recognition result, target motion state parameter and target heading angle, determining the position threshold in the data association threshold based on the target type recognition result and a preset spatial position scaling factor, and determining the Doppler speed threshold in the data association threshold based on the target motion state parameter and the target heading angle, combined with a preset Doppler speed threshold scaling factor. In the data association process, the present invention can adaptively set the data association threshold based on the target type recognition result, the target motion state parameter and the target heading angle, combined with the spatial position scaling factor and the Doppler speed threshold scaling factor. The entire association threshold setting process is relatively flexible, and refers to the actual working conditions of the target. Compared with traditional methods, it is more widely applicable and has strong engineering practice significance.

[0084] In one embodiment, after step S102, the method for determining the data association threshold may further include:

[0085] (1) Obtain the valid measurement values ​​of all measurement points within the detection range of the environmental perception sensor at the current moment.

[0086] Among them, the environmental perception sensor can be a vehicle-mounted radar.

[0087] For the convenience of expression, it is assumed that the number of all measurement points within the detection range of the environmental perception sensor is m, and the effective measurement values ​​of each measurement point include: spatial lateral position x zi , spatial longitudinal position y zi and the Doppler velocity v zi , valid measurements are marked as {x zi , y zi , v zi}, i=1,2,…,m.

[0088] (2) According to the target heading angle, the position threshold is rotated to a direction corresponding to the target heading to obtain a target position threshold.

[0089] Specifically, the position thresholds shown in formula (1) and formula (2) are calculated according to the target heading angle The angle shown is rotated accordingly, that is, rotated to the direction corresponding to the target heading. Taking the rectangular threshold as a reference, such as Figure 3 As shown in the figure, the target position threshold obtained after rotation is a solid line frame. Figure 3 The dotted frame and dotted arrow in the figure represent the position and heading information of the target at the previous moment before the current moment, and the solid frame represents the position and heading information of the target at the current moment.

[0090] (3) Determine a spatial position threshold constraint condition based on the target position threshold and the valid measurement values ​​of all measurement points obtained.

[0091] Assume that the target heading angle at the current moment is , The identification is as Figure 3 As shown in , the position threshold constraint in the rotated data association threshold is Figure 4 Center Line 1 , l 2 , l 3 and l 4 The closed area formed by the spatial position threshold constraint conditions are as follows:

[0092] (3);

[0093] In the formula, represents the target heading angle, represents the slope of the constraint line obtained based on the target heading angle at the current moment, Represents the spatial lateral coordinate of the i-th valid measurement value among all valid measurement values ​​within the detection range of the environmental perception sensor at the current moment, Represents the spatial longitudinal coordinate of the i-th valid measurement value among all valid measurement values ​​within the detection range of the environment perception sensor at the current moment; represents the horizontal position threshold, Indicates the vertical position threshold, x n Indicates the spatial horizontal coordinate of the nth target at the current moment, y n Indicates the spatial longitudinal coordinate of the nth target at the current moment.

[0094] In one embodiment, step S103 may specifically include:

[0095] (1) Determining a plurality of pseudo-Doppler velocity values ​​of the velocity information of the nth target at a data association threshold at a current moment based on the target motion state parameter and the target heading angle.

[0096] The target motion state parameters include velocity information, which includes: the spatial lateral velocity v of the nth target at the current moment xn And the spatial longitudinal velocity v of the nth target at the current moment yn .

[0097] Specifically, according to the target heading angle, the position threshold is rotated to a direction corresponding to the target heading to obtain a target position threshold of the data association threshold;

[0098] The pseudo-Doppler velocity value of the velocity information of the n-th target at the corner point of the target position threshold at the current moment is determined.

[0099] Consider the size information attribute of the nth target, with the rectangular threshold as a reference, such as Figure 5 As shown, the speed information of the nth target at the current moment can be calculated separately at the four corner points p of the data association threshold i The pseudo-Doppler velocity value at (i=1,2,3,4) is expressed as follows:

[0100] (4);

[0101] In the formula, represents the pseudo-Doppler velocity value, represents the spatial lateral velocity of the nth target at the current moment, represents the spatial longitudinal velocity of the nth target at the current moment, x i Represents the horizontal coordinate of the i-th corner point, y i Represents the ordinate of the i-th corner point.

[0102] (2) Determining a Doppler velocity threshold in the data association threshold based on the multiple pseudo-Doppler velocity values ​​and the Doppler velocity threshold scaling factor.

[0103] Specifically, taking the rectangular threshold as a reference, such as Figure 5 As shown in FIG. 1 , the difference between the maximum pseudo-Doppler velocity and the minimum pseudo-Doppler velocity in the four corner points is taken, and combined with the Doppler velocity threshold scaling factor, the Doppler velocity threshold of the nth target in the data association threshold at the current moment can be obtained.

[0104] The expression of Doppler velocity threshold is as follows:

[0105] (5);

[0106] In the formula, represents the Doppler velocity threshold, represents the Doppler velocity threshold scaling factor, represents the maximum pseudo-Doppler velocity, Indicates the minimum pseudo-Doppler velocity.

[0107] Similarly, considering the influence of measurement noise, random error and Doppler spread, the Doppler velocity threshold scaling factor is Usually, any value between [1.0 and 3.75] can be taken to meet the data association requirements.

[0108] In one embodiment, after step S103, the following steps may also be included:

[0109] The Doppler velocity prediction value of the nth target at the current moment is determined according to the target motion state parameter. The expression of the Doppler velocity prediction value is as follows:

[0110] (6);

[0111] In the formula, represents the Doppler velocity prediction value, represents the spatial lateral velocity of the nth target at the current moment, represents the spatial longitudinal velocity of the nth target at the current moment, x n Indicates the spatial horizontal coordinate of the nth target at the current moment, y n Indicates the spatial longitudinal coordinate of the nth target at the current moment;

[0112] According to the Doppler velocity prediction value and the valid measurement values ​​of all measurement points within the detection range of the environment perception sensor at the current moment, the Doppler constraint threshold is determined as follows:

[0113] (7);

[0114] In the formula, represents the Doppler velocity threshold, It represents the Doppler velocity of the ith valid measurement value among all valid measurement values ​​within the detection range of the environment perception sensor at the current moment.

[0115] In summary, the method for determining the data association threshold disclosed in the present invention is based on the target type recognition result of the nth target at the current moment, combined with the spatial position scaling coefficient and , adaptively perform location threshold (also known as location basic threshold) and The setting and the position threshold are combined with the heading determination result. and The rotation of , finally get the spatial position threshold constraint condition shown in formula (3). In the setting of Doppler velocity threshold (also known as Doppler velocity threshold), based on the target motion state parameters and target heading angle of the nth target at the current moment, combined with the Doppler velocity threshold scaling factor , adaptively perform Doppler velocity threshold (also known as Doppler constraint threshold) The position threshold in the present invention and and the Doppler velocity threshold The settings are all based on the selected vehicle sensors and the data processing characteristics of the sensors.

[0116] It should be noted that. Figure 2~Figure 5 The related rotation is explained by taking a rectangular threshold as an example. For an elliptical threshold or a threshold of any other shape, the rotation method combined with the heading information is the same. For the setting of the Doppler threshold, any associated threshold of any shape can be set based on formula (5).

[0117] The method for determining the data association threshold disclosed in the present invention is described below in conjunction with a specific embodiment. Figure 5 As shown, z 1 ~z 6 are the 6 measured values ​​at the current moment, and the target motion state parameter X corresponding to the target at this time n =[3.51,12.3,2.1,4.25], target heading angle α n =63.71.

[0118] Assume that the target type recognition result is: heavy truck, spatial lateral position scaling factor =1.15, spatial longitudinal position scaling factor =1.0, the position threshold includes: Horizontal position threshold =1.38, vertical position threshold =9.0, based on formula (3), we know that z 1 and z 2 Satisfy the spatial position threshold constraint; based on the information of the four corner points of the target at this time, the Doppler velocity threshold scaling factor =1.25, combined with formula (5), the Doppler velocity threshold can be calculated =0.62,. So far, the data association threshold is set adaptively. Combining formula (3) and formula (7), it can be determined that the measurement point that meets the association threshold constraint condition at the current moment is z 1 and z 2 .

[0119] Corresponding to the above method embodiment, the present invention also discloses a device for determining a data association threshold.

[0120] See also Figure 6 , a schematic diagram of a structure of a device for determining a data association threshold disclosed in an embodiment of the present invention, the device may include:

[0121] The data acquisition unit 201 is used to acquire the target data of the nth target at the current moment, wherein the target data includes: target type recognition result, target motion state parameters and target heading angle.

[0122] The nth target mentioned in this application refers to any target, and the value of n is a positive integer.

[0123] In practical applications, the target type recognition result can be determined by a vehicle-mounted sensor (such as a vehicle-mounted radar), and the vehicle-mounted sensor can distinguish and classify the detected targets. For example, the target type recognition result is a heavy truck.

[0124] The target motion state parameter in this application can be expressed as: n =[x n ,y n ,v xn ,v yn ], where x n Indicates the spatial horizontal coordinate of the nth target at the current moment, y n represents the spatial longitudinal coordinate of the nth target at the current moment, v xn represents the spatial lateral velocity of the nth target at the current moment, v yn It represents the spatial longitudinal velocity of the nth target at the current moment, where n is a positive integer.

[0125] Target heading angle express.

[0126] Among them, when the nth target is a target with a certain size, for example, the nth target is a rectangle, the target width is W, and the target length is L, it can be assumed that the tracking point is at the center point of the target, such as Figure 2 At point P shown in n Indicates the speed direction of the target, that is, the target's heading information.

[0127] The position threshold determination unit 202 is used to determine the position threshold in the data association threshold based on the target type recognition result and a preset spatial position scaling coefficient.

[0128] In practical applications, there is a strong correlation between the position threshold in the data association threshold and the target size. This application determines the target size corresponding to the target type recognition result from the target type and size parameter correspondence table, and then determines the position threshold based on the target size and the preset spatial position scaling factor.

[0129] The spatial position scaling factor describes the ratio of the change in the spatial length or size of the same object in different observation reference systems, reflecting the degree of size change of the object under different conditions.

[0130] The speed threshold determination unit 203 is used to determine the Doppler speed threshold in the data association threshold based on the target motion state parameter and the target heading angle in combination with a preset Doppler speed threshold scaling factor.

[0131] The Doppler speed threshold is a critical value set for the target speed measured based on the Doppler effect when detecting or tracking a target. When the target speed exceeds or falls below this critical value, corresponding alarms, recording or other processing actions may be triggered.

[0132] In multi-sensor data association, Doppler velocity thresholds can be used to screen potential targets. By setting different Doppler velocity thresholds, different types of targets can be distinguished. For example, fast-moving targets (such as aircraft, missiles) and slow-moving targets (such as pedestrians, vehicles) may have different Doppler velocity thresholds.

[0133] The Doppler velocity threshold itself is a critical value set according to the target velocity measured by the Doppler effect when performing target detection or tracking. Different types of targets may have different velocity ranges, so different Doppler velocity thresholds are required. The Doppler velocity threshold scaling factor can scale the Doppler velocity threshold to adapt to different application scenarios or target characteristics.

[0134] In summary, the present invention discloses a device for determining a data association threshold, which obtains target data of the nth target at the current moment, wherein the target data includes a target type recognition result, a target motion state parameter, and a target heading angle, and determines a position threshold in the data association threshold based on the target type recognition result and a preset spatial position scaling factor, and determines a Doppler speed threshold in the data association threshold based on the target motion state parameter and the target heading angle, combined with a preset Doppler speed threshold scaling factor. In the data association process, the present invention can adaptively set the data association threshold based on the target type recognition result, the target motion state parameter, and the target heading angle, combined with the spatial position scaling factor and the Doppler speed threshold scaling factor. The entire association threshold setting process is relatively flexible, and refers to the actual working conditions of the target. Compared with traditional methods, it is more widely applicable and has strong engineering practice significance.

[0135] In one embodiment, the location threshold determination unit 202 is specifically configured to:

[0136] Determine the target size corresponding to the target type recognition result from a target type and size parameter correspondence table;

[0137] The position threshold is determined based on the target size and a preset spatial position scaling factor.

[0138] In one embodiment, the location threshold determination unit 202 is specifically configured to:

[0139] When the data association threshold is a rectangular threshold, the target size includes: target width W and target length L, and the expression of the position threshold is as follows:

[0140] (1);

[0141] (2);

[0142] In the formula, represents the horizontal position threshold, represents the vertical position threshold, Represents the spatial horizontal position scaling factor, Indicates the spatial longitudinal position scaling factor.

[0143] In one embodiment, after the location threshold determination unit 202, the data association threshold determination device may further include:

[0144] A measurement value acquisition unit, used to acquire valid measurement values ​​of all measurement points within the detection range of the environment perception sensor at the current moment;

[0145] A rotation unit, configured to rotate the position threshold to a direction corresponding to the target heading according to the target heading angle to obtain a target position threshold;

[0146] The position threshold constraint condition determination unit is used to determine the spatial position threshold constraint condition based on the target position threshold and the acquired valid measurement values ​​of all measurement points, as follows:

[0147] (3);

[0148] In the formula, represents the target heading angle, represents the slope of the constraint line obtained based on the target heading angle at the current moment, Represents the spatial lateral coordinate of the i-th valid measurement value among all valid measurement values ​​within the detection range of the environmental perception sensor at the current moment, Represents the spatial longitudinal coordinate of the i-th valid measurement value among all valid measurement values ​​within the detection range of the environment perception sensor at the current moment; represents the horizontal position threshold, Indicates the vertical position threshold, x n Indicates the spatial horizontal coordinate of the nth target at the current moment, y n represents the spatial longitudinal coordinate of the nth target at the current moment, wherein the target motion state parameters include: x n and n .

[0149] In one embodiment, the speed threshold determination unit 203 specifically includes:

[0150] a pseudo-Doppler velocity value determination subunit, configured to determine a plurality of pseudo-Doppler velocity values ​​of the velocity information of the nth target at a data association threshold at a current moment based on the target motion state parameter and the target heading angle, wherein the target motion state parameter includes the velocity information;

[0151] The Doppler velocity threshold determination subunit is configured to determine a Doppler velocity threshold in the data association threshold based on the multiple pseudo-Doppler velocity values ​​and the Doppler velocity threshold scaling factor.

[0152] In one embodiment, the pseudo-Doppler velocity value determination subunit is further configured to:

[0153] According to the target heading angle, the position threshold is rotated to a direction corresponding to the target heading to obtain a target position threshold of the data association threshold;

[0154] Determine the pseudo-Doppler velocity value of the velocity information of the nth target at the corner point of the target position threshold at the current moment, and the expression of the pseudo-Doppler velocity value is as follows:

[0155] (4);

[0156] In the formula, represents the pseudo-Doppler velocity value, represents the spatial lateral velocity of the nth target at the current moment, represents the spatial longitudinal velocity of the nth target at the current moment, x i Represents the horizontal coordinate of the i-th corner point, y i represents the ordinate of the i-th corner point, wherein the target motion state parameters include and .

[0157] In one embodiment, the Doppler velocity threshold determination subunit is specifically configured to:

[0158] The Doppler velocity threshold is determined according to the following formula, and the expression of the Doppler velocity threshold is as follows:

[0159] (5);

[0160] In the formula, represents the Doppler velocity threshold, represents the Doppler velocity threshold scaling factor, represents the maximum pseudo-Doppler velocity, Indicates the minimum pseudo-Doppler velocity.

[0161] In one embodiment, after the speed threshold determination unit 203, the data association threshold determination device may further include:

[0162] A Doppler velocity prediction value determination unit is used to determine the Doppler velocity prediction value of the nth target at the current moment according to the target motion state parameter, and the expression of the Doppler velocity prediction value is as follows:

[0163] ;

[0164] In the formula, represents the Doppler velocity prediction value, represents the spatial lateral velocity of the nth target at the current moment, represents the spatial longitudinal velocity of the nth target at the current moment, x n Indicates the spatial horizontal coordinate of the nth target at the current moment, y n Represents the spatial longitudinal coordinate of the nth target at the current moment, wherein the target motion state parameters include: , 、x n and n ;

[0165] The Doppler constraint threshold determination unit is used to determine the Doppler constraint threshold according to the Doppler velocity prediction value and the valid measurement values ​​of all measurement points within the detection range of the environment perception sensor at the current moment, as follows:

[0166] ;

[0167] In the formula, represents the Doppler velocity threshold, It represents the Doppler velocity of the ith valid measurement value among all valid measurement values ​​within the detection range of the environment perception sensor at the current moment.

[0168] Corresponding to the above embodiment, Figure 7 As shown, the present invention also provides an electronic device, which may include: a processor 1 and a memory 2;

[0169] The processor 1 and the memory 2 communicate with each other via a communication bus 3;

[0170] Processor 1, configured to execute at least one instruction;

[0171] Memory 2, used to store at least one instruction;

[0172] The processor 1 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0173] The memory 2 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0174] The processor executes at least one instruction to implement the steps shown in the embodiment of the method for determining a data association threshold.

[0175] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0176] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0177] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for determining a data association threshold, characterized in that: include: Get the current time n target data of a target, the target data comprising: target type recognition result, target motion state parameters and target heading angle; Determine the target size corresponding to the target type recognition result from the target type and size parameter correspondence table, and determine the position threshold in the data association threshold based on the target size and a preset spatial position scaling factor; the spatial position scaling factor is a ratio describing the change in the spatial size of the same object under different observation reference systems; Determine the first n a plurality of pseudo-Doppler velocity values ​​of velocity information of a target at a data association threshold, wherein the target motion state parameter includes the velocity information; A Doppler velocity threshold in the data association threshold is determined based on the plurality of pseudo-Doppler velocity values ​​and a Doppler velocity threshold scaling factor.

2. The method for determining a data association threshold according to claim 1, characterized in that: The determining the position threshold based on the target size and a preset spatial position scaling factor includes: When the data association threshold is a rectangular threshold, the target size includes: target width W and target length L , the expression of the position threshold is as follows: ； ； In the formula, represents the horizontal position threshold, represents the vertical position threshold, Represents the spatial horizontal position scaling factor, Indicates the spatial longitudinal position scaling factor.

3. The method for determining a data association threshold according to claim 1, characterized in that: After determining the position threshold in the data association threshold based on the target type recognition result and the preset spatial position scaling coefficient, the method further includes: Obtain the valid measurement values ​​of all measurement points within the detection range of the environmental perception sensor at the current moment; According to the target heading angle, the position threshold is rotated to a direction corresponding to the target heading to obtain a target position threshold; Based on the target position threshold and the valid measurement values ​​of all measurement points obtained, the spatial position threshold constraint condition is determined as follows: ； In the formula, represents the target heading angle, represents the slope of the constraint line obtained based on the target heading angle at the current moment, Indicates the first value among all valid measurements within the detection range of the current environment perception sensor. i The spatial lateral coordinates of the valid measurement values, Indicates the first value among all valid measurements within the detection range of the current environment perception sensor. i The spatial longitudinal coordinates of the valid measurement values; represents the horizontal position threshold, represents the vertical position threshold, x n Indicates the current moment n The spatial lateral coordinates of the target, y n Indicates the current moment n The spatial longitudinal coordinates of a target, wherein the target motion state parameters include: x n and y n .

4. The method for determining a data association threshold according to claim 1, characterized in that: The method of determining the first n The velocity information of a target at a data association threshold contains multiple pseudo-Doppler velocity values, including: According to the target heading angle, the position threshold is rotated to a direction corresponding to the target heading to obtain a target position threshold of the data association threshold; Determine the current moment n The velocity information of a target is the pseudo-Doppler velocity value at the corner point of the target position threshold, and the expression of the pseudo-Doppler velocity value is as follows: ； In the formula, represents the pseudo-Doppler velocity value, Indicates the current moment n The spatial lateral velocity of the target, Indicates the current moment n The spatial longitudinal velocity of the target, x i Indicates i The horizontal coordinates of the corner points, y i Indicates i The vertical coordinates of the corner points, wherein the target motion state parameters include and .

5. The method for determining a data association threshold according to claim 1 or 4, characterized in that: The determining the Doppler velocity threshold in the data association threshold based on the multiple pseudo-Doppler velocity values ​​and the Doppler velocity threshold scaling factor comprises: The Doppler velocity threshold is determined according to the following formula, and the expression of the Doppler velocity threshold is as follows: ； In the formula, represents the Doppler velocity threshold, represents the Doppler velocity threshold scaling factor, represents the maximum pseudo-Doppler velocity, Indicates the minimum pseudo-Doppler velocity.

6. The method for determining a data association threshold according to claim 1, characterized in that: After determining the Doppler velocity threshold in the data association threshold based on the target motion state parameter and the target heading angle in combination with a preset Doppler velocity threshold scaling factor, the method further includes: Determine the first n The Doppler velocity prediction value of a target, the expression of the Doppler velocity prediction value is as follows: ； In the formula, represents the Doppler velocity prediction value, Indicates the current moment n The spatial lateral velocity of the target, Indicates the current moment n The spatial longitudinal velocity of the target, x n Indicates the current moment n The spatial lateral coordinates of the target, y n Indicates the current moment n The spatial longitudinal coordinates of a target, wherein the target motion state parameters include: , , x n and y n ; According to the Doppler velocity prediction value and the valid measurement values ​​of all measurement points within the detection range of the environment perception sensor at the current moment, the Doppler constraint threshold is determined as follows: ； In the formula, represents the Doppler velocity threshold, Indicates the first value among all valid measurements within the detection range of the current environment perception sensor. i The Doppler velocity of the valid measurement.

7. A device for determining a data association threshold, characterized in that: include: The data acquisition unit is used to obtain the current moment n target data of a target, the target data comprising: target type recognition result, target motion state parameters and target heading angle; a position threshold determination unit, configured to determine the target size corresponding to the target type recognition result from a target type and size parameter correspondence table, and determine the position threshold in the data association threshold based on the target size and a preset spatial position scaling factor; the spatial position scaling factor is a ratio describing the change in the spatial size of the same object under different observation reference systems; A speed threshold determination unit for Determine the first n a plurality of pseudo-Doppler velocity values ​​of velocity information of a target at a data association threshold, wherein the target motion state parameter includes the velocity information; A Doppler velocity threshold in the data association threshold is determined based on the plurality of pseudo-Doppler velocity values ​​and a Doppler velocity threshold scaling factor.

8. An electronic device, characterized in that: The electronic device comprises: a memory and a processor; The memory is used to store at least one instruction; The processor is used to execute the at least one instruction to implement the method for determining the data association threshold as described in any one of claims 1 to 6.

Images