Object matching method, device, related equipment and vehicle

Abstract

The present application relates to an object matching method, device, related equipment and vehicle, which obtains the target object sensed by the sensor and the first sensed data corresponding to the target object; obtains the second sensed data used to generate the object tracking trajectory; matches the target object and the object tracking trajectory according to the first sensed data and the second sensed data, and obtains the target object tracking trajectory to which the target object belongs. Based on the above steps, the problem of different objects recognized by different sensors being fused incorrectly is solved, thereby improving the accuracy of the vehicle's autonomous driving planning and control, and improving the user experience.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to an object matching method, apparatus, related equipment and vehicle. Background Art

[0002] With the development of autonomous driving technology, vehicles are becoming more and more intelligent, and the algorithms of the sensor fusion modules on vehicles are also constantly improving. The sensor fusion module is used to match and fuse objects sensed by different sensors on the vehicle, and send the fusion results to the vehicle's planning and control module for planning and control of the vehicle's autonomous driving.

[0003] However, when different objects from different sensors are close to each other, they are easily judged as the same object, causing the problem of different objects being fused incorrectly, resulting in low accuracy of vehicle autonomous driving planning and control, affecting user experience. Summary of the invention

[0004] The embodiments of the present application provide an object matching method, device, electronic device, storage medium, computer program product and vehicle. By combining first perception data and second perception data that generates an object tracking trajectory, a target object and an object tracking trajectory are matched and processed to determine the target object tracking trajectory to which the target object belongs, thereby solving the problem of different objects recognized by different sensors being erroneously fused, improving the accuracy of vehicle autonomous driving planning and control, and improving user experience.

[0005] The present application provides an object matching method, including:

[0006] Acquire a target object sensed by a sensor and first sensed data corresponding to the target object;

[0007] Acquiring second perception data for generating an object tracking trajectory;

[0008] The target object and the object tracking trajectory are matched according to the first perception data and the second perception data to obtain the target object tracking trajectory to which the target object belongs.

[0009] Accordingly, an embodiment of the present application provides an object matching device, including:

[0010] A first perception data acquisition module, used to acquire a target object perceived by a sensor and first perception data corresponding to the target object;

[0011] A second perception data acquisition module, used to acquire second perception data for generating an object tracking trajectory;

[0012] A matching module is used to match the target object and the object tracking trajectory according to the first perception data and the second perception data to obtain the target object tracking trajectory to which the target object belongs.

[0013] In addition, an embodiment of the present application also provides an electronic device, including one or more processors and a memory, wherein the memory stores a computer program, and the processor is used to run the computer program in the memory to implement the object matching method provided in the embodiment of the present application.

[0014] In addition, an embodiment of the present application further provides a storage medium, wherein the storage medium stores a computer program. When the computer program runs on an electronic device, the computer program is used to enable the electronic device to execute any object matching method provided in the embodiment of the present application.

[0015] In addition, an embodiment of the present application also provides a computer program product, including a computer program or instructions, which, when executed by a processor, implements any object matching method provided in the embodiment of the present application.

[0016] In addition, an embodiment of the present application also provides a vehicle, including the above-mentioned electronic device, or the above-mentioned storage medium, or the above-mentioned computer program product.

[0017] In the embodiment of the present application, the target object sensed by the sensor and the first sensed data corresponding to the target object are obtained; the second sensed data used to generate the object tracking trajectory are obtained; the target object and the object tracking trajectory are matched according to the first sensed data and the second sensed data to obtain the target object tracking trajectory to which the target object belongs. Based on the above steps, the problem of different objects recognized by different sensors being fused incorrectly is solved, thereby improving the accuracy of the vehicle's autonomous driving planning and control, and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 is a flowchart of an object matching method provided by an embodiment of the present application;

[0020] Figure 2 This is a matching schematic diagram of an object matching method provided by an embodiment of the present application;

[0021] Figure 3is another matching schematic diagram of the object matching method provided by an embodiment of the present application;

[0022] Figure 4 It is a flow chart of the existing object matching method provided by this application;

[0023] Figure 5 This is a flow chart of an object matching method provided by an embodiment of the present application;

[0024] Figure 6 This is a schematic diagram of an error fusion provided by an embodiment of the present application;

[0025] Figure 7 is another schematic diagram of mis-fusion provided by an embodiment of the present application;

[0026] Figure 8 is another schematic diagram of mis-fusion provided by an embodiment of the present application;

[0027] Fig. 9 is another schematic diagram of mis-fusion provided by an embodiment of the present application;

[0028] Fig.10 is a schematic diagram of the structure of an object matching device provided by an embodiment of the present application;

[0029] Fig.11 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0031] The embodiments of the present application provide an object matching method, device, electronic device, storage medium, computer program product and vehicle. The object matching device can be integrated in an electronic device, which can be a server or a terminal.

[0032] Among them, the server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, network acceleration services (Content Delivery Network, CDN), as well as big data and artificial intelligence platforms.

[0033] The terminal may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal and the server may be directly or indirectly connected via wired or wireless communication, and this application does not limit this.

[0034] In addition, the term "plurality" in the embodiments of the present application refers to two or more than two. The terms "first" and "second" in the embodiments of the present application are used to distinguish descriptions and should not be understood as implying relative importance.

[0035] It should be noted that the description order of the following embodiments is not intended to limit the preferred order of the embodiments.

[0036] See also Figure 1 , Figure 1 : is a flowchart of an object matching method provided by an embodiment of the present application. The object matching method may include the following steps S101 to S103:

[0037] Step S101: Acquire a target object sensed by a sensor and first sensing data corresponding to the target object.

[0038] Among them, sensors are used to obtain the vehicle's perception data of surrounding objects during driving.

[0039] It should be noted that the embodiments of the present application include multiple types of sensors at the same time. The specific type of sensor can be adjusted according to actual conditions and is not limited by the embodiments of the present application.

[0040] For example, the sensor includes a camera sensor and a radar sensor. For another example, the sensor includes a camera sensor, a radar sensor, and an ultrasonic sensor. Furthermore, the radar sensor may also include a radio wave radar sensor, a laser radar sensor, and a millimeter wave radar sensor.

[0041] Among them, camera sensors are usually installed in the front, rear, side and rearview mirror of the vehicle. They obtain environmental information by shooting real-time video, and can be used to detect obstacles, pedestrians and traffic signs in front and around. Radar sensors can be used to detect the position and distance of surrounding objects, as well as their relative speed. By sending radio waves or laser pulses or millimeter wave signals and receiving their reflected signals, distance measurement and object recognition of obstacles around the vehicle can be achieved. Ultrasonic sensors can be used to detect the distance around the vehicle and measure the time of reflected sound wave signals to achieve obstacle detection during low-speed approach and reversing.

[0042] The target object is used to indicate the object or object detected by the data collected by the sensor. The first perception data is used to indicate the perception data belonging to the target object in the data collected by the sensor. The perception data includes but is not limited to the position information, speed information, acceleration information, etc. of the object. The specific information can be adjusted according to the actual situation.

[0043] It should be noted that the perception data (i.e., observation data) can be data collected by the sensor, or data obtained after a series of processing of the data collected by the sensor. Among them, the series of processing can be adjusted according to the actual situation, and the embodiments of the present application are not limited. For example, the series of processing may include filtering processing, that is, filtering the objects detected by the sensor, filtering out invalid or other objects that do not need to be stored, and the relevant data of the object. For another example, the series of processing may also include fusion processing, that is, obtaining the vehicle's own vehicle state data, combining it with the data collected by the sensor at the same time for fusion, and obtaining perception data. Here, the data collected by the sensor at the same time is relative perception data, and the perception data obtained after fusion is absolute perception data, and the subsequent processes use absolute perception data.

[0044] In some embodiments, obtaining first perception data corresponding to the target object includes: obtaining perception data perceived by the sensor on the target object at the current frame time, and perception data perceived by the sensor on the target object at the historical frame time, as the first perception data corresponding to the target object.

[0045] The historical frame time is used to indicate the time before the current frame time. For example, if the current frame time is time t, the historical frame time may be time (t-1).

[0046] Among them, the number of historical frame moments can be 1 or more, which is adjusted according to actual conditions and is not limited in the embodiments of the present application.

[0047] By acquiring the first perception data including the current frame time and the historical frame time, calling the historical information to participate in the calculation, the historical influence is taken into account, thereby improving the accuracy of object matching.

[0048] Step S102: Acquire second perception data for generating an object tracking trajectory.

[0049] The object tracking trajectory refers to a trajectory for the object formed by tracking the object.

[0050] The second perception data is used to indicate the composition, or the perception data for the object perceived by the sensor that generates the object tracking trajectory.

[0051] There are many ways to obtain the second perception data, which are not limited by the embodiments of the present application. For example, a list of object tracking trajectories formed at a certain moment is obtained, and the object tracking trajectory list includes multiple object tracking trajectories and perception data of the object tracking trajectories, and the perception data in the object tracking trajectory list is used as the second perception data. For another example, a historical object tracking trajectory memory is set up to store a historical message queue of multiple objects, and the historical message queue includes perception data of the object at multiple historical moments, and the perception data at each historical moment can be used to generate the object tracking trajectory of the object at the corresponding historical moment. From the historical object tracking trajectory memory, the second perception data for generating the object tracking trajectory is obtained, wherein the historical object tracking trajectory memory is used to store the perception data for generating the object tracking trajectory at a preset number of frames.

[0052] The second sensing data may be expressed in a form that is specifically set according to the sensor, and the present application embodiment does not limit this.

[0053] Exemplarily, when the sensor includes a first sensor and a second sensor, and the first sensor is a camera and the second sensor is a radar. The expression form of the second perception data may include [camera id, -1], [camera id, radar id], [-1, radar id]. Among them, [camera id, -1] indicates that the second perception data only includes data perceived by the camera, and the camera id indicates the object number perceived by the camera that generates the corresponding object tracking trajectory. [camera id, radar id] indicates that the second perception data includes data perceived by the camera and data perceived by the radar, the camera id indicates the object number perceived by the camera that generates the corresponding object tracking trajectory, and the radar id indicates the object number perceived by the radar that generates the corresponding object tracking trajectory. [-1, radar id] indicates that the second perception data only includes data perceived by the radar, and the radar id indicates the object number perceived by the radar that generates the corresponding object tracking trajectory.

[0054] Step S103: Matching the target object and the object tracking trajectory according to the first perception data and the second perception data to obtain the target object tracking trajectory to which the target object belongs.

[0055] Among them, the matching processing refers to the process of determining the target object tracking trajectory to which the target object corresponding to the first perception data belongs by measuring the matching degree between the first perception data and the second perception data.

[0056] In some embodiments, after obtaining the target object tracking trajectory to which the target object belongs, it is also necessary to update the historical object tracking trajectory memory according to the target object tracking trajectory to which each target object belongs and the first perception data corresponding to the target object.

[0057] In the object matching method provided in the embodiment of the present application, the target object sensed by the sensor and the first sensed data corresponding to the target object are obtained; the second sensed data used to generate the object tracking trajectory are obtained; the target object and the object tracking trajectory are matched according to the first sensed data and the second sensed data to obtain the target object tracking trajectory to which the target object belongs. Based on the above steps, the problem of different objects recognized by different sensors being fused incorrectly is solved, thereby improving the accuracy of the vehicle's autonomous driving planning and control, and improving the user experience.

[0058] In some embodiments, the first sensory data includes first location information, and the second sensory data includes second location information.

[0059] The first position information is used to indicate the position information of the target object corresponding to the first perception data, and the second position information is used to indicate the position information of the object to which the object tracking trajectory corresponding to the second perception data belongs.

[0060] In this embodiment, the target object and the object tracking trajectory are matched according to the first perception data and the second perception data to obtain the target object tracking trajectory to which the target object belongs, and the process may include: determining a distance index value between the target object and the object corresponding to the object tracking trajectory according to the first position information and the second position information, wherein the distance index value is used to indicate the degree of match between the target object and the object corresponding to the object tracking trajectory; based on the distance index value, matching the target object and the object tracking trajectory to obtain the target object tracking trajectory to which the target object belongs.

[0061] There are many ways to determine the distance index value, which are not limited in the embodiments of the present application. For example, the Mahalanobis distance between the target object and the object corresponding to the object tracking trajectory can be calculated based on the first position information and the second position information, and the distance index value can be determined based on the Mahalanobis distance result. For another example, the Euclidean distance between the target object and the object corresponding to the object tracking trajectory can be calculated based on the first position information and the second position information, and the distance index value can be determined based on the Euclidean distance result.

[0062] In some embodiments, the first perception data further includes first identification information, and the second perception data further includes second identification information.

[0063] In this embodiment, a matching result can be obtained by matching the first identification information and the second identification information, wherein the identification information is used to identify the sensor to which the corresponding perception data belongs, and the sensor includes a first sensor and a second sensor; if the matching result indicates a first matching result, the distance index value between the target object and the object corresponding to the object tracking trajectory is determined based on the first position information and the second position information.

[0064] The first identification information is used to identify the sensor to which the first perception data belongs. For example, the first perception data comes from a camera sensor. For another example, the first perception data comes from a radar sensor. The second identification information is used to identify the sensor to which the second perception data belongs. For example, the second perception data comes from a camera sensor. For another example, the second perception data comes from a radar sensor.

[0065] The sensor includes a first sensor and a second sensor, and the trust of the first sensor is greater than the trust of the second sensor. It can be understood that the first sensor and the second sensor refer to the classification standard of the sensors as the trust. The first sensor and the second sensor do not limit the number of sensor types. That is, the first sensor and the second sensor are not absolute names. They are also relative names. That is to say, when the sensor types include three or more, the sensors are divided with reference to the first sensor and the second sensor.

[0066] Furthermore, the first identification information may also identify the object to which the first perception data belongs. The second identification information may also identify the object to which the object tracking trajectory corresponding to the second perception data belongs.

[0067] Exemplarily, it is assumed that the first sensor is a camera and the second sensor is a radar, wherein the number of the target object detected by the camera is below 100, and the number of the target object detected by the radar is above 100. When the first identification information is 1, it means that the sensor to which the first perception data belongs is the camera, and the number of the object to which the first perception data belongs is 1. When the second identification information is 1000, it means that the sensor to which the second perception data belongs is the radar, and the number of the object to which the second perception data belongs is 1000.

[0068] The first matching result refers to a matching result obtained by calculating the distance index value between the target object and the object corresponding to the object tracking trajectory according to the first position information and the second position information. There are many ways to determine the first matching result.

[0069] In one example, the first identification information and the second identification information may be matched; if the second identification information does not contain the same target identification as the first identification information, the matching result is determined as the first matching result.

[0070] In this example, the second perception data also includes speed information of at least one object corresponding to the object tracking trajectory.

[0071] If the second identification information does not contain the same target identification as the first identification information, the specific process of determining the matching result as the first matching result may include: if the second identification information does not contain the same target identification as the first identification information, performing speed judgment based on the first speed information of the object corresponding to the identification in the second identification information to obtain a speed judgment result; if the speed judgment result is that the first speed information is within a preset speed range, determining the matching result as the first matching result.

[0072] The first speed information is used to indicate the speed information of the object corresponding to the identifier in the second identification information in the second perception data. The above-mentioned preset speed range refers to the speed range that can associate the target object detected by the sensor with the object corresponding to the object tracking trajectory.

[0073] In another example, the first identification information and the second identification information may also be matched; if the second identification information contains the same target identification as the first identification information, and the target identification is used to identify the second sensor, the matching result is determined as the first matching result.

[0074] In this example, the second perception data also includes speed information of at least one object corresponding to the object tracking trajectory.

[0075] If the second identification information contains a target identifier that is identical to the first identification information, and the target identifier is used to identify the second sensor, the specific process of determining the matching result as the first matching result may include: if the second identification information contains a target identifier that is identical to the first identification information, and the target identifier is used to identify the second sensor, performing speed judgment based on the second speed information of the object corresponding to the target identifier to obtain a speed judgment result; if the speed judgment result is that the second speed information is within a preset speed range, determining the matching result as the first matching result.

[0076] The second speed information is used to indicate the speed information of the object corresponding to the target identifier in the second perception data. The above-mentioned preset speed range refers to the speed range that can associate the target object detected by the sensor with the object corresponding to the object tracking trajectory.

[0077] In another example, the first identification information and the second identification information can also be matched; if the target first identification in the second identification information is different from the first identification information, and the second identification information also includes the target second identification, the matching result is determined as the first matching result, wherein the target first identification is used to identify the first sensor, and the target second identification is used to identify the second sensor.

[0078] In this example, the second perception data also includes speed information of at least one object corresponding to the object tracking trajectory. The above-mentioned preset speed range refers to a speed range that can associate the target object detected by the sensor with the object corresponding to the object tracking trajectory.

[0079] If the target first identification in the second identification information is different from the first identification information, and the second identification information also includes the target second identification, the specific process of determining the matching result as the first matching result may include: if the target first identification in the second identification information is different from the first identification information, and the second identification information also includes the target second identification, then performing speed judgment based on the third speed information of the object corresponding to the target second identification to obtain a speed judgment result; if the speed judgment result is that the third speed information is within a preset speed range, then determining the matching result as the first matching result.

[0080] Among them, the third speed information is used to indicate the speed information of the object corresponding to the target second identifier in the second perception data.

[0081] In one embodiment, after matching the first identification information and the second identification information to obtain a matching result, the method further includes: if the matching result indicates a second matching result, determining a distance index value between the target object and an object corresponding to the object tracking trajectory according to a preset distance index value.

[0082] The second matching result refers to a matching result in which the distance index value between the target object and the object corresponding to the object tracking trajectory can be directly determined.

[0083] The preset distance index value includes a preset minimum distance index value and a preset maximum distance index value.

[0084] The preset minimum distance index value refers to a preset distance index value that can directly determine that the target object is associated with the object corresponding to the object tracking trajectory. For example, the preset minimum distance index value is 0. The preset maximum distance index value refers to a preset distance index value that can directly determine that the target object is not associated with the object corresponding to the object tracking trajectory. For example, the preset maximum distance index value is 1. For another example, the preset maximum distance index value is a threshold value.

[0085] In this embodiment, if the matching result indicates a second matching result, the specific process of determining the distance index value between the target object and the object corresponding to the object tracking trajectory according to the preset distance index value may include: if there is a target identifier that is the same as the first identification information in the second identification information, and the target identifier is used to identify the first sensor, then according to the preset minimum distance index value, the distance index value between the target object and the object corresponding to the object tracking trajectory is determined.

[0086] In this embodiment, if the matching result indicates a second matching result, the specific process of determining the distance index value between the target object and the object corresponding to the object tracking trajectory according to the preset distance index value may also include: if the speed judgment result is that the first speed information is not within the preset speed range, or the speed judgment result is that the second speed information is not within the preset speed range, or the speed judgment result is that the third speed information is not within the preset speed range, then determining the distance index value between the target object and the object corresponding to the object tracking trajectory according to the preset maximum distance index value.

[0087] For example, for objects whose absolute values ​​of absolute longitudinal velocities in the recorded historical frames (i.e., the second perception data) are all greater than 2m / s, they are set to a pseudo-longitudinal motion state. For objects whose absolute values ​​of absolute longitudinal velocities in the recorded historical frames are all less than 1m / s, they are set to a pseudo-longitudinal still state. Two objects in pseudo-longitudinal motion and pseudo-longitudinal stillness cannot be associated. The same calculation and judgment is performed for the lateral velocity. For two objects with a velocity > 2m / s and a velocity <-2m / s, they are identified as two objects in opposite directions and cannot be associated.

[0088] By determining the second matching result, it can be directly determined whether the target object and the object corresponding to the object tracking trajectory can be associated, so as to reduce the subsequent amount of calculation and improve the speed of object matching.

[0089] Specifically, a specific embodiment is used to explain and illustrate the distance index value between the target object and the object corresponding to the object tracking trajectory. Figure 2 and Figure 3 It can be seen that Figure 2 and Figure 3 Applied in sensor systems consisting of cameras and millimeter-wave radars.

[0090] It should be noted that the stability of the camera detecting objects is much greater than that of the millimeter-wave radar detecting objects, that is, the trust of the camera is greater than that of the millimeter-wave radar. Therefore, the first sensor is the camera, and the second sensor is the millimeter-wave radar. The camera is the main sensor in the sensor system, and the millimeter-wave radar is the auxiliary sensor in the sensor system.

[0091] like Figure 2 As shown, when the input is a list of target objects detected by the camera (i.e., the first identification information is used to identify the first sensor). According to the first perception data and the second perception data, the target object in the target object list corresponding to the first perception data is matched with the object corresponding to the object tracking trajectory corresponding to the second perception data in the historical object tracking trajectory memory. The first identification information corresponding to the first perception data is the camera id.

[0092] When the second identification information is [camera id, -1] or [camera id, radar id], if the camera id in the first identification information is the same as the camera id in the second identification information, the distance index value between the target object and the object corresponding to the object tracking trajectory is directly determined to be 0 (that is, the preset minimum distance index value).

[0093] When the second identification information is [camera id, -1], if the camera id in the first identification information is different from the camera id in the second identification information, the distance index value between the target object and the object corresponding to the object tracking trajectory is directly determined to be the threshold value gate (that is, the preset maximum distance index value).

[0094] When the second identification information is [camera id, radar id], and the camera id in the first identification information is different from the camera id in the second identification information, it is necessary to obtain the speed information of the object corresponding to the radar id from the second perception data to perform speed judgment, so as to determine the distance index value between the target object and the object corresponding to the object tracking trajectory.

[0095] When the second identification information is [-1, radar id], determine whether the radar id in the second identification information is in the historical object tracking trajectory memory. If it is, it is necessary to obtain the speed information of the object corresponding to the radar id from the second perception data to perform speed determination, so as to determine the distance index value between the target object and the object corresponding to the object tracking trajectory. If it is not, directly determine the distance index value between the target object and the object corresponding to the object tracking trajectory as the threshold value gate.

[0096] like Figure 3 As shown, when the input is a list of target objects detected by the radar (i.e., the first identification information is used to identify the second sensor). According to the first perception data and the second perception data, the target object in the target object list corresponding to the first perception data is matched with the object corresponding to the object tracking track corresponding to the second perception data in the historical object tracking track memory. The first identification information corresponding to the first perception data is all radar id.

[0097] When the second identification information is [camera id, -1] or [camera id, radar id], it is determined whether the camera id in the second identification information is in the historical object tracking trajectory memory. If it exists, it is necessary to obtain the speed information of the object corresponding to the camera id from the second perception data to perform speed determination, so as to determine the distance index value between the target object and the object corresponding to the object tracking trajectory.

[0098] If it does not exist, when the second identification information is [camera id, -1], the distance index value between the target object and the object corresponding to the object tracking trajectory is directly determined as the threshold value gate. When the second identification information is [camera id, radarid], it is necessary to determine whether the radar id in the second identification information is in the historical object tracking trajectory memory. If it exists, it is necessary to obtain the speed information of the object corresponding to the radar id from the second perception data for speed determination, so as to determine the distance index value between the target object and the object corresponding to the object tracking trajectory.

[0099] When the second identification information is [-1, radar id], determine whether the radar id in the second identification information is in the historical object tracking trajectory memory. If it is, it is necessary to obtain the speed information of the object corresponding to the radar id from the second perception data for speed determination, so as to determine the distance index value between the target object and the object corresponding to the object tracking trajectory. If it does not exist or the speed information is not within the preset speed range, the distance index value between the target object and the object corresponding to the object tracking trajectory is directly determined as the threshold value gate.

[0100] In some embodiments, the process of determining the distance index value between the target object and the object corresponding to the object tracking trajectory based on the first position information and the second position information can also be: performing distance calculation based on the first position information and the second position information to obtain an initial distance index value; determining a correction parameter based on the first perception data; and adjusting the initial distance index value based on the correction parameter to obtain the distance index value between the target object and the object corresponding to the object tracking trajectory.

[0101] Among them, the correction parameter includes at least one of a speed correction parameter, a distance correction parameter, a frame number correction parameter, and a penalty correction parameter. The speed correction parameter is used to indicate a parameter for adjusting the initial distance index value based on the speed dimension. The distance correction parameter is used to indicate a parameter for adjusting the initial distance index value based on the distance dimension. The frame number correction parameter is used to indicate a parameter for adjusting the initial distance index value based on the number dimension of historical frame moments of the perception data. The penalty correction parameter is used to indicate a parameter for adjusting the initial distance index value based on a preset penalty coefficient.

[0102] For example, the distance index value is obtained according to the following formula (1):

[0103] (1)

[0104] Among them, Dist is the distance index value, MDist is the Mahalanobis distance between the trajectory corresponding to the first perception data and the trajectory corresponding to the second perception data, SpeedCost is the speed correction parameter, MagnifyCost is the distance correction parameter, TraSizeCost is the frame number correction parameter, and NearbyCost is the penalty correction parameter.

[0105] Among them, MagnifyCost can be understood as the distance variance cost, which is used to reflect the inter-frame stability of the distance between two trajectories. Instability means that the objects corresponding to the two trajectories are more likely to be not the same object and the correlation is weak.

[0106] Determine MagnifyCost according to the following formula (2):

[0107]

[0108] (2)

[0109] Where x is the lateral position information, y is the longitudinal position information, and vx is the speed in the x direction (e.g., the x direction refers to the direction perpendicular to the rear axle of the vehicle). Σ is the covariance matrix of the multidimensional random variable, μ is the sample mean, and n is the number of first perception data.

[0110] Among them, TraSizeCost can be understood as the cost related to the number of frames. According to the following formula (3), TraSizeCos is determined:

[0111] (3)

[0112] Among them, FrameGainA, FrameGainB, and FrameGainC are all frame correction values.

[0113] It should be noted that due to the different lengths of the two trajectories, it is necessary to add a penalty TraSizeCost to the function for calculating the distance index value. The frame correction value is determined according to the number of frame moments contained in the first perception data. For example, the number of frame moments contained in the first perception data is 3, that is, the trajectory involved in the matching calculation has at least 1 frame and at most 3 frames. Therefore, 3 frame correction values ​​are set. The specific content of each frame correction value can be adjusted according to the actual situation. For example, the correction values ​​of FrameGainA, FrameGainB, and FrameGainC gradually decrease as the corresponding historical frame moments are from near to far.

[0114] Among them, SpeedCost can be understood as speed cost. For the two objects involved in the calculation, their x-position, y-position, and x-speed are comprehensively considered in the Mahalanobis distance. However, for two objects with similar positions, their position difference is small, and it is necessary to increase the lateral speed cost and the longitudinal speed cost to make up for the shortcomings of the Mahalanobis distance. For two objects within the x-range of 19m of the vehicle, they are set as close-point objects and their SpeedCost is doubled, which means increasing the difficulty of close-point object fusion and ensuring the accuracy of fusion.

[0115] According to the following formula (4), SpeedCos is determined:

[0116] (4)

[0117] Among them, VecDiff represents the i-th speed information contained in the first perception data. Indicates the average speed information contained in the first perception data.

[0118] Among them, NearbyCost can be understood as the additional penalty for nearby objects. For example, for pedestrians at a nearby point, their speed and lateral speed are relatively small compared to non-motor vehicles and motor vehicles, and the above cost is sometimes difficult to play a role. Therefore, for pedestrians at a nearby point, the NearbyCost penalty is increased, and the default value is 0.5 gate.

[0119] In some embodiments, based on the distance index value, the target object and the object tracking trajectory are matched to obtain the target object tracking trajectory to which the target object belongs, including: filling the distance index value between the target object and each object tracking trajectory into the corresponding rows and columns of the distance matrix, wherein the columns of the distance matrix are used to indicate the target object, and the rows of the distance matrix are used to indicate the objects corresponding to the object tracking trajectory; performing association processing based on the filled distance matrix to obtain the target object tracking trajectory to which the target object belongs.

[0120] Among them, the process of performing association processing based on the filled distance matrix to obtain the target object tracking trajectory to which the target object belongs can be: performing row and column matching on the distance matrix to obtain the minimum distance index value corresponding to each row and column; and using the object tracking trajectory corresponding to the row where the minimum distance index value is located as the target object tracking trajectory to which the target object corresponding to the column where the minimum distance index value is located belongs.

[0121] Furthermore, association algorithms such as nearest neighbor association and Hungarian algorithm are used to match the target object list and the object tracking trajectory list through the calculation results of the distance matrix to obtain matching association results; according to the association results, the information of the target object is used as observation, and the maintenance and update operations of the object tracking trajectory list are completed through filtering methods such as Kalman filtering to complete the maintenance of the fusion object. The object tracking trajectory in the object tracking trajectory list is prioritized and the quality of each object tracking trajectory is judged, and it is adjusted to the format required by the downstream for distribution.

[0122] like Figure 4 As shown, Figure 4 It is a flow chart of the prior art. That is, in the prior art, the process of determining the target object tracking trajectory to which the target object belongs is: according to the effective sensor observation data of a certain perception sensor input and the effective vehicle state of the vehicle body sensor, the target object list and the vehicle body state are obtained respectively. The input data is preprocessed to filter out unreasonable target objects. The target object and the object tracking trajectory are temporally and spatially registered. According to the single frame data at the current timestamp, the distance matrix between the target object in the target object list and the object tracking trajectory in the object tracking trajectory list is determined by the matching algorithm. Using association algorithms such as nearest neighbor association, Hungarian algorithm, etc., the target object list and the object tracking trajectory list are matched by the calculation results of the distance matrix to obtain the matching association results; according to the association results, the information of the target object is used as observation, and the maintenance and update operation of the object tracking trajectory list is completed by filtering methods such as Kalman filtering, and the maintenance of the fusion object is completed. The object tracking trajectory in the object tracking trajectory list is prioritized and the quality of each object tracking trajectory is judged, and it is adjusted to the format required by the downstream for distribution. Among them, Kalman filtering is an algorithm that uses the linear system state equation to optimally estimate the system state through the system input and output observation data. Since the observation data includes the influence of noise and interference in the system, the optimal estimation can also be regarded as a filtering process.

[0123] In the prior art, when different objects from different sensors are close to each other, the matching algorithm may determine that the two objects are the same target object and perform incorrect fusion, which has a serious impact on the downstream autonomous driving planning and control modules. For example, when pedestrians traveling laterally relative to the vehicle and roadside fences are close in position, mis-fusion will occur. However, due to the limitation of sensor performance, there will be a situation where target detection is lost. For example, in a vehicle scene, the camera sensor only detects pedestrians, and the radar sensor only detects pillars. Due to the different trust levels of different sensors. And the target object after mis-fusion will trust the radar sensor more in the x direction and the camera sensor more in the y direction, resulting in the mis-fusion target object being closer to the vehicle relative to the position detected by the camera, but the actual situation is very far away, which will also cause problems in downstream planning and control, such as the possibility of mis-triggering the automatic emergency braking system (Autonomous Emergency Braking, AEB).

[0124] For example, Figures 6 to 9 As shown, Figures 6 to 9 This is a mis-fusion scenario caused by the solution based on the existing technology. It should be noted that Figures 6 to 9 The left picture is the display of the visualization software, and the right picture is the picture of the on-board camera at the corresponding moment. The white box in the left picture is the object detected by the camera, the other boxes are the objects detected by the radar, the green triangle is the fusion object selected by AEB, and the red dotted box is the location of the object detected by the camera in the fusion object selected by AEB.

[0125] Figure 6 1 is a schematic diagram of a horizontal scene with mis-fusion provided in an embodiment of the present application. The horizontal scene refers to a scene in which a pedestrian crossing horizontally and a stationary obstacle such as a fence or a vehicle on the roadside may mis-fusion.

[0126] Figure 7 1 is a schematic diagram of a longitudinal scene provided by an embodiment of the present application where mis-fusion occurs. The longitudinal scene refers to a scene where a non-motor vehicle traveling longitudinally may mis-merge with stationary obstacles such as fences and vehicles at the roadside.

[0127] Figure 8 This is a schematic diagram of a mis-fusion in a vehicle waiting for a red light and starting at rest provided in an embodiment of the present application. The vehicle waiting for a red light and starting at rest scenario refers to a mis-fusion scenario caused by a radar point hitting the front car and slowly moving to a stationary obstacle such as a roadside fence as the front car starts, but due to a recognition error of the radar.

[0128] Fig. 91 is a schematic diagram of a static obstacle scene provided by an embodiment of the present application where the static obstacle scene refers to a scene where the static obstacle is mistakenly merged due to various influences.

[0129] like Figure 5 As shown, Figure 5 A flow chart of the object matching method provided in the embodiment of the present application. Figure 5 As shown, in the embodiment of the present application, the process of obtaining the target object tracking trajectory to which the target object belongs is: according to the valid sensor observation data of a certain perception sensor input, and the valid vehicle state of the vehicle body sensor, the target object list and the vehicle body state are obtained respectively. The input data is preprocessed to filter out unreasonable target objects. The target object and the object tracking trajectory are aligned in time and space. The second perception data and the historical object tracking trajectory corresponding to the target object under the current timestamp and the historical timestamp are obtained from the historical object tracking trajectory data. Through the matching algorithm, the distance matrix between the first perception data and the second perception data of the target object in the target object list is determined. Using an association algorithm, such as the nearest neighbor association, the Hungarian algorithm, etc., the first perception data and the second perception data are matched by the calculation result of the distance matrix to obtain a matching association result; according to the association result, the information of the target object is used as an observation, and the maintenance and update operation of the object tracking trajectory list is completed by a filtering method such as a Kalman filter, and the maintenance of the fusion object is completed. The object tracking trajectory in the object tracking trajectory list is prioritized and the quality of each object tracking trajectory is judged, and it is adjusted to the format required by the downstream for distribution.

[0130] In the embodiment of the present application, the target object sensed by the sensor and the first sensed data corresponding to the target object are obtained; the second sensed data used to generate the object tracking trajectory are obtained; the target object and the object tracking trajectory are matched according to the first sensed data and the second sensed data to obtain the target object tracking trajectory to which the target object belongs. Based on the above steps, the problem of different objects recognized by different sensors being fused incorrectly is solved, thereby improving the accuracy of the vehicle's autonomous driving planning and control, and improving the user experience.

[0131] In order to better implement the object matching method provided in the embodiment of the present application, the embodiment of the present application also provides a device based on the above object matching method. The meanings of the terms are the same as those in the above object matching method, and the specific implementation details can refer to the description in the method embodiment.

[0132] For example, Fig.10 As shown, the object matching device may include a first perception data acquisition unit 201, a second perception data acquisition unit 202 and a matching unit 203, as follows:

[0133] A first perception data acquisition unit 201 is used to acquire a target object perceived by a sensor and first perception data corresponding to the target object;

[0134] A second perception data acquisition unit 202, used to acquire second perception data for generating an object tracking trajectory;

[0135] The matching unit 203 is used to match the target object and the object tracking trajectory according to the first perception data and the second perception data to obtain the target object tracking trajectory to which the target object belongs.

[0136] Optionally, in the embodiment of the present application, the first perception data includes the first location information, the second perception data includes the second location information, and the matching unit 203 includes:

[0137] a distance index value calculation subunit, configured to determine a distance index value between the target object and the object corresponding to the object tracking trajectory according to the first position information and the second position information, wherein the distance index value is used to indicate a matching degree between the target object and the object corresponding to the object tracking trajectory;

[0138] The matching subunit is used to match the target object and the object tracking trajectory based on the distance index value to obtain the target object tracking trajectory to which the target object belongs.

[0139] Optionally, in an embodiment of the present application, the first perception data further includes first identification information, and the second perception data further includes second identification information; the distance index value calculation subunit includes:

[0140] A matching result determination module, used to match the first identification information and the second identification information to obtain a matching result, wherein the identification information is used to identify the sensor to which the corresponding perception data belongs, and the sensor includes a first sensor and a second sensor;

[0141] The first matching module is configured to determine a distance index value between the target object and an object corresponding to the object tracking trajectory according to the first position information and the second position information if the matching result indicates a first matching result.

[0142] Optionally, in an embodiment of the present application, the matching result determination module includes:

[0143] A first matching submodule, used to match the first identification information with the second identification information;

[0144] The first matching result determination submodule is used to determine the matching result as the first matching result if the second identification information does not contain the same target identification as the first identification information.

[0145] Optionally, in an embodiment of the present application, the second perception data further includes speed information of at least one object corresponding to the object tracking trajectory; the above-mentioned matching result first determination submodule includes:

[0146] If the target identifier that is the same as the first identifier information does not exist in the second identifier information, speed judgment is performed according to the first speed information of the object corresponding to the identifier in the second identifier information to obtain a speed judgment result;

[0147] If the speed determination result is that the first speed information is within the preset speed range, the matching result is determined as the first matching result.

[0148] Optionally, in an embodiment of the present application, the matching result determination module includes:

[0149] A second matching submodule, used to match the first identification information with the second identification information;

[0150] The second matching result determination submodule is configured to determine the matching result as the first matching result if the second identification information contains a target identification that is the same as the first identification information, and the target identification is used to identify the second sensor.

[0151] Optionally, in an embodiment of the present application, the second perception data further includes speed information of at least one object corresponding to the object tracking trajectory; the above-mentioned second matching result determination submodule includes:

[0152] If the second identification information contains a target identification that is the same as the first identification information, and the target identification is used to identify the second sensor, a speed judgment is performed according to the second speed information of the object corresponding to the target identification to obtain a speed judgment result;

[0153] If the speed determination result is that the second speed information is within the preset speed range, the matching result is determined as the first matching result.

[0154] Optionally, in an embodiment of the present application, the matching result determination module includes:

[0155] A matching third submodule, used to match the first identification information with the second identification information;

[0156] The third matching result determination submodule is used to determine the matching result as the first matching result if the target first identification in the second identification information is different from the first identification information, and the second identification information also includes the target second identification, wherein the target first identification is used to identify the first sensor and the target second identification is used to identify the second sensor.

[0157] Optionally, in the embodiment of the present application, the second perception data further includes speed information of at least one object corresponding to the object tracking trajectory; the third matching result determination submodule includes:

[0158] If the target first identification in the second identification information is different from the first identification information, and the second identification information also includes the target second identification, then the speed is judged according to the third speed information of the object corresponding to the target second identification to obtain a speed judgment result;

[0159] If the speed determination result is that the third speed information is within the preset speed range, the matching result is determined as the first matching result.

[0160] Optionally, in the embodiment of the present application, after the above-mentioned matching result determination module, it also includes:

[0161] The second matching module is configured to determine a distance index value between the target object and an object corresponding to the object tracking trajectory according to a preset distance index value if the matching result indicates a second matching result.

[0162] Optionally, in an embodiment of the present application, the preset distance index value includes a preset minimum distance index value, and the second matching module includes:

[0163] If the second identification information contains the same target identification as the first identification information, and the target identification is used to identify the first sensor, a distance index value between the target object and the object corresponding to the object tracking trajectory is determined according to a preset minimum distance index value.

[0164] Optionally, in an embodiment of the present application, the distance index value calculation subunit includes:

[0165] An initial distance index value determination module, used to perform distance calculation according to the first position information and the second position information to obtain an initial distance index value;

[0166] A correction parameter determination module, used to determine the correction parameter based on the first perception data;

[0167] The adjustment module is used to adjust the initial distance index value based on the correction parameter to obtain the distance index value between the target object and the object corresponding to the object tracking trajectory.

[0168] Optionally, in an embodiment of the present application, the above-mentioned correction parameters include at least one of a speed correction parameter, a distance correction parameter, a frame number correction parameter, and a penalty correction parameter.

[0169] Optionally, in an embodiment of the present application, the matching subunit includes:

[0170] A filling module is used to fill the distance index value between the target object and each object tracking track into the corresponding row and column of the distance matrix, wherein the column of the distance matrix is ​​used to indicate the target object, and the row of the distance matrix is ​​used to indicate the object corresponding to the object tracking track;

[0171] The association module is used to perform association processing based on the filled distance matrix to obtain the target object tracking trajectory to which the target object belongs.

[0172] Optionally, in an embodiment of the present application, the above-mentioned association module includes:

[0173] The row-column matching submodule is used to match the rows and columns of the distance matrix to obtain the minimum distance index value corresponding to each row and column;

[0174] The matching submodule is used to use the object tracking trajectory corresponding to the row where the minimum distance index value is located as the target object tracking trajectory to which the target object corresponding to the column where the minimum distance index value is located belongs.

[0175] Optionally, in an embodiment of the present application, the step of obtaining the first perception data corresponding to the target object includes:

[0176] The first perception data acquisition subunit is used to acquire the perception data of the target object perceived by the sensor at the current frame time, and the perception data of the target object perceived by the sensor at the historical frame time, as the first perception data corresponding to the target object.

[0177] In the device provided in the embodiment of the present application, the first perception data acquisition unit 201 acquires the target object perceived by the sensor and the first perception data corresponding to the target object; the second perception data acquisition unit 202 acquires the second perception data used to generate the object tracking trajectory; the matching unit 203 matches the target object and the object tracking trajectory according to the first perception data and the second perception data to obtain the target object tracking trajectory to which the target object belongs. Based on the above steps, the problem of different objects recognized by different sensors being fused incorrectly is solved, thereby improving the accuracy of the vehicle's autonomous driving planning and control, and improving the user experience.

[0178] In specific implementation, the above modules can be implemented as independent entities, or can be arbitrarily combined and implemented as the same or several entities. The specific implementation methods and corresponding beneficial effects of the above modules can be found in the previous method embodiments, which will not be repeated here.

[0179] The embodiment of the present application also provides an electronic device, wherein the operating system of the electronic device includes a first operating system and a second operating system. Fig.11 As shown, it shows a schematic diagram of the structure of the electronic device involved in the embodiment of the present application, specifically:

[0180] The electronic device may include components such as a processor 301 with one or more processing cores, a memory 302 with one or more storage media, a power supply 303, and an input unit 304. Those skilled in the art will appreciate that Fig.11 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0181] The processor 301 is the control center of the electronic device, which uses various interfaces and lines to connect various parts of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing computer programs and / or modules stored in the memory 302, and calling data stored in the memory 302. Optionally, the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 301.

[0182] The memory 302 can be used to store computer programs and modules. The processor 301 executes various functional applications and data processing by running the computer programs and modules stored in the memory 302. The memory 302 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, a computer program required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the electronic device, etc. In addition, the memory 302 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 302 can also include a memory controller to provide the processor 301 with access to the memory 302.

[0183] The electronic device also includes a power supply 303 for supplying power to each component. Preferably, the power supply 303 can be logically connected to the processor 301 through a power management system, so that the power management system can manage charging, discharging, power consumption and other functions. The power supply 303 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components.

[0184] The electronic device may further include an input unit 304, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0185] Although not shown, the electronic device may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 301 in the electronic device will load the executable files corresponding to the processes of one or more computer programs into the memory 302 according to the following instructions, and the processor 301 will run the computer programs stored in the memory 302, thereby realizing various functions, such as:

[0186] Acquire a target object sensed by a sensor and first sensed data corresponding to the target object;

[0187] Acquiring second perception data for generating an object tracking trajectory;

[0188] According to the first perception data and the second perception data, the target object and the object tracking trajectory are matched to obtain the target object tracking trajectory to which the target object belongs.

[0189] It can be seen that the electronic device provided in the embodiment of the present application obtains the target object sensed by the sensor and the first sensed data corresponding to the target object; obtains the second sensed data used to generate the object tracking trajectory; matches the target object and the object tracking trajectory according to the first sensed data and the second sensed data, and obtains the target object tracking trajectory to which the target object belongs. Based on the above steps, the problem of different objects recognized by different sensors being fused incorrectly is solved, thereby improving the accuracy of the vehicle's autonomous driving planning and control, and improving the user experience.

[0190] The specific implementation methods and corresponding beneficial effects of the above operations can be found in the detailed description of the object matching method above, which will not be elaborated here.

[0191] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by a computer program, or by controlling related hardware through a computer program. The computer program may be stored in a storage medium and loaded and executed by a processor.

[0192] To this end, an embodiment of the present application provides a storage medium in which a computer program is stored, and the computer program can be loaded by a processor to execute the steps in any object matching method provided in the embodiment of the present application. For example, the computer program can execute the following steps:

[0193] Acquire a target object sensed by a sensor and first sensed data corresponding to the target object;

[0194] Acquiring second perception data for generating an object tracking trajectory;

[0195] According to the first perception data and the second perception data, the target object and the object tracking trajectory are matched to obtain the target object tracking trajectory to which the target object belongs.

[0196] It can be seen that the storage medium provided in the embodiment of the present application obtains the target object sensed by the sensor and the first sensed data corresponding to the target object; obtains the second sensed data used to generate the object tracking trajectory; matches the target object and the object tracking trajectory according to the first sensed data and the second sensed data, and obtains the target object tracking trajectory to which the target object belongs. Based on the above steps, the problem of different objects recognized by different sensors being fused incorrectly is solved, thereby improving the accuracy of the vehicle's autonomous driving planning and control, and improving the user experience.

[0197] The specific implementation methods and corresponding beneficial effects of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0198] The storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0199] Since the computer program stored in the storage medium can execute the steps in any object matching method provided in the embodiments of the present application, the beneficial effects that can be achieved by any object matching method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0200] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program includes computer instructions, the computer instructions are stored in a storage medium. A processor of a computer device reads the computer instructions from the storage medium, and the processor executes the computer instructions, so that the computer device performs the above-mentioned object matching method.

[0201] The embodiment of the present application also provides a vehicle, which includes the above-mentioned object matching device, or the above-mentioned electronic device, or the above-mentioned computer program product. The specific structure of the vehicle is not limited in this application. The specific implementation methods and corresponding beneficial effects of the above-mentioned operations of the electronic device are also applicable to the vehicle. For details, please refer to the detailed description of the object matching method above, which will not be repeated here.

[0202] The above is a detailed introduction to an object matching method, device, electronic device, storage medium and vehicle provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. An object matching method, characterized in that: include: Acquire a target object sensed by a sensor and first sensed data corresponding to the target object, wherein the first sensed data includes first position information; Acquire second perception data for generating an object tracking trajectory, wherein a sensor for acquiring the second perception data includes a sensor of a different type from a sensor for acquiring the first perception data, and the second perception data includes second position information; Performing distance calculation according to the first location information and the second location information to obtain an initial distance index value; Determine a correction parameter based on the first perception data, the correction parameter comprising at least one of a speed correction parameter, a distance correction parameter, a frame number correction parameter, and a penalty correction parameter; Based on the correction parameter, the initial distance index value is adjusted to obtain a distance index value between the target object and the object corresponding to the object tracking trajectory, wherein the distance index value is used to indicate a matching degree between the target object and the object corresponding to the object tracking trajectory; Based on the distance index value, the target object and the object tracking trajectory are matched to obtain the target object tracking trajectory to which the target object belongs.

2. The object matching method according to claim 1, characterized in that: The first perception data further includes first identification information, and the second perception data further includes second identification information; and the method further includes: Matching the first identification information and the second identification information to obtain a matching result, wherein the identification information is used to identify a sensor to which corresponding perception data belongs, and the sensor includes a first sensor and a second sensor; If the matching result indicates a first matching result, the steps of performing distance calculation based on the first position information and the second position information to obtain an initial distance index value; determining a correction parameter based on the first perception data; and adjusting the initial distance index value based on the correction parameter to obtain a distance index value between the target object and the object corresponding to the object tracking trajectory.

3. The object matching method according to claim 2, characterized in that: The matching the first identification information and the second identification information to obtain a matching result includes: Matching the first identification information and the second identification information; If the second identification information does not contain the same target identification as the first identification information, the matching result is determined as the first matching result.

4. The object matching method according to claim 3, characterized in that: The second perception data further includes speed information of at least one object corresponding to the object tracking trajectory; if the second identification information does not contain the same target identification as the first identification information, determining the matching result as the first matching result includes: If the target identifier that is the same as the first identifier information does not exist in the second identifier information, speed judgment is performed according to the first speed information of the object corresponding to the identifier in the second identifier information to obtain a speed judgment result; If the speed determination result is that the first speed information is within a preset speed range, the matching result is determined as a first matching result.

5. The object matching method according to claim 2, characterized in that: The matching the first identification information and the second identification information to obtain a matching result includes: Matching the first identification information and the second identification information; If the second identification information contains a target identification that is the same as the first identification information, and the target identification is used to identify the second sensor, the matching result is determined as the first matching result.

6. The object matching method according to claim 5, characterized in that: The second perception data further includes speed information of at least one object corresponding to the object tracking trajectory; if the second identification information contains a target identifier that is the same as the first identification information, and the target identifier is used to identify the second sensor, determining the matching result as the first matching result includes: If the second identification information contains a target identification that is the same as the first identification information, and the target identification is used to identify the second sensor, then speed determination is performed according to second speed information of the object corresponding to the target identification to obtain a speed determination result; If the speed determination result is that the second speed information is within a preset speed range, the matching result is determined as the first matching result.

7. The object matching method according to claim 2, characterized in that: The matching the first identification information and the second identification information to obtain a matching result includes: Matching the first identification information and the second identification information; If the target first identifier in the second identification information is different from the first identification information, and the second identification information also includes a target second identifier, the matching result is determined as a first matching result, wherein the target first identifier is used to identify the first sensor, and the target second identifier is used to identify the second sensor.

8. The object matching method according to claim 7, characterized in that: The second perception data further includes speed information of at least one object corresponding to the object tracking trajectory; if the target first identification in the second identification information is different from the first identification information, and the second identification information further includes the target second identification, determining the matching result as the first matching result, including: If the target first identification in the second identification information is different from the first identification information, and the second identification information also includes the target second identification, then performing speed judgment according to the third speed information of the object corresponding to the target second identification to obtain a speed judgment result; If the speed judgment result is that the third speed information is within a preset speed range, the matching result is determined as the first matching result.

9. The object matching method according to claim 2, characterized in that: After matching the first identification information and the second identification information to obtain a matching result, the method further includes: If the matching result indicates a second matching result, a distance index value between the target object and the object corresponding to the object tracking trajectory is determined according to a preset distance index value.

10. The object matching method according to claim 9, characterized in that: The preset distance index value includes a preset minimum distance index value, and if the matching result indicates a second matching result, determining the distance index value between the target object and the object corresponding to the object tracking trajectory according to the preset distance index value, comprises: If the second identification information contains the same target identification as the first identification information, and the target identification is used to identify the first sensor, a distance index value between the target object and the object corresponding to the object tracking trajectory is determined according to a preset minimum distance index value.

11. The object matching method according to claim 1, characterized in that: The matching process of the target object and the object tracking trajectory based on the distance index value to obtain the target object tracking trajectory to which the target object belongs includes: Filling the distance index value between the target object and each of the object tracking trajectories into corresponding rows and columns of a distance matrix, wherein the columns of the distance matrix are used to indicate the target object, and the rows of the distance matrix are used to indicate the objects corresponding to the object tracking trajectories; An association process is performed based on the filled distance matrix to obtain a target object tracking trajectory to which the target object belongs.

12. The object matching method according to claim 11, characterized in that: The performing association processing based on the filled distance matrix to obtain the target object tracking trajectory to which the target object belongs includes: Perform row and column matching on the distance matrix to obtain the minimum distance index value corresponding to each row and column; The object tracking trajectory corresponding to the row where the minimum distance index value is located is used as the target object tracking trajectory to which the target object corresponding to the column where the minimum distance index value is located belongs.

13. The object matching method according to any one of claims 1 to 12, characterized in that: The step of acquiring first perception data corresponding to the target object includes: Acquire the perception data of the target object perceived by the sensor at the current frame time, and the perception data of the target object perceived by the sensor at the historical frame time, as the first perception data corresponding to the target object.

14. An object matching device, characterized in that: include: A first perception data acquisition unit, configured to acquire a target object perceived by a sensor and first perception data corresponding to the target object, wherein the first perception data includes first position information; a second perception data acquisition unit, configured to acquire second perception data for generating an object tracking trajectory, wherein a sensor for acquiring the second perception data includes a sensor of a different type from a sensor for acquiring the first perception data, and the second perception data includes second position information; A matching unit is used to perform distance calculation according to the first position information and the second position information to obtain an initial distance index value; based on the first perception data, determine a correction parameter, the correction parameter including at least one of a speed correction parameter, a distance correction parameter, a frame number correction parameter, and a penalty correction parameter; based on the correction parameter, adjust the initial distance index value to obtain a distance index value between the target object and the object corresponding to the object tracking trajectory, wherein the distance index value is used to indicate a degree of match between the target object and the object corresponding to the object tracking trajectory; based on the distance index value, match the target object and the object tracking trajectory to obtain a target object tracking trajectory to which the target object belongs.

15. An electronic device, characterized in that: The invention comprises one or more processors and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the object matching method according to any one of claims 1 to 13.

16. A storage medium, characterized in that: The invention comprises a computer program, and when the computer program is run on an electronic device, the computer program is used to make the electronic device execute the steps of the object matching method according to any one of claims 1 to 13.

17. A computer program product, characterized in that The method comprises a computer program or an instruction, which implements the steps of the object matching method according to any one of claims 1 to 13 when the computer program or the instruction is executed by a processor.

18. A vehicle, characterized in that: The vehicle comprises the object matching device according to claim 14 , or the electronic device according to claim 15 , or the computer program product according to claim 17 .

Images