A cross-rod blind area identity binding method and device based on queue information, an electronic device, and a storage medium

Abstract

The application is suitable for the technical field of target detection, and provides a cross-rod blind area identity binding method and device based on queue information, an electronic equipment and a storage medium. The method comprises the following steps: when a sensor at an upstream point detects disappearance of a target, recording a disappearance order of the disappeared target and first target information at the time of disappearance; when a sensor at a downstream point detects appearance of a new target, recording an appearance order of the new target and second target information at the time of appearance; determining a corresponding relationship according to the appearance order of the new target and the disappearance order of the disappeared target, comparing information of the new target and the disappeared target which match in order; if the first target information matches the second target information, determining that the two targets are the same target and performing identity binding. Thus, through order matching and multi-dimensional information verification, the problem of inaccurate target identity association in a cross-sensor blind area scene is effectively solved, and the continuity and robustness of target tracking are improved.

Description

Technical Field

[0001] This application belongs to the field of target detection technology, and in particular relates to a method, device, electronic device, storage medium and computer program product for cross-pole blind zone identity binding based on queue information. Background Technology

[0002] In fields such as intelligent traffic monitoring and personnel and object tracking in large venues, multi-point 3D sensor systems are often used for continuous monitoring of moving targets. Due to limitations in sensor installation location and viewing angle, blind spots often exist between adjacent sensors. When a target enters the blind spot from the upstream sensor's field of view and subsequently reappears in the downstream sensor's field of view, the system struggles to determine whether the two targets are the same. This makes continuous target tracking and accurate analysis difficult, impacting the overall performance and application effectiveness of the monitoring system. Summary of the Invention

[0003] This application provides a method, apparatus, electronic device, storage medium, and computer program product for cross-pole blind zone identity binding based on queue information, which can effectively solve the problem of inaccurate target identity association in cross-sensor blind zone scenarios and improve the continuity and robustness of target tracking.

[0004] In a first aspect, embodiments of this application provide a method for cross-pole blind zone identity binding based on queue information, comprising: when a sensor at an upstream point detects the disappearance of a target, recording the disappearance order of the disappeared target and the first target information when the disappeared target disappears; when a sensor at a downstream point corresponding to the upstream point detects the appearance of a new target, recording the appearance order of the new target and the second target information when the new target appears, wherein the number of new targets is N, and N is an integer greater than or equal to 1; determining the disappearance target corresponding to each new target based on the appearance order of each new target and the disappearance order of each disappeared target, wherein the disappearance order of the disappearance target corresponding to the i-th new target matches the appearance order of the i-th new target, and i is an integer greater than or equal to 1 and less than or equal to N; if the second target information of the i-th new target matches the first target information of the disappearance target corresponding to the i-th new target, determining that the i-th new target and the disappearance target corresponding to the i-th new target are the same target; and binding the identity of the i-th new target to the disappearance target corresponding to the i-th new target.

[0005] In one possible implementation of the first aspect, determining the disappearing target corresponding to each emerging target based on the order of appearance of each emerging target and the order of disappearance of each disappearing target includes: Based on the order in which each newly generated target appears and the order in which each disappears, the disappearing target whose disappearance order is the same as the order in which the i-th newly generated target appears is determined as the disappearing target corresponding to the i-th newly generated target.

[0006] Optionally, in another possible implementation of the first aspect, the first target information includes the first static attribute information of the disappearing target and the first dynamic attribute information when the disappearing target disappears, and the second target information includes the second static attribute information of the newly formed target and the second dynamic attribute information when the newly formed target appears.

[0007] Optionally, in another possible implementation of the first aspect, before determining that the i-th newly generated target and the i-th newly generated target are the same target when the second target information of the i-th newly generated target matches the first target information of the i-th newly generated target's corresponding disappearing target, the method further includes: The static attribute matching degree is determined based on the second static attribute information of the i-th newly formed target and the first static attribute information of the disappearing target corresponding to the i-th newly formed target; The dynamic attribute matching degree is determined based on the second dynamic attribute information of the i-th newly formed target and the first dynamic attribute information of the disappearing target corresponding to the i-th newly formed target; Based on the static attribute matching degree and the dynamic attribute matching degree, determine whether the second target information of the i-th newly generated target matches the first target information of the corresponding disappearing target.

[0008] Optionally, in another possible implementation of the first aspect, the first dynamic attribute information includes at least one of the lane where the disappearing target disappeared, the speed at which it disappeared, the heading angle at which it disappeared, and the disappearance location; and the second dynamic attribute information includes at least one of the lane where the new target appears, the speed at which it appears, the heading angle at which it appears, and the appearance location.

[0009] Optionally, in another possible implementation of the first aspect, determining the dynamic attribute matching degree based on the second dynamic attribute information of the i-th newly formed target and the first dynamic attribute information of the disappearing target corresponding to the i-th newly formed target includes: The lane matching degree is determined based on the lane where the i-th newly emerging target appears and the lane where the corresponding disappearing target disappears. and / or The speed matching degree is determined based on the speed at which the i-th newly formed target appears and the speed at which the corresponding disappearing target disappears. and / or The heading angle matching degree is determined by the heading angle when the i-th newly formed target appears and the heading angle when the corresponding disappearing target disappears. and / or The position matching degree is determined based on the appearance position of the i-th newly formed target and the speed and disappearance position of the disappearing target corresponding to the i-th newly formed target when it disappears; The dynamic attribute matching degree is determined based on at least one of the lane matching degree, speed matching degree, heading angle matching degree, and position matching degree.

[0010] Optionally, in another possible implementation of the first aspect, after determining the disappearing target corresponding to each new target based on the appearance order of each new target and the disappearance order of each disappearing target, the method further includes: If the second target information of the i-th newly generated target does not match the first target information of the i-th newly generated target corresponding to the disappearing target, then the i-th newly generated target and the i-th newly generated target corresponding to the disappearing target are determined to be different targets.

[0011] Secondly, embodiments of this application provide a cross-pole blind zone identity binding device based on queue information, comprising: a first recording module, used to record the disappearance order of the disappeared targets and the first target information when the disappeared targets disappear, when the sensor at the upstream point detects the disappearance of a target; a second recording module, used to record the appearance order of the new targets and the second target information when the sensor at the downstream point corresponding to the upstream point detects the appearance of a new target, wherein the number of new targets is N, and N is an integer greater than or equal to 1; a first determining module, used to determine the disappearance target corresponding to each new target according to the appearance order of each new target and the disappearance order of each disappeared target, wherein the disappearance order of the disappearance target corresponding to the i-th new target matches the appearance order of the i-th new target, and i is an integer greater than or equal to 1 and less than or equal to N; a second determining module, used to determine that the i-th new target and the disappearance target corresponding to the i-th new target are the same target when the second target information of the i-th new target matches the first target information of the disappearance target corresponding to the i-th new target; and an identity binding module, used to bind the identity of the i-th new target to the disappearance target corresponding to the i-th new target.

[0012] In one possible implementation of the second aspect, the first determining module mentioned above includes: The first determining unit is used to determine the disappearing target whose disappearing order is the same as the appearance order of the i-th new target as the disappearing target corresponding to the i-th new target, based on the appearance order of each new target and the disappearing order of each disappearing target.

[0013] Optionally, in another possible implementation of the second aspect, the first target information includes the first static attribute information of the disappearing target and the first dynamic attribute information when the disappearing target disappears, and the second target information includes the second static attribute information of the newly formed target and the second dynamic attribute information when the newly formed target appears.

[0014] Optionally, in another possible implementation of the second aspect, the aforementioned cross-pole blind zone identity binding device based on queue information further includes: The third determining module is used to determine the static attribute matching degree based on the second static attribute information of the i-th newly generated target and the first static attribute information of the disappearing target corresponding to the i-th newly generated target; The fourth determination module is used to determine the dynamic attribute matching degree based on the second dynamic attribute information of the i-th newly formed target and the first dynamic attribute information of the disappearing target corresponding to the i-th newly formed target; The fifth determination module is used to determine whether the second target information of the i-th newly generated target matches the first target information of the corresponding disappearing target based on the static attribute matching degree and the dynamic attribute matching degree.

[0015] Optionally, in another possible implementation of the second aspect, the first dynamic attribute information includes at least one of the lane where the disappearing target disappeared, the speed at which it disappeared, the heading angle at which it disappeared, and the disappearance location, and the second dynamic attribute information includes at least one of the lane where the new target appears, the speed at which it appears, the heading angle at which it appears, and the appearance location.

[0016] Optionally, in another possible implementation of the second aspect, the fourth determining module mentioned above includes: The second determining unit is used to determine the lane matching degree based on the lane where the i-th newly emerging target appears and the lane where the i-th newly emerging target disappears. and / or The third determining unit is used to determine the speed matching degree based on the speed at which the i-th newly emerging target appears and the speed at which the corresponding disappearing target disappears. and / or The fourth determining unit is used to determine the heading angle matching degree based on the heading angle when the i-th newly formed target appears and the heading angle when the i-th newly formed target disappears. and / or The fifth determining unit is used to determine the position matching degree based on the appearance position of the i-th newly formed target and the speed and disappearance position of the disappearing target corresponding to the i-th newly formed target when it disappears; The sixth determining unit is used to determine the dynamic attribute matching degree based on at least one of lane matching degree, speed matching degree, heading angle matching degree and position matching degree.

[0017] Optionally, in another possible implementation of the second aspect, the aforementioned cross-pole blind zone identity binding device based on queue information further includes: The sixth determination module is used to determine that the i-th newly generated target and the i-th newly generated target are different targets when the second target information of the i-th newly generated target does not match the first target information of the i-th newly generated target corresponding to the disappearing target.

[0018] Thirdly, embodiments of this application provide an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the cross-pole blind zone identity binding method based on queue information as described above.

[0019] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program thereon, wherein the computer program, when executed by a processor, implements the cross-pole blind zone identity binding method based on queue information as described above.

[0020] Fifthly, embodiments of this application provide a computer program product that, when run on an electronic device, causes the electronic device to execute the cross-pole blind zone identity binding method based on queue information as described above.

[0021] The beneficial effects of this application's embodiments compared to existing technologies are as follows: When an upstream sensor detects a target disappearing, it records the order of disappearance and the first target information at the time of disappearance; when a downstream sensor detects the appearance of a new target, it records the order of appearance and the multi-dimensional second target information at the time of appearance. Then, it performs a corresponding match based on the order of disappearance and the order of appearance, comparing the first target information and the second target information at the matching position. If they match, they are determined to be the same target and their identities are bound. Therefore, by introducing a sequence constraint and multi-dimensional information fusion matching mechanism, the accuracy of target identity association during blind zone crossing is significantly improved, enhancing the continuity of cross-sensor target tracking and the system's robustness in complex traffic scenarios. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart illustrating a cross-pole blind zone identity binding method based on queue information provided in an embodiment of this application; Figure 2 This is a schematic diagram of the cross-pole blind zone identity binding device based on queue information provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0024] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0025] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0026] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0027] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0028] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0029] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0030] The following description, with reference to the accompanying drawings, details the cross-pole blind zone identity binding method, apparatus, electronic device, storage medium, and computer program based on queue information provided in this application.

[0031] Figure 1 The illustration shows a flowchart of a cross-pole blind zone identity binding method based on queue information provided in an embodiment of this application.

[0032] like Figure 1 As shown, this cross-pole blind zone identity binding method based on queue information includes the following steps: Step 101: If the sensor at the upstream point detects that a target has disappeared, record the order in which the targets disappeared and the information of the first target when the target disappeared.

[0033] The upstream sensors can refer to three-dimensional sensing devices located behind the target's direction of movement within the monitoring area, such as three-dimensional LiDAR, millimeter-wave radar, or depth vision cameras, but are not limited to prediction. Their monitoring area can be referred to as the "upstream field of view."

[0034] Among them, a missing target can refer to a moving target (such as a vehicle or pedestrian) that has been continuously tracked by an upstream sensor, which leaves its monitoring field of view and enters the blind zone between the downstream and upstream sensors, causing the target to no longer be detected in several subsequent frames of data.

[0035] The disappearance order refers to the sequential order in which multiple targets disappear from the upstream field of view. As an example, this order is usually determined based on the timestamp of the last frame in which each target was stably detected.

[0036] The first target information can refer to a set of attributes that the target possesses at the moment of disappearance (or the last valid detection frame before disappearance).

[0037] As an example, the first target information may include first static attribute information and first dynamic attribute information. The first static attribute information may include multi-dimensional information such as the type (e.g., vehicle type), color, and size of the disappearing target, but is not limited to these; the first dynamic attribute information may include multi-dimensional information such as the lane in which the disappearing target disappeared, the speed at which it disappeared, the heading angle at which it disappeared, and the location at which it disappeared, but is not limited to these.

[0038] As one possible implementation, when sensors at upstream locations (such as roadside lidar) detect and track several targets in continuous frame point cloud data, a unique temporary identifier (e.g., ID_1, ID_2) is assigned to each target, and the system monitors in real time whether each target is still within the current field of view. When it is determined that a target has disappeared from the field of view of the upstream sensor, a recording process can be triggered immediately. First, the disappearance order of the disappearing targets can be determined by maintaining a "disappearance queue," adding the disappearing targets sequentially according to their timestamps. For example, if target A disappears before target B, then A's disappearance order is 1, and B's disappearance order is 2. Then, the first target information at the time of disappearance can be extracted and recorded. This can be achieved by extracting multi-dimensional attributes from the last frame or several frames of tracking data before the target's disappearance, thus forming the first target information. This information typically includes: static attribute information such as vehicle type (e.g., sedan, truck) and color identified through point cloud contours or visual features; dynamic attribute information such as the lane where the target was located at the moment of disappearance or the moment before (which can be calculated based on the relative position of the target and the lane line); instantaneous speed (which can be initially estimated from the displacement of the first few frames); heading angle (which can be calculated based on the angle between the target's direction of motion and the lane direction); and disappearance position in the sensor coordinate system.

[0039] Finally, information association and storage are performed, which means that the disappearance order of the disappearing targets and the information of the first target can be bound with the unique identifier of the disappearing target to form a structured disappearance record, which is stored in the cache or database for use in subsequent splicing steps.

[0040] For example, suppose in a highway scenario, an upstream LiDAR detects two lanes (Lane 1 and Lane 2). Two vehicles successively exit its field of view: The first disappearing target (temporary ID: T001): a white sedan traveling in Lane 2. Its last frame of data calculates its speed to be approximately 60 km / h, its heading angle to be 2° (basically straight), and its disappearance position to be (X1, Y1, Z1). This is marked as disappearance sequence 1, and its associated information is recorded. The second disappearing target (temporary ID: T002): a red truck traveling in Lane 1. At the moment of disappearance, the system records its speed to be 55 km / h, its heading angle to be -1°, and its disappearance position to be (X2, Y2, Z2). This is marked as disappearance sequence 2, and its associated information is recorded. At this point, the upstream point's "disappearance queue" stores two records sequentially, providing basic data for subsequent sequential matching and multi-dimensional comparison with newly emerging downstream targets.

[0041] As an example, the conditions for determining "target disappearance" may include: the target outline completely moves out of the sensor's preset monitoring bounding box, or the target is not effectively detected in consecutive frames (such as 3-5 frames) due to occlusion, excessive distance, etc., but are not limited to these.

[0042] It should be noted that the above-listed criteria for determining the disappearance of a target are merely exemplary and should not be considered as limitations on this application. In actual use, appropriate criteria can be set according to needs and specific application scenarios, and this application embodiment does not limit this.

[0043] Step 102: When the sensor at the downstream point corresponding to the upstream point detects the appearance of a new target, record the appearance order of the new target and the information of the second target when the new target appears. The number of new targets is N, where N is an integer greater than or equal to 1.

[0044] The downstream sensor refers to a 3D sensing device located in the monitoring area in front of the target's direction of movement, with a partial blind spot compared to the upstream sensor. Its monitoring area can be called the "downstream field of view," and it can be used to detect targets emerging from the blind spot.

[0045] In this context, "new targets" can refer to moving targets that are detected for the first time within the field of view of the downstream sensor. These targets were not previously tracked by the downstream sensor and typically correspond to targets that have moved out of the upstream blind spot or newly entered the monitoring area.

[0046] The order of appearance can refer to the sequence in which multiple emerging targets are first detected in the downstream field of view. As an example, this order of appearance can be determined based on the timestamp of the first stable detection of each target in the first frame.

[0047] The second target information can refer to a set of attributes possessed by the new target at the moment of its appearance (or at the first effective detection frame).

[0048] As an example, the second target information may include second static attribute information and second dynamic attribute information for comparison with upstream disappearance records. The second static attribute information may include, but is not limited to, multi-dimensional information such as the type (e.g., vehicle type), color, and size of the new target; the second dynamic attribute information may include, but is not limited to, multi-dimensional information such as the lane in which the new target appeared, its speed at the time of appearance, its heading angle at the time of appearance, and its location at the time of appearance.

[0049] Where N represents the total number of new targets identified by the downstream sensor in a certain processing cycle, and is an integer greater than or equal to 1.

[0050] As one possible implementation, downstream sensors continuously scan the monitoring area (e.g., point cloud acquisition by LiDAR). When a new target point cloud cluster is identified in consecutive frames of data, and this target is not recorded in the current tracking list, it can be determined that a new target has appeared, triggering the following recording process: First, a unique temporary identifier is assigned to the new target (e.g., downstream IDs: D001, D002), and its tracking trajectory is initialized. Then, the appearance order is determined by maintaining a "new target queue," adding new targets sequentially according to the timestamp of their first stable detection. For example, if target D001 is detected before D002, then the appearance order of D001 is 1, and the appearance order of D002 is 2. Next, the second target information when the new target appears is extracted and recorded. Multi-dimensional attributes can be extracted from the first frame or the first few frames of stable detection data of the new target to form the second target information. It can usually include: static attribute information such as vehicle type (such as car or truck) and color identified by point cloud contour or visual features; dynamic attribute information such as the lane where it appears at the moment of appearance (which can be calculated based on the relative position of the target and the lane line); instantaneous speed (which can be calculated based on the displacement of consecutive frames); heading angle (which can be calculated based on the angle between the target's direction of movement and the lane direction); and appearance position in the sensor coordinate system.

[0051] Finally, information association storage is performed, which means that the order of appearance and the second target information are bound to the temporary identifier of the new target to form a new record, which is stored in the cache or database for use in subsequent splicing steps.

[0052] For example, continuing the example from the upstream point embodiment, suppose a vehicle leaves the upstream field of view, passes through a blind spot, and reappears in the downstream lidar field of view. The downstream point's sensor first detects a white sedan entering its field of view (system-assigned downstream ID: D001), determines it as a new target, records it as appearance order 1, and extracts its first frame data: lane 2, estimated instantaneous speed of 58 km / h, heading angle of 3°, and appearance location (X1', Y1', Z1'). Subsequently, a red truck enters the downstream field of view (downstream ID: D002), records it as appearance order 2, and extracts its information: lane 1, speed of 53 km / h, heading angle of 0°, and appearance location (X2', Y2', Z2'). At this time, the downstream point's "new target queue" stores two records sequentially. Their appearance order (1, 2) will correspond to the upstream disappearance order (1, 2), and combined with their respective multi-dimensional information (second target information and first target information), subsequent matching and binding judgments will be performed.

[0053] Step 103: Based on the order of appearance of each new target and the order of disappearance of each disappearing target, determine the disappearing target corresponding to each new target. The disappearance order of the disappearing target corresponding to the i-th new target matches the appearance order of the i-th new target, where i is an integer greater than or equal to 1 and less than or equal to N.

[0054] Here, the disappearing target corresponding to the emerging target can refer to an upstream candidate disappearing target found for the i-th downstream emerging target through a sequential matching strategy. Both are considered to be potentially the same physical target. Establishing this correspondence is a prerequisite for subsequent detailed comparison of multi-dimensional information.

[0055] It should be noted that the sequential matching strategy can refer to a strategy that, based on the assumption of the temporal continuity of target movement, associates and maps the disappearing queue of upstream points with the emerging queue of downstream points. Its core is to utilize the physical law of "first to disappear, first to appear" to find the most likely corresponding disappearing target upstream for each emerging downstream target.

[0056] As one possible implementation, based on the order in which each new target appears and the order in which each disappears, the disappearing target whose disappearing order is the same as the order in which the i-th new target appears can be identified as the disappearing target corresponding to the i-th new target.

[0057] As an example, we can obtain the disappearance queue (arranged in disappearance order 1, 2, 3...) corresponding to the upstream points of the record and the new generation queue (arranged in appearance order 1, 2, 3...) corresponding to the downstream points of the record. Then, we can directly align the sorting indices of the two queues, so that the disappearance target with disappearance order i can be directly determined as the disappearance target corresponding to the new generation target with appearance order i.

[0058] For example, continuing the previous example, the disappearance queue corresponding to the upstream point records two targets with a disappearance order of 1 (white sedan, ID: T001) and 2 (red truck, ID: T002), while the new appearance queue corresponding to the downstream point records two new appearance targets with an appearance order of 1 (white sedan, ID: D001) and 2 (red truck, ID: D002). Therefore, the disappearing target T001 can be identified as the disappearing target corresponding to the new appearance target D001, and the disappearing target T002 can be identified as the disappearing target corresponding to the new appearance target D002.

[0059] It should be noted that this sequence-based correspondence establishes the foundation for comparing detailed target information (static and dynamic attributes) of newly created and disappeared targets in subsequent steps. If the sequence matching is accurate and the information comparison is successful, identity binding can be completed efficiently. If the information comparison fails (e.g., vehicle model mismatch), they may be identified as different targets, or a more complex re-matching logic may be triggered.

[0060] Step 104: If the second target information of the i-th newly generated target matches the first target information of the disappearing target corresponding to the i-th newly generated target, determine that the i-th newly generated target and the disappearing target corresponding to the i-th newly generated target are the same target.

[0061] In this embodiment of the application, if the second target information of the i-th newly generated target matches the first target information of the disappearing target corresponding to the i-th newly generated target, it can be said that the information of the i-th newly generated target is very similar to the information of the disappearing target, so that the i-th newly generated target and the disappearing target can be identified as the same target.

[0062] One possible implementation is to determine whether the second target information of the i-th newly generated target matches the first target information of the corresponding disappeared target based on pre-configured matching rules. For example, when both the first and second target information contain multiple attributes, matching rules for each attribute can be configured separately, and the second target information of the i-th newly generated target matches the first target information of the corresponding disappeared target when all attributes in the first and second target information satisfy the corresponding matching rules.

[0063] As one possible implementation, a matching model can be pre-trained to generate a second feature vector corresponding to the second target information of the i-th newly generated target and a first feature vector corresponding to the first target information of the corresponding disappeared target. The first and second feature vectors are then input into the matching model to calculate and output the matching degree between them. When the matching degree between them is greater than or equal to the matching degree threshold, it is determined that the second target information of the i-th newly generated target matches the first target information of the corresponding disappeared target.

[0064] As one possible implementation, when the first target information includes first static attribute information and first dynamic attribute information, and the second target information includes second static attribute information and second dynamic attribute information, the second target information of the newly formed target can be comprehensively evaluated based on both static and dynamic attributes to determine whether it matches the first target information of the corresponding disappeared target. That is, in one possible implementation of this application embodiment, the first target information includes the first static attribute information of the disappeared target and the first dynamic attribute information when the disappeared target disappears; the second target information includes the second static attribute information of the newly formed target and the second dynamic attribute information when the newly formed target appears; correspondingly, before step 104, the following may also be included: The static attribute matching degree is determined based on the second static attribute information of the i-th newly formed target and the first static attribute information of the disappearing target corresponding to the i-th newly formed target; The dynamic attribute matching degree is determined based on the second dynamic attribute information of the i-th newly formed target and the first dynamic attribute information of the disappearing target corresponding to the i-th newly formed target; Based on the static attribute matching degree and the dynamic attribute matching degree, determine whether the second target information of the i-th newly generated target matches the first target information of the corresponding disappearing target.

[0065] As one possible implementation, after determining the static attribute matching degree and dynamic attribute matching degree between the i-th newly generated target and the corresponding disappearing target, the two can be fused to generate a comprehensive matching degree between the i-th newly generated target and the corresponding disappearing target. Then, if the comprehensive matching degree is greater than or equal to the matching degree threshold, it can be determined that the second target information of the i-th newly generated target matches the first target information of the disappearing target corresponding to the i-th newly generated target; otherwise, it can be determined that the second target information of the i-th newly generated target does not match the first target information of the disappearing target corresponding to the i-th newly generated target.

[0066] It should be noted that the overall matching degree can be the sum of the static attribute matching degree and the dynamic attribute matching degree, or it can be the weighted sum of the static attribute matching degree and the dynamic attribute matching degree, etc. This application embodiment does not limit this, and the weights corresponding to the static attribute matching degree and the dynamic attribute matching degree can be determined according to actual needs and specific application scenarios. This application embodiment does not limit this.

[0067] It should be noted that the specific methods for determining the static attribute matching degree and the dynamic attribute matching degree can be the aforementioned rule matching method, or they can be generated by the matching model, or other possible implementation methods, which will not be elaborated here.

[0068] As one possible implementation, the first dynamic attribute information may include at least one of the following: the lane where the disappearing target disappeared, its speed at the time of disappearance, its heading angle at the time of disappearance, and its disappearance location. The second dynamic attribute information may include at least one of the following: the lane where the new target appeared, its speed at the time of appearance, its heading angle at the time of appearance, and its appearance location. Accordingly, the determination of the dynamic attribute matching degree based on the second dynamic attribute information of the i-th new target and the first dynamic attribute information of the disappearing target corresponding to the i-th new target includes: The lane matching degree is determined based on the lane where the i-th newly emerging target appears and the lane where the corresponding disappearing target disappears. and / or The speed matching degree is determined based on the speed at which the i-th newly formed target appears and the speed at which the corresponding disappearing target disappears. and / or The heading angle matching degree is determined by the heading angle when the i-th newly formed target appears and the heading angle when the corresponding disappearing target disappears. and / or The position matching degree is determined based on the appearance position of the i-th newly formed target and the speed and disappearance position of the disappearing target corresponding to the i-th newly formed target when it disappears; The dynamic attribute matching degree is determined based on at least one of the lane matching degree, speed matching degree, heading angle matching degree, and position matching degree.

[0069] As an example, the sum of at least one of lane matching degree, speed matching degree, heading angle matching degree, and position matching degree can be determined as the dynamic attribute matching degree. For instance, if the first dynamic attribute information includes the lane where the disappearing target disappeared, the speed at which it disappeared, the heading angle at which it disappeared, and the disappearance position, and the second dynamic attribute information includes the lane where the new target appeared, the speed at which it appeared, the heading angle at which it appeared, and the appearance position, then the sum of the lane matching degree, speed matching degree, heading angle matching degree, and position matching degree can be determined as the dynamic attribute matching degree.

[0070] As an example, the dynamic attribute matching degree can be determined by the weighted sum of at least one of lane matching degree, speed matching degree, heading angle matching degree, and position matching degree. For instance, when the first dynamic attribute information may include the lane where the disappearing target disappeared, the speed at which it disappeared, the heading angle at which it disappeared, and the disappearance position, and the second dynamic attribute information includes the lane where the new target appeared, the speed at which it appeared, the heading angle at which it appeared, and the appearance position, the dynamic attribute matching degree can be determined by the weighted sum of lane matching degree, speed matching degree, heading angle matching degree, and position matching degree.

[0071] It should be noted that in actual use, the weights corresponding to lane matching degree, speed matching degree, heading angle matching degree and position matching degree can be set according to actual needs and specific application scenarios. This application embodiment does not limit this.

[0072] As an example, lane matching can be determined through rule-based matching. For instance, a lane matching rule could be: 100% matching degree when lanes are the same; 0% matching degree when lanes are different. Alternatively, a lane matching rule could be: 100% matching degree when lanes are the same; 50% matching degree when lanes are adjacent; and 0% matching degree when lanes are not adjacent.

[0073] It should be noted that the above examples are merely illustrative and should not be considered as limitations on this application. In actual use, appropriate lane matching rules can be set according to actual needs and specific application scenarios, and this application embodiment does not limit this.

[0074] As an example, speed matching can be determined through rule-based matching. For instance, a speed matching rule could be: when the absolute value of the speed difference is less than or equal to a first speed threshold (e.g., 5 km / h), the speed matching degree is 100%; when the absolute value of the speed difference is greater than the first speed threshold, the speed matching degree is 0. Alternatively, the speed matching rule could be: when the absolute value of the speed difference is less than or equal to the first speed threshold (e.g., 5 km / h), the speed matching degree is 100%; when the absolute value of the speed difference is greater than the first speed threshold and less than or equal to a second speed threshold (e.g., 10 km / h), the speed matching degree is 80%; when the absolute value of the speed difference is greater than the second speed threshold and less than or equal to a third speed threshold (e.g., 15 km / h), the speed matching degree is 50%, and so on.

[0075] It should be noted that the above examples are merely illustrative and should not be considered as limitations on this application. In actual use, appropriate speed matching rules can be set according to actual needs and specific application scenarios, and the embodiments of this application do not limit this.

[0076] As an example, when determining the heading angle matching degree, it can be determined through rule matching. For instance, the heading angle matching rule could be: when the absolute value of the heading angle error is less than or equal to the first heading angle threshold (e.g., 5°), the heading angle matching degree is 100%; when the absolute value of the heading angle error is greater than the first heading angle threshold, the heading angle matching degree is 0. Alternatively, the heading angle matching rule could also be: when the absolute value of the heading angle error is less than or equal to the first heading angle threshold (e.g., 5°), the heading angle matching degree is 100%; when the absolute value of the heading angle error is greater than the first heading angle threshold and less than or equal to the second heading angle threshold (e.g., 10°), the heading angle matching degree is 80%; when the absolute value of the heading angle error is greater than the second heading angle threshold and less than or equal to the third heading angle threshold (e.g., 15°), the heading angle matching degree is 50%, and so on.

[0077] It should be noted that the above examples are merely illustrative and should not be considered as limitations on this application. In actual use, appropriate heading angle matching rules can be set according to actual needs and specific application scenarios, and the embodiments of this application do not limit this.

[0078] As an example, the predicted appearance position of the disappearing target at the time of appearance of the i-th new target can be calculated based on the speed and position of the disappearing target corresponding to the i-th new target. Then, the position matching degree can be determined based on the distance between the predicted appearance position of the disappearing target and the appearance position of the i-th new target.

[0079] As an example, the location matching degree can be determined through rule matching. For instance, the location matching rule could be: when the distance between the predicted occurrence location and the actual occurrence location is less than or equal to a first distance threshold (e.g., 5 meters), the location matching degree is 100%; when the distance between the predicted occurrence location and the actual occurrence location is greater than the first distance threshold, the location matching degree is 0. Alternatively, the location matching rule could be: when the distance between the predicted occurrence location and the actual occurrence location is less than or equal to the first distance threshold (e.g., 5 meters), the location matching degree is 100%; when the distance between the predicted occurrence location and the actual occurrence location is greater than the first distance threshold but less than or equal to a second distance threshold (e.g., 10 meters), the heading angle matching degree is 80%; when the distance between the predicted occurrence location and the actual occurrence location is greater than the second distance threshold but less than or equal to a third distance threshold (e.g., 15 meters), the location matching degree is 50%, and so on.

[0080] It should be noted that the above examples are merely illustrative and should not be considered as limitations on this application. In actual use, appropriate location matching rules can be set according to actual needs and specific application scenarios, and this application embodiment does not limit this.

[0081] As one possible implementation, if the second target information of the i-th newly generated target does not match the first target information of the i-th newly generated target corresponding to the disappearing target, it can be determined that the i-th newly generated target and the i-th newly generated target corresponding to the disappearing target are different targets.

[0082] As another possible implementation, if the second target information of the i-th newly generated target does not match the first target information of the corresponding disappearing target, the second target information of the i-th newly generated target can be matched with the first target information of all other disappearing targets in the disappearing queue, until a disappearing target matching the i-th newly generated target is determined in the aforementioned manner. If there is no disappearing target matching the i-th newly generated target in the disappearing queue, the i-th newly generated target can be determined as a new target without needing to be bound to any disappearing target.

[0083] Step 105: Bind the identity of the i-th new target to the disappearing target corresponding to the i-th new target.

[0084] In this embodiment of the application, after determining that any one of the newly generated targets and the disappearing targets are the same target, the identity of the newly generated target and the disappearing target can be bound together, so as to realize the identity association of the target during the blind zone crossing process.

[0085] It should be noted that after identifying a newly created target and a disappeared target as the same target and binding their identities, the information of the newly created target can be deleted from the newly created queue, and the information of the disappeared target can be deleted from the disappeared list.

[0086] The cross-pole blind zone identity binding method provided in this application, based on queue information, records the disappearance order and the first target information at the time of disappearance when the upstream sensor detects the disappearance of a target, and records the appearance order and multi-dimensional second target information at the time of appearance when the downstream sensor detects the appearance of a new target. Then, it performs a corresponding match based on the disappearance order and appearance order, comparing the first target information and second target information at the matching position. If they match, they are determined to be the same target and identity binding is performed. Therefore, by introducing a sequence constraint and multi-dimensional information fusion matching mechanism, the accuracy of target identity association during blind zone crossing is significantly improved, enhancing the continuity of cross-sensor target tracking and the robustness of the system in complex traffic scenarios.

[0087] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0088] Corresponding to the cross-pole blind zone identity binding method based on queue information described in the above embodiments, Figure 2 The diagram shows a structural schematic of a cross-pole blind zone identity binding device based on queue information provided in an embodiment of this application. For ease of explanation, only the parts related to the embodiment of this application are shown.

[0089] Reference Figure 2 The cross-pole blind zone identity binding device 20 based on queue information includes: The first recording module 21 is used to record the disappearance sequence of the disappearing targets and the first target information when the disappearing targets disappear, when the sensor at the upstream point detects that a target has disappeared. The second recording module 22 is used to record the order of occurrence of the new target and the information of the second target when the sensor at the downstream point corresponding to the upstream point detects the occurrence of the new target. The number of new targets is N, where N is an integer greater than or equal to 1. The first determining module 23 is used to determine the disappearing target corresponding to each new target according to the appearance order of each new target and the disappearance order of each disappearing target, wherein the disappearance order of the disappearing target corresponding to the i-th new target matches the appearance order of the i-th new target, and i is an integer greater than or equal to 1 and less than or equal to N. The second determining module 24 is used to determine that the i-th newly generated target and the i-th newly generated target are the same target when the second target information of the i-th newly generated target matches the first target information of the i-th newly generated target corresponding to the disappearing target. The identity binding module 25 is used to bind the identity of the i-th new target to the disappearing target corresponding to the i-th new target.

[0090] The cross-pole blind zone identity binding device provided in this application embodiment records the disappearance order and the first target information at the time of disappearance when the upstream sensor detects the disappearance of a target, and records the appearance order and multi-dimensional second target information at the time of appearance when the downstream sensor detects the appearance of a new target. Then, it performs a corresponding match based on the disappearance order and appearance order, and compares the first target information and second target information at the matching position. If they match, they are determined to be the same target and identity binding is performed. Therefore, by introducing a sequence constraint and multi-dimensional information fusion matching mechanism, the accuracy of target identity association during blind zone crossing is significantly improved, enhancing the continuity of cross-sensor target tracking and the robustness of the system in complex traffic scenarios.

[0091] In one possible implementation of this application, the first determining module 23 includes: The first determining unit is used to determine the disappearing target whose disappearing order is the same as the appearance order of the i-th new target as the disappearing target corresponding to the i-th new target, based on the appearance order of each new target and the disappearing order of each disappearing target.

[0092] Furthermore, in another possible implementation of this application, the first target information includes the first static attribute information of the disappearing target and the first dynamic attribute information when the disappearing target disappears, and the second target information includes the second static attribute information of the newly formed target and the second dynamic attribute information when the newly formed target appears.

[0093] Furthermore, in another possible implementation of this application, the aforementioned cross-pole blind zone identity binding device 20 based on queue information further includes: The third determining module is used to determine the static attribute matching degree based on the second static attribute information of the i-th newly generated target and the first static attribute information of the disappearing target corresponding to the i-th newly generated target; The fourth determination module is used to determine the dynamic attribute matching degree based on the second dynamic attribute information of the i-th newly formed target and the first dynamic attribute information of the disappearing target corresponding to the i-th newly formed target; The fifth determination module is used to determine whether the second target information of the i-th newly generated target matches the first target information of the corresponding disappearing target based on the static attribute matching degree and the dynamic attribute matching degree.

[0094] Furthermore, in another possible implementation of this application, the first dynamic attribute information includes at least one of the following: the lane where the disappearing target disappeared, the speed at which it disappeared, the heading angle at which it disappeared, and the disappearance location; and the second dynamic attribute information includes at least one of the following: the lane where the new target appeared, the speed at which it appeared, the heading angle at which it appeared, and the appearance location.

[0095] Furthermore, in yet another possible implementation of this application, the aforementioned fourth determining module includes: The second determining unit is used to determine the lane matching degree based on the lane where the i-th newly emerging target appears and the lane where the i-th newly emerging target disappears. and / or The third determining unit is used to determine the speed matching degree based on the speed at which the i-th newly emerging target appears and the speed at which the corresponding disappearing target disappears. and / or The fourth determining unit is used to determine the heading angle matching degree based on the heading angle when the i-th newly formed target appears and the heading angle when the i-th newly formed target disappears. and / or The fifth determining unit is used to determine the position matching degree based on the appearance position of the i-th newly formed target and the speed and disappearance position of the disappearing target corresponding to the i-th newly formed target when it disappears; The sixth determining unit is used to determine the dynamic attribute matching degree based on at least one of lane matching degree, speed matching degree, heading angle matching degree and position matching degree.

[0096] Furthermore, in another possible implementation of this application, the aforementioned cross-pole blind zone identity binding device 20 based on queue information further includes: The sixth determination module is used to determine that the i-th newly generated target and the i-th newly generated target are different targets when the second target information of the i-th newly generated target does not match the first target information of the i-th newly generated target corresponding to the disappearing target.

[0097] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0098] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0099] To implement the above embodiments, this application also proposes an electronic device.

[0100] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application.

[0101] like Figure 3 As shown, the above-mentioned electronic device 200 includes: The system includes a memory 210 and at least one processor 220, and a bus 230 connecting different components (including the memory 210 and the processor 220). The memory 210 stores a computer program, which, when executed by the processor 220, implements the cross-pole blind zone identity binding method based on queue information as described in the embodiments of this application.

[0102] Bus 230 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0103] Electronic device 200 typically includes a variety of electronic device readable media. These media can be any available media that can be accessed by electronic device 200, including volatile and non-volatile media, removable and non-removable media.

[0104] Memory 210 may also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 240 and / or cache memory 250. Electronic device 200 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 260 may be used to read and write non-removable, non-volatile magnetic media (… Figure 3 Not shown; usually referred to as a "hard drive"). Although Figure 3 As not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 230 via one or more data media interfaces. Memory 210 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.

[0105] A program / utility 280 having a set (at least one) of program modules 270 may be stored in, for example, memory 210. Such program modules 270 include—but are not limited to—an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 270 typically perform the functions and / or methods described in the embodiments of this application.

[0106] Electronic device 200 can also communicate with one or more external devices 290 (e.g., keyboard, pointing device, display 291, etc.), and with one or more devices that enable a user to interact with electronic device 200, and / or with any device that enables electronic device 200 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 292. Furthermore, electronic device 200 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 293. As shown, network adapter 293 communicates with other modules of electronic device 200 via bus 230. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0107] The processor 220 performs various functional applications and data processing by running programs stored in the memory 210.

[0108] It should be noted that the implementation process and technical principles of the electronic device in this embodiment are explained in the foregoing description of the cross-pole blind zone identity binding method based on queue information in this application embodiment, and will not be repeated here.

[0109] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0110] This application provides a computer program product that, when run on an electronic device, enables the electronic device to perform the steps described in the various method embodiments above.

[0111] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a device / electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0112] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0113] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0114] In the embodiments provided in this application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings or direct couplings or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0115] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0116] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for cross-pole blind zone identity binding based on queue information, characterized in that, include: If the sensor at the upstream point detects the disappearance of a target, record the order in which the targets disappear and the information of the first target when the targets disappear; When the sensor at the downstream point corresponding to the upstream point detects the appearance of a new target, the appearance order of the new target and the second target information at the time of the appearance of the new target are recorded, wherein the number of the new targets is N, and N is an integer greater than or equal to 1; Based on the order of appearance of each newly formed target and the order of disappearance of each newly formed target, the disappearance target corresponding to each newly formed target is determined, wherein the disappearance order of the disappearance target corresponding to the i-th newly formed target matches the order of appearance of the i-th newly formed target, and i is an integer greater than or equal to 1 and less than or equal to N; If the second target information of the i-th newly formed target matches the first target information of the disappearing target corresponding to the i-th newly formed target, then the i-th newly formed target and the disappearing target corresponding to the i-th newly formed target are determined to be the same target. Bind the identity of the i-th newly created target to the disappearing target corresponding to the i-th newly created target.

2. The method as described in claim 1, characterized in that, The step of determining the disappearing target corresponding to each newly generated target based on the order of appearance of each newly generated target and the order of disappearance of each disappearing target includes: Based on the order in which each of the newly formed targets appears and the order in which each of the disappearing targets disappears, the disappearing targets whose disappearing order is the same as the order in which the i-th newly formed target appears are determined as the disappearing targets corresponding to the i-th newly formed target.

3. The method as described in claim 1, characterized in that, The first target information includes the first static attribute information of the disappeared target and the first dynamic attribute information when the disappeared target disappears. The second target information includes the second static attribute information of the newly formed target and the second dynamic attribute information when the newly formed target appears.

4. The method as described in claim 3, characterized in that, Before determining that the i-th newly formed target and the i-th newly formed target are the same target when the second target information of the i-th newly formed target matches the first target information of the disappearing target corresponding to the i-th newly formed target, the method further includes: The static attribute matching degree is determined based on the second static attribute information of the i-th newly formed target and the first static attribute information of the disappearing target corresponding to the i-th newly formed target; The dynamic attribute matching degree is determined based on the second dynamic attribute information of the i-th newly formed target and the first dynamic attribute information of the disappearing target corresponding to the i-th newly formed target; Based on the static attribute matching degree and the dynamic attribute matching degree, determine whether the second target information of the i-th newly generated target matches the first target information of the disappearing target corresponding to the i-th newly generated target.

5. The method as described in claim 4, characterized in that, The first dynamic attribute information includes at least one of the following: the lane where the disappearing target disappeared, the speed at which it disappeared, the heading angle at which it disappeared, and the location of the disappearance. The second dynamic attribute information includes at least one of the following: the lane where the new target appeared, the speed at which it appeared, the heading angle at which it appeared, and the location of the appearance.

6. The method as described in claim 5, characterized in that, The step of determining the dynamic attribute matching degree based on the second dynamic attribute information of the i-th newly formed target and the first dynamic attribute information of the disappearing target corresponding to the i-th newly formed target includes: The lane matching degree is determined based on the lane where the i-th newly formed target appears and the lane where the i-th disappearing target disappears. and / or The speed matching degree is determined based on the speed at which the i-th newly formed target appears and the speed at which the corresponding disappearing target disappears. and / or The heading angle matching degree is determined based on the heading angle when the i-th newly formed target appears and the heading angle when the i-th newly formed target disappears. and / or The position matching degree is determined based on the appearance position of the i-th newly formed target and the speed and disappearance position of the disappearing target corresponding to the i-th newly formed target when it disappears; The dynamic attribute matching degree is determined based on at least one of the lane matching degree, the speed matching degree, the heading angle matching degree, and the position matching degree.

7. The method according to any one of claims 1-6, characterized in that, After determining the disappearing target corresponding to each new target based on the appearance order of each new target and the disappearance order of each disappearing target, the method further includes: If the second target information of the i-th newly formed target does not match the first target information of the disappearing target corresponding to the i-th newly formed target, the i-th newly formed target and the disappearing target corresponding to the i-th newly formed target are determined to be different targets.

8. A cross-pole blind zone identity binding device based on queue information, characterized in that, include: The first recording module is used to record the disappearance sequence of the disappearing targets and the first target information when the disappearing targets disappear, when the sensor at the upstream point detects that a target has disappeared. The second recording module is used to record the order of occurrence of the new target and the second target information when the sensor at the downstream point corresponding to the upstream point detects the occurrence of the new target, wherein the number of the new target is N, and N is an integer greater than or equal to 1. The first determining module is used to determine the disappearing target corresponding to each new target according to the appearance order of each new target and the disappearance order of each disappearing target, wherein the disappearance order of the disappearing target corresponding to the i-th new target matches the appearance order of the i-th new target, and i is an integer greater than or equal to 1 and less than or equal to N. The second determining module is used to determine that the i-th newly generated target and the i-th newly generated target are the same target when the second target information of the i-th newly generated target matches the first target information of the disappearing target corresponding to the i-th newly generated target. The identity binding module is used to bind the identity of the i-th newly generated target to the disappearing target corresponding to the i-th newly generated target.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-7.

11. A computer program product, characterized in that, Includes a computer program that, when run on an electronic device, causes the electronic device to perform the method as described in any one of claims 1-7.

Images