Method and apparatus for determining repeated target trajectory, electronic device, and storage medium

Abstract

This invention discloses a method, apparatus, electronic device, and storage medium for determining repeating target trajectories. The method includes: determining at least two sets of target trajectory sets, each set including a baseline target trajectory and at least one candidate target trajectory that satisfies a similarity condition to the baseline target trajectory, wherein first position points of the baseline target trajectories in each set are matched; determining whether a trajectory consistency condition is satisfied between the baseline target trajectory and the candidate target trajectory in each set based on the first position points of the baseline target trajectory and the second position points of the candidate target trajectories; if the trajectory consistency condition is satisfied, then the candidate target trajectory in each set is determined to be a repeating target trajectory corresponding to the baseline target trajectory. This invention can automatically identify repeating target trajectories, improving the accuracy of target trajectory identification.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to a method, apparatus, electronic device, and storage medium for determining a repeating target trajectory. Background Technology

[0002] With the development of computer vision technology, target trajectory detection has become increasingly widely used. For example, it can be used to count the number of targets. However, in scenarios with mirror reflections or live video playback on a screen, false detections of mirrored or screen-based target trajectories can occur, affecting the accuracy of target trajectory detection and increasing detection costs.

[0003] In existing technologies, mirror target trajectories or screen target trajectories that repeat the actual target trajectory are usually removed manually. However, this method is costly and has a certain error rate. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for determining repeating target trajectories, so as to automatically identify repeating target trajectories and improve the accuracy of target trajectory identification.

[0005] In a first aspect, embodiments of the present invention provide a method for determining a repeating target trajectory, the method comprising:

[0006] At least two sets of target trajectories are determined, wherein each set of target trajectories includes a baseline target trajectory and at least one candidate target trajectory that satisfies a similarity condition to the baseline target trajectory, and the first position points of the baseline target trajectories in each set of target trajectories are matched.

[0007] Based on the first position point of the baseline target trajectory and the second position point of the candidate target trajectory in each target trajectory set, determine whether the baseline target trajectory and the candidate target trajectory in each target trajectory set meet the trajectory consistency condition;

[0008] If the baseline target trajectory and candidate target trajectory of each target trajectory set are determined to meet the trajectory consistency condition, then the candidate target trajectory of each target trajectory set is determined to be a duplicate target trajectory corresponding to the baseline target trajectory.

[0009] Secondly, embodiments of the present invention also provide a device for determining a repeating target trajectory, the device comprising:

[0010] The target trajectory set determination module is used to determine at least two sets of target trajectory sets, wherein each target trajectory set includes a baseline target trajectory and at least one candidate target trajectory that satisfies the similarity condition with the baseline target trajectory, and the first position points of the baseline target trajectories in each target trajectory set are matched.

[0011] The trajectory consistency judgment module is used to determine whether the baseline target trajectory and the candidate target trajectory of each target trajectory set meet the trajectory consistency condition based on the first position point of the baseline target trajectory and the second position point of the candidate target trajectory in each target trajectory set.

[0012] The repeating target trajectory determination module is used to determine the candidate target trajectory of each target trajectory set as the repeating target trajectory corresponding to the reference target trajectory if the baseline target trajectory and the candidate target trajectory of each target trajectory set meet the trajectory consistency condition.

[0013] Thirdly, embodiments of the present invention also 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 program to implement the method for determining a repeating target trajectory as described in any of the embodiments of the present invention.

[0014] Fourthly, embodiments of the present invention also provide a storage medium for storing computer-executable instructions, which, when executed by a computer processor, are used to perform the method for determining a repeating target trajectory as described in any of the embodiments of the present invention.

[0015] The technical solution of this invention determines multiple target trajectory combinations. Each target combination includes a baseline target trajectory and candidate target trajectories that satisfy a similarity condition with the baseline target trajectory. The first position points of the baseline target trajectories in different target trajectory combinations are matched. If, based on the first position points of each baseline target trajectory and the second position points of each candidate target trajectory, it is determined that the baseline target trajectory and the candidate target trajectory of each target trajectory set are consistent, then the candidate target trajectory is regarded as a repeated target trajectory corresponding to the baseline target trajectory. The technical solution of this invention realizes the automatic identification of repeated target trajectories, improving the authenticity and accuracy of target trajectory identification.

[0016] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of a method for determining a repeating target trajectory provided in Embodiment 1 of the present invention;

[0019] Figure 2 This is a schematic diagram of a similar candidate target provided in Embodiment 1 of the present invention;

[0020] Figure 3 This is a flowchart of a method for determining a repeating target trajectory provided in Embodiment 2 of the present invention;

[0021] Figure 4 This is a schematic diagram of the structure of a device for determining a repeating target trajectory provided in Embodiment 3 of the present invention;

[0022] Figure 5 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0023] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices. In the embodiments of this application, certain software, components, models, and other existing industry solutions may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solutions of this application, and do not imply that the applicant has already used or necessarily used such solutions.

[0025] The acquisition, transmission, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0026] Example 1

[0027] Figure 1 The flowchart below shows a method for determining a repeating target trajectory according to Embodiment 1 of the present invention. This embodiment is applicable to the identification of repeating target trajectories. The method can be executed by a repeating target trajectory determination device, which can be implemented in hardware and / or software. The repeating target trajectory determination device can be configured in an electronic device and used in conjunction with a shooting device.

[0028] like Figure 1 As shown, the method includes:

[0029] S110. Determine at least two sets of target trajectories.

[0030] Each target trajectory set includes a baseline target trajectory and at least one candidate target trajectory that satisfies the similarity condition with the baseline target trajectory.

[0031] In this set of target trajectories, each target trajectory belongs to the target trajectory corresponding to a similar target. The target can be a moving object such as a human body, face, vehicle, or animal. This embodiment does not limit the type of target. It is understood that when performing target recognition and target trajectory generation based on real-time acquired images, due to factors such as specular reflection or live screen playback, the generated target trajectories may contain both the real target trajectory and target trajectories that overlap with the real target trajectory. Regardless of whether it is specular reflection or live screen playback, the real target trajectory and the target trajectory that overlaps with the real target trajectory correspond to the same target. Therefore, in this embodiment, to identify overlapping target trajectories, the target trajectories corresponding to similar targets can be considered as a set of target trajectories.

[0032] In a set of target trajectories, one target trajectory is selected as the baseline target trajectory, and the other target trajectories are selected as candidate target trajectories. The baseline target trajectory can be selected from those trajectories located closer to the bottom of the image; alternatively, it can be selected from those trajectories with the larger corresponding target area; if the number of target trajectories is greater than or equal to three, the target trajectory located at the center of each target trajectory can also be selected as the baseline target trajectory. This embodiment does not restrict the criteria for selecting the baseline target trajectory.

[0033] The similarity condition between the candidate target trajectory and the baseline target trajectory means that the target corresponding to the candidate target trajectory and the target corresponding to the baseline target trajectory meet the similarity condition, that is, the similarity between the target corresponding to the candidate target trajectory and the target corresponding to the baseline target trajectory is greater than or equal to the preset similarity threshold.

[0034] In this embodiment, based on multiple sets of baseline target trajectories and their corresponding candidate target trajectories, a comprehensive judgment is made on whether there is trajectory consistency between the baseline target trajectory and the candidate target trajectory, thereby determining whether there is a problem of target trajectory duplication in the current shooting scene.

[0035] Furthermore, S110 may include:

[0036] A1. If it is determined that there are at least two candidate targets that meet the similarity condition, then determine the trajectory of each candidate target;

[0037] A2. The candidate target trajectory that meets the preset position conditions is taken as the reference target trajectory, and the reference target trajectory and other candidate target trajectories other than the reference target trajectory are taken as a set of target trajectories.

[0038] The similarity condition is met when the similarity between at least two candidate targets is greater than or equal to a preset similarity threshold. In this embodiment, target recognition is performed on the captured image or video frame image obtained by the shooting device to obtain multiple target regions. The similarity between the target regions is calculated, and the target regions with a similarity greater than or equal to the preset similarity threshold are selected as candidate targets. For example, if the target is a human body, human target recognition is performed on the captured image or video frame image to obtain multiple human target regions, and the similarity between the human target regions is calculated. Furthermore, if the completeness of different human target regions is different, the face region in each human target region can be extracted separately for similarity calculation and comparison. This embodiment does not impose any limitations on this.

[0039] Figure 2 A schematic diagram of similar candidate targets is provided, such as... Figure 2 As shown, the coordinates of the two similar candidate targets in the image are (L1, W1) and (L2, W2), respectively. The coordinates of the candidate targets can be represented by the coordinates of the center point of the target region of the candidate targets. When the target is a human body, it can also be represented by the coordinates of the center point of the face region. This embodiment does not restrict the selection method of the candidate targets' position points.

[0040] After identifying at least two similar candidate targets, the candidate target trajectory is determined based on the coordinates of the similar candidate targets' locations in multiple images. It is understandable that mirrors or screens typically do not occupy the entire frame of the camera; therefore, the candidate target trajectory may be less than or equal to the complete trajectory of the candidate target within the camera's frame.

[0041] After determining the candidate target trajectories for each candidate target, a baseline target trajectory is selected from these candidate trajectories. The purpose of selecting the baseline target trajectory is to use it as the true target trajectory among multiple candidate target trajectories for similar targets, thereby facilitating subsequent trajectory consistency judgment based on multiple sets of baseline and candidate target trajectories.

[0042] Meeting the preset position condition can mean that the candidate target is closer to the bottom of the shooting screen of the shooting device in the candidate target trajectory of each candidate target; when the number of candidate target trajectories is greater than or equal to three, meeting the preset position condition can also mean that the position is located in the center or middle area of ​​each candidate target trajectory. This embodiment does not limit the specific content of the preset position condition.

[0043] In an optional embodiment, since the main causes of target trajectory repetition include specular reflection and live screen playback, and based on symmetrical reflection relationships and screen positioning, the position of the repeating target in the captured image of the shooting device is usually higher than the actual position of the target. Therefore, the candidate target trajectory whose position coordinates are closer to the bottom of the captured image can be used as the reference target trajectory.

[0044] In this embodiment, the coordinates of each first position point of the baseline target trajectory and the coordinates of each second position point of the candidate target trajectory in a set of target trajectories are saved. Table 1 provides a record table of the coordinates of the first position points of the baseline target trajectory and the second position points of the candidate target trajectories in a set of target trajectories:

[0045] Table 1

[0046] (L11, W11) (L21, W21) (L12, W12) (L22, W22) … … (L1n, W1n) (L2n, W2n)

[0047] In this context, the first column POS1 represents the coordinates of each first position point on the baseline target trajectory, and the second column POS2 represents the coordinates of each second position point on the candidate target trajectory. (L1n, W1n) represents the coordinates of the nth first position point on the baseline target trajectory, and (L2n, W2n) represents the coordinates of the nth second position point on the candidate target trajectory.

[0048] It should be noted that when there are two or more candidate target trajectories, a corresponding column can be added to the record table, as shown in Table 2 below. This embodiment does not impose any restrictions on this.

[0049] Table 2

[0050] (L11, W11) (L21, W21) (L31, W31) (L12, W12) (L22, W22) (L32, W32) … … … (L1n, W1n) (L2n, W2n) (L3n, W3n)

[0051] S120. Based on the first position point of the baseline target trajectory and the second position point of the candidate target trajectory in each target trajectory set, determine whether the baseline target trajectory and the candidate target trajectory in each target trajectory set meet the trajectory consistency condition.

[0052] Among them, satisfying the trajectory consistency condition means that, considering the baseline target trajectory and the candidate target trajectory of each target trajectory set, the overall trend shows a high degree of consistency between the baseline target trajectory and its corresponding candidate target trajectory.

[0053] In an optional embodiment, to determine whether the baseline target trajectory and the candidate target trajectory of each target trajectory set meet the trajectory consistency condition, a vector can be constructed for the baseline target trajectory and the candidate target trajectory in a target trajectory set, with the first position point on the baseline target trajectory pointing to the second position point on the corresponding candidate target trajectory.

[0054] Based on the direction and magnitude of the vectors corresponding to each first position point on the baseline target trajectory, it is determined whether the baseline target trajectory and the candidate target trajectory in the target trajectory set meet the trajectory consistency condition. Specifically, the average angle can be calculated based on the angle of each vector's direction, and the vector angle range can be determined based on the average angle. The average vector magnitude can be calculated based on the average vector magnitude, and the vector magnitude range can be determined based on the average vector magnitude. If the ratio of the number of vectors whose angles are within the vector angle range to the total number of vectors is greater than or equal to a preset first ratio threshold, and / or the ratio of the number of vectors whose magnitudes are within the vector magnitude range to the total number of vectors is greater than or equal to a preset second ratio threshold, then it is determined whether the baseline target trajectory and the candidate target trajectory in the target trajectory set meet the trajectory consistency condition.

[0055] If it is determined that the number of target trajectory sets that meet the trajectory consistency condition is greater than or equal to a preset number threshold, or the ratio of the number of target trajectory sets that meet the trajectory consistency condition to the total number of target trajectory sets is greater than or equal to a preset proportion threshold, then it is determined that the baseline target trajectory and the candidate target trajectory of each target trajectory set meet the trajectory consistency condition.

[0056] In another optional embodiment, determining whether the baseline target trajectory and candidate target trajectory of each target trajectory set satisfy the trajectory consistency condition can be achieved by constructing a first vector for the baseline target trajectory and candidate target trajectory in a target trajectory set, pointing from the previous first position point on the baseline target trajectory to the adjacent next first position point; and constructing a second vector by pointing from the previous second position point on the candidate target trajectory to the adjacent next second position point. For example, if the baseline target trajectory includes 10 first position points and the candidate target trajectory includes 10 second position points, then a total of 9 first vectors and 9 second vectors can be obtained.

[0057] Based on the direction and magnitude of the first vector and its corresponding second vector, it is determined whether the baseline target trajectory and candidate target trajectory in the target trajectory set meet the trajectory consistency condition. Specifically, it is determined whether the angle between the direction of each first vector and the direction of its corresponding second vector is less than or equal to a preset angle threshold; the ratio of the magnitude of each first vector to its corresponding second vector is calculated, and the range of vector magnitude ratios is determined based on the magnitude ratios of each vector. If the ratio of the number of first vectors that meet the above angle condition to the total number of vectors is greater than or equal to a preset first ratio threshold, or if the ratio of the number of first vectors whose vector magnitude ratio is within the range of vector magnitude ratios to the total number of vectors is greater than or equal to a preset second ratio threshold, then it is determined whether the baseline target trajectory and candidate target trajectory in the target trajectory set meet the trajectory consistency condition.

[0058] Similarly, if it is determined that the number of target trajectory sets that meet the trajectory consistency condition is greater than or equal to a preset number threshold, or the ratio of the number of target trajectory sets that meet the trajectory consistency condition to the total number of target trajectory sets is greater than or equal to a preset proportion threshold, then it is determined that the baseline target trajectory and the candidate target trajectory of each target trajectory set meet the trajectory consistency condition.

[0059] In another optional embodiment, to determine whether the baseline target trajectory and candidate target trajectory of each target trajectory set meet the trajectory consistency condition, the first position point of the baseline target trajectory and the second position point of the candidate target trajectory in the first acquired target trajectory set can be recorded. When a new target trajectory set is acquired again, based on the first position point of the new baseline target trajectory, a matching recorded first position point is determined from the recorded first position points of the baseline target trajectory, that is, a recorded first position point that meets the preset distance condition, and the corresponding recorded second position point is determined. If there is no recorded first position point that meets the preset distance condition, the first position point of the new baseline target trajectory and the second position point of its corresponding candidate target trajectory are recorded. The preset distance condition is compared between the second position point of the new candidate target trajectory and the recorded second position point. If it is, the statistical count corresponding to the recorded first position point is incremented by one. When a new target trajectory set is acquired again, the above process is repeated. If the statistical count corresponding to a recorded first position point is greater than or equal to a preset statistical count threshold, the recorded first position point is determined to be a duplicate first position point. If the number of repeated first position points is greater than or equal to a preset threshold, then the baseline target trajectory and candidate target trajectory of each target trajectory set are determined to meet the trajectory consistency condition.

[0060] In this embodiment, based on the first position point on the multiple sets of reference target trajectories and the second position point on their corresponding candidate target trajectories, it is determined whether the multiple sets of reference target trajectories and candidate target trajectories have trajectory consistency, thereby determining whether there is target trajectory duplication caused by mirror reflection or live screen playback.

[0061] Furthermore, S120 may include: determining whether the baseline target trajectory and the candidate target trajectory of each target trajectory set meet the trajectory consistency condition based on the first position point of the baseline target trajectory, the second position point of the candidate target trajectory, the target size matching the first position point of the baseline target trajectory, and the target size matching the second position point of the candidate target trajectory in each target trajectory set.

[0062] The target size can be the length and / or width of the target region. In this embodiment, if the integrity of the target region corresponding to the first position point and the integrity of the target region corresponding to the second position point are both greater than or equal to the integrity threshold, then the target size matching the first position point of the baseline target trajectory and the target size matching the second position point of the candidate target trajectory are determined respectively. The consistency of the trajectory is then assessed by combining the target sizes of each position point.

[0063] Understandably, when the baseline target trajectory is the true target trajectory and the candidate target trajectory is a duplicate target trajectory caused by specular reflection or live screen playback, the target size at the first position point is the true target size, and the target size at the second position point is the duplicate target size. When different targets pass through the same position in the image captured by the shooting device, the ratio of the true target size to the duplicate target size should remain consistent. Therefore, in this embodiment, combining position point consistency and target size ratio consistency to judge trajectory consistency can improve the accuracy of trajectory consistency judgment. Furthermore, adding target size ratio consistency to assist in trajectory consistency judgment can also distinguish whether the candidate target trajectory is a duplicate target trajectory caused by specular reflection or live screen playback, or a true target trajectory adjacent to the baseline target trajectory. This avoids interference from the simultaneous movement of adjacent true targets on trajectory consistency judgment and improves the accuracy of duplicate trajectory identification.

[0064] S130. If the baseline target trajectory and candidate target trajectory of each target trajectory set meet the trajectory consistency condition, then the candidate target trajectory of each target trajectory set is determined to be a duplicate target trajectory corresponding to the baseline target trajectory.

[0065] In this embodiment, when the baseline target trajectory and the candidate target trajectory of each target trajectory set meet the trajectory consistency condition, that is, when the baseline target trajectory and the candidate target trajectory of each target trajectory set show a high degree of consistency, the baseline target trajectory is taken as the real target trajectory and the candidate target trajectory is taken as the repeated target trajectory.

[0066] The technical solution of this embodiment can identify repeating target trajectories for similar targets, ensuring the accuracy of target trajectory identification.

[0067] Furthermore, after identifying candidate target trajectories as duplicate target trajectories, each candidate target trajectories are deleted. In a specific application scenario, if the generated target trajectories are used for target quantity counting, then the identification and deletion of duplicate trajectories in this embodiment can improve the accuracy of target quantity counting. In another specific application scenario, if the generated target trajectories are used to assist in determining the size of the area to be identified in the image captured by the shooting device, for example, when the target is a human body, the size of the walkable area in the image can be determined by the human body's trajectory in the image. In this embodiment, the identification and deletion of duplicate trajectories can improve the accuracy of determining the area to be identified.

[0068] Furthermore, following S130, it can also include:

[0069] B1. Determine the repeating area based on the trajectory of each repeating target;

[0070] B2. The target trajectory within the repeated region in the obtained current image is taken as the repeated target trajectory.

[0071] The repeated regions can be obtained by taking the minimum bounding rectangle of the second position point of each repeated target trajectory.

[0072] In this embodiment, after determining that the candidate target trajectory is a repeating target trajectory, the region where the repeating target trajectory is distributed is defined as the mirror area or screen area that causes the target trajectory to repeat, and this area is designated as the repeating region. For new targets identified within the repeating region, their trajectories are directly designated as repeating target trajectories.

[0073] Furthermore, a monitoring period can be preset, and the consistency of target trajectory combinations within the monitoring period prior to the current time can be judged. After identifying overlapping areas, as new target trajectory combinations are obtained, the consistency between the baseline target trajectory and candidate target trajectories of each target trajectory set is continuously monitored. If, based on the real-time obtained target trajectory combinations, it is determined that the baseline target trajectory and candidate target trajectories of each target trajectory set no longer meet the trajectory consistency requirement, then the overlapping area in the captured image's frame is removed. This setting allows for dynamic adjustment of overlapping areas, achieving a dynamic adaptation to the scene.

[0074] The technical solution of this invention determines multiple target trajectory combinations. Each target combination includes a baseline target trajectory and candidate target trajectories that satisfy a similarity condition with the baseline target trajectory. The first position points of the baseline target trajectories in different target trajectory combinations are matched. If, based on the first position points of each baseline target trajectory and the second position points of each candidate target trajectory, it is determined that the baseline target trajectory and the candidate target trajectory of each target trajectory set are consistent, then the candidate target trajectory is regarded as a repeated target trajectory corresponding to the baseline target trajectory. The technical solution of this invention realizes the automatic identification of repeated target trajectories, improving the authenticity and accuracy of target trajectory identification.

[0075] Example 2

[0076] Figure 3 This is a flowchart of a method for determining a repeating target trajectory according to Embodiment 2 of the present invention. Based on the above embodiments, the present invention further specifies the specific process of determining whether the baseline target trajectory and the candidate target trajectory of each target trajectory set meet the trajectory consistency condition.

[0077] like Figure 3 As shown, the method includes:

[0078] S210. Determine at least two sets of target trajectories.

[0079] The method for determining the target trajectory combination has been described in the above embodiments, and will not be repeated here.

[0080] S220. Determine at least two reference target trajectories for a first position point to be processed, and in the candidate target trajectories corresponding to the reference target trajectories, determine a second position point to be processed that corresponds to the first position point to be processed at the same time.

[0081] Among them, the first position points to be processed in each benchmark target trajectory meet the preset distance conditions.

[0082] Here, the first position point to be processed refers to the first position point currently being processed on the baseline target trajectory, and the first position points to be processed on different baseline target trajectories meet a preset distance condition. Figure 2 For example, if the coordinates of the first position point a on the reference target trajectory A are (L11, W11) and the coordinates of the first position point b on the reference target trajectory B are (L11', W11'), and the distance between the first position point a and the first position point b is less than or equal to a preset distance threshold, that is, the preset distance condition is met, then the first position point a and the first position point b are taken as the first position points to be processed.

[0083] It should be noted that because different targets may move at different speeds within the field of view of the shooting device, the number of first position points in the baseline target trajectory of different target trajectory sets may be different, and the order of the first position points to be processed in different baseline target trajectories may also be different among all the first position points of that baseline target trajectory. For example, baseline target trajectory A corresponds to 15 first position points, and the order of first position point a is the 1st position point. Baseline target trajectory B corresponds to 10 first position points, and the order of first position point b is the 2nd position point.

[0084] Taking the first position point to be processed as position point a as an example, the process of determining the second position point to be processed is explained. Candidate target trajectories A' belonging to the same target trajectory set as the baseline target trajectory A are determined. Among the second position points of candidate target trajectories A', the second position point a' corresponding to the first position point a at the same time is determined as the second position point to be processed. The first position point a and the second position point a' are located in the same image captured by the imaging device.

[0085] In an optional embodiment, whether the first position points meet the preset distance condition can be determined by using the first position point to be processed of the earliest acquired benchmark target trajectory as the reference for distance comparison. Specifically, each first position point of the benchmark target trajectory and each second position point of the candidate target trajectory in the initially acquired target trajectory set are recorded. When a new target trajectory set is acquired again, the distance between a certain first position point of the new benchmark target trajectory and each of the recorded first position points of the benchmark target trajectory is calculated. If the first position point and a certain recorded first position point meet the preset distance condition, then the first position point and the recorded first position point are used as the first position points to be processed.

[0086] It should be noted that if the first position point meets the preset distance condition with at least two recorded first position points, the closest recorded first position point is selected. However, if at least two first position points on the same reference target trajectory meet the preset distance condition with the same recorded first position point, then both of these first position points on the same reference target trajectory and the recorded first position point can be used as first position points to be processed. For example, if the reference target trajectory and candidate target trajectory in the first target trajectory set each include 10 first position points, and the reference target trajectory in the second target trajectory set includes 15 first position points, and the first and second first position points in the second reference target trajectory both meet the preset distance condition with the first position point in the first reference target trajectory, then the first position point in the first reference target trajectory and the first and second first position points in the second reference target trajectory can both be used as first position points to be processed for subsequent processing.

[0087] In another optional embodiment, whether the first position points meet the preset distance condition can be determined by using the first position points as the distance comparison benchmark for the two earliest acquired benchmark target trajectories, and using the centroid of the combination of first position points as the distance comparison benchmark for subsequent acquired benchmark target trajectories. Specifically, each first position point of the benchmark target trajectory and each second position point of the candidate target trajectory in the first acquired target trajectory set are recorded. When acquiring the second target trajectory set, the distance between a certain first position point of the second benchmark target trajectory and each first position point of the first benchmark target trajectory is calculated. If the first position point of the second benchmark target trajectory and a certain first position point of the first benchmark target trajectory meet the preset distance condition, then the first position point of the second benchmark target trajectory and the first position point of the first benchmark target trajectory are combined into a first position point combination. For a new target trajectory set acquired subsequently, the distance between the first position point of the new benchmark target trajectory and the centroid of the first position point combination is calculated. If the distance between a certain first position point of the new benchmark target trajectory and the centroid of the first position point combination meets the preset distance condition, then the first position point on the new benchmark target trajectory is added to the first position point combination, and both are treated as first position points to be processed.

[0088] In this embodiment, for each first location point to be processed that meets the preset distance condition, if its corresponding second location point to be processed also largely overlaps, it means that for most of the targets passing through the points corresponding to the first location points to be processed in the captured image, there is a similar target at the point corresponding to the second location point to be processed. At this time, the point can be identified as a valid duplicate location point.

[0089] S230. Determine the size ratio based on the target size matching the first position point to be processed and the target size matching the second position point to be processed.

[0090] This embodiment uses the example of combining the target size at each location point to assist in judging trajectory consistency. Figure 2 For example, if the target size of the first position point a at coordinates (L11, W11) is H1, and the target size of the second position point a' at coordinates (L21, W21) is H2, then the size ratio is H1 / H2.

[0091] It should be noted that if there are two or more candidate target trajectories, then the size ratio of each candidate target trajectory should be determined separately. For example, if Figure 2 There is also a second position point a” at coordinates (L31, W31), and the target size is H3, so the size ratio is H1 / H3.

[0092] S240. Based on each second position point to be processed and each size ratio, determine whether the first position point to be processed meets the position point consistency condition.

[0093] Among them, the condition that the first position point to be processed meets the position point consistency condition means that the position corresponding to the first position point to be processed in the captured image is highly consistent with the position corresponding to the second position point to be processed, and the second position point to be processed corresponding to the first position point to be processed is a valid duplicate position point.

[0094] In this embodiment, for each first location point to be processed that meets the preset distance condition, the corresponding second location point to be processed and its corresponding size ratio are combined to comprehensively determine whether the second location point to be processed corresponding to the first location point to be processed is a valid duplicate location point. For each first location point to be processed that meets the preset distance condition, if its corresponding second location point to be processed also largely overlaps, and its corresponding size ratio is also roughly the same, it means that for most targets passing through the points corresponding to the first location points to be processed in the captured image, there is a similar target at the point corresponding to the second location point to be processed, and the size ratio of the target at each point corresponding to the first location point to be processed in the captured image is roughly the same as that of the similar target. At this time, the point can be identified as a valid duplicate location point.

[0095] Furthermore, S240 may include:

[0096] C1. Determine the first number of second position points to be processed that meet the preset distance conditions and whose corresponding size ratios meet the preset ratio conditions.

[0097] C2. Determine the second number of second position points to be processed that meet the preset distance conditions but whose corresponding size ratios do not meet the preset ratio conditions.

[0098] C3. Determine the third number of second location points to be processed that do not meet the preset distance conditions;

[0099] C4. If the difference between the first quantity and the third quantity is greater than or equal to the preset first difference threshold, or the difference between the first quantity and the third quantity is less than the preset first difference threshold, and the difference between the second quantity and the third quantity is greater than or equal to the preset second difference threshold, then the first position point to be processed is determined to meet the position point consistency condition.

[0100] Whether the preset distance condition is met between the second position points to be processed can be determined by using the earliest acquired second position point as the distance comparison benchmark; alternatively, for the two earliest acquired second position points, the distance comparison benchmark can be used, and for subsequent acquired second position points, the centroid of the combination of the two acquired second position points can be used as the distance comparison benchmark. This embodiment will not elaborate on the specific process. Similarly, whether the preset ratio condition is met between size ratios refers to whether the difference between size ratios is less than or equal to a preset ratio threshold. This can be determined by using the earliest acquired size ratio as the size ratio comparison benchmark; alternatively, for the two earliest acquired size ratios, the size ratio can be used as the size ratio comparison benchmark, and for subsequent acquired size ratios, the average value of the combination of size ratios can be used as the size ratio comparison benchmark. This embodiment will not elaborate on the specific process.

[0101] In this embodiment, for a pair of first position points to be processed that meet a preset distance condition, if their corresponding second position points to be processed also meet the preset distance condition and their size ratio meets the preset ratio condition, it indicates that when two different targets pass through the point corresponding to the first position point to be processed, there is a similar target at the point corresponding to the second position point to be processed, and the size ratio between the similar target and the target is also consistent. At this time, the probability of specular reflection or live screen playback at the point corresponding to the second position point to be processed increases, and the probability that the point corresponding to the second position point to be processed is a duplicate position point increases.

[0102] For a pair of first location points that meet preset distance conditions, if their corresponding second location points also meet preset distance conditions but their size ratios do not meet preset ratio conditions, it indicates that when two different targets pass through the location corresponding to the first location point, a similar target exists at the location corresponding to the second location point, but the size ratio between the similar target and the first location point is inconsistent. In this case, it could be due to mirror reflection or live screen playback at the location corresponding to the second location point, or it could be due to two similar targets passing side by side. This does not necessarily increase the probability that the location corresponding to the second location point is a duplicate location point. Therefore, this situation can be recorded. If this situation occurs frequently, it can also be considered that the location corresponding to the second location point is a duplicate location point.

[0103] For a pair of first location points that satisfy the preset distance condition, if their corresponding second location points do not satisfy the preset distance condition, it means that when two different targets pass through the points corresponding to the first location points, the points corresponding to their similar targets are different, possibly indicating that the two similar targets simply pass by side by side. In this case, the probability that the point corresponding to the second location point is a duplicate location point decreases.

[0104] Therefore, in this embodiment, if the difference between the first quantity and the third quantity is greater than or equal to a preset first difference threshold, it indicates that the probability of specular reflection or live screen playback at the point corresponding to the second position point to be processed is relatively high, and the point corresponding to the second position point to be processed is a valid repeated position point. Alternatively, if the difference between the first quantity and the third quantity is less than the first difference threshold, but the difference between the second quantity and the third quantity is greater than or equal to a preset second difference threshold, it can also be considered that the probability of specular reflection or live screen playback at the point corresponding to the second position point to be processed is relatively high, and the point corresponding to the second position point to be processed is a valid repeated position point.

[0105] In this embodiment, by determining whether the second position point to be processed corresponding to the first position point to be processed that meets the preset distance condition also meets the preset distance condition, and whether the corresponding size ratio meets the size ratio condition, the high consistency between the position of the first position point to be processed and the position of the second position point to be processed is quantitatively represented, and it is possible to accurately determine whether the position of the second position point to be processed is a valid duplicate position point.

[0106] Furthermore, following C3, it also includes: if the difference between the second quantity and the third quantity is determined to be less than or equal to a preset third difference threshold, then delete each set of target trajectories.

[0107] The third difference threshold can be set to 0. In this embodiment, since the second quantity represents the number of second location points to be processed that also meet the preset distance condition but whose size ratio does not meet the preset ratio condition, and the third quantity represents the number of second location points to be processed that do not meet the preset distance condition, when the difference between the second quantity and the third quantity is 0, it can be considered that the point corresponding to the second location point to be processed is less likely to be a duplicate location point, and each set of target trajectories can be deleted.

[0108] S250. If the number of first position points that meet the position point consistency condition is greater than or equal to a preset number threshold, then the baseline target trajectory and candidate target trajectory of each target trajectory set meet the trajectory consistency condition.

[0109] In this embodiment, if the number of valid repeating location points exceeds the number threshold, it indicates that there is a high degree of consistency between the baseline target trajectory and the candidate target trajectory, and the candidate target trajectory can be identified as a repeating target trajectory.

[0110] S260. If the baseline target trajectory and candidate target trajectory of each target trajectory set meet the trajectory consistency condition, then the candidate target trajectory of each target trajectory set is determined to be a duplicate target trajectory corresponding to the baseline target trajectory.

[0111] S270. Determine the repeating area based on the trajectory of each repeating target.

[0112] In this embodiment, the identification of duplicate target trajectories corresponding to similar targets is performed continuously and dynamically. The identified duplicate target trajectories can be directly deleted. Alternatively, a duplicate region can be constructed based on the duplicate target trajectories. When processing subsequent images, the target trajectories within the duplicate region are no longer judged as duplicate target trajectories, and all target trajectories within the duplicate region are directly identified as duplicate target trajectories. Alternatively, a duplicate region can be constructed based on the duplicate target trajectories. When processing subsequent images, the target identification within the duplicate region is no longer performed. This embodiment does not impose any restrictions on this approach.

[0113] S280. The target trajectory within the repeated region in the obtained current image is taken as the repeated target trajectory.

[0114] In this embodiment, for the real-time acquired target trajectory combination, a first position point to be processed for the baseline target trajectory that meets the preset distance condition is determined, and a second position point to be processed at the same moment on the corresponding candidate target trajectory is determined, and the size ratio is calculated. Based on the second position point to be processed and the size ratio, it is determined whether there is a high degree of consistency between the first position point to be processed and the second position point to be processed. Based on the number of first position points with high consistency, it is determined whether there is a high degree of consistency between the baseline target trajectory and the candidate target trajectory. This embodiment can automatically adapt to scene changes and eliminate abnormal position points by utilizing the consistency between position points and target size ratios, and effectively and accurately identify duplicate target trajectories. This embodiment can be applied to the target quantity statistics in large scenes or the target quantity statistics in the entry and exit directions of small scenes. By identifying duplicate target trajectories, the accuracy of target quantity statistics can be improved, and the problem of inaccurate target quantity statistics caused by mirror interference or live screen playback can be eliminated.

[0115] In a specific application scenario, this embodiment provides an example of a process for recognizing repeating target trajectories: The captured image is monitored in real time using a camera, target recognition is performed on the captured image, and similarity comparisons are made between the identified targets to obtain similar targets. The location points and dimensions of the similar targets are determined, and similar target trajectories are obtained based on the location points of similar targets in consecutive images. The similar target trajectory closest to the bottom of the captured image is selected as the baseline target trajectory, and other similar target trajectories are selected as candidate target trajectories. At this point, the first location points of the baseline target trajectory, the second location points of the candidate target trajectories, and the corresponding target size ratios at each location point are obtained, and the coordinates and target size ratios of each location point are recorded.

[0116] When a similar target is detected again in the captured image, the same steps described above are followed to obtain the first position points of the new baseline target trajectory, the second position points of the new candidate target trajectory, and the target size ratio corresponding to each position point. The distances between the first position points of the new baseline target trajectory and the previously recorded first position points are compared. If the distance between a certain first position point of the new baseline target trajectory and a previously recorded first position point is less than or equal to a preset distance threshold, then the second position point corresponding to that first position point at the same time, the previously recorded second position point corresponding to the previously recorded first position point at the same time, and the previously recorded target size corresponding to the previously recorded first position point are determined.

[0117] If the distance between the new second location point and the recorded second location point is also less than or equal to the preset distance threshold, and the difference between the new target size ratio and the recorded target size ratio is less than or equal to the preset target size ratio difference threshold, then the NUM1 value is incremented by one (the initial value of NUM1 is set to 0).

[0118] If the distance between the new second location point and the recorded second location point is also less than or equal to the preset distance threshold, but the difference between the new target size ratio and the recorded target ratio is greater than the preset target size ratio difference threshold, then the NUM2 value is incremented by one (the initial value of NUM2 is set to 0).

[0119] If the distance between the new second location point and the already recorded second location point is greater than the preset distance threshold, then the NUM1 and NUM2 values ​​corresponding to the already recorded first location point will both be reduced by one.

[0120] The NUM1 and NUM2 values ​​of each recorded first location point are dynamically updated in real time. If the NUM1 value of a recorded first location point is greater than or equal to a preset value threshold, or if the NUM1 value is less than the preset value threshold but the NUM2 value is greater than or equal to the preset value threshold, then the second location point corresponding to that first location point is considered a valid duplicate location point. When the number of valid duplicate location points is greater than or equal to a preset value threshold, then each candidate target trajectory is considered a duplicate target trajectory.

[0121] Based on the contour range of each repeating target trajectory, a repeating region is constructed, and the trajectory data within the repeating region in the captured image is deleted.

[0122] Example 3

[0123] Figure 4 This is a schematic diagram of the structure of a device for determining a repeating target trajectory provided in Embodiment 3 of the present invention. Figure 4 As shown, the device includes:

[0124] The target trajectory set determination module 310 is used to determine at least two sets of target trajectory sets, wherein each target trajectory set includes a baseline target trajectory and at least one candidate target trajectory that satisfies the similarity condition with the baseline target trajectory;

[0125] The trajectory consistency judgment module 320 is used to determine whether the baseline target trajectory and the candidate target trajectory of each target trajectory set meet the trajectory consistency condition based on the first position point of the baseline target trajectory and the second position point of the candidate target trajectory in each target trajectory set.

[0126] The repeating target trajectory determination module 330 is used to determine the candidate target trajectory of each target trajectory set as the repeating target trajectory corresponding to the reference target trajectory if the baseline target trajectory and the candidate target trajectory of each target trajectory set meet the trajectory consistency condition.

[0127] The technical solution of this invention determines multiple target trajectory combinations. Each target combination includes a baseline target trajectory and candidate target trajectories that satisfy a similarity condition with the baseline target trajectory. The first position points of the baseline target trajectories in different target trajectory combinations are matched. If, based on the first position points of each baseline target trajectory and the second position points of each candidate target trajectory, it is determined that the baseline target trajectory and the candidate target trajectory of each target trajectory set are consistent, then the candidate target trajectory is regarded as a repeated target trajectory corresponding to the baseline target trajectory. The technical solution of this invention realizes the automatic identification of repeated target trajectories, improving the authenticity and accuracy of target trajectory identification.

[0128] Based on the above embodiments, the trajectory consistency judgment module 320 includes:

[0129] The trajectory consistency judgment unit is used to determine whether the baseline target trajectory and the candidate target trajectory of each target trajectory set meet the trajectory consistency condition based on the first position point of the baseline target trajectory, the second position point of the candidate target trajectory, the target size matching the first position point of the baseline target trajectory, and the target size matching the second position point of the candidate target trajectory in each target trajectory set.

[0130] Based on the above embodiments, the trajectory consistency judgment unit includes:

[0131] The target first position point determination subunit is used to determine the first position point to be processed of at least two reference target trajectories, and to determine the second position point to be processed at the same time as the first position point to be processed in the candidate target trajectories corresponding to the reference target trajectories; wherein, the first position points to be processed of each reference target trajectory meet a preset distance condition.

[0132] The size ratio determination subunit is used to determine the size ratio based on the target size matching the first position point to be processed and the target size matching the second position point to be processed.

[0133] The position point consistency condition judgment subunit is used to determine whether the first position point to be processed meets the position point consistency condition based on each second position point to be processed and each size ratio.

[0134] The trajectory consistency condition judgment subunit is used to determine that the baseline target trajectory and the candidate target trajectory of each target trajectory set meet the trajectory consistency condition if the number of first position points that meet the position point consistency condition is greater than or equal to a preset number threshold.

[0135] Based on the above embodiments, the location point consistency condition judgment subunit is specifically used for:

[0136] Determine the first number of second position points to be processed that meet the preset distance conditions and whose corresponding size ratios meet the preset ratio conditions;

[0137] Determine the second number of second position points to be processed that meet the preset distance condition but whose corresponding size ratio does not meet the preset ratio condition.

[0138] Determine the third number of second location points to be processed that do not meet the preset distance conditions;

[0139] If the difference between the first quantity and the third quantity is greater than or equal to a preset first difference threshold, or the difference between the first quantity and the third quantity is less than a preset first difference threshold, and the difference between the second quantity and the third quantity is greater than or equal to a preset second difference threshold, then the first location point to be processed is determined to meet the location point consistency condition.

[0140] Based on the above embodiments, the device further includes:

[0141] The target trajectory set deletion module is used to delete each set of target trajectories if the difference between the second quantity and the third quantity is less than or equal to a preset third difference threshold.

[0142] Based on the above embodiments, the target trajectory set determination module 310 includes:

[0143] The candidate target trajectory determination unit is used to determine the trajectory of each candidate target if it is determined that there are at least two candidate targets that meet the similarity condition.

[0144] The reference target trajectory determination unit is used to take the candidate target trajectory that meets the preset position conditions as the reference target trajectory, and to take the reference target trajectory and other candidate target trajectories other than the reference target trajectory as a set of target trajectories.

[0145] Based on the above embodiments, the device further includes:

[0146] The repeating region determination module is used to determine the repeating region based on the trajectory of each repeating target.

[0147] The second repeating target trajectory determination module is used to determine the target trajectory within the repeating region in the current image as the repeating target trajectory.

[0148] The repeating target trajectory determination device provided in the embodiments of the present invention can execute the repeating target trajectory determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0149] Example 4

[0150] Figure 5 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0151] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0152] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0153] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as methods for determining repeating target trajectories.

[0154] In some embodiments, the method for determining a repeating target trajectory may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for determining a repeating target trajectory described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the method for determining a repeating target trajectory by any other suitable means (e.g., by means of firmware).

[0155] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0156] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0157] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0158] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0159] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0160] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0161] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0162] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining a repeating target trajectory, characterized in that, include: Determine at least two sets of target trajectories, wherein each set of target trajectories includes a baseline target trajectory and at least one candidate target trajectory that satisfies a similarity condition to the baseline target trajectory; Based on the first position point of the baseline target trajectory and the second position point of the candidate target trajectory in each target trajectory set, determine whether the baseline target trajectory and the candidate target trajectory in each target trajectory set meet the trajectory consistency condition; If the baseline target trajectory and candidate target trajectory of each target trajectory set are determined to meet the trajectory consistency condition, then the candidate target trajectory of each target trajectory set is determined to be a duplicate target trajectory corresponding to the baseline target trajectory. The step of determining whether the baseline target trajectory and the candidate target trajectory of each target trajectory set satisfy the trajectory consistency condition based on the first position point of the baseline target trajectory and the second position point of the candidate target trajectory in each target trajectory set includes: Based on the first position point of the baseline target trajectory, the second position point of the candidate target trajectory, the target size matching the first position point of the baseline target trajectory, and the target size matching the second position point of the candidate target trajectory in each target trajectory set, determine whether the baseline target trajectory and the candidate target trajectory in each target trajectory set meet the trajectory consistency condition.

2. The method according to claim 1, characterized in that, Based on the first position point of the baseline target trajectory, the second position point of the candidate target trajectory, the target size matching the first position point of the baseline target trajectory, and the target size matching the second position point of the candidate target trajectory in each target trajectory set, determine whether the baseline target trajectory and the candidate target trajectory in each target trajectory set meet the trajectory consistency condition, including: Determine at least two reference target trajectories for a first position point to be processed, and in the candidate target trajectories corresponding to the reference target trajectories, determine a second position point to be processed at the same time as the first position point to be processed; Among them, the first location points to be processed in each benchmark target trajectory meet the preset distance condition; Determine the size ratio based on the target size matching the first position point to be processed and the target size matching the second position point to be processed; Based on each second position point to be processed and each size ratio, determine whether the first position point to be processed meets the position point consistency condition; If the number of first location points that meet the location point consistency condition is greater than or equal to a preset number threshold, then the baseline target trajectory and candidate target trajectory of each target trajectory set are determined to meet the trajectory consistency condition.

3. The method according to claim 2, characterized in that, Based on each second position point to be processed and each size ratio, determine whether the first position point to be processed meets the position point consistency condition, including: Determine the first number of second position points to be processed that meet the preset distance conditions and whose corresponding size ratios meet the preset ratio conditions; Determine the second number of second position points to be processed that meet the preset distance condition but whose corresponding size ratio does not meet the preset ratio condition. Determine the third number of second location points to be processed that do not meet the preset distance conditions; If the difference between the first quantity and the third quantity is greater than or equal to a preset first difference threshold, or the difference between the first quantity and the third quantity is less than a preset first difference threshold, and the difference between the second quantity and the third quantity is greater than or equal to a preset second difference threshold, then the first location point to be processed is determined to meet the location point consistency condition.

4. The method according to claim 3, characterized in that, After determining the third number of times the target's second location point does not meet the preset distance condition, the following is also included: If the difference between the second and third quantities is less than or equal to a preset third difference threshold, then each set of target trajectories is deleted.

5. The method according to claim 1, characterized in that, Identify at least two sets of target trajectories, including: If it is determined that there are at least two candidate targets that meet the similarity criteria, then the trajectory of each candidate target is determined; Candidate target trajectories that meet the preset location conditions are used as the baseline target trajectories, and the baseline target trajectories and other candidate target trajectories are used as a set of target trajectories.

6. The method according to claim 1, characterized in that, After determining that the candidate target trajectories of each target trajectory set are repeating target trajectories corresponding to the baseline target trajectory, the following steps are also included: Based on the trajectories of each repeating target, determine the repeating region; The target trajectory within the repeated region in the obtained current image is taken as the repeated target trajectory.

7. A device for determining a repeating target trajectory, characterized in that, include: The target trajectory set determination module is used to determine at least two sets of target trajectory sets, wherein each target trajectory set includes a baseline target trajectory and at least one candidate target trajectory that satisfies the similarity condition with the baseline target trajectory, and the first position points of the baseline target trajectories in each target trajectory set are matched. The trajectory consistency judgment module is used to determine whether the baseline target trajectory and the candidate target trajectory of each target trajectory set meet the trajectory consistency condition based on the first position point of the baseline target trajectory and the second position point of the candidate target trajectory in each target trajectory set. The repeating target trajectory determination module is used to determine the candidate target trajectory of each target trajectory set as the repeating target trajectory corresponding to the reference target trajectory if the baseline target trajectory and the candidate target trajectory of each target trajectory set meet the trajectory consistency condition. The trajectory consistency judgment module includes: The trajectory consistency judgment unit is used to determine whether the baseline target trajectory and the candidate target trajectory of each target trajectory set meet the trajectory consistency condition based on the first position point of the baseline target trajectory, the second position point of the candidate target trajectory, the target size matching the first position point of the baseline target trajectory, and the target size matching the second position point of the candidate target trajectory in each target trajectory set.

8. 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 program, it implements the method for determining a repeating target trajectory as described in any one of claims 1-6.

9. A storage medium for storing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the method for determining a repeating target trajectory as described in any one of claims 1-6.

Images