A target trajectory determination method, apparatus, device, medium and program product

Abstract

Embodiments of the application disclose a target trajectory determination method, device, equipment, medium and program product, and relate to the technical field of target tracking. The method comprises: tracking a target based on at least two image collectors, and determining first trajectory information of the target according to image data; detecting a mobile terminal identification code in a tracking area based on a mobile terminal identification code detection device in a tracking period, and determining the mobile terminal identification code appearing in the tracking area; associating the target with the mobile terminal identification code according to a trajectory distribution feature of the mobile terminal identification code and a trajectory distribution feature of the target to form a target association pair; and determining fusion trajectory information of the target according to the first trajectory information of the target and second trajectory information of the mobile terminal identification code in the target association pair. The above scheme realizes cross verification and missing completion of the target trajectory through fusion of multi-modal data, and improves the completeness and accuracy of the target trajectory.

Description

Technical Field

[0001] This application relates to the field of target tracking technology, and in particular to a method, apparatus, device, medium, and program product for determining target trajectory. Background Technology

[0002] Currently, surveillance cameras are widely used in various fields, including security monitoring, traffic safety monitoring, and industrial robot tracking. In business scenarios involving the tracking of large-scale targets, cross-camera joint tracking is often employed to overcome the limitations of a single camera's field of view, enabling tracking of targets over a wider area.

[0003] During cross-camera joint tracking, the fields of view of multiple cameras may not be seamlessly stitched together. There may be blind spots between the fields of view of different cameras, making it difficult to accurately locate the target's position within the blind spots. Furthermore, during the detection and tracking process, due to factors such as ambient light, occlusion, and changes in the target angle, the camera may be unable to accurately locate and track the target, resulting in low accuracy and poor integrity of the target trajectory formed during the target tracking process. Summary of the Invention

[0004] This application provides a method, apparatus, device, medium, and program product for determining a target trajectory, which improves the accuracy and completeness of the target trajectory through multimodal data fusion.

[0005] According to one aspect of this application, a method for determining a target trajectory is provided, the method comprising:

[0006] The target is tracked and its first trajectory information is determined based on image data acquired by at least two image acquisition devices.

[0007] During the tracking period, the mobile terminal identification code detection device detects the mobile terminal identification code in the tracking area to determine the mobile terminal identification code appearing in the tracking area; wherein, the tracking period is the time period from the first detection of the target by at least two image acquisition devices to the last detection of the target; the tracking area is the union of the field of view ranges of at least two image acquisition devices;

[0008] Based on the trajectory distribution characteristics of the mobile terminal identifier and the trajectory distribution characteristics of the target, the target is associated with the mobile terminal identifier to form a target association pair;

[0009] For each target association pair, the fused trajectory information of the target is determined based on the first trajectory information of the target in the target association pair and the second trajectory information of the mobile terminal identification code; wherein, the second trajectory information includes the trajectory information of the mobile terminal identification code appearing in the tracking area and outside the tracking area during the tracking period.

[0010] According to one aspect of this application, a target trajectory determination apparatus is provided, the apparatus comprising:

[0011] A visual tracking module is used to track a target and determine the first trajectory information of the target based on image data acquired by at least two image acquisition devices;

[0012] The identification code detection module is used to detect mobile terminal identification codes in the tracking area based on the mobile terminal identification code detection device during the tracking period, and determine the mobile terminal identification codes appearing in the tracking area; wherein, the tracking period is the time period from the first detection of the target by at least two image acquisition devices to the last detection of the target; and the tracking area is the union of the field of view ranges of at least two image acquisition devices.

[0013] The association module is used to associate the target with the mobile terminal identifier based on the trajectory distribution characteristics of the mobile terminal identifier and the trajectory distribution characteristics of the target, to form a target association pair;

[0014] The trajectory fusion module is used to determine the fused trajectory information of each target association pair based on the first trajectory information of the target in the target association pair and the second trajectory information of the mobile terminal identification code; wherein, the second trajectory information includes the trajectory information of the mobile terminal identification code appearing in the tracking area and outside the tracking area during the tracking period.

[0015] According to another aspect of this application, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and,

[0017] A memory that is communicatively connected to at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform a target trajectory determination method according to any embodiment of the present application.

[0019] According to another aspect of this application, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute a target trajectory determination method according to any embodiment of this application.

[0020] According to another aspect of this application, a computer program product is provided, comprising a computer program that, when executed by a processor, implements a target trajectory determination method according to any embodiment of this application.

[0021] The technical solution of this application embodiment tracks and determines the first trajectory information of a target based on image data collected by at least two image acquisition devices. It utilizes multi-camera collaboration to acquire the target's visual trajectory. During the tracking period, a mobile terminal identification code detection device detects mobile terminal identification codes within the tracking area to identify the mobile terminal identification codes appearing in the tracking area. The mobile terminal identification codes supplement non-visual information, achieving real-time tracking across the entire scope. Based on the trajectory distribution characteristics of the mobile terminal identification codes and the target's trajectory distribution characteristics, the target and the mobile terminal identification codes are associated to form target association pairs, achieving a corresponding binding between the target and the mobile terminal identification codes and effectively solving the target identity confusion problem in complex scenarios. For each target association pair, based on the first trajectory information of the target and the second trajectory information of the mobile terminal identification code in the target association pair, the fused trajectory information of the target is determined. This overcomes the limitations of camera blind spots, solves the problem of trajectory fragmentation, and compensates for the inaccurate positioning caused by inaccurate target matching and unclear targets due to image quality issues during single-camera tracking.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application, 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 this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 A flowchart illustrating a target trajectory determination method provided in this application embodiment;

[0025] Figure 2 A flowchart illustrating a target trajectory determination method provided in another embodiment of this application;

[0026] Figure 3 A flowchart of a target trajectory determination method provided in another embodiment of this application;

[0027] Figure 4A flowchart illustrating a target trajectory determination method provided in another embodiment of this application;

[0028] Figure 5 A flowchart of a target trajectory determination method is also provided in another embodiment of this application.

[0029] Figure 6 This is a schematic diagram of the structure of a target trajectory determination device provided in an embodiment of this application;

[0030] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0032] It should be noted that the terms "first," "second," "third," "fourth," "actual," "preset," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. 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 apparatus 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 apparatus.

[0033] It should be noted that the data obtained in this application embodiment is obtained with the permission of the target and will not be disclosed without the target's permission, will not infringe upon the target's portrait rights, will not be used for illegal purposes, will not be used for purposes that harm the target's interests, will not be used for personalized analysis of the target, or for product promotion, and will not affect the target's normal life.

[0034] Figure 1This is a flowchart illustrating a target trajectory determination method provided in an embodiment of this application. This embodiment is applicable to situations where a target is tracked to determine a complete trajectory. The method can be executed by a target trajectory determination device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0035] S110. Based on image data acquired by at least two image acquisition devices, track the target and determine the first trajectory information of the target.

[0036] At least two image acquisition devices are used to track targets appearing in a preset area, and the field of view of at least two image acquisition devices must include the preset area. The target can be a pre-defined target or a target identified by the image acquisition devices in real-time detection. The image data is acquired in real-time by at least two image acquisition devices. The acquisition mode of the image acquisition devices can be to acquire data in real-time at a preset frequency and then uniformly identify multiple frames of images; or, the image acquisition devices can first acquire data and identify targets at a mode lower than the preset frequency, and if an image acquisition device identifies a target, it is activated to acquire data in real-time at the preset frequency, or all image acquisition devices within the target area are activated to acquire data in real-time at the preset frequency.

[0037] In this embodiment, the target is tracked using images acquired by at least two image acquisition devices. The acquired images used for target tracking analysis can be a set of images acquired by the at least two image acquisition devices throughout the entire tracking period, or a set of images acquired by each image acquisition device within a sub-tracking period when the target appears within its field of view. That is, assuming the tracking period is the time between the first and last time the target is detected by the at least two image acquisition devices, the set of images acquired by both devices within the tracking period constitutes the acquired images used for target tracking. Alternatively, suppose the time period from the first detection of the target by image collector A to the last detection of the target is sub-tracking period 1, and the images collected by image collector A in sub-tracking period 1 are set A; the time period from the first detection of the target by image collector B to the last detection of the target is sub-tracking period 2, and the images collected by image collector B in sub-tracking period 2 are set B; the time period from the first detection of the target by image collector C to the last detection of the target is sub-tracking period 3, and the images collected by image collector C in sub-tracking period 3 are set C. Then the images collected for target tracking are the union of sets A, B, and C.

[0038] Specifically, determining the first trajectory information of a target based on acquired images can involve: for each image acquisition device's set of acquired images, detecting and recognizing image frames within the set; matching the subjects enclosed by detection boxes in different image frames to identify the same target; and determining the target's position and time of appearance in each image frame. ,in Indicates the position of the target within the image frame. This indicates the time when the target appeared at that location. Representing the Image frames. The location and time of the target's appearance in each image frame form a trajectory point, thus forming trajectory information of the target appearing within the field of view of each image acquisition device based on each image frame. The subjects enclosed by detection boxes in the image sets acquired by other image acquisition devices are matched with this target to lock onto the same target. Similarly, the trajectory information of the target appearing within the field of view of other image acquisition devices is determined based on the image sets acquired by other image acquisition devices. The trajectory information of the target appearing within the field of view of each image acquisition device constitutes the first trajectory information. This can be represented as... ,in, It is the position of the target in the image frame. This indicates the time when the target appeared at that location. It is the image acquisition device ID. Representing the Image frame. It should be noted that the target position mentioned above is the target's position within the image frame. In subsequent processing, the position information in different coordinate systems will be unified.

[0039] S120. During the tracking period, the mobile terminal identification code detection device detects the mobile terminal identification code in the tracking area to determine the mobile terminal identification code appearing in the tracking area; wherein, the tracking period is the time period from the first detection of the target by at least two image acquisition devices to the last detection of the target; the tracking area is the union of the field of view ranges of at least two image acquisition devices.

[0040] The tracking period refers to the time between the first and last time at least two image acquisition devices detect a target, not just a single image acquisition device, but all image acquisition devices. For example, if image acquisition device A first detects a target at time t1 and last detects it at time t2, image acquisition device B first detects the target at time t3 and last detects it at time t4, and image acquisition device C first detects the target at time t5 and last detects it at time t6, then for these three image acquisition devices, the first detection time is t1 and the last detection time is t6, and the tracking period is t1-t6. The mobile terminal identification code detection device is a detection device set within a preset range of the image acquisition devices, used to detect the signal of the mobile terminal identification code. The mobile terminal identification code is a digital or character code used to uniquely identify a mobile device, such as IMSI, IMEI, MEID, ICCID, etc. Mobile device identification codes can generally be bound to SIM cards and baseband chips and can be detected by the mobile terminal identification code detection device. The detection range of mobile terminal identification code detection equipment is limited. Generally, a mobile terminal identification code detection equipment is only used to detect mobile terminal identification codes that appear within the field of view of an image acquisition device.

[0041] In this embodiment of the application, during the tracking time period, it is determined that there is a target appearing within the field of view of at least two image acquisition devices. Therefore, during the tracking time period, the mobile terminal identification code detection device is used to detect the mobile terminal identification code in the tracking area, that is, to detect the mobile terminal identification code appearing within the field of view of at least two image acquisition devices. The target is indirectly detected from dimensions other than vision to assist in target tracking.

[0042] Specifically, in the process of detecting mobile terminal identification codes within a tracking area using a mobile terminal identification code detection device, the detection can be performed on each image acquisition device based on the mobile terminal identification code detection device within the field of view of that image acquisition device, thereby determining the set of mobile terminal identification codes appearing within the field of view of that image acquisition device. ,in, The tracking period is defined as follows. The set of mobile terminal identifiers contains all mobile terminal identifiers that appear within the field of view of the image capture device. Different mobile terminal identifiers may exist, reflecting the movement of different mobile terminals within the field of view of the image capture device. There may also be identical mobile terminal identifiers, reflecting the movement of the same mobile terminal within the field of view of the image capture device.

[0043] S130. Based on the trajectory distribution characteristics of the mobile terminal identifier and the trajectory distribution characteristics of the target, the target is associated with the mobile terminal identifier to form a target association pair.

[0044] For example, the trajectory distribution characteristics of a mobile terminal identifier can reflect the distribution of the mobile terminal in the time dimension and / or spatial dimension within the tracking area. Its form can be discrete and diverse, and can be presented separately in the time and spatial dimensions, not limited to being presented as trajectory points, where a trajectory point includes both spatial location and time. For example, it can be in the form of the aforementioned set of mobile terminal identifiers. Similarly, the trajectory distribution characteristics of a target can be based solely on the target's spatial distribution, or solely on the target's temporal distribution, or the target's first trajectory information, depending on the specific circumstances.

[0045] In this embodiment, generally, if the target and the mobile terminal to which the mobile terminal identifier belongs are bound together, the trajectory distribution characteristics of the mobile terminal identifier and the trajectory distribution characteristics of the target have a certain degree of matching. This matching is reflected in both the time and spatial dimensions. Therefore, the target and the mobile terminal identifier can be associated based on their respective trajectory distribution characteristics to form a target association pair. Specifically, in one possible implementation, the trajectory distribution characteristics of the mobile terminal identifier in the time dimension can be matched with the trajectory distribution characteristics of the target in the time dimension, and the association between the target and the mobile terminal identifier is determined based on the consistency of the time-dimensional matching. For example, the time-dimensional trajectory distribution characteristics of mobile terminal identifiers are as follows: the occurrence times of mobile terminal identifier a are {t1, t2, t3, t4, t5}, the occurrence times of mobile terminal identifier b are {t4, t5, t6, t7, t8}, and the occurrence times of the target are {t1, t2, t3, t4', t5}. Furthermore, the time difference between t4' and t4 is less than a preset time difference threshold, indicating that the two times are close. Therefore, it can be seen that the occurrence times of mobile terminal identifier a and the target are consistent, indicating a high matching consistency. Thus, mobile terminal identifier a and the target can be associated to form a target association pair. However, the occurrence times of mobile terminal identifier b and the target are inconsistent, indicating a low matching consistency, and therefore, they are not associated. Similarly, the spatial trajectory distribution characteristics of mobile terminal identifiers can be used to select mobile terminal identifiers associated with the target for association, or the trajectory distribution characteristics formed by the trajectory points of the mobile terminal identifiers and the target can be used to select mobile terminal identifiers associated with the target for association.

[0046] S140. For each target association pair, determine the fused trajectory information of the target based on the first trajectory information of the target in the target association pair and the second trajectory information of the mobile terminal identification code; wherein, the second trajectory information includes the trajectory information of the mobile terminal identification code appearing in the tracking area and outside the tracking area during the tracking period.

[0047] In this embodiment, the target association pair reflects the mobile terminal and target that are bound together and move together within the tracking time period and tracking area. Therefore, the trajectory information of the mobile terminal identifier can reflect the trajectory information of the target to a certain extent. For the target association pair, the fused trajectory information of the target can be determined based on the first trajectory information of the target and the second trajectory information of the mobile terminal identifier in the target association pair. The second trajectory information includes the trajectory information of the mobile terminal identifier appearing within and outside the tracking area during the tracking time period. That is, based on the tracking time period, the trajectory information of the mobile terminal identifier appearing during the tracking time period is determined, including both trajectory information appearing within and outside the tracking area. The second trajectory information of the mobile terminal identifier can be obtained through the positioning function of the base station.

[0048] Specifically, based on the first trajectory information of the target associated with the target and the second trajectory information of the mobile terminal identification code, the fused trajectory information of the target is determined. This can be achieved by weighted fusion of the first and second trajectory information, or by supplementing and correcting the first trajectory information based on the second trajectory information. In other words, by mutually assisting and referencing the first and second trajectory information, more complete and accurate fused trajectory information is obtained.

[0049] The technical solution of this application embodiment tracks and determines the first trajectory information of a target based on image data collected by at least two image acquisition devices. It utilizes multi-camera collaboration to acquire the target's visual trajectory. During the tracking period, a mobile terminal identification code detection device detects mobile terminal identification codes within the tracking area to identify the mobile terminal identification codes appearing in the tracking area. The mobile terminal identification codes supplement non-visual information, achieving real-time tracking across the entire scope. Based on the trajectory distribution characteristics of the mobile terminal identification codes and the target's trajectory distribution characteristics, the target and the mobile terminal identification codes are associated to form target association pairs, achieving a corresponding binding between the target and the mobile terminal identification codes and effectively solving the target identity confusion problem in complex scenarios. For each target association pair, based on the first trajectory information of the target and the second trajectory information of the mobile terminal identification code in the target association pair, the fused trajectory information of the target is determined. This overcomes the limitations of camera blind spots, solves the problem of trajectory fragmentation, and compensates for the inaccurate positioning caused by inaccurate target matching and unclear targets due to image quality issues during single-camera tracking.

[0050] Figure 2 This is a flowchart illustrating a target trajectory determination method according to another embodiment of this application. This embodiment is an optimization based on the above embodiment; solutions not described in detail in this embodiment are found in the above embodiment. Figure 2 As shown, the method in this embodiment of the application specifically includes the following steps:

[0051] S210. Based on image data acquired by at least two image acquisition devices, track the target and determine the first trajectory information of the target.

[0052] S220. During the tracking period, the mobile terminal identification code detection device detects the mobile terminal identification code in the tracking area to determine the mobile terminal identification code appearing in the tracking area; wherein, the tracking period is the time period from the first detection of the target by at least two image acquisition devices to the last detection of the target; the tracking area is the union of the field of view ranges of at least two image acquisition devices.

[0053] S230. Based on the trajectory distribution characteristics of the mobile terminal identification code, count the number of times the mobile terminal identification code appears in the tracking area during the tracking period.

[0054] For example, the trajectory distribution characteristics of a mobile terminal identifier can be reflected by the number of times the mobile terminal identifier appears within the tracking area during the tracking period. The number of appearances is positively correlated with the number of times it appears in a single time dimension, and similarly, it is positively correlated with the number of locations it appears in a single spatial dimension. The number of times a mobile terminal identifier appears within the tracking area during the tracking period refers to the number of times the same mobile terminal identifier appears; therefore, each detected mobile terminal identifier corresponds to a count of appearances.

[0055] In this embodiment of the application, during the tracking period, the mobile terminal identification code is detected by a mobile terminal identification code detection device within the tracking area to determine the mobile terminal identification code appearing within the tracking area, including:

[0056] For each image acquisition device, determine the sub-tracking time period in which the target appears within the field of view of the image acquisition device;

[0057] Based on the mobile terminal identification code detection device, the mobile terminal identification codes that appear within the field of view during the sub-tracking period are detected, and the set of mobile terminal identification codes corresponding to the sub-tracking period is determined.

[0058] Accordingly, based on the distribution characteristics of the mobile terminal identification code, the number of times the mobile terminal identification code appears in the tracking area during the tracking period is statistically analyzed, including:

[0059] Iterate through the set of mobile terminal identifiers corresponding to each sub-tracking period, and detect the number of sets of mobile terminal identifiers that contain the same mobile terminal identifier, which is taken as the number of times that mobile terminal identifier appears.

[0060] For example, for each image acquisition device, a sub-tracking period in which the target appears within the field of view of the image acquisition device is determined, that is, the period from the first time the image acquisition device detects the target to the last time it detects the target. Based on the mobile terminal identification code detection device detecting the mobile terminal identification codes appearing within the field of view of the image acquisition device during the sub-tracking period, the set of mobile terminal identification codes corresponding to the sub-tracking period is determined, which can be represented as follows: In this scenario This can also be represented as a sub-tracking period. The set of mobile terminal identifiers corresponding to a sub-tracking period includes the mobile terminal identifiers of the mobile terminal bound to the target, and may also include the mobile terminal identifiers of other mobile terminals. Each image acquisition device corresponds to a sub-tracking period, and each sub-tracking period corresponds to a set of mobile terminal identifiers. In counting the number of times a mobile terminal identifier appears in the tracking area within a tracking period, the set of mobile terminal identifiers corresponding to each sub-tracking period can be traversed, and the number of sets of mobile terminal identifiers containing the same mobile terminal identifier can be detected, which is taken as the count of that mobile terminal identifier. The above scheme, by segmenting and detecting collisions with each set of mobile terminal identifiers, more conveniently and quickly counts the number of times a mobile terminal identifier appears.

[0061] S240. Based on the frequency of occurrence of the mobile terminal identification code and the trajectory distribution characteristics of the target, the target is associated with the mobile terminal identification code to form a target association pair.

[0062] For example, when a target and a mobile terminal are linked and move synchronously, there is a certain correlation between the frequency of occurrence of the mobile terminal identifier and the target's trajectory distribution characteristics. For instance, the frequency of occurrence of the mobile terminal identifier should be consistent with the frequency of occurrence of the target within the field of view of each image acquisition device, or the difference between the frequency of occurrence of the mobile terminal identifier and the frequency of occurrence of the target within the field of view of each image acquisition device should be less than a preset difference threshold. Based on this, the target and the mobile terminal identifier can be associated to form a target association pair.

[0063] In this embodiment of the application, the target is associated with the mobile terminal identifier based on the frequency of occurrence of the mobile terminal identifier and the trajectory distribution characteristics of the target, forming a target association pair, including:

[0064] If only one target appears in the tracking area during the tracking period, the mobile terminal identifier that appears most frequently is associated with the target to form a target association pair.

[0065] For example, if it is determined that only one target appears in the tracking area during the tracking period, then this target appears most frequently. Therefore, the mobile terminal identifier code of the mobile terminal that is synchronously moving with and bound to this target should also appear most frequently. Thus, the mobile terminal corresponding to the most frequently appearing and unique mobile terminal identifier code is identified as the mobile terminal that is synchronously moving with and bound to the target, establishing an association between this mobile terminal identifier code and the target, forming a target association pair. This scheme achieves accurate association identification of a single target by dynamically tracking the frequency of mobile terminal identifier codes within the tracking area, solving the problem of high computational complexity and low efficiency in one-to-one trajectory comparison.

[0066] S250. For each target association pair, determine the fused trajectory information of the target based on the first trajectory information of the target in the target association pair and the second trajectory information of the mobile terminal identification code; wherein, the second trajectory information includes the trajectory information of the mobile terminal identification code appearing in the tracking area and outside the tracking area during the tracking period.

[0067] The solution in this embodiment counts the number of times the mobile terminal identifier appears in the tracking area during the tracking period based on the trajectory distribution characteristics of the mobile terminal identifier. Based on the number of times the mobile terminal identifier appears and the trajectory distribution characteristics of the target, the target and the mobile terminal identifier are associated to form a target association pair. This joint analysis of trajectory distribution characteristics and frequency of appearance not only captures the spatiotemporal activity patterns of the target and the mobile terminal identifier, achieving accurate association, but also reduces the difficulty of association matching, enabling real-time and efficient association.

[0068] Figure 3 This is a flowchart illustrating a target trajectory determination method according to another embodiment of this application. This embodiment is an optimization based on the above embodiments; solutions not described in detail in this embodiment are found in the above embodiments. Figure 3 As shown, the method in this embodiment of the application specifically includes the following steps:

[0069] S310. Based on image data acquired by at least two image acquisition devices, track the target and determine the first trajectory information of the target.

[0070] S320. During the tracking period, the mobile terminal identification code detection device detects the mobile terminal identification code in the tracking area to determine the mobile terminal identification code appearing in the tracking area; wherein, the tracking period is the time period from the first detection of the target by at least two image acquisition devices to the last detection of the target; the tracking area is the union of the field of view ranges of at least two image acquisition devices.

[0071] S330. Match the trajectory distribution features of the mobile terminal identification code with the trajectory distribution features of the target to determine the matching degree between each mobile terminal identification code and each target.

[0072] For example, if a mobile terminal is bound to a target and moves synchronously, the trajectory distribution characteristics of the mobile terminal's identifier code should match the trajectory distribution characteristics of the target. The trajectory distribution characteristics of the mobile terminal's identifier code can be matched with the trajectory distribution characteristics of the target to determine the matching degree between each mobile terminal's identifier code and each target. For a given target, each mobile terminal's identifier code can be traversed, and the trajectory distribution characteristics of the target can be matched with the trajectory distribution characteristics of each mobile terminal's identifier code to determine the matching degree. Specifically, there may be some deviation between the trajectory distribution characteristics of the mobile terminal's identifier code and the trajectory distribution characteristics of the target during the matching process; they are not a perfect match. In this embodiment, a certain tolerance is set, meaning that if the deviation between the trajectory distribution characteristics of the mobile terminal's identifier code and the trajectory distribution characteristics of the target is within a certain deviation range, then a match is determined. The matching degree between the mobile terminal's identifier code and the target can be positively correlated with the number of matching moments in the time dimension, or with the number of matching locations in the spatial dimension, or with the number of matching trajectory points in the trajectory point matching.

[0073] In this embodiment of the application, the trajectory distribution features of the mobile terminal identifier code and the trajectory distribution features of the target are matched to determine the matching degree between each mobile terminal identifier code and each target, including:

[0074] The mobile terminal identifier and the target are matched based on the time dimension trajectory distribution features and the spatial dimension trajectory distribution features.

[0075] The mobile terminal identifier and target that match the time dimension trajectory distribution features and the spatial dimension trajectory distribution features most frequently are identified as having the highest matching degree.

[0076] For example, to more accurately match mobile terminal identifiers with targets, the mobile terminal identifiers and targets can be matched based on both temporal and spatial trajectory distribution features. This means checking if the mobile terminal identifier and the target match in both time and location. If a continuous trajectory in the trajectory distribution features of the mobile terminal identifier and the target matches in both time and location, it is counted as one match. The number of matches after matching all trajectory distribution features is counted, and the mobile terminal identifier that matches the target the most times is determined to have the highest matching degree with that target.

[0077] S340. Associate the mobile terminal identifier code with the highest matching degree with the target to form a target association pair.

[0078] For example, if there is a mobile terminal identifier that matches the target with the highest degree of matching and is unique, then the mobile terminal identifier is associated with the target to form a target association pair.

[0079] S350. For each target association pair, determine the fused trajectory information of the target based on the first trajectory information of the target in the target association pair and the second trajectory information of the mobile terminal identification code; wherein, the second trajectory information includes the trajectory information of the mobile terminal identification code appearing in the tracking area and outside the tracking area during the tracking period.

[0080] This application provides a target trajectory determination method. It matches the trajectory distribution features of the mobile terminal identifier code with the trajectory distribution features of the target to determine the matching degree between each mobile terminal identifier code and each target. The mobile terminal identifier code with the highest matching degree is then associated with the target to form a target association pair. This scheme, based on spatiotemporal trajectory similarity matching, quantifies the association strength between the mobile terminal identifier code and the target, effectively detecting and identifying bound and synchronized mobile terminals and targets, effectively distinguishing and removing interference from other mobile terminals, and using devices associated with the target for assisted target tracking, thereby improving the accuracy of target tracking.

[0081] Figure 4 This is a flowchart illustrating a target trajectory determination method according to another embodiment of this application. This embodiment is an optimization based on the above embodiments; solutions not described in detail in this embodiment are found in the above embodiments. Figure 4 As shown, the method in this embodiment of the application specifically includes the following steps:

[0082] S410. Based on image data acquired by at least two image acquisition devices, track the target and determine the first trajectory information of the target.

[0083] S420. During the tracking period, the mobile terminal identification code detection device detects the mobile terminal identification code in the tracking area to determine the mobile terminal identification code appearing in the tracking area; wherein, the tracking period is the time period from the first detection of the target by at least two image acquisition devices to the last detection of the target; the tracking area is the union of the field of view ranges of at least two image acquisition devices.

[0084] S430. Based on the trajectory distribution characteristics of the mobile terminal identifier and the trajectory distribution characteristics of the target, associate the target with the mobile terminal identifier to form a target association pair.

[0085] S440. For the mobile terminal identification code in the target association pair, traverse the adjacent field of view of at least two image acquisition devices, and determine the continuity score of the mobile terminal identification code based on the occurrence results of the mobile terminal identification code in the adjacent field of view.

[0086] For example, after associating the target with the mobile terminal identification code, the association can be further verified to determine whether the association is appropriate. Specifically, for the field of view of at least two image acquisition devices, if the mobile terminal identification code appears in adjacent field of view, it reflects that the mobile terminal identification code has strong continuity. Accordingly, based on the occurrence of the mobile terminal identification code in adjacent field of view, a continuity score for the mobile terminal identification code is determined.

[0087] In this embodiment of the application, the continuity score of the mobile terminal identification code is determined based on the occurrence of the mobile terminal identification code within adjacent fields of view, including:

[0088] The continuity score determined when the result is that the mobile terminal identification code is detected in all adjacent fields of view is higher than the continuity score determined when the result is that the mobile terminal identification code is not detected in at least one field of view in adjacent fields of view.

[0089] For example, in determining the continuity score of a mobile terminal, the continuity score determined when the mobile terminal identifier is detected in all adjacent fields of view is higher than the continuity score determined when the mobile terminal identifier is not detected in at least one field of view within adjacent fields of view. For instance, the occurrence of the mobile terminal identifier in adjacent fields of view includes: appearing in all adjacent fields of view, appearing in one of the fields of view, and not appearing in any adjacent fields of view. The continuity score corresponding to the occurrence in all adjacent fields of view is the highest, reflecting the spatial continuity of the mobile terminal identifier's appearance. In other cases, at least one field of view does not contain the mobile terminal identifier, therefore the continuity score is lower than the occurrence of the mobile terminal identifier in all adjacent fields of view. Furthermore, the continuity score corresponding to a mobile terminal identifier appearing in only one field of view is higher than the continuity score corresponding to a mobile terminal identifier not appearing in adjacent fields of view. For example, if mobile terminal identifier 1 appears in an adjacent field of view A but not in another adjacent field of view B, and mobile terminal identifier 2 does not appear in either adjacent field of view A or adjacent field of view B, then the continuity score of mobile terminal identifier 1 is higher than that of mobile terminal identifier 2. The above only illustrates the continuity score corresponding to the appearance of a mobile terminal identifier within one adjacent field of view. The final continuity score for a mobile terminal identifier can be a combination of the continuity scores corresponding to its appearance in each group of adjacent field of view. Specifically, for mobile terminal identifiers that are... In the The detection result within each field of view can be represented as a Boolean value. ,Right now

[0090] ;

[0091] If the mobile terminal identification code is detected in both adjacent fields of view, then:

[0092] .

[0093] This represents the continuity score for mobile terminal identification code detection, when within adjacent fields of view. and All were detected hour, The value is 1. If no mobile terminal identification code is detected within the field of view, then... A score of 0 indicates that the mobile terminal corresponding to this identification code is moving within the adjacent field of view, suggesting that the same target exists in both areas. The final continuity score is... .

[0094] S450. For the target in the target association pair, obtain the matching similarity probability of matching the same target in target images collected within adjacent fields of view.

[0095] For example, in the field of vision, during target tracking based on image data acquired by at least two image acquisition devices, target images acquired by two image acquisition devices with adjacent fields of view can be matched to identify the same target. After matching, the matching similarity probability of the same target in the target images acquired in the two fields of view is obtained, and this matching similarity probability reflects the accuracy of tracking the same target.

[0096] Specifically, for example, target detection and matching can be performed using the ReID algorithm, and the field of view range... and field of view The probability of matching the same target is . ,in and These are the field of view ranges and field of view Captured target image features. The ReID algorithm provides the matching similarity probability for the same target:

[0097] ;

[0098] The closer the value is to 1, the more similar the visual features of the targets within the two fields of view are.

[0099] S460. Based on the continuity score and the matching similarity probability, determine the matching score of the target association pair, and verify the target association pair based on the matching score.

[0100] For example, the matching score of a target association pair is determined based on the continuity score and the matching similarity probability. This involves scoring the target association pairs already formed in the above embodiments, using the matching score to reflect the degree of association between the target association pairs, and then verifying the target association pairs based on the matching score. The process of determining the matching score of a target association pair based on the continuity score and the matching similarity probability can be as follows: a weighted sum of the continuity score and the matching similarity probability is performed to determine the matching score. The matching score is expressed as... ;in: It is a weighting parameter with a value range of [0,1], used to balance the influence of continuity score and matching similarity probability. For continuous scoring, To match similarity probabilities.

[0101] Specifically, a preset matching score threshold can be set. If the matching score is higher than or equal to the preset matching score threshold, the verification of the target association pair is considered successful, and they are actually associated. If the matching score is lower than the preset matching score threshold, the verification of the target association pair is considered unsuccessful, and they are not actually associated. The association of the target association pair is then terminated, and no further operations are performed on that target association pair.

[0102] S470. For each target association pair, determine the fused trajectory information of the target based on the first trajectory information of the target in the target association pair and the second trajectory information of the mobile terminal identification code; wherein, the second trajectory information includes the trajectory information of the mobile terminal identification code appearing in the tracking area and outside the tracking area during the tracking period.

[0103] This application provides a target trajectory determination method. It utilizes the continuity score of the mobile terminal identification code to confirm the consistency of the mobile terminal identification code identity, and verifies the identity of physical entities through feature matching similarity probabilities of targets in adjacent fields of view. Finally, the two types of scores are merged into a comprehensive matching score. This dual verification mechanism avoids misjudgment based on a single feature and solves the problem of mis-association of identities caused by signal drift, making it suitable for cross-camera target tracking in complex dynamic scenarios.

[0104] Figure 5 This application also provides a flowchart of a target trajectory determination method according to another embodiment. This application embodiment is based on and optimized from the above embodiments. Solutions not described in detail in this application embodiment can be found in the above embodiments. Figure 5 As shown, the method in this embodiment of the application specifically includes the following steps:

[0105] S510. Based on image data acquired by at least two image acquisition devices, track the target and determine the first trajectory information of the target.

[0106] S520. During the tracking period, the mobile terminal identification code detection device detects the mobile terminal identification code in the tracking area to determine the mobile terminal identification code appearing in the tracking area; wherein, the tracking period is the time period from the first detection of the target by at least two image acquisition devices to the last detection of the target; the tracking area is the union of the field of view of at least two image acquisition devices.

[0107] S530. Based on the trajectory distribution characteristics of the mobile terminal identifier and the trajectory distribution characteristics of the target, the target is associated with the mobile terminal identifier to form a target association pair.

[0108] S540. For the first trajectory information and the second trajectory information under the same coordinate system, perform timestamp alignment processing on the first trajectory information and the second trajectory information.

[0109] In this embodiment, before fusing visual and communication information, spatiotemporal calibration of the visual and communication information from multiple sources is required. This involves aligning the multi-source data temporally and spatially. Spatial alignment refers to transforming the first and second trajectory information into the same coordinate system to present an accurate relative positional relationship. Temporal alignment involves aligning the first and second trajectory information in the same coordinate system using timestamps, thereby achieving multi-source data calibration in the time dimension.

[0110] In this embodiment, during the spatial alignment of the first trajectory information and the second trajectory information, both can be converted into coordinates on the image plane acquired by the image acquisition device. Specifically, the first trajectory information represents points presented in the coordinate system of the image acquisition device, and perspective projection is used to transform the points in the image acquisition device's coordinate system... Projected onto a two-dimensional image plane. The projection formula is:

[0111] ;

[0112] in:

[0113] It refers to the focal length of the camera.

[0114] It is the depth of the object in a three-dimensional coordinate system.

[0115] Final result These are coordinates on the image plane.

[0116] The second trajectory information is a point in the time coordinate system, which is transformed into world coordinate P using a rotation matrix R and a translation vector T. The rotation matrix R describes the rotation of the image acquisition device relative to the world coordinate system, and the translation vector T describes the position offset of the image acquisition device.

[0117] ;

[0118] Where R is a 3×3 rotation matrix and T is a 3×1 offset vector. These are coordinates on the image plane.

[0119] S550. The first trajectory information and the second trajectory information with timestamp alignment are weighted and summed to obtain the fused trajectory information of the target; wherein, if the location information corresponding to the timestamp in the first trajectory information does not exist, the weight of the location information corresponding to the timestamp in the first trajectory information is reset to 0.

[0120] Specifically, in the process of weighted summation of the first trajectory information and the second trajectory information, the first trajectory information and the second trajectory information can be weighted and summed to obtain the target's fused trajectory information, expressed by the formula as follows: .in, This represents the fused trajectory information at time t. This refers to the second trajectory information corresponding to time t. Let β be the weight of the second trajectory information at time t, and 1-β be the weight of the first trajectory information. The weights can be determined based on actual conditions, such as the confidence levels of the detected first and second trajectory information at time t. For example, if at time t, the image quality score of the target image is higher than a preset quality score, indicating high accuracy in target recognition, while the signal strength of the detected mobile terminal identification code is lower than a preset strength, indicating low confidence in mobile terminal identification code detection, then the weight of the first trajectory information can be set greater than the weight of the second trajectory information. If the first trajectory information of the target is not detected within a time period (i.e., the location information corresponding to the timestamp is missing in the timestamp-aligned first trajectory information), then the weight of the first trajectory information is set to 0. The target trajectory information is then supplemented based on the second trajectory information corresponding to the mobile terminal identification code, improving the completeness of the target trajectory.

[0121] The technical solution in this application ensures the temporal consistency of trajectory data through timestamp alignment, eliminating temporal misalignment caused by differences in acquisition frequency. Weighted summation fuses the complementary advantages of multi-source trajectories, suppressing noise or drift errors from a single sensor. The resulting fused trajectory combines the high-precision positioning characteristics of the first trajectory with the continuous smoothness of the second trajectory, significantly improving the robustness of target tracking. It is particularly suitable for trajectory reconstruction and prediction tasks in dynamic and complex environments, solving the problem of inaccurate target identification caused by target blurring, low light, or angular deviations in monitoring and tracking alone. It also addresses the issue of blind spots between multiple image acquisition devices, which prevent accurate target positioning.

[0122] Figure 6 This is a schematic diagram of a target trajectory determination device provided in an embodiment of this application. This device can execute a target trajectory determination method provided in any embodiment of this application, and possesses the corresponding functional modules and beneficial effects of the method. Figure 6 As shown, the device includes:

[0123] The visual tracking module 610 is used to track a target and determine the first trajectory information of the target based on image data acquired by at least two image acquisition devices;

[0124] The identification code detection module 620 is used to detect the mobile terminal identification code in the tracking area based on the mobile terminal identification code detection device during the tracking period, and determine the mobile terminal identification code appearing in the tracking area; wherein, the tracking period is the time period from the first detection of the target by at least two image acquisition devices to the last detection of the target; the tracking area is the union of the field of view ranges of at least two image acquisition devices;

[0125] The association module 630 is used to associate the target with the mobile terminal identifier based on the trajectory distribution characteristics of the mobile terminal identifier and the trajectory distribution characteristics of the target, to form a target association pair;

[0126] The trajectory fusion module 640 is used to determine the fused trajectory information of each target association pair based on the first trajectory information of the target in the target association pair and the second trajectory information of the mobile terminal identification code; wherein, the second trajectory information includes the trajectory information of the mobile terminal identification code appearing in the tracking area and outside the tracking area during the tracking period.

[0127] In this embodiment, the association module 630 associates the target with the mobile terminal identifier based on the trajectory distribution characteristics of the mobile terminal identifier and the trajectory distribution characteristics of the target, forming a target association pair, including:

[0128] The number of times the mobile terminal identification code appears in the tracking area during the tracking period is counted based on the trajectory distribution characteristics of the mobile terminal identification code.

[0129] Based on the frequency of occurrence of the mobile terminal identifier and the trajectory distribution characteristics of the target, the target is associated with the mobile terminal identifier to form a target association pair.

[0130] In this embodiment of the application, the association module 630 detects the mobile terminal identification code in the tracking area based on the mobile terminal identification code detection device during the tracking period, and determines the mobile terminal identification code appearing in the tracking area, including:

[0131] For each image acquisition device, determine the sub-tracking time period in which the target appears within the field of view of the image acquisition device;

[0132] Based on the mobile terminal identification code detection device, the mobile terminal identification codes that appear within the field of view during the sub-tracking period are detected, and the set of mobile terminal identification codes corresponding to the sub-tracking period is determined.

[0133] Accordingly, based on the distribution characteristics of the mobile terminal identification code, the number of times the mobile terminal identification code appears in the tracking area during the tracking period is statistically analyzed, including:

[0134] Iterate through the set of mobile terminal identifiers corresponding to each sub-tracking period, and detect the number of sets of mobile terminal identifiers that contain the same mobile terminal identifier, which is taken as the number of times that mobile terminal identifier appears.

[0135] In this embodiment, the association module 630 associates the target with the mobile terminal identifier based on the frequency of occurrence of the mobile terminal identifier and the trajectory distribution characteristics of the target, forming a target association pair, including:

[0136] If only one target appears in the tracking area during the tracking period, the mobile terminal identifier that appears most frequently is associated with the target to form a target association pair.

[0137] In this embodiment, the association module 630 associates the target with the mobile terminal identifier based on the trajectory distribution characteristics of the mobile terminal identifier and the trajectory distribution characteristics of the target, forming a target association pair, including:

[0138] The trajectory distribution characteristics of the mobile terminal identification code and the trajectory distribution characteristics of the target are matched to determine the matching degree between each mobile terminal identification code and each target.

[0139] The mobile terminal identifier with the highest matching degree is associated with the target to form a target association pair.

[0140] In this embodiment of the application, the association module 630 matches the trajectory distribution features of the mobile terminal identifier code with the trajectory distribution features of the target to determine the matching degree between each mobile terminal identifier code and each target, including:

[0141] The mobile terminal identifier and the target are matched based on the time dimension trajectory distribution features and the spatial dimension trajectory distribution features.

[0142] The mobile terminal identifier and target that match the time dimension trajectory distribution features and the spatial dimension trajectory distribution features most frequently are identified as having the highest matching degree.

[0143] In this embodiment of the application, after associating the target with the mobile terminal identifier based on the trajectory distribution characteristics of the mobile terminal identifier and the trajectory distribution characteristics of the target to form a target association pair, the device further includes a verification module, used for:

[0144] For the mobile terminal identification code in the target association pair, traverse each adjacent field of view of at least two image acquisition devices, and determine the continuity score of the mobile terminal identification code based on the occurrence of the mobile terminal identification code in the adjacent field of view.

[0145] For the target in the target association pair, obtain the matching similarity probability of matching the same target in target images acquired within adjacent fields of view;

[0146] Based on the continuity score and the matching similarity probability, the matching score of the target association pair is determined, and the target association pair is verified based on the matching score.

[0147] In this embodiment of the application, the verification module determines the continuity score of the mobile terminal identification code based on the occurrence of the mobile terminal identification code within adjacent fields of view, including:

[0148] The continuity score determined when the result is that the mobile terminal identification code is detected in all adjacent fields of view is higher than the continuity score determined when the result is that the mobile terminal identification code is not detected in at least one field of view in adjacent fields of view.

[0149] In this embodiment, the trajectory fusion module 640 determines the fused trajectory information of the target based on the first trajectory information of the target in the target association pair and the second trajectory information of the mobile terminal identification code, including:

[0150] For the first trajectory information and the second trajectory information under the same coordinate system, the first trajectory information and the second trajectory information are timestamped.

[0151] The first trajectory information and the second trajectory information aligned with the timestamp are weighted and summed to obtain the fused trajectory information of the target; wherein, if the location information corresponding to the timestamp in the first trajectory information does not exist, the weight of the location information corresponding to the timestamp in the first trajectory information is reset to 0.

[0152] The target trajectory determination device provided in this application embodiment can execute a target trajectory determination method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects of the method execution.

[0153] Figure 7 A schematic diagram of an electronic device 10, which can be used to implement embodiments of this application, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital processors, 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 application described and / or claimed herein.

[0154] like Figure 7 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 can 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.

[0155] 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.

[0156] 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, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a target trajectory determination method.

[0157] In some embodiments, a target trajectory determination method 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 target trajectory determination method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform a target trajectory determination method by any other suitable means (e.g., by means of firmware).

[0158] 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), complex 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.

[0159] Computer programs used to implement the methods of this application 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 target trajectory determination 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 implemented. 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.

[0160] In the context of this application, 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 can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can 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 fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0161] 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).

[0162] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or 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.

[0163] 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.

[0164] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements a target trajectory determination method as provided in any embodiment of this application.

[0165] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0166] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired information of the technical solution of this application can be achieved, and this is not limited herein.

[0167] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. 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 application should be included within the scope of protection of this application.

Claims

1. A method for determining a target trajectory, characterized in that, The method includes: The target is tracked and its first trajectory information is determined based on image data acquired by at least two image acquisition devices. During the tracking period, the mobile terminal identification code detection device detects the mobile terminal identification code in the tracking area to determine the mobile terminal identification code appearing in the tracking area; wherein, the tracking period is the time period from the first detection of the target by at least two image acquisition devices to the last detection of the target; the tracking area is the union of the field of view ranges of at least two image acquisition devices; Based on the trajectory distribution characteristics of the mobile terminal identifier and the trajectory distribution characteristics of the target, the target is associated with the mobile terminal identifier to form a target association pair; For each target association pair, the fused trajectory information of the target is determined based on the first trajectory information of the target in the target association pair and the second trajectory information of the mobile terminal identification code; wherein, the second trajectory information includes the trajectory information of the mobile terminal identification code appearing in the tracking area and outside the tracking area during the tracking period.

2. The method according to claim 1, characterized in that, Based on the trajectory distribution characteristics of the mobile terminal identifier and the trajectory distribution characteristics of the target, the target is associated with the mobile terminal identifier to form a target association pair, including: The number of times the mobile terminal identification code appears in the tracking area during the tracking period is counted based on the trajectory distribution characteristics of the mobile terminal identification code. Based on the frequency of occurrence of the mobile terminal identifier and the trajectory distribution characteristics of the target, the target is associated with the mobile terminal identifier to form a target association pair.

3. The method according to claim 2, characterized in that, During the tracking period, the mobile terminal identification code detection device detects the mobile terminal identification code within the tracking area to determine the mobile terminal identification code appearing in the tracking area, including: For each image acquisition device, determine the sub-tracking time period in which the target appears within the field of view of the image acquisition device; Based on the mobile terminal identification code detection device, the mobile terminal identification codes that appear within the field of view during the sub-tracking period are detected, and the set of mobile terminal identification codes corresponding to the sub-tracking period is determined. Accordingly, based on the distribution characteristics of the mobile terminal identification code, the number of times the mobile terminal identification code appears in the tracking area during the tracking period is statistically analyzed, including: Iterate through the set of mobile terminal identifiers corresponding to each sub-tracking period, and detect the number of sets of mobile terminal identifiers that contain the same mobile terminal identifier, which is taken as the number of times that mobile terminal identifier appears.

4. The method according to claim 2, characterized in that, Based on the frequency of occurrence of the mobile terminal identifier and the trajectory distribution characteristics of the target, the target is associated with the mobile terminal identifier to form a target association pair, including: If only one target appears in the tracking area during the tracking period, the mobile terminal identifier that appears most frequently is associated with the target to form a target association pair.

5. The method according to claim 1, characterized in that, Based on the trajectory distribution characteristics of the mobile terminal identifier and the trajectory distribution characteristics of the target, the target is associated with the mobile terminal identifier to form a target association pair, including: The trajectory distribution characteristics of the mobile terminal identification code and the trajectory distribution characteristics of the target are matched to determine the matching degree between each mobile terminal identification code and each target. The mobile terminal identifier with the highest matching degree is associated with the target to form a target association pair.

6. The method according to claim 5, characterized in that, Matching the trajectory distribution features of the mobile terminal identifier with the trajectory distribution features of the target to determine the matching degree between each mobile terminal identifier and each target includes: The mobile terminal identifier and the target are matched based on the time dimension trajectory distribution features and the spatial dimension trajectory distribution features. The mobile terminal identifier and target that match the time dimension trajectory distribution features and the spatial dimension trajectory distribution features most frequently are identified as having the highest matching degree.

7. The method according to claim 1, characterized in that, After associating the target with the mobile terminal identifier based on the trajectory distribution characteristics of the mobile terminal identifier and the trajectory distribution characteristics of the target to form a target association pair, the method further includes: For the mobile terminal identification code in the target association pair, traverse each adjacent field of view of at least two image acquisition devices, and determine the continuity score of the mobile terminal identification code based on the occurrence of the mobile terminal identification code in the adjacent field of view. For the target in the target association pair, obtain the matching similarity probability of matching the same target in target images acquired within adjacent fields of view; Based on the continuity score and the matching similarity probability, the matching score of the target association pair is determined, and the target association pair is verified based on the matching score.

8. The method according to claim 7, characterized in that, Based on the occurrence of the mobile terminal identification code within adjacent fields of view, a continuity score for the mobile terminal identification code is determined, including: The continuity score determined when the result is that the mobile terminal identification code is detected in all adjacent fields of view is higher than the continuity score determined when the result is that the mobile terminal identification code is not detected in at least one field of view in adjacent fields of view.

9. The method according to claim 1, characterized in that, Based on the first trajectory information of the target in the target association pair and the second trajectory information of the mobile terminal identifier, the fused trajectory information of the target is determined, including: For the first trajectory information and the second trajectory information under the same coordinate system, the first trajectory information and the second trajectory information are timestamped. The first trajectory information and the second trajectory information aligned with the timestamp are weighted and summed to obtain the fused trajectory information of the target; wherein, if the location information corresponding to the timestamp in the first trajectory information does not exist, the weight of the location information corresponding to the timestamp in the first trajectory information is reset to 0.

10. A target trajectory determination device, characterized in that, The device includes: The first trajectory information determination module is used to track the target and determine the first trajectory information of the target based on image data collected by at least two image acquisition devices; A mobile terminal identification code detection module is used to detect mobile terminal identification codes in a tracking area based on a mobile terminal identification code detection device during a tracking period, and to determine the mobile terminal identification codes appearing in the tracking area; wherein, the tracking period is the time period from the first detection of the target by at least two image acquisition devices to the last detection of the target; and the tracking area is the union of the field of view ranges of at least two image acquisition devices. The association module is used to associate the target with the mobile terminal identifier based on the trajectory distribution characteristics of the mobile terminal identifier and the trajectory distribution characteristics of the target, to form a target association pair; The trajectory fusion module is used to determine the fused trajectory information of each target association pair based on the first trajectory information of the target in the target association pair and the second trajectory information of the mobile terminal identification code; wherein, the second trajectory information includes the trajectory information of the mobile terminal identification code appearing in the tracking area and outside the tracking area during the tracking period.

11. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform a target trajectory determination method according to any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the target trajectory determination method according to any one of claims 1-9.

13. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the target trajectory determination method as described in any one of claims 1-9.

Images