Target trajectory tracking method and device, storage medium and electronic equipment

Abstract

The invention discloses a target trajectory tracking method and device, a storage medium and electronic equipment, and is applied to a distributed network, and the method comprises the steps: obtaining the first state information of a trajectory tracking target when the trajectory tracking target enters the sensing range of a first base station, and transmitting the first state information to a second base station, so as to obtain the second state information. Wherein the second base station is an adjacent base station of the first base station determined in the distributed network according to topological information of the first base station, the first state information is state information generated by the trajectory tracking target based on the first base station, and the second state information is state information generated by the trajectory tracking target based on the second base station. And fusing the first state information and the second state information to generate fused trajectory data of the trajectory tracking target. According to the technical scheme, stable tracking of the trajectory tracking target under the non-line-of-sight condition can be achieved, the trajectory precision and the system robustness can be improved, and the high-precision positioning requirement is met.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wireless communication, and in particular to a target trajectory tracking method and device, a storage medium and an electronic device. BACKGROUND

[0002] Multi-base station cooperative target trajectory tracking technology in an integrated sensing and communication (ISAC) network is an important technical direction in the field of communication and sensing technology fusion. The technology realizes accurate tracking of a moving target through multi-base station cooperation. Among them, the integrated sensing and communication network integrates communication and sensing functions, uses base stations to realize environmental sensing and maintain communication functions, and can perform various operations such as positioning and ranging on target or environmental information; the trajectory tracking technology uses sensors to identify and track the moving trajectory of the target in real time, and the system needs to accurately perceive the position, speed and trajectory information of the target.

[0003] In the process of target trajectory tracking, the communication and sensing functions can be realized by dividing resources by the base station or processing radar point cloud data. The resource division method of the base station is to divide the resources into two parts for communication and target sensing, and to set a cooperative tracking scheme through a central controller; the processing of radar point cloud data is to match the radar point cloud data with the map point cloud data, convert the coordinates to determine the target area, and then identify the target object.

[0004] However, the cooperative tracking technology based on the central controller is prone to failure, which affects the tracking effect; the technology involving point cloud data processing needs to additionally increase the laser radar equipment, and the system complexity is high; and the above methods cannot realize the fusion of sensing data, resulting in reduced reliability of target trajectory tracking. SUMMARY

[0005] Therefore, the present application provides a target trajectory tracking method, device, storage medium and electronic device to solve the problem of low reliability of target trajectory tracking.

[0006] In a first aspect, the present application provides a target trajectory tracking method applied to a distributed network, comprising:

[0007] In response to a sensing event of a trajectory tracking target, first state information of the trajectory tracking target is obtained; the sensing event is triggered when the trajectory tracking target enters the sensing range of a first base station, and the first state information is state information generated by the trajectory tracking target based on the first base station;

[0008] sending the first state information to a second base station to obtain second state information; the second base station being a neighboring base station of the first base station determined in the distributed network according to topology information of the first base station, and the second state information being state information generated by the second base station based on the trajectory tracking target;

[0009] fusing the first state information and the second state information to generate fused trajectory data of the trajectory tracking target.

[0010] In the above method, the multi-base station state information is fused through the cooperative sensing and information interaction of the neighboring base stations in the distributed network, which not only effectively improves the accuracy and reliability of the target trajectory tracking, avoids the limitations and error accumulation of single base station observation, but also realizes continuous tracking of the target during cross-region movement by taking advantage of the topology of the distributed network, reduces data transmission pressure and delay, enhances the adaptability and robustness of the system in complex environments, and balances the tracking performance and efficient use of network resources.

[0011] Optionally, obtaining the first state information of the trajectory tracking target comprises:

[0012] detecting position data of the trajectory tracking target, the position data comprising at least one of distance, azimuth, altitude and moving speed of the trajectory tracking target relative to the first base station;

[0013] calculating three-dimensional data according to the position data, the three-dimensional data comprising three-dimensional position and motion parameters of the trajectory tracking target;

[0014] generating identification information of the trajectory tracking target according to the three-dimensional data;

[0015] performing encrypted storage on the three-dimensional data and the identification information to generate encrypted data;

[0016] reading the encrypted data to obtain the first state information.

[0017] In the above method, the position data of the trajectory tracking target is detected and the corresponding three-dimensional information is calculated, and unique identification and encrypted storage are combined, which not only provides accurate data for subsequent cooperative tracking, but also guarantees information security and lays a solid foundation for trajectory fusion.

[0018] Optionally, the method further comprises:

[0019] obtaining topology information of the first base station in the distributed network, and detecting cell awareness state of base station cells in the distributed network;

[0020] establishing a topology network model according to the topology information and the cell awareness state;

[0021] performing weighted processing on the topological network model to obtain weights of base station cells in the distributed network;

[0022] querying a target cell according to the weights, the target cell being a base station cell with a weight being a preset value;

[0023] marking a base station of the target cell as the second base station;

[0024] In the above method, the weighted network model is constructed through the topological information and the perception state, the cooperative base stations are accurately screened and information is transmitted, efficient and targeted base station cooperation is ensured, and the accuracy and efficiency of perception data interaction are improved.

[0025] Optionally, the performing of the weighted processing on the topological network model comprises:

[0026] calculating a comprehensive weight of the base station cell, the comprehensive weight comprising a distance weight and an azimuth weight of a base station in the base station cell relative to the first base station;

[0027] performing normalization processing on the comprehensive weight to generate the weights of the base station cells in the distributed network.

[0028] In the above method, the comprehensive weight is calculated and normalized through the distance and the azimuth, the priority of base station cooperation is accurately quantified, and the targeting and efficiency of cooperative perception are improved.

[0029] Optionally, the sending of the first state information to the second base station comprises:

[0030] sending the first state information to the second base station through a perception function logical interface of the first base station and the second base station; the perception function logical interface is used for data transmission between base stations in the distributed network.

[0031] In the above method, the cooperative perception of each base station in the distributed network is realized through the perception function logical interface.

[0032] Optionally, the fusing of the first state information and the second state information comprises:

[0033] establishing a discrete-time model of the trajectory tracking target, the discrete-time model comprising a discrete-time state equation and a measurement equation of the trajectory tracking target;

[0034] generating an optimal weight matrix based on the discrete-time model, the optimal weight matrix being used to describe a minimum state estimation covariance of the base stations in the distributed network; the optimal weight matrix is generated according to measurement accuracy, topological distance and relative azimuth of the base stations in the distributed network;

[0035] update state information of the first base station and the second base station according to the optimal weight matrix and the Kalman gain to generate update information;

[0036] generate the fused trajectory data through the update information.

[0037] In the method, the optimal weight matrix is generated through construction of a discrete-time model, the base station state is updated in combination with the Kalman gain, and the fused trajectory is generated, so that the trajectory tracking precision and stability can be effectively improved. The optimal weight matrix fuses the base station measurement precision, the topological distance and the azimuth angle factor, so that the state estimation is more accurate, and the fused trajectory reliability is improved.

[0038] Optionally, after fusing the first state information and the second state information, the method further includes:

[0039] reading fused trajectory data of a trajectory tracking target in the distributed network;

[0040] predicting a trajectory position of the trajectory tracking target based on the fused trajectory data to generate predicted trajectory data.

[0041] In the method, the target position is predicted based on the fused trajectory data, and the predicted trajectory data is generated, so that the target motion trend can be grasped in advance, and the foresight and continuity of the trajectory tracking are enhanced.

[0042] In a second aspect, the application provides a target trajectory tracking device applied to a distributed network, including:

[0043] a perception module configured to acquire first state information of a trajectory tracking target in response to a perception event of the trajectory tracking target; the perception event is triggered when the trajectory tracking target enters a perception range of a first base station, and the first state information is state information generated by the trajectory tracking target based on the first base station;

[0044] a coordination module configured to send the first state information to a second base station to obtain second state information; the second base station is an adjacent base station of the first base station determined in the distributed network according to topological information of the first base station, and the second state information is state information generated by the trajectory tracking target based on the second base station;

[0045] a fusion module configured to fuse the first state information and the second state information to generate fused trajectory data of the trajectory tracking target.

[0046] In a third aspect, the application provides a computer readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the method of the first aspect.

[0047] In a fourth aspect, the present application provides an electronic device, comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, and the processor implements the method of the first aspect when executing the computer program.

[0048] In a fifth aspect, the present application provides a computer program product having a computer program stored thereon, and the computer program product implements the method of the first aspect when executed by a processor.

[0049] From the above technical solutions, the target trajectory tracking method, device, storage medium and electronic device provided by the present application are applied to a distributed network, and the method comprises the following steps: when a trajectory tracking target enters the sensing range of a first base station, acquiring first state information of the trajectory tracking target, and sending the first state information to a second base station to obtain second state information. The second base station is an adjacent base station of the first base station determined in the distributed network according to the topology information of the first base station, the first state information is state information generated by the trajectory tracking target based on the first base station, and the second state information is state information generated by the trajectory tracking target based on the second base station. The first state information and the second state information are fused to generate fused trajectory data of the trajectory tracking target. By applying the technical solutions of the present application, stable tracking of the trajectory tracking target under non-line-of-sight conditions can be achieved, the trajectory accuracy and system robustness can be improved, and the high-precision positioning requirement can be met.

[0050] The above description is only a summary of the technical solutions of the present application. In order to more clearly understand the technical means of the present application, the content of the specification can be implemented, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0051] The drawings incorporated into the specification and forming part of the specification, show embodiments consistent with the present application, and together with the specification, serve to explain the principles of the present application.

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiment or prior art description will be briefly introduced as follows. Obviously, for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0053] Figure 1 The architecture schematic diagram of the distributed network provided by the embodiments of the present application is shown;

[0054] Figure 2 The flow schematic diagram of a target trajectory tracking method provided by the embodiments of the present application is shown;

[0055] Figure 3 Fig. 1 shows a flowchart of a process of tracking a target by a first base station according to an embodiment of the present application;

[0056] Figure 4 Fig. 2 shows a flowchart of a process of cooperative sensing by base stations according to an embodiment of the present application;

[0057] Figure 5 Fig. 3 shows a schematic diagram of a network of distributed integrated sensing base stations according to an embodiment of the present application;

[0058] Figure 6 Fig. 4 shows an example of a sensing node of a base station according to an embodiment of the present application;

[0059] Figure 7 Fig. 5 shows a flowchart of a process of fusing sensing results according to an embodiment of the present application;

[0060] Figure 8 Fig. 6 shows a flowchart of a distributed Kalman filtering algorithm according to an embodiment of the present application;

[0061] Figure 9 Fig. 7 shows a schematic diagram of a device for tracking a target trajectory according to an embodiment of the present application. DETAILED DESCRIPTION

[0062] Embodiments of the present application will be described in detail below with reference to the accompanying drawings. It should be noted that the embodiments and features of the embodiments in the present application can be combined with each other without conflict.

[0063] The integrated sensing network achieves accurate tracking of a moving target through the cooperative work of multiple base stations. In the network, the base stations not only have the basic communication function to maintain normal information transmission and interaction, but also have environmental sensing capabilities to perform diversified operations on the trajectory tracking target or environmental information, such as accurate positioning of the trajectory tracking target position and accurate measurement of the trajectory tracking target distance.

[0064] For the process of tracking a trajectory tracking target, in some embodiments, a multi-target cooperative tracking strategy is set among the base stations by a central controller based on the positions of the trajectory tracking targets uploaded by the base stations and the tracking resources allocated by each base station, and the strategy is distributed to each base station for multi-target cooperative tracking. However, the central controller based cooperative tracking is prone to failure, which will affect the tracking effect of the trajectory tracking target.

[0065] To this end, in some embodiments, the region where the trajectory tracking target is located can also be accurately determined by using coordinate conversion technology through matching the point cloud data collected by the radar with the pre-stored map point cloud data, and then the trajectory tracking target can be accurately identified. However, the additional laser radar device in the present embodiment increases the complexity and cost of target tracking.

[0066] Moreover, the improved target tracking methods in the above embodiments cannot realize the fusion of perception data, resulting in a decrease in the reliability of target tracking.

[0067] In order to improve the above problems, some embodiments of the present application provide a target trajectory tracking method, which can be applied to a distributed network, the distributed network comprising a plurality of base stations (i.e., perception base stations), and the distributed network supporting multi-node collaborative perception, which can be represented as a perception-integrated network.

[0068] In some embodiments, the base stations in the distributed network can be divided into signal level, symbol level and data level according to the degree of preprocessing of the original data. Among them, the signal level is the most original signal directly shared, and the cooperation is the most bottom layer; the symbol level is to cooperate after converting the signal into meaningful symbols; the data level can be directly processed into usable data, such as the position and speed of the trajectory tracking target, and then cooperated, which is a higher layer of cooperation.

[0069] In some embodiments, a distributed target tracking method using self-organizing network is used at the data level, and each base station collects the state information of the trajectory tracking target and directly and independently performs local estimation or joint estimation of the measurement information after the inter-base-station collaborative cooperation. In this way, compared with centralized target tracking, distributed target tracking does not require a central node, the reduction of communication links makes the system more stable, and parallel computing and processing are performed by each base station, which can improve the system running speed and enhance the performance of real-time tracking.

[0070] For example, as shown in the distributed network shown in Figure 1 The distributed network supports multi-node collaborative perception. The base stations (i.e., perception base stations) can be cooperatively controlled and data transmitted through the inter-base-station perception function logical interface, and each base station has a corresponding GPS (Global Positioning System) position. Each perception base station can share the perception results of the trajectory tracking target (i.e., the perception target) with each other, and jointly perceive the surrounding environment to form a unified target tracking to obtain the motion trajectory data of the target.

[0071] In order to facilitate differentiation and description, the perception base station that detects the target in the following embodiments of the present application is represented as a first base station, and the remaining adjacent base stations that support collaborative perception are represented as second base stations.

[0072] Correspondingly, in some embodiments, asFigure 2 As shown, the target trajectory tracking method can include:

[0073] S201, in response to a perception event of a target, obtaining first state information of the target.

[0074] The perception event is triggered when the trajectory tracking target enters the perception range of the first base station, and the first state information is generated based on the first base station, for example, based on the three-dimensional position, moving speed, acceleration and other information of the trajectory tracking target calculated by the first base station.

[0075] In some embodiments, the first state information of the trajectory tracking target can include three-dimensional data of the trajectory tracking target relative to the first base station and identification information of the trajectory tracking target. The three-dimensional data can include three-dimensional position and motion parameters of the trajectory tracking target, and the identification information is a unique identification of the trajectory tracking target in the distributed network. For example, the motion parameters can include acceleration, moving speed, etc.

[0076] To further illustrate the implementation process of the above embodiments, in some embodiments, as Figure 3 As shown, obtaining the first state information of the trajectory tracking target (i.e., step S201) can include:

[0077] S11, detecting position data of the trajectory tracking target.

[0078] The position data of the trajectory tracking target is detected according to the position of the trajectory tracking target relative to the first base station, i.e., in some embodiments, the position data includes at least one of the distance, azimuth, altitude and moving speed of the trajectory tracking target relative to the first base station.

[0079] S12, calculating three-dimensional data according to the position data.

[0080] After detecting the position data of the trajectory tracking target relative to the first base station, the corresponding three-dimensional data can be calculated according to the position data. The three-dimensional data can include three-dimensional position and motion parameters of the trajectory tracking target.

[0081] In some embodiments, the position data and three-dimensional data of the trajectory tracking target are detected or calculated by receiving echo signals of the trajectory tracking target.

[0082] S13, generating identification information of the trajectory tracking target according to the three-dimensional data.

[0083] After determining the three-dimensional data of the trajectory tracking target, the trajectory tracking target is uniquely identified, and the identification information (i.e., identification number) corresponding to the trajectory tracking target is generated. The identification number is a unique identification of the trajectory tracking target in the distributed network.

[0084] In some embodiments, when generating the identification information of the track tracking target, the current timestamp, the cell global identifier (CGI) of the base station in the distributed network, and the incremental number of the base station can be combined as the identification information of the track tracking target. For example, the format of the identification information can be timestamp+base station cell identifier+incremental number.

[0085] S14, performing encrypted storage on the three-dimensional data and the identification information to generate encrypted data.

[0086] After calculating the three-dimensional data of the track tracking target and the corresponding identification information, the three-dimensional data and the identification information are encrypted, and the encrypted data is stored to ensure the security of network data transmission.

[0087] S15, reading the encrypted data to obtain first state information.

[0088] For the encrypted storage of the three-dimensional data and the identification information, in some embodiments, the encryption method can be symmetric encryption, asymmetric encryption, hash encryption, stream cipher or block cipher encryption method.

[0089] Correspondingly, in some embodiments, the decrypted data is read and decrypted in a predetermined manner to obtain the corresponding first state information.

[0090] Based on the above embodiments, for example, when the track tracking target enters the sensing range of the first base station, the distance, azimuth, height, and moving speed of the track tracking target relative to the first base station are obtained, and the three-dimensional data such as the three-dimensional position and acceleration of the track tracking target are calculated according to the above information. The track tracking target is uniquely identified, and an identification number is generated, which is composed of the following parts: timestamp+base station cell identifier+incremental number. The three-dimensional data and the identification information of the track tracking target are encrypted, and the encrypted information is stored for network transmission.

[0091] As can be seen from the above embodiments, in the sensing mode of the base station of the integrated sensing network (distributed network) in the embodiments of the present application, when it is monitored that the track tracking target enters the sensing range of the base station, the initial state information of the track tracking target is obtained by receiving the echo signal of the track tracking target and the track tracking target is identified.

[0092] S202, sending the first state information to the second base station to obtain second state information.

[0093] The second base station is a neighboring base station of the first base station determined in the distributed network according to the topological information of the first base station; and the second state information is generated by the second base station based on the track tracking target.

[0094] To further illustrate the implementation process of the above embodiments, in some embodiments, as shown in Figure 4 S21, obtaining the topology information of the first base station in the distributed network, and detecting the cell awareness state of the base station cell in the distributed network.

[0095] S21, obtaining the topology information of the first base station in the distributed network, and detecting the cell awareness state of the base station cell in the distributed network.

[0096] In some embodiments, the distributed network is a distributed self-organizing network, which can change with the change of network nodes. In this way, the topology can dynamically change with the nodes without the need of a central controller.

[0097] For example, the integrated sensing network is a distributed network, and the connection topology of each base station node and the inter-node in the network and the bidirectional communication link are as shown in Figure 5 As shown in the figure, when a node joins or exits, the distributed network is updated.

[0098] In some embodiments, the obtained topology information can be manually configured or self-configured base station topology information, and the detected cell awareness state can be determined by reading a specific identification field. For example, the base station cell in the distributed network can be provided with a sensing function identification field, which is used to represent whether the base station cell has a sensing function.

[0099] S22, establishing a topology network model according to the topology information and the cell awareness state.

[0100] After obtaining the topology information, a topology network model can be established based on the distributed network where the base station is located.

[0101] For example, a topology network model containing N base stations is represented as G=(V, E). Wherein, V={1, 2, …, n} is the set of base stations with sensing function in the integrated sensing network, which is the vertex set, E={e} is the edge set, and e(i, j) represents the adjacent base station j of base station i. It is represented that base station i and adjacent base station j can communicate with each other, and the set of all adjacent base stations of base station i is represented as N k .

[0102] S23, performing weighted processing on the topology network model to obtain the weight of the base station cell in the distributed network.

[0103] After the topology network model is established, the network model can be weighted. The weight of the base station cell obtained by the weighted processing can be a comprehensive weight, such as the comprehensive weight of the distance and the azimuth angle.

[0104] That is, in some embodiments, performing the weighting processing on the topological network model (i.e., step S23) comprises: calculating a comprehensive weight of the base station cell, and performing normalization processing on the comprehensive weight to generate the weight of the base station cell in the distributed network. The comprehensive weight comprises the distance weight of the base station in the base station cell relative to the first base station and the azimuth angle weight.

[0105] That is, by weighting the edges of the topological network model according to the distance between the adjacent base station and the first base station and the azimuth angle of the antenna of the base station cell and performing normalization processing, a weighted network topology graph can be obtained.

[0106] For example, for the calculation of the comprehensive weight, ω is defined as the comprehensive weight, and:

[0107] ω = k1e d +k2cos(Δθ)

[0108] wherein e d is a distance weight function, d in e d is the actual distance between the adjacent base station and the first base station, cos(Δθ) is an azimuth angle weight function, and Δθ is the relative azimuth angle difference between the two base station antennas; when the two antennas are completely aligned, the weight is the largest; the greater the angle difference, the smaller the weight; k1 and k2 are weight factors corresponding to the respective weights.

[0109] For the normalization processing, the minimum value ω min and the maximum value ω max of all edge weights are found, and using the minimum-to-maximum normalization, the weights of all edges are compressed into the interval [0, 1], and the expression of the normalized comprehensive weight is:

[0110]

[0111] S24, querying the target cell according to the weight.

[0112] S25, marking the base station of the target cell as a second base station.

[0113] The target cell is a base station cell with a preset weight, and the second base station to be cooperatively sensed can be determined by the weight of each base station cell.

[0114] For the determination of the second base station, in some embodiments, a weighted adjacency matrix is generated through the weighting processing and the normalization processing, and the target cell is queried based on the weighted adjacency matrix to determine the second base station in the distributed network through the target cell.

[0115] For example, the weighted adjacency matrix C of G N (V, E) is defined as C ij ∈ Rm*n Then:

[0116]

[0117] The base station i and the adjacent base station j can communicate with each other equally, so w ij = w ji The weight value of the corresponding edge, all weight values constitute a weight matrix W = [w ij ] ∈ R n*m .

[0118] For example, as Figure 6 shown, Figure 6 is a perception network topology graph composed of 3 base station nodes. After weighting and normalization processing are performed on the distance and azimuth angle between the base stations, the weight matrix C of the collaborative perception network for the perception target is as follows:

[0119]

[0120] S26, sending the first state information to the second base station through the perception function logical interface of the first base station and the second base station.

[0121] The perception function logical interface is used for data transmission between base stations in a distributed network, and the second base station is a base station of a base station cell with a preset weight value. The preset value can be a predefined range. For example, through the perception function logical interface between the base stations, the base station cells with a weight value of 0 are informed to perform collaborative perception; that is, the first state information is sent to the base station cells with a weight value of 0 to realize collaborative perception of the trajectory tracking target.

[0122] From the above embodiments, it can be seen that the collaborative perception strategy in the embodiments of the present application is that: according to the topology information configured manually or configured automatically, such as the inherited adjacent area of the wireless communication function configuration and the base station point-to-point information of the 5G Xn interface generated automatically or configured manually, the base station informs the adjacent base station cells with perception function to perform collaborative perception through the perception function logical interface between the base stations. In some embodiments of the present application, the state information of the trajectory tracking target perceived by the adjacent base station cells with perception function is represented as second state information.

[0123] S203, fusing the first state information and the second state information to generate fusion trajectory data of the trajectory tracking target.

[0124] After the collaborative perception of the first base station and the second base station is performed, the perception result of the trajectory tracking target based on the first base station and the second base station can be obtained, that is, the trajectory data of the trajectory tracking target. At this time, the trajectory data obtained by multiple base stations can be fused to improve the accuracy of target tracking.

[0125] To improve the accuracy, in some embodiments, the first state information and the second state information are fused according to a distributed Kalman filtering algorithm.

[0126] To this end, as Figure 7 shown, in some embodiments, when fusing the state information of the trajectory tracking target perceived by different base stations (i.e., step S203), it can include:

[0127] S31, a discrete-time model of the trajectory tracking target is established.

[0128] The discrete-time model includes a discrete-time state equation and a measurement equation of the trajectory tracking target, and the discrete-time state equation and the measurement equation can be set according to three-dimensional data, position data of the trajectory tracking target.

[0129] For example, the state vector x of the trajectory tracking target is defined as follows:

[0130]

[0131] wherein, represents the three-dimensional position information of the trajectory tracking target t at time k, respectively represent the moving speed of the trajectory tracking target t at time k under x, y, z three-dimensional coordinates, respectively represent the acceleration of the trajectory tracking target t at time k under x, y, z three-dimensional coordinates.

[0132] The discrete-time state equation and the measurement equation of the discrete-time model are described as follows:

[0133]

[0134] wherein, (i = 1, 2, …, N), x is the state vector of the trajectory tracking target, A is the state transition matrix of the trajectory tracking target, v is the system process noise, y i is the measurement value of the i-th base station, C i is the measurement matrix of the i-th base station, w i is the measurement noise of the i-th base station.

[0135] The state transition matrix is defined as follows:

[0136]

[0137] wherein, T is the perception time slot sending period of the base station.

[0138] S32, an optimal weight matrix is generated based on the discrete-time model, and the optimal weight matrix is used to describe the minimum state estimation covariance of the base station in the distributed network.

[0139] The observation noise values of each sensing base station in the cooperative sensing cluster in the integrated sensing network (i.e., a distributed network) are compared comprehensively, the information importance of each base station is divided by the state estimation accuracy, the state estimation covariance of each base station is minimized, and thus an optimal estimation of the cluster or the whole for the trajectory tracking target is obtained.

[0140] For example, the optimization problem is described by the following equation:

[0141]

[0142] wherein P cluster is a covariance matrix of the cooperative sensing base station cluster, and represents the estimation error obtained by the base station after fusing the measurement information of the adjacent base stations. represents the covariance matrix of the i th base station in the cluster in the integrated sensing network. W ij (k) represents the weight matrix between the i th sensing base station and the j th sensing base station in the cluster in the integrated sensing network at the k th moment. When W ij (k) = 0, that is, the adjacent base station j of the i th base station does not participate in the fusion of the cooperative sensing data.

[0143] The optimal weight matrix W is obtained by solving the equation of the above optimization problem, and the importance of the sensing data of each adjacent base station is weighed, so that the cluster covariance matrix of each sensing base station is minimized, and the state estimation tends to be stable and consistent. That is, when the covariance matrix P of each sensing base station in the integrated sensing network changes slightly, the size of the Kalman gain K and the weight W also tends to be a constant value. Only when the topology of the integrated sensing base station network changes, such as increasing or deleting, is it necessary to dynamically optimize and solve the weight matrix W and the Kalman matrix K. Therefore, the weighting method does not increase the additional calculation amount of the sensing base station.

[0144] Correspondingly, the measurement data update of the base station for the trajectory tracking target in the integrated sensing network is represented by the following equation:

[0145]

[0146] wherein, represents the local trajectory data of the base station i without fusion, K i .(k) represents the Kalman gain used for filtering by the base station i, represents the local covariance matrix of the base station i. When i = j, it represents that the information comes from the base station itself; when i ≠ j, it represents that the information comes from the adjacent base station.

[0147] S33, according to the optimal weight matrix and the Kalman gain, the state information of the first base station and the second base station is updated to generate update information.

[0148] After the local state measurement update at the base station, trajectory data exchange is needed between the base stations in the cooperative perception base station cluster. At this time, the data can be updated according to the optimal weight matrix and the Kalman gain.

[0149] In some embodiments, the optimal weight matrix is generated according to the measurement accuracy, topological distance and relative azimuth angle of the base stations in the distributed network.

[0150] Exemplarily, the fusion update equation of the trajectory data in the cooperative perception integrated network is represented as:

[0151]

[0152] P cluster (k)=W(k)·P local (k)·W T (k)

[0153] wherein P cluster (k) is the covariance matrix of the cooperative perception base station cluster k at the moment, is the trajectory data of the cooperative perception base station cluster k at the moment, W ij (k) is the weight matrix.

[0154] S34, generating fusion trajectory data by updating information.

[0155] After updating the state information, the fusion trajectory data can be generated according to the updated trajectory data of the trajectory tracking target, thereby improving the trajectory tracking accuracy and stability.

[0156] In some embodiments, after fusing the first state information and the second state information, the fusion trajectory data of the trajectory tracking target in the distributed network is also read, and the trajectory position of the trajectory tracking target is predicted based on the fusion trajectory data to generate predicted trajectory data.

[0157] In some embodiments, after obtaining the fusion trajectory data of the trajectory tracking target, the fusion trajectory data is also reported to the data center. When generating the predicted trajectory data, the fusion trajectory data can be read in the data center.

[0158] Exemplarily, the prediction update equation of the trajectory tracking target trajectory data in the cooperative perception cluster is represented as:

[0159]

[0160] wherein, is the trajectory prediction data of the trajectory tracking target of the cooperative perception base station cluster, is the prediction covariance matrix of the cooperative perception base station cluster.

[0161] Based on the above embodiments, asFigure 8 As shown, the distributed Kalman filtering algorithm process provided by steps S31-S34 can refer to Figure 8 .

[0162] From the above embodiments, it can be seen that the fusion processing of the trajectory data corresponding to the trajectory tracking target includes that the base station establishes a discrete time model and uses a distributed Kalman filtering algorithm to fuse and splice the trajectory data of each cooperatively perceived base station.

[0163] Based on the improved target trajectory tracking method in the above embodiments, the present embodiment further provides a target trajectory tracking device, as shown in Figure 9 The target trajectory tracking device includes a perception module 901, a cooperation module 902, and a fusion module 903, wherein:

[0164] The perception module 901 is configured to acquire first state information of a trajectory tracking target in response to a perception event of the trajectory tracking target; the perception event is triggered when the trajectory tracking target enters a perception range of a first base station, and the first state information is generated based on the first base station;

[0165] The cooperation module 902 is configured to send the first state information to a second base station to obtain second state information; the second base station is an adjacent base station of the first base station determined in the distributed network according to topology information of the first base station, and the second state information is generated based on the second base station;

[0166] The fusion module 903 is configured to fuse the first state information and the second state information to generate fusion trajectory data of the trajectory tracking target.

[0167] In some embodiments, the perception module 901 is further configured to detect position data of the trajectory tracking target, the position data including at least one of a distance, an azimuth angle, an altitude, and a moving speed of the trajectory tracking target relative to the first base station. Three-dimensional data including a three-dimensional position and a motion parameter of the trajectory tracking target is calculated according to the position data. Identification information of the trajectory tracking target is generated according to the three-dimensional data. The three-dimensional data and the identification information are executed for encrypted storage to generate encrypted data. The encrypted data is read to obtain the first state information.

[0168] In some embodiments, the coordination module 902 is further configured to acquire topology information of the first base station in the distributed network, and detect a cell awareness state of a base station cell in the distributed network; establish a topology network model according to the topology information and the cell awareness state; perform a weighted processing on the topology network model to obtain a weight of the base station cell in the distributed network; query a target cell according to the weight, the target cell being a base station cell with a weight being a preset value; mark a base station of the target cell as the second base station; and send the first state information to the second base station through an awareness function logical interface of the first base station and the second base station, the awareness function logical interface being used for data transmission between the base stations in the distributed network.

[0169] In some embodiments, the coordination module 902 is further configured to calculate a comprehensive weight of the base station cell, the comprehensive weight including a distance weight and an azimuth angle weight of a base station in the base station cell relative to the first base station; and perform a normalization processing on the comprehensive weight to generate the weight of the base station cell in the distributed network.

[0170] In some embodiments, the fusion module 903 is further configured to establish a discrete-time model of the trajectory tracking target, the discrete-time model including a discrete-time state equation and a measurement equation of the trajectory tracking target; generate an optimal weight matrix based on the discrete-time model, the optimal weight matrix being used to describe a minimum state estimation covariance of the base stations in the distributed network; update the state information of the first base station and the second base station according to the optimal weight matrix and a Kalman gain to generate update information; and generate the fusion trajectory data through the update information.

[0171] In some embodiments, the target trajectory tracking device further includes a prediction module configured to read the fusion trajectory data of the trajectory tracking target in the distributed network; and predict a trajectory position of the trajectory tracking target based on the fusion trajectory data to generate prediction trajectory data.

[0172] It should be noted that other corresponding descriptions of the functions of the various functional units involved in the target trajectory tracking device provided in this embodiment can be referred to the corresponding descriptions in the Figure 2 , which will not be described here in detail.

[0173] Based on the above method as shown in Figure 2 , accordingly, the present embodiment also provides a computer readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the above method as shown in Figure 2 .

[0174] Based on the above method as shown in Figure 2Accordingly, this embodiment also provides a computer program product on which a computer program is stored, which, when executed by a processor, implements the above-described method. Figure 2 The method shown.

[0175] Based on this understanding, the technical solution of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as CD-ROM, USB flash drive, mobile hard drive, etc.) and includes several instructions to cause a computer device (such as personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of this application.

[0176] Based on the above, Figure 2 The method shown, and Figure 9 To achieve the above objectives, this application also provides an electronic device, such as a terminal device, in the illustrated virtual device embodiment. This electronic device includes a storage medium and a processor; the storage medium stores a computer program; the processor executes the computer program to achieve the above-described objectives. Figure 2 The method shown.

[0177] Optionally, the aforementioned physical devices may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB interfaces, card reader interfaces, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Wi-Fi interfaces), etc.

[0178] Those skilled in the art will understand that the physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0179] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the aforementioned physical device, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software in the information processing physical device.

[0180] According to the technical scheme, the target trajectory tracking method, device, storage medium and electronic equipment provided by the application can improve the target trajectory tracking accuracy, reduce tracking errors, and improve the stability, reliability, non-line-of-sight perception capability of the integrated network system, and meet the demand for network intelligence.

[0181] Through the description of the above embodiments, those skilled in the art can clearly understand that the application can be implemented by means of software and necessary general hardware platforms, or by hardware. Compared with the prior art, by applying the technical scheme of the embodiment, the parts and samples do not need to be compared one by one, and the defects of parts with different shapes and structures can be effectively detected, the characteristics of complex parts can be quickly adapted, various defects can be efficiently recognized and classified, and the production efficiency, cost and product quality can be improved, which is of great significance.

[0182] It should be noted that, in this document, relational terms such as "first" and "second", and the like, are used solely to distinguish one entity or action from another entity or action, without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element preceded by "comprises... " does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that comprises the recited element.

[0183] The above description is only a specific implementation of the application, which enables those skilled in the art to understand or implement the application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the application. Therefore, the application will not be limited to these embodiments described herein, but will conform to the widest scope consistent with the principles and novel features applied herein.

Claims

1. A target trajectory tracking method characterized by, The method is applied to a distributed network, and comprises: in response to a perception event of a track tracking target, obtaining first state information of the track tracking target; the perception event is triggered when the track tracking target enters the perception range of a first base station, and the first state information is state information generated by the track tracking target based on the first base station; sending the first state information to a second base station to obtain second state information; the second base station is a neighboring base station of the first base station determined in the distributed network according to the topology information of the first base station, and the second state information is state information generated by the track tracking target based on the second base station; fusing the first state information and the second state information to generate fused trajectory data of the track tracking target.

2. The method of claim 1, wherein, The method comprises: detecting position data of the track tracking target, the position data comprising at least one of distance, azimuth, altitude and moving speed of the track tracking target relative to the first base station; calculating three-dimensional data according to the position data, the three-dimensional data comprising three-dimensional position and motion parameters of the track tracking target; generating identification information of the track tracking target according to the three-dimensional data; performing encrypted storage on the three-dimensional data and the identification information to generate encrypted data; reading the encrypted data to obtain the first state information.

3. The method of claim 1, wherein, Further comprising: obtaining topology information of the first base station in the distributed network, and detecting cell perception state of base station cells in the distributed network; establishing a topology network model according to the topology information and the cell perception state; performing weighted processing on the topology network model to obtain weights of base station cells in the distributed network; querying a target cell according to the weights, the target cell being a base station cell with a weight being a preset value; marking a base station of the target cell as the second base station.

4. The method of claim 3, wherein, The method comprises: calculating a comprehensive weight of the base station cell, the comprehensive weight comprising distance weight and azimuth weight of a base station in the base station cell relative to the first base station; performing normalization processing on the comprehensive weight to generate the weights of the base station cells in the distributed network.

5. The method of claim 1, wherein, The method comprises: sending the first state information to the second base station through a perception function logical interface of the first base station and the second base station; the perception function logical interface is used for data transmission between base stations in the distributed network.

6. The method of claim 1, wherein, The method comprises: establishing a discrete time model of the track tracking target, the discrete time model comprising discrete time state equation and measurement equation of the track tracking target; generating an optimal weight matrix based on the discrete time model, the optimal weight matrix being used to describe minimum state estimation covariance of base stations in the distributed network, the optimal weight matrix being generated according to measurement accuracy, topology distance and relative azimuth of base stations in the distributed network; updating state information of the first base station and the second base station according to the optimal weight matrix and the Kalman gain to generate update information; generating the fused trajectory data of the trajectory tracking target through the update information.

7. The method of claim 1, wherein, After fusing the first state information and the second state information, the method further comprises: reading the fused trajectory data of the trajectory tracking target in the distributed network; predicting a trajectory position of the trajectory tracking target based on the fused trajectory data to generate predicted trajectory data.

8. A target trajectory tracking device characterized by comprising: The method is applied to a distributed network, and comprises: a perception module configured to acquire first state information of a trajectory tracking target in response to a perception event of the trajectory tracking target; the perception event is triggered when the trajectory tracking target enters a perception range of a first base station, and the first state information is state information of the trajectory tracking target generated based on the first base station; a coordination module configured to send the first state information to a second base station to obtain second state information; the second base station is a neighboring base station of the first base station determined in the distributed network according to topology information of the first base station, and the second state information is state information of the trajectory tracking target generated based on the second base station; a fusion module configured to fuse the first state information and the second state information to generate fused trajectory data of the trajectory tracking target.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by a processor to implement the method in any one of claims 1 to 7.

10. An electronic device comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, The processor executes the computer program to implement the method in any one of claims 1 to 7.

11. A computer program product having stored thereon a computer program, characterized in that, The computer program product is executed by a processor to implement the method in any one of claims 1 to 7.

Images