Data fusion method and system based on road section relay distributed radar layout
By adopting a data fusion method based on section relay distributed radar layout in road traffic monitoring, a Gaussian distribution and random finite set of vehicle status information is constructed, and the data fusion problem of multi-radar nodes is solved, and traffic monitoring of the entire section is realized and improved. Monitoring accuracy and coverage area are provided.
Patent Information
- Application Number
- CN202411337583.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-25
- Publication Date
- 2024-11-15
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Due to the lack of joint data processing and data fusion technology under the linkage of multi-radar nodes, the existing road traffic monitoring system has limited traffic monitoring accuracy and coverage area, and it is impossible to achieve effective monitoring of the entire road section.
Using a data fusion method based on the relay distributed radar layout of section relay, the Gaussian distribution and random finite set of vehicle state information are constructed, and the data is predicted and updated using the vehicle motion model and measurement model, and the matching judgment is made based on the preset weight coefficient and probability threshold. , realize real-time processing and fusion analysis of multi-radar node data.
The traffic monitoring of the entire road section is realized, the monitoring accuracy and coverage area are improved, the technical support for data fusion processing is provided, and the effective transmission and coordinated work of radar data is ensured.
Smart Images

Figure CN118968763A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent traffic management, and in particular to a data fusion method and system based on road section relay distributed radar layout. Background Art
[0002] With the development of urbanization and the popularization of transportation, road traffic is becoming increasingly busy, and the demand for traffic management and safety monitoring is becoming more and more urgent. In order to improve traffic safety and smoothness, the transportation department needs to monitor and analyze road traffic conditions in real time so as to take timely measures. Traditional road traffic monitoring methods are mainly based on sensors such as cameras and geomagnetic sensors, but these sensors have some defects. For example, cameras require a lot of bandwidth and storage space, and geomagnetic sensors have low vehicle recognition accuracy.
[0003] Radar is an all-weather sensor that is less affected by the environment and weather. However, due to the lack of technical support for joint data processing and data fusion under the linkage of multiple radar nodes, some existing road traffic monitoring systems based on radar technology usually use a single radar node for road traffic monitoring, which is unable to monitor the entire road section, thus limiting the accuracy and coverage area of existing traffic monitoring. Summary of the invention
[0004] In order to solve the above technical problems, the present invention provides a data fusion method and system based on the section relay distributed radar layout, which can solve the problem that the traffic monitoring accuracy and coverage area are limited due to the inability to achieve data association fusion when multiple radar nodes perform road traffic monitoring.
[0005] To achieve the above object, on the one hand, the present invention provides a data fusion method based on a road section relay distributed radar layout, the method comprising:
[0006] The status information corresponding to different vehicles is obtained by relaying distributed radars at different locations on the road section and Gaussian distribution corresponding to the status information of different vehicles is constructed;
[0007] Construct a random finite set according to the Gaussian distribution corresponding to different vehicle status information;
[0008] The random finite set at the current moment is obtained according to the prediction of the random finite set at the previous moment, and the state information of the vehicle collected by the radar at the current moment is updated according to the state information of the vehicle at the previous moment in the random finite set;
[0009] Determine whether the status information of each vehicle in the random finite set at the current moment matches the status information of the vehicle collected by the radar at the current moment according to the preset weight coefficient and the preset probability threshold;
[0010] If so, the state information of the corresponding vehicle in the random finite set at the current moment is updated according to the state information of the vehicle collected by the radar at the current moment.
[0011] Furthermore, the step of predicting and obtaining the random finite set at the current moment according to the random finite set at the adjacent previous moment includes:
[0012] Based on the vehicle motion model, the current position information and speed information of each vehicle are obtained according to the position information and speed information of each vehicle at the previous moment;
[0013] According to the preset weight function and the current position information and speed information corresponding to each vehicle, the current position information and speed information are combined into a random finite set.
[0014] Furthermore, the step of obtaining the position information and speed information of each vehicle at the previous moment based on the vehicle motion model comprises:
[0015] The position information and speed information at the current moment are obtained according to the coefficient matrix of the motion model corresponding to the vehicle, the process noise of the vehicle position and speed, and the position information and speed information of each vehicle at the previous moment.
[0016] Furthermore, the step of updating and acquiring the vehicle status information collected by the radar at the current moment according to the status information of the adjacent vehicles at the previous moment in the random finite set comprises:
[0017] A measurement model is constructed based on the state information of adjacent vehicles at the previous moment in a random finite set and preset measurement noise;
[0018] The vehicle status information collected by the radar at the current moment is updated and acquired according to the measurement model.
[0019] Furthermore, the method further comprises:
[0020] If the status information of each vehicle in the random finite set at the current moment does not match the status information of the vehicle collected by the radar at the current moment, the status information of the vehicle collected by the radar at the current moment and the identification information of the vehicle are saved in the random finite set at the current moment.
[0021] On the other hand, the present invention provides a data fusion system based on a relay distributed radar layout of a road section, the system comprising: an acquisition unit, for acquiring state information corresponding to different vehicles respectively through radars of relay distributed configuration at different position points on the road section and constructing Gaussian distributions corresponding to the state information of different vehicles respectively;
[0022] A construction unit, used for constructing a random finite set according to Gaussian distributions corresponding to different vehicle status information;
[0023] The acquisition unit is further used to predict and acquire the random finite set at the current moment according to the random finite set at the previous moment, and to update and acquire the state information of the vehicle collected by the radar at the current moment according to the state information of the vehicle at the previous moment in the random finite set;
[0024] A judgment unit, used for judging whether the state information of each vehicle in the random finite set at the current moment matches the state information of the vehicle collected by the radar at the current moment according to a preset weight coefficient and a preset probability threshold;
[0025] The updating unit is used to update the status information of the corresponding vehicle in the random finite set at the current moment according to the status information of the vehicle collected by the radar at the current moment.
[0026] Furthermore, the acquisition unit is specifically used to acquire the position information and speed information of the current moment according to the position information and speed information of each vehicle at the previous moment based on the vehicle motion model; and merge the position information and speed information of each vehicle at the current moment into a random finite set at the current moment according to a preset weight function.
[0027] Furthermore, the acquisition unit is specifically used to acquire the position information and speed information at the current moment based on the coefficient matrix of the motion model corresponding to the vehicle, the process noise of the vehicle position and speed, and the position information and speed information of each vehicle at the previous moment.
[0028] Furthermore, the acquisition unit is specifically used to construct a measurement model based on the state information of adjacent vehicles at the previous moment in the random finite set and preset measurement noise; and update and acquire the state information of the vehicle collected by the radar at the current moment according to the measurement model.
[0029] Furthermore, the acquisition unit is also used to save the status information of the vehicle collected by the radar at the current moment and the identification information of the vehicle into the random finite set at the current moment if the status information of each vehicle in the random finite set at the current moment does not match the status information of the vehicle collected by the radar at the current moment.
[0030] The present invention provides a data fusion method and system based on the relay distributed radar layout of a road section. A random finite set is constructed according to the Gaussian distribution corresponding to different vehicle status information. Then, based on the Gaussian hypothesis filter algorithm of the random finite set, the vehicle status information collected by different radar nodes can be processed and fused and analyzed in real time, thereby providing technical support for data fusion processing for the relay distributed radar layout of the road section, realizing the transmission of radar data fusion results of one area to adjacent areas on both sides, thereby realizing the monitoring of the entire road section, and improving the traffic monitoring accuracy and coverage area. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] Figure 1 It is a flow chart of a data fusion method based on section relay distributed radar layout provided by the present invention;
[0032] Figure 2 It is a structural schematic diagram of a data fusion system based on a road section relay distributed radar layout provided by the present invention;
[0033] Figure 3 This is a schematic diagram of the layout of the road section relay distributed radar provided by the present invention Figure 1 ;
[0034] Figure 4 This is a schematic diagram of the layout of the road section relay distributed radar provided by the present invention Figure 2 ;
[0035] Figure 5 This is a schematic diagram of the layout of the road section relay distributed radar provided by the present invention Figure 3 ;
[0036] Figure 6 This is a schematic diagram of the layout of the road section relay distributed radar provided by the present invention Figure 4 ;
[0037] Figure 7 This is a schematic diagram of the layout of the road section relay distributed radar provided by the present invention Figure 5 . DETAILED DESCRIPTION
[0038] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments.
[0039] Before elaborating on the method steps of the present invention in detail, the radar layout mode adopted in the embodiment of the present invention is first described. The road section relay distributed traffic radar system of the present invention is divided into multiple subsystems, and each subsystem is responsible for monitoring a road section of a certain length. Each subsystem includes multiple radar nodes, a control node and a data processing node. Each radar node is a millimeter wave radar installed at a position such as a road test lamp pole, which is used to send and receive radar signals and complete data preprocessing. The control node is used to control the working mode and data acquisition of each radar node, and can communicate with each radar node wirelessly or wired. The data processing node uses an edge calculator to receive and process the data collected by each radar node, and can track, identify, count, etc. vehicles as needed. Due to the long length of the road section and the limited coverage of a single radar node, the present invention first fuses the data of multiple radars in a certain area, and then uses the signal relay technology to transmit the radar data fusion result of one area to the adjacent areas on both sides, thereby realizing the monitoring of the entire road section. Due to the problems such as signal interference between radar nodes, the present invention adopts multi-node collaborative work technology to enable each radar node to cooperate with each other and jointly complete the monitoring task of road traffic. Specifically, the control node can adjust the observation area and working mode of each radar node according to the specific road condition information, so as to achieve the best monitoring effect.
[0040] For roads with lamp poles, in order to save the cost of erecting poles, the radar module can be directly installed on the side at 5-6m of the lamp pole, and the angle between the radar's tilt angle and the plumb plane is usually 3-6°. The horizontal angle is adjusted according to the width of the road and the field of view of the radar module. The mainstream frequencies of the radar module are 24G, 77G-81G, which can meet the ranging and speed measurement of motor vehicles in scenarios with 2-8 lanes in both directions and a longitudinal distance of 50-200m. In addition, each subsystem is equipped with a corresponding edge controller and edge calculator to process the sensor data. It is generally installed in a pole distribution box or an intersection signal control box, and is mainly responsible for multi-radar spatiotemporal calibration, node control, target detection, tracking and fusion.
[0041] In engineering, the installation of sensors can be adjusted according to the specific road conditions and radar coverage, so that there are appropriate data overlap areas and redundant areas, which can make fusion easier and avoid interference between radars. For wider roads, radars are generally installed on both sides of the road. For narrower roads, they can be configured on only one side. For roads where poles are close, they can also be configured at intervals. The following is a brief introduction to the configuration schemes in different scenarios. For example, Case 1: Figure 3The configuration scheme of bilateral relay radars with the same view in the same direction is shown. This configuration scheme is suitable for scenes with wider roads, where the radars on both sides are facing the same direction. For this arrangement method, after the radars at all points in the section complete data collection, they are sent to the edge calculator, and the radar data of points 1 and 4, points 2 and 5, and points 3 and 6 are fused respectively. Finally, the fusion data of different points are fused for the total fusion of the section, and finally the fusion result of the section is output to the sections on both sides. Note that the radar field of view is usually not visible at 0-20m from the radar pole, so it is necessary to ensure that the radar field of view of points 1 and 4 on the left can cover the radar poles of points 3 and 5 on the right, and the same applies to other positions.
[0042] Case 2: Figure 4 and Figure 5 The figure shows the configuration of the dual-side reverse vision relay radar. Different from the first case, the radars on both sides in this scheme are facing different directions. Figure 4 After the radar data at different points are sent to the edge computer, the staggered points 2 and 4, 3 and 5, etc. are fused. Finally, the three different point data are finally fused and the fusion result of the road section is output. Figure 4 The vehicle enters the field of view of each radar from far to near and establishes a track. The radar direction can also be changed so that the vehicle is captured by the radar at a close distance and travels from near to far, such as Figure 5 shown.
[0043] Case 3: Figure 6 and Figure 7 The configuration scheme of the single-side relay radar is shown. For application scenarios with narrow roads, only a certain number of radars need to be configured on one side to complete the detection and tracking process of the road section targets. For this arrangement method, the radar data of all points on the road section are collected and sent to the edge calculator, and the data of different points need only be fused in sequence. Finally, the fusion data of different points are fused for the total fusion of the road section, and finally the fusion result of the road section is output to the sections on both sides.
[0044] Based on the above radar layout architecture, an embodiment of the present invention provides a data fusion method based on a road section relay distributed radar layout, such as Figure 1 As shown, the following steps are included:
[0045] 101. The status information corresponding to different vehicles is obtained by relaying distributed radars at different locations on the road section, and the Gaussian distribution corresponding to the status information of different vehicles is constructed.
[0046] Specifically, for example, for a relay distributed radar system on a road section, it can detect the position and speed information of different vehicles. Suppose the number of vehicles detected by the radar at time t is N t , the state of each vehicle is determined by its position and speed Represents, where i is the vehicle number. The state of each vehicle is represented as a Gaussian distribution:
[0047]
[0048] in, represents the observation data of the i-th vehicle at time t, P t (i) , P t,xv (i) and P t,xv (i)T is the covariance matrix. The conditional probability distribution is used here, that is, given the observed data H t (i) Under the condition of , the distribution of vehicle state is Gaussian distribution.
[0049] 102. Construct a random finite set according to the Gaussian distribution corresponding to different vehicle status information.
[0050] Specifically, for example, based on the state model of each vehicle in step 1, a random finite set is defined to represent the set of all vehicle states. At time t = 1, the measured value of the vehicle state detected by the radar is used to construct a random finite set to complete the initialization. Assuming that the radar can detect N1 vehicles, the state of each vehicle is represented as a Gaussian distribution, and then these Gaussian distributions are combined into a random finite set:
[0051]
[0052] The Gaussian distribution of each vehicle state is given by the following formula:
[0053]
[0054] 103. The random finite set at the current moment is obtained based on the prediction of the random finite set at the previous adjacent moment, and the state information of the vehicle collected by the radar at the current moment is updated based on the state information of the vehicle at the previous adjacent moment in the random finite set.
[0055] Specifically, for example, at time t>1, the random finite set X at the previous time can be used t-1 To predict the random finite set X at the current moment t The prediction step can be divided into two sub-steps: prediction based on the motion model for each vehicle and prediction update of multiple vehicle states in a random finite set.
[0056] (103.1) For each vehicle, prediction is made based on the motion model, assuming that the vehicle motion follows a linear motion model. Specifically, assuming that the state of the vehicle at time t-1 is x t-1(i) and v t-1 (i) , the state at time t is and Then we have:
[0057] x t (i) =F t x t-1 (i) +G t v t-1 (i) +q t (i)
[0058] v t (i) =H t v t-1 (i) +q t,v (i)
[0059] Among them, F t , G t and H t is the coefficient matrix of the motion model, q t (i) and q t,v (i) They represent the process noise of vehicle position and speed respectively, they are both Gaussian distributions and satisfy:
[0060] w t (i) :N(0,Q t )
[0061] w t,v (i) :N(0,Q t,v )
[0062] Q t and Q t,v are the process noise covariance matrices of position and velocity, which are known constant matrices at each time t.
[0063] (103.2) Prediction update of multiple vehicle states in a random finite set. After each vehicle is predicted based on the motion model, the Gaussian distributions of multiple vehicle states are merged into a random finite set. Specifically, a weight function is used To represent the weight of each vehicle state, to measure the prediction confidence of each vehicle, and these weights together with the corresponding Gaussian distribution form a new random finite set X t :
[0064]
[0065] Among them, N t is the number of vehicles detected at time t.
[0066] Furthermore, after completing the prediction update of the random finite set, the radar data is measured and updated. Assume that at time t, the radar detects m vehicles, and their states are and The measurement noise is r t (j) and The measurement model can be expressed as:
[0067] z t (j) =A t x t-1 (j) +r t (j)
[0068] z t,v (j) =B t v t-1 (j) +r t,v (j)
[0069] r t (j) :N(0,R t (j) )
[0070] r t,v (j) :N(0,R t,v (j) )
[0071] Among them, A t and B t is the coefficient matrix of the measurement model, and is the position and velocity measurement noise covariance matrix.
[0072] For the embodiment of the present invention, the step of predicting and obtaining the random finite set at the current moment based on the random finite set at the adjacent previous moment includes: obtaining the position information and speed information at the current moment based on the position information and speed information of each vehicle at the previous moment based on the vehicle motion model; and merging the position information and speed information at the current moment corresponding to each vehicle into a random finite set at the current moment according to a preset weight function.
[0073] Furthermore, the step of obtaining the current position information and speed information based on the position information and speed information of each vehicle at the previous moment based on the vehicle motion model includes: obtaining the current position information and speed information based on the coefficient matrix of the motion model corresponding to the vehicle, the process noise of the vehicle position and speed, and the position information and speed information of each vehicle at the previous moment.
[0074] For an embodiment of the present invention, the step of updating and acquiring the status information of the vehicle collected by the radar at the current moment according to the status information of the adjacent vehicles at the previous moment in the random finite set includes: constructing a measurement model according to the status information of the adjacent vehicles at the previous moment in the random finite set and preset measurement noise; and updating and acquiring the status information of the vehicle collected by the radar at the current moment according to the measurement model.
[0075] 104. Determine, based on a preset weight coefficient and a preset probability threshold, whether the state information of each vehicle in the random finite set at the current moment matches the state information of the vehicle collected by the radar at the current moment.
[0076] Specifically, for example, for each vehicle state x t (i) ,v t (i) and measure z t (j) ,z t,v (j) Matching is performed according to the weight coefficient And the probability threshold determines whether the match is successful. Use a matching matrix M t To represent the matching relationship, where M i,j =1 indicates that the i-th vehicle state matches the j-th measurement successfully, M i,j =0 means the match fails.
[0077] For each successfully matched vehicle state and measurement, we need to calculate their joint probability distribution, namely:
[0078] p(x t (i) ,v t (i) |X t-1 )=N(x t (i) ,v t (i) ;P t (i,j) )
[0079] in, is the covariance matrix of the joint probability distribution.
[0080] After the vehicle status information is updated, the random finite set of vehicles at time t is recalculated. After calculating the joint probability distribution of all successfully matched vehicle status and measurements, the new random finite set X at time t is finally obtained. t 'as follows:
[0081]
[0082] Among them, each vehicle state and The update can be expressed as:
[0083]
[0084] K t (i,j) is the state gain matrix after the measurement update process, and the calculation method is similar to the Kalman gain matrix. -The weight of each vehicle state The update can be expressed as:
[0085]
[0086] Among them, p D,t (z t (j) ,z t,v (j) ) is the probability density function of the appearance of vehicle j, which can be estimated based on the historical trajectory of the vehicle and the detection range of the radar. In practical applications, this probability density function can be learned using a probabilistic machine learning method. After calculating the weights of all vehicle states, we need to normalize them to ensure that their sum is equal to 1.
[0087] 105. If yes, then update the status information of the corresponding vehicle in the random finite set at the current moment according to the status information of the vehicle collected by the radar at the current moment.
[0088] Furthermore, if the status information of each vehicle in the random finite set at the current moment does not match the status information of the vehicle collected by the radar at the current moment, the status information of the vehicle collected by the radar at the current moment and the identification information of the vehicle are saved in the random finite set at the current moment.
[0089] The present invention provides a data fusion method based on the relay distributed radar layout of a road section. A random finite set is constructed according to the Gaussian distribution corresponding to different vehicle status information. Then, based on the Gaussian hypothesis filter algorithm of the random finite set, the vehicle status information collected by different radar nodes can be processed and fused and analyzed in real time, thereby providing technical support for data fusion processing for the relay distributed radar layout of the road section, realizing the transmission of radar data fusion results of one area to adjacent areas on both sides, thereby realizing the monitoring of the entire road section, and improving the traffic monitoring accuracy and coverage area.
[0090] To implement the method provided by the embodiment of the present invention, the embodiment of the present invention provides a data fusion system based on the layout of the road section relay distributed radar, such as Figure 2 As shown, the system includes: an acquisition unit 21, a construction unit 22, a judgment unit 23, and an update unit 24.
[0091] An acquisition unit 21 is used to acquire status information corresponding to different vehicles through radars in a distributed relay configuration at different locations on the road section and to construct Gaussian distributions corresponding to the status information of different vehicles;
[0092] A construction unit 22, used for constructing a random finite set according to Gaussian distributions corresponding to different vehicle status information;
[0093] The acquisition unit 21 is further used to predict and acquire the random finite set at the current moment according to the random finite set at the previous moment, and to update and acquire the state information of the vehicle collected by the radar at the current moment according to the state information of the vehicle at the previous moment in the random finite set;
[0094] A judgment unit 23, used for judging whether the state information of each vehicle in the random finite set at the current moment matches the state information of the vehicle collected by the radar at the current moment according to a preset weight coefficient and a preset probability threshold;
[0095] The updating unit 24 is configured to update the status information of the corresponding vehicle in the random finite set at the current moment according to the status information of the vehicle collected by the radar at the current moment.
[0096] Furthermore, the acquisition unit 21 is specifically used to acquire the position information and speed information of the current moment according to the position information and speed information of each vehicle at the previous moment based on the vehicle motion model; and merge the position information and speed information of each vehicle at the current moment into a random finite set at the current moment according to a preset weight function.
[0097] Furthermore, the acquisition unit 21 is specifically used to acquire the position information and speed information at the current moment based on the coefficient matrix of the motion model corresponding to the vehicle, the process noise of the vehicle position and speed, and the position information and speed information of each vehicle at the previous moment.
[0098] Furthermore, the acquisition unit 21 is specifically used to construct a measurement model according to the state information of adjacent vehicles at the previous moment in the random finite set and preset measurement noise; and update and acquire the state information of the vehicle collected by the radar at the current moment according to the measurement model.
[0099] Furthermore, the acquisition unit 21 is also used to save the status information of the vehicle collected by the radar at the current moment and the identification information of the vehicle into the random finite set at the current moment if the status information of each vehicle in the random finite set at the current moment does not match the status information of the vehicle collected by the radar at the current moment.
[0100] The present invention provides a data fusion method and system based on the relay distributed radar layout of a road section. A random finite set is constructed according to the Gaussian distribution corresponding to different vehicle status information. Then, based on the Gaussian hypothesis filter algorithm of the random finite set, the vehicle status information collected by different radar nodes can be processed and fused and analyzed in real time, thereby providing technical support for data fusion processing for the relay distributed radar layout of the road section, realizing the transmission of radar data fusion results of one area to adjacent areas on both sides, thereby realizing the monitoring of the entire road section, and improving the traffic monitoring accuracy and coverage area.
[0101] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process can be rearranged without departing from the scope of protection of the present disclosure. The attached method claims present the elements of the various steps in an exemplary order and are not intended to be limited to the specific order or hierarchy described.
[0102] In the above detailed description, various features are grouped together in a single embodiment to simplify the disclosure. This method of disclosure should not be interpreted as reflecting an intention that the embodiments of the claimed subject matter require more features than are clearly stated in each claim. On the contrary, as reflected in the appended claims, the invention is in a state of having less than all the features of the disclosed individual embodiments. Therefore, the appended claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.
[0103] The disclosed embodiments are described above to enable any person skilled in the art to implement or use the present invention. Various modifications of these embodiments are obvious to those skilled in the art, and the general principles defined herein may also be applied to other embodiments without departing from the spirit and scope of the present disclosure. Therefore, the present disclosure is not limited to the embodiments given herein, but is consistent with the broadest scope of the principles and novel features disclosed in this application.
[0104] The above description includes examples of one or more embodiments. Of course, it is impossible to describe all possible combinations of components or methods for the purpose of describing the above embodiments, but it should be recognized by those skilled in the art that the various embodiments may be further combined and arranged. Therefore, the embodiments described herein are intended to cover all such changes, modifications and variations that fall within the scope of protection of the appended claims. In addition, with respect to the term "comprising" used in the specification or claims, the word is covered in a manner similar to the term "including", just as "including," is explained as a transitional word in the claims. In addition, any term "or" used in the specification of the claims is intended to mean "non-exclusive or".
[0105] Those skilled in the art may also understand that the various illustrative logical blocks, units, and steps listed in the embodiments of the present invention may be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly demonstrate the interchangeability of hardware and software, the various illustrative components, units, and steps described above have generally described their functions. Whether such functions are implemented by hardware or software depends on the specific application and the design requirements of the entire system. Those skilled in the art may use various methods to implement the described functions for each specific application, but such implementation should not be understood as exceeding the scope of protection of the embodiments of the present invention.
[0106] The various illustrative logic blocks or units described in the embodiments of the present invention can be implemented or operated by a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field programmable gate array or other programmable logic system, a discrete gate or transistor logic, a discrete hardware component, or any combination of the above. The general-purpose processor can be a microprocessor, and optionally, the general-purpose processor can also be any conventional processor, controller, microcontroller or state machine. The processor can also be implemented by a combination of computing systems, such as a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors combined with a digital signal processor core, or any other similar configuration.
[0107] The steps of the method or algorithm described in the embodiments of the present invention can be directly embedded in hardware, a software module executed by a processor, or a combination of the two. The software module can be stored in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a removable disk, a CD-ROM, or other storage media of any form in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Optionally, the storage medium can also be integrated into the processor. The processor and the storage medium can be arranged in an ASIC, and the ASIC can be arranged in a user terminal. Optionally, the processor and the storage medium can also be arranged in different components in the user terminal.
[0108] In one or more exemplary designs, the above functions described in the embodiments of the present invention can be implemented in hardware, software, firmware or any combination of the three. If implemented in software, these functions can be stored on a computer-readable medium, or transmitted in the form of one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media that facilitate the transfer of computer programs from one place to another. The storage medium can be any available medium that can be accessed by any general or special computer. For example, such computer-readable media can include but are not limited to RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage or other magnetic storage systems, or any other medium that can be used to carry or store program codes in the form of instructions or data structures and other forms that can be read by general or special computers, or general or special processors. In addition, any connection can be appropriately defined as a computer-readable medium, for example, if the software is transmitted from a website site, server or other remote resource through a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL) or wirelessly, such as infrared, wireless and microwave, it is also included in the defined computer-readable medium. The disk and disc include compact disk, laser disk, optical disk, DVD, floppy disk and blue-ray disk. Disks usually copy data magnetically, while discs usually copy data optically with lasers. The above combination can also be included in computer readable media.
[0109] The specific implementations described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation of the present invention and is not intended to limit the protection scope of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.
Claims
1. A data fusion method based on road section relay distributed radar layout, characterized in that: The method comprises: The status information corresponding to different vehicles is obtained by relaying distributed radars at different locations on the road section and Gaussian distribution corresponding to the status information of different vehicles is constructed; Construct a random finite set according to the Gaussian distribution corresponding to different vehicle status information; The random finite set at the current moment is obtained according to the prediction of the random finite set at the previous moment, and the state information of the vehicle collected by the radar at the current moment is updated according to the state information of the vehicle at the previous moment in the random finite set; Determine whether the status information of each vehicle in the random finite set at the current moment matches the status information of the vehicle collected by the radar at the current moment according to the preset weight coefficient and the preset probability threshold; If so, the state information of the corresponding vehicle in the random finite set at the current moment is updated according to the state information of the vehicle collected by the radar at the current moment.
2. The data fusion method based on the road section relay distributed radar layout according to claim 1 is characterized in that: The step of predicting and obtaining the random finite set at the current moment according to the random finite set at the adjacent previous moment comprises: Based on the vehicle motion model, the current position information and speed information of each vehicle are obtained according to the position information and speed information of each vehicle at the previous moment; According to the preset weight function and the current position information and speed information corresponding to each vehicle, the current position information and speed information are combined into a random finite set at the current time.
3. The data fusion method based on the road section relay distributed radar layout according to claim 2 is characterized in that: The step of obtaining the current position information and speed information based on the vehicle motion model according to the position information and speed information of each vehicle at the previous moment comprises: The position information and speed information at the current moment are obtained according to the coefficient matrix of the motion model corresponding to the vehicle, the process noise of the vehicle position and speed, and the position information and speed information of each vehicle at the previous moment.
4. The data fusion method based on the road section relay distributed radar layout according to claim 1 is characterized in that: The step of updating and acquiring the vehicle status information collected by the radar at the current moment according to the status information of the adjacent vehicles at the previous moment in the random finite set comprises: A measurement model is constructed based on the state information of adjacent vehicles at the previous moment in a random finite set and preset measurement noise; The vehicle status information collected by the radar at the current moment is updated and acquired according to the measurement model.
5. The data fusion method based on the road section relay distributed radar layout according to claim 1 is characterized in that: The method further comprises: If the status information of each vehicle in the random finite set at the current moment does not match the status information of the vehicle collected by the radar at the current moment, the status information of the vehicle collected by the radar at the current moment and the identification information of the vehicle are saved in the random finite set at the current moment.
6. A data fusion system based on road section relay distributed radar layout, characterized in that: The system comprises: An acquisition unit, used for acquiring status information corresponding to different vehicles through radars in a distributed relay configuration at different positions on the road section and constructing Gaussian distributions corresponding to the status information of different vehicles; A construction unit, used for constructing a random finite set according to Gaussian distributions corresponding to different vehicle status information; The acquisition unit is further used to predict and acquire the random finite set at the current moment according to the random finite set at the previous moment, and to update and acquire the state information of the vehicle collected by the radar at the current moment according to the state information of the vehicle at the previous moment in the random finite set; A judgment unit, used for judging whether the state information of each vehicle in the random finite set at the current moment matches the state information of the vehicle collected by the radar at the current moment according to a preset weight coefficient and a preset probability threshold; The updating unit is used to update the status information of the corresponding vehicle in the random finite set at the current moment according to the status information of the vehicle collected by the radar at the current moment.
7. The data fusion system based on the road section relay distributed radar layout according to claim 6 is characterized in that: The acquisition unit is specifically used to acquire the current position information and speed information according to the position information and speed information of each vehicle at the previous moment based on the vehicle motion model; and merge the current position information and speed information corresponding to each vehicle at the current moment into a random finite set at the current moment according to a preset weight function.
8. The data fusion system based on the road section relay distributed radar layout according to claim 7 is characterized in that: The acquisition unit is specifically used to acquire the position information and speed information at the current moment based on the coefficient matrix of the motion model corresponding to the vehicle, the process noise of the vehicle position and speed, and the position information and speed information of each vehicle at the previous moment.
9. The data fusion system based on the road section relay distributed radar layout according to claim 6 is characterized in that: The acquisition unit is further specifically used to construct a measurement model according to the state information of adjacent vehicles at the previous moment in the random finite set and the preset measurement noise; and update and acquire the state information of the vehicle collected by the radar at the current moment according to the measurement model.
10. The data fusion system based on the road section relay distributed radar layout according to claim 6 is characterized in that: The acquisition unit is also used to save the status information of the vehicle collected by the radar at the current moment and the identification information of the vehicle into the random finite set at the current moment if the status information of each vehicle in the random finite set at the current moment does not match the status information of the vehicle collected by the radar at the current moment.
Citation Information
Patent Citations
Multi-radar asynchronous data distributed fusion method based on random set theory
CN106896352A
Multi-sensor-based integrated amplitude information fusion method and system
CN108304869A
Passive sonar non-cooperative target line spectrum information fusion method
CN110208808A
Target tracking method for radar networking disorder measurement concentrated fusion
CN110646790A
Over-the-horizon radar multi-target tracking method and system, electronic equipment and medium
CN116400345A
