Tracking positioning method and apparatus, electronic device, and storage medium

Abstract

Embodiments of the present application disclose a tracking positioning method and device, electronic equipment and storage medium. The method comprises: determining the current three-dimensional point cloud information of at least one to-be-tracked subject; updating the centroid information of each to-be-tracked subject according to the current three-dimensional point cloud information of each to-be-tracked subject; processing the updated centroid information and three-dimensional point cloud information of each to-be-tracked subject based on a Markov random field algorithm to determine the current position information of the to-be-tracked subject. The method solves the problem of high cost caused by the positioning mode based on laying a large number of base stations in the prior art, and achieves the effect of improving the tracking positioning accuracy of the to-be-tracked subject while reducing the tracking positioning cost.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to computer processing technology, and particularly relate to a tracking positioning method and device, electronic equipment and storage medium. BACKGROUND

[0002] In the prior art, tracking positioning of a target object is mainly achieved through wireless positioning, Bluetooth positioning, UWB (Ultra Wideband) positioning and audio positioning. These methods usually need to pre-deploy a large number of base stations in a scene to achieve positioning, and have the problem of high cost. SUMMARY

[0003] Embodiments of the present application provide a tracking positioning method, device, electronic equipment and storage medium to improve the tracking positioning accuracy of a to-be-tracked subject while reducing the tracking positioning cost.

[0004] In a first aspect, embodiments of the present application provide a tracking positioning method, which comprises:

[0005] determining current three-dimensional point cloud information of at least one to-be-tracked subject;

[0006] updating the center of mass information of each to-be-tracked subject according to the current three-dimensional point cloud information of each to-be-tracked subject;

[0007] processing the updated center of mass information and three-dimensional point cloud information of each to-be-tracked subject based on a Markov random field algorithm to determine the current position information of the to-be-tracked subject.

[0008] In a second aspect, embodiments of the present application also provide a tracking positioning device, which comprises:

[0009] a three-dimensional point cloud information determination module configured to determine current three-dimensional point cloud information of at least one to-be-tracked subject;

[0010] a subject center of mass information updating module configured to update the center of mass information of each to-be-tracked subject according to the current three-dimensional point cloud information of each to-be-tracked subject;

[0011] a subject position information determination module configured to process the updated center of mass information and three-dimensional point cloud information of each to-be-tracked subject based on a Markov random field algorithm to determine the current position information of the to-be-tracked subject.

[0012] In a third aspect, embodiments of the present application also provide an electronic device, which comprises:

[0013] one or more processors;

[0014] a storage device configured to store one or more programs,

[0015] When the one or more programs are executed by the one or more processors, the one or more processors implement the tracking positioning method according to any of the embodiments of the present application.

[0016] In a fourth aspect, the embodiments of the present application further provide a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the tracking positioning method according to any of the embodiments of the present application.

[0017] The technical scheme of the embodiments of the present application determines the current three-dimensional point cloud information of at least one to-be-tracked subject, updates the centroid information of each to-be-tracked subject according to the current three-dimensional point cloud information of each to-be-tracked subject, processes the updated centroid information of each to-be-tracked subject based on a Markov random field algorithm, and determines the current position information of the to-be-tracked subject. The technical scheme solves the problem that the positioning mode based on a large number of base stations in the prior art leads to high cost, realizes accurate determination of the centroid position representing the positioning result of the to-be-tracked subject based on the current three-dimensional point cloud information of the to-be-tracked subject, performs precision processing on the centroid information based on the Markov random field algorithm, obtains centroid information with higher precision as the current position information of the to-be-tracked subject, and improves the tracking positioning precision of the to-be-tracked subject while reducing the tracking positioning cost. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical scheme of the exemplary embodiments of the present application, the drawings needed in the description of the embodiments will be briefly introduced. Obviously, the drawings introduced are only a part of the drawings of the embodiments to be described by the present application, and not all the drawings. Those skilled in the art can obtain other drawings according to these drawings without creating creative labor.

[0019] Figure 1 A flowchart of a tracking positioning method provided by the first embodiment of the present application;

[0020] Figure 2 A schematic diagram of a tracking positioning method provided by the second embodiment of the present application;

[0021] Figure 3 A structural block diagram of a tracking positioning device provided by the third embodiment of the present application;

[0022] Figure 4 A structural schematic diagram of an electronic device provided by the fourth embodiment of the present application. DETAILED DESCRIPTION

[0023] The application will be described in further detail below with reference to the drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the application and not to limit the application. In addition, it should be noted that, for the sake of description, only the parts related to the application are shown in the drawings, not all the structures.

[0024] Before introducing the technical solution, the application scenario can be exemplarily described. The technical solution of the present disclosure can be applied in any scenario requiring tracking and positioning, for example, when a subject needs to be tracked and positioned in a vehicle navigation scenario, a traffic management scenario or a logistics tracking scenario, the technical solution can be used to achieve the tracking and positioning.

[0025] Embodiment one

[0026] Figure 1 A flowchart of a tracking and positioning method provided for the first embodiment of the application, the present embodiment can be applicable to real-time tracking and positioning, the method can be executed by the tracking and positioning device in the embodiment of the application, the device can be realized in software and / or hardware, and optionally, realized by an electronic device, which can be a mobile terminal, a PC terminal or a server, etc. The device can be configured in a computing device, and the tracking and positioning method provided in the present embodiment specifically includes the following steps:

[0027] S110, determining the current three-dimensional point cloud information of at least one subject to be tracked.

[0028] The to-be-tracked subject refers to an object that needs to be tracked and positioned, such as a user, a pet, a to-be-delivered object, a traffic barrier, and the like. For example, in a traffic management scenario, there can be multiple subjects. The attribute features of the to-be-tracked subjects can be pre-set according to actual working conditions. The subjects that match the attribute features can be determined as the to-be-tracked subjects based on the attribute features within the range of the positioning device. Alternatively, the positioning device can send electromagnetic wave signals to the subjects, and also receive reflected electromagnetic wave signals, thereby generating electromagnetic wave fluctuations. The subjects with electromagnetic wave fluctuation intensity greater than a certain threshold can be determined as the to-be-tracked subjects. Alternatively, multiple subjects appearing in the scene in real time can be determined as the to-be-tracked subjects. The three-dimensional point cloud information can be understood as data information of points on the surface of an object. The data can include at least one parameter feature such as three-dimensional coordinates, longitude, latitude, distance from the measuring device, altitude, electromagnetic wave reflectivity, and color information. When each three-dimensional point cloud information of the to-be-tracked subject needs to be determined, any one three-dimensional point cloud information of the to-be-tracked subject can be determined as the current three-dimensional point cloud information of the to-be-tracked subject for processing. One of the three-dimensional point cloud information is described as the current three-dimensional point cloud information. It should be noted that after the to-be-tracked subject is determined, the measuring device can be used to detect the to-be-tracked subject in the scene and collect point cloud data of the to-be-tracked subject. For example, the radar device can send electromagnetic wave signals to the to-be-tracked subject, and also receive electromagnetic wave signals reflected by each point of the to-be-tracked subject. Then, the algorithm can be used to process the electromagnetic wave signals emitted to a certain point of the to-be-tracked subject and the corresponding reflected electromagnetic wave signals, calculate the distance and angle between the current point of the to-be-tracked subject, and obtain the point cloud information of the current point, i.e., the current three-dimensional point cloud information. Accordingly, each three-dimensional point cloud information of the to-be-tracked subject in the scene can be obtained.

[0029] It should be noted that before the current three-dimensional point cloud information of the at least one to-be-tracked subject is determined, the to-be-tracked subject is also pre-determined. For example, when the tracking and positioning device tracks the subject, the electromagnetic wave signal can be sent to the subject, and the reflected electromagnetic wave signal can also be received. The data of the two signals can be pre-processed based on the algorithm to determine the subject that needs to be tracked and positioned in the scene. The to-be-tracked subject is determined in the following manner: a linear frequency modulation pulse is emitted based on a pre-deployed millimeter wave radar antenna to determine the intermediate frequency signal of the at least one to-be-screened tracking subject; and the intermediate frequency signal of each to-be-screened tracking subject is processed based on a target Fourier transform to determine the to-be-tracked subject.

[0030] The millimeter wave radar refers to a radar working in a millimeter wave band for detection. Optionally, the millimeter wave radar is a single-chip radar mainly composed of an antenna, a transmitter, a receiver, and a display. The linear frequency modulation pulse can be understood as an electromagnetic wave signal. The target Fourier transform refers to a fast Fourier transform algorithm.

[0031] It should be noted that the millimeter wave radar can be pre-deployed at a specified position in an application scenario. For example, in a vehicle driving scenario, the millimeter wave radar can be pre-deployed in a vehicle for detecting an environment in the vehicle. The millimeter wave radar can also be pre-deployed outside the vehicle for detecting an obstacle or detecting position information of the vehicle. In a traffic management scenario, the millimeter wave radar can be pre-deployed at each traffic intersection for tracking and positioning a vehicle, a pedestrian, or a traffic barrier.

[0032] In an actual application scenario, the pre-deployed millimeter wave radar antenna can emit an electromagnetic wave signal, i.e., a linear frequency modulation pulse, to all subjects in the scenario. At this time, the antenna also receives the reflected linear frequency modulation pulse. The two linear frequency modulation pulses can be processed by a mixer to obtain a mixed electromagnetic wave signal. Accordingly, a corresponding intermediate frequency signal of each subject can be obtained. For example, a linear frequency modulation pulse is emitted by a millimeter wave radar Tx (transport) antenna. When the signal is blocked and reflected by an obstacle subject A and is captured by an Rx (receive) antenna, the Tx signal and the Rx signal are combined by a mixer to generate an intermediate frequency signal. The intermediate frequency signal includes an intermediate frequency signal corresponding to each point position of the obstacle. By sampling the intermediate frequency signal, the intermediate frequency signal of the subject can be transformed and processed by a fast Fourier transform algorithm. The transformed intermediate frequency signal of each point position of the subject can be obtained. The point positions of the intermediate frequency signal less than a preset intermediate frequency signal threshold can be screened out by an algorithm. The screened point positions of the subject can be obtained. Accordingly, the screened subject can be obtained as a to-be-tracked subject.

[0033] It should be noted that after the intermediate frequency signal of each to-be-screened tracking subject is processed by the target Fourier transform, a maximum value algorithm can be used to distinguish the intermediate frequency signal from a noise signal. For example, the intermediate frequency signal of a certain point of the obstacle can be compared with surrounding signals. The signals less than the intermediate frequency signal in the surrounding signals can be considered as noise signals to distinguish the subject from the noise. Accordingly, the noise signal can be screened out to determine the to-be-tracked subject without noise, thereby improving the efficiency of tracking and positioning.

[0034] Optionally, the target Fourier transform includes a range Fourier transform and a radial velocity Fourier transform, and the target Fourier transform is used to process the intermediate frequency signals of each to-be-screened tracking subject to determine the to-be-tracked subject, including: processing the intermediate frequency signals of each to-be-screened tracking subject based on the range Fourier transform to obtain first to-be-processed data; performing radial velocity Fourier transform on the corresponding first to-be-processed data to determine target processing data; processing the target processing data of each to-be-screened tracking subject according to a constant false alarm rate algorithm, and determining the to-be-tracked subject according to the processing result.

[0035] In this embodiment, after the intermediate frequency signals of each to-be-screened tracking subject are collected, the intermediate frequency signals can be processed by the range Fourier transform algorithm, and the processed intermediate frequency signals can be obtained as the first to-be-processed data. The first to-be-processed data can be processed by the radial velocity Fourier transform (Doppler FFT) algorithm, and the processed intermediate frequency signals can be obtained as the target processing data. The target processing data of each to-be-screened tracking subject can be screened by the constant false alarm rate algorithm, and at this time, the noise signals in the target processing data can be screened out, and accordingly, the processed intermediate frequency signal data of each to-be-screened tracking subject can be obtained, and the subject corresponding to the intermediate frequency signal data can be determined as the to-be-tracked subject. For example, in actual application, assuming that the intermediate frequency signals of a to-be-screened tracking subject A are 1, 2, 5, 4, 6, and 3. The intermediate frequency signals can be processed by the range FFT (Fast Fourier Transformation) algorithm, and the first to-be-processed data is output, which is assumed to be 1, 1, 6, 1, 1, and 1. The first to-be-processed data can be processed by the Doppler FFT, and the target processing data is output, which is assumed to be 1, 1, 1, 5, 1, and 1. The constant false alarm rate algorithm can be used to extract the data corresponding to the possible obstacle target points in the target processing data. For example, the constant false alarm rate algorithm can be considered as a maximum value algorithm, assuming that the intermediate frequency signal of the point A of the obstacle is 5, the signals smaller than 5 in the preset range can be considered as noise signals or other interference signals, and can be screened out. Accordingly, the constant false alarm rate algorithm can be used to accurately screen out all noise signals or other interference signals in the intermediate frequency signals of each to-be-screened tracking subject, and the screened tracking subject can be obtained as the to-be-tracked subject.

[0036] It should be noted that the current three-dimensional point cloud information of the at least one to-be-tracked subject can be determined based on processing the intermediate frequency signal of the to-be-tracked subject by using a distance FFT algorithm, and accordingly, the distance information of the point of the to-be-tracked subject can be obtained. The intermediate frequency signal of the to-be-tracked subject can be processed based on an angle FFT algorithm, and accordingly, the angle information of the point of the to-be-tracked subject can be obtained. The distance information and the angle information of the point can be used as the corresponding three-dimensional point cloud information, or the distance information and the angle information of the point can be subjected to spatial coordinate transformation to obtain coordinate-transformed data information as the three-dimensional point cloud information.

[0037] Optionally, the current three-dimensional point cloud information of the at least one to-be-tracked subject is determined by: determining target distance information of each to-be-tracked subject relative to each millimeter wave radar antenna according to the first to-be-processed data of each to-be-tracked subject; processing the target to-be-processed data of each to-be-tracked subject based on an angle Fourier transform to obtain an offset angle of each to-be-tracked subject relative to each millimeter wave radar antenna; and determining the current three-dimensional point cloud information of the to-be-tracked subject according to the offset angle and the target distance information corresponding to each to-be-tracked subject.

[0038] In actual application, after obtaining the first to-be-processed data based on the distance Fourier transform, the first to-be-processed data of the to-be-tracked subject can be retrieved by using an algorithm, and then the distance information of the to-be-tracked subject relative to each millimeter wave radar antenna, i.e., the target distance information, can be determined based on the first to-be-processed data. For example, assuming that the first to-be-processed data of the to-be-tracked subject A is 1, 1, 6, 1, 1, and 1. The target distance can be 6. The target to-be-processed data of each to-be-tracked subject can be processed by using an angle FFT algorithm to obtain an offset angle of each to-be-tracked subject relative to each millimeter wave radar antenna, which can be a horizontal offset angle and a height offset angle. The target distance information, the horizontal offset angle, and the height offset angle can be used as the polar coordinates of each to-be-tracked subject, and then the polar coordinates can be converted to Cartesian coordinates by using an algorithm, and the three-dimensional point cloud information of each to-be-tracked subject can be obtained.

[0039] S120, updating the center of mass information of each to-be-tracked subject according to the current three-dimensional point cloud information of each to-be-tracked subject.

[0040] In actual application, after obtaining the three-dimensional point cloud information of each to-be-tracked subject in the scene, the three-dimensional point cloud information of each to-be-tracked subject can be clustered by using a clustering algorithm. The clustering algorithm can be a DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm, and the clustering result corresponding to each to-be-tracked subject can be obtained. The centroid of each clustering result can be calculated by using an average algorithm, and the centroid can be taken as the centroid position of the to-be-tracked subject. Accordingly, the centroid information of each to-be-tracked subject can be obtained. It should be noted that in an actual application scenario, the millimeter wave radar can be mobile, and the to-be-tracked subject can also be mobile. Accordingly, the centroid information of the to-be-tracked subject is also updated in real time with the target distance information and the offset angle relative to each millimeter wave radar antenna.

[0041] It should also be noted that, in order to improve the accuracy of the clustering result and thus improve the accuracy of determining the centroid position of the to-be-tracked subject, the clustering result and the centroid can be determined comprehensively based on the point cloud quantity of the to-be-tracked subject and the signal reflection intensity corresponding to the point cloud. The reflection intensity can be determined based on a preset surface area size and a reflection signal energy. Different materials absorb different frequency-modulated pulses, and the reflection intensity information is also different. Accordingly, the reflection intensity information is different, and the material category is also different, so as to obtain a more accurate clustering result based on the category information.

[0042] Optionally, the centroid information of each to-be-tracked subject is updated according to the current three-dimensional point cloud information of each to-be-tracked subject, including: the centroid information of the corresponding to-be-tracked subject is updated according to the point cloud density information and the point cloud intensity information of the current three-dimensional point cloud.

[0043] The point cloud intensity information refers to the frequency-modulated pulse reflection intensity corresponding to the point cloud.

[0044] In actual application, after obtaining the three-dimensional point cloud in the scene, the three-dimensional point cloud quantity corresponding to each to-be-tracked subject can be calculated by using an algorithm, as the point cloud density information. The point cloud can be clustered by using the point cloud quantity in a certain range being greater than a preset quantity threshold, and the clustering result can be obtained. The centroid of the clustering result can be calculated by using an algorithm, and the centroid can represent the centroid of the tracking target. The signal reflection intensity corresponding to the point of the to-be-tracked subject can also be used to provide category information of the to-be-tracked subject, and the determination of the clustering result is enhanced. In this way, the clustering result corresponding to each to-be-tracked subject can be obtained based on the point cloud density information and the point cloud reflection intensity information. The centroid information of the clustering result can be taken as the centroid position of the to-be-tracked subject, and accordingly, the centroid information of each to-be-tracked subject can be obtained.

[0045] S130, based on the Markov random field algorithm, processing the updated center of mass information and three-dimensional point cloud information of each to-be-tracked subject, to determine the current position information of the to-be-tracked subject.

[0046] In this embodiment, the three-dimensional point cloud information corresponding to the center of mass of each to-be-tracked subject can be input into the Markov random field algorithm, and the algorithm can process each information to obtain more accurate three-dimensional point cloud information of the center of mass.

[0047] It should be noted that, in order to improve the accuracy of positioning, the motion speed of the to-be-tracked subject can also be determined based on the collected intermediate frequency signal, so as to obtain the updated position information of the to-be-tracked subject based on the motion speed.

[0048] Optionally, the radial velocity information of each to-be-tracked subject relative to each millimeter wave radar antenna is determined according to the target processing data of each to-be-tracked subject, so as to determine the current position information of the to-be-tracked subject according to the radial velocity information.

[0049] The radial velocity information can be understood as the velocity component of the object motion speed in the line-of-sight direction of the observer, and the observer is the millimeter wave radar.

[0050] In this embodiment, after the first to-be-processed data is processed based on the radial velocity Fourier transform algorithm to obtain the target processing data, the radial velocity information of each to-be-tracked subject relative to each millimeter wave radar antenna can be determined based on the target processing data. The current three-dimensional point cloud information and the radial velocity information corresponding to the center of mass of the to-be-tracked subject can be used as the current position information of the to-be-tracked subject.

[0051] It should be noted that, in order to improve the processing accuracy of the Markov random field, the reflection intensity information of the point cloud can be used as an adjustment parameter in the processing process of the Markov random field, so as to control the interference rate when processing the data of each to-be-tracked subject, and improve the accuracy of the positioning result.

[0052] Optionally, the radial velocity information of each to-be-tracked subject relative to each millimeter wave radar antenna is determined according to the target processing data of each to-be-tracked subject, so as to determine the current position information of the to-be-tracked subject according to the radial velocity information.

[0053] In this embodiment, the three-dimensional point cloud information, the radial velocity and the reflection intensity corresponding to the center of mass of the current to-be-tracked subject can be input into the Markov random field, and the Markov random field can process these information, and more accurate three-dimensional point cloud information and radial velocity corresponding to the center of mass can be obtained, that is, the current position information of the current to-be-tracked subject.

[0054] The technical scheme of the embodiment determines the current three-dimensional point cloud information of at least one to-be-tracked subject, updates the centroid information of each to-be-tracked subject according to the current three-dimensional point cloud information of each to-be-tracked subject, processes the updated centroid information of each to-be-tracked subject based on a Markov random field algorithm, and determines the current position information of the to-be-tracked subject, thereby solving the problem of high cost caused by the positioning mode based on a large number of base stations in the prior art, and achieving the technical effect of accurately determining the centroid position representing the positioning result of the to-be-tracked subject based on the current three-dimensional point cloud information of the to-be-tracked subject, processing the centroid information based on the Markov random field algorithm, obtaining centroid information with higher precision as the current position information of the to-be-tracked subject, improving the tracking and positioning precision of the to-be-tracked subject, and reducing the tracking and positioning cost.

[0055] Embodiment Two

[0056] As an optional embodiment of the above embodiment, Figure 2 FIG. 1 is a schematic diagram of a tracking and positioning method according to Embodiment Two of the present application. Specifically, refer to the following specific content.

[0057] For example, Figure 2 The Tx (transport) antenna of the low-cost single-chip millimeter wave radar emits a linear frequency modulation pulse, the signal is blocked and reflected by an obstacle and captured by the Rx (receive) antenna, the Tx signal and the Rx signal are combined by a mixer to generate an intermediate frequency signal. The intermediate frequency signal is sampled and processed by distance FFT (Fast Fourier Transformation) to obtain first to-be-processed data, and the distance of the obstacle is determined based on the first to-be-processed data. The first to-be-processed data is processed by Doppler FFT to obtain target processing data, and the radial velocity of the obstacle is determined based on the target processing data. The target processing data is processed by a constant false alarm rate algorithm to extract possible obstacle targets, i.e., to-be-tracked subjects. The target processing data is processed by angle FFT, and the angle of the to-be-tracked subject is determined based on the target processing data. The angle and distance of the to-be-tracked subject can be used as the polar coordinates of the to-be-tracked subject, and the polar coordinates of the to-be-tracked subject can be converted into Cartesian coordinates to generate three-dimensional point cloud information of the to-be-tracked subject. After obtaining the three-dimensional point cloud in the scene, the point cloud is clustered by using the density information and the reflection intensity information of the point cloud, and the centroid of the clustering result is calculated as the centroid position of the tracking target. The three-dimensional point cloud information, the radial velocity, and the reflection intensity corresponding to the centroid are input into the Markov random field to obtain a more accurate tracking position and velocity.

[0058] The technical scheme of the embodiment determines current three-dimensional point cloud information of at least one to-be-tracked subject, updates centroid information of each to-be-tracked subject according to the current three-dimensional point cloud information of each to-be-tracked subject, processes the updated centroid information of each to-be-tracked subject based on a Markov random field algorithm, and determines current position information of the to-be-tracked subject, thereby solving the problem of high cost caused by the positioning mode based on a large number of base stations in the prior art, accurately determining the centroid position representing the positioning result of the to-be-tracked subject based on the current three-dimensional point cloud information of the to-be-tracked subject, performing precision processing on the centroid information based on the Markov random field algorithm, obtaining centroid information with higher precision as the current position information of the to-be-tracked subject, and improving the tracking positioning precision of the to-be-tracked subject while reducing the tracking positioning cost.

[0059] Embodiment three

[0060] Figure 3 A structural block diagram of a tracking positioning device is provided for the third embodiment of the application. The device comprises a three-dimensional point cloud information determination module 310, a subject centroid information updating module 320, and a subject position information determination module 330.

[0061] The three-dimensional point cloud information determination module 310 is configured to determine current three-dimensional point cloud information of at least one to-be-tracked subject. The subject centroid information updating module 320 is configured to update centroid information of each to-be-tracked subject according to the current three-dimensional point cloud information of each to-be-tracked subject. The subject position information determination module 330 is configured to process the updated centroid information and three-dimensional point cloud information of each to-be-tracked subject based on a Markov random field algorithm, and determine current position information of the to-be-tracked subject.

[0062] The technical scheme of the embodiment determines current three-dimensional point cloud information of at least one to-be-tracked subject, updates centroid information of each to-be-tracked subject according to the current three-dimensional point cloud information of each to-be-tracked subject, processes the updated centroid information of each to-be-tracked subject based on a Markov random field algorithm, and determines current position information of the to-be-tracked subject, thereby solving the problem of high cost caused by the positioning mode based on a large number of base stations in the prior art, accurately determining the centroid position representing the positioning result of the to-be-tracked subject based on the current three-dimensional point cloud information of the to-be-tracked subject, performing precision processing on the centroid information based on the Markov random field algorithm, obtaining centroid information with higher precision as the current position information of the to-be-tracked subject, and improving the tracking positioning precision of the to-be-tracked subject while reducing the tracking positioning cost.

[0063] On the basis of the above device, the device can further comprise a to-be-tracked subject determination module. The to-be-tracked subject determination module comprises an intermediate frequency signal determination unit and a to-be-tracked subject determination unit.

[0064] an intermediate frequency signal determination unit, configured to determine intermediate frequency signals of the at least one to-be-screened tracking subject by transmitting a linear frequency modulation pulse based on a pre-deployed millimeter wave radar antenna;

[0065] a to-be-tracked subject determination unit, configured to determine a to-be-tracked subject by processing the intermediate frequency signals of each to-be-screened tracking subject based on a target Fourier transform.

[0066] In the above device, optionally, the target Fourier transform includes a range Fourier transform and a radial velocity Fourier transform, and the to-be-tracked subject determination unit includes a first to-be-processed data determination subunit, a target processed data determination subunit, and a to-be-tracked subject determination subunit.

[0067] The first to-be-processed data determination subunit is configured to process the intermediate frequency signals of each to-be-screened tracking subject based on the range Fourier transform to obtain first to-be-processed data.

[0068] The target processed data determination subunit is configured to determine target processed data by performing the radial velocity Fourier transform on the corresponding first to-be-processed data.

[0069] The to-be-tracked subject determination subunit is configured to process the target processed data of each to-be-screened tracking subject according to a constant false alarm rate algorithm, and determine a to-be-tracked subject according to a processing result.

[0070] In the above device, optionally, the three-dimensional point cloud information determination module 310 includes a target distance information determination unit, an offset angle acquisition unit, and a three-dimensional point cloud information determination unit.

[0071] The target distance information determination unit is configured to determine target distance information of each to-be-tracked subject relative to each millimeter wave radar antenna based on the first to-be-processed data of each to-be-tracked subject.

[0072] The offset angle acquisition unit is configured to process the target to-be-processed data of each to-be-tracked subject based on an angle Fourier transform to obtain an offset angle of each to-be-tracked subject relative to each millimeter wave radar antenna.

[0073] The three-dimensional point cloud information determination unit is configured to determine current three-dimensional point cloud information of the to-be-tracked subject according to the offset angle and the target distance information corresponding to each to-be-tracked subject.

[0074] In the above device, optionally, the subject centroid information updating module 320 includes a subject centroid information updating unit.

[0075] The subject centroid information updating unit is configured to update centroid information of a corresponding to-be-tracked subject according to point cloud density information and point cloud intensity information of a current three-dimensional point cloud.

[0076] Optionally, based on the above-mentioned device, the main body position information determination module 330 includes a main body position information determination first unit.

[0077] The first unit for determining the subject position information is used to determine the radial velocity information of each subject relative to each millimeter-wave radar antenna based on the target processing data of each subject to be tracked, so as to determine the current position information of the subject to be tracked based on the radial velocity information.

[0078] Optionally, based on the above-mentioned device, the main body position information determination module 330 may include a second unit for determining main body position information.

[0079] The second unit for determining the subject position information is used to determine the current position information of each subject to be tracked by taking the centroid information, radial velocity information, and reflection intensity information of the subject to be tracked.

[0080] The tracking and positioning device provided in the embodiments of the present invention can execute the tracking and positioning method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0081] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of the present invention.

[0082] Example 4

[0083] Figure 4 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Figure 4 A block diagram is shown of an exemplary electronic device 40 suitable for implementing embodiments of the present invention. Figure 4 The electronic device 40 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0084] like Figure 4 As shown, electronic device 40 is represented in the form of a general-purpose computing device. The components of electronic device 40 may include, but are not limited to: one or more processors or processing units 401, system memory 402, and bus 403 connecting different system components (including system memory 402 and processing unit 401).

[0085] Bus 403 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration bus, a processor or local bus using any of a variety of bus architectures. By way of example, these architectures include Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, Enhanced ISA (EISA) bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0086] Electronic device 40 typically includes a variety of computer system readable media. These media can be any available media that is accessible by electronic device 40 and includes both volatile and non-volatile media, removable and non-removable media.

[0087] System memory 402 can include computer system readable media in the form of volatile memory, such as random access memory (RAM) 404 and / or cache memory 405. Electronic device 40 can further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 406 can be provided for reading from and writing to a non-removable, non-volatile magnetic media (not shown and typically called a "hard drive"). Figure 4 Although not shown, a magnetic disk drive can also be utilized in some embodiments to access and read / write from one or more magnetic disk drives (not shown) that can also be part of electronic device 40. As stated above, a disk drive can also be used to read from or write to a temporary non-removable, non-volatile magnetic medium (not shown) included in a removable memory port. Such approaches can also be used with programs written in Java and / or other like computer languages. Figure 4 A disk drive unit 410 can also be used to read from or write to a non-removable, non-volatile magnetic media (not shown). Such approaches can also be used with programs written in Java and / or other like computer languages. An optical disk drive 412 can be used to read from or write to a removable non-volatile media (not shown). Such approaches can also be used with programs written in Java and / or other like computer languages. The drives and their associated computer system readable media can provide non-volatile storage of computer-executable program code, data structures, program modules and other data for electronic device 40. Those skilled in the art will further appreciate that the functionality of the drives can be combined into a single device or the functionality can be separated into several devices.

[0088] Program / utility 408, having a set of programs / modules 407, can be stored in, for example, memory 402 by way of example, such programs includes, but is not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or a combination can include implementation of a network environment. Program modules 407 generally carry out the functions and / or methodologies of embodiments of the present application.

[0089] The electronic device 40 can also communicate with one or more external devices 409, such as a keyboard or pointing device, a display 410, etc.; other devices such as a storage device or an external effects device; and / or one or more devices that enable a user to interact with the electronic device 40; and / or any devices (e.g., a network card, a modem, etc.) that enable the electronic device 40 to communicate with one or more other computing devices. Such communication can occur via an input / output (I / O) interface 411. Still yet, the electronic device 40 can communicate with one or more networks, such as a local area network (LAN), a wide area network (WAN), and / or the Internet, through a network adapter 412. As depicted, the network adapter 412 communicates with the other components of the electronic device 40 via the bus 403. It should be appreciated that the bus 403 represents what can be one or more busses (e.g., an address bus, data bus, and / or control bus) that enables the electronic device 40's various components to communicate with one another. The electronic device 40 can be implemented in a number of different forms, as shown in the figure. For example, it can be implemented using a desktop computer, a laptop computer, a tablet computer, a personal digital assistant (PDA), a cellular telephone, a smart phone, a network appliance, a camera, a hand-held electronic device, a gaming device, a media player, a navigation device, a game console, a television, a satellite radio, a Bluetooth device, a wireless device, a fixed location data unit, and / or any other suitable device. Figure 4 It should be appreciated that the electronic device 40 can include other components not shown in the figure, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc.

[0090] The processing unit 401 performs various functions applications and data processing by running programs stored in the system memory 402, such as implementing the tracking positioning method provided by the embodiments of the present application.

[0091] Embodiment Five

[0092] The embodiment five of the present application also provides a storage medium containing computer executable instructions, which when executed by a computer processor, are used to perform a tracking positioning method. The method comprises:

[0093] determining current three-dimensional point cloud information of at least one to-be-tracked subject;

[0094] updating the center of mass information of each to-be-tracked subject according to the current three-dimensional point cloud information of each to-be-tracked subject;

[0095] processing the updated center of mass information and three-dimensional point cloud information of each to-be-tracked subject based on a Markov random field algorithm to determine the current position information of the to-be-tracked subject.

[0096] The computer storage medium of the embodiments of the present application can adopt any combination of one or more computer readable media. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination thereof. More specific examples (non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus or device.

[0097] The computer readable signal medium can include a data signal propagated in baseband or propagated as a carrier wave, in which computer readable program code is embodied. Such propagated data signals can take a wide variety of forms, including but not limited to electro-magnetic signals, optical signals, or any suitable combination thereof. The computer readable signal medium can also be any computer readable medium that is not a storage medium, that is capable of storing the program for use by or in connection with the instruction execution system, apparatus or device.

[0098] The program code embodied on the computer readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire line, optical fiber cable, RF, etc., or any suitable combination of the above.

[0099] The computer program code for carrying out operations of the embodiments of the present application can be written in one or more programming languages or combinations of languages including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages such as "C" or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0100] Note that the above merely describes preferred embodiments of the present application and the principles of the technology applied. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, modifications and substitutions can be made to the present application without departing from the scope of the present application. Therefore, although the present application has been described in detail through the above embodiments, the present application is not limited to the above embodiments, and can include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. A method of tracking positioning, characterized by, The method comprises the following steps: determining the current three-dimensional point cloud information of at least one to-be-tracked subject; updating the centroid information of each to-be-tracked subject according to the current three-dimensional point cloud information of each to-be-tracked subject; processing the updated centroid information and three-dimensional point cloud information of each to-be-tracked subject based on a Markov random field algorithm to determine the current position information of the to-be-tracked subject; The method further comprises determining the to-be-tracked subject: The determination of the to-be-tracked subject comprises: transmitting a linear frequency modulation pulse based on a pre-deployed millimeter wave radar antenna to determine the intermediate frequency signal of the at least one to-be-screened tracking subject; processing the intermediate frequency signal of each to-be-screened tracking subject based on a target Fourier transform to determine the to-be-tracked subject; wherein the target Fourier transform comprises a distance Fourier transform and a radial velocity Fourier transform; The determination of the current three-dimensional point cloud information of at least one to-be-tracked subject comprises: determining the target distance information of each to-be-tracked subject relative to each millimeter wave radar antenna according to the first to-be-processed data of each to-be-tracked subject; processing the target to-be-processed data of each to-be-tracked subject based on an angle Fourier transform to obtain the offset angle of each to-be-tracked subject relative to each millimeter wave radar antenna; wherein the offset angle is a horizontal offset angle and a height offset angle; determining the current three-dimensional point cloud information of the to-be-tracked subject according to the offset angle and the target distance information corresponding to each to-be-tracked subject.

2. The method of claim 1, wherein, The processing of the intermediate frequency signal of each to-be-screened tracking subject based on a target Fourier transform to determine the to-be-tracked subject comprises: processing the intermediate frequency signal of each to-be-screened tracking subject based on a distance Fourier transform to obtain first to-be-processed data; determining target processing data by subjecting the corresponding first to-be-processed data to the radial velocity Fourier transform; processing the target processing data of each to-be-screened tracking subject according to a constant false alarm rate algorithm, and determining the to-be-tracked subject according to the processing result.

3. The method of claim 1, wherein, The updating of the centroid information of each to-be-tracked subject according to the current three-dimensional point cloud information of each to-be-tracked subject comprises: updating the centroid information of the corresponding to-be-tracked subject according to the point cloud density information and the point cloud intensity information of the current three-dimensional point cloud.

4. The method of claim 1, wherein, Further comprising: determining the radial velocity information of each to-be-tracked subject relative to each millimeter wave radar antenna according to the target processing data of each to-be-tracked subject, so as to determine the current position information of the to-be-tracked subject according to the radial velocity information.

5. The method of claim 4, wherein, The processing of the updated centroid information and three-dimensional point cloud information of each to-be-tracked subject based on a Markov random field algorithm to determine the current position information of the to-be-tracked subject comprises: for each to-be-tracked subject, determining the current position information of the current to-be-tracked subject based on the centroid information, the radial velocity information and the reflection intensity information of the current to-be-tracked subject.

6. A tracking and positioning device, characterized by The method comprises the following steps: a three-dimensional point cloud information determination module for determining the current three-dimensional point cloud information of at least one to-be-tracked subject; a subject centroid information updating module for updating the centroid information of each to-be-tracked subject according to the current three-dimensional point cloud information of each to-be-tracked subject; The main body position information determination module is configured to determine the current position information of the to-be-tracked main body by processing the updated centroid information and three-dimensional point cloud information of each to-be-tracked main body based on a Markov random field algorithm. The device further comprises a to-be-tracked main body determination module. The to-be-tracked main body determination module comprises an intermediate frequency signal determination unit and a to-be-tracked main body determination unit. The intermediate frequency signal determination unit is configured to determine the intermediate frequency signal of the at least one to-be-screened tracked main body based on a pre-deployed millimeter wave radar antenna transmitting a linear frequency modulation pulse. The to-be-tracked main body determination unit is configured to determine the to-be-tracked main body by processing the intermediate frequency signal of each to-be-screened tracked main body based on a target Fourier transform, wherein the target Fourier transform comprises a distance Fourier transform and a radial velocity Fourier transform. The three-dimensional point cloud information determination module comprises a target distance information determination unit, an offset angle acquisition unit, and a three-dimensional point cloud information determination unit. The target distance information determination unit is configured to determine the target distance information of each to-be-tracked main body relative to each millimeter wave radar antenna according to the first to-be-processed data of each to-be-tracked main body. The offset angle acquisition unit is configured to obtain the offset angle of each to-be-tracked main body relative to each millimeter wave radar antenna by processing the target to-be-processed data of each to-be-tracked main body based on an angle Fourier transform, wherein the offset angle is a horizontal offset angle and a height offset angle. The three-dimensional point cloud information determination unit is configured to determine the current three-dimensional point cloud information of the to-be-tracked main body according to the offset angle and the target distance information corresponding to each to-be-tracked main body.

7. An electronic device, comprising: The device comprises: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the tracking positioning method of any one of claims 1-5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the tracking positioning method of any one of claims 1-5.

Images