Target track state switching method and device, electronic equipment and storage medium

Abstract

The invention provides a target track state switching method and device, electronic equipment and a storage medium, and relates to the technical field of target detection, and the method comprises the steps: obtaining a first track converted from a motion state to a target state in a radar detection range, and terminal coordinates corresponding to at least one mobile terminal detected by a WIFI probe; determining a first target confidence coefficient corresponding to the first track based on the measurement data corresponding to the first track; determining a second target confidence coefficient based on a target track coordinate corresponding to the first track and each terminal coordinate; and based on the first target confidence coefficient and the second target confidence coefficient, determining the total confidence coefficient in the target state, and based on the total confidence coefficient, determining a state switching result of the first track. The method can achieve the detection of a shielded target and a static target, and improves the accuracy of target track detection of the millimeter wave radar.

Description

Technical Field

[0001] The present invention relates to the field of target detection technology, and in particular to a target track state switching method, device, electronic equipment and storage medium. Background Art

[0002] In target trajectory detection, a millimeter-wave radar is generally used to transmit a pulse wave signal of a fixed frequency to a moving target, and the track of the moving target is detected and tracked through the Doppler frequency formed by the frequency of the echo signal and the frequency of the transmitted signal.

[0003] However, when the state of a moving target changes, for example, when a moving target changes from a moving state to a stationary state or when the moving target is blocked by other targets, the millimeter-wave radar cannot detect the track states of blocked targets and stationary targets, resulting in low accuracy of target track detection by the millimeter-wave radar. Summary of the invention

[0004] The present invention provides a target track state switching method, device, electronic device and storage medium, which are used to solve the defect of low accuracy of target track detection by millimeter wave radar in the prior art, realize the detection of obscured targets and stationary targets, and improve the accuracy of target track detection by millimeter wave radar.

[0005] The present invention provides a target track state switching method, comprising:

[0006] Acquire a first track that is converted from a motion state to a target state within the radar detection range, and terminal coordinates corresponding to at least one mobile terminal detected by the WIFI probe;

[0007] Determining a first target confidence level corresponding to the first track based on the measurement data corresponding to the first track;

[0008] Determine the second target confidence based on the target track coordinates corresponding to the first track and the coordinates of each terminal; the target track coordinates are the track coordinates corresponding to the last frame before the first track is converted to the target state;

[0009] Based on the first target confidence and the second target confidence, a total confidence in the target state is determined, and based on the total confidence, a state switching result of the first track is determined.

[0010] According to the target track state switching method provided by the present invention, determining the first target confidence corresponding to the first track based on the measurement data corresponding to the first track includes:

[0011] When the target state is a disappeared state, obtaining at least one second track other than the first track within the radar detection range; determining the first target confidence corresponding to the first track based on the measurement data corresponding to each of the first track and the at least one second track; the motion state of the second track does not change;

[0012] When the target state is a stationary state, a first target confidence level corresponding to the first track is determined based on measurement data corresponding to the first track.

[0013] According to the target track state switching method provided by the present invention, determining the first target confidence corresponding to the first track based on the measurement data corresponding to each of the first track and the at least one second track includes:

[0014] For each of the second tracks, determining a first confidence level between the first track and the second track based on the measurement data corresponding to each of the first track and the second track;

[0015] When the number of the second track is equal to 1, determining the first confidence level corresponding to the second track as the first target confidence level corresponding to the conversion of the first track to the target state;

[0016] When the number of the second tracks is greater than 1, the maximum first confidence is determined as the first target confidence corresponding to the conversion of the first track to the target state.

[0017] According to the target track state switching method provided by the present invention, when the target state is a disappearing state, the measurement data includes a radial distance and an azimuth corresponding to the last frame before the first track is converted to the disappearing state;

[0018] The determining, based on the measurement data corresponding to each of the first track and the second track, a first confidence level between the first track and the second track, comprises:

[0019] Determine a first difference between a radial distance of the first track and a radial distance of the second track, and determine a second difference between an azimuth of the first track and an azimuth of the second track;

[0020] A first confidence level between the first track and the second track is determined based on the first difference and the second difference.

[0021] According to the target track state switching method provided by the present invention, when the target state is a stationary state, the measurement data includes the speed, acceleration and radar frame period corresponding to the last frame before the first track is converted to the stationary state;

[0022] The determining, based on the measurement data corresponding to the first track, a first target confidence level corresponding to the first track, comprises:

[0023] A first target confidence level corresponding to the conversion of the first track to the stationary state is determined based on the speed, the acceleration and the radar frame period.

[0024] According to the target track state switching method provided by the present invention, the second target confidence is determined based on the target track coordinates corresponding to the first track and the coordinates of each terminal, including:

[0025] For each terminal coordinate, determining a second confidence level between the first track and the terminal coordinate based on the target track coordinate corresponding to the first track and the terminal coordinate;

[0026] When the number of the terminal coordinates is equal to 1, determining the second confidence as the second target confidence;

[0027] When the number of the terminal coordinates is greater than 1, the maximum second confidence is determined as the second target confidence.

[0028] According to the target track state switching method provided by the present invention, the method further includes:

[0029] Acquire at least two point cloud data within the radar detection range;

[0030] Density clustering is performed on the at least two point cloud data to obtain at least one point cloud cluster;

[0031] For each of the point cloud clusters, when the number of point clouds in the point cloud cluster is greater than or equal to a first preset threshold, determining the coordinates of the center point of the point cloud in the point cloud cluster;

[0032] Based on the coordinates of the center point of the point cloud, determine at least two target terminal coordinates within the neighborhood radius of the point cloud cluster from the terminal coordinates corresponding to each of the at least one mobile terminal, and determine the target terminal coordinates as the initial track coordinates corresponding to the second track;

[0033] In the case where the second track is converted from the motion state to the target state, the second track is determined as the first track, and based on the initial track coordinates, the target track coordinates of the last frame before the first track is converted to the target state are determined.

[0034] The present invention also provides a target track state switching device, comprising:

[0035] An acquisition module, used to acquire a first track converted from a motion state to a target state within a radar detection range, and terminal coordinates corresponding to at least one mobile terminal detected by a WIFI probe;

[0036] A first determination module, configured to determine a first target confidence corresponding to the first track based on measurement data corresponding to the first track;

[0037] A second determination module is used to determine a second target confidence based on the target track coordinates corresponding to the first track and the coordinates of each terminal; the target track coordinates are the track coordinates corresponding to the last frame before the first track is converted to the target state;

[0038] The state switching module is used to determine the total confidence in the target state based on the first target confidence and the second target confidence, and determine the state switching result of the first track based on the total confidence.

[0039] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the target track state switching method described in any one of the above methods is implemented.

[0040] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the target track state switching method as described in any one of the above is implemented.

[0041] The target track state switching method, device, electronic device and storage medium provided by the present invention, after obtaining the first track whose motion state changes within the radar detection range and the terminal coordinates corresponding to at least one mobile terminal detected by the WIFI probe, determine the first target confidence according to the measurement data of the first track to judge whether the motion state of the first track is converted to the target state, then determine the second target confidence in combination with the target track coordinates and each terminal coordinate corresponding to the first track, and determine the total confidence based on the first target confidence and the second target confidence, and determine the state switching result of the first track based on the total confidence, based on the popularity of mobile terminals, combined with the first track and terminal coordinates detected by the radar, improve the accuracy of the judgment result of the motion state of the first track being converted to the target state, thereby improving the accuracy of the millimeter wave radar in detecting target tracks. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 is a flow chart of a target track state switching method provided by an embodiment of the present invention;

[0044] Figure 2 is a schematic diagram of the structure of a target track state switching device provided by an embodiment of the present invention;

[0045] Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] Aiming at the problem that the millimeter wave radar in the prior art cannot detect the target track status of blocked targets and stationary targets, resulting in low accuracy of target track detection by the millimeter wave radar, an embodiment of the present invention provides a target track status switching method. Figure 1 FIG. 1 is a flow chart of a target track state switching method provided by an embodiment of the present invention. Figure 1 As shown, the method includes:

[0048] Step 110: Acquire a first track that is converted from a motion state to a target state within a radar detection range, and terminal coordinates corresponding to at least one mobile terminal detected by a WIFI probe.

[0049] Optionally, the radar detection range is the detection range of the millimeter wave radar, and the detection radius of the radar detection range is affected by factors such as the operating frequency, transmission power and receiving sensitivity of the millimeter wave radar. The operating frequency of the millimeter wave radar is between 30-300GHz, and it has high resolution and anti-interference capabilities in this frequency band. The transmission power determines how far the transmission signal of the millimeter wave radar can be transmitted, and the receiving sensitivity determines how weak the millimeter wave radar can receive the echo signal, which in turn affects the detection radius of the radar detection range.

[0050] Furthermore, the method further comprises:

[0051] Acquire at least two point cloud data within the radar detection range;

[0052] Density clustering is performed on the at least two point cloud data to obtain at least one point cloud cluster;

[0053] For each of the point cloud clusters, when the number of point clouds in the point cloud cluster is greater than or equal to a first preset threshold, determining the coordinates of the center point of the point cloud in the point cloud cluster;

[0054] Based on the coordinates of the center point of the point cloud, determine at least two target terminal coordinates within the neighborhood radius of the point cloud cluster from the terminal coordinates corresponding to each of the at least one mobile terminal, and determine the target terminal coordinates as the initial track coordinates corresponding to the second track;

[0055] In the case where the second track is converted from the motion state to the target state, the second track is determined as the first track, and based on the initial track coordinates, the target track coordinates of the last frame before the first track is converted to the target state are determined.

[0056] Specifically, when the millimeter-wave radar performs target track detection, reflection and scattering occur after sending a transmission signal to the target to be measured within the radar detection range, forming an echo signal. After receiving the echo signal, the millimeter-wave radar processes the echo signal to obtain at least two point cloud data corresponding to each target to be measured within the radar detection range, and each point cloud data is used to characterize the spatial distribution corresponding to each target to be measured. After obtaining each point cloud data, the neighborhood radius and the minimum number of point clouds in the point cloud cluster are pre-set, and all point cloud data are density clustered to obtain at least one point cloud cluster. The point cloud cluster includes point cloud data corresponding to at least one target to be measured. For each point cloud cluster, if the number of point clouds in the point cloud cluster is greater than or equal to the first preset threshold, it can be considered that there are multiple targets to be measured adjacent to each other in the point cloud cluster, and the distance between the multiple targets to be measured is relatively close. At this time, the millimeter-wave radar will mistakenly identify the multiple targets to be measured in the point cloud cluster as a single target to be measured, and track the point cloud cluster to determine the track corresponding to the single target to be measured. Therefore, in the embodiment of the present invention, the coordinates of the point cloud center point corresponding to the point cloud cluster are determined. Based on the popularity of mobile terminals, formula (1) is used to determine at least two target terminal coordinates within the neighborhood radius of the point cloud center point coordinates according to the distance between the terminal coordinates of each mobile terminal and the coordinates of the point cloud center point, and among the at least two target terminal coordinates, the distance between any two target terminal coordinates is greater than the second preset threshold, excluding the situation where a single target to be measured carries multiple mobile terminals. Formula (1) is:

[0057]

[0058] Among them, W c represents the target terminal coordinate set, and W c includes m target terminal coordinates, W represents the terminal coordinate set corresponding to all mobile terminals detected by the WIFI probe, m is an integer greater than 1, x i W c The x-axis coordinate of the i-th target terminal coordinate, y i W c The y-axis coordinate of the i-th target terminal coordinate in , 1≤i≤m, x c Represents the x-axis coordinate of the center point of the point cloud, y c represents the y-axis coordinate of the center point of the point cloud, E represents the neighborhood radius, and w i W c The i-th target terminal coordinates in .

[0059] After determining the target terminal coordinates, the number of targets to be measured included in the point cloud cluster can be determined based on the number of determined target terminal coordinates, and each target terminal coordinate can be used as the initial track coordinate corresponding to each target to be measured, so as to avoid the millimeter wave radar from misdetecting multiple targets to be measured as a single target, and accurately determine the target terminal coordinates of each target to be measured. Afterwards, by monitoring each initial track coordinate, a second track corresponding to each target to be measured is formed, and based on the kinematic relationship, the initial track coordinate is Kalman filtered to gradually determine the predicted position at the next moment. For each second track, if the motion state of the second track changes, that is, the target to be measured changes from a moving state to a disappearing state or a stationary state, the second track with a changed motion state can be determined as the first track, and the track coordinates of the last frame before the state change are determined as the target track coordinates, thereby determining whether the target to be measured corresponding to the first track is blocked or the target to be measured is in a stationary state.

[0060] It should be noted that the above-mentioned second track indicates that the target to be measured has been in motion and the state has not changed. The above-mentioned second preset threshold can be determined according to the average shoulder width of the target to be measured. If the distance between the terminal coordinates corresponding to the two mobile terminals is less than the second preset threshold, it can be considered that the target to be measured carries two mobile terminals. If the distance between the terminal coordinates corresponding to the two mobile terminals is greater than or equal to the second preset threshold, it can be considered that the distance between the two targets to be measured is relatively close and each carries a mobile terminal. The above-mentioned first preset threshold can be determined by the number of point clouds contained in a target to be measured. For example, the first preset threshold can be set to twice the minimum number of point clouds.

[0061] Optionally, density clustering can be performed based on the DBSCAN (Density Based Spatial Clustering of Application with Noise) clustering algorithm or the OPTICS (Ordering Points To Identify the Clustering Structure) clustering algorithm. Taking the DBSCAN clustering algorithm as an example, the specific steps of density clustering are as follows: for each point cloud data, determine the local density of the point cloud data, that is, with the point cloud data as the center of the circle, determine the number of point cloud data within the neighborhood radius corresponding to the point cloud data according to the distance between the point cloud data and other point cloud data. According to the comparison result of the local density of each point cloud data and the minimum number of point clouds, determine the type corresponding to each point cloud data, which includes core points, boundary points or noise points. The core point indicates that the number of point clouds within the neighborhood radius of the point cloud data is greater than or equal to the minimum number of point clouds, and the density of the core point is reachable. The boundary point is the neighborhood point cloud data within the neighborhood radius of the core point, that is, the neighboring point cloud data of the boundary point is not enough to form a dense area. The noise point is other point cloud data except the core point and the boundary point. Afterwards, the core points that are density-reachable and the boundary points within the neighborhood radius of each core point are aggregated to form a point cloud cluster. The above aggregation operation is repeated to obtain multiple point cloud clusters.

[0062] After determining the first track, each WIFI probe can receive the RSSI signal strength of each mobile terminal according to any three WIFI probes deployed in the environment. There is a negative exponential relationship between the RSSI signal strength and the distance, that is, the RSSI signal strength decays as the distance increases. Through the RSSI signal strength, the distance between each mobile terminal and the three WIFI probes can be determined, and the terminal coordinates of each mobile terminal can be determined according to the coordinates of the three WIFI probes and the distance between each mobile terminal and the three WIFI probes through the three-point positioning method. For example, the coordinates of WIFI probe A are: (0, 0), the coordinates of WIFI probe B are: (5, 0), and the coordinates of WIFI probe C are: (5, 5), and WIFI probe A measures the first distance between WIFI probe A and mobile terminal D as d1, WIFI probe B measures the first distance between WIFI probe B and mobile terminal D as d2, and WIFI probe C measures the first distance between WIFI probe C and mobile terminal D as d3, then the equation group shown in formula (2) is obtained, and formula (2) is:

[0063]

[0064] Among them, x d represents the x-axis coordinate of the mobile terminal D corresponding to the terminal coordinate, y dIt represents the y-axis coordinate in the terminal coordinates corresponding to the mobile terminal D. Solving the system of equations in Equation (2), it can be known that the terminal coordinates corresponding to the mobile terminal D are (3, 2).

[0065] It should be noted that the terminal coordinates corresponding to the above-mentioned mobile terminal D are the coordinates in the radar coordinate system of the millimeter-wave radar. Through coordinate conversion, the coordinate system corresponding to the WIFI probe can be converted to the radar coordinate system. The embodiments of the present invention do not limit this.

[0066] Step 120: Based on the measurement data corresponding to the first track, determine the first target confidence corresponding to the first track.

[0067] Specifically, after determining the first track, according to the measurement data corresponding to the first track, calculate the first target confidence, and initially determine whether the first track is converted into a target state.

[0068] Furthermore, the determining the first target confidence corresponding to the first track based on the measurement data corresponding to the first track includes:

[0069] In the case where the target state is a disappearing state, obtain at least one second track other than the first track within the radar detection range; based on the measurement data corresponding to the first track and the at least one second track respectively, determine the first target confidence corresponding to the first track; the motion state of the second track has not changed;

[0070] In the case where the target state is a stationary state, based on the measurement data corresponding to the first track, determine the first target confidence corresponding to the first track.

[0071] Specifically, if the first track changes from a motion state to a disappearing state, the millimeter-wave radar cannot determine whether the target to be measured corresponding to the first track is due to being blocked and unable to receive the echo signal, resulting in the disappearance of the track, or due to radar misdetection resulting in the disappearance of the track. Therefore, it is necessary to further obtain multiple second tracks whose motion states have not changed other than the first track. According to the measurement data of the last frame before the first track changes from a motion state to a disappearing state, and the measurement data corresponding to each second track, calculate the first target confidence to initially determine the reason for the change in the state of the first track. If the first track changes from a motion state to a stationary state, the millimeter-wave radar cannot determine whether the target to be measured corresponding to the first track is due to being stationary, resulting in the radar being unable to detect the track change through the Doppler effect, or due to radar misdetection resulting in the disappearance of the track. Therefore, it is necessary to calculate the first target confidence according to the measurement data of the last frame before the first track changes from a motion state to a disappearing state to initially determine the reason for the change in the state of the first track.

[0072] Further, the determining the first target confidence corresponding to the first track based on the measurement data corresponding to each of the first track and the at least one second track includes:

[0073] For each of the second tracks, determining a first confidence level between the first track and the second track based on the measurement data corresponding to each of the first track and the second track;

[0074] When the number of the second track is equal to 1, determining the first confidence level corresponding to the second track as the first target confidence level corresponding to the conversion of the first track to the target state;

[0075] When the number of the second tracks is greater than 1, the maximum first confidence is determined as the first target confidence corresponding to the conversion of the first track to the target state.

[0076] Specifically, when the first track changes from a moving state to a disappearing state, the first confidence between the first track and any second track is calculated based on the measurement data corresponding to the first track and each second track. If there is only one second track, the first confidence is the first target confidence, and the higher the first confidence, the higher the possibility that the target to be measured corresponding to the first track is blocked by the target to be measured corresponding to the second track. If there are at least two second tracks, the maximum first confidence can be determined as the first target confidence, and the target to be measured corresponding to the first track is most likely to be blocked by the target to be measured corresponding to the maximum first confidence.

[0077] Further, in the case where the target state is a disappearing state, the measurement data includes a radial distance and an azimuth corresponding to the last frame before the first track is converted into the disappearing state;

[0078] The determining, based on the measurement data corresponding to each of the first track and the second track, a first confidence level between the first track and the second track, comprises:

[0079] Determine a first difference between a radial distance of the first track and a radial distance of the second track, and determine a second difference between an azimuth of the first track and an azimuth of the second track;

[0080] A first confidence level between the first track and the second track is determined based on the first difference and the second difference.

[0081] Specifically, when the target to be detected corresponding to the first track changes from a moving state to a disappearing state, for each second track, the first difference can be determined according to the radial distance of the first track and the radial distance of the second track using formula (3), and the second difference can be determined according to the azimuth of the first track and the azimuth of the second track, and the first confidence can be determined according to the reciprocal of the first difference and the product of the reciprocal of the second difference. Formula (3) is:

[0082]

[0083] Among them, C 11 Indicates the first confidence or the first target confidence of the first track turning into a disappeared state, r 1 represents the radial distance of the first track, that is, the distance between the target track coordinates of the last frame before the first track is converted to the disappearing state and the millimeter wave radar, r 2 represents the radial distance of the second track, azi 1 represents the azimuth of the first track, that is, the horizontal angle between the target track coordinates of the first track and the position of the millimeter-wave radar, azi 2 Indicates the azimuth of the second track.

[0084] Further, in the case where the target state is a stationary state, the measurement data includes a velocity, an acceleration, and a radar frame period corresponding to the last frame before the first track is converted to the stationary state;

[0085] The determining, based on the measurement data corresponding to the first track, a first target confidence level corresponding to the first track, comprises:

[0086] A first target confidence level corresponding to the conversion of the first track to the stationary state is determined based on the speed, the acceleration and the radar frame period.

[0087] Specifically, when the target to be measured corresponding to the first track is converted from a moving state to a stationary state, the first target confidence can be calculated according to the speed, acceleration and radar frame period of the last frame before the first track is converted to a stationary state using formula (4), that is, the predicted speed when the first track is converted to a stationary state. The first target confidence is an integer greater than or equal to 0. Through the first target confidence, it is preliminarily determined whether the target to be measured corresponding to the first track is converted to a stationary state, or whether the millimeter-wave radar makes an error in predicting the next frame in the last frame. Formula (4) is:

[0088] C 12 =|v+at|

[0089] Among them, C 12represents the confidence of the first target when the first track is converted to a stationary state, v represents the velocity of the last frame, a represents the acceleration of the last frame, t represents the radar frame period, that is, the time interval between two adjacent frames, and |*| represents taking the absolute value.

[0090] Step 130: Determine a second target confidence based on the target track coordinates corresponding to the first track and the coordinates of each terminal; the target track coordinates are the track coordinates corresponding to the last frame before the first track is converted to the target state.

[0091] Specifically, after calculating the first target confidence, the second target confidence is determined by combining the target track coordinates of the last frame before the first track is converted to the target state and the terminal coordinates corresponding to all mobile terminals detected by the WIFI probe, that is, the mobile terminal closest to the target track coordinates.

[0092] Further, the determining of the second target confidence based on the target track coordinates corresponding to the first track and the coordinates of each terminal includes:

[0093] For each terminal coordinate, determining a second confidence level between the first track and the terminal coordinate based on the target track coordinate corresponding to the first track and the terminal coordinate;

[0094] When the number of the terminal coordinates is equal to 1, determining the second confidence as the second target confidence;

[0095] When the number of the terminal coordinates is greater than 1, the maximum second confidence is determined as the second target confidence.

[0096] Specifically, when the first track is converted from the motion state to the target state, the second confidence between the target track coordinates of the first track and the coordinates of each terminal can be calculated using formula (5). Formula (5) is:

[0097]

[0098] Among them, C 2 represents the second confidence or second target confidence between the target track coordinates of the first track and each terminal coordinate, (x j ,y j ) represents the terminal coordinates corresponding to the jth mobile terminal, j is greater than or equal to 1 and less than or equal to the number of all mobile terminals in the terminal coordinate set W, (x t ,y t ) represents the target track coordinates of the first track.

[0099] If the WIFI probe detects only one mobile terminal, the second confidence level corresponding to the mobile terminal is determined as the second target confidence level, and the higher the second target confidence level, the closer the distance between the mobile terminal corresponding to the second confidence level and the target to be measured corresponding to the first track is. If the WIFI probe detects multiple mobile terminals, the maximum second confidence level can be used to determine the second target confidence level, and the mobile terminal corresponding to the maximum second confidence level is closest to the target to be measured corresponding to the first track.

[0100] Step 140: Determine a total confidence in the target state based on the first target confidence and the second target confidence, and determine a state switching result of the first track based on the total confidence.

[0101] Specifically, after determining the first target confidence and the second target confidence, the confidence weights corresponding to the millimeter wave radar and the WIFI probe can be further determined, and the weighted sum of each confidence weight, the first target confidence and the second target confidence can be determined by using formula (6) to calculate the total confidence. Formula (6) is:

[0102]

[0103] Where C represents the total confidence in the target state, n represents the number of collectors, that is, the sum of the number of millimeter-wave radars and WIFI probes, k represents the kth collector, ω k represents the confidence weight of the kth collector. When the collector is a millimeter-wave radar, ω k Represents the confidence weight of the millimeter-wave radar. When the collector is a WIFI probe, ω k Represents the confidence weight of the WIFI probe. k represents the confidence of the kth collector. When the collector is a millimeter-wave radar, C k Indicates the first target confidence corresponding to the millimeter-wave radar in the target state. When the collector is a WIFI probe, C k Indicates the second target confidence corresponding to the WIFI probe in the target state.

[0104] After the total confidence is calculated, the total confidence is judged with the third preset threshold. If the total confidence is greater than or equal to the third preset threshold, it can be determined that the state switching result of the first track is allowed to switch to the target state, that is, the reason for the state conversion of the first track is that the target to be measured is blocked or the target to be measured is in a stationary state. If the total confidence is less than the third preset threshold, it can be determined that the state switching result of the first track is prohibited from switching to the target state, that is, the reason for the state conversion of the first track is the false detection of each collector. This mode greatly improves the accuracy of track state switching and has a good optimization for maintaining the state for a long time.

[0105] The target track state switching method provided by the embodiment of the present invention determines the first target confidence according to the measurement data of the first track after obtaining the first track whose motion state changes within the radar detection range and the terminal coordinates corresponding to each of the at least one mobile terminal detected by the WIFI probe, so as to judge whether the motion state of the first track is converted into the target state. Then, the second target confidence is determined in combination with the target track coordinates and each terminal coordinates corresponding to the first track, and the total confidence is determined according to the first target confidence and the second target confidence. Based on the total confidence, the state switching result of the first track is determined. Based on the popularity of mobile terminals and the first track and terminal coordinates detected by the radar, the accuracy of the judgment result of the conversion of the motion state of the first track into the target state is improved, thereby improving the accuracy of the target track detection by the millimeter wave radar. At the same time, after combining the radar and the WIFI probe, multiple targets to be measured can also be identified, so as to solve the problem that the millimeter wave radar misdetects multiple targets to be measured as a single target to be measured.

[0106] The target track state switching device provided by the present invention is described below. The target track state switching device described below and the target track state switching method described above can be referred to each other.

[0107] The embodiment of the present invention also provides a target track state switching device, Figure 2 is a schematic diagram of the structure of a target track state switching device provided by an embodiment of the present invention, such as Figure 2 As shown, the target track state switching device 200 includes: an acquisition module 210, a first determination module 220, a second determination module 230 and a state switching module 240, wherein:

[0108] An acquisition module 210 is used to acquire a first track converted from a motion state to a target state within a radar detection range, and terminal coordinates corresponding to at least one mobile terminal detected by a WIFI probe;

[0109] A first determination module 220, configured to determine a first target confidence level corresponding to the first track based on the measurement data corresponding to the first track;

[0110] A second determination module 230 is used to determine a second target confidence based on the target track coordinates corresponding to the first track and the coordinates of each terminal; the target track coordinates are the track coordinates corresponding to the last frame before the first track is converted to the target state;

[0111] The state switching module 240 is used to determine the total confidence in the target state based on the first target confidence and the second target confidence, and determine the state switching result of the first track based on the total confidence.

[0112] The target track state switching device provided by the embodiment of the present invention determines the first target confidence according to the measurement data of the first track after obtaining the first track whose motion state changes within the radar detection range and the terminal coordinates corresponding to each of the at least one mobile terminal detected by the WIFI probe, so as to judge whether the motion state of the first track is converted into the target state. Then, the second target confidence is determined in combination with the target track coordinates and each terminal coordinates corresponding to the first track, and the total confidence is determined according to the first target confidence and the second target confidence. Based on the total confidence, the state switching result of the first track is determined. Based on the popularity of mobile terminals and the first track and terminal coordinates detected by the radar, the accuracy of the judgment result of the conversion of the motion state of the first track into the target state is improved, thereby improving the accuracy of the target track detection by the millimeter wave radar. At the same time, after combining the radar and the WIFI probe, multiple targets to be measured can also be identified, so as to solve the problem that the millimeter wave radar mistakenly detects multiple targets to be measured as a single target to be measured.

[0113] Optionally, the first determining module 220 is specifically configured to:

[0114] When the target state is a disappeared state, obtaining at least one second track other than the first track within the radar detection range; determining the first target confidence corresponding to the first track based on the measurement data corresponding to each of the first track and the at least one second track; the motion state of the second track does not change;

[0115] When the target state is a stationary state, a first target confidence level corresponding to the first track is determined based on measurement data corresponding to the first track.

[0116] Optionally, the first determining module 220 is specifically configured to:

[0117] For each of the second tracks, determining a first confidence level between the first track and the second track based on the measurement data corresponding to each of the first track and the second track;

[0118] When the number of the second track is equal to 1, determining the first confidence level corresponding to the second track as the first target confidence level corresponding to the conversion of the first track to the target state;

[0119] When the number of the second tracks is greater than 1, the maximum first confidence is determined as the first target confidence corresponding to the conversion of the first track to the target state.

[0120] Optionally, when the target state is a disappearing state, the measurement data includes a radial distance and an azimuth corresponding to the last frame before the first track is converted into the disappearing state.

[0121] Optionally, the first determining module 220 is specifically configured to:

[0122] Determine a first difference between a radial distance of the first track and a radial distance of the second track, and determine a second difference between an azimuth of the first track and an azimuth of the second track;

[0123] A first confidence level between the first track and the second track is determined based on the first difference and the second difference.

[0124] Optionally, when the target state is a stationary state, the measurement data includes a speed, an acceleration and a radar frame period corresponding to the last frame before the first track is converted to the stationary state.

[0125] Optionally, the first determining module 220 is specifically configured to:

[0126] A first target confidence level corresponding to the conversion of the first track to the stationary state is determined based on the speed, the acceleration and the radar frame period.

[0127] Optionally, the second determining module 230 is specifically configured to:

[0128] For each terminal coordinate, determining a second confidence level between the first track and the terminal coordinate based on the target track coordinate corresponding to the first track and the terminal coordinate;

[0129] When the number of the terminal coordinates is equal to 1, determining the second confidence as the second target confidence;

[0130] When the number of the terminal coordinates is greater than 1, the maximum second confidence is determined as the second target confidence.

[0131] Optionally, the target track state switching device 200 further includes a third determination module, and the third determination module is specifically used to:

[0132] Acquire at least two point cloud data within the radar detection range;

[0133] Density clustering is performed on the at least two point cloud data to obtain at least one point cloud cluster;

[0134] For each of the point cloud clusters, when the number of point clouds in the point cloud cluster is greater than or equal to a first preset threshold, determining the coordinates of the center point of the point cloud in the point cloud cluster;

[0135] Based on the coordinates of the center point of the point cloud, determine at least two target terminal coordinates within the neighborhood radius of the point cloud cluster from the terminal coordinates corresponding to each of the at least one mobile terminal, and determine the target terminal coordinates as the initial track coordinates corresponding to the second track;

[0136] In the case where the second track is converted from the motion state to the target state, the second track is determined as the first track, and based on the initial track coordinates, the target track coordinates of the last frame before the first track is converted to the target state are determined.

[0137] Figure 3 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 3 As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communication interface 320 and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the target track state switching method, which includes:

[0138] Acquire a first track that is converted from a motion state to a target state within the radar detection range, and terminal coordinates corresponding to at least one mobile terminal detected by the WIFI probe;

[0139] Determining a first target confidence level corresponding to the first track based on the measurement data corresponding to the first track;

[0140] Determine the second target confidence based on the target track coordinates corresponding to the first track and the coordinates of each terminal; the target track coordinates are the track coordinates corresponding to the last frame before the first track is converted to the target state;

[0141] Based on the first target confidence and the second target confidence, a total confidence in the target state is determined, and based on the total confidence, a state switching result of the first track is determined.

[0142] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0143] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored in a computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the target track state switching method provided by the above methods, the method includes:

[0144] Acquire a first track that is converted from a motion state to a target state within the radar detection range, and terminal coordinates corresponding to at least one mobile terminal detected by the WIFI probe;

[0145] Determining a first target confidence level corresponding to the first track based on the measurement data corresponding to the first track;

[0146] Determine the second target confidence based on the target track coordinates corresponding to the first track and the coordinates of each terminal; the target track coordinates are the track coordinates corresponding to the last frame before the first track is converted to the target state;

[0147] Based on the first target confidence and the second target confidence, a total confidence in the target state is determined, and based on the total confidence, a state switching result of the first track is determined.

[0148] In another aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the target track state switching method provided by the above methods is implemented, and the method includes:

[0149] Acquire a first track that is converted from a motion state to a target state within the radar detection range, and terminal coordinates corresponding to at least one mobile terminal detected by the WIFI probe;

[0150] Determining a first target confidence level corresponding to the first track based on the measurement data corresponding to the first track;

[0151] Determine the second target confidence based on the target track coordinates corresponding to the first track and the coordinates of each terminal; the target track coordinates are the track coordinates corresponding to the last frame before the first track is converted to the target state;

[0152] Based on the first target confidence and the second target confidence, a total confidence in the target state is determined, and based on the total confidence, a state switching result of the first track is determined.

[0153] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0154] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0155] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A target track state switching method, It is characterized in that include: Acquire a first track that is converted from a motion state to a target state within the radar detection range, and terminal coordinates corresponding to at least one mobile terminal detected by the WIFI probe; Determining a first target confidence level corresponding to the first track based on the measurement data corresponding to the first track; Determine the second target confidence based on the target track coordinates corresponding to the first track and the coordinates of each terminal; the target track coordinates are the track coordinates corresponding to the last frame before the first track is converted to the target state; Based on the first target confidence and the second target confidence, a total confidence in the target state is determined, and based on the total confidence, a state switching result of the first track is determined.

2. The target track state switching method according to claim 1, It is characterized in that The determining, based on the measurement data corresponding to the first track, a first target confidence level corresponding to the first track, comprises: When the target state is a disappeared state, obtaining at least one second track other than the first track within the radar detection range; determining the first target confidence corresponding to the first track based on the measurement data corresponding to each of the first track and the at least one second track; the motion state of the second track does not change; When the target state is a stationary state, a first target confidence level corresponding to the first track is determined based on measurement data corresponding to the first track.

3. The target track state switching method according to claim 2, It is characterized in that The determining, based on the measurement data corresponding to each of the first track and the at least one second track, a first target confidence corresponding to the first track comprises: For each of the second tracks, determining a first confidence level between the first track and the second track based on the measurement data corresponding to each of the first track and the second track; When the number of the second track is equal to 1, determining the first confidence level corresponding to the second track as the first target confidence level corresponding to the conversion of the first track to the target state; When the number of the second tracks is greater than 1, the maximum first confidence is determined as the first target confidence corresponding to the conversion of the first track to the target state.

4. The target track state switching method according to claim 3, It is characterized in that In the case where the target state is a disappearing state, the measurement data includes a radial distance and an azimuth corresponding to the last frame before the first track is converted into the disappearing state; The determining, based on the measurement data corresponding to each of the first track and the second track, a first confidence level between the first track and the second track, comprises: Determine a first difference between a radial distance of the first track and a radial distance of the second track, and determine a second difference between an azimuth of the first track and an azimuth of the second track; A first confidence level between the first track and the second track is determined based on the first difference and the second difference.

5. The target track state switching method according to claim 2, It is characterized in that In the case where the target state is a stationary state, the measurement data includes a velocity, an acceleration, and a radar frame period corresponding to the last frame before the first track is converted to the stationary state; The determining, based on the measurement data corresponding to the first track, a first target confidence level corresponding to the first track, comprises: A first target confidence level corresponding to the conversion of the first track to the stationary state is determined based on the speed, the acceleration and the radar frame period.

6. The target track state switching method according to any one of claims 1 to 5, It is characterized in that The determining of the second target confidence based on the target track coordinates corresponding to the first track and the coordinates of each terminal includes: For each terminal coordinate, determining a second confidence level between the first track and the terminal coordinate based on the target track coordinate corresponding to the first track and the terminal coordinate; When the number of the terminal coordinates is equal to 1, determining the second confidence as the second target confidence; When the number of the terminal coordinates is greater than 1, the maximum second confidence is determined as the second target confidence.

7. The target track state switching method according to any one of claims 1 to 5, It is characterized in that The method further comprises: Acquire at least two point cloud data within the radar detection range; Density clustering is performed on the at least two point cloud data to obtain at least one point cloud cluster; For each of the point cloud clusters, when the number of point clouds in the point cloud cluster is greater than or equal to a first preset threshold, determining the coordinates of the center point of the point cloud in the point cloud cluster; Based on the coordinates of the center point of the point cloud, determine at least two target terminal coordinates within the neighborhood radius of the point cloud cluster from the terminal coordinates corresponding to each of the at least one mobile terminal, and determine the target terminal coordinates as the initial track coordinates corresponding to the second track; In the case where the second track is converted from the motion state to the target state, the second track is determined as the first track, and based on the initial track coordinates, the target track coordinates of the last frame before the first track is converted to the target state are determined.

8. A target track state switching device, It is characterized in that include: An acquisition module, used to acquire a first track converted from a motion state to a target state within a radar detection range, and terminal coordinates corresponding to at least one mobile terminal detected by a WIFI probe; A first determination module, configured to determine a first target confidence corresponding to the first track based on measurement data corresponding to the first track; A second determination module is used to determine a second target confidence based on the target track coordinates corresponding to the first track and the coordinates of each terminal; the target track coordinates are the track coordinates corresponding to the last frame before the first track is converted to the target state; The state switching module is used to determine the total confidence in the target state based on the first target confidence and the second target confidence, and determine the state switching result of the first track based on the total confidence.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the program, the target track state switching method as described in any one of claims 1-7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the target track state switching method as described in any one of claims 1 to 7 is implemented.

Images