Method and device for detecting moving targets in position

Abstract

The embodiments of this specification provide a method and device for detecting the presence of moving targets. The method uses a millimeter-wave radar to obtain point cloud data of multiple moving points in the detection area. Based on these point cloud data, at least one moving target included in the detection area can be determined, and then the location information of the moving target can be determined based on the attribute information of the moving points in the point cloud data. Finally, it can be determined whether the moving target is located in the target area based on the range information of the target area and the location information of the moving target. This solution for detecting whether there is a moving target entering a target area only requires the use of a millimeter-wave radar. Even if the target area changes, this solution can continue to detect the moving target in place by changing the range information of the target area without the need to continue to redeploy sensors in the changed target area, thereby reducing the operational complexity of detecting the moving target in place.

Description

Technical Field

[0001] One or more embodiments of the present specification relate to computer technology, and more particularly, to a method and apparatus for detecting the location of a moving target. Background Art

[0002] In-place detection is a technology used to detect whether there is an active target entering a target area.

[0003] At present, detection is usually achieved by deploying sensors in the target area. However, when implementing the above technical solution, since the sensors can only detect the target area after deployment, once the target area changes, the sensors can only be redeployed in the changed target area. This operation of detecting active targets in place is complicated. Summary of the invention

[0004] One or more embodiments of the present specification describe a method and apparatus for detecting the location of a moving target, which can reduce the operational complexity of detecting the location of a moving target.

[0005] According to a first aspect, a method for detecting the presence of a moving target is provided, comprising:

[0006] Acquire range information of a target area; the target area is obtained by dividing the detection area;

[0007] Acquire point cloud data corresponding to a plurality of moving points detected by the millimeter wave radar in the detection area; the point cloud data includes the number of moving points and attribute information of each moving point;

[0008] Determine at least one moving target included in the detection area according to the number of moving points detected by the millimeter wave radar in the detection area and the attribute information of each moving point; wherein each moving target is composed of multiple moving points;

[0009] For each activity goal, execute:

[0010] Determining the position information of the moving target according to the attribute information of the moving point corresponding to the moving target;

[0011] According to the range information of the target area and the position information of the moving target, it is determined whether the moving target is located in the target area.

[0012] In one embodiment of the present specification, the attribute information includes coordinates, speed, and signal-to-noise ratio;

[0013] The determining, based on the number of moving points detected by the millimeter wave radar in the detection area and the attribute information of each moving point, at least one moving target included in the detection area comprises:

[0014] Clustering the multiple moving points in the detection area according to the coordinates, speed and signal-to-noise ratio of each moving point to obtain at least one initial point cloud cluster;

[0015] For each initial point cloud cluster, if the number of moving points included in the initial point cloud cluster is not less than a preset first number threshold, and the distance between any two moving points included in the initial point cloud cluster is less than a preset first distance threshold, then the initial point cloud cluster is determined as a valid point cloud cluster;

[0016] The valid point cloud cluster that meets the activity target determination rules is determined as the activity target.

[0017] In one embodiment of the present specification, the activity target determination rule includes at least one of the following:

[0018] The duration of the effective point cloud cluster is not less than the preset first duration;

[0019] The number of moving points included in the valid point cloud cluster is not less than a preset second quantity threshold;

[0020] The distance between a valid point cloud cluster and a valid point cloud cluster closest to the valid point cloud cluster is not less than a preset second distance threshold.

[0021] In one embodiment of the present specification, the point cloud data includes a distance from each moving point to the millimeter wave radar and an azimuth from each moving point to the millimeter wave radar;

[0022] Before determining the position information of the moving target, the method further includes: acquiring the position information of the millimeter wave radar;

[0023] The determining of the location information of the activity target includes:

[0024] Calculate the average distance from the moving target to the millimeter-wave radar according to the distance from each moving point in the moving target to the millimeter-wave radar;

[0025] Calculate the average azimuth angle from the moving target to the millimeter-wave radar according to the azimuth angle from each moving point in the moving target to the millimeter-wave radar;

[0026] The position information of the moving target is determined based on the position information of the millimeter wave radar and the calculated average distance and average azimuth.

[0027] In one embodiment of the present specification, there are at least two target areas within the detection area;

[0028] Within a preset second time period, the millimeter wave radar detects the detection area to obtain at least two frames of point cloud data corresponding to the plurality of motion points;

[0029] The determining, based on the range information of the target area and the position information of the activity target, whether the activity target is located in the target area includes:

[0030] According to the range information of the target area and the position information of the moving target in each frame, determining whether the moving target is located in the target area;

[0031] After determining that an active target in at least one frame is located in one of the target areas, the method further includes:

[0032] During the preset second time period, it is determined whether the active target in at least one frame is located in another target area. If yes, the following processing is performed:

[0033] Performing noise reduction processing on the motion points corresponding to the moving target in all frames within the second time length;

[0034] Determine the new location information of the activity target;

[0035] According to the determined new position information, the target area where the activity target is located is determined.

[0036] In one embodiment of the present specification, the performing noise reduction processing on the motion points corresponding to the moving target in all frames within the second time length includes:

[0037] Determine a boundary zone area of ​​the two target areas; wherein the boundary zone area of ​​the target area is formed by moving the boundary line of the target area toward the inside of the target area by a preset distance;

[0038] removing the motion points located on the boundary zone in all frames within the second time length;

[0039] and / or,

[0040] The point cloud data includes a Doppler value of each moving point; wherein the Doppler value of each moving point is used to characterize the rate of change of the relative distance from the moving point to the millimeter wave radar;

[0041] The performing noise reduction processing on the motion points corresponding to the moving target in all frames within the second time length includes:

[0042] Calculating an average Doppler value of the moving point corresponding to the moving target in all frames within the second time length;

[0043] The moving points whose Doppler values ​​are lower than the average Doppler value are removed.

[0044] In one embodiment of the present specification, determining the new location information of the activity target includes:

[0045] The moving points corresponding to the moving target after the noise reduction process are clustered again to obtain at least two new point cloud clusters;

[0046] The new position information of the moving target is determined according to the attribute information of the moving points in the new point cloud cluster with the largest number of moving points.

[0047] According to a second aspect, there is provided a device for detecting the position of a moving target, comprising:

[0048] A first acquisition module is configured to acquire range information of a target area; the target area is obtained by dividing the detection area;

[0049] A second acquisition module is configured to acquire point cloud data corresponding to a plurality of moving points detected by the millimeter wave radar in the detection area; the point cloud data includes the number of moving points and attribute information of each moving point;

[0050] The moving target determination module is configured to determine at least one moving target included in the detection area according to the number of moving points detected by the millimeter wave radar in the detection area and the attribute information of each moving point; wherein each moving target is composed of a plurality of moving points;

[0051] The processing module is configured to execute, for each activity target, the following steps: determining the location information of the activity target based on the attribute information of the motion point corresponding to the activity target; and determining whether the activity target is located within the target area based on the range information of the target area and the location information of the activity target.

[0052] According to a third aspect, a device for detecting the presence of a moving target is provided, comprising a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, the method described in any embodiment of the present specification is implemented.

[0053] According to a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed in a computer, the computer is caused to execute the method described in any embodiment of the present specification.

[0054] According to the method and device for detecting the presence of moving targets provided in the embodiments of this specification, by using millimeter-wave radar to obtain point cloud data of multiple moving points in the detection area, at least one moving target included in the detection area can be determined based on these point cloud data, and then the location information of the moving target can be determined based on the attribute information of the moving points in the point cloud data, and finally, it can be determined whether the moving target is located in the target area based on the range information of the target area and the location information of the moving target. This scheme of detecting whether there is a moving target entering a certain target area only requires the use of a millimeter-wave radar. Even if the target area changes, this scheme can continue to detect the moving target in place by changing the range information of the target area without continuing to redeploy sensors in the changed target area, thereby reducing the operational complexity of detecting the moving target in place. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0056] Figure 1 A flow chart showing a method for detecting the location of a moving target in one embodiment of the present specification is shown;

[0057] Figure 2 A flowchart for determining an activity target in one embodiment of this specification is shown;

[0058] Figure 3 A flowchart of determining the location information of an activity target in one embodiment of this specification is shown;

[0059] Figure 4 A schematic diagram showing the positions of a point cloud cluster and a millimeter wave radar in one embodiment of this specification is shown;

[0060] Figure 5 A flow chart showing a target area where an active target is located in one embodiment of the present specification is shown;

[0061] Figure 6 A schematic diagram showing the positions of a point cloud cluster and two target areas in one embodiment of the present specification is shown;

[0062] Figure 7 A schematic diagram showing the structure of a device where a device for detecting the position of a moving target is located in one embodiment of the present specification;

[0063] Figure 8A schematic diagram of a device for detecting the position of a moving target in one embodiment of the present specification is shown. DETAILED DESCRIPTION

[0064] The solution provided in this specification is described below in conjunction with the accompanying drawings.

[0065] In the existing process of detecting the location of moving targets, the detection is usually achieved by deploying sensors in the target area. For example, the sensor is an infrared sensor, a laser sensor or an image sensor, and the above sensors are used to directly determine whether a moving target enters the target area.

[0066] However, after the sensor is deployed, it can only detect the target area. Once the target area changes, the sensor can only be redeployed in the changed target area. This operation of detecting active targets in place is complicated.

[0067] From the analysis of the above process of detecting the presence of active targets, it can be seen that it is only necessary to rely on the changes in the acquisition signals of some of these sensors in the target area (for example, the infrared is blocked, the laser is blocked, and an active target enters the image) to directly determine whether an active target has entered the target area. If the target area changes, for example, a sensor was originally set in target area A, and now if you want to add detection of whether an active target has entered target area B, you need to add a sensor to target area B. This operation is more complicated. In other words, when the target area changes, you can consider a method of judging whether the position information of the active target falls within the range of the target area, so that the presence response can be triggered.

[0068] In addition, since the common defects of the above sensors are mainly short detection distance and susceptibility to environmental influences (such as light, temperature and obstacles), a sensing method with a long detection distance and less susceptible to environmental influences can be considered, such as a sensing method using a millimeter wave radar. Based on this, the embodiment of this specification uses a millimeter wave radar to detect active targets and uses an indirect detection method (i.e., replacing the direct detection method of existing sensors) to determine whether the location information of the active target falls within the range of the target area.

[0069] The specific implementation of the concept provided in this specification is described below.

[0070] Figure 1 A flow chart of a method for detecting a presence according to an embodiment is shown. It is understood that the method can be executed by any device, equipment, platform, or device point cloud group with computing and processing capabilities. Figure 1 , the method comprising:

[0071] Step 101: Obtain range information of the target area.

[0072] In this embodiment, the target area is obtained by dividing the detection area.

[0073] In the embodiments of this specification, the detection area and the target area are both two-dimensional areas. For example, the detection area can be a regular plane figure or an irregular plane figure; similarly, the target area can be a regular plane figure or an irregular plane figure. The range information of the target area is used to characterize the contour shape of the target area. For example, the range information can be a collection of coordinate information of multiple coordinate points, or a collection of coordinate information and size information of a coordinate point.

[0074] Taking the example that both the detection area and the target area are rectangular areas, the range information of the detection area and the target area can include a vertex coordinate of the detection area, the length and width of the detection area. For example, the vertex coordinate of the lower left corner of the detection area is (0, 0), the length is 4 (dimensionless unit), and the width is 2 (dimensionless unit). If you want to determine a target area within the detection area, you only need to obtain a vertex coordinate, the length and width of the target area.

[0075] Step 102: Obtain point cloud data corresponding to a plurality of moving points obtained by detecting the detection area by the millimeter wave radar.

[0076] In this embodiment, the point cloud data includes the number of moving points and attribute information of each moving point.

[0077] Millimeter wave radar (Radio detecting and ranging, Radar) refers to radar that works in the millimeter wave band. Usually, millimeter waves refer to electromagnetic waves with a length of 1 to 10 mm, and the corresponding frequency range is 30 to 300 GHz. Millimeter wave radar can accurately measure information such as the position and speed of a target, and has the characteristics of all-day, all-weather, low cost, low power consumption, and long life. Millimeter wave radar can distinguish and identify very small targets, and can identify multiple targets at the same time.

[0078] Among them, the millimeter wave radar can emit electromagnetic waves in the millimeter wave frequency band within a preset range, and then the millimeter wave radar can collect echo signals, and convert the collected echo signals into analog-to-digital signals, and then perform DSP (Digital Signal Processing) on ​​the converted signals to obtain point cloud data.

[0079] Step 103: Determine at least one moving target included in the detection area according to the number of moving points detected by the millimeter wave radar in the detection area and the attribute information of each moving point.

[0080] In this embodiment, each moving object is composed of a plurality of moving points.

[0081] In some implementations, this can be accomplished by Figure 2 The flowchart shown in the figure determines at least one moving target included in the detection area. Specifically, it includes the following steps:

[0082] Attribute information includes coordinates, velocity, and signal-to-noise ratio;

[0083] Step 201: clustering the multiple moving points in the detection area according to the coordinates, speed and signal-to-noise ratio of each moving point to obtain at least one initial point cloud cluster.

[0084] In this step, the clustering process using the DBSCAN algorithm is taken as an example. It should be understood that the clustering process in the embodiments of this specification is not limited to the DBSCAN algorithm.

[0085] Among them, the clustering process of the DBSCAN algorithm is as follows:

[0086] Starting from a moving point that is not divided into the initial point cloud cluster and has not been visited, calculate the neighborhood whose coordinates and speed differences with the moving point are within a certain threshold. In this embodiment, the threshold of the coordinate difference is set to 0.15m, and the threshold of the speed difference is set to 1m / s, that is, other moving points whose plane distance from the point does not exceed 0.15m and the absolute value of the speed difference does not exceed 1m / s are all within the neighborhood of the point.

[0087] If the number of moving points falling within the neighborhood exceeds a threshold (for example, 10, which can be set according to different scenarios), the moving point is marked as the first point in the new point cloud cluster; otherwise, the moving point is marked as a noise point, and the state of the marked moving point is changed to visited.

[0088] The first point in the new point cloud cluster is processed, and all moving points in its neighborhood are marked as moving points in the new point cloud cluster, and all moving points in the new point cloud cluster are processed until no new moving points are added to the new point cloud cluster. After the above processing is completed in the current point cloud cluster, a new unvisited point will be extracted and processed, so that the next point cloud cluster or noise will be found. This process is repeated until all points are marked as visited. After the processing is completed, each moving point is marked as belonging to a point cloud cluster or a noise point.

[0089] The sum of the signal-to-noise ratios of the points in each point cloud cluster is calculated, and the point cloud cluster whose sum of the signal-to-noise ratio is greater than a threshold (for example, 100 dB, the threshold of the sum of the signal-to-noise ratio may be determined according to different scenarios) is marked as an initial point cloud cluster, otherwise it is marked as a noise point cloud cluster.

[0090] Step 202: For each initial point cloud cluster, if the number of moving points included in the initial point cloud cluster is not less than a preset first quantity threshold, and the distance between any two moving points included in the initial point cloud cluster is less than a preset first distance threshold, then the initial point cloud cluster is determined to be a valid point cloud cluster.

[0091] Since the determined initial point cloud cluster may still have interference factors, such as wind blowing the curtains in the detection area, it may also be determined as an initial point cloud cluster. However, usually the number of active points in the point cloud cluster corresponding to the active target and the distance between any two moving points should have certain restrictions (that is, the number of moving points included in the initial point cloud cluster is not less than the preset first number threshold, and the distance between any two moving points included in the initial point cloud cluster is less than the preset first distance threshold) before it can be further determined as an active target.

[0092] It should be noted that, combined with Figure 4 , the distance between any two moving points included in the initial point cloud can be calculated by the following formula:

[0093]

[0094] Among them, D p Used to represent the distance between any two moving points, l p1 Used to characterize the distance from one of the moving points to the millimeter wave radar, l p2 Used to characterize the distance from another moving point to the millimeter wave radar, θ p1 Used to characterize the azimuth angle from one of the moving points to the millimeter-wave radar, θ p2 Used to characterize the azimuth angle of another moving point to the millimeter-wave radar.

[0095] Step 203: Determine the valid point cloud cluster that meets the activity target determination rule as the activity target.

[0096] In this embodiment, the activity target determination rule includes at least one of the following:

[0097] 1) The duration of the valid point cloud cluster is not less than the preset first duration (e.g. 5s);

[0098] 2) The number of moving points included in the valid point cloud cluster is not less than a preset second quantity threshold (e.g., 20);

[0099] 3) The distance between a valid point cloud cluster and the valid point cloud cluster closest to the valid point cloud cluster is not less than a preset second distance threshold (eg, 0.1 m).

[0100] If a valid point cloud cluster can satisfy any one of the three activity target determination rules mentioned above, it can be said that the probability that the valid point cloud cluster is an activity target is relatively high; further, the more valid point cloud clusters that can satisfy the three activity target determination rules mentioned above, the greater the probability that the valid point cloud cluster is an activity target.

[0101] Step 104: For each moving target, the following steps are performed: determining the position information of the moving target based on the attribute information of the moving point corresponding to the moving target; and judging whether the moving target is located in the target area based on the range information of the target area and the position information of the moving target.

[0102] In this embodiment, combined with Figure 3 and Figure 4 , the point cloud data includes the distance from each moving point to the millimeter wave radar and the azimuth from each moving point to the millimeter wave radar;

[0103] Before determining the position information of the moving target, the method further includes: acquiring the position information of the millimeter wave radar;

[0104] The determining of the location information of the activity target includes:

[0105] Step 301: Calculate the average distance from the moving target to the millimeter-wave radar according to the distance from each moving point in the moving target to the millimeter-wave radar.

[0106] In this step, the average distance from the moving target to the millimeter wave radar is calculated by the following formula:

[0107]

[0108] Among them, l a Used to characterize the average distance from active targets to the millimeter-wave radar.

[0109] Step 302: Calculate the average azimuth from the moving target to the millimeter-wave radar according to the azimuth from each moving point in the moving target to the millimeter-wave radar;

[0110] In this step, the average azimuth angle from the moving target to the millimeter wave radar is calculated by the following formula:

[0111]

[0112] Among them, θa Used to characterize the average azimuth angle of active targets to the millimeter-wave radar.

[0113] Step 303: Determine the location information of the moving target based on the location information of the millimeter wave radar and the calculated average distance and average azimuth.

[0114] In this step, the location information of the activity target is calculated using the following formula group:

[0115]

[0116] Among them, X0 is used to represent the horizontal axis coordinate of the activity target, Y0 is used to represent the vertical axis coordinate of the activity target, and X R The horizontal axis coordinate used to represent the millimeter wave radar, Y R The vertical axis used to characterize the millimeter wave radar.

[0117] It should be noted that the embodiment of this specification uses the position information of (X0, Y0) to represent the position information of the moving target, and this representation method has a high accuracy. Of course, the coordinates of other moving points in the moving target or other position information can also be used to represent the moving target, which is not limited here.

[0118] In this embodiment, when the target area is a rectangular area, the following formula group can be used to determine whether the active target is within the target area:

[0119]

[0120] Among them, X a The horizontal coordinate of the lower left corner vertex of the target area, Y a It is used to represent the vertical coordinate of the lower left corner vertex of the target area, L is used to represent the length of the target area, and W is used to represent the width of the target area.

[0121] If the formula group is not satisfied, it means that the activity target is not located in the target area.

[0122] In the embodiments of the present specification, the above-mentioned scheme for detecting whether there is an active target entering a certain target area only requires the use of a millimeter-wave radar. Even if the target area changes, this scheme can continue to detect the active target in place by changing the range information of the target area without continuing to redeploy sensors in the changed target area, thereby reducing the operational complexity of detecting the active target in place.

[0123] In some implementation schemes, judging whether the moving target is located in the target area according to the range information of the target area and the position information of the moving target in step 104 includes:

[0124] According to the range information of the target area and the position information of the moving object in each frame, it is determined whether the moving object is located in the target area.

[0125] That is to say, for each frame of point cloud data detected by the millimeter-wave radar, if there is an active target's position information in the target area in one frame of point cloud data, the in-position response will be triggered, otherwise it will not be triggered. Of course, for a preset number of frames of point cloud data detected by the millimeter-wave radar, if there is an active target's position information in the target area in each frame of point cloud data exceeding a preset threshold, the in-position response will be triggered, otherwise it will not be triggered.

[0126] The above embodiment describes the situation when the moving target enters one target area. However, in actual application, if there are at least two target areas in the detection area, there may be a situation where the moving target repeatedly enters two of the target areas in a short period of time, which will trigger the arrival response (such as alarm information) of the two target areas more frequently, which will affect the user experience.

[0127] The reason is that the above embodiment processes each frame of point cloud data. If the position information of the moving target is located in the target area in a frame of point cloud data, the in-position response will be triggered, that is, the sensitivity of this triggering method is relatively high. Considering that the moving target may enter a target area by mistake, the sensitivity of the above triggering method can be appropriately reduced. For example, noise reduction processing can be considered for the moving points generated within a preset time.

[0128] Combination Figure 5 After determining in step 104 that an active target in at least one frame is located in one of the target areas, the method further includes:

[0129] Step 501: within a preset second time period, determine whether the active target in at least one frame is located in another target area, if yes, execute step 502, if not, end the current process.

[0130] In this step, for example, the preset second time length is 1s, and the millimeter wave radar can detect 20 frames of point cloud data within 1s. If there is an active target in at least one frame of point cloud data located in the first target area, and there is also an active target in at least one frame of point cloud data located in the second target area, then execute step 502. For example, there are active targets in 8 frames of point cloud data located in the first target area, and active targets in 12 frames of point cloud data located in the second target area. Within 1s, both the first target area and the second target area will detect the entry of active targets, that is, within 1s, the in-place responses corresponding to the first target area and the second target area will be triggered several times, which will affect the user experience. Therefore, this frequent triggering problem can be solved by executing step 502.

[0131] Step 502: performing noise reduction processing on the motion points corresponding to the moving target in all frames within the second time length.

[0132] In this step, the noise reduction process may include at least one of the following two methods.

[0133] Method 1

[0134] Step A1: Determine the boundary area between the two target areas.

[0135] The boundary zone of the target area is formed by moving the boundary line of the target area toward the inside of the target area by a preset distance. Figure 6 For example, the two target areas are the first target area and the second target area, and the boundary area is Figure 6 The two annular shadow areas in .

[0136] Step A2: removing the motion points located on the boundary zone in all frames within the second time length.

[0137] In this embodiment, by defining a boundary band area, blurring and weakening processing is performed on the motion points located in the adjacent boundary area between the first target area and the second target area, so that the attribute information of other motion points except those located in the boundary band area can be focused on, thereby preparing to determine the target area where the active target is located (that is, specifically the first target area or the second target area).

[0138] Method 2

[0139] Step B1: Calculate the average Doppler value of the moving point corresponding to the moving target in all frames within the second time length.

[0140] The point cloud data includes the Doppler value of each moving point; wherein the Doppler value of each moving point is used to characterize the rate of change of the relative distance from the moving point to the millimeter wave radar. In other words, the Doppler value of the moving point describes the motion attribute of the moving point, and the screening of the Doppler value can help accurately determine the activity characteristics of the moving target. For example, if the Doppler value of the moving point located in the first target area is generally higher than the Doppler value of the moving point located in the second target area, it can be proved that the moving target is more likely to be located in the first target area.

[0141] Step B2: removing moving points whose Doppler values ​​are lower than the average Doppler value.

[0142] In this embodiment, since the Doppler value of a moving point describes the moving attribute of the moving point, the screening of the Doppler value can help accurately determine the moving characteristics of the moving target. To further process the noise moving points, the moving points whose Doppler values ​​are higher than the average Doppler value can be focused on, that is, the moving points whose Doppler values ​​are lower than the average Doppler value can be removed.

[0143] Step 503: Determine the new location information of the activity target.

[0144] This step can be specifically implemented in the following manner.

[0145] Step C1: clustering the moving points corresponding to the moving target after noise reduction again to obtain at least two new point cloud clusters.

[0146] In this step, for example, the DBSCAN algorithm can be used for clustering processing, as described above, which will not be repeated here. It should be noted that the parameters of the clustering algorithm in this step (such as the threshold of the coordinate difference, the threshold of the speed difference, the threshold of the signal-to-noise ratio, and the threshold of the number) are stricter than the parameters of the first clustering in the above text, otherwise the moving points corresponding to the moving target cannot be clustered into at least two new point cloud clusters.

[0147] Step C2: Determine the new position information of the moving target based on the attribute information of the moving points in the new point cloud cluster with the largest number of moving points.

[0148] In this step, the implementation method of determining the new position information of the moving target is consistent with the above. For example, first, the coordinates, speed and signal-to-noise ratio of each moving point are used to determine the initial point cloud cluster, then the valid point cloud cluster is determined, and then the new moving target is determined; next, the average distance from the new moving target to the millimeter wave radar, the average azimuth angle and the position information of the millimeter wave radar are used to determine the new moving target position information, that is, the new position information of the moving target in step C2 is obtained.

[0149] Step 504: Determine the target area where the activity target is located according to the determined new position information.

[0150] In this embodiment, the new position information of the active target determined through the above steps can better represent the real position information of the active target. By determining the new position information, the problem of frequent triggering of location response of the active target can be effectively solved, that is, the result of the trigger is only whether the active target is located in the first target area or the second target area.

[0151] In summary, by using a single millimeter-wave radar, it is possible to realize the function of virtualizing multiple sub-sensors. When the target area changes, the virtual sub-sensors can still accurately trigger the in-place response, reducing the operational complexity of in-place detection of active targets. At the same time, the trigger status of these virtual sub-sensors can be transmitted to the application terminal in real time for use and display by the terminal application.

[0152] like Figure 7 and Figure 8 As shown, the embodiments of this specification provide a device for detecting the position of a moving target and a device for detecting the position of a moving target. The device embodiment can be implemented by software, or by hardware or a combination of software and hardware. From the hardware level, Figure 7 As shown in the figure, it is a hardware structure diagram of the device where the device for detecting the location of the moving target provided in the embodiment of this specification is located, except Figure 7 In addition to the processor, memory, network interface, and non-volatile memory shown in the figure, the device in the embodiment may also include other hardware, such as a forwarding chip responsible for processing messages, etc. Taking software implementation as an example, Figure 8 As shown, as a device in a logical sense, the CPU of the device in which it is located reads the corresponding computer program instructions in the non-volatile memory into the internal memory and runs them.

[0153] like Figure 8 As shown, in one embodiment of the present specification, a device for detecting the location of a moving target is proposed, comprising:

[0154] The first acquisition module 801 is configured to acquire range information of a target area; the target area is obtained by dividing the detection area;

[0155] The second acquisition module 802 is configured to acquire point cloud data corresponding to a plurality of moving points detected by the millimeter wave radar in the detection area; the point cloud data includes the number of moving points and attribute information of each moving point;

[0156] The moving target determination module 803 is configured to determine at least one moving target included in the detection area according to the number of moving points detected by the millimeter wave radar in the detection area and the attribute information of each moving point; wherein each moving target is composed of multiple moving points;

[0157] The processing module 804 is configured to execute, for each activity target, the following steps: determining the location information of the activity target based on the attribute information of the motion point corresponding to the activity target; and determining whether the activity target is located within the target area based on the range information of the target area and the location information of the activity target.

[0158] In one embodiment of the device proposed in this specification, the attribute information includes coordinates, speed, and signal-to-noise ratio;

[0159] The activity target determination module 803 is configured to perform the following processing:

[0160] Clustering the multiple moving points in the detection area according to the coordinates, speed and signal-to-noise ratio of each moving point to obtain at least one initial point cloud cluster;

[0161] For each initial point cloud cluster, if the number of moving points included in the initial point cloud cluster is not less than a preset first number threshold, and the distance between any two moving points included in the initial point cloud cluster is less than a preset first distance threshold, then the initial point cloud cluster is determined as a valid point cloud cluster;

[0162] The valid point cloud cluster that meets the activity target determination rules is determined as the activity target.

[0163] In one embodiment of the device proposed in this specification, the activity target determination rule includes at least one of the following:

[0164] The duration of the effective point cloud cluster is not less than the preset first duration;

[0165] The number of moving points included in the valid point cloud cluster is not less than a preset second quantity threshold;

[0166] The distance between a valid point cloud cluster and a valid point cloud cluster closest to the valid point cloud cluster is not less than a preset second distance threshold.

[0167] In one embodiment of the device proposed in this specification, the point cloud data includes a distance from each moving point to the millimeter wave radar and an azimuth from each moving point to the millimeter wave radar;

[0168] Further including:

[0169] A third acquisition module is configured to acquire the position information of the millimeter wave radar;

[0170] When determining the location information of the activity target, the processing module 804 is configured to perform the following processing:

[0171] Calculate the average distance from the moving target to the millimeter-wave radar according to the distance from each moving point in the moving target to the millimeter-wave radar;

[0172] Calculate the average azimuth angle from the moving target to the millimeter-wave radar according to the azimuth angle from each moving point in the moving target to the millimeter-wave radar;

[0173] The position information of the moving target is determined based on the position information of the millimeter wave radar and the calculated average distance and average azimuth.

[0174] In one embodiment of the device proposed in this specification, there are at least two target areas within the detection area;

[0175] Within a preset second time period, the millimeter wave radar detects the detection area to obtain at least two frames of point cloud data corresponding to the plurality of motion points;

[0176] When the processing module 804 determines whether the moving target is located in the target area according to the range information of the target area and the position information of the moving target, the processing module 804 is configured to perform the following processing:

[0177] According to the range information of the target area and the position information of the moving target in each frame, determining whether the moving target is located in the target area;

[0178] After determining that an active target in at least one frame is located in one of the target areas, the method further includes:

[0179] The target area determination module is configured to perform the following processing:

[0180] Within a preset second time length, determine whether the active target in at least one frame is located in another target area. If so, perform the following processing: perform noise reduction processing on the motion points corresponding to the active target in all frames within the second time length; determine the new position information of the active target; and determine the target area where the active target is located based on the determined new position information.

[0181] In one embodiment of the device proposed in this specification, when performing the noise reduction process on the motion points corresponding to the moving target in all frames within the second time length, the target area determination module is configured to perform the following process:

[0182] Determine a boundary zone area of ​​the two target areas; wherein the boundary zone area of ​​the target area is formed by moving the boundary line of the target area toward the inside of the target area by a preset distance;

[0183] removing the motion points located on the boundary zone in all frames within the second time length;

[0184] In one embodiment of the device proposed in this specification, the point cloud data includes a Doppler value of each moving point; wherein the Doppler value of each moving point is used to characterize the rate of change of the relative distance from the moving point to the millimeter wave radar;

[0185] When performing the noise reduction process on the motion points corresponding to the moving target in all frames within the second time length, the target area determination module is configured to perform the following process:

[0186] Calculating an average Doppler value of the moving point corresponding to the moving target in all frames within the second time length;

[0187] The moving points whose Doppler values ​​are lower than the average Doppler value are removed.

[0188] In one embodiment of the device proposed in this specification, the target area determination module is configured to perform the following processing when determining the new location information of the activity target:

[0189] The moving points corresponding to the moving target after the noise reduction process are clustered again to obtain at least two new point cloud clusters;

[0190] The new position information of the moving target is determined according to the attribute information of the moving points in the new point cloud cluster with the largest number of moving points.

[0191] In one embodiment of the present specification, the above-mentioned device for detecting the presence of a moving target may be integrated into a terminal device for presence detection, or may be integrated into an independent device or server connected to the terminal device for presence detection.

[0192] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0193] According to another aspect of the embodiment, there is also provided an apparatus for detecting the presence of a moving target, comprising: at least one memory and at least one processor;

[0194] The at least one memory is used to store a machine-readable program;

[0195] The at least one processor is used to call the machine-readable program to execute the method for detecting the presence of a moving target in any embodiment of the present specification.

[0196] According to another embodiment, a computer-readable medium is provided, storing instructions for causing a computer to execute the method for detecting the presence of a moving target as described herein. Specifically, a method or device equipped with a storage medium can be provided, on which a software program code for implementing the functions of any of the above embodiments is stored, and a computer (or CPU or MPU) of the method or device is caused to read and execute the program code stored in the storage medium.

[0197] In this case, the program code itself read from the storage medium can realize the function of any one of the above embodiments, and thus the program code and the storage medium storing the program code constitute part of this specification.

[0198] The storage medium embodiments for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a non-volatile memory card, and a ROM. Alternatively, the program code can be downloaded from a server computer by a communication network.

[0199] In addition, it should be clear that the functions of any of the above embodiments can be realized not only by executing the program code read by the computer, but also by completing part or all of the actual operations by operating methods operated on the computer based on the instructions of the program code.

[0200] In addition, it can be understood that the program code read from the storage medium is written to a memory provided in an expansion board inserted into the computer or written to a memory provided in an expansion unit connected to the computer, and then based on the instructions of the program code, a CPU installed on the expansion board or the expansion unit is enabled to perform part or all of the actual operations, thereby realizing the functions of any of the above-mentioned embodiments.

[0201] Those skilled in the art should be aware that in one or more of the above examples, the functions described in this specification can be implemented using hardware, software, firmware, or any combination thereof. When implemented using software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium.

[0202] It is to be understood that the structures illustrated in the embodiments of this specification do not constitute a specific limitation on the device for detecting the presence of a moving target. In other embodiments of this specification, the device for detecting the presence of a moving target may include more or fewer components than those shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0203] Since the information interaction, execution process and other contents between the modules in the above-mentioned device are based on the same concept as the method embodiments of this specification, the specific contents can be found in the description of the method embodiments of this specification and will not be repeated here.

[0204] The above specific implementation methods further explain the purpose, technical solutions and beneficial effects of this specification in detail. It should be understood that the above are only specific implementation methods of this specification and are not used to limit the protection scope of this specification. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solutions of this specification should be included in the protection scope of this specification.

Claims

1. A method for detecting the presence of a moving target, characterized in that: include: Get the range information of the target area; The target area is obtained by dividing the detection area; Acquire point cloud data corresponding to a plurality of moving points detected by the millimeter wave radar in the detection area; the point cloud data includes the number of moving points and attribute information of each moving point; Determine at least one moving target included in the detection area according to the number of moving points detected by the millimeter wave radar in the detection area and the attribute information of each moving point; wherein each moving target is composed of multiple moving points; For each activity goal, execute: Determining the position information of the moving target according to the attribute information of the moving point corresponding to the moving target; Determining whether the moving target is located in the target area according to the range information of the target area and the position information of the moving target; There are at least two target areas within the detection area; Within a preset second time period, the millimeter wave radar detects the detection area to obtain at least two frames of point cloud data corresponding to the plurality of motion points; The determining, based on the range information of the target area and the position information of the activity target, whether the activity target is located in the target area includes: According to the range information of the target area and the position information of the moving target in each frame, determining whether the moving target is located in the target area; After determining that an active target in at least one frame is located in one of the target areas, the method further includes: During the preset second time period, it is determined whether the active target in at least one frame is located in another target area. If yes, the following processing is performed: Performing noise reduction processing on the motion points corresponding to the moving target in all frames within the second time length; Determine the new location information of the activity target; According to the determined new position information, the target area where the activity target is located is determined.

2. The method according to claim 1, characterized in that The attribute information includes coordinates, speed and signal-to-noise ratio; The determining, based on the number of moving points detected by the millimeter wave radar in the detection area and the attribute information of each moving point, at least one moving target included in the detection area comprises: Clustering the multiple moving points in the detection area according to the coordinates, speed and signal-to-noise ratio of each moving point to obtain at least one initial point cloud cluster; For each initial point cloud cluster, if the number of moving points included in the initial point cloud cluster is not less than a preset first number threshold, and the distance between any two moving points included in the initial point cloud cluster is less than a preset first distance threshold, then the initial point cloud cluster is determined as a valid point cloud cluster; The valid point cloud cluster that meets the activity target determination rules is determined as the activity target.

3. The method according to claim 2, characterized in that The activity target determination rule includes at least one of the following: The duration of the effective point cloud cluster is not less than the preset first duration; The number of moving points included in the valid point cloud cluster is not less than a preset second quantity threshold; The distance between a valid point cloud cluster and a valid point cloud cluster closest to the valid point cloud cluster is not less than a preset second distance threshold.

4. The method according to claim 1, characterized in that The point cloud data includes a distance from each moving point to the millimeter wave radar and an azimuth from each moving point to the millimeter wave radar; Before determining the position information of the moving target, the method further includes: acquiring the position information of the millimeter wave radar; The determining of the location information of the activity target includes: Calculate the average distance from the moving target to the millimeter-wave radar according to the distance from each moving point in the moving target to the millimeter-wave radar; Calculate the average azimuth angle from the moving target to the millimeter-wave radar according to the azimuth angle from each moving point in the moving target to the millimeter-wave radar; The position information of the moving target is determined based on the position information of the millimeter wave radar and the calculated average distance and average azimuth.

5. The method according to claim 1, characterized in that: The performing noise reduction processing on the motion points corresponding to the moving target in all frames within the second time length includes: Determine a boundary zone area of ​​the two target areas; wherein the boundary zone area of ​​the target area is formed by moving the boundary line of the target area toward the inside of the target area by a preset distance; removing the motion points located on the boundary zone in all frames within the second time length; and / or, The point cloud data includes a Doppler value of each moving point; wherein the Doppler value of each moving point is used to characterize the rate of change of the relative distance from the moving point to the millimeter wave radar; The performing noise reduction processing on the motion points corresponding to the moving target in all frames within the second time length includes: Calculating an average Doppler value of the moving point corresponding to the moving target in all frames within the second time length; The moving points whose Doppler values ​​are lower than the average Doppler value are removed.

6. The method according to claim 1, characterized in that The determining of the new location information of the activity target includes: The moving points corresponding to the moving target after the noise reduction process are clustered again to obtain at least two new point cloud clusters; The new position information of the moving target is determined according to the attribute information of the moving points in the new point cloud cluster with the largest number of moving points.

7. A device for detecting the position of a moving target, characterized in that: include: A first acquisition module is configured to acquire range information of a target area; The target area is obtained by dividing the detection area; A second acquisition module is configured to acquire point cloud data corresponding to a plurality of moving points detected by the millimeter wave radar in the detection area; the point cloud data includes the number of moving points and attribute information of each moving point; The moving target determination module is configured to determine at least one moving target included in the detection area according to the number of moving points detected by the millimeter wave radar in the detection area and the attribute information of each moving point; wherein each moving target is composed of a plurality of moving points; The processing module is configured to execute, for each moving target, the following steps: determining the position information of the moving target according to the attribute information of the moving point corresponding to the moving target; and determining whether the moving target is located in the target area according to the range information of the target area and the position information of the moving target; There are at least two target areas within the detection area; Within a preset second time period, the millimeter wave radar detects the detection area to obtain at least two frames of point cloud data corresponding to the plurality of motion points; When the processing module determines whether the moving target is located in the target area according to the range information of the target area and the position information of the moving target, the processing module is configured to perform the following processing: According to the range information of the target area and the position information of the moving target in each frame, determining whether the moving target is located in the target area; After determining that an active target in at least one frame is located in one of the target areas, the method further includes: The target area determination module is configured to perform the following processing: Within a preset second time length, determine whether the active target in at least one frame is located in another target area. If so, perform the following processing: perform noise reduction processing on the motion points corresponding to the active target in all frames within the second time length; determine the new position information of the active target; and determine the target area where the active target is located based on the determined new position information.

8. A device for detecting the position of a moving target, characterized in that: The method comprises a memory and a processor, wherein the memory stores executable codes, and when the processor executes the executable codes, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed in a computer, the computer is caused to execute any one of the methods described in claims 1 to 6.

Images