A radar turning prediction method and device for target detection

Abstract

The application provides a radar turning prediction method and device for target detection, the method comprising: obtaining description information of O targets and R radars, the description information comprising: position information, moving direction and moving speed of the O targets, and position information, rotating speed and detection range of the R radars, wherein O and R are positive integers; determining coverage effects of the R radars in different rotating states when the R radars detect the O targets according to the description information; wherein the rotating states comprise clockwise rotation, counterclockwise rotation and static state, and the coverage effects are used to represent time length proportions of the O targets in the detection range of the R radars within a preset time; and determining the rotating state of the R radars when the coverage effect is the best.

Description

Technical Field

[0001] This invention relates to the field of radar, and more particularly to a radar steering prediction method and apparatus for target detection. Background Technology

[0002] In vast areas requiring strict management, sensing technologies such as radar are commonly used to detect and track various moving targets, ensuring that monitoring and surveillance tasks can be carried out on these targets.

[0003] In these technological applications, the sensor network composed of radars consists of a limited number of radars in relatively fixed locations, while the number of monitored targets is variable and they often move randomly. Under these circumstances, achieving comprehensive monitoring of all moving targets is extremely challenging. Furthermore, the detection range and angle of a single radar are limited, further increasing the difficulty of comprehensive monitoring by the sensor network. Summary of the Invention

[0004] In view of this, the present invention provides a radar turning prediction method and apparatus for target detection to overcome the shortcomings of related technologies.

[0005] Specifically, the present invention is achieved through the following technical solution:

[0006] According to a first aspect of the present invention, a radar steering prediction method for target detection is provided, the method comprising:

[0007] Obtain descriptive information for O targets and R radars, wherein the descriptive information includes: the position information, direction of movement, and speed of movement of the O targets, and the position information, rotation speed, and detection range of the R radars, wherein O and R are positive integers;

[0008] The coverage effect of the R radars when detecting the O targets under different rotation states is determined based on the description information; wherein, the rotation state includes clockwise rotation, counterclockwise rotation, and stationary, and the coverage effect is used to characterize the proportion of time that the O targets are within the detection range of the R radars within a preset time period;

[0009] Determine the rotation state of the R radars when the coverage effect is optimal.

[0010] According to a second aspect of the present invention, a method for training a radar steering prediction model is provided, the method comprising:

[0011] Obtain description information for O targets and R radars, as well as the corresponding calibration rotation state; wherein, the description information includes: the position information, direction of movement, and speed of movement of the O targets, and the position information, rotation speed, and detection range of the R radars, and the rotation state includes clockwise rotation, counterclockwise rotation, and stationary, and O and R are positive integers;

[0012] The description information is input into the radar turning prediction model so that the R radar turning prediction models can determine the coverage effect of the R radars when detecting the O targets under different rotation states based on the description information; wherein, the coverage effect is used to characterize the proportion of time that the O targets are within the detection range of the R radars within a preset time period, and the calibration rotation state is determined in advance by a human based on the coverage effect.

[0013] The predicted rotation state of the R radars is determined when the coverage effect is optimal, and the radar turning prediction model is optimized based on the comparison between the predicted rotation state and the calibrated rotation state.

[0014] According to a third aspect of the present invention, a radar steering prediction device for target detection is provided, the device comprising:

[0015] The acquisition unit is used to acquire description information of O targets and R radars. The description information includes: the position information, direction of movement, and speed of movement of the O targets, and the position information, rotation speed, and detection range of the R radars, where O and R are positive integers.

[0016] The first determining unit is used to determine the coverage effect of the R radars when detecting the O targets in different rotation states according to the description information; wherein, the rotation state includes clockwise rotation, counterclockwise rotation, and stationary, and the coverage effect is used to characterize the proportion of time that the O targets are within the detection range of the R radars within a preset time.

[0017] The second determining unit is used to determine the rotation state of the R radars when the coverage effect is optimal.

[0018] According to a fourth aspect of the present invention, a training apparatus for a radar steering prediction model is provided, the apparatus comprising:

[0019] An acquisition unit is used to acquire description information of O targets and R radars, as well as the calibration rotation state corresponding to the description information; wherein, the description information includes: the position information, direction of movement, and speed of movement of the O targets, and the position information, rotation speed, and detection range of the R radars, and the rotation state includes clockwise rotation, counterclockwise rotation, and stationary, and O and R are positive integers;

[0020] An input unit is used to input the description information into the radar turning prediction model, so that the R radar turning prediction models can determine the coverage effect of the R radars when detecting the O targets under different rotation states based on the description information; wherein, the coverage effect is used to characterize the proportion of time that the O targets are within the detection range of the R radars within a preset time period, and the calibration rotation state is determined in advance by a human based on the coverage effect.

[0021] An optimization unit is used to determine the predicted rotation state of the R radars when the coverage effect is optimal, and to optimize the radar turning prediction model based on the comparison between the predicted rotation state and the calibrated rotation state.

[0022] According to a fifth aspect of the present invention, an electronic device is provided, comprising:

[0023] processor;

[0024] Memory used to store processor-executable instructions;

[0025] The processor implements the method as described in any one of the first or second aspects by executing the executable instructions.

[0026] According to a sixth aspect of the present invention, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in either the first or second aspect.

[0027] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0028] In embodiments of the present invention, the coverage effect of the radar when detecting the target under different rotation states is determined by the description information of the target and the radar. The coverage effect is used to characterize the proportion of time the target is within the radar's detection range within a preset time. The better the coverage effect, the more targets are within the radar's detection range, thus ensuring that the radar's detection range can cover the target to the greatest extent. Attached Figure Description

[0029] To more clearly illustrate the technical solutions of the present invention, the accompanying drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention, and those skilled in the art can obtain other drawings based on these drawings without any creative effort.

[0030] Figure 1 This is an architectural diagram of a radar and target system shown in an embodiment of the present invention;

[0031] Figure 2 This is a flowchart illustrating a radar steering prediction method for target detection, as shown in an embodiment of the present invention.

[0032] Figure 3 This is a flowchart illustrating a training method for a radar steering prediction model according to an embodiment of the present invention;

[0033] Figure 4 This is a schematic structural diagram of an electronic device shown in an embodiment of the present invention;

[0034] Figure 5 This is a block diagram of a radar steering prediction device for target detection, as shown in an embodiment of the present invention.

[0035] Figure 6 This is a block diagram of a training device for a radar steering prediction model, as shown in an embodiment of the present invention. Detailed Implementation

[0036] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the present invention.

[0037] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The singular forms “a,” “the,” and “the” used in this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0038] It should be understood that although the terms first, second, third, etc., may be used in this invention to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first information may also be referred to as second information without departing from the scope of this invention, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0039] An embodiment of a radar turning prediction method for target detection according to the present invention will be described in detail below with reference to the accompanying drawings.

[0040] In vast areas requiring strict management, radar and other sensing technologies are commonly used to detect and track various moving targets, ensuring the ability to monitor and surveillance these targets. In these applications, the radar-based sensor network consists of a limited number of relatively fixed radars, while the number of monitored targets is variable and often moves randomly. Under these circumstances, achieving comprehensive monitoring of all moving targets is extremely challenging. Furthermore, the detection range and angle of a single radar are limited, further increasing the difficulty of comprehensive monitoring by the sensor network.

[0041] This type of problem can be formalized as using a sensor network of R radars to monitor O moving targets in an area in real time at minimal cost, while maximizing the coverage of targets by ensuring that each target is detected by at least one radar. Figure 1 In the simulation environment shown, there are a total of 5 radars (r1-r5) and 9 targets (o1-o9). The radars can rotate clockwise or counterclockwise, while the targets are in a random walk state. In the current state, targets o6, o7, and o9 are not detected by any radar. By rotating radar r4 clockwise and radar r3 counterclockwise, the target coverage can be greatly improved.

[0042] In related technologies, radar turning is manually controlled to scan for moving targets within the sensing range in an attempt to detect as many targets as possible. This method is not only inefficient but also fails to achieve optimal results. To address the shortcomings of related technologies, this specification proposes a radar turning prediction method for target detection.

[0043] Figure 2 This is a flowchart illustrating an exemplary embodiment of the present invention for a radar steering prediction method for target detection, which may specifically include the following steps:

[0044] Step 202: Obtain description information for O targets and R radars. The description information includes: the position information, direction of movement, and speed of movement of the O targets, and the position information, rotation speed, and detection range of the R radars. O and R are positive integers.

[0045] Step 204: Determine the coverage effect of the R radars when detecting the O targets under different rotation states based on the description information; wherein, the rotation state includes clockwise rotation, counterclockwise rotation, and stationary, and the coverage effect is used to characterize the proportion of time that the O targets are within the detection range of the R radars within a preset time period.

[0046] Step 206: Determine the rotation state of the R radars when the coverage effect is optimal.

[0047] In this embodiment, the coverage effect of the radar when detecting the target under different rotation states is determined by the description information of the target and the radar. The coverage effect is used to characterize the proportion of time the target is within the radar's detection range within a preset time. The better the coverage effect, the more targets are within the radar's detection range, thus ensuring that the radar's detection range can cover the target to the greatest extent.

[0048] In one embodiment, determining the coverage effect of the R radars under different rotation states based on the description information includes: inputting the description information into a pre-trained radar turning prediction model, so that the radar turning prediction model determines the coverage effect of the R radars under different rotation states based on the description information.

[0049] Typical neural network models such as LSTM, RNN, and Transformer are used.

[0050] In one embodiment, the method further includes: visually displaying the motion state of the O targets, the R radars, and the detection range of the R radars within a preset time period.

[0051] To demonstrate the radar steering prediction process, a visual simulation platform is needed to intuitively display radar detection, allowing designers to verify the accuracy of radar steering based on simulation results. The following are the specific steps for converting radar and target position information onto a visual interface:

[0052] S01: Obtain the number of radars R, the number of targets O, and set the radar's sensing radius r, sensing angle φ, step angle θ, and the area width W and height H of the entire scene. Treat the entire scene as a coordinate system, with the top left corner of the scene as the origin, and determine the position (R_X, R_Y) and orientation angle R_Angle of each radar sensor, as well as the position (O_X, O_Y) of each target.

[0053] S02 processes the radar coordinates, target coordinates, and radar detection range to facilitate drawing and rendering on the system interface:

[0054] S0201, scale the position coordinates of the radar and the target to a unit coordinate range centered on the origin of the coordinate axes. Specifically, use the ratio of the horizontal coordinate of the radar to the area width W as the new horizontal coordinate, and the ratio of the vertical coordinate of the radar to the height H as the new vertical coordinate. Similarly, use the ratio of the horizontal coordinate of the target to the area width W as the new horizontal coordinate, and the ratio of the vertical coordinate of the target to the height H as the new vertical coordinate.

[0055] S0202 transforms the range of radar and target coordinates from unit coordinates centered at the origin to unit coordinates within the first quadrant for easier plotting.

[0056] S0203 sets the size of the system interface display area to: width real_W, height real_H. In practice, besides the radar and target, a certain amount of space needs to be reserved in the display area for the detection range, and the actual radar or target coordinates need to be mapped to the coordinates on the display area.

[0057] S03 indicates the radar's detection range.

[0058] In this embodiment, by visualizing the motion state, designers can verify the accuracy of radar steering based on simulation results.

[0059] In one embodiment, the method further includes: controlling the R radars to rotate according to a determined rotation state within a preset time period.

[0060] Figure 3 This is a flowchart illustrating a training method for a radar steering prediction model, as disclosed in an exemplary embodiment of the present invention. Specifically, it may include the following steps:

[0061] Step 302: Obtain description information for O targets and R radars, as well as the calibration rotation state corresponding to the description information; wherein, the description information includes: the position information, direction of movement, and speed of movement of the O targets, and the position information, rotation speed, and detection range of the R radars, and the rotation state includes clockwise rotation, counterclockwise rotation, and stationary, and O and R are positive integers;

[0062] Step 304: Input the description information into the radar turning prediction model so that the R radar turning prediction models can determine the coverage effect of the R radars when detecting the O targets under different rotation states based on the description information; wherein, the coverage effect is used to characterize the proportion of time that the O targets are within the detection range of the R radars within a preset time period, and the calibration rotation state is determined manually in advance based on the coverage effect.

[0063] Step 306: Determine the predicted rotation state of the R radars when the coverage effect is optimal, and optimize the radar turning prediction model based on the comparison results between the predicted rotation state and the calibrated rotation state.

[0064] In this embodiment, the coverage effect of the radar when detecting the target under different rotation states is determined by the description information of the target and the radar. The coverage effect is used to characterize the proportion of time the target is within the radar's detection range within a preset time. The better the coverage effect, the more targets are within the radar's detection range, thus ensuring that the radar's detection range can cover the target to the greatest extent.

[0065] Corresponding to the embodiments of the foregoing methods, the present invention also provides embodiments of electronic devices and apparatuses.

[0066] Figure 4 This is a schematic structural diagram of an electronic device according to an embodiment of the present invention. Please refer to it. Figure 4 At the hardware level, the device includes a processor 401, a network interface 402, memory 403, non-volatile memory 404, and an internal bus 405, and may also include other hardware required for business operations. One or more embodiments of the present invention can be implemented in software, for example, the processor 401 reads the corresponding computer program from the non-volatile memory 404 into memory 403 and then runs it. Of course, in addition to software implementation, one or more embodiments of the present invention do not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0067] Figure 5 This invention illustrates a block diagram of a radar steering prediction device for target detection. Please refer to... Figure 5 This device can be applied to, for example Figure 5 The device shown, in order to implement the technical solution described in this invention, includes:

[0068] The acquisition unit 502 is used to acquire description information of O targets and R radars. The description information includes: the position information, direction of movement, and speed of movement of the O targets, and the position information, rotation speed, and detection range of the R radars. The O and R are positive integers.

[0069] The first determining unit 504 is used to determine the coverage effect of the R radars when detecting the O targets in different rotation states according to the description information; wherein, the rotation state includes clockwise rotation, counterclockwise rotation, and stationary, and the coverage effect is used to characterize the proportion of time that the O targets are within the detection range of the R radars within a preset time.

[0070] The second determining unit 506 is used to determine the rotation state of the R radars when the coverage effect is optimal.

[0071] Optionally, the first determining unit 504 is specifically used for:

[0072] The description information is input into a pre-trained radar steering prediction model so that the radar steering prediction model can determine the coverage effect of the R radars under different rotation states based on the description information.

[0073] Optional, also includes:

[0074] Display unit 508 is used to visualize the motion state of the O targets, the R radars, and the detection range of the R radars within the preset time period.

[0075] Optionally, the description information may further include at least one of the following: relative azimuth information between the O targets and the R radars, and the angle between the movement direction of the O targets and the orientation of the R radars.

[0076] Optional, also includes:

[0077] The control unit 510 is used to control the R radars to rotate according to the determined rotation state within the preset time.

[0078] Figure 6 This invention provides a block diagram of a training device for a radar steering prediction model. Please refer to... Figure 6 This device can be applied to, for example Figure 6 The device shown, in order to implement the technical solution described in this invention, includes:

[0079] The acquisition unit 602 is used to acquire description information of O targets and R radars, as well as the calibration rotation state corresponding to the description information; wherein, the description information includes: the position information, movement direction, and movement speed of the O targets, and the position information, rotation speed, and detection range of the R radars, and the rotation state includes clockwise rotation, counterclockwise rotation, and stationary, and O and R are positive integers;

[0080] Input unit 604 is used to input the description information into the radar turning prediction model, so that the R radar turning prediction models can determine the coverage effect of the R radars when detecting the O targets in different rotation states according to the description information; wherein, the coverage effect is used to characterize the proportion of time that the O targets are within the detection range of the R radars within a preset time, and the calibration rotation state is determined in advance by a human based on the coverage effect.

[0081] The optimization unit 606 is used to determine the predicted rotation state of the R radars when the coverage effect is best, and to optimize the radar turning prediction model based on the comparison result between the predicted rotation state and the calibrated rotation state.

[0082] While this invention contains numerous specific details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily intended to describe features of specific embodiments of particular inventions. Certain features described in the multiple embodiments of this invention may also be implemented in combination in a single embodiment. On the other hand, various features described in a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation of a sub-combination.

[0083] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0084] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0085] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A radar steering prediction method for target detection, characterized in that, The method includes: Obtain descriptive information for O targets and R radars, wherein the descriptive information includes: the position information, direction of movement, and speed of movement of the O targets, and the position information, rotation speed, and detection range of the R radars, wherein O and R are positive integers; The coverage effect of the R radars when detecting the O targets under different rotation states is determined based on the description information; wherein, the rotation state includes clockwise rotation, counterclockwise rotation, and stationary, and the coverage effect is used to characterize the proportion of time that the O targets are within the detection range of the R radars within a preset time period; Determine the rotation state of the R radars when the coverage effect is optimal; Determining the coverage effect of the R radars under different rotation states based on the description information includes: The description information is input into a pre-trained radar steering prediction model so that the radar steering prediction model can determine the coverage effect of the R radars under different rotation states based on the description information. The description information also includes at least one of the following: the relative azimuth between the O targets and the R radars, and the relative relationship between the movement direction of the O targets and the turning direction of the R radars; The method further includes: The R radars are controlled to rotate according to a determined rotation state within a preset time period; The radar steering prediction model is trained using the following method: Obtain description information for O targets and R radars, as well as the corresponding calibration rotation state; wherein, the description information includes: the position information, direction of movement, and speed of movement of the O targets, and the position information, rotation speed, and detection range of the R radars, and the rotation state includes clockwise rotation, counterclockwise rotation, and stationary, and O and R are positive integers; The description information is input into the radar turning prediction model so that the R radar turning prediction models can determine the coverage effect of the R radars when detecting the O targets under different rotation states based on the description information; wherein, the coverage effect is used to characterize the proportion of time that the O targets are within the detection range of the R radars within a preset time period, and the calibration rotation state is determined in advance by a human based on the coverage effect. The predicted rotation state of the R radars is determined when the coverage effect is optimal, and the radar turning prediction model is optimized based on the comparison between the predicted rotation state and the calibrated rotation state.

2. The method according to claim 1, characterized in that, The method further includes: The motion status of the O targets, the R radars, and the detection range of the R radars within the preset time period is visualized.

3. A radar turning prediction device for target detection, characterized in that, The prediction device includes: The acquisition unit is used to acquire description information of O targets and R radars. The description information includes: the position information, direction of movement, and speed of movement of the O targets, and the position information, rotation speed, and detection range of the R radars, where O and R are positive integers. The first determining unit is used to determine the coverage effect of the R radars when detecting the O targets in different rotation states according to the description information; wherein, the rotation state includes clockwise rotation, counterclockwise rotation, and stationary, and the coverage effect is used to characterize the proportion of time that the O targets are within the detection range of the R radars within a preset time. The second determining unit is used to determine the rotation state of the R radars when the coverage effect is optimal; The first determining unit is specifically used for: The description information is input into a pre-trained radar steering prediction model so that the radar steering prediction model can determine the coverage effect of the R radars under different rotation states based on the description information. The description information also includes at least one of the following: the relative azimuth between the O targets and the R radars, and the relative relationship between the movement direction of the O targets and the turning direction of the R radars; The prediction device further includes: The control unit is used to control the R radars to rotate according to the determined rotation state within the preset time. The radar steering prediction model is trained using a training device, which includes: An acquisition unit is used to acquire description information of O targets and R radars, as well as the calibration rotation state corresponding to the description information; wherein, the description information includes: the position information, direction of movement, and speed of movement of the O targets, and the position information, rotation speed, and detection range of the R radars, and the rotation state includes clockwise rotation, counterclockwise rotation, and stationary, and O and R are positive integers; An input unit is used to input the description information into the radar turning prediction model, so that the R radar turning prediction models can determine the coverage effect of the R radars when detecting the O targets under different rotation states based on the description information; wherein, the coverage effect is used to characterize the proportion of time that the O targets are within the detection range of the R radars within a preset time period, and the calibration rotation state is determined in advance by a human based on the coverage effect. An optimization unit is used to determine the predicted rotation state of the R radars when the coverage effect is optimal, and to optimize the radar turning prediction model based on the comparison between the predicted rotation state and the calibrated rotation state.

4. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor implements the method as described in any one of claims 1 to 2 by executing the executable instructions.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 2.

Images