Radar-based target detection method, apparatus, device, and medium

Abstract

This invention discloses a radar-based target detection method, apparatus, device, and medium. The method includes: determining at least two sets of candidate point cloud data obtained by the radar performing at least two consecutive scans of the target to be detected; performing a scan operation at a preset time interval, where the preset time interval is less than a preset value; and merging the at least two sets of candidate point cloud data to obtain denser target point cloud data. This technical solution, based on the characteristics of radar's all-weather, all-time operation and high stability, and the slow movement of inland waterway vessels, improves the algorithm by generating dense target point cloud data through multiple cumulative scans of the target to be detected by the radar. This solves the problem of sparse point cloud data generated by radar when detecting vessels. Based on the denser target point cloud data, the target to be detected can be identified more accurately, and the measurement of target size becomes possible, making the monitoring of detected targets more intelligent and refined.

Description

Technical Field

[0001] This invention relates to the field of radar detection technology, and in particular to a target detection method, apparatus, equipment, and medium based on millimeter-wave radar. Background Technology

[0002] With technological advancements and the increasing demands for intelligence, automation, and precision in target monitoring, more and more technologies are being applied to target detection, including cameras, LiDAR, and even thermal imaging.

[0003] However, using technologies such as cameras, lidar, and even thermal imaging for target detection has certain limitations, leading to issues with accuracy and reliability, and even high costs. For example, cameras are susceptible to environmental factors such as light, air pollution, and lens dust; lidar operates in the near-visible infrared band, making it equally susceptible to air pollution and lens dust, and most high-beam lidar systems use mechanical scanning, resulting in mechanical reliability issues; thermal imaging sensors are sensitive to heat sources, easily affected by interference from other heat sources under sunlight, and are also relatively expensive. Therefore, improving the reliability of target detection becomes particularly important. Summary of the Invention

[0004] This invention provides a radar-based target detection method, apparatus, device, and medium to address the problem of low reliability in radar target detection.

[0005] According to one aspect of the present invention, a radar-based target detection method is provided, the method comprising:

[0006] Determine at least two sets of candidate point cloud data obtained by the radar performing at least two consecutive scan operations on the target to be detected, and perform a scan operation once at a preset time interval, wherein the preset time interval is less than a preset value;

[0007] At least two sets of candidate point cloud data are merged to obtain the target point cloud data;

[0008] The target to be detected is identified based on the target point cloud data.

[0009] According to another aspect of the present invention, a radar-based target detection device is provided, the device comprising:

[0010] The point cloud data acquisition module is used to determine at least two sets of candidate point cloud data obtained by the radar performing at least two consecutive scanning operations on the target to be detected. The scanning operation is performed once at a preset time interval, and the preset time interval is less than a preset value.

[0011] The point cloud data merging module is used to merge at least two sets of candidate point cloud data to obtain the target point cloud data.

[0012] The detection and recognition module is used to detect and recognize the target to be detected based on the target point cloud data.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the radar-based target detection method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the radar-based target detection method according to any embodiment of the present invention.

[0018] The technical solution of this invention involves performing at least two consecutive scans of the target at predetermined intervals using radar to obtain at least two sets of candidate point cloud data. These two sets of candidate point cloud data are then merged to obtain denser target point cloud data compared to a single scan. This denser target point cloud data is then used for target detection, identification, and size measurement. This technical solution leverages the all-weather, all-time operation, high reliability, and stability of millimeter-wave radar sensors, and the low-speed operation of inland waterway vessels (5-15 km / h). By improving the algorithm, the denser target point cloud data is generated through multiple scans of the target using millimeter-wave radar. This solves the problem of sparse point cloud data in ship or vehicle detection scenarios, improves the accuracy of target detection, enables target size measurement, and makes target monitoring more intelligent and precise.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of a radar-based target detection method according to Embodiment 1 of the present invention;

[0022] Figure 2a This is a schematic diagram of candidate point cloud data generated by a radar sensor in a single scan of a small number of ships according to an embodiment of the present invention;

[0023] Figure 2b This is a schematic diagram of candidate point cloud data generated by a radar sensor performing at least two scans on a small number of ships, according to an embodiment of the present invention.

[0024] Figure 3a This is a schematic diagram of candidate point cloud data generated by a radar sensor in a single scan of a majority of ships according to an embodiment of the present invention;

[0025] Figure 3b This is a schematic diagram of candidate point cloud data generated by a radar sensor performing at least two scans on a majority of ships according to an embodiment of the present invention;

[0026] Figure 4 This is a flowchart of a radar-based target detection method according to Embodiment 2 of the present invention;

[0027] Figure 5 This is a schematic diagram of candidate point cloud data generated by a radar sensor performing at least two scans on the top of a ship according to an embodiment of the present invention;

[0028] Figure 6 This is a schematic diagram of the structure of a radar-based target detection device according to Embodiment 3 of the present invention;

[0029] Figure 7 This is a schematic diagram of the structure of an electronic device that implements the radar-based target detection method according to an embodiment of the present invention. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] Example 1

[0033] Figure 1 This is a flowchart illustrating a radar-based target detection method according to Embodiment 1 of the present invention. This embodiment is applicable to detecting information such as the location and outline of ships on water and vehicles at intersections. The method can be executed by a radar-based target detection device, which can be implemented in hardware and / or software. This radar-based target detection device can be configured in any electronic device with network communication capabilities. Figure 1 As shown, the method includes:

[0034] S110. Determine at least two sets of candidate point cloud data obtained by the radar performing at least two consecutive scan operations on the target to be detected, and perform a scan operation once at a preset time interval, wherein the preset time interval is less than a preset value.

[0035] The radar can be a device that acquires candidate point cloud data of a target to be detected by emitting electromagnetic waves, and the radar can be a millimeter-wave radar; the radar mentioned below can be understood as a millimeter-wave radar. The candidate point cloud data can be point-like marks mapped onto a three-dimensional coordinate system after a single scan of the target by the millimeter-wave radar. The preset value can be the interval between each scan of the target by the millimeter-wave radar, and the preset value can be set to tens of milliseconds.

[0036] As an optional but not limited implementation, determining at least two sets of candidate point cloud data obtained by the radar performing at least two consecutive scans of the target to be detected may include steps A1-A2:

[0037] Step A1: Control the radar to perform a scan operation on the moving target to be detected once at preset time intervals.

[0038] Specifically, millimeter-microwave radar can be controlled by infrared sensors or wireless communication devices to perform a scan operation on the moving target at preset intervals.

[0039] For example, the scanning direction of millimeter-wave radar can be controlled by remote control devices such as infrared sensors or wireless communication, scanning inland waterway vessels once every tens of milliseconds, or scanning slow-moving vehicles at intersections once every tens of milliseconds.

[0040] Step A2: Obtain at least two sets of candidate point cloud data obtained by performing at least two consecutive scanning operations on the target to be detected using radar.

[0041] Specifically, when a millimeter-wave radar performs a scanning operation on a target to be detected, it generates candidate point cloud data. If the millimeter-wave radar performs at least two consecutive scanning operations on the target to be detected, it can obtain at least two sets of candidate point cloud data.

[0042] For example, millimeter-wave radar scans inland waterway vessels traveling at speeds of only 5-15 km / h every tens of milliseconds and generates candidate point cloud data for this millimeter-wave radar scan. Each generated candidate point cloud data is independent of the others. Alternatively, millimeter-wave radar can scan vehicles at intersections every tens of milliseconds and generate candidate point cloud data for this millimeter-wave radar scan. Each generated candidate point cloud data is independent of the others.

[0043] As an optional but not limited implementation, controlling the radar to perform a scan operation on the moving target to be detected once at preset time intervals may include steps A11-A13:

[0044] Step A11: Determine the relative speed between the target to be detected and the radar as detected by the radar.

[0045] Specifically, the millimeter-wave radar transmits electromagnetic waves to the target and records the frequency of the transmitted electromagnetic waves. The millimeter-wave radar receives the echo and records the frequency of the echo. The relative speed between the millimeter-wave radar and the target is determined based on the difference between the transmitted electromagnetic frequency and the echo frequency.

[0046] For example, millimeter-wave radar can obtain the relative speed between the radar and a ship by using the frequency difference between the received echo and the transmitted wave and the Doppler effect principle. The radar can also transmit electromagnetic waves to a slow-moving vehicle at an intersection and receive the echo. Based on the frequency difference between the transmitted electromagnetic wave and the echo, the Doppler effect principle is used to obtain the relative speed between the radar and the vehicle.

[0047] Step A12: Determine the preset duration for scanning the target to be detected by radar based on the relative velocity. The greater the relative velocity, the smaller the preset duration.

[0048] Specifically, the preset duration for scanning the target by the millimeter-wave radar is determined based on the relative velocity between the millimeter-wave radar and the target to be detected. When the relative velocity is greater, a smaller preset duration is used in order to avoid missing detections when the millimeter-wave radar detects the target. The preset duration can be set to tens of milliseconds to increase the scanning frequency of the target to be detected.

[0049] Step A13: Control the radar to perform a scan operation on the target to be detected once at preset intervals.

[0050] Specifically, based on the preset duration for the millimeter-wave radar to scan the target to be detected, determined by the above steps, the millimeter-wave radar is controlled to perform a scan of the target to be detected once at corresponding preset intervals.

[0051] As an optional but not limited implementation, after the control radar performs a scan operation on the target to be detected at preset intervals, steps A3-A4 are also included:

[0052] Step A3: Determine the cumulative amount of candidate point cloud data obtained from at least one consecutive scan operation;

[0053] Specifically, each time the millimeter-wave radar performs a scan operation on the target to be detected, it can obtain candidate point cloud data corresponding to this scan. It is necessary to accumulate and calculate the candidate point cloud data generated by the millimeter-wave radar for each scan of the target to be detected to obtain the cumulative amount of candidate point cloud data.

[0054] Step A4: If the cumulative amount of candidate point cloud data is detected to be greater than the preset cumulative amount threshold, then stop performing scanning operations on the target to be detected by radar.

[0055] Specifically, according to step A3, the cumulative amount of candidate point cloud data is obtained, and the relationship between the cumulative amount of candidate point cloud data detected by the millimeter-wave radar and the preset cumulative amount threshold is determined. When the cumulative amount of candidate point cloud data is greater than the preset cumulative amount threshold, the millimeter-wave radar will stop performing scanning operations on the target to be detected.

[0056] S120. Merge at least two sets of candidate point cloud data to obtain the target point cloud data.

[0057] Specifically, the millimeter-wave radar scans the target to be detected and generates candidate point cloud data. The point cloud data generated by the millimeter-wave radar scanning the target to be detected at least twice are merged to form a denser target point cloud data compared to a single scan. The dense target point cloud data can more closely approximate the actual size of ships and vehicles.

[0058] For example, such as Figure 2a As shown, a millimeter-wave radar performs a single scan of two ships, generating candidate point cloud data for both ships. The candidate point cloud data is sparsely distributed in a three-dimensional coordinate system, and the intelligent algorithm cannot accurately segment the candidate point cloud data for different ships. However, as... Figure 2b As shown, candidate point cloud data generated by 10 scans of a ship within 500 milliseconds from a millimeter-wave radar are merged to generate target point cloud data. The target point cloud data is densely distributed in a three-dimensional coordinate system, and the intelligent algorithm can accurately segment different ships. Figure 3a and 3b As shown, when the number of ships to be detected increases from two to four, the intelligent algorithm is more likely to segment and identify ships from the dense candidate point cloud data compared to the sparse candidate point cloud data.

[0059] S130. Detect and identify the target to be detected based on the target point cloud data.

[0060] As an optional but not limited implementation, detecting and identifying the target based on the target point cloud data may include steps B1-B2:

[0061] Step B1: Determine the height difference between the highest point of the target to be detected and the first preset marker based on the candidate point cloud data or target point cloud data;

[0062] Specifically, based on the candidate point cloud data or target point cloud data of the target to be detected, or based on the coordinates of the target to be detected, and knowing the information that the millimeter-wave radar is installed at the position of the first preset marker, the height difference between the highest point of the target to be detected and the first preset marker is calculated according to the distance calculation formula.

[0063] For example, based on the candidate point cloud data or target point cloud data of the target to be detected, or based on the coordinates of the target to be detected, and knowing information such as the specific location of the millimeter-wave radar installed on the bridge, the height difference between the highest point of the ship and the bridge or the height difference between the highest point of the vehicle and the viaduct can be calculated according to the distance calculation formula.

[0064] Step B2: Based on the height difference between the highest point of the target to be detected and the first preset marker, determine whether the target to be detected will collide with the first preset marker when it moves under the first preset marker.

[0065] Specifically, the height difference between the highest point of the target to be detected and the first preset marker is obtained, and it is determined whether the highest point of the target to be detected will collide with the first preset marker when the highest point of the target to be detected moves past the building where the first preset marker is located.

[0066] Optionally, the movement trajectory of the target to be detected can be determined based on the candidate point cloud data obtained by performing at least two consecutive scanning operations.

[0067] Specifically, the millimeter-wave radar scans the target to be detected at least twice, acquires at least two sets of candidate point cloud data, and determines the movement trajectory of the target to be detected based on the candidate point cloud data.

[0068] Optionally, based on the movement trajectory of the target to be detected and the position of the second preset marker, it can be predicted whether the target to be detected will collide with the second preset marker.

[0069] Specifically, based on the movement trajectory of the target to be detected and the position of the second preset marker, it can be determined whether the target to be detected will collide with the second preset marker.

[0070] For example, the height difference between the highest point of the vessel to be detected and the bridge can be obtained to determine whether the highest point of the vessel to be detected will collide with the bridge when it passes under the bridge. Furthermore, by obtaining the horizontal coordinates and movement trajectory of the vessel to be detected, and knowing the specific location of the millimeter-wave radar on the bridge pier, it can be determined whether the vessel to be detected will collide with the bridge pier where the millimeter-wave radar is located. If it is detected that the vessel to be detected may collide with the bridge or other structures, the vessel can be alerted through an alarm display screen or a loudspeaker.

[0071] For example, when this method is applied to vehicle detection, it is necessary to obtain the height difference between the highest point of the vehicle to be detected and the overpass to determine whether the highest point of the vehicle to be detected will collide with the bridge when it passes under the bridge. By obtaining the horizontal coordinates and movement trajectory of the vehicle to be detected, and knowing the specific location of the millimeter-wave radar on the building, it is possible to determine whether the vehicle to be detected will collide with the building where the millimeter-wave radar is installed. If it is detected that the vehicle to be detected will collide with the building where the millimeter-wave radar is located, the vehicle can be alerted through an alarm display screen or a loudspeaker.

[0072] In this embodiment, millimeter-wave radar performs at least two consecutive scans of the target at predetermined time intervals to obtain at least two sets of candidate point cloud data. These two sets of candidate point cloud data are then merged to obtain denser target point cloud data compared to a single scan. Based on this denser target point cloud data, the target is detected, identified, and its size is measured. This technical solution leverages the all-weather, all-time operation, high reliability, and stability of millimeter-wave radar sensors, and the low-speed operation of inland waterway vessels (5-15 km / h). An improved algorithm generates denser target point cloud data by accumulating multiple scans of the target using millimeter-wave radar. This solves the problem of sparse point cloud data in ship or vehicle detection scenarios. The target point cloud data generated by millimeter-wave radar can detect ship dimensions, improving the accuracy of target detection and making the monitoring of the target more intelligent and precise.

[0073] Example 2

[0074] Figure 4 This is a flowchart of a radar-based target detection method provided in Embodiment 2 of the present invention. This embodiment details how radar identifies the contour information of the target to be detected. Figure 4 As shown, the method includes:

[0075] S210. Determine at least two sets of candidate point cloud data obtained by the radar performing at least two consecutive scan operations on the target to be detected, and perform a scan operation once at a preset time interval, wherein the preset time interval is less than a preset value.

[0076] Specifically, the millimeter-wave radar performs a scan of the target at preset intervals, and performs at least two scans of the target and acquires at least two sets of candidate point cloud data.

[0077] S220. Merge at least two sets of candidate point cloud data to obtain the target point cloud data.

[0078] Specifically, the millimeter-wave radar scans the target to be detected and generates candidate point cloud data. The candidate point cloud data generated by the millimeter-wave radar scanning the target to be detected at least twice are merged to form target point cloud data that is denser than that of a single scan.

[0079] S230. Determine the displacement of the target to be detected during at least two consecutive scanning operations performed by the radar.

[0080] As an optional but not limited implementation, determining the displacement of the target to be detected during at least two consecutive radar scans may include steps C1-C2:

[0081] Step C1: Determine the relative velocity between the target to be detected by the radar and the radar. The relative velocity is calculated based on the frequency difference between the radar echo and the radar transmitted wave using the Doppler effect principle.

[0082] Specifically, the millimeter-wave radar transmits electromagnetic waves to the target and acquires the echo returned by the target. Based on the frequency difference between the transmitted wave and the echo of the millimeter-wave radar, the relative velocity between the target and the millimeter-wave radar is calculated using the Doppler effect.

[0083] Step C2: Determine the displacement of the target to be detected during at least two consecutive scanning operations of the radar based on the relative velocity.

[0084] Specifically, the millimeter-wave radar scans the target to be detected once every tens of milliseconds. It can obtain the total time of at least two scans of the target to be detected by the millimeter-wave radar. The total time of scanning the target to be detected can be represented by the product of the number of scans of the target to be detected and the time interval between scans. According to the velocity formula, the displacement of the target to be detected after at least two continuous scans by the millimeter-wave radar can be determined by the relative velocity of the target to be detected and the total time of scanning the target to be detected.

[0085] S240. Based on the displacement, remove reference point cloud data from the target point cloud data to update the target point cloud data; wherein, the reference point cloud data are the point cloud data located at both ends in the movement direction of the target to be detected in the target point cloud data, and the sum of the lengths of the reference point cloud data along the movement direction of the target to be detected is the same as the length corresponding to the displacement.

[0086] Specifically, the target to be detected moves by a certain amount of displacement in the direction of movement. The reference point cloud data at one end of the direction of movement is retained in the target point cloud data, while the reference point cloud data in the opposite direction of the target to be detected is removed, thereby achieving the purpose of updating the target point cloud data. The amount of reference point cloud data is equal to the amount of displacement.

[0087] For example, such as Figure 5 As shown, millimeter-wave radar continuously scans ships multiple times and performs merging operations to obtain dense target point cloud data. When the ship moves a certain amount in the displacement direction, reference point cloud data opposite to the ship's movement direction needs to be removed from the target point cloud data to obtain new target point cloud data and calculate the corresponding ship's contour information. When detecting vehicles at intersections, millimeter-wave radar continuously scans vehicles multiple times and performs merging operations to obtain dense target point cloud data. When a vehicle moves a certain amount in the movement direction, reference point cloud data opposite to the vehicle's movement direction needs to be removed from the target point cloud data to obtain new target point cloud data and calculate the corresponding vehicle's contour information.

[0088] S250. Detect and identify the contour size information of the target to be detected based on the target point cloud data.

[0089] Specifically, based on dense target point cloud data that more closely approximates the actual size of the target to be detected, the target point cloud data of the target to be detected can be segmented, and the contour size information of the target to be detected can be calculated according to the length, width and coordinate system ratio.

[0090] S260. Adjust the length of the outline dimension information of the target to be detected by reducing the displacement amount.

[0091] Specifically, the calculation of the target contour size information is based on the target point cloud data. When the target moves a certain amount of displacement in the direction of movement, the target point cloud data needs to remove the reference point cloud data with the same displacement in the opposite direction of the target movement to obtain updated target point cloud data. The intelligent algorithm recalculates the target contour size information based on the updated target point cloud data. Therefore, the recalculated target contour information is the difference between the previous target contour information and the displacement.

[0092] In this embodiment, the millimeter-wave radar performs at least two consecutive scans of the target at predetermined time intervals to obtain at least two sets of candidate point cloud data. These two sets of candidate point cloud data are then merged to obtain denser target point cloud data compared to a single scan. The denser target point cloud data is then used to detect the target's contour information. This technical solution, based on the properties of millimeter waves emitted by the millimeter-wave radar, and leveraging the all-weather, all-time operation, high reliability and stability of millimeter-wave radar sensors, as well as the low-speed operation of inland waterway vessels (5-15 km / h), improves the algorithm. By accumulating multiple scans of the target by the millimeter-wave radar, it generates denser target point cloud data, solving the problem of sparse point cloud data in ship or vehicle detection scenarios. The radar can detect ship dimensions, improving the accuracy of target detection.

[0093] Example 3

[0094] Figure 6 This is a schematic diagram of a radar-based target detection device provided in Embodiment 3 of the present invention. Figure 6 As shown, the device includes:

[0095] The point cloud data acquisition module 310 is used to determine at least two sets of candidate point cloud data obtained by the radar performing at least two consecutive scanning operations on the target to be detected. The scanning operation is performed once at a preset time interval, and the preset time interval is less than a preset value.

[0096] The point cloud data merging module 320 is used to merge at least two sets of candidate point cloud data to obtain target point cloud data.

[0097] The detection and recognition module 330 is used to detect and recognize the target to be detected based on the target point cloud data.

[0098] In this embodiment of the application, the point cloud data acquisition module 310 includes:

[0099] The target scanning unit is used to control the radar to perform a scanning operation on the moving target at preset intervals.

[0100] The point cloud data acquisition unit is used to acquire at least two sets of candidate point cloud data obtained by performing at least two consecutive scanning operations on the target to be detected using millimeter-wave radar.

[0101] In this embodiment of the application, the target scanning unit is specifically used for:

[0102] Determine the relative velocity between the target to be detected and the radar, as detected by the radar.

[0103] The preset time for scanning the target to be detected by radar is determined based on the relative velocity. The greater the relative velocity, the smaller the preset time.

[0104] The control radar performs a scan operation on the target to be detected once at preset intervals;

[0105] Determine the cumulative amount of candidate point cloud data obtained from at least one consecutive scan operation;

[0106] If the cumulative amount of candidate point cloud data is detected to be greater than the preset cumulative amount threshold, the scanning operation of the target to be detected by radar will be stopped.

[0107] In this embodiment of the application, the detection and identification module 330 includes:

[0108] The displacement determination unit is used to determine the displacement of the target to be detected during at least two consecutive scanning operations performed by the radar.

[0109] A point cloud data update unit is used to remove reference point cloud data from the target point cloud data based on the displacement amount, so as to update the target point cloud data; wherein, the reference point cloud data are the point cloud data located at both ends in the movement direction of the target to be detected in the target point cloud data, and the sum of the lengths of the reference point cloud data along the movement direction of the target to be detected is the same as the length corresponding to the displacement amount.

[0110] A contour size detection unit is used to detect and identify the contour size information of the target to be detected based on the target point cloud data;

[0111] The displacement determination unit is used to determine the displacement of the target to be detected during at least two consecutive scanning operations performed by the radar.

[0112] The contour size adjustment unit is used to reduce and adjust the length in the contour size information of the target to be detected based on the displacement amount.

[0113] In this embodiment of the application, the displacement determination unit is specifically used for:

[0114] The relative velocity between the target to be detected and the radar is determined by radar detection, and the relative velocity is calculated based on the frequency difference between the radar echo and the radar transmitted wave using the Doppler effect principle;

[0115] The displacement of the target to be detected during at least two consecutive scanning operations of the radar is determined based on the relative velocity.

[0116] In this embodiment of the application, the device further includes:

[0117] The height difference determination module is used to determine the height difference between the highest point of the target to be detected and the first preset marker based on the candidate point cloud data or the target point cloud data.

[0118] The marker collision judgment module is used to determine whether the target to be detected will collide with the first preset marker when it moves from below the first preset marker, based on the height difference between the highest point of the target to be detected and the first preset marker.

[0119] The trajectory determination module is used to determine the trajectory of the target to be detected based on the candidate point cloud data obtained by performing at least two consecutive scanning operations.

[0120] The marker collision prediction module is used to predict whether the target to be detected will collide with the second preset marker based on the movement trajectory of the target to be detected and the position of the second preset marker.

[0121] The radar-based target detection device provided in the embodiments of the present invention can execute the radar-based target detection method provided in any of the embodiments of the present invention, and has the corresponding functions and beneficial effects of executing the radar-based target detection method. For details, please refer to the relevant operations of the radar-based target detection method in the foregoing embodiments.

[0122] Example 4

[0123] Figure 7A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0124] like Figure 7 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0125] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0126] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as millimeter-wave radar-based target detection methods.

[0127] In some embodiments, the radar-based target detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the radar-based target detection method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the radar-based target detection method by any other suitable means (e.g., by means of firmware).

[0128] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0129] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0130] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0131] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0132] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0133] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0134] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0135] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A radar-based target detection method, characterized by, The method includes: Determine at least two sets of candidate point cloud data obtained by the radar performing at least two consecutive scan operations on the target to be detected, and perform a scan operation once at a preset time interval, wherein the preset time interval is less than a preset value; At least two sets of candidate point cloud data are merged to obtain the target point cloud data; The target to be detected is identified based on the target point cloud data; The detection and identification of the target based on the target point cloud data includes: Determine the displacement of the target under test during at least two consecutive radar scans; Based on the displacement, reference point cloud data located at one end of the movement direction in the target point cloud data is retained, while reference point cloud data located at the opposite end of the movement direction is removed to update the target point cloud data; wherein, the reference point cloud data are the point cloud data located at both ends in the movement direction of the target to be detected in the target point cloud data, and the sum of the lengths of the reference point cloud data along the movement direction of the target to be detected is the same as the length corresponding to the displacement. The contour size information of the target to be detected is identified based on the target point cloud data.

2. The method of claim 1, wherein, Identify at least two sets of candidate point cloud data obtained by the radar performing at least two consecutive scans of the target to be detected, including: The control radar performs a scan operation on the moving target to be detected once at preset time intervals; Acquire at least two sets of candidate point cloud data obtained by performing at least two consecutive scanning operations on the target to be detected using radar.

3. The method of claim 2, wherein, The control radar performs a scan operation on the target to be detected once at preset time intervals, including: Determine the relative velocity between the target to be detected and the radar, as detected by the radar. The preset time for scanning the target to be detected by radar is determined based on the relative velocity. The greater the relative velocity, the smaller the preset time. The control radar performs a scan operation on the target to be detected once at preset intervals.

4. The method of claim 2, wherein, After the control radar performs a scan operation on the target to be detected at preset time intervals, it also includes: Determine the cumulative amount of candidate point cloud data obtained from at least one consecutive scan operation; If the cumulative amount of candidate point cloud data is detected to be greater than the preset cumulative amount threshold, the scanning operation of the target to be detected by radar will be stopped.

5. The method of claim 1, wherein, Detecting and identifying the target based on the target point cloud data includes: The contour size information of the target to be detected is detected and identified based on the target point cloud data; Determine the displacement of the target under test during at least two consecutive radar scans; Based on the displacement, the length of the target's outline dimensions is reduced in the opposite direction.

6. The method according to claim 1 or 5, characterized in that, Determine the displacement of the target under test during at least two consecutive radar scans, including: The relative velocity between the target to be detected and the radar is determined by radar detection, and the relative velocity is calculated based on the frequency difference between the radar echo and the radar transmitted wave using the Doppler effect principle; The displacement of the target to be detected during at least two consecutive scanning operations of the radar is determined based on the relative velocity.

7. The method of claim 1, wherein, The method further includes: The height difference between the highest point of the target to be detected and the first preset marker is determined based on the candidate point cloud data or the target point cloud data. Based on the height difference between the highest point of the target to be detected and the first preset marker, it is determined whether the target to be detected will collide with the first preset marker when it moves under the first preset marker.

8. The method of claim 1, wherein, The method further includes: The movement trajectory of the target to be detected is determined based on the candidate point cloud data obtained by performing at least two consecutive scanning operations. Based on the movement trajectory of the target to be detected and the position of the second preset marker, it is predicted whether the target to be detected will collide with the second preset marker.

9. A radar-based target detection apparatus, characterized by comprising: include: The point cloud data acquisition module is used to determine at least two sets of candidate point cloud data obtained by the radar performing at least two consecutive scanning operations on the target to be detected. The scanning operation is performed once at a preset time interval, and the preset time interval is less than a preset value. The point cloud data merging module is used to merge at least two sets of candidate point cloud data to obtain the target point cloud data. The detection and recognition module is used to detect and recognize the target to be detected based on the target point cloud data; The detection and identification of the target based on the target point cloud data includes: Determine the displacement of the target under test during at least two consecutive radar scans; Based on the displacement, reference point cloud data located at one end of the movement direction in the target point cloud data is retained, while reference point cloud data located at the opposite end of the movement direction is removed to update the target point cloud data; wherein, the reference point cloud data are the point cloud data located at both ends in the movement direction of the target to be detected in the target point cloud data, and the sum of the lengths of the reference point cloud data along the movement direction of the target to be detected is the same as the length corresponding to the displacement. The contour size information of the target to be detected is identified based on the target point cloud data.

10. An electronic device, comprising: The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the radar-based target detection method according to any one of claims 1-8.

11. A computer readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the radar-based target detection method according to any one of claims 1-8.

Images