A method, system, and platform for obstruction detection of vehicle-mounted millimeter-wave radar.

Abstract

This invention discloses an occlusion detection method, system, and platform suitable for vehicle-mounted millimeter-wave radar. The method generates and acquires first data corresponding to the vehicle-mounted millimeter-wave radar based on target objects in the surrounding environment. Based on the first data, second and third data corresponding to the current frame are generated. Based on the second data, first preset parameters are generated and acquired. Based on the first preset parameters, it is determined and marked whether a target point is a valid target point. Fourth, fifth, and sixth data corresponding to the preset frame are generated and acquired. Based on the fourth, fifth, and sixth data, corresponding seventh data is calculated and generated. Based on the seventh data, it is determined in real time whether the vehicle-mounted millimeter-wave radar is obstructed. The corresponding system and platform can detect whether the vehicle-mounted millimeter-wave radar is obstructed in real time, improving the accuracy of vehicle-mounted millimeter-wave radar identification.

Description

Technical Field

[0001] This invention belongs to the field of millimeter-wave radar detection and processing technology, specifically relating to an obstruction detection method, system, and platform suitable for vehicle-mounted millimeter-wave radar. Background Technology

[0002] Currently, automotive millimeter-wave radar primarily provides accurate target information for the autonomous driving function of automobiles and is one of the important sensors for automobiles to perceive their surroundings. However, when millimeter-wave radar is obstructed by objects such as rain, snow, and dust during use, it may result in missed or false detections of targets, leading to a decrease in the detection performance of millimeter-wave radar. In severe cases, it may even cause the detection function of millimeter-wave radar to fail, making it unable to detect targets such as vehicles in the surrounding environment.

[0003] When millimeter-wave radar is blocked, common obstructions include dust, mud, and snow. Mud can significantly reduce the number of targets and concentrate the energy distribution in the echo within a very small area. Dust can reduce the echo energy received by the millimeter-wave radar, resulting in a decrease in the number of targets detected and a corresponding reduction in the radar's detection range. Heavy rain and snow can reduce the energy in the radar echo, and because rain and snow have a certain degree of wave transmission, the channel uniformity of the target will be significantly worse.

[0004] Furthermore, different obstructions have different characteristics, so a single feature cannot be used for identification when making an occlusion judgment. It is necessary to comprehensively consider the recognition accuracy of multiple scenarios, and use the radar's maximum detection range, the number of targets, and the channel balance of the targets as recognition features. Statistical analysis of the changing patterns of multiple frames is needed to make occlusion judgments in order to improve the accuracy of the recognition.

[0005] Therefore, in view of the above-mentioned technical problems and defects, there is an urgent need to design and develop an obstruction detection method, system and platform suitable for vehicle-mounted millimeter-wave radar. Summary of the Invention

[0006] To overcome the shortcomings and difficulties of the existing technology, the purpose of this invention is to propose an obstruction detection method, system and platform suitable for vehicle-mounted millimeter-wave radar, which can detect whether there is obstruction in vehicle-mounted millimeter-wave radar in real time.

[0007] The first objective of this invention is to provide an obstruction detection method suitable for vehicle-mounted millimeter-wave radar; the second objective of this invention is to provide an obstruction detection system suitable for vehicle-mounted millimeter-wave radar; and the third objective of this invention is to provide an obstruction detection platform suitable for vehicle-mounted millimeter-wave radar.

[0008] The first objective of this invention is achieved as follows: the method comprises the following steps:

[0009] Based on the target objects in the surrounding environment, first data corresponding to the vehicle-mounted millimeter-wave radar is generated and acquired. Based on the first data, second data and third data corresponding to the current frame are generated respectively. The first data is target point cloud information data; the second data is the channel imbalance data of each target in the current frame; and the third data is the mean value data of the channel imbalance data in the current frame.

[0010] Based on the second data, generate and obtain the first preset parameters, and based on the first preset parameters, determine and mark whether the target point is a valid target point; if so, proceed to the next step; otherwise, repeat the above steps.

[0011] The fourth, fifth, and sixth data corresponding to the preset frame are generated and acquired respectively, and the corresponding seventh data is calculated based on the fourth, fifth, and sixth data; wherein, the fourth data is the number of valid targets in the most recent preset frame; the fifth data is the farthest detection distance of valid targets in the most recent preset frame; the sixth data is the mean channel imbalance data in the most recent preset frame; and the seventh data is the weighted summation data corresponding to the target point cloud in the most recent preset frame.

[0012] Based on the seventh data, it is determined in real time whether there is any obstruction to the vehicle-mounted millimeter-wave radar.

[0013] Furthermore, the step of generating and acquiring first data corresponding to the vehicle-mounted millimeter-wave radar based on target objects in the surrounding environment, and generating second and third data corresponding to the current frame based on the first data, further includes:

[0014] Generate first control data corresponding to the vehicle-mounted millimeter-wave radar; wherein, the first control data is control command data for outputting target point cloud information;

[0015] Based on the first control data and the target object in the surrounding environment, and in conjunction with the frequency-modulated continuous wave, corresponding first data is generated.

[0016] Furthermore, the step of generating and obtaining a first preset parameter based on the second data, and marking and determining whether a target point is a valid target point based on the first preset parameter, further includes:

[0017] Based on the second data, generate and obtain the first preset parameters corresponding to the vehicle-mounted millimeter-wave radar;

[0018] Based on the first preset parameter, the corresponding target point is determined and marked. If the second data is greater than the first preset parameter, the target point is marked as an invalid target; if the second data is less than the first preset parameter, the target point is marked as a valid target.

[0019] Furthermore, the step of generating and acquiring the fourth, fifth, and sixth data corresponding to the preset frame, and calculating and generating the corresponding seventh data based on the fourth, fifth, and sixth data, further includes:

[0020] Generate and acquire at least one set of eighth data, wherein the eighth data includes data on occlusion and non-occlusion states;

[0021] Based on the eighth data, corresponding ninth, tenth, and eleventh data are generated respectively; wherein, the ninth data is the weighted data of the maximum detection distance; the tenth data is the weighted data of the number of targets; and the eleventh data is the weighted data of the channel imbalance.

[0022] Furthermore, the preset frame is greater than or equal to 100;

[0023] The calculation formula for generating the corresponding seventh data is as follows:

[0024]

[0025] In the formula, q1 is the weight of the maximum detection range, q2 is the weight of the number of targets, q3 is the weight of the channel imbalance, q1,q2,q3∈(0,1), q1+q2+q3=1, R wave For the radar to be designed, the maximum detection range of the waveform is N. thred CM is the target quantity threshold, is a constant. thred is the threshold for channel imbalance, and is a constant.

[0026] Furthermore, the step of determining in real time whether the vehicle-mounted millimeter-wave radar is obstructed based on the seventh data also includes:

[0027] A second preset parameter is generated and obtained, and based on the seventh data, it is determined whether the vehicle-mounted millimeter-wave radar is obstructed, and a corresponding obstruction flag is output. If the seventh data is less than the second preset parameter, it is determined that there is obstruction, and a corresponding obstruction flag is output. If the seventh data is greater than the second preset parameter, it is determined that there is no obstruction, and a corresponding no obstruction flag is output.

[0028] The second objective of this invention is achieved as follows: the system is used to implement the occlusion detection method suitable for vehicle-mounted millimeter-wave radar, the system comprising:

[0029] The first data generation unit is used to generate and acquire first data corresponding to the vehicle-mounted millimeter-wave radar based on target objects in the surrounding environment, and to generate second data and third data corresponding to the current frame based on the first data; wherein, the first data is target point cloud information data; the second data is the channel imbalance data of each target in the current frame; and the third data is the mean value data of the channel imbalance data in the current frame.

[0030] The first data determination unit is used to generate and obtain the first preset parameters based on the second data, and determine and mark whether the target point is a valid target point based on the first preset parameters.

[0031] The second data generation unit is used to generate and acquire the fourth, fifth, and sixth data corresponding to the preset frame, and to calculate and generate the corresponding seventh data based on the fourth, fifth, and sixth data; wherein, the fourth data is the number of valid targets in the most recent preset frame; the fifth data is the farthest detection distance of valid targets in the most recent preset frame; the sixth data is the average channel imbalance data in the most recent preset frame; and the seventh data is the weighted summation data corresponding to the target point cloud in the most recent preset frame.

[0032] The second data determination unit is used to determine in real time whether the vehicle-mounted millimeter-wave radar is obstructed based on the seventh data.

[0033] Furthermore, the first data generation unit further includes:

[0034] The first generation module is used to generate first control data corresponding to the vehicle-mounted millimeter-wave radar; wherein, the first control data is control command data for outputting target point cloud information;

[0035] The second generation module is used to generate corresponding first data based on the first control data, the target object in the surrounding environment, and the frequency-modulated continuous wave.

[0036] And / or, the first data determination unit further includes:

[0037] The third generation module is used to generate and obtain the first preset parameters corresponding to the vehicle-mounted millimeter-wave radar based on the second data;

[0038] The first determination module is used to determine and mark the corresponding target points based on the first preset parameters;

[0039] And / or, the second data generation unit further includes:

[0040] The fourth generation module is used to generate and acquire at least one set of eighth data, wherein the eighth data includes data on occlusion and non-occlusion states;

[0041] The fifth generation module is used to generate corresponding ninth, tenth, and eleventh data based on the eighth data; wherein the ninth data is weighted data for the maximum detection distance; the tenth data is weighted data for the number of targets; and the eleventh data is weighted data for the channel imbalance.

[0042] And / or, the second data determination unit further includes:

[0043] The sixth generation module is used to generate and obtain the second preset parameters, and based on the seventh data, determine whether the vehicle-mounted millimeter-wave radar is obstructed, and output the corresponding obstruction flag.

[0044] Furthermore, the preset frame is greater than or equal to 100;

[0045] The calculation formula for generating the corresponding seventh data is as follows:

[0046]

[0047] In the formula, q1 is the weight of the maximum detection range, q2 is the weight of the number of targets, q3 is the weight of the channel imbalance, q1,q2,q3∈(0,1), q1+q2+q3=1, R wave For the radar to be designed, the maximum detection range of the waveform is N. thred CM is the target quantity threshold, is a constant. thred is the threshold for channel imbalance, and is a constant.

[0048] The third objective of this invention is achieved as follows: it includes a processor, a memory, and an obstruction detection platform control program suitable for vehicle-mounted millimeter-wave radar; wherein the obstruction detection platform control program suitable for vehicle-mounted millimeter-wave radar is executed in the processor, the obstruction detection platform control program suitable for vehicle-mounted millimeter-wave radar is stored in the memory, and the obstruction detection platform control program suitable for vehicle-mounted millimeter-wave radar implements the obstruction detection method suitable for vehicle-mounted millimeter-wave radar.

[0049] This invention generates and acquires first data corresponding to an onboard millimeter-wave radar based on target objects in the surrounding environment, and generates second and third data corresponding to the current frame based on the first data. The first data is target point cloud information data; the second data is the channel imbalance data for each target in the current frame; and the third data is the mean value of the channel imbalance data for the current frame. Based on the second data, a first preset parameter is generated and acquired, and based on the first preset parameter, it is determined and marked whether a target point is a valid target point. If so, the next step is executed; otherwise, the above steps are repeated. The data corresponding to the target objects in the preset frame are generated and acquired. The corresponding fourth, fifth, and sixth data are used, and a corresponding seventh data is calculated based on the fourth, fifth, and sixth data. The fourth data is the number of valid targets within the most recent preset frame; the fifth data is the furthest detection distance of valid targets within the most recent preset frame; the sixth data is the average channel imbalance data within the most recent preset frame; and the seventh data is a weighted summation of the target point cloud data corresponding to the most recent preset frame. Based on the seventh data, it is determined in real time whether the vehicle-mounted millimeter-wave radar is obstructed. The corresponding system and platform can detect whether the vehicle-mounted millimeter-wave radar is obstructed in real time.

[0050] In other words, the present invention comprehensively considers the recognition accuracy of multiple scenarios, that is, the radar's maximum detection range, the number of targets, and the channel balance of the targets are used as recognition features, and the change patterns of multiple frames are statistically analyzed to make occlusion recognition judgment in order to improve the recognition accuracy of vehicle-mounted millimeter-wave radar. Attached Figure Description

[0051] 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.

[0052] Figure 1 This is a schematic diagram of the process steps of an obstruction detection method for vehicle-mounted millimeter-wave radar according to the present invention;

[0053] Figure 2 This is a schematic diagram of the energy distribution in the target channel.

[0054] Figure 3 This is a schematic diagram of the millimeter-wave radar occlusion detection process, which is an embodiment of the occlusion detection method for vehicle-mounted millimeter-wave radar according to the present invention.

[0055] Figure 4This is a schematic diagram illustrating the ratio of the number of effective targets before and after radar obstruction, as an embodiment of the present invention for an obstruction detection method applicable to vehicle-mounted millimeter-wave radar.

[0056] Figure 5 This is a schematic diagram showing the maximum detection range of the radar in an embodiment of an obstruction detection method for vehicle-mounted millimeter-wave radar according to the present invention.

[0057] Figure 6 This is a schematic diagram comparing channel imbalance in an embodiment of an obstruction detection method for vehicle-mounted millimeter-wave radar according to the present invention.

[0058] Figure 7 This is a schematic diagram illustrating the effective target quantity ratio of an embodiment of an obstruction detection method for vehicle-mounted millimeter-wave radar according to the present invention.

[0059] Figure 8 This is a schematic diagram showing the radar detection distance ratio of an embodiment of the occlusion detection method applicable to vehicle-mounted millimeter-wave radar according to the present invention;

[0060] Figure 9 This is a schematic diagram illustrating the channel imbalance ratio of an embodiment of an obstruction detection method for vehicle-mounted millimeter-wave radar according to the present invention.

[0061] Figure 10 This is a schematic diagram of an obstruction detection system architecture suitable for vehicle-mounted millimeter-wave radar according to the present invention;

[0062] Figure 11 This is a schematic diagram of an obstruction detection platform architecture suitable for vehicle-mounted millimeter-wave radar according to the present invention. Detailed Implementation

[0063] To facilitate a clearer understanding of the objectives, technical solutions, and advantages of this invention, the invention will be further described below in conjunction with the accompanying drawings and specific embodiments. Those skilled in the art can easily understand other advantages and effects of this invention from the content disclosed in this specification.

[0064] This invention can also be implemented or applied through other different specific examples, and various details in this specification can also be modified and changed based on different viewpoints and applications without departing from the spirit of this invention.

[0065] It should be noted that if the embodiments of the present invention involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0066] Furthermore, if the embodiments of this invention involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Secondly, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0067] Preferably, the occlusion detection method for vehicle-mounted millimeter-wave radar of the present invention is applied in one or more terminals or servers. The terminal is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0068] The terminal can be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal can interact with the customer via a keyboard, mouse, remote control, touchpad, or voice control device.

[0069] This invention provides a method, system, platform, and storage medium for obstruction detection suitable for vehicle-mounted millimeter-wave radar.

[0070] like Figure 1 The diagram shown is a flowchart of an obstruction detection method for vehicle-mounted millimeter-wave radar provided by an embodiment of the present invention.

[0071] In this embodiment, the occlusion detection method applicable to vehicle-mounted millimeter-wave radar can be applied to terminals with display functions or fixed terminals. The terminals are not limited to personal computers, smartphones, tablets, desktop computers or all-in-one computers with cameras, etc.

[0072] The occlusion detection method for vehicle-mounted millimeter-wave radar can also be applied to a hardware environment consisting of a terminal and a server connected to the terminal via a network. The network includes, but is not limited to, a wide area network (WAN), a metropolitan area network (MAN), or a local area network (LAN). The occlusion detection method for vehicle-mounted millimeter-wave radar in this embodiment can be executed by the server, by the terminal, or by both the server and the terminal.

[0073] For example, for terminals requiring occlusion detection for automotive millimeter-wave radar, the occlusion detection function provided by the method of this invention can be directly integrated into the terminal, or a client for implementing the method of this invention can be installed. Alternatively, the method provided by this invention can also run on servers or other devices in the form of a Software Development Kit (SDK), providing an interface for occlusion detection for automotive millimeter-wave radar. Terminals or other devices can then implement the occlusion detection function for automotive millimeter-wave radar through the provided interface. The invention will be further described below with reference to the accompanying drawings.

[0074] like Figure 1 As shown, the present invention provides an obstruction detection method suitable for vehicle-mounted millimeter-wave radar, the method comprising the following steps:

[0075] S01. Based on the target objects in the surrounding environment, generate and acquire first data corresponding to the vehicle-mounted millimeter-wave radar, and generate second data and third data corresponding to the current frame according to the first data; wherein, the first data is target point cloud information data; the second data is the channel imbalance data of each target in the current frame; and the third data is the mean value data of the channel imbalance data in the current frame.

[0076] S02. Based on the second data, generate and obtain the first preset parameters, and based on the first preset parameters, determine and mark whether the target point is a valid target point; if so, proceed to the next step; otherwise, repeat the above steps.

[0077] S03. Generate and acquire the fourth, fifth, and sixth data corresponding to the preset frame, and calculate and generate the corresponding seventh data based on the fourth, fifth, and sixth data; wherein, the fourth data is the number of valid targets in the most recent preset frame; the fifth data is the farthest detection distance of valid targets in the most recent preset frame; the sixth data is the average channel imbalance data in the most recent preset frame; and the seventh data is the weighted summation data corresponding to the target point cloud in the most recent preset frame.

[0078] S04. Based on the seventh data, determine in real time whether the vehicle-mounted millimeter-wave radar is obstructed.

[0079] The process of generating and acquiring first data corresponding to the vehicle-mounted millimeter-wave radar based on target objects in the surrounding environment, and generating second and third data corresponding to the current frame based on the first data, further includes:

[0080] S011. Generate first control data corresponding to the vehicle-mounted millimeter-wave radar; wherein, the first control data is control command data for outputting target point cloud information;

[0081] S012. Based on the first control data and the target object in the surrounding environment, and in conjunction with the frequency-modulated continuous wave, generate corresponding first data.

[0082] The step of generating and obtaining first preset parameters based on the second data, and marking and determining whether a target point is a valid target point based on the first preset parameters, further includes:

[0083] S021. Based on the second data, generate and obtain the first preset parameters corresponding to the vehicle-mounted millimeter-wave radar;

[0084] S022. Based on the first preset parameter, determine and mark the corresponding target point. If the second data is greater than the first preset parameter, mark the target point as an invalid target; if the second data is less than the first preset parameter, mark the target point as a valid target.

[0085] The step of generating and acquiring the fourth, fifth, and sixth data corresponding to the preset frame, and calculating and generating the corresponding seventh data based on the fourth, fifth, and sixth data, further includes:

[0086] S031. Generate and acquire at least one set of eighth data, wherein the eighth data includes data on occlusion and non-occlusion states;

[0087] S032. Based on the eighth data, generate corresponding ninth, tenth, and eleventh data respectively; wherein, the ninth data is the weighted data of the maximum detection distance; the tenth data is the weighted data of the number of targets; and the eleventh data is the weighted data of the channel imbalance.

[0088] The preset frame is greater than or equal to 100; the calculation formula for generating the corresponding seventh data is:

[0089]

[0090] In the formula, q1 is the weight of the maximum detection range, q2 is the weight of the number of targets, q3 is the weight of the channel imbalance, q1,q2,q3∈(0,1), q1+q2+q3=1, R wave For the radar to be designed, the maximum detection range of the waveform is N. thred CM is the target quantity threshold, is a constant. thred is the threshold for channel imbalance, and is a constant.

[0091] The step of determining in real time whether the vehicle-mounted millimeter-wave radar is obstructed based on the seventh data also includes:

[0092] S041. Generate and obtain the second preset parameter, and based on the seventh data, determine whether the vehicle-mounted millimeter-wave radar is obstructed, and output the corresponding obstruction flag; wherein, if the seventh data is less than the second preset parameter, it is determined that there is obstruction, and the corresponding obstruction flag is output; if the seventh data is greater than the second preset parameter, it is determined that there is no obstruction, and the corresponding no obstruction flag is output.

[0093] Specifically, in this embodiment of the invention, the millimeter-wave radar detects the target by relying on the echo energy scattered by the target, and the radar's transmit power P t The energy is fed to the antenna, radiated outwards, and the electromagnetic waves illuminate the target at a radial distance R from the radar. Assume the target's RCS is σ. 2 The energy intercepted by the target is:

[0094]

[0095] Radar echo energy is the energy of electromagnetic waves reflected from the target back to the radar and intercepted by the radar antenna. Assume the effective area of ​​the radar antenna is A. e The energy received by the radar can be expressed as:

[0096]

[0097] Since the relationship between antenna gain and effective area is... Therefore, the energy scattered by the target received by the radar is:

[0098]

[0099] When the radar is blocked, the energy P scattered by the radar t Some of the radar signal will be reflected back by obstructions, and the effective area A of the radar receiving antenna will also be affected. e This will also reduce energy loss, leading to an increase in energy dissipation and consequently reducing the target echo energy P received by the radar. r With reduced noise, weak targets will be submerged in the noise, reducing the number of targets detected by the radar, and simultaneously decreasing the maximum detection range R. max It also becomes smaller; if the radar is completely blocked, the target echo energy P r It will greatly reduce, R max The radar will become very small, and the number of targets detected may only be a few, or even worse, no effective targets within the radar's detection range may be detected.

[0100] When the transmitting antenna or receiving antenna of the radar is partially blocked, the channel energy becomes uneven, and the energy difference between different channels becomes larger. The channel imbalance is the value that describes the channel power difference of the target, defined as the difference between the maximum and minimum channel powers. As Figure 2 shown, the blue is the channel energy distribution of the target without occlusion, which is relatively uniform, and the red is the channel energy distribution of the target when it is partially occluded. Obviously, the channel energy distribution is uneven and the channel imbalance becomes larger.

[0101] Based on the above principle, an algorithm is designed here to detect whether the radar is occluded. The millimeter-wave radar senses the objects in the surrounding environment through the FMCW waveform and outputs the target point cloud information.

[0102] The occlusion detection processing steps are as follows: Calculate the channel imbalance CM for the target point cloud detected by the millimeter-wave radar; Calculate the average value C n of the channel imbalance of the current frame; Mark the target point as a valid target or an invalid target according to the CM value. Target points with CM > a are considered invalid targets, and target points with CM < a are considered valid targets; a is a constant, which can be set by the CM value of the corner reflector or moving vehicle; Count the number N valid of valid targets within the last M frames. To prevent false alarms, the value of M is generally greater than 100;

[0103] Count the farthest detection distance R max of the valid targets within the last M frames; Count the average value CM[[ID=I8]] mean of the channel imbalance within the last M frames. [[ID=I0]]

[0104] Weighted summation:

[0105] <00002G7>In the formula, q1 is the weight of the maximum detection distance, q2 is the weight of the target quantity, q3 is the weight of the channel imbalance, q1, q2, q3 ∈ (0,1), q1 + q2 + q3 = 1, R wave is the farthest distance that the radar-designed waveform can detect, N thred is the target quantity threshold, which is an empirical constant, CM thred is the channel imbalance threshold, which is a constant;

[0107] Under the conditions of no foreign object occlusion and foreign object occlusion of the millimeter-wave radar, repeat steps 1 to 6, and collect at least one set of data on the occlusion and non-occlusion states to solve the thresholds q1, q2, q3. <00G0270>

[0108] |If Q is less than b, it is considered occluded, otherwise not occluded, and b is an empirical constant.

[0109] The following example illustrates the steps described above. Let's take the example of a vehicle being obstructed by aluminum foil while in motion. When the millimeter-wave radar is unobstructed, it can detect a large number of target points, has a long detection range, and most targets have relatively low channel uniformity, making them all valid targets. However, when the radar is obstructed by aluminum foil, its detection energy decreases, it detects very few targets, and most of these are invalid targets, rendering the radar essentially ineffective. Taking a preset frame count M=200 as an example, the ratio of the number of valid targets before and after the radar obstruction is as follows: Figure 4 As shown, the y-axis represents the proportion of effective targets in each frame within a preset frame. The average value is calculated before occlusion. It is 0.67 after occlusion. The value is 0.07, which clearly shows that when the radar is blocked, the proportion of effective targets detected decreases significantly; while when it is not blocked, the proportion of effective targets detected by the radar is relatively large; the proportion of radar's furthest detection range is as follows. Figure 5 As shown, the y-axis represents the detection distance ratio. Find the maximum value before occlusion. It is 0.98 after occlusion. The value was 0.15, and this proportion dropped significantly after being blocked; the channel imbalance comparison chart is shown below. Figure 6 As shown, the y-axis represents the channel imbalance ratio. Where C n Given the average CM value for each frame, then before occlusion... It is 0.72 after occlusion. With a weighting of 0.36, when the radar is not obstructed, the target's CM value is low, the channel distribution is relatively uniform, and the proportion is low. When obstructed, the energy distribution is uneven, the CM value increases, and the proportion rises. Assuming the weighting values ​​are 0.4, 0.4, and 0.2, the Q value when the radar is not obstructed is 0.804, and the Q value when obstructed is 0.16. Assuming the preset parameter is 0.3, the above weighting values ​​and preset parameters can be used to determine whether the radar is obstructed.

[0110] The test scenario was selected as a public road, with the radar's effective target count compared to, for example, [the number of targets was] ... Figure 7 Radar detection range is, for example Figure 8 Channel imbalance ratio, for example Figure 9 The weighted summation value Q is calculated to be 0.21, which is less than the preset parameter. Therefore, it is considered that the radar is blocked, which is consistent with the actual situation.

[0111] To achieve the above objectives, the present invention also provides an obstruction detection system suitable for vehicle-mounted millimeter-wave radar, such as... Figure 10 As shown, the system is used to implement the occlusion detection method suitable for vehicle-mounted millimeter-wave radar, and the system includes:

[0112] The first data generation unit is used to generate and acquire first data corresponding to the vehicle-mounted millimeter-wave radar based on target objects in the surrounding environment, and to generate second data and third data corresponding to the current frame based on the first data; wherein, the first data is target point cloud information data; the second data is the channel imbalance data of each target in the current frame; and the third data is the mean value data of the channel imbalance data in the current frame.

[0113] The first data determination unit is used to generate and obtain the first preset parameters based on the second data, and determine and mark whether the target point is a valid target point based on the first preset parameters.

[0114] The second data generation unit is used to generate and acquire the fourth, fifth, and sixth data corresponding to the preset frame, and to calculate and generate the corresponding seventh data based on the fourth, fifth, and sixth data; wherein, the fourth data is the number of valid targets in the most recent preset frame; the fifth data is the farthest detection distance of valid targets in the most recent preset frame; the sixth data is the average channel imbalance data in the most recent preset frame; and the seventh data is the weighted summation data corresponding to the target point cloud in the most recent preset frame.

[0115] The second data determination unit is used to determine in real time whether the vehicle-mounted millimeter-wave radar is obstructed based on the seventh data.

[0116] Specifically, the first data generation unit further includes:

[0117] The first generation module is used to generate first control data corresponding to the vehicle-mounted millimeter-wave radar; wherein, the first control data is control command data for outputting target point cloud information;

[0118] The second generation module is used to generate corresponding first data based on the first control data, the target object in the surrounding environment, and the frequency-modulated continuous wave.

[0119] And / or, the first data determination unit further includes:

[0120] The third generation module is used to generate and obtain the first preset parameters corresponding to the vehicle-mounted millimeter-wave radar based on the second data;

[0121] The first determination module is used to determine and mark the corresponding target points based on the first preset parameters;

[0122] And / or, the second data generation unit further includes:

[0123] The fourth generation module is used to generate and acquire at least one set of eighth data, wherein the eighth data includes data on occlusion and non-occlusion states;

[0124] The fifth generation module is used to generate corresponding ninth, tenth, and eleventh data based on the eighth data; wherein the ninth data is weighted data for the maximum detection distance; the tenth data is weighted data for the number of targets; and the eleventh data is weighted data for the channel imbalance.

[0125] And / or, the second data determination unit further includes:

[0126] The sixth generation module is used to generate and obtain the second preset parameters, and based on the seventh data, determine whether the vehicle-mounted millimeter-wave radar is obstructed, and output the corresponding obstruction flag.

[0127] Furthermore, the preset frame is greater than or equal to 100;

[0128] The calculation formula for generating the corresponding seventh data is as follows:

[0129]

[0130] In the formula, q1 is the weight of the maximum detection range, q2 is the weight of the number of targets, q3 is the weight of the channel imbalance, q1,q2,q3∈(0,1), q1+q2+q3=1, R wave For the radar to be designed, the maximum detection range of the waveform is N. thred CM is the target quantity threshold, is a constant. thred is the threshold for channel imbalance, and is a constant.

[0131] In the system solution embodiment of the present invention, the specific details of the method steps involved in the occlusion detection of vehicle-mounted millimeter-wave radar have been described above. That is to say, the functional modules in the system are used to implement the steps or sub-steps in the above method embodiment, which will not be repeated here.

[0132] To achieve the above objectives, the present invention also provides an obstruction detection platform suitable for vehicle-mounted millimeter-wave radar, such as... Figure 11 As shown, it includes a processor, a memory, and a control program for an obstruction detection platform suitable for automotive millimeter-wave radar. The processor executes the control program, which is stored in the memory. This control program implements the steps of the obstruction detection method for automotive millimeter-wave radar. For example:

[0133] S01. Based on the target objects in the surrounding environment, generate and acquire first data corresponding to the vehicle-mounted millimeter-wave radar, and generate second data and third data corresponding to the current frame according to the first data; wherein, the first data is target point cloud information data; the second data is the channel imbalance data of each target in the current frame; and the third data is the mean value data of the channel imbalance data in the current frame.

[0134] S02. Based on the second data, generate and obtain the first preset parameters, and based on the first preset parameters, determine and mark whether the target point is a valid target point; if so, proceed to the next step; otherwise, repeat the above steps.

[0135] S03. Generate and acquire the fourth, fifth, and sixth data corresponding to the preset frame, and calculate and generate the corresponding seventh data based on the fourth, fifth, and sixth data; wherein, the fourth data is the number of valid targets in the most recent preset frame; the fifth data is the farthest detection distance of valid targets in the most recent preset frame; the sixth data is the average channel imbalance data in the most recent preset frame; and the seventh data is the weighted summation data corresponding to the target point cloud in the most recent preset frame.

[0136] S04. Based on the seventh data, determine in real time whether the vehicle-mounted millimeter-wave radar is obstructed.

[0137] The specific details of the steps have been explained above and will not be repeated here.

[0138] In this embodiment of the invention, the built-in processor of the obstruction detection platform for vehicle-mounted millimeter-wave radar can be composed of integrated circuits. For example, it can be composed of a single packaged integrated circuit, or multiple integrated circuits packaged with the same or different functions. This includes combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor connects to various components using various interfaces and lines, and executes programs or units stored in memory, as well as calling data stored in memory, to perform various obstruction detection functions and process data suitable for vehicle-mounted millimeter-wave radar.

[0139] The memory is used to store program code and various data. It is installed in the obstruction detection platform suitable for vehicle-mounted millimeter-wave radar and enables high-speed and automatic access to programs or data during operation.

[0140] The memory includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0141] This invention generates and acquires first data corresponding to an onboard millimeter-wave radar based on target objects in the surrounding environment, and generates second and third data corresponding to the current frame based on the first data. The first data is target point cloud information data; the second data is the channel imbalance data for each target in the current frame; and the third data is the mean value of the channel imbalance data for the current frame. Based on the second data, a first preset parameter is generated and acquired, and based on the first preset parameter, it is determined and marked whether a target point is a valid target point. If so, the next step is executed; otherwise, the above steps are repeated. The data corresponding to the target objects in the preset frame are generated and acquired. The corresponding fourth, fifth, and sixth data are used, and a corresponding seventh data is calculated based on the fourth, fifth, and sixth data. The fourth data is the number of valid targets within the most recent preset frame; the fifth data is the furthest detection distance of valid targets within the most recent preset frame; the sixth data is the average channel imbalance data within the most recent preset frame; and the seventh data is a weighted summation of the target point cloud data corresponding to the most recent preset frame. Based on the seventh data, it is determined in real time whether the vehicle-mounted millimeter-wave radar is obstructed. The corresponding system and platform can detect whether the vehicle-mounted millimeter-wave radar is obstructed in real time.

[0142] In other words, the present invention comprehensively considers the recognition accuracy of multiple scenarios, that is, the radar's maximum detection range, the number of targets, and the channel balance of the targets are used as recognition features, and the change patterns of multiple frames are statistically analyzed to make occlusion recognition judgment in order to improve the recognition accuracy of vehicle-mounted millimeter-wave radar.

[0143] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. An obstruction detection method suitable for vehicle-mounted millimeter-wave radar, characterized in that, The method includes: Based on the target objects in the surrounding environment, first data corresponding to the vehicle-mounted millimeter-wave radar is generated and acquired. Based on the first data, second data and third data corresponding to the current frame are generated respectively. The first data is target point cloud information data; the second data is the channel imbalance data of each target in the current frame; and the third data is the mean value data of the channel imbalance data in the current frame. Based on the second data, generate and obtain the first preset parameter, compare the second data with the first preset parameter, and determine and mark whether the target point is a valid target point; if so, proceed to the next step; otherwise, repeat the above steps. The fourth, fifth, and sixth data corresponding to the preset frame are generated and acquired respectively, and the corresponding seventh data is calculated based on the fourth, fifth, and sixth data; wherein, the fourth data is the number of valid targets in the most recent preset frame; the fifth data is the farthest detection distance of valid targets in the most recent preset frame; the sixth data is the mean channel imbalance data in the most recent preset frame; and the seventh data is the weighted summation data corresponding to the target point cloud in the most recent preset frame. Based on the seventh data, it is determined in real time whether the vehicle-mounted millimeter-wave radar is obstructed; The calculation formula for generating the corresponding seventh data is as follows: （4） In the formula, As the weight of the maximum detection range, The weights for the target quantity The weight for channel imbalance. , , The maximum distance that a radar waveform can detect. The target quantity threshold is denoted by , which is a constant. The channel imbalance threshold is a constant. This represents the mean of channel imbalance. Maximum detection range of effective targets; Number of valid targets.

2. The occlusion detection method for vehicle-mounted millimeter-wave radar according to claim 1, characterized in that, The process of generating and acquiring first data corresponding to the vehicle-mounted millimeter-wave radar based on target objects in the surrounding environment, and generating second and third data corresponding to the current frame based on the first data, further includes: Generate first control data corresponding to the vehicle-mounted millimeter-wave radar; wherein, the first control data is control command data for outputting target point cloud information; Based on the first control data and the target object in the surrounding environment, and in conjunction with the frequency-modulated continuous wave, corresponding first data is generated.

3. The occlusion detection method for vehicle-mounted millimeter-wave radar according to claim 1, characterized in that, Based on the second data, generating and obtaining first preset parameters, and based on the first preset parameters, marking and determining whether a target point is a valid target point, further includes: Based on the second data, generate and obtain the first preset parameters corresponding to the vehicle-mounted millimeter-wave radar; Based on the first preset parameter, the corresponding target point is determined and marked. If the second data is greater than the first preset parameter, the target point is marked as an invalid target; if the second data is less than the first preset parameter, the target point is marked as a valid target.

4. The occlusion detection method for vehicle-mounted millimeter-wave radar according to claim 1, characterized in that, The step of generating and acquiring the fourth, fifth, and sixth data corresponding to the preset frame, and calculating and generating the corresponding seventh data based on the fourth, fifth, and sixth data, further includes: Generate and acquire at least one set of eighth data, wherein the eighth data includes data on occlusion and non-occlusion states; Based on the eighth data, corresponding ninth, tenth, and eleventh data are generated respectively; wherein, the ninth data is the weighted data of the maximum detection distance; the tenth data is the weighted data of the number of targets; and the eleventh data is the weighted data of the channel imbalance.

5. A method for detecting obstruction in vehicle-mounted millimeter-wave radar according to claim 1 or 4, characterized in that, The preset frame is greater than or equal to 100.

6. The occlusion detection method for vehicle-mounted millimeter-wave radar according to claim 1, characterized in that, The step of determining in real time whether the vehicle-mounted millimeter-wave radar is obstructed based on the seventh data also includes: A second preset parameter is generated and obtained, and based on the seventh data, it is determined whether the vehicle-mounted millimeter-wave radar is obstructed, and a corresponding obstruction flag is output. If the seventh data is less than the second preset parameter, it is determined that there is obstruction, and a corresponding obstruction flag is output. If the seventh data is greater than the second preset parameter, it is determined that there is no obstruction, and a corresponding no obstruction flag is output.

7. An obstruction detection system suitable for vehicle-mounted millimeter-wave radar, characterized in that, The system is applied to the occlusion detection method for vehicle-mounted millimeter-wave radar as described in any one of claims 1 to 6, and the system comprises: The first data generation unit is used to generate and acquire first data corresponding to the vehicle-mounted millimeter-wave radar based on target objects in the surrounding environment, and to generate second data and third data corresponding to the current frame based on the first data; wherein, the first data is target point cloud information data; the second data is the channel imbalance data of each target in the current frame; and the third data is the mean value data of the channel imbalance data in the current frame. The first data determination unit is used to generate and obtain the first preset parameters based on the second data, and compare the second data with the first preset parameters to determine and mark whether the target point is a valid target point. The second data generation unit is used to generate and acquire the fourth, fifth, and sixth data corresponding to the preset frame, and to calculate and generate the corresponding seventh data based on the fourth, fifth, and sixth data; wherein, the fourth data is the number of valid targets in the most recent preset frame; the fifth data is the farthest detection distance of valid targets in the most recent preset frame; the sixth data is the average channel imbalance data in the most recent preset frame; and the seventh data is the weighted summation data corresponding to the target point cloud in the most recent preset frame. The second data determination unit is used to determine in real time whether the vehicle-mounted millimeter-wave radar is obstructed based on the seventh data.

8. An obstruction detection system for vehicle-mounted millimeter-wave radar according to claim 7, characterized in that, The first data generation unit further includes: The first generation module is used to generate first control data corresponding to the vehicle-mounted millimeter-wave radar; wherein, the first control data is control command data for outputting target point cloud information; The second generation module is used to generate corresponding first data based on the first control data, the target object in the surrounding environment, and the frequency-modulated continuous wave. And / or, the first data determination unit further includes: The third generation module is used to generate and obtain the first preset parameters corresponding to the vehicle-mounted millimeter-wave radar based on the second data; The first determination module is used to determine and mark the corresponding target points based on the first preset parameters; And / or, the second data generation unit further includes: The fourth generation module is used to generate and acquire at least one set of eighth data, wherein the eighth data includes data on occlusion and non-occlusion states; The fifth generation module is used to generate corresponding ninth, tenth, and eleventh data based on the eighth data; wherein the ninth data is weighted data for the maximum detection distance; the tenth data is weighted data for the number of targets; and the eleventh data is weighted data for the channel imbalance. And / or, the second data determination unit further includes: The sixth generation module is used to generate and obtain the second preset parameters, and based on the seventh data, determine whether the vehicle-mounted millimeter-wave radar is obstructed, and output the corresponding obstruction flag.

9. An obstruction detection system for vehicle-mounted millimeter-wave radar according to claim 7 or 8, characterized in that, The preset frame is greater than or equal to 100; The calculation formula for generating the corresponding seventh data is as follows: （4） In the formula, As the weight of the maximum detection range, The weights for the target quantity The weight for channel imbalance. , , The maximum distance that a radar waveform can detect. The target quantity threshold is denoted by , which is a constant. The channel imbalance threshold is a constant. This represents the mean of channel imbalance. Maximum detection range of effective targets; Number of valid targets.

10. An obstruction detection platform suitable for vehicle-mounted millimeter-wave radar, characterized in that, The system includes a processor, a memory, and an obstruction detection platform control program for vehicle-mounted millimeter-wave radar; wherein the obstruction detection platform control program for vehicle-mounted millimeter-wave radar is executed on the processor, the obstruction detection platform control program for vehicle-mounted millimeter-wave radar is stored in the memory, and the obstruction detection platform control program for vehicle-mounted millimeter-wave radar implements the obstruction detection method for vehicle-mounted millimeter-wave radar as described in any one of claims 1 to 6.

Images