Complex environment-oriented vehicle-mounted millimeter wave radar anti-interference method and system

Abstract

The invention relates to the technical field of intelligent driving, in particular to a vehicle-mounted millimeter wave radar anti-interference method and system for a complex environment. The method comprises the following steps: identifying tracking targets based on vehicle-mounted millimeter wave radar data in a historical vehicle use process, and respectively calculating the track length validity and track distribution validity of each tracking target so as to determine an invalid tracking target and determine a historical false alarm degree to perform high-frequency IMF extraction on an IF signal of the invalid tracking target; obtaining IF waveform characteristics of the invalid tracking target; and if a new IF signal is obtained, whether the newly obtained IF signal is an interference signal is judged by combining a historical false alarm degree and IF waveform characteristics, so that an effective tracking target is screened out, and corresponding early warning is triggered. According to the invention, the false alarm rate of the vehicle-mounted millimeter-wave radar is reduced, and the identification accuracy of the tracking target is improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving technology, specifically to an anti-interference method and system for vehicle-mounted millimeter-wave radar in complex environments. Background Technology

[0002] With the rapid development of intelligent transportation, vehicle-mounted millimeter-wave radar has become a core component of vehicle perception systems, playing a crucial role in autonomous driving and driver assistance. However, as vehicle intelligence continues to increase and the number of vehicle-mounted radars on the road grows exponentially, the interference problems faced by vehicle-mounted millimeter-wave radar are becoming increasingly severe.

[0003] Existing anti-jamming methods for vehicle-mounted millimeter-wave radars suffer from distorted reference unit noise power estimation during actual operation, leading to a surge in false alarm rates. This can result in some invalid tracking targets being identified as valid tracking targets, resulting in an overall excessively high false alarm rate. Summary of the Invention

[0004] To address the technical problem of excessively high false alarm rates in anti-interference methods for vehicle-mounted millimeter-wave radar, the present invention aims to provide an anti-interference method and system for vehicle-mounted millimeter-wave radar in complex environments. The specific technical solution adopted is as follows: In a first aspect, embodiments of the present invention provide an anti-interference method for vehicle-mounted millimeter-wave radar in complex environments, the method comprising: Based on the vehicle's historical usage data, the vehicle-mounted millimeter-wave radar identifies and tracks targets, and calculates the validity of the trajectory length and trajectory distribution of each tracked target to determine invalid tracked targets and the degree of historical false alarms. High-frequency IMF extraction is performed on the IF signal of the invalid tracking target, and the IF waveform characteristics of the invalid tracking target are obtained; If a new IF signal is acquired, the historical false alarm level and the IF waveform characteristics are combined to determine whether the newly acquired IF signal is an interference signal, thereby filtering out effective tracking targets and triggering corresponding warnings.

[0005] In some embodiments, the vehicle-mounted millimeter-wave radar data is acquired in the following ways: Real-time acquisition of IF signals in the vehicle's driving area via vehicle-mounted millimeter-wave radar; The acquired IF signal is preprocessed in a preset manner, and the preprocessed vehicle millimeter-wave radar data is stored in a cache.

[0006] In some embodiments, the vehicle-mounted millimeter-wave radar is equipped with a specific frequency band radio frequency chip and a multi-channel antenna array, and the real-time acquisition of the IF signal of the vehicle driving area by the vehicle-mounted millimeter-wave radar specifically includes: The specific frequency band radio frequency chip transmits FMCW frequency-modulated continuous waves to the vehicle driving area in real time, covering a preset detection distance; The target radio frequency echo signal is received through the multi-channel antenna array; The target radio frequency echo signal is mixed with the transmitted signal to generate an IF signal.

[0007] In some embodiments, the identification and tracking of targets based on vehicle-mounted millimeter-wave radar data from historical vehicle usage includes: Retrieve vehicle-mounted millimeter-wave radar data and warning signals from multiple vehicle usage cycles; For the vehicle-mounted millimeter-wave radar data and warning signals during a single vehicle use, the CFAR algorithm is used to identify target signals and non-target signals. The target is identified and tracked using a target tracking algorithm.

[0008] In some embodiments, calculating the trajectory length validity and trajectory distribution validity of each of the tracked targets includes: Extract the complete trajectory data of a single tracked target within consecutive sampling moments during a single use of the vehicle, and count the number of sampling points contained in the trajectory data and / or the cumulative length of the trajectory in the spatial dimension to obtain the total trajectory length of the tracked target; The correlation between the total length of the trajectory and the preset minimum ideal value is established by exponential operation in order to obtain the validity of the trajectory length of the tracked target; 2D-FFT was used to process the complete trajectory data of a single tracked target, and the range spectrum and velocity spectrum corresponding to the trajectory at each sampling time were extracted respectively; The effectiveness of the range spectrum and the effectiveness of the velocity spectrum are calculated using a preset calculation method to generate range spectrum effectiveness index and velocity spectrum effectiveness index, thereby determining the effectiveness of the trajectory distribution of the tracked target.

[0009] In some embodiments, the step of performing high-frequency IMF extraction on the IF signal of the invalid tracking target and obtaining the IF waveform features of the invalid tracking target includes: Collect all IF signals of a single invalid tracking target within its existence period to form an IF signal set; High-frequency IMF extraction is performed on each IF signal in the IF signal set using the EMD method. The high-frequency IMF similarity of adjacent IF signals of the invalid tracking target is calculated, and the similarity result is obtained after normalization. Using the similarity results as a distance index, the k-means clustering algorithm is used to cluster all the IF signals, and the high-frequency IMF corresponding to the feature cluster containing the most IF signals is taken as the IF waveform feature of the invalid tracking target.

[0010] In some embodiments, the step of determining whether a newly acquired IF signal is an interference signal by combining the historical false alarm rate and the IF waveform characteristics if a new IF signal is acquired includes: If a new IF signal is acquired, the newly acquired IF signal is subjected to high-frequency IMF extraction using the EMD method; The high-frequency IMF of the real-time intermediate frequency signal is compared with all features in the IF waveform feature library of historical invalid tracking targets. The similarity is calculated and the maximum similarity value under each high-frequency dimension is extracted. Based on the false alarm rate and the number of corresponding invalid targets in each historical vehicle usage process, a weighted average of the maximum similarity value is used to obtain a probability score of the real-time intermediate frequency signal as an interference signal. The probability score is compared with a preset threshold. If it exceeds the preset threshold, it is determined to be an interference signal; otherwise, it is determined to be a valid target signal.

[0011] In some embodiments, it also includes: The IF signals of all the invalid tracking targets are decomposed to obtain high-frequency interference components; The similarity of the high-frequency interference components is analyzed to determine the common features of the interference signals. These common features are then categorized and stored to form an interference feature library. If a new IF signal is acquired, the matching degree between the newly acquired IF signal and the features in the interference feature library is calculated. If the matching degree exceeds the preset interference value, it is determined to be an interference signal and is excluded; if the matching degree does not exceed the preset interference value, it is determined to be a valid tracking target and is included in the tracking range.

[0012] In some embodiments, it also includes: Each time a vehicle is used, the sampled data, and / or warning signals, and / or tracking target information, and / or false alarm level, and / or IF waveform characteristics of this vehicle use process are preprocessed and stored in the database; Update the data in the database at a preset frequency.

[0013] Secondly, embodiments of the present invention provide an anti-jamming system for vehicle-mounted millimeter-wave radar in complex environments, the system comprising the following modules: The determination module is used to identify and track targets based on vehicle millimeter-wave radar data from historical vehicle usage, and to calculate the validity of the trajectory length and trajectory distribution of each tracked target, thereby determining invalid tracked targets and determining the degree of historical false alarms. The acquisition module is used to perform high-frequency IMF extraction on the IF signal of the invalid tracking target and acquire the IF waveform characteristics of the invalid tracking target; The filtering module is used to determine whether a new IF signal is an interference signal by combining the historical false alarm level and the IF waveform characteristics, thereby filtering out effective tracking targets and triggering corresponding warnings.

[0014] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, it implements the various possible implementations of the first aspect.

[0015] Fourthly, embodiments of the present invention provide a computer program product comprising: computer program code, which, when executed on a computer, causes the computer to perform the method described in the first aspect or any possible implementation thereof.

[0016] Fifthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the various possible implementations of the first aspect.

[0017] The embodiments of the present invention have at least the following beneficial effects: This invention determines the effectiveness of tracked targets by analyzing the effectiveness of the trajectory length and trajectory distribution of each tracked target during each vehicle operation, thereby determining the false alarm rate (FAR) of the onboard millimeter-wave radar during each vehicle operation. Then, by analyzing the similarity of the IF waveforms between invalid tracked targets during each vehicle operation, the IF waveform characteristics of invalid tracked targets are determined. Furthermore, the effectiveness of IF fluctuations obtained during subsequent vehicle operations is judged based on the obtained IF waveform characteristics of invalid tracked targets. Thus, based on CFAR, determining whether a tracked target is a valid target by analyzing the effectiveness of the IF waveform reduces the FAR rate of the onboard millimeter-wave radar and improves the accuracy of target identification. Attached Figure Description

[0018] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the 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.

[0019] Figure 1 A flowchart illustrating an anti-jamming method for vehicle-mounted millimeter-wave radar in complex environments, provided in an embodiment of the present invention. Figure 2 This is a system block diagram of an anti-jamming system for vehicle-mounted millimeter-wave radar in complex environments, provided as an embodiment of the present invention. Figure 3 This is a schematic diagram of the structure of a computer device provided in one embodiment of the present invention. Detailed Implementation

[0020] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of the vehicle-mounted millimeter-wave radar anti-interference method and system for complex environments proposed in accordance with the present invention.

[0021] In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments may be combined in any suitable form.

[0022] In the description of the embodiments of the present invention, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of the present invention, "multiple" means two or more.

[0023] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0025] The embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided by the embodiments of the present invention are also applicable to similar technical problems.

[0026] The following description, in conjunction with the accompanying drawings, details the specific solution of the anti-interference method and system for vehicle-mounted millimeter-wave radar in complex environments provided by this invention.

[0027] Example 1: Please see Figure 1 The diagram illustrates a flowchart of a method for anti-jamming of vehicle-mounted millimeter-wave radar in complex environments according to an embodiment of the present invention. The method includes the following steps: S10. Identify and track targets based on vehicle-mounted millimeter-wave radar data from historical vehicle usage, and calculate the validity of the trajectory length and trajectory distribution of each tracked target to determine invalid tracked targets and the degree of historical false alarms.

[0028] It should be noted that the vehicle-mounted millimeter-wave radar in this embodiment of the invention has blind spot detection (BSD), lane change assist (LCA), door open warning (DOW), and rear collision warning (RCW) functions. Furthermore, the detection range of the vehicle-mounted millimeter-wave radar in this embodiment of the invention is centered on the rear of the vehicle. The lateral distance is X, and the longitudinal distance is Y. The lateral distance to the left of the center is negative, and the lateral distance to the right of the center is positive; different functions correspond to different detection ranges.

[0029] In some embodiments, the vehicle-mounted millimeter-wave radar data is acquired in the following ways: Real-time acquisition of IF signals in the vehicle's driving area via vehicle-mounted millimeter-wave radar; The acquired IF signal is preprocessed in a preset manner, and the preprocessed vehicle millimeter-wave radar data is stored in a cache.

[0030] In some embodiments, the vehicle-mounted millimeter-wave radar is equipped with a specific frequency band radio frequency chip and a multi-channel antenna array, and the real-time acquisition of the IF signal of the vehicle driving area by the vehicle-mounted millimeter-wave radar specifically includes: The specific frequency band radio frequency chip transmits FMCW frequency-modulated continuous waves to the vehicle driving area in real time, covering a preset detection distance (e.g., 10m-250m). The target radio frequency echo signal is received through the multi-channel antenna array; The target radio frequency echo signal is mixed with the transmitted signal to generate an IF signal.

[0031] Specifically, the vehicle-mounted millimeter-wave radar RF chip (such as a 77GHz RF chip) transmits a frequency-modulated continuous wave (FMCW). For example, specific parameters may include: bandwidth of 1-4GHz, timing of 40μs / chirp, and detection range of 10m-250m. A 4RX channel antenna array receives the target RF echo signal. The RF echo signal is mixed with the transmitted signal to generate an intermediate frequency (IF) signal. An analog-to-digital converter (ADC) samples the IF signal at a rate of 40-100MSPS. The IF signal sampled by the ADC undergoes preprocessing operations such as DC cancellation, windowing, and zero-padding to obtain the final ADC sampled signal. The acquired ADC data is then cached using enhanced direct memory to avoid blocking of the central processing unit (CPU).

[0032] In some embodiments, the identification and tracking of targets based on vehicle-mounted millimeter-wave radar data from historical vehicle usage includes: Retrieve vehicle-mounted millimeter-wave radar data and warning signals from multiple vehicle usage cycles; For the vehicle-mounted millimeter-wave radar data and warning signals during a single vehicle use, the CFAR algorithm is used to identify target signals and non-target signals. The target is identified and tracked using a target tracking algorithm.

[0033] Furthermore, the calculation of the trajectory length validity and trajectory distribution validity of each of the tracked targets includes: Extract the complete trajectory data of a single tracked target within consecutive sampling moments during a single use of the vehicle, and count the number of sampling points contained in the trajectory data and / or the cumulative length of the trajectory in the spatial dimension to obtain the total trajectory length of the tracked target; The correlation between the total length of the trajectory and the preset minimum ideal value is established by exponential operation in order to obtain the validity of the trajectory length of the tracked target; 2D-FFT was used to process the complete trajectory data of a single tracked target, and the range spectrum and velocity spectrum corresponding to the trajectory at each sampling time were extracted respectively; The effectiveness of the range spectrum and the effectiveness of the velocity spectrum are calculated using a preset calculation method to generate range spectrum effectiveness index and velocity spectrum effectiveness index, thereby determining the effectiveness of the trajectory distribution of the tracked target.

[0034] Specifically, assume that the database stores ADC sampling data and warning signals from n vehicle usage cycles.

[0035] During the nth vehicle use, the ADC acquires one or more IF signals at each sampling time (if there is only one target in the field of view of the vehicle millimeter-wave radar, one IF signal will be acquired; otherwise, if there are multiple targets in the field of view, multiple IF signals will be acquired). Then, the Constant False Alarm Rate (CFAR) algorithm determines which signals are target signals by using a detection threshold and returns the target signals.

[0036] Suppose that at the i-th sampling moment during the n-th vehicle usage, there are N1 target signals and N2 non-target signals. Since the millimeter-wave transmitted signal is a continuous frequency-modulated signal during vehicle operation, when encountering different target vehicles, the frequency difference between the reflected signal and the transmitted signal varies due to differences in the distance and relative speed between the target vehicles and the vehicle, resulting in different IF frequencies.

[0037] During the operation of the vehicle-mounted millimeter-wave radar, after detecting a target signal, the CFAR algorithm continuously tracks the target until it leaves the field of view. Therefore, in the nth vehicle usage, there are I sampling times. Let's assume the target tracking algorithm finds S tracking targets during these I sampling times. Then, it analyzes the trajectory of each tracking target to determine which of these targets are currently interfering.

[0038] For the s-th tracked target, whether the s-th tracked target is a normal tracked target is determined based on the trajectory length and trajectory distribution of the s-th tracked target. If the trajectory length of the s-th tracked target exceeds a preset length threshold, it indicates that the s-th tracked target is a normally moving target vehicle (if the trajectory length does not exceed the preset length threshold, it does not meet the driving characteristics of a vehicle, that is, the target vehicle disappears shortly after being detected).

[0039] Therefore, the mathematical formula for the effectiveness of the trajectory length of the s-th tracked target is: In the formula, This indicates the validity of the trajectory length of the s-th tracked target during the nth vehicle use. This represents an exponential function with base e. This represents the trajectory length of the s-th tracked target during the nth vehicle usage. This represents the minimum ideal value for the length of the tracked target (a preset value, for example, not less than 10 meters).

[0040] According to conventional rules, vehicles do not change lanes multiple times within a close proximity during operation. Therefore, it is necessary to analyze the trajectory changes of the s-th tracked target during the nth vehicle usage to determine the effectiveness of the trajectory distribution of the s-th tracked target during the nth vehicle usage. Specifically: After the target is determined, the distance spectrum (distance between the target and the vehicle) and velocity spectrum (vehicle velocity information) of each trajectory of the target can be obtained by using the Two-Dimensional Fast Fourier Transform (2D-FFT).

[0041] Therefore, the effectiveness of the trajectory distribution of the s-th tracked target during the nth vehicle use is determined by analyzing the changes in the distance spectrum and velocity spectrum of the trajectory during the nth vehicle use. Taking the effectiveness of the distance spectrum in the trajectory distribution of the s-th tracked target during the nth vehicle use as an example, the specific mathematical formula is: In the formula, This indicates the effectiveness of the distance spectrum in the trajectory distribution of the s-th tracked target during the nth vehicle use. This represents an inverse proportional exponential function with the natural constant e as its base. This represents the trajectory length of the s-th tracked target during the nth vehicle usage. It represents the absolute value of the difference in distance spectrum between the j-th trajectory and the (j+1)-th trajectory of the s-th tracked target during the n-th vehicle use. It represents the absolute value of the difference in distance spectrum between the (j+1)th and (j+2)th trajectories of the (s)th tracked target during the nth vehicle use.

[0042] The smaller the value, the more similar the distance spectrum changes of the s-th tracked target are during the m-th vehicle use.

[0043] Furthermore, the mathematical formula for the effectiveness of the velocity spectrum in the trajectory distribution of the s-th tracked target during the nth vehicle use is: In the formula, This indicates the effectiveness of the velocity spectrum in the trajectory distribution of the s-th tracked target during the nth vehicle use. This represents an inverse proportional exponential function with the natural constant e as its base. This represents the trajectory length of the s-th tracked target during the nth vehicle usage. This represents the absolute value of the difference between the velocity spectra of the j-th trajectory and the (j+1)-th trajectory of the s-th tracked target during the n-th vehicle use. It represents the absolute value of the difference between the velocity spectra of the (j+1)th and (j+2)th trajectories of the (s)th tracked target during the nth vehicle use.

[0044] The smaller the value, the more stable the velocity spectrum change of the s-th tracked target during the nth vehicle use.

[0045] Then and The mean value is denoted as the effectiveness of the trajectory distribution of the s-th tracked target during the nth vehicle use, and is denoted as... .

[0046] Therefore, the greater the effectiveness of the trajectory length and trajectory distribution of the s-th tracked target during the nth vehicle use, the greater the effectiveness of the s-th tracked target. The specific mathematical formula for the effectiveness of the s-th tracked target during the nth vehicle use is as follows: In the formula, This indicates the effectiveness of the s-th tracked target during the nth vehicle use. This indicates the validity of the trajectory length of the s-th tracked target during the nth vehicle use. This indicates the validity of the trajectory distribution of the s-th tracked target during the nth vehicle use.

[0047] therefore, A higher value indicates greater effectiveness of the s-th tracked target during the nth vehicle use. Similarly, the effectiveness of each tracked target during the nth vehicle use can be calculated using the above method. In practical applications, a threshold can be set for effectiveness based on actual needs; for example, targets with an effectiveness below 0.4 can be considered invalid.

[0048] Suppose that Y invalid tracking targets were found, then the mathematical formula for the false alarm rate of the onboard millimeter-wave radar during the nth vehicle use is: In the formula, This indicates the false alarm level of the onboard millimeter-wave radar during the nth use of the vehicle. This represents the number of invalid tracking targets found during the nth vehicle usage. This represents the total number of tracked targets detected during the nth vehicle use.

[0049] S11. Perform high-frequency IMF extraction on the IF signal of the invalid tracking target and obtain the IF waveform characteristics of the invalid tracking target.

[0050] In some embodiments, the step of performing high-frequency IMF extraction on the IF signal of the invalid tracking target and obtaining the IF waveform features of the invalid tracking target includes: Collect all IF signals of a single invalid tracking target within its existence period to form an IF signal set; The high-frequency intrinsic mode function (IMF) of each IF signal in the IF signal set is extracted using the EMD method. The high-frequency IMF similarity of adjacent IF signals of the invalid tracking target is calculated, and the similarity result is obtained after normalization. Using the similarity results as a distance index, the k-means clustering algorithm is used to cluster all the IF signals, and the high-frequency IMF corresponding to the feature cluster containing the most IF signals is taken as the IF waveform feature of the invalid tracking target.

[0051] Specifically, the aforementioned method can be used to calculate the number of invalid tracking targets and the false alarm rate of the onboard millimeter-wave radar during each vehicle use. A higher false alarm rate for the onboard millimeter-wave radar during the nth vehicle use indicates a greater number of invalid tracking targets. Therefore, the reference value of the IF waveforms corresponding to these invalid tracking targets is greater.

[0052] Therefore, for the y-th invalid tracking target during the nth vehicle usage, the Empirical Mode Decomposition (EMD) method is first used to process the multiple IF signals of the y-th invalid tracking target, resulting in multiple high-frequency IMFs for each IF signal. Since the high-frequency IMFs (such as IMF1-3) after EMD decomposition typically contain noise and transient interference, the similarity of the high-frequency IMFs of the multiple IF signals in the y-th invalid tracking target is analyzed to determine the interference IMF characteristics of the y-th invalid tracking target. Specifically: For the k-th and (k+1)-th IF signals of the y-th invalid tracked target, we first analyze the similarity of the various high-frequency IMFs of the k-th and (k+1)-th IF signals. The specific mathematical formulas are shown below: In the formula, This represents the similarity between the k-th IF signal of the y-th invalid tracked target and the m-th high-frequency IMF of the (k+1)-th IF signal. This represents the normalization function. This represents the cross-correlation coefficient between the k-th IF signal and the m-th high-frequency IMF of the (k+1)-th IF signal.

[0053] Specifically, the number of cross-relationships The calculation can be performed using the following steps: Let the m-th high-frequency IMF of the k-th IF signal be a sequence. The m-th high-frequency IMF of the (k+1)-th IF signal is a sequence. Where N is the number of sampling points for the two high-frequency IMF sequences (ensuring the two sequences have the same length). Further, the mean values ​​of sequences X and Y are calculated separately: Furthermore, the linear correlation between the two sequences is calculated using the following formula: The result ranges from [-1, 1]. The closer to 1, the stronger the positive correlation; the closer to -1, the stronger the negative correlation; and the closer to 0, the less significant the correlation.

[0054] This represents the amplitude fluctuation of the m-th high-frequency IMF of the k-th IF signal (determined by the difference between the highest and lowest amplitudes). This represents the amplitude fluctuation value of the m-th high-frequency IMF of the (k+1)-th IF signal. The smaller the value, the more similar the amplitude fluctuations of the k-th IF signal and the m-th high-frequency IMF of the (k+1)-th IF signal of the y-th invalid tracked target, and the greater the cross-correlation. Therefore The larger the value, the greater the similarity between the k-th IF signal of the y-th invalid tracked target and the m-th high-frequency IMF of the (k+1)-th IF signal.

[0055] Furthermore, the k-means clustering algorithm is used to cluster all IF signals of the y-th invalid tracking target, where the distance between different IF signals is determined by... Quantization is then performed. The number of clusters is determined based on the silhouette coefficient. The high-frequency IMF corresponding to the cluster with the most IF signals within the cluster after clustering is used as the IF waveform feature of the invalid tracking target.

[0056] Similarly, using the method described above, all high-frequency IMF features of the y-th invalid tracked target can be calculated. Furthermore, all high-frequency IMF features of each invalid tracked target during the nth vehicle usage can be calculated.

[0057] S12. If a new IF signal is acquired, the historical false alarm level and the IF waveform characteristics are combined to determine whether the newly acquired IF signal is an interference signal, thereby filtering out the effective tracking target (i.e., the tracking object that is determined to be a non-interference signal and conforms to the characteristics of the real target after filtering) and triggering the corresponding warning.

[0058] In some embodiments, the step of determining whether a newly acquired IF signal is an interference signal by combining the historical false alarm rate and the IF waveform characteristics if a new IF signal is acquired includes: If a new IF signal is acquired, the newly acquired IF signal is subjected to high-frequency IMF extraction using the EMD method; The high-frequency IMF of the real-time intermediate frequency signal is compared with all features in the IF waveform feature library of historical invalid tracking targets. The similarity is calculated and the maximum similarity value under each high-frequency dimension is extracted. Based on the false alarm rate and the number of corresponding invalid targets in each historical vehicle usage process, a weighted average of the maximum similarity value is used to obtain a probability score of the real-time intermediate frequency signal as an interference signal. The probability score is compared with a preset probability score threshold (e.g., 0.6). If it exceeds the preset threshold, it is determined to be an interference signal; otherwise, it is determined to be a valid target signal.

[0059] Specifically, during the subsequent operation of the vehicle, after identifying new IF signals using the CFAR algorithm, it is necessary to analyze the similarity between the new IF signals and high-frequency IMF features. The higher the similarity between the new IF signals and high-frequency IMF features, the higher the likelihood that it is an interference signal. Specifically, the mathematical formula for scoring the probability that a new IF signal is an interference signal is: In the formula, This indicates the probability score that the new IF signal is an interference signal. This indicates the number of times a vehicle has been used in its history. This indicates the false alarm level of the onboard millimeter-wave radar during the nth use of the vehicle. This represents the number of invalid targets during the nth vehicle use. M represents the number of high-frequency IMFs. This represents the maximum similarity among all high-frequency IMF features of the m-th high-frequency IMF and the y-th invalid target in the new IF signal.

[0060] In practical applications, a threshold can be set for the probability of interference signals based on actual needs. For example, if the calculated... A value greater than 0.6 indicates that the new IF signal may be an interference signal. Therefore, it does not need to be added to the target tracking set; if the calculated value is... If the value is less than or equal to 0.6, it indicates that the new IF signal may be a valid target signal, and it needs to be added to the target tracking set. This process continues until all IF signals have been processed, thus obtaining the target tracking set. Finally, the trajectory of the tracked target is obtained based on the target tracking algorithm, and early warning processing is performed when necessary.

[0061] For example, when a valid target enters the blind spot detection (BSD) range and the lateral distance between it and the vehicle is less than a preset distance threshold (e.g., 1.5m), the system triggers a warning. The warning can be issued by flashing a warning light on the rearview mirror and emitting a low-frequency warning sound to remind the driver that a vehicle has entered the blind spot from the side and rear, and to exercise caution when changing lanes or opening doors.

[0062] If a valid target enters the Lane Change Assist (LCA) detection range and its relative speed exceeds a preset speed threshold (e.g., 20 km / h), a warning is activated. At this time, the Lane Change Assist indicator light on the vehicle's instrument panel illuminates, and tactile feedback is provided to the driver via steering wheel vibration, informing the driver that there is a risk in changing lanes.

[0063] When the vehicle is stationary, a warning is triggered when the millimeter-wave radar detects a valid target within the door opening warning (DOW) range, and the relative speed and distance changes between the target and the vehicle meet the conditions for a potential collision. The warning manifests as the warning lights at the power window buttons on all four doors illuminating, accompanied by a sharp alarm sound, to prevent passengers from recklessly opening the doors and colliding with oncoming vehicles or pedestrians.

[0064] If a valid target is located behind the vehicle, and its trajectory, speed, distance, and other parameters are calculated to predict a potential collision with the vehicle within a short period (e.g., within 2 seconds), the Rear Collision Warning (RCW) system will activate. The warning will manifest as a vibration of the vehicle's seat back, accompanied by a rapid alarm sound from the in-vehicle multimedia system, reminding the driver to take braking or evasive action to avoid a rear-end collision.

[0065] In some embodiments, it also includes: For all invalid tracking targets' IF signals, Empirical Mode Decomposition (EMD) is used to decompose them, separating the high-frequency intrinsic mode functions (IMFs) as high-frequency interference components, focusing on the core fluctuation characteristics of the interference signal. The core characteristics of interference signals (such as multi-radar interference, environmental noise, etc.) are often hidden in high-frequency fluctuations. Through EMD, non-stationary IF signals can be decomposed into a series of intrinsic mode functions (IMFs), among which the high-frequency IMFs (usually IMF1-3) reflect the transient fluctuation characteristics of the interference.

[0066] By calculating the cross-correlation coefficient and amplitude fluctuation difference of high-frequency interference components, similarity is analyzed, and clustering is used to identify common characteristics of interference of the same type (such as fluctuation patterns in specific frequency bands and amplitude change patterns). The interference is then classified and stored according to the type of interference to form a dynamically updated interference feature library. Upon receiving a new IF signal, EMD decomposition is immediately performed on the newly acquired IF signal to extract its first three high-frequency IMFs (which can also be adjusted according to actual needs), serving as the matching benchmark. Using all common features in the feature library as references, the matching degree between the new signal's high-frequency IMFs and each reference feature is calculated. Commonly used indicators include: cosine similarity (measures the directional consistency between two IMF sequences; the closer the value is to 1, the more similar the features); Euclidean distance (measures the numerical difference between two IMF sequences; the smaller the value, the closer the features), etc.

[0067] Specifically, let the two high-frequency IMF sequences to be matched be: the high-frequency IMF sequence of the newly acquired IF signal: High-frequency IMF sequences with a common feature in the interference feature library: , Where N is the number of sampling points in the two sequences (the length needs to be consistent by padding with zeros or truncating).

[0068] Furthermore, cosine similarity measures the directional consistency between two high-frequency IMF sequences, focusing on the "fluctuation pattern similarity" of key features. It is unaffected by sequence amplitude scaling and ranges from [-1, 1]. The specific calculation formula is as follows: In this model, the numerator represents the dot product of sequences X and Y, reflecting the degree of coordinated fluctuation between the two sequences; the denominator represents the product of the L2 norm (modulus) of sequence X and the L2 norm of sequence Y, used for normalization to eliminate the influence of amplitude differences. In interference feature matching, cosine similarity is used to determine the consistency of the fluctuation pattern between the high-frequency IMF of the new signal and the interference features in the feature library (e.g., whether they all have a periodic fluctuation of 100Hz). The closer the value is to 1, the more likely the new signal belongs to the same type of interference.

[0069] Furthermore, the Euclidean distance measures the absolute distance between two high-frequency IMF sequences in numerical space, focusing on the "amplitude difference" of the feature. The smaller the value, the closer the numerical distributions of the two sequences are. The specific calculation formula is as follows: The formula calculates the difference between the two sequences point by point, squares the differences, sums them, and takes the square root to obtain the "overall numerical deviation" of the two sequences. In interference feature matching, the Euclidean distance is used to determine the "amplitude stability similarity" between the high-frequency IMF of the new signal and the interference features in the feature library (such as whether both have an amplitude fluctuation range of ±2V). The smaller the value, the more the amplitude change pattern of the new signal matches the known interference.

[0070] In the real-time interference determination stage, two indicators are usually combined for comprehensive judgment: first, candidate interference features with similar fluctuation patterns are screened by cosine similarity; then, similar amplitude change patterns are verified by Euclidean distance; finally, the "maximum matching degree" (maximum cosine similarity / minimum Euclidean distance, which needs to be normalized to unify the dimension) is compared with a preset interference value (such as 85%) to determine whether it is an interference signal. If the matching degree exceeds the preset interference value (such as 85%), it is determined to be an interference signal and is removed; if it does not exceed the preset interference value, it is confirmed as a valid target signal and included in the real-time tracking system.

[0071] In some embodiments, it also includes: Each time the vehicle is turned off or the trip ends, the radar sampling data, triggered warning records, tracked target trajectory / speed information, false alarm rate statistics, and newly extracted IF waveform features are automatically cleaned (denoised, missing values ​​are filled) and standardized. The processed data is categorized and stored in the database according to timestamps and scene tags (such as city roads and highways); The database is incrementally updated at a preset frequency (such as every 24 hours or every 10 trips), retaining recent valid data and eliminating outdated features to ensure that the interference identification model is always adapted to the latest environment.

[0072] It should be noted that the device provided in the above embodiments is only an example of the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above.

[0073] Example 2: Please see Figure 2 This illustrates an embodiment of the present invention providing an anti-jamming system for vehicle-mounted millimeter-wave radar in complex environments, the system comprising: The determination module 20 is used to identify and track targets based on vehicle millimeter-wave radar data from the historical vehicle usage process, and to calculate the validity of the trajectory length and trajectory distribution of each tracked target, thereby determining invalid tracked targets and determining the degree of historical false alarms. The acquisition module 21 is used to perform high-frequency IMF extraction on the IF signal of the invalid tracking target and acquire the IF waveform features of the invalid tracking target; The filtering module 22 is used to determine whether a new IF signal is an interference signal by combining the historical false alarm level and the IF waveform characteristics if a new IF signal is acquired, thereby filtering out effective tracking targets and triggering corresponding warnings.

[0074] Alternatively, the transmission medium may be a wired link, such as, but not limited to, coaxial cable, fiber optic cable and digital subscriber line, or a wireless link, such as, but not limited to, wireless Fidelity (WIFI), Bluetooth and mobile device networks.

[0075] It should be noted that the device provided in the above embodiments is only an example of the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above.

[0076] Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. For example, as shown... Figure 3 As shown, the computer device 30 includes: a memory 31, a processor 32, and a computer program 33 stored in the memory 31 and running on the processor 32. When the processor 32 executes the computer program 33, the computer device can execute any vehicle-mounted millimeter-wave radar anti-jamming method for complex environments described above.

[0077] Furthermore, embodiments of the present invention also protect an apparatus that may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to perform the anti-jamming method for vehicle-mounted millimeter-wave radar in complex environments provided by embodiments of the present invention.

[0078] In this embodiment of the invention, the device can be divided into functional modules according to the above method example. For example, each module can correspond to a separate function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and is only a logical functional division. In actual implementation, there may be other division methods.

[0079] It should be understood that the apparatus provided in this embodiment of the invention is used to perform the above-described anti-interference method for vehicle-mounted millimeter-wave radar in complex environments, and therefore can achieve the same effect as the above-described implementation method.

[0080] When using integrated units, the device may include a processing module and a storage module. When applied to a device, the processing module can be used to control and manage the device's operations. The storage module can be used to support the device in executing program code, etc. The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits as described in this disclosure. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of Digital Signal Processing (DSP) and a microprocessor, etc., and the storage module may be a memory.

[0081] In addition, the device provided in the embodiments of the present invention may specifically be a chip, component or module. The chip may include a connected processor and a memory. The memory is used to store instructions. When the processor calls and executes the instructions, the chip can execute the anti-interference method for vehicle-mounted millimeter-wave radar in complex environments provided in the above embodiments.

[0082] This invention also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, the computer executes the aforementioned method steps to implement the anti-interference method for vehicle-mounted millimeter-wave radar in complex environments provided in the above embodiments.

[0083] This invention also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to achieve the anti-interference method for vehicle-mounted millimeter-wave radar in complex environments provided in the above embodiments.

[0084] In this invention, the apparatus, computer-readable storage medium, computer program product, or chip provided in the embodiments are all used to execute the corresponding methods described above. Therefore, the beneficial effects they achieve can be referred to the beneficial effects in the corresponding methods described above, and will not be repeated here. Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In the embodiments provided by this invention, it should be understood that the disclosed apparatus and method can be implemented in other ways.

[0085] The device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0086] It should also be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0087] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0088] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0089] The above content is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the protection scope of the present invention.

Claims

1. A method for anti-interference of vehicle-mounted millimeter-wave radar in complex environments, characterized in that, The method includes the following steps: Based on the vehicle's historical usage data, the vehicle-mounted millimeter-wave radar identifies and tracks targets, and calculates the validity of the trajectory length and trajectory distribution of each tracked target to determine invalid tracked targets and the degree of historical false alarms. High-frequency IMF extraction is performed on the IF signal of the invalid tracking target, and the IF waveform characteristics of the invalid tracking target are obtained; If a new IF signal is acquired, the historical false alarm level and the IF waveform characteristics are combined to determine whether the newly acquired IF signal is an interference signal, thereby filtering out effective tracking targets and triggering corresponding warnings.

2. The anti-interference method for vehicle-mounted millimeter-wave radar in complex environments according to claim 1, characterized in that, The vehicle-mounted millimeter-wave radar data is acquired through the following methods: Real-time acquisition of IF signals in the vehicle's driving area via vehicle-mounted millimeter-wave radar; The acquired IF signal is preprocessed in a preset manner, and the preprocessed vehicle millimeter-wave radar data is stored in a cache.

3. The anti-interference method for vehicle-mounted millimeter-wave radar in complex environments according to claim 2, characterized in that, The vehicle-mounted millimeter-wave radar is equipped with a specific frequency band radio frequency chip and a multi-channel antenna array. The real-time acquisition of the IF signal of the vehicle's driving area by the vehicle-mounted millimeter-wave radar specifically includes: The specific frequency band radio frequency chip transmits FMCW frequency-modulated continuous waves to the vehicle driving area in real time, covering a preset detection distance; The target radio frequency echo signal is received through the multi-channel antenna array; The target radio frequency echo signal is mixed with the transmitted signal to generate an IF signal.

4. The anti-interference method for vehicle-mounted millimeter-wave radar in complex environments according to claim 1, characterized in that, The vehicle-mounted millimeter-wave radar data based on historical vehicle usage data is used to identify and track targets, including: Retrieve vehicle-mounted millimeter-wave radar data and warning signals from multiple vehicle usage cycles; For the vehicle-mounted millimeter-wave radar data and warning signals during a single vehicle use, the CFAR algorithm is used to identify target signals and non-target signals. The target is identified and tracked using a target tracking algorithm.

5. The anti-interference method for vehicle-mounted millimeter-wave radar in complex environments according to claim 1, characterized in that, The calculation of the trajectory length validity and trajectory distribution validity of each of the tracked targets includes: Extract the complete trajectory data of a single tracked target within consecutive sampling moments during a single use of the vehicle, and count the number of sampling points contained in the trajectory data and / or the cumulative length of the trajectory in the spatial dimension to obtain the total trajectory length of the tracked target; The correlation between the total length of the trajectory and the preset minimum ideal value is established by exponential operation in order to obtain the validity of the trajectory length of the tracked target; 2D-FFT was used to process the complete trajectory data of a single tracked target, and the range spectrum and velocity spectrum corresponding to the trajectory at each sampling time were extracted respectively; The effectiveness of the range spectrum and the effectiveness of the velocity spectrum are calculated using a preset calculation method to generate range spectrum effectiveness index and velocity spectrum effectiveness index, thereby determining the effectiveness of the trajectory distribution of the tracked target.

6. The anti-interference method for vehicle-mounted millimeter-wave radar in complex environments according to claim 1, characterized in that, The step of performing high-frequency IMF extraction on the IF signal of the invalid tracking target and obtaining the IF waveform features of the invalid tracking target includes: Collect all IF signals of a single invalid tracking target within its existence period to form an IF signal set; High-frequency IMF extraction is performed on each IF signal in the IF signal set using the EMD method. The high-frequency IMF similarity of adjacent IF signals of the invalid tracking target is calculated, and the similarity result is obtained after normalization. Using the similarity results as a distance index, the k-means clustering algorithm is used to cluster all the IF signals, and the high-frequency IMF corresponding to the feature cluster containing the most IF signals is taken as the IF waveform feature of the invalid tracking target.

7. The anti-interference method for vehicle-mounted millimeter-wave radar in complex environments according to claim 1, characterized in that, If a new IF signal is acquired, determining whether the newly acquired IF signal is an interference signal by combining the historical false alarm level and the IF waveform characteristics includes: If a new IF signal is acquired, the newly acquired IF signal is subjected to high-frequency IMF extraction using the EMD method; The high-frequency IMF of the real-time intermediate frequency signal is compared with all features in the IF waveform feature library of historical invalid tracking targets, the similarity is calculated and the maximum similarity value under each high-frequency dimension is extracted. Based on the false alarm rate and the number of corresponding invalid targets in each historical vehicle usage process, a weighted average of the maximum similarity value is used to obtain a probability score of the real-time intermediate frequency signal as an interference signal. The probability score is compared with a preset threshold. If it exceeds the preset threshold, it is determined to be an interference signal; otherwise, it is determined to be a valid target signal.

8. The anti-interference method for vehicle-mounted millimeter-wave radar in complex environments according to claim 1, characterized in that, Also includes: The IF signals of all the invalid tracking targets are decomposed to obtain high-frequency interference components; The similarity of the high-frequency interference components is analyzed to determine the common features of the interference signals. These common features are then categorized and stored to form an interference feature library. If a new IF signal is acquired, the matching degree between the newly acquired IF signal and the features in the interference feature library is calculated. If the matching degree exceeds the preset interference value, it is determined to be an interference signal and is eliminated; If the matching degree does not exceed the preset interference value, it is determined to be a valid tracking target and included in the tracking range.

9. The anti-interference method for vehicle-mounted millimeter-wave radar in complex environments according to claim 1, characterized in that, Also includes: Each time a vehicle is used, the sampled data, and / or warning signals, and / or tracking target information, and / or false alarm level, and / or IF waveform characteristics of this vehicle use process are preprocessed and stored in the database; Update the data in the database at a preset frequency.

10. A vehicle-mounted millimeter-wave radar anti-jamming system for complex environments, characterized in that, The system includes the following modules: The determination module is used to identify and track targets based on vehicle millimeter-wave radar data from historical vehicle usage, and to calculate the validity of the trajectory length and trajectory distribution of each tracked target, thereby determining invalid tracked targets and determining the degree of historical false alarms. The acquisition module is used to perform high-frequency IMF extraction on the IF signal of the invalid tracking target and acquire the IF waveform characteristics of the invalid tracking target; The filtering module is used to determine whether a new IF signal is an interference signal by combining the historical false alarm level and the IF waveform characteristics, thereby filtering out valid tracking targets and triggering corresponding warnings.

Images