False alarm identification modeling method, identification method, equipment, storage medium and product

Abstract

The present invention discloses a false alarm identification modeling method, identification method, device, storage medium, and product, relating to the field of radar technology. The modeling method comprises acquiring target trajectory data; extracting the target point echo signal based on target point information, the acquired radar echo signal, and a steering vector; performing micro-Doppler feature extraction on the target point echo signal to obtain a micro-Doppler map; annotating the micro-Doppler map and constructing a sample data set based on the micro-Doppler map and its annotations; constructing a deep learning network model, and using the sample data set to train and test the deep learning network model to obtain a false alarm identification model. The present invention achieves accurate detection of real targets and false targets in complex backgrounds, improves detection accuracy, reduces false alarm rate, and enhances the anti-interference capability and robustness of radar equipment.

Description

Technical Field

[0001] The present invention belongs to the field of radar technology, and in particular relates to a false alarm identification modeling method, an identification method, a device, a storage medium and a product. Background Art

[0002] A wall-penetrating radar uses electromagnetic signals to detect targets behind walls or other obstructions. It utilizes the strong penetration of ultra-wideband radar signals through non-metallic walls and other obstacles. After penetrating these non-metallic obstacles, it encounters human targets and generates radar echoes. Small movements such as human movement, breathing, heartbeat, body swaying, and limb swinging create a Doppler effect on these echoes. Based on this effect, the received echoes are processed and analyzed to determine the location, number, and posture of human targets behind the wall, which is then displayed on the control terminal client software interface.

[0003] A false alarm occurs when the system mistakenly indicates the presence of a target when no actual target exists. For example, in typical everyday situations, there are often not only human targets but also non-human objects such as fans, air conditioners, and curtains. These non-human objects can also create a Doppler effect on the echo during use, causing the through-wall radar equipment to generate false alarms. False alarms reduce the reliability and effectiveness of radar systems, potentially leading to wasted resources, poor decision-making, and even security threats. For example, they can place unnecessary burdens on emergency response, delay rescue efforts, and result in loss of life and property.

[0004] False alarm suppression technology aims to reduce false alarms in detection systems, ensuring that only targets are detected and displayed or triggered. This helps improve detection accuracy, avoids wasted resources due to false detections, and ensures that operators can rely on the information provided by the system to make correct decisions. Therefore, false alarm suppression technology plays a vital role in improving the overall performance and effectiveness of the system.

[0005] The development of micro-Doppler technology provides an effective approach for radar target identification and false alarm suppression. Research has shown that the micro-motion characteristics of human targets, whether stationary or in motion, differ significantly from those of non-human targets. These differences in micro-motion characteristics can provide effective information for radar target detection and identification. Micro-motion refers to small, periodic movements of an object that are independent of macroscopic motion. For example, human breathing or heartbeats cause tiny vibrations in the body; a robotic arm may also experience subtle vibrations while performing a task. These tiny movements are usually imperceptible to the naked eye, but can be detected by radar and other sensor technologies. The micro-Doppler effect occurs when an object's micro-motion causes a slight shift in the frequency of its radar echo signal. Different targets exhibit different micro-Doppler characteristics due to factors such as their material, shape, and motion. For example, human breathing and heartbeats produce a specific micro-Doppler pattern, while rotating fan blades produce another distinct set of micro-Doppler patterns. These differences in micro-Doppler patterns can be distinguished through time-frequency analysis of the echo signals. Common time-frequency analysis methods include short-time Fourier transform (STFT) and Wigner-Ville distribution. To distinguish the differences in micro-Doppler characteristics between different targets, a micro-motion model can be established, and machine learning algorithms can be used to learn the typical micro-Doppler signatures of different targets from a large amount of training data. These signatures can then be matched in practical applications to identify target types.

[0006] In recent years, artificial intelligence technologies, represented by deep learning, have developed rapidly. Deep learning offers advantages in solving practical problems, including strong learning capabilities, higher accuracy than traditional machine learning models, and strong generalization capabilities. Deep learning has also been widely applied in fields such as radar signal processing. For example, human posture recognition methods based on deep learning and Doppler radar have been used in areas such as gesture recognition and gait recognition. Convolutional Neural Networks (CNNs) are the most commonly used algorithms in computer vision, particularly in image processing. CNNs can achieve high-precision classification of input images, and feature extraction requires no human intervention.

[0007] Therefore, combining deep learning with micro-Doppler images for intelligent extraction and recognition of target micro-motion features can not only make full use of the micro-motion information in micro-Doppler images, but also give play to the advantages of deep learning in image processing, thereby realizing radar target recognition and false alarm suppression.

[0008] Currently, false alarm identification methods for through-wall radar include traditional methods and feature extraction-based methods. Among them, traditional methods usually rely on threshold setting to filter out false alarms. This method is simple but easily affected by environmental noise. Especially in complex scenarios, its performance will be greatly reduced. Feature extraction-based methods manually design features and then use machine learning algorithms (such as support vector machines (SVMs) and random forests (RFs) for classification. Although this method can improve the accuracy of target detection to a certain extent, it has poor adaptability to dynamically changing environments. Summary of the Invention

[0009] The present invention aims to provide a false alarm identification modeling method, an identification method, a device, a storage medium and a product to solve the problems of poor environmental adaptability and low false alarm detection accuracy of traditional false alarm suppression technologies.

[0010] The present invention solves the above technical problems through the following technical solutions: a false alarm identification modeling method, comprising:

[0011] Acquire target trajectory data; wherein the target trajectory data includes target point information at different times, and the target point information includes the distance unit and the azimuth unit where the target is located;

[0012] Obtain radar echo signals and guidance vectors after clutter suppression;

[0013] Extracting the target point echo signal according to the target point information, the radar echo signal after clutter suppression, and the guidance vector;

[0014] When the length of the target point echo signal reaches a set threshold, performing micro-Doppler feature extraction on the target point echo signal to obtain a micro-Doppler map;

[0015] Annotating the micro-Doppler image and constructing a sample data set based on the micro-Doppler image and its annotations;

[0016] A deep learning network model is constructed, and the deep learning network model is trained and tested using the sample data set to obtain a false alarm recognition model.

[0017] Furthermore, before extracting the target point echo signal, the modeling method further includes performing a sliding average process on the target point information. The specific processing formula is:

[0018]

[0019] Among them, N A and P AThey represent the distance unit and azimuth unit of the target after sliding average processing, round() represents the rounding function, K represents the size of the sliding average window, and N i and P i They represent the distance unit and azimuth unit of the target at the i-th moment before sliding average processing.

[0020] Furthermore, extracting the target point echo signal according to the target point information, the radar echo signal after clutter suppression, and the steering vector specifically includes:

[0021] Extract the Nth A The echo signal of the range unit is extracted from the guidance vector. A Steering vector of each azimuth unit;

[0022] According to the Nth A The echo signal of the first distance unit and the A The target point echo signal is calculated based on the guidance vector of each azimuth unit. The specific calculation formula is:

[0023] I(N A ,P A )=X N θ p ;

[0024] Among them, X N Indicates the Nth A The echo signal of the range unit, θ p Indicates the P A The steering vector of the azimuth unit, I(N A ,P A ) represents the Nth A The distance unit is in the P A The signal strength of each azimuth unit, N A and P A Respectively represent the distance unit and azimuth unit where the target is located.

[0025] Furthermore, when the length of the target point echo signal reaches a set threshold, before extracting the micro-Doppler feature of the target point echo signal, the modeling method further includes correcting the target point echo signal, specifically including:

[0026] Performing first-order difference processing on the target point echo signal to obtain the difference between the data before and after each moment;

[0027] The one-dimensional constant false alarm rate method is used to detect the difference between the data before and after each moment to obtain the discontinuity point;

[0028] Calculating the amplitude and phase difference of the data before and after each discontinuity point, and using the amplitude and phase difference as the correction weight of the discontinuity point;

[0029] According to the correction weight, the data after the discontinuous point is weighted point by point to obtain a corrected target point echo signal.

[0030] Furthermore, the deep learning network model selects the MobileNetV3 model, and the MobileNetV3 model is built based on the pytorch deep learning framework, and the number of channels of the input layer of the MobileNetV3 model is changed to 1.

[0031] Based on the same concept, the present application also provides a false alarm identification method, which includes:

[0032] Calling a false alarm identification model; wherein the false alarm identification model is constructed according to the false alarm identification modeling method described above;

[0033] A micro-Doppler map of an unknown target is obtained, and false alarm identification is performed on the micro-Doppler map of the unknown target using the false alarm identification model.

[0034] Furthermore, the micro-Doppler map of the unknown target is obtained, including:

[0035] Acquire unknown target trajectory data; wherein the unknown target trajectory data includes unknown target point information at different times, and the unknown target point information includes the distance unit and the azimuth unit where the unknown target is located;

[0036] Obtain radar echo signals and guidance vectors after clutter suppression;

[0037] Extracting the unknown target point echo signal according to the unknown target point information, the radar echo signal after clutter suppression, and the guidance vector;

[0038] When the length of the unknown target point echo signal reaches a set threshold, micro-Doppler feature extraction is performed on the unknown target point echo signal to obtain a micro-Doppler map of the unknown target.

[0039] Furthermore, the identification method further includes abnormal target management, and the abnormal target management specifically includes:

[0040] When the length of the unknown target point echo signal does not reach the set threshold, it is determined whether the target corresponding to the unknown target point echo signal matches the target in the abnormal target library. If so, the micro-Doppler feature extraction is performed on the echo signal of the target in the abnormal target library to obtain the micro-Doppler map of the unknown target; if not, the unknown target point echo signal is discarded;

[0041] When an unknown target is identified as a false target, it is determined whether the false target matches the target in the abnormal target library. If so, the information of the target in the abnormal target library is updated; if not, the false target is entered into the abnormal target library.

[0042] Based on the same concept, the present application also provides an electronic device, including a memory, a processor, and a computer program / instruction stored in the memory, wherein the processor executes the computer program / instruction to implement the false alarm identification modeling method as described above.

[0043] Based on the same concept, the present application also provides a computer-readable storage medium having a computer program / instruction stored thereon, which implements the false alarm identification modeling method described above when the computer program / instruction is executed by a processor.

[0044] Based on the same concept, the present application also provides a computer program product, including a computer program / instruction, which implements the false alarm identification modeling method described above when executed by a processor.

[0045] Beneficial effects

[0046] Compared with the prior art, the advantages of the present invention are:

[0047] The present invention uses micro-Doppler characteristics to distinguish human targets from non-human targets (i.e., false targets). Micro-Doppler characteristics reflect the frequency changes caused by the different movement speeds of different parts of the target. This frequency change can provide information about the physical characteristics of the target. By utilizing the strong learning ability of the deep learning network model to learn the association between micro-Doppler characteristics and target categories, the difference between human targets and false targets can be more accurately identified, thereby achieving precise detection of real targets and false targets in complex backgrounds, improving detection accuracy, reducing false alarm rate, and enhancing the anti-interference ability and robustness of radar equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only one embodiment of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 1 is a flow chart of a false alarm identification modeling method according to an embodiment of the present invention;

[0050] Figure 2 1 is a schematic diagram of discontinuous point detection of a target point echo signal in an embodiment of the present invention;

[0051] Figure 3is a time-frequency diagram of the target point echo signal before correction in an embodiment of the present invention;

[0052] Figure 4 is a time-frequency diagram of the target point echo signal after correction in an embodiment of the present invention;

[0053] Figure 5 Schematic diagram of extracting micro-Doppler characteristics using short-time Fourier transform in an embodiment of the present invention;

[0054] Figure 6 is a micro-Doppler map of a false target in an embodiment of the present invention;

[0055] Figure 7 is a micro-Doppler image of a human target in an embodiment of the present invention;

[0056] Figure 8 4 is a flow chart of a false alarm identification method in an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The following is a clear and complete description of the technical solutions of the present invention in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts are within the scope of protection of the present invention.

[0058] The following specific embodiments are used to describe the technical solution of the present application in detail. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0059] Example 1

[0060] Figure 1 The flowchart of the false alarm identification modeling method provided by the present invention is shown. Figure 1 As shown, the modeling method includes the following steps:

[0061] Step 1: Obtain target trajectory data.

[0062] During detection, through-the-wall radar receives and processes radar echo signals to determine the target location. The target location refers to the range and azimuth units of the target. Tracking the target location yields target trajectory data, which includes target location information at different times, i.e., the range and azimuth units of the target at each moment.

[0063] Step 2: Obtain the radar echo signal and steering vector after clutter suppression.

[0064] To prevent clutter from affecting detection accuracy, radar echo signals are subjected to clutter suppression to obtain a clutter-suppressed radar echo signal. A steering vector describes the directional characteristics of the signal received by the antenna array. This vector is determined based on the radar's antenna array type and the signal's incident angle. Obtaining this vector is a well-known technique.

[0065] Step 3: Perform sliding average processing on the target point information of the target trajectory data in step 1.

[0066] Since static targets may not be completely stationary, the target point information recorded in the target trajectory data will vary within a small range. This variation is not conducive to the extraction of the target point echo signal. It is necessary to perform sliding average processing on the target point information to eliminate short-term fluctuations in the target point information. In a specific embodiment of the present invention, the sliding average processing formula is:

[0067]

[0068] Among them, N A and P A They represent the distance unit and azimuth unit of the target after sliding average processing, round() represents the rounding function, K represents the size of the sliding average window, and N i and P i They represent the distance unit and azimuth unit of the target at the i-th moment before sliding average processing.

[0069] The size K of the sliding average window represents the amount of target point information considered when calculating the average value. The advantage of sliding average processing is that it is simple and easy to implement, but the disadvantage is that it is easily affected by outliers, so it is necessary to select an appropriate window size. The present invention determines the size of the sliding average window based on the sampling frequency of the target point information and the fluctuation period of the target point information. For example, assuming the sampling frequency is 20 times / second and the disturbance period is 5s, the size K of the sliding average window should be no less than 100 to ensure that short-term fluctuations in the target point information are eliminated. In this embodiment, after experimental verification, the size K of the sliding average window is preferably 120.

[0070] Step 4: Extract the target point echo signal based on the target point information processed in step 3, the radar echo signal after clutter suppression obtained in step 2, and the guidance vector.

[0071] Since multi-pulse accumulation is used in the MTD (Moving Target Detection) process, it is impossible to extract the target point echo signal directly through beamforming. Therefore, the present invention extracts the echo signal from the radar echo signal after clutter suppression and the steering vector based on the target point information processed in step 3. In a specific embodiment of the present invention, the target point echo signal is extracted based on the target point information, the radar echo signal after clutter suppression, and the steering vector, specifically including:

[0072] Step 4.1: Extract the Nth signal from the radar echo signal after clutter suppression. A The echo signal of each distance unit;

[0073] Step 4.2: Extract the Pth from the steering vector A Steering vector of each azimuth unit;

[0074] Step 4.3: According to the Nth A The echo signal of the first distance unit and the A The target point echo signal is calculated based on the guidance vector of each azimuth unit. The specific calculation formula is:

[0075] I(N A ,P A )=X N θ p (2)

[0076] Among them, X N Indicates the Nth A The echo signal of the range unit, θ p Indicates the P A The steering vector of the azimuth unit, I(N A ,P A ) represents the Nth A The distance unit is in the P A The signal strength of each azimuth unit, N A and P A They represent the distance unit and azimuth unit of the target. Based on the radar echo signals of multiple pulses, the target point echo signal of a certain length can be obtained.

[0077] Step 5: Correct the target point echo signal extracted in step 4.

[0078] Since the position information of a static target may change within a small range, this change will cause the echo signal between two consecutive frames to be discontinuous (e.g. Figure 2 As shown in the figure), the obvious discontinuity of the target point echo signal will cause the micro-Doppler image to have spectrum diffusion phenomenon at the discontinuous moment (as shown in the figure). Figure 3As shown), the target point echo signal extracted in step 4 may not be used directly and needs to be corrected. In a specific embodiment of the present invention, the target point echo signal extracted in step 4 is corrected, specifically including:

[0079] Step 5.1: Perform first-order difference processing on the target point echo signal to obtain the difference between the data before and after each moment;

[0080] Step 5.2: Use the one-dimensional constant false-alarm rate (CFAR) method to detect the difference between the data before and after each moment to obtain the discontinuity point; when the difference is greater than the threshold value, the moment is the discontinuity point, such as Figure 2 As shown;

[0081] Step 5.3: Calculate the amplitude and phase difference of the data before and after each discontinuity point, and use the amplitude and phase difference as the correction weight of the discontinuity point;

[0082] Step 5.4: According to the correction weight, the data after the discontinuous point is weighted point by point to make the amplitude and phase continuous, and obtain the corrected target point echo signal.

[0083] Figure 4 The time-frequency diagram of the target point echo signal after correction is shown. Figure 4 It can be seen that after correction, the micro-Doppler spectrum diffusion phenomenon of the target point echo signal is well suppressed.

[0084] Step 6: Determine whether the length of the target point echo signal corrected in step 5 reaches the set threshold.

[0085] By setting the threshold reasonably, the target point echo signal with too short length can be filtered out, so as to prevent the micro-Doppler features extracted in the subsequent steps from being insufficient due to the short signal, thereby affecting the subsequent recognition effect.

[0086] When the length of the corrected target point echo signal reaches the set threshold, proceed to step 7, that is, extract the micro-Doppler features of the target point echo signal; when the length of the corrected target point echo signal does not reach the set threshold, discard the target point echo signal.

[0087] Step 7: Extract the micro-Doppler features of the target point echo signal to obtain a micro-Doppler map.

[0088] In a specific embodiment of the present invention, the short-time Fourier transform (STFT) is used to extract micro-Doppler features from the echo signals of target points or targets in the abnormal target library. For a continuous echo signal x(t), its short-time Fourier transform X(τ, ω) can be expressed as:

[0089]

[0090] Where w(t) represents the window function (such as a Hamming window), τ represents the time offset (i.e., the position of the window), t represents time, and ω represents the angular frequency. When implementing STFT on a computer device, a discrete form is required. For a discrete echo signal x[n], its discrete form short-time Fourier transform X[m,k] can be expressed as:

[0091]

[0092] Among them, m represents the window index, H represents the sliding step size, w[n] represents the discrete window function, n represents the time index or frame index, k represents the frequency index, and N represents the length of the window function (i.e., the number of points of the short-time Fourier transform). The implementation process of STFT is as follows Figure 5 As shown, a window function is applied to different time periods of the echo signal. Then, the signal within each window is subjected to an FFT to obtain the time-varying frequency characteristics of the signal, i.e., a micro-Doppler map. In this embodiment, the window function length N is preferably 256, the sliding step size H is preferably 16, and the number of slides M is preferably 255. Therefore, the required echo signal length is M × H + N = 4336, meaning that the threshold can be set to 4336.

[0093] In another embodiment of the present invention, other time-frequency analysis methods may be used to extract micro-Doppler features.

[0094] Step 8: Annotate the micro-Doppler map obtained in step 7 and construct a sample dataset based on the micro-Doppler map and its annotations.

[0095] For through-wall radar, the target types only include human targets (indicated by "1") and false targets (indicated by "0"). The target type is marked on each micro-Doppler map. The micro-Doppler map of false targets (i.e. non-human targets) is marked with "0", such as Figure 6 As shown in the figure; for the micro-Doppler image of the human target, mark "1", as shown in the figure. Figure 7 shown.

[0096] Before constructing the sample dataset, the micro-Doppler images are preprocessed, including:

[0097] Data augmentation: Transform the micro-Doppler image using rotation, flipping, etc. to increase the diversity of training samples and enhance the generalization ability of the model;

[0098] Resizing: resizing the micro-Doppler image to meet the model input requirements;

[0099] Normalization: Subtract the mean and divide by the standard deviation so that the micro-Doppler map has zero mean and unit variance;

[0100] Normalization: scaling the pixel values of the micro-Doppler image to a fixed range, usually [0, 1];

[0101] Quantization: Convert floating-point pixels to integer values between 0 and 255.

[0102] A sample data set is constructed based on the preprocessed micro-Doppler map and its annotations; the sample data set is divided into a training set and a test set. The training set is used to train the deep learning network model, and the test set is used to test the deep learning network model.

[0103] Step 9: Build a deep learning network model, use the sample data set to train and test the deep learning network model, and obtain a false alarm recognition model.

[0104] Based on the balance between the requirements for accuracy and computing resources, this embodiment uses the MobileNetV3 model as the classifier, and builds the MobileNetV3 model based on the pytorch deep learning framework. According to the characteristics of the micro-Doppler map, the number of channels of the input layer of the MobileNetV3 model is changed to 1, that is, the input is changed from the original 224×224×3 to 224×224×1. Converting the input image from three channels (RGB) to a single channel (grayscale image) can significantly reduce memory usage, which is especially important for embedded systems or devices with limited computing resources. Compared with three-channel input, single-channel input reduces the amount of computation by two-thirds, especially in convolution operations. The reduction in computation can significantly improve the operational efficiency of the model.

[0105] Changing the model's input layer reduces the number of parameters in subsequent layers. For example, the number of parameters in the first convolutional layer decreases from 3×c×c to 1×c×c, where c represents the size of the convolutional kernel. This reduction in computational complexity also shortens model training time, facilitating faster model development and tuning.

[0106] In some application scenarios, the original data is inherently single-channel (such as grayscale images and infrared images). Converting the input data to a single channel makes the model more adaptable to these scenarios. In some cases, removing color information can reduce the model's detection accuracy, especially in scenarios where color information is crucial for target detection. However, micro-Doppler images can be viewed as single-channel grayscale images, so changing the number of channels does not affect the model's recognition accuracy, ensuring that the model remains accurate.

[0107] During training, the deep learning network model takes micro-Doppler maps as input and outputs the target class of the micro-Doppler maps. All training and testing were performed on a Windows platform using an Intel i7-8700 CPU and an NVIDIA RTX 1050ti GPU. During training, the hyperparameters were set to: 200 epochs, 64 batch size, and an initial learning rate of 1e. -2 , the final learning rate is 1e -7 , the learning rate adjustment strategy is the cosine annealing algorithm, and Adam is used to optimize the model parameters.

[0108] Example 2

[0109] like Figure 8 As shown, a false alarm identification method provided by an embodiment of the present invention includes the following steps:

[0110] Step 1: Calling a false alarm recognition model; wherein the false alarm recognition model is constructed according to the false alarm recognition modeling method in Example 1 of the present application;

[0111] Step 2: Obtain the micro-Doppler map of the unknown target and use the false alarm identification model to perform false alarm identification on the micro-Doppler map of the unknown target.

[0112] In a specific embodiment of the present invention, obtaining a micro-Doppler map of an unknown target includes:

[0113] Step 2.1: Obtain unknown target trajectory data; wherein the unknown target trajectory data includes unknown target point information at different times, and the unknown target point information includes the distance unit and the azimuth unit where the unknown target is located;

[0114] Step 2.2: Obtain the radar echo signal and steering vector after clutter suppression;

[0115] Step 2.3: Extract the unknown target point echo signal based on the unknown target point information, the radar echo signal after clutter suppression, and the steering vector, see formula (2) in Example 1 of the present application;

[0116] Step 2.4: When the length of the unknown target point echo signal reaches the set threshold, the micro-Doppler feature of the unknown target point echo signal is extracted to obtain the micro-Doppler map of the unknown target.

[0117] In a specific embodiment of the present invention, when the length of the corrected target point echo signal does not reach the set threshold, it is determined whether the target corresponding to the unknown target point echo signal (i.e., the current target) matches the target in the abnormal target library; if it matches, the process proceeds to step 2.4, i.e., performing micro-Doppler feature extraction on the echo signal of the target in the abnormal target library to obtain a micro-Doppler map of the unknown target; if it does not match, the target point echo signal is discarded, i.e., the target point echo signal is not processed.

[0118] When the false alarm recognition model identifies an unknown target as a false target, it determines whether the false target matches the target in the abnormal target library. If so, the information of the target in the abnormal target library is updated; if not, the false target is entered into the abnormal target library.

[0119] The nearest neighbor algorithm is used to match the current target with the targets in the abnormal target library. That is, the abnormal target closest to the current target is found among the targets in the abnormal target library. If the current target matches the target in the abnormal target library, it is a match; if the current target does not match the target in the abnormal target library, it is a mismatch.

[0120] During the application phase, the micro-Doppler map of the unknown target is first acquired and then input into the false alarm identification model for classification, resulting in the unknown target's category. If the unknown target is classified as a false target, it is filtered out to prevent false targets from influencing subsequent decision-making, ensuring that only true targets are displayed by the terminal or that true and false targets are clearly identified.

[0121] If a target is determined to be a false target during a classification, the area where the target is located is determined to be an abnormal target area. Because abnormal targets may not persist during the tracking process, special management of targets that exhibit abnormal behavior throughout the entire false alarm identification and filtering process is required to ensure that such targets can quickly respond to the false alarm identification and filtering process. Abnormal target management primarily involves creating abnormal target information, associating and updating abnormal target information, and so on. Abnormal target information association and updating involves updating the target in the abnormal target library based on the false target information when a false target matches a target in the abnormal target library. Abnormal target information creation involves creating a new target in the abnormal target library based on the false target information when a false target does not match any target in the abnormal target library. Abnormal target management persistently stores information such as the false target's location and target echo data.

[0122] When extracting micro-Doppler features, if the length of the echo signal of the unknown target point does not reach the set threshold and the current target matches a target in the abnormal target library, the echo signal of the target in the abnormal target library is directly used to extract the micro-Doppler features.

[0123] Targets identified as abnormal are not necessarily false alarms. This can occur in at least two situations: first, the model may misjudge difficult-to-distinguish targets; second, false alarms may dominate the abnormal target area at a certain moment, but later, a true target may appear. In both cases, a single or limited number of detections cannot be used to assume that a target appearing in the abnormal target area is a false alarm. Therefore, repeated detections are performed, ultimately determining the most frequent target category as the true target. Abnormal target management ensures that false targets can be quickly identified even after tracking is interrupted.

[0124] The micro-Doppler effect refers to the frequency shift in radar echoes caused by the varying speeds of different parts of a target. This shift can provide information about the target's physical properties. Deep learning algorithms can automatically extract features from a large number of samples. Leveraging the learning capabilities of multi-layer neural networks, they can more accurately distinguish between human targets and false targets. Combining micro-Doppler features with deep learning algorithms can more accurately distinguish real and false targets in complex backgrounds, thereby reducing false alarm rates.

[0125] In today's increasingly complex electromagnetic environment, radar systems face a variety of man-made and natural interference. Leveraging micro-Doppler signatures, radar systems can identify the true attributes of a target by analyzing specific frequency variations, even in the presence of interference. After deep learning network model training, these interference signals can be effectively identified and filtered out, further enhancing system robustness.

[0126] The working environment of radars in different application scenarios varies greatly, and deep learning methods have strong generalization capabilities, that is, they can adapt to new environmental changes by adjusting model parameters. Micro-Doppler features show different characteristics for different types of targets (such as pedestrians, vehicles, drones, etc.), which makes cross-scenario applications possible. The deep learning framework optimized by the input layer can achieve fast response while ensuring accuracy; micro-Doppler processing usually involves efficient algorithms such as fast Fourier change, which is suitable for real-time processing of large amounts of data. Therefore, combining these two technologies can achieve real-time monitoring of dynamic environments while maintaining high accuracy. In summary, the present invention significantly improves the working efficiency and reliability of the radar system by improving detection accuracy, enhancing anti-interference capability, improving adaptability, and maintaining good real-time performance.

[0127] Example 3

[0128] An embodiment of the present application also provides an electronic device, which includes: a memory, a processor, and a computer program / instructions stored in the memory, and the processor executes the computer program / instructions to implement the false alarm identification modeling method in Example 1 of the present application or the false alarm identification method in Example 2 of the present application.

[0129] Although not shown, the electronic device includes a processor that can perform various appropriate operations and processes based on programs and / or data stored in a read-only memory (ROM) or programs and / or data loaded from a storage portion into a random access memory (RAM). The processor can be a multi-core processor or can include multiple processors. In some embodiments, the processor can include a general-purpose main processor and one or more special coprocessors, such as a central processing unit, a graphics processing unit (GPU), a neural network processor (NPU), a digital signal processor (DSP), etc. Various programs and data required for device operation are also stored in RAM. The processor, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0130] The processor and memory are used together to execute the program / instructions stored in the memory. When the program / instructions are executed by the computer, the methods, steps or functions described in the above embodiments can be implemented.

[0131] Although not shown, the embodiment of the present application further provides a computer-readable storage medium having a computer program / instruction stored thereon, which, when executed by a processor, implements the false alarm identification modeling method in embodiment 1 of the present application or the false alarm identification method in embodiment 2 of the present application.

[0132] Computer-readable storage media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0133] Although not shown, the embodiment of the present application further provides a computer program product, including: a computer program / instruction, which, when executed by a processor, implements the false alarm identification modeling method in Example 1 of the present application or the false alarm identification method in Example 2 of the present application.

[0134] The above disclosure is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field can easily think of changes or modifications within the technical scope disclosed in the present invention, and they should all be covered by the scope of protection of the present invention.

Claims

1. A false alarm identification modeling method, characterized in that: The modeling method comprises: Acquire target trajectory data; wherein the target trajectory data includes target point information at different times, and the target point information includes the distance unit and the azimuth unit where the target is located; Obtain radar echo signals and guidance vectors after clutter suppression; Extracting the target point echo signal according to the target point information, the radar echo signal after clutter suppression, and the guidance vector; When the length of the target point echo signal reaches a set threshold, performing micro-Doppler feature extraction on the target point echo signal to obtain a micro-Doppler map; Annotating the micro-Doppler image and constructing a sample data set based on the micro-Doppler image and its annotations; A deep learning network model is constructed, and the deep learning network model is trained and tested using the sample data set to obtain a false alarm recognition model.

2. The false alarm identification modeling method according to claim 1, wherein: Before extracting the target point echo signal, the modeling method further includes performing a sliding average process on the target point information. The specific processing formula is: Among them, N A and P A They represent the distance unit and azimuth unit of the target after sliding average processing, round() represents the rounding function, K represents the size of the sliding average window, and N i and P i They represent the distance unit and azimuth unit of the target at the i-th moment before sliding average processing.

3. The false alarm identification modeling method according to claim 1, wherein: Extracting the target point echo signal according to the target point information, the radar echo signal after clutter suppression, and the guidance vector specifically includes: Extract the Nth A The echo signal of the range unit is extracted from the guidance vector. A Steering vector of each azimuth unit; According to the Nth A The echo signal of the first distance unit and the A The target point echo signal is calculated based on the guidance vector of each azimuth unit. The specific calculation formula is: I(N A ,P A )=X N θ p ; Among them, X N Indicates the Nth A The echo signal of the range unit, θ p Indicates the P A The steering vector of the azimuth unit, I(N A ,P A ) represents the Nth A The distance unit is in the P A The signal strength of each azimuth unit, N A and P A Respectively represent the distance unit and azimuth unit where the target is located.

4. The false alarm identification modeling method according to claim 1, wherein When the length of the target point echo signal reaches a set threshold, before extracting the micro-Doppler feature of the target point echo signal, the modeling method further includes correcting the target point echo signal, specifically including: Performing first-order difference processing on the target point echo signal to obtain the difference between the data before and after each moment; The one-dimensional constant false alarm rate method is used to detect the difference between the data before and after each moment to obtain the discontinuity point; Calculating the amplitude and phase difference of the data before and after each discontinuity point, and using the amplitude and phase difference as the correction weight of the discontinuity point; According to the correction weight, the data after the discontinuous point is weighted point by point to obtain a corrected target point echo signal.

5. The false alarm identification modeling method according to claim 1, wherein: Short-time Fourier transform is used to extract micro-Doppler features of the target point echo signal.

6. The false alarm identification modeling method according to any one of claims 1 to 5, characterized in that: The deep learning network model uses the MobileNetV3 model, and the MobileNetV3 model is built based on the pytorch deep learning framework, and the number of channels of the input layer of the MobileNetV3 model is changed to 1.

7. A false alarm identification method, characterized in that: The identification method comprises: Calling a false alarm recognition model; wherein the false alarm recognition model is constructed according to the false alarm recognition modeling method according to any one of claims 1 to 6; A micro-Doppler map of an unknown target is obtained, and false alarm identification is performed on the micro-Doppler map of the unknown target using the false alarm identification model.

8. The false alarm identification method according to claim 7, characterized in that: Obtain micro-Doppler images of unknown targets, including: Acquire unknown target trajectory data; wherein the unknown target trajectory data includes unknown target point information at different times, and the unknown target point information includes the distance unit and the azimuth unit where the unknown target is located; Obtain radar echo signals and guidance vectors after clutter suppression; Extracting the unknown target point echo signal according to the unknown target point information, the radar echo signal after clutter suppression, and the guidance vector; When the length of the unknown target point echo signal reaches a set threshold, micro-Doppler feature extraction is performed on the unknown target point echo signal to obtain a micro-Doppler map of the unknown target.

9. The false alarm identification method according to claim 8, characterized in that: The identification method further includes abnormal target management, which specifically includes: When the length of the unknown target point echo signal does not reach the set threshold, it is determined whether the target corresponding to the unknown target point echo signal matches the target in the abnormal target library. If so, the micro-Doppler feature extraction is performed on the echo signal of the target in the abnormal target library to obtain the micro-Doppler map of the unknown target; if not, the unknown target point echo signal is discarded; When an unknown target is identified as a false target, it is determined whether the false target matches the target in the abnormal target library. If so, the information of the target in the abnormal target library is updated; if not, the false target is entered into the abnormal target library.

10. An electronic device comprising a memory, a processor, and a computer program / instruction stored in the memory, characterized in that: The processor executes the computer program / instruction to implement the false alarm identification modeling method according to any one of claims 1 to 6 or the false alarm identification method according to claims 7 to 9.

11. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instruction is executed by a processor, the false alarm identification modeling method according to any one of claims 1 to 6 or the false alarm identification method according to claims 7 to 9 is implemented.

12. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the false alarm identification modeling method according to any one of claims 1 to 6 or the false alarm identification method according to claims 7 to 9 is implemented.

Images