An in-vehicle target detection method, device and equipment based on ultra-wideband radar and a storage medium

Abstract

The application discloses a kind of based on ultra-wideband radar's in-vehicle target detection method, device, equipment and storage medium.It includes: obtaining the signal pulse response CIR signal data of ultra-wideband radar in preset length;Wherein, the CIR signal data is determined by the reflection signal of the ultra-wideband radar;The CIR signal data includes the data sequence of multiple taps;Respectively on the data sequence of each tap, extraction of breathing feature and / or jitter feature is carried out, and breathing feature and / or jitter feature are obtained;The breathing feature and / or jitter feature are input into target detection model and carried out multi-target detection, and the target category and target occupancy information are output.The in-vehicle target detection method based on ultra-wideband radar provided in the embodiment of the application will extract the breathing feature and / or jitter feature from CIR signal data into target detection model and carry out multi-target detection, to obtain target category and target occupancy information, can improve in-vehicle target detection precision and accuracy.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of target detection technology, and in particular to an in-vehicle target detection method, apparatus, device and storage medium based on ultra-wideband radar. Background Technology

[0002] With the increasing prevalence of automobiles, in-vehicle safety has become a growing concern. Traditional in-vehicle detection methods primarily rely on cameras and sensors, but these methods have certain limitations. For example, cameras perform poorly in low-light or privacy-preserving scenarios and cannot penetrate obstacles such as seats; ordinary sensors struggle to distinguish between different types of targets. Therefore, developing an efficient, accurate, and reliable in-vehicle multi-target detection technology is of great significance. Existing in-vehicle target detection methods suffer from the following problems: ① Low detection accuracy, unable to accurately distinguish between adults, children, and pets. ② Inability to penetrate obstacles such as seats, failing to comprehensively detect the in-vehicle environment. ③ Limited effectiveness in low-light or privacy-preserving scenarios. Summary of the Invention

[0003] This invention provides a method, apparatus, device, and storage medium for in-vehicle target detection based on ultra-wideband radar, which can improve the accuracy and precision of in-vehicle target detection.

[0004] In a first aspect, embodiments of the present invention provide an in-vehicle target detection method based on ultra-wideband radar, comprising: Acquire signal impulse response (CIR) data of an ultra-wideband radar within a preset time period; wherein, the CIR signal data is determined by the reflected signal of the ultra-wideband radar; the CIR signal data includes a data sequence with multiple taps; Respiratory features and / or jitter features are extracted from the data sequences of each tap to obtain respiratory features and / or jitter features; The breathing features and / or shaking features are input into the target detection model for multi-target detection, and the target category and target occupancy information are output.

[0005] Secondly, embodiments of the present invention also provide an in-vehicle target detection device based on ultra-wideband radar, comprising: The CIR signal data acquisition module is used to acquire the signal impulse response (CIR) signal data of the ultra-wideband radar within a preset time period; wherein, the CIR signal data is determined by the reflected signal of the ultra-wideband radar; the CIR signal data includes a data sequence with multiple taps; The feature extraction module is used to extract breathing features and / or jitter features from the data sequence of each tap, and obtain breathing features and / or jitter features. The target detection module is used to input the breathing features and / or shaking features into the target detection model for multi-target detection, and output the target category and target occupancy information.

[0006] Thirdly, embodiments of the present invention also provide an electronic device, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the in-vehicle target detection method based on ultra-wideband radar as described in the embodiments of the present invention.

[0007] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer instructions, which are used to cause a processor to execute the in-vehicle target detection method based on ultra-wideband radar as described in the embodiments of the present invention.

[0008] This invention discloses an in-vehicle target detection method, apparatus, device, and storage medium based on ultra-wideband radar. The method involves acquiring the signal impulse response (CIR) data of the ultra-wideband radar within a preset time period; wherein the CIR signal data is determined by the reflected signal of the ultra-wideband radar; the CIR signal data includes a data sequence with multiple taps; breathing features and / or jitter features are extracted from the data sequence of each tap to obtain breathing features and / or jitter features; the breathing features and / or jitter features are input into a target detection model for multi-target detection, outputting target category and target occupancy information. The in-vehicle target detection method based on ultra-wideband radar provided by this invention inputs the breathing features and / or jitter features extracted from the CIR signal data into a target detection model for multi-target detection to obtain target category and target occupancy information, which can improve the accuracy and precision of in-vehicle target detection, while simultaneously alerting the driver or triggering corresponding vehicle safety functions. Attached Figure Description

[0009] Figure 1 This is a flowchart of an in-vehicle target detection method based on ultra-wideband radar according to Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of the structure of an in-vehicle target detection device based on ultra-wideband radar in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device according to Embodiment 3 of the present invention. Detailed Implementation

[0010] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0011] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0012] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0013] Example 1 Figure 1 This is a flowchart of an in-vehicle target detection method based on ultra-wideband radar according to Embodiment 1 of the present invention. This embodiment is applicable to situations where the category and occupancy information of in-vehicle targets need to be detected. The method can be executed by an in-vehicle target detection device based on ultra-wideband radar. This device can be implemented in software and / or hardware, optionally through an electronic device, such as a mobile terminal, PC, or server. Specifically, it includes the following steps: S110: Acquire the signal impulse response (CIR) signal data of the ultra-wideband radar within a preset time period.

[0014] The CIR signal data is determined by the reflected signal from the ultra-wideband radar; the CIR signal data includes a multi-tap data sequence. In this embodiment, the ultra-wideband radar (UWB) is installed on the front lighting device inside the vehicle, for example, above the front reading lights, with a signal frequency range of 3.1 GHz to 10.6 GHz, and can be configured with one transmitting antenna and two receiving antennas. Living objects inside the vehicle (such as adults, children, pets, etc.) will reflect the signal. After the radar receives the reflected signal, it is processed internally by the chip to obtain the Channel Impulse Response (CIR) signal data.

[0015] In this application scenario, CIR signal data from two radar antennas are acquired every 50ms. Each radar antenna's CIR data contains data from 16 taps, with each tap corresponding to a distance resolution of 15cm, meaning a detection range of 2.4m, covering both the front and rear seats of the vehicle. The preset duration can be pre-set. For example, assuming a preset duration of 10s, the acquired CIR signal data will be a 200×16 matrix, with each tap's data being a vector of length 200, where each element is a complex number containing both real and imaginary parts.

[0016] S120, extract breathing features and / or jitter features from the data sequences of each tap to obtain breathing features and / or jitter features.

[0017] Among them, the respiratory characteristics can be represented by the ratio of the sum of the energy spectrum corresponding to the respiratory frequency to the sum of the energy spectrum corresponding to the non-respiratory frequency, and the jitter characteristics can be represented by the standard deviation of the amplitude of the CIR signal data.

[0018] Optionally, breathing features and / or jitter features can be extracted from the data sequences of each tap. The breathing features and / or jitter features can be obtained by: determining the amplitude of each CIR signal data in the data sequence of each tap to obtain the amplitude sequence of each tap; and extracting breathing features and / or jitter features from the amplitude sequence of each tap to obtain the breathing features and / or jitter features.

[0019] The amplitude is obtained by performing a modulo operation on the CIR signal data. The specific process of performing a modulo operation on the CIR signal data can be as follows: sum the squares of the real and imaginary parts of the CIR signal data and then take the square root.

[0020] Specifically, the method for extracting respiratory features from the amplitude sequences of each tap can be as follows: For the amplitude sequences of each tap, perform a Fourier transform on the amplitude sequences to obtain a spectral sequence; determine the sum of the first spectral energy corresponding to the respiratory frequency and the sum of the second spectral energy corresponding to the non-respiratory frequency based on the spectral sequence; and determine the ratio of the sum of the first spectral energy to the sum of the second spectral energy as the respiratory feature.

[0021] The spectral sequence consists of spectral energy. A Fourier transform of the amplitude sequence can be performed by applying a 256-point Fourier transform (FFT). Respiratory frequency can be understood as the frequency range corresponding to human breathing; non-respiratory frequencies can be understood as frequencies outside the frequency range corresponding to human breathing.

[0022] In this application scenario, a person's respiratory rate is between 0.3 and 0.6 Hz, corresponding to f = 1.3-3.8. The process of determining the sum of the first spectral energies corresponding to the respiratory rate can be as follows: first, extract multiple spectral energies corresponding to the respiratory rate from the spectral sequence, and then sum these multiple spectral energies to obtain the first spectral energy sum. The process of determining the sum of the second spectral energies corresponding to non-respiratory rates can be as follows: first, extract multiple spectral energies corresponding to non-respiratory rates from the spectral sequence, and then sum these multiple spectral energies to obtain the second spectral energy sum. After obtaining the sum of the first spectral energy and the sum of the second spectral energy, the ratio of the sum of the first spectral energy to the sum of the second spectral energy is determined as the respiratory characteristic.

[0023] In this embodiment, after obtaining the breathing features corresponding to each tap, the breathing features of the 16 taps are combined into a breathing feature vector.

[0024] Specifically, the method for extracting jitter features from the amplitude sequences of each tap can be as follows: for the amplitude sequences of each tap, filter the amplitude sequences; perform differential processing on the filtered amplitude sequences; determine the standard deviation of the differential amplitude sequences, and use the standard deviation as the jitter feature.

[0025] One method for filtering the amplitude sequence is to apply a moving average filter. Another method for differentiating the filtered amplitude sequence is to calculate the first difference. A larger standard deviation indicates greater jitter, suggesting the target is performing a large-amplitude movement; a smaller standard deviation indicates less jitter, suggesting the target is relatively still.

[0026] In this embodiment, after obtaining the jitter features corresponding to each tap, the jitter features of the 16 taps are combined into a jitter feature vector.

[0027] S130: Input breathing features and / or shaking features into the target detection model for multi-target detection, and output target category and target occupancy information.

[0028] The object detection model is pre-trained and can be a Convolutional Neural Network (CNN) model based on an attention mechanism. This model includes multiple convolutional layers, pooling layers, and fully connected layers. The convolutional kernels are 3×3, and the pooling layers use max pooling with a 2×2 window size. Target categories can include adults, children, or pets; occupancy information can include: front passenger seat, rear right seat, rear middle seat, and rear left seat.

[0029] Specifically, the method of inputting breathing features and / or shaking features into the target detection model for multi-target detection can be as follows: input breathing feature vectors and / or shaking feature vectors into the target detection model for multi-target detection to obtain target category and target occupancy information.

[0030] The calculation formula for the attention module can be expressed as: Where X is the input feature, W1 and W2 are weight matrices, and b1 and b2 are bias terms. Activation function. In this embodiment, the input breathing feature vector and / or tremor feature vector are forward-propagated in the target detection model to obtain the model's output. The Softmax function is used to convert the output into a probability distribution: , z i Let C be the score for the i-th category output by the model, and C be the total number of categories (adult, child, pet). The category with the highest probability is selected as the target category.

[0031] In this embodiment, targets are classified into adults, children, or pets based on the probability distribution output by the target detection model. The number of detected targets is counted to generate a liveness distribution map inside the vehicle. The detection results are output to the vehicle's intelligent system to alert the driver or trigger safety functions.

[0032] Optionally, the target detection model can be trained as follows: acquire CIR signal sample data; the CIR signal sample data includes sample data sequences from multiple taps; extract respiratory features and / or jitter features from the sample data sequences of each tap to obtain respiratory sample features and / or jitter sample features; the target detection model performs multi-target detection and outputs target category probability and occupancy information probability; and trains the target detection model based on the target category probability, occupancy information probability, true target category, and true occupancy information.

[0033] The CIR signal sample data carries the true target category and true occupancy information. The CIR signal sample data can be obtained by processing the reflected signal from an ultra-wideband radar installed on the front row lighting device inside the vehicle. The method for extracting breathing and / or jitter features from the sample data sequences of each tap is similar to the method for extracting breathing and / or jitter features from the data sequences of each tap in the above embodiments, and will not be repeated here.

[0034] One method for training the target detection model based on the target category probability, the occupant information probability, the true target category, and the true occupant information is as follows: First, determine the loss function based on the target category probability, the occupant information probability, the true target category, and the true occupant information. Then, backpropagate the loss function in the target detection model to tune the parameters, thereby training the target detection model.

[0035] The loss function can be the cross-entropy loss function, which can be expressed as: Where M is the sample size, y i For real labels, p i This represents the probability predicted by the model.

[0036] The technical solution of this embodiment acquires the signal impulse response (CIR) signal data of an ultra-wideband radar within a preset time period. The CIR signal data is determined by the reflected signal of the ultra-wideband radar. The CIR signal data includes a data sequence with multiple taps. Breathing and / or jitter features are extracted from the data sequence of each tap to obtain breathing and / or jitter features. The breathing and / or jitter features are input into a target detection model for multi-target detection, outputting target category and target occupancy information. The in-vehicle target detection method based on ultra-wideband radar provided by this embodiment of the invention inputs the breathing and / or jitter features extracted from the CIR signal data into a target detection model for multi-target detection to obtain target category and target occupancy information. This can improve the accuracy and precision of in-vehicle target detection, while simultaneously alerting the driver or triggering corresponding vehicle safety functions.

[0037] Example 2 Figure 2 This is a schematic diagram of the structure of an in-vehicle target detection device based on ultra-wideband radar provided in Embodiment 2 of the present invention, as shown below. Figure 2 As shown, the device includes: CIR signal data acquisition module 210 is used to acquire signal impulse response (CIR) signal data of ultra-wideband radar within a preset time period; wherein, the CIR signal data is determined by the reflected signal of ultra-wideband radar; the CIR signal data includes a data sequence of multi-tap. The feature extraction module 220 is used to extract breathing features and / or jitter features from the data sequence of each tap, and obtain breathing features and / or jitter features. The target detection module 230 is used to input breathing features and / or shaking features into the target detection model for multi-target detection and output target category and target occupancy information.

[0038] Optionally, the feature extraction module 220 is also used for: Determine the amplitude of each CIR signal data in the data sequence of each tap to obtain the amplitude sequence of each tap; where the amplitude is obtained by performing a modulo operation on the CIR signal data; Breathing features and / or jitter features are extracted from the amplitude sequence of each tap to obtain breathing features and / or jitter features.

[0039] Optionally, the feature extraction module 220 is also used for: For the amplitude sequence of each tap, perform a Fourier transform on the amplitude sequence to obtain the spectrum sequence; The sum of the first spectral energy corresponding to the respiratory frequency and the sum of the second spectral energy corresponding to the non-respiratory frequency are determined based on the spectral sequence. The ratio of the sum of the first spectral energy to the sum of the second spectral energy is determined as the respiratory characteristic.

[0040] Optionally, the feature extraction module 220 is also used for: For the amplitude sequence of each tap, the amplitude sequence is filtered; The filtered amplitude sequence is then subjected to differential processing. Determine the standard deviation of the amplitude sequence after differential processing, and use the standard deviation as a jitter feature.

[0041] Optionally, the object detection model includes multiple convolutional layers, pooling layers, and fully connected layers.

[0042] Optionally, it also includes: an object detection model training module, used for: Acquire CIR signal sample data; wherein, the CIR signal sample data carries the true target category and true occupancy information; the CIR signal sample data includes a multi-tap sample data sequence; Respiratory features and / or jitter features are extracted from the sample data sequences of each tap to obtain respiratory sample features and / or jitter sample features; the target detection model performs multi-target detection and outputs the target category probability and the occupancy information probability. The target detection model is trained based on the target category probability, the occupant information probability, the true target category, and the true occupant information.

[0043] Optionally, the ultra-wideband radar can be mounted on the front interior lighting unit.

[0044] The above-described apparatus can execute the methods provided in all the foregoing embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the above methods. Technical details not described in detail in this embodiment can be found in the methods provided in all the foregoing embodiments of the present invention.

[0045] Example 3 Figure 3 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components, connections and relationships between components, and their functions shown herein are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0046] like Figure 3 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0047] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0048] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as an in-vehicle target detection method based on ultra-wideband radar.

[0049] In some embodiments, the in-vehicle target detection method based on ultra-wideband radar can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the in-vehicle target detection method based on ultra-wideband radar described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the in-vehicle target detection method based on ultra-wideband radar by any other suitable means (e.g., by means of firmware).

[0050] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0051] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0052] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0053] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0054] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0055] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0056] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the in-vehicle target detection method based on ultra-wideband radar as provided in any embodiment of this application.

[0057] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0058] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0059] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for in-vehicle target detection based on ultra-wideband radar, characterized in that, include: Acquire signal impulse response (CIR) data of an ultra-wideband radar within a preset time period; wherein, the CIR signal data is determined by the reflected signal of the ultra-wideband radar; the CIR signal data includes a data sequence with multiple taps; Respiratory features and / or jitter features are extracted from the data sequences of each tap to obtain respiratory features and / or jitter features; The breathing features and / or shaking features are input into the target detection model for multi-target detection, and the target category and target occupancy information are output.

2. The method according to claim 1, characterized in that, Respiratory features and / or jitter features are extracted from the data sequences of each tap to obtain respiratory features and / or jitter features, including: The amplitude of each CIR signal data in the data sequence of each tap is determined to obtain the amplitude sequence of each tap; wherein the amplitude is obtained by performing a modulo operation on the CIR signal data; Breathing features and / or jitter features are extracted from the amplitude sequence of each tap to obtain breathing features and / or jitter features.

3. The method according to claim 2, characterized in that, Respiratory features are extracted from the amplitude sequences of each tap, including: For the amplitude sequence of each tap, perform a Fourier transform on the amplitude sequence to obtain the spectrum sequence; Based on the spectral sequence, determine the sum of the first spectral energy corresponding to the respiratory frequency and the sum of the second spectral energy corresponding to the non-respiratory frequency; The ratio of the sum of the first spectral energies to the sum of the second spectral energies is determined as the respiratory characteristic.

4. The method according to claim 2, characterized in that, Jitter features are extracted from the amplitude sequences of each tap, including: For the amplitude sequence of each tap, the amplitude sequence is filtered; The filtered amplitude sequence is then subjected to differential processing. Determine the standard deviation of the amplitude sequence after differential processing, and use the standard deviation as a jitter feature.

5. The method according to claim 1, characterized in that, The target detection model includes multiple convolutional layers, pooling layers, and fully connected layers.

6. The method according to claim 1, characterized in that, The training method for the object detection model is as follows: Acquire CIR signal sample data; wherein, the CIR signal sample data carries the true target category and true occupancy information; the CIR signal sample data includes a multi-tap sample data sequence; Respiratory features and / or jitter features are extracted from the sample data sequences of each tap to obtain respiratory sample features and / or jitter sample features; the target detection model performs multi-target detection and outputs the target category probability and the occupancy information probability. The target detection model is trained based on the target category probability, the occupant information probability, the true target category, and the true occupant information.

7. The method according to claim 1, characterized in that, The ultra-wideband radar is mounted on the front lighting unit inside the vehicle.

8. An in-vehicle target detection device based on ultra-wideband radar, characterized in that, include: The CIR signal data acquisition module is used to acquire the signal impulse response (CIR) signal data of the ultra-wideband radar within a preset time period; wherein, the CIR signal data is determined by the reflected signal of the ultra-wideband radar; the CIR signal data includes a data sequence with multiple taps; The feature extraction module is used to extract breathing features and / or jitter features from the data sequence of each tap, and obtain breathing features and / or jitter features. The target detection module is used to input the breathing features and / or shaking features into the target detection model for multi-target detection, and output the target category and target occupancy information.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the in-vehicle target detection method based on ultra-wideband radar as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the in-vehicle target detection method based on ultra-wideband radar as described in any one of claims 1-7.

Images