Vehicle data processing method, vehicle, electronic equipment and storage medium

Abstract

The invention provides a vehicle data processing method, a vehicle, electronic equipment and a storage medium, and the method comprises the steps: obtaining a sensing signal of the vehicle, the sensing signal being a signal sensed by the vehicle in an intelligent driving process, and the sensing signal being continuous in a preset time period; detecting a distribution characteristic of the sensing signal in a preset time period, and determining a noise type of the sensing signal according to the distribution characteristic; performing linear interpolation processing on the sensing signal under the condition that the noise type is determined to be a first type of noise signal and the sensing signal has a first frame loss signal in a preset time period; and under the condition that the noise type is determined to be a second type noise signal and the sensing signal has a second frame loss signal in a preset time period, performing linear interpolation processing on the sensing signal, and performing noise reduction processing on the sensing signal after the linear interpolation processing. According to the invention, the processing efficiency of the vehicle data can be improved while the precision of the vehicle data is ensured.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and in particular, to a vehicle data processing method, a vehicle, an electronic device, and a storage medium. Background Art

[0002] With the development of autonomous driving technology, it has become very important to predict the future trajectories of surrounding vehicles and other traffic participants. As the upper layer of the autonomous driving system and also the input for subsequent links such as decision-making, planning, and control, accurately predicting the intentions of potential interaction objects is the key to improving the overall performance of the algorithm. For trajectory prediction, many research teams and scholars have proposed some very classic algorithms and models, and all of them have high prediction accuracy from their respective results. However, most of the current research conclusions are based on ideal prediction inputs, which usually come from some public datasets, such as HighD, NGSIM, and nuSences, etc. These datasets have undergone careful data cleaning and can be directly used as ground truth. Therefore, using these data to train the prediction algorithm model can achieve very high accuracy.

[0003] However, when the prediction algorithm model faces the actual perception data input of the vehicle, due to measurement errors in the vehicle sensors themselves and noise and interference in the real environment, the perception data of the vehicle is inaccurate, which in turn leads to the deterioration of the performance of the prediction algorithm model and even makes it unusable. Summary of the Invention

[0004] In view of this, this application provides a vehicle data processing method, a vehicle, an electronic device, and a storage medium, which can improve the processing efficiency of vehicle data while ensuring the accuracy of vehicle data.

[0005] An embodiment of this application provides a vehicle data processing method, including: obtaining a perception signal of the vehicle, where the perception signal is a signal sensed by the vehicle during the process of intelligent driving, and the perception signal is continuous in a preset time period; detecting the distribution characteristics of the perception signal in the preset time period, and determining the noise category of the perception signal according to the distribution characteristics; when it is determined that the noise category is the first type of noise signal and there is a first dropped frame signal in the perception signal in the preset time period, performing linear interpolation processing on the perception signal to fill the first dropped frame signal; when it is determined that the noise category is the second type of noise signal and there is a second dropped frame signal in the perception signal in the preset time period, performing linear interpolation processing on the perception signal to fill the second dropped frame signal, and performing noise reduction processing on the perception signal after linear interpolation processing; where the noise of the second type of noise signal is higher than the noise of the first type of noise signal.

[0006] Compared with the related art, the embodiments of the present application have at least the following advantages: By detecting the distribution characteristics of the sensing signal over a preset time period, it is possible to determine whether the sensing signal is a high-noise signal or a low-noise signal based on the distribution characteristics. When it is determined that the sensing signal is a first type of noise signal, that is, a low-noise signal, linear interpolation processing is directly performed on the sensing signal with a first frame loss signal within the preset time period to fill the first frame loss signal lost by the sensing signal, improving the data processing efficiency; when it is determined that the sensing signal is a second type of noise signal, that is, a high-noise signal, linear interpolation processing is first performed on the sensing signal with a second frame loss signal within the preset time period to fill the second frame loss signal lost by the sensing signal, and then noise reduction processing is performed on the sensing signal after the linear interpolation processing, so that while ensuring the accuracy of the sensing data, the processing efficiency of the sensing data can be improved.

[0007] In some possible implementation manners, the detecting the distribution characteristics of the sensing signal over the preset time period includes: sampling the sensing signal at a preset sampling frequency to obtain N sampling signals, where N is an integer greater than 1; calculating the mean of the N sampling signals, and calculating the standard deviation of the N sampling signals according to the mean, and taking the standard deviation as the distribution characteristics.

[0008] In some possible implementation manners, the determining the noise category of the sensing signal according to the distribution characteristics includes: comparing three times the standard deviation with a preset threshold; in the case where three times the standard deviation is less than or equal to the preset threshold, determining that the noise category is the first type of noise signal; in the case where three times the standard deviation is greater than the preset threshold, determining that the noise category is the second type of noise signal.

[0009] In some possible implementation manners, the N sampling signals are arranged in the order of the time when the vehicle senses them, and the first dropped frame signal is the missing sampling signal among the N sampling signals; wherein, the first dropped frame signal divides the N sampling signals into a first segment signal and a second segment signal, the time when the vehicle senses the first segment signal is before the time when the vehicle senses the first dropped frame signal, and the time when the vehicle senses the second segment signal is after the time when the vehicle senses the first dropped frame signal; the linear interpolation processing of the sensing signal includes: determining the last P first sampling signals in the first segment signal and the first Q second sampling signals at the beginning of the second segment signal, where both P and Q are integers greater than 1; calculating a first mean value of the P first sampling signals and a second mean value of the Q second sampling signals; calculating the first dropped frame signal according to the first mean value, the second mean value and the preset sampling frequency; and inserting the first dropped frame signal between the first segment signal and the second segment signal.

[0010] In some possible implementation manners, the calculating the first dropped frame signal according to the first mean value, the second mean value and the preset sampling frequency includes: calculating the difference between the second mean value and the first mean value; dividing the difference by the preset sampling frequency and then subtracting 1 to obtain the total number of the first dropped frame signals; and calculating the value of each first dropped frame signal according to the first mean value, the second mean value and the total number of the first dropped frame signals.

[0011] In some possible implementation manners, the noise reduction processing of the sensing signal after the linear interpolation processing includes: dividing the preset time period into multiple sub-time periods according to a preset sliding step; respectively calculating a third mean value of the sampling signals in each sub-time period, and obtaining the sensing signal after the noise reduction processing according to the third mean value.

[0012] In some possible implementation manners, before detecting the distribution characteristic of the sensing signal on the preset time period, the method further includes: detecting whether there is a lane line signal in the sensing signal; and in the case of detecting that there is a lane line signal in the sensing signal, detecting whether the lane line is abnormal according to the lane line signal; the detecting the distribution characteristic of the sensing signal on the preset time period includes: in the case that there is a lane line signal in the sensing signal and the lane line is detected to be normal according to the lane line signal, detecting the distribution characteristic of the sensing signal on the preset time period.

[0013] The second aspect of the present application discloses a vehicle, including: an acquisition module, a detection module, a determination module, a first processing module, and a second processing module; the acquisition module is configured to acquire the perception signal of the vehicle, where the perception signal is the signal sensed by the vehicle during the process of intelligent driving, and the perception signal is continuous over a preset time period; the detection module is configured to detect the distribution characteristics of the perception signal over the preset time period; the determination module is configured to determine the noise category of the perception signal according to the distribution characteristics; the first processing module is configured to perform linear interpolation processing on the perception signal when the determination module determines that the noise category is the first type of noise signal and there is a first dropped frame signal in the perception signal within the preset time period, so as to fill the first dropped frame signal; the second processing module is configured to perform linear interpolation processing on the perception signal when the determination module determines that the noise category is the second type of noise signal and there is a second dropped frame signal in the perception signal within the preset time period, so as to fill the second dropped frame signal, and perform noise reduction processing on the perception signal after the linear interpolation processing; where the noise of the second type of noise signal is higher than the noise of the first type of noise signal.

[0014] The third aspect of the present application discloses an electronic device, which includes a processor and a memory. The memory is used to store instructions, and the processor is used to call the instructions in the memory, so that the electronic device executes the above vehicle data processing method.

[0015] The fourth aspect of the present application discloses a storage medium, including computer instructions, which, when running on an electronic device, cause the electronic device to execute the above vehicle data processing method.

[0016] It can be understood that the vehicle in the second aspect, the electronic device in the third aspect, and the storage medium in the fourth aspect provided above all correspond to the method in the first aspect. Therefore, the beneficial effects they can achieve can refer to the beneficial effects in the corresponding method provided above, and will not be elaborated here. Description of the Drawings

[0017] Figure 1 is a flowchart of a vehicle data processing method provided by an embodiment of the present application.

[0018] Figure 2 is a relationship diagram of the sensing time and value of a sampling signal provided by an embodiment of the present application.

[0019] Figure 3 is a relationship diagram of the sensing time and value of a sampling signal after interpolation processing provided by an embodiment of the present application.

[0020] Figure 4It is a flowchart of a vehicle data processing method provided by an embodiment of the present application.

[0021] Figure 5 It is a schematic diagram of the functional modules of a vehicle provided by an embodiment of the present application.

[0022] Figure 6 It is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0023] In order to be able to more clearly understand the above-mentioned objects, features, and advantages of the present application, the present application will be described in detail below in conjunction with the accompanying drawings and specific implementation manners. It should be noted that, without conflict, the implementation manners of the present application and the features in the implementation manners can be combined with each other.

[0024] In the following description, many specific details are set forth in order to fully understand the present application. The described implementation manners are only a part of the implementation manners of the present application, rather than all of the implementation manners.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs. The terms used in the description of the present application in this specification are only for the purpose of describing specific implementation manners, and are not intended to limit the present application.

[0026] Furthermore, it should be noted that in this article, the term "including", "comprising", or any other variant thereof is intended to cover a non-exclusive inclusion, such that a process, method, article, or device including a series of elements not only includes those elements but also includes other elements that are not explicitly listed, or further includes elements inherent to such a process, method, article, or device. Without further limitation, an element defined by the phrase "including a..." does not exclude the existence of additional identical elements in the process, method, article, or device including that element.

[0027] In the present application, "at least one" means one or more, and "a plurality" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B can be singular or plural. The terms "first", "second", "third", "fourth", etc. (if any) in the description, claims, and drawings of the present application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0028] In the embodiments of the present application, words such as "exemplary" or "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or more advantageous than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present relevant concepts in a specific manner.

[0029] Please refer to Figure 1 , which is a flowchart of the vehicle data processing method provided by the embodiments of the present application. This embodiment is applied to a vehicle and includes the following steps: Step 101: Obtain the perception signal of the vehicle, where the perception signal is the signal sensed by the vehicle during the process of intelligent driving, and the perception signal is continuous over a preset time period.

[0030] In some embodiments, intelligent driving includes, but is not limited to, autonomous driving, semi-autonomous driving, etc. of the vehicle.

[0031] In some embodiments, the perception signal is the signal sensed by the sensors installed on the vehicle during the process of intelligent driving. Specifically, the perception signal includes information such as the positions, speeds, accelerations, etc. of the host vehicle and surrounding vehicles. It can be understood that as long as it is an autonomous driving perception signal that is continuous in time, it is the perception signal of this embodiment.

[0032] Step 102: Detect the distribution characteristics of the perception signal over a preset time period, and determine the noise category of the perception signal according to the distribution characteristics.

[0033] In some embodiments, the distribution characteristics of the perception signal over a preset time period are detected in the following manner: sampling the perception signal at a preset sampling frequency to obtain N sampling signals, where N is an integer greater than 1; calculating the mean of the N sampling signals, and calculating the standard deviation of the N sampling signals according to the mean, and taking the standard deviation as the distribution characteristics.

[0034] Specifically, the mean of the N sampling signals is calculated according to the following formula: ; where is the mean, is the i-th sampled sampling signal.

[0035] The standard deviation of the N sampling signals is calculated according to the following formula: ; where is the standard deviation. It should be noted that the standard deviation can reflect the degree of dispersion of the distribution of the N sampling signals of the perception signal. Therefore, the distribution characteristics of the perception signal over a preset time period can be characterized by the standard deviation.

[0036] In some embodiments, determining the noise category of the sensing signal according to the distribution characteristics includes: comparing three times the standard deviation with a preset threshold; when three times the standard deviation is less than or equal to the preset threshold, determining that the noise category is the first type of noise signal; when three times the standard deviation is greater than the preset threshold, determining that the noise category is the second type of noise signal.

[0037] Specifically, according to the three - standard - deviation criterion, for a sample, approximately 99.74% of the data will be evenly distributed within the ( ) interval. Therefore, in this embodiment, by defining a preset threshold , for different sensing signals, if , then the sensing signal is considered a low - noise signal; otherwise, it is a high - noise signal.

[0038] In this embodiment, the size of the preset threshold is not specifically limited and can be set according to actual requirements.

[0039] Step 103: When it is determined that the noise category is the first type of noise signal and there is a first frame - loss signal in the sensing signal within a preset time period, perform linear interpolation processing on the sensing signal to fill the first frame - loss signal.

[0040] Specifically, N sampling signals are arranged in the order of the time when the vehicle senses them. The first frame - loss signal is the missing sampling signal among the N sampling signals. Among them, the first frame - loss signal divides the N sampling signals into a first - segment signal and a second - segment signal. The time when the vehicle senses the first - segment signal is all before the time when the vehicle senses the first frame - loss signal, and the time when the vehicle senses the second - segment signal is all after the time when the vehicle senses the first frame - loss signal.

[0041] In some embodiments, performing linear interpolation processing on the sensing signal includes: determining the last P first sampling signals in the first - segment signal and the first Q second sampling signals at the beginning of the second - segment signal, where both P and Q are integers greater than 1; calculating the first mean of the P first sampling signals and the second mean of the Q second sampling signals; calculating the first frame - loss signal according to the first mean, the second mean, and the preset sampling frequency; inserting the first frame - loss signal between the first - segment signal and the second - segment signal. In this way, to a certain extent, it is possible to avoid the problem of inaccurate interpolation results caused by large random noise when selecting endpoints in the conventional method.

[0042] In some embodiments, calculating the first dropped frame signal according to the first mean value, the second mean value, and the preset sampling frequency includes: calculating the difference between the second mean value and the first mean value; dividing the difference by the preset sampling frequency and then subtracting 1 to obtain the total number of the first dropped frame signals; calculating the value of each of the first dropped frame signals according to the first mean value, the second mean value, and the total number of the first dropped frame signals.

[0043] For ease of understanding, the following specifically describes how to perform linear interpolation processing on the sensing signal in this embodiment with reference to Figure 2 : Please refer to Figure 2 , which is a relationship diagram of the sensing time and value of the sampling signal provided by the embodiment of the present application. As can be seen from Figure 2 , the values of P and Q are both 3, is the set of the last 3 sampling signals of the first segment signal, is the set of the first three sampling signals of the second segment signal. Assuming that the calculated first mean value is 20, the second mean value is 30, and the preset sampling frequency is 2S, then the sampling interval value is (30 - 20) / 2 - 1 = 4, so the total number of the first dropped frame signals can be obtained as 4. Taking 20 as the starting endpoint value and 30 as the ending endpoint value, the values of the first dropped frame signals can be obtained as 22, 24, 26, and 28.

[0044] Step 104: When it is determined that the noise category is the second type of noise signal and there is a second dropped frame signal in the sensing signal within the preset time period, perform linear interpolation processing on the sensing signal to fill the second dropped frame signal, and perform noise reduction processing on the sensing signal after the linear interpolation processing; wherein, the noise of the second type of noise signal is higher than the noise of the first type of noise signal.

[0045] It can be understood that the manner of performing linear interpolation processing on the sensing signal in this step is the same as that in the previous step for performing linear interpolation processing on the sensing signal. To avoid repetition, it will not be elaborated here.

[0046] In some embodiments, performing noise reduction processing on the sensing signal after the linear interpolation processing includes: dividing the preset time period into multiple sub-time periods according to the preset sliding step; respectively calculating the third mean value of the sampling signals within each sub-time period, and obtaining the sensing signal after the noise reduction processing according to the third mean value.

[0047] For ease of understanding, the following specifically describes how to perform noise reduction processing on the sensing signal in this embodiment with reference to Figure 3 : Please refer to Figure 3, which is a relationship diagram of the sensing time and value of the sampled signal after interpolation processing provided by the embodiment of the present application. By setting a preset sliding step length, it is possible to ensure that the time length within the sliding window remains constant, and the number of sampled signals included in each window is the value obtained by dividing the time length by the preset sampling frequency. As can be seen from Figure 3 , each sub-time period includes three sampled signals. By calculating the third mean value of the three sampled signals and then connecting the lines between each third mean value, a relationship curve of the sensing time and value of the sensing signal is obtained. The value corresponding to each sensing time in this relationship curve is the value of the sensing signal after noise reduction processing.

[0048] It should be noted that for a time-series signal containing random noise, that is, a sensing signal, the moving average method can effectively smooth the sensing signal, has a good noise suppression effect, and can quickly process a large amount of data with high calculation efficiency. However, this method has the problem that it is difficult to select the window size in practical applications. If the window is too small, it cannot effectively suppress noise; if the window is too large, it will cause the loss of signal details and trends. To address the above problems, this embodiment designs a sliding window with a preset sliding step length to ensure that the time length within the window is consistent for sensing signals of different lengths and different sampling frequencies, thereby further improving the accuracy of data processing.

[0049] In some embodiments, when it is determined that the noise category is the second type of noise signal and there is no second frame loss signal in the sensing signal within the preset time period, noise reduction processing is performed on the sensing signal. It can be understood that the noise reduction processing method is the same as the foregoing, and will not be repeated here to avoid redundancy.

[0050] Compared with the related art, the embodiment of the present application has at least the following advantages: By detecting the distribution characteristics of the sensing signal within the preset time period, it is possible to determine whether the sensing signal is a high-noise signal or a low-noise signal based on the distribution characteristics. When it is determined that the sensing signal is the first type of noise signal, that is, a low-noise signal, linear interpolation processing is directly performed on the sensing signal with the first frame loss signal within the preset time period to fill in the missing first frame loss signal of the sensing signal and improve the data processing efficiency; when it is determined that the sensing signal is the second type of noise signal, that is, a high-noise signal, linear interpolation processing is first performed on the sensing signal with the second frame loss signal within the preset time period to fill in the missing second frame loss signal of the sensing signal, and then noise reduction processing is performed on the sensing signal after linear interpolation processing, so as to improve the processing efficiency of the sensing data while ensuring the accuracy of the sensing data.

[0051] Please refer to Figure 4 , Figure 4It is a flowchart of the steps of an embodiment of the vehicle data processing method of this application. According to different requirements, the order of the steps in this flowchart can be changed, and some steps can be omitted. This vehicle data processing method can be applied to the aforementioned vehicle, but is not limited thereto, and the embodiments of this application do not limit this.

[0052] This embodiment is a further improvement of the aforementioned embodiment. The main improvement lies in that: in this embodiment, before detecting the distribution characteristics of the sensing signal over a preset time period, it is also detected whether there is a lane line signal in the sensing signal, and when there is a lane line signal in the sensing signal, it is detected whether the lane line is abnormal according to the lane line signal. In this way, it is possible to avoid processing abnormal sensing signals, improve the reliability of the vehicle data processing method, and further improve the data processing efficiency.

[0053] The specific process of this embodiment is as Figure 4 shown and includes the following steps: Step 201: Obtain the sensing signal of the vehicle, where the sensing signal is the signal sensed by the vehicle during the process of intelligent driving, and the sensing signal is continuous over a preset time period.

[0054] Step 202: Detect whether there is a lane line signal in the sensing signal. If it is detected that there is a lane line in the sensing signal, execute Step 203; otherwise, execute Step 207.

[0055] Step 203: Detect whether the lane line is abnormal according to the lane line signal. If the lane line is abnormal, execute Step 207; otherwise, execute Step 204.

[0056] Step 204: Detect the distribution characteristics of the sensing signal over a preset time period, and determine the noise category of the sensing signal according to the distribution characteristics.

[0057] Step 205: When it is determined that the noise category is the first type of noise signal and there is a first dropped frame signal in the sensing signal within the preset time period, perform linear interpolation processing on the sensing signal to fill the first dropped frame signal.

[0058] Step 206: When it is determined that the noise category is the second type of noise signal and there is a second dropped frame signal in the sensing signal within the preset time period, perform linear interpolation processing on the sensing signal to fill the second dropped frame signal, and perform noise reduction processing on the sensing signal after the linear interpolation processing; where the noise of the second type of noise signal is higher than the noise of the first type of noise signal.

[0059] Step 207: Reject the sensing signal.

[0060] Compared with the related art, the embodiments of the present application have at least the following advantages: By detecting the distribution characteristics of the sensing signal over a preset time period, it is possible to determine whether the sensing signal is a high-noise signal or a low-noise signal based on the distribution characteristics. When it is determined that the sensing signal is a first type of noise signal, that is, a low-noise signal, linear interpolation processing is directly performed on the sensing signal with a first dropped frame signal within the preset time period to fill the first dropped frame signal lost by the sensing signal, improving the data processing efficiency; when it is determined that the sensing signal is a second type of noise signal, that is, a high-noise signal, linear interpolation processing is first performed on the sensing signal with a second dropped frame signal within the preset time period to fill the second dropped frame signal lost by the sensing signal, and then noise reduction processing is performed on the sensing signal after the linear interpolation processing, so that while ensuring the accuracy of the sensing data, the processing efficiency of the sensing data can be improved.

[0061] Please refer to Figure 5 , which is a schematic diagram of the functional modules of the vehicle 50 provided by the embodiments of the present application. The vehicle data 50 includes an acquisition module 501, a detection module 502, a determination module 503, a first processing module 504, and a second processing module 505.

[0062] The acquisition module 501 is used to acquire the sensing signal of the vehicle 50, where the sensing signal is the signal sensed by the vehicle 50 during the process of intelligent driving, and the sensing signal is continuous over a preset time period; the detection module 502 is used to detect the distribution characteristics of the sensing signal over a preset time period; the determination module 503 is used to determine the noise category of the sensing signal according to the distribution characteristics; the first processing module 504 is used to perform linear interpolation processing on the sensing signal when the determination module 503 determines that the noise category is the first type of noise signal and the sensing signal has a first dropped frame signal within the preset time period to fill the first dropped frame signal; the second processing module 505 is used to perform linear interpolation processing on the sensing signal when the determination module 503 determines that the noise category is the second type of noise signal and the sensing signal has a second dropped frame signal within the preset time period to fill the second dropped frame signal, and perform noise reduction processing on the sensing signal after the linear interpolation processing; where the noise of the second type of noise signal is higher than the noise of the first type of noise signal.

[0063] Please refer to Figure 6 , which is a schematic diagram of the hardware structure of the electronic device 1000 provided by the embodiments of the present application. As Figure 6 shown, the electronic device 1000 may include a processor 1001 and a memory 1002. The memory 1002 is used to store one or more computer programs 1003. The one or more computer programs 1003 are configured to be executed by the processor 1001. The one or more computer programs 1003 include instructions, and the above instructions can be used to implement the above vehicle data processing method in the electronic device 1000.

[0064] It can be understood that the structure illustrated in this embodiment does not constitute a specific limitation on the electronic device 1000. In some other embodiments, the electronic device 1000 may include more or fewer components than those shown in the figure, or combine certain components, or split certain components, or have different component arrangements.

[0065] The processor 1001 may include one or more processing units. For example, the processor 1001 may include an application processor (AP), a modem, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Among them, different processing units may be independent devices or integrated in one or more processors.

[0066] The processor 1001 may also be provided with a memory for storing instructions and data. In some embodiments, the memory in the processor 1001 is a cache memory. This memory can save the instructions or data that the processor 1001 has just used or recycled. If the processor 1001 needs to use the instruction or data again, it can be directly called from this memory. This avoids repeated accesses, reduces the waiting time of the processor 1001, and thus improves the efficiency of the system.

[0067] In some embodiments, the processor 1001 may include one or more interfaces. The interfaces may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a SIM interface, and / or a USB interface, etc.

[0068] In some embodiments, the processor 1001 is used to execute acceleration schemes such as single instruction multiple data (SIMD) and very long instruction word (VLIW).

[0069] In some embodiments, the memory 1002 may include high-speed random access memory and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one magnetic disk storage device, flash device, or other volatile solid-state storage devices.

[0070] This embodiment also provides a computer-readable storage medium storing computer instructions that, when run on an electronic device, cause the electronic device to execute the above-related method steps to implement the vehicle data processing method in the above embodiments.

[0071] Among them, the electronic device and computer storage medium provided in this embodiment are both used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, which will not be elaborated here.

[0072] In practical applications, the above functions can be allocated to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0073] In several embodiments provided in this application, the disclosed device and method can be implemented in other ways. For example, the device embodiments described above are illustrative. For example, the division of the module or unit is a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in electrical, mechanical or other forms.

[0074] The unit described as a separated component may or may not be physically separated. The component displayed as a unit may be a physical unit or multiple physical units, that is, it may be located in one place or distributed to multiple different places. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0075] In addition, in each embodiment of the present application, each functional unit can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0076] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiments of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The software product is stored in a storage medium and includes several instructions for causing a device (which can be a single-chip microcomputer, a chip, etc.) or a processor to execute all or part of the steps of the methods described in the embodiments of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0077] As described above, the above are only the specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be covered by the protection scope of the present application.

Claims

1. A vehicle data processing method, characterized in that: include: Acquire a perception signal of the vehicle, wherein the perception signal is a signal sensed by the vehicle during intelligent driving, and the perception signal is continuous over a preset time period; detecting a distribution characteristic of the perception signal in the preset time period, and determining a noise category of the perception signal according to the distribution characteristic; When it is determined that the noise category is a first type of noise signal and the perception signal contains a first frame loss signal within the preset time period, performing linear interpolation processing on the perception signal to fill the first frame loss signal; When it is determined that the noise category is a second type of noise signal and the perception signal contains a second frame loss signal within the preset time period, linear interpolation processing is performed on the perception signal to fill the second frame loss signal, and noise reduction processing is performed on the perception signal after the linear interpolation processing; The noise of the second type of noise signal is higher than the noise of the first type of noise signal.

2. The vehicle data processing method according to claim 1, characterized in that: The detecting the distribution characteristics of the sensing signal in the preset time period includes: Sampling the perception signal at a preset sampling frequency to obtain N sampling signals, where N is an integer greater than 1; The mean of the N sampling signals is calculated, and the standard deviation of the N sampling signals is calculated according to the mean, and the standard deviation is used as the distribution characteristic.

3. The vehicle data processing method according to claim 2, characterized in that: The determining the noise category of the perception signal according to the distribution characteristic includes: Comparing three times of the standard deviation with a preset threshold; When three times of the standard deviation is less than or equal to the preset threshold, determining that the noise category is the first type of noise signal; When three times of the standard deviation is greater than the preset threshold, the noise category is determined to be the second type of noise signal.

4. The vehicle data processing method according to claim 2, characterized in that: The N sampling signals are arranged in the order of time when the vehicle senses them, and the first frame loss signal is a sampling signal missing from the N sampling signals; The first frame loss signal separates the N sampling signals into a first segment signal and a second segment signal, the time when the vehicle senses the first segment signal is before the time when the vehicle senses the first frame loss signal, and the time when the vehicle senses the second segment signal is after the time when the vehicle senses the first frame loss signal; The performing linear interpolation processing on the perception signal comprises: Determine the last P first sampling signals in the first segment of the signal and the first two Q second sampling signals in the second segment of the signal, where P and Q are both integers greater than 1; Calculating first mean values ​​of P of the first sampling signals and second mean values ​​of Q of the second sampling signals; Calculating the first frame loss signal according to the first mean value, the second mean value and the preset sampling frequency; The first frame loss signal is inserted between the first segment signal and the second segment signal.

5. The vehicle data processing method according to claim 4, characterized in that: The calculating the first frame loss signal according to the first mean value, the second mean value and the preset sampling frequency includes: calculating a difference between the second mean and the first mean; Divide the difference by the preset sampling frequency and then subtract 1 to obtain the total number of the first frame loss signals; The value of each of the first frame loss signals is determined according to the first mean value, the second mean value, and the total number of the first frame loss signals.

6. The vehicle data processing method according to claim 2, characterized in that: The performing noise reduction processing on the perception signal after the linear interpolation processing comprises: Dividing the preset time period into a plurality of sub-time periods according to a preset sliding step size; A third mean value of the sampling signal in each of the sub-time periods is calculated respectively, and the perception signal after noise reduction processing is obtained according to the third mean value.

7. The vehicle data processing method according to claim 1, characterized in that: Before detecting the distribution characteristics of the perception signal in the preset time period, the method further includes: Detecting whether there is a lane line signal in the perception signal; In the case where the lane line signal is detected in the perception signal, detecting whether the lane line is abnormal according to the lane line signal; The detecting the distribution characteristics of the sensing signal in the preset time period includes: When the lane line signal exists in the perception signal and there is no abnormality in the lane line detected according to the lane line signal, the distribution characteristics of the perception signal in the preset time period are detected.

8. A vehicle, characterized in that: include: An acquisition module, a detection module, a determination module, a first processing module, and a second processing module; The acquisition module is used to acquire a perception signal of the vehicle, wherein the perception signal is a signal sensed by the vehicle during intelligent driving, and the perception signal is continuous over a preset time period; The detection module is used to detect the distribution characteristics of the sensing signal in the preset time period; The determination module is used to determine the noise category of the perception signal according to the distribution characteristics; The first processing module is used for performing linear interpolation processing on the perception signal to fill the first frame loss signal when the determination module determines that the noise category is a first type of noise signal and the perception signal contains a first frame loss signal in the preset time period; The second processing module is used for performing linear interpolation processing on the perception signal to fill the second frame loss signal, and performing noise reduction processing on the perception signal after the linear interpolation processing, when the determination module determines that the noise category is a second type of noise signal and the perception signal contains a second frame loss signal in the preset time period; The noise of the second type of noise signal is higher than the noise of the first type of noise signal.

9. An electronic device, characterized in that: The electronic device comprises a processor and a memory, wherein the memory is used to store instructions, and the processor is used to call the instructions in the memory, so that the electronic device executes the vehicle data processing method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The method comprises computer instructions, which, when executed on an electronic device, enable the electronic device to execute the vehicle data processing method according to any one of claims 1 to 7.

Images