A data processing method and device for intelligent vehicle target recognition

Abstract

This invention provides a data processing method and apparatus for intelligent vehicle target recognition. The method includes: acquiring data to be processed, which consists of pre-stored, measured driving data from both a primary vehicle and a target vehicle; aligning the spatiotemporal data of the primary vehicle and the target vehicle in time and space to obtain aligned data, which is used to determine the relative position between the primary and target vehicles. Since the data read is pre-stored, measured driving data, real-time communication between the primary and target vehicles is not required. This method of acquiring data first and then processing it solves the problem of test distance limitations during driving tests and eliminates the need to install real-time communication equipment on both vehicles, thus reducing costs.

Description

Technical Field

[0001] This invention relates to the field of target recognition for intelligent vehicles, and more particularly to a data processing method and apparatus for target recognition in intelligent vehicles. Background Technology

[0002] The perception system of an intelligent vehicle (the host vehicle) needs to accurately identify the target (the target vehicle) and determine the driving strategy to be adopted based on information such as the target's speed, position, and distance. The functionality and performance of an intelligent vehicle are highly dependent on the perception system; therefore, accurately testing the target recognition accuracy is crucial during the development of the perception system.

[0003] Currently, the industry has specialized equipment for similar measurements, such as the RT-RANGE integrated navigation equipment produced by OXTS, which is widely used in the development and testing of driver assistance systems. This type of system mainly consists of a positioning system and a communication system. The positioning system is an inertial navigation system composed of GPS and an IMU unit, with one set installed in each of the main vehicle and the target vehicle. It is used to measure the absolute position, speed, acceleration, attitude, and other information of both vehicles. GPS, or Global Positioning System, does not require the user to send any data and operates independently of any telephone or internet data receiving method. IMU, or Inertial Measurement Unit, is a sensor mainly used to detect and measure acceleration and rotational motion. The communication system is also installed in both the main vehicle and the target vehicle, with each vehicle designated as a master station and slave station. Communication between the master and slave stations is conducted wirelessly point-to-point. The communication system is connected to the corresponding measurement system to acquire measurement data. The slave station transmits the measurement data to the master station via wireless communication. The master station then calculates the relative distance, speed, and position of the master vehicle and the target vehicle, and stores the various types of data locally or sends them to the host computer for storage.

[0004] The aforementioned traditional technical solutions have the following drawbacks:

[0005] 1. Insufficient testing distance. The point-to-point wireless communication between the host vehicle and the target vehicle requires high data bandwidth, thus typically employing a 2.4GHz high-frequency communication scheme similar to WiFi. This communication method has a short operating distance; in unobstructed conditions, the signal begins to attenuate significantly beyond 200 meters, and beyond 300 meters, signal loss and stuttering are common. Therefore, the testing distance is very limited and cannot meet the needs of long-distance testing.

[0006] 2. Complex installation and configuration. The measurement system has high requirements for installation location and fixing method. The measurement system needs to be connected to the communication system, and both the measurement system and the communication system have their own antennas, which need to be fixed to the outside of the vehicle body. The measurement system and communication system on the main vehicle and the target vehicle need to be configured separately, and the setup is cumbersome and complex, thus requiring a high level of technical expertise from the installers.

[0007] 3. High cost. Traditional solutions involve equipment with many components and require specialized software, resulting in very high overall costs. The purchase price is generally around two million RMB, which is unaffordable for most companies. Summary of the Invention

[0008] To address the problems in the prior art, embodiments of the present invention provide a data processing method and apparatus for target recognition in intelligent vehicles.

[0009] Specifically, the embodiments of the present invention provide the following technical solutions:

[0010] In a first aspect, embodiments of the present invention provide a data processing method for intelligent vehicle target recognition, comprising: acquiring data to be processed, wherein the data to be processed is driving data that has been measured and pre-stored in advance by a master vehicle and a target vehicle, the data to be processed including spatiotemporal data of the master vehicle and spatiotemporal data of the target vehicle; aligning the spatiotemporal data of the master vehicle and the spatiotemporal data of the target vehicle in time and space to obtain aligned data, wherein the aligned data is used to determine information on the relative position between the master vehicle and the target vehicle.

[0011] Furthermore, the spatiotemporal data of the main vehicle includes first data and corresponding first time data. The first data includes data determined by fusing the IMU measurement value and the satellite positioning system measurement value of the main vehicle, as well as at least one UTC time received by the main vehicle. The first time data is a timestamp corresponding to the first data, determined by the power-on time of the main vehicle. The spatiotemporal data of the target vehicle includes second data and corresponding second time data. The second data includes data determined by fusing the IMU measurement value and the satellite positioning system measurement value of the target vehicle, as well as at least one UTC time received by the target vehicle. The second time data is a timestamp corresponding to the second data, determined by the power-on time of the target vehicle. Wherein, the IMU measurement value represents the inertial measurement unit measurement value, and the UTC time represents Universal Time.

[0012] Furthermore, the spatiotemporal data of the main vehicle and the spatiotemporal data of the target vehicle are aligned in time and space to obtain aligned data. This includes: storing the first data and the corresponding first time data in a first array, and storing the second data and the corresponding second time data in a second array; determining the target time axis, and converting the first array and the second array onto the target time axis and performing linear interpolation to obtain the aligned first array and the second array. The aligned first array and the second array are used to verify the deviation of the data generated by the main vehicle and the target vehicle during the driving measurement process, so as to accurately measure the accuracy of target recognition.

[0013] Further, determining the target time axis includes: selecting the first UTC time received among at least one UTC time received by the main vehicle as the starting UTC time of the main vehicle, and selecting the first UTC time received among at least one UTC time received by the target vehicle as the starting UTC time of the target vehicle; comparing the starting UTC time of the main vehicle and the starting UTC time of the target vehicle to determine the earlier starting UTC time; determining the difference between the UTC time of the main vehicle and the target vehicle and the earlier starting UTC time, respectively, and determining the origin of the target time axis based on the difference.

[0014] Further, the step of converting the first array and the second array onto the target time axis includes: determining a first UTC time corresponding to the first data based on the first time data and at least one UTC time received by the main vehicle; determining a second UTC time corresponding to the second data based on the second time data and at least one UTC time of the target vehicle; and subtracting the first UTC time and the second UTC time from the earlier starting UTC time to convert the first / second data onto the target time axis.

[0015] Furthermore, the method also includes converting the aligned IMU and GPS measurements of the master vehicle / target vehicle into data in a planar coordinate system to determine the relative position information between the master vehicle and the target vehicle.

[0016] Secondly, embodiments of the present invention also provide a data processing device for intelligent vehicle target recognition, comprising: a first processing module for acquiring data to be processed, wherein the data to be processed is driving data that has been measured and pre-stored by a host vehicle and a target vehicle, respectively, and the data to be processed includes spatiotemporal data of the host vehicle and spatiotemporal data of the target vehicle; and a second processing module for aligning the spatiotemporal data of the host vehicle and the spatiotemporal data of the target vehicle in time and space to obtain aligned data, wherein the aligned data is used to determine information on the relative position between the host vehicle and the target vehicle.

[0017] Thirdly, embodiments of the present invention also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the data processing method for intelligent vehicle target recognition as described in the first aspect.

[0018] Fourthly, embodiments of the present invention also provide a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the data processing method for intelligent vehicle target recognition as described in the first aspect.

[0019] Fifthly, embodiments of the present invention also provide a computer program product having executable instructions stored thereon, which, when executed by a processor, cause the processor to implement the steps of the data processing method for intelligent vehicle target recognition described in the first aspect.

[0020] This invention provides a data processing method and apparatus for intelligent vehicle target recognition. The invention acquires data to be processed, which consists of pre-stored, measured driving data from both the host vehicle and the target vehicle. This data includes spatiotemporal data of both the host vehicle and the target vehicle. The spatiotemporal data of the host vehicle and the target vehicle are aligned in time and space to obtain aligned data. This aligned data is used to determine the relative position between the host vehicle and the target vehicle. Since the data read is pre-stored, measured driving data, real-time communication between the host vehicle and the target vehicle is not required. This method of acquiring data first and then processing it solves the problem of test distance limitations during driving tests and eliminates the need to install real-time communication equipment on both vehicles, thus reducing costs. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating an embodiment of a data processing method for target recognition in intelligent vehicles according to the present invention;

[0023] Figure 2 This is a schematic diagram of the measurement system structure;

[0024] Figure 3 A flowchart illustrating an application scenario for data processing in intelligent vehicle target recognition;

[0025] Figure 4 This is a schematic diagram of an embodiment of a data processing device for target recognition in intelligent vehicles according to the present invention;

[0026] Figure 5 This is a schematic diagram of the structure of a physical embodiment of the electronic device of the present invention. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] Figure 1 This is a flowchart illustrating an embodiment of a data processing method for target recognition in intelligent vehicles according to the present invention. Figure 1 As shown, the method of this embodiment of the invention includes:

[0029] S101, acquire data to be processed. The data to be processed is the driving data that has been measured and pre-stored in the master vehicle and the target vehicle. The data to be processed includes the spatiotemporal data of the master vehicle and the spatiotemporal data of the target vehicle.

[0030] As an example, before acquiring the data to be processed, only a measurement system needs to be installed on both the host vehicle and the target vehicle; a communication system is not required. The measurement system includes: a power supply, a GPS (Global Positioning System) antenna, a GPS receiver, an IMU (Inertial Measurement Unit), a data processing unit, and a data storage unit. See [link to relevant documentation]. Figure 2 Compared to traditional measurement driving methods, this method only requires installing a measurement system, improving testing efficiency and simplifying operation. It also avoids problems such as short measurement distances and unstable data communication caused by limitations in wireless communication capabilities, making the measurement process unrestricted by distance. Since it does not rely on a wireless communication system, the hardware is significantly simplified, making system installation and configuration easier, resulting in substantial cost reductions and a significant decrease in the technical skill requirements for operators.

[0031] The power supply is responsible for providing power to the GPS receiver, IMU, data processing unit, and data storage unit. Since it is mainly used in vehicles, an external power supply voltage of 9-36V is preferred.

[0032] The GPS antenna is mounted on the vehicle roof, requiring unobstructed access and freedom from strong electromagnetic interference. Its primary function is to receive satellite positioning signals. The GPS antenna connects to a GPS receiver, which analyzes the received signals to determine the absolute position, speed, and other positioning results. Preferably, a positioning receiver that supports BeiDou, GPS, and GLONASS is used. To obtain more accurate positioning information, a satellite receiver supporting network RTK is employed, ensuring an absolute satellite positioning accuracy of ±2cm even in open areas.

[0033] The IMU measures the vehicle's three-axis acceleration and three-axis angular velocity to obtain the vehicle's attitude information, i.e., the IMU's measurements. The IMU is mounted on the vehicle's centerline, and its X-axis and Y-axis should be aligned with and perpendicular to the vehicle's direction of travel, respectively. Once correctly installed, the IMU must be securely fixed to ensure that it does not move or rotate relative to the vehicle body during the entire measurement driving process.

[0034] During the measurement and driving process of the main vehicle and the target vehicle, the measurement values ​​from their respective IMUs and the positioning results received by the GPS receiver are sent to their respective data processing units in real time. The data processing units process the data to be processed, and the data storage unit records the processed data. To ensure higher storage speed and data integrity, binary format is preferably used to store the data. The recorded data to be processed includes, but is not limited to, latitude and longitude, positioning status, GPS week / second time, speed, acceleration, attitude angle, system time, etc. Preferably, the data recording frequency is 100Hz.

[0035] After the measurement drive is completed, the data to be processed is read from the data storage units of the master vehicle and the target vehicle for analysis and processing. Since it does not rely on real-time communication between the two vehicles during the measurement drive, the measurement distance is not limited by communication, enabling accurate measurement over ultra-long distances and solving the problem of excessively short measurement distances in traditional solutions.

[0036] Spatiotemporal data includes information such as the absolute position and speed of the main vehicle or target vehicle, as well as the system time corresponding to the absolute position and speed information.

[0037] S102, the spatiotemporal data of the main vehicle and the spatiotemporal data of the target vehicle are aligned in time and space to obtain aligned data, which is used to determine the relative position information between the main vehicle and the target vehicle.

[0038] Because the power-on times of the measurement systems of the master vehicle and the target vehicle may differ, and the timestamps of the spatiotemporal data are determined based on the power-on times of the measurement systems, there will be temporal discrepancies in the spatiotemporal data recorded by each. For example, the master vehicle's measurement system may power on first and record the spatiotemporal data at the first moment, while the target vehicle's measurement system may power on later and also record the spatiotemporal data at the first moment. However, the master vehicle's first moment will be earlier than the target vehicle's first moment. Therefore, it is necessary to align the spatiotemporal data of the master vehicle and the target vehicle in both time and space.

[0039] As an example, the spatiotemporal data of the target vehicle can be mapped onto the timeline of the main vehicle, taking the timeline of the main vehicle as the reference, thus aligning the spatiotemporal data of the main vehicle and the target vehicle and converting the data to the same time dimension.

[0040] Since the primary vehicle (or target vehicle) may not have recorded spatial data at the same time, spatial alignment of the data is also required. As an example, if the primary vehicle (or target vehicle) does not record spatial data at a certain moment, the data for both the primary and target vehicles at that moment is deleted. If both the primary vehicle (or target vehicle) has recorded spatial data at a certain moment, the data for that moment is retained as the spatial alignment data.

[0041] The spatiotemporally aligned data includes information such as the absolute position and speed of the main vehicle and the target vehicle at the same moment. Based on this information, the data of the main vehicle and the target vehicle can be processed very easily. For example, the data can be transformed into the same spatiotemporal dimension to accurately calculate the relative position information between the two vehicles. The relative position information includes, but is not limited to, the relative distance, speed, and position between the main vehicle and the target vehicle, which makes it easier to judge the accuracy of target recognition.

[0042] As an example, the steps of a data processing method for target recognition in intelligent vehicles are as follows: Figure 3 As shown. After reading the data to be processed, the data is time-aligned, interpolated, and transformed before numerical calculations are performed. The calculation results are then saved to determine the measurement data between the master vehicle and the target vehicle. By independently collecting data from the master vehicle and the target vehicle and post-processing the collected data, spatiotemporal synchronization of the two vehicle data is achieved, thereby obtaining information such as distance, relative speed, and relative position of the two vehicles during the test. Because it does not rely on a wireless communication system, the system composition is greatly simplified, it is easy to use, the cost is significantly reduced, and it can support long-distance measurement, even if the distance between the two vehicles exceeds 1km, it can still measure relatively accurately.

[0043] This invention provides a data processing method for intelligent vehicle target recognition. The method involves acquiring data to be processed, which consists of pre-stored, measured driving data from both the host vehicle and the target vehicle. This data includes spatiotemporal data of both the host and target vehicles. The spatiotemporal data of the host and target vehicles are then aligned in time and space to obtain aligned data. This aligned data is used to determine the relative position between the host and target vehicles. Since the data read is pre-stored, measured driving data, real-time communication between the host and target vehicles is not required. This method of acquiring data first and then processing it solves the problem of test distance limitations during driving tests and eliminates the need to install real-time communication equipment on both vehicles, thus reducing costs.

[0044] In one implementation, the spatiotemporal data of the main vehicle includes first data and corresponding first time data. The first data includes data determined by fusing the IMU measurement value and the satellite positioning system measurement value of the main vehicle, as well as at least one UTC time received by the main vehicle. The first time data is a timestamp corresponding to the first data, determined by the power-on time of the main vehicle. The spatiotemporal data of the target vehicle includes second data and corresponding second time data. The second data includes data determined by fusing the IMU measurement value and the satellite positioning system measurement value of the target vehicle, as well as at least one UTC time received by the target vehicle. The second time data is a timestamp corresponding to the second data, determined by the power-on time of the target vehicle. Wherein, the IMU measurement value represents the inertial measurement unit measurement value, and the UTC time represents Universal Time.

[0045] As an example, the satellite positioning system can be a GPS positioning system, where the measurements represent those of the Global Positioning System. While satellite positioning (i.e., GPS positioning) can obtain absolute position, it is highly susceptible to signal interference and has a relatively low positioning frequency, generally not exceeding 20Hz. IMU positioning does not rely on external signals and has a very high positioning output frequency, thus possessing very strong anti-interference capabilities. However, because accumulated errors cannot be avoided, IMU positioning errors gradually amplify over time. Therefore, after the host vehicle (or target vehicle) sends the IMU measurements and the positioning results received by the GPS receiver (i.e., GPS measurements) to its data processing unit in real time, the data processing unit can combine the advantages and disadvantages of these two positioning methods and employ a specific fusion algorithm to calculate a high-precision, high-stability positioning result. This positioning result is the first (or second) data determined by fusing the IMU and GPS measurements. Preferably, the positioning fusion algorithm employs a loosely coupled extended Kalman filter algorithm.

[0046] UTC stands for Coordinated Universal Time, also known as World Standard Time or Coordinated International Time. It is a time measurement system based on atomic second lengths, designed to be as close as possible to Universal Time in terms of timing. Since the UTC time of the main vehicle / target vehicle records the week and second time of GPS, which begins at 00:00:00 on January 1, 1970, and is broadcast by satellite, the week and second times in both sets of data originate from the same source. To facilitate calculations between the two sets of data, UTC week and second time can be used as a time axis, converting all data onto this time axis to achieve time synchronization.

[0047] In another embodiment, the spatiotemporal data of the main vehicle and the spatiotemporal data of the target vehicle are aligned in time and space to obtain aligned data. This includes: storing the first data and the corresponding first time data in a first array, and storing the second data and the corresponding second time data in a second array; determining the target time axis, and converting the first array and the second array onto the target time axis and performing linear interpolation to obtain the aligned first array and the second array. The aligned first array and the second array are used to verify the deviation of the data generated by the main vehicle and the target vehicle during the driving measurement process, so as to accurately measure the accuracy of target recognition.

[0048] The first / second data and their corresponding timestamps (i.e., first / second time data) are stored in the corresponding first / second array variables. The timestamp of the data is the time when the main vehicle / target vehicle is powered on, and this time starts counting from 0 o'clock as the equipment is powered on. Since the main vehicle and the target vehicle cannot be guaranteed to be powered on at the same time, the timestamps of the two sets of data have different starting points and are not comparable. Therefore, the target time axis must be determined first, and the first and second arrays are respectively converted to the target time axis to align the data times in the first and second arrays.

[0049] After aligning the data of the master vehicle and the target vehicle in time, a problem remains: the master vehicle records the first data at a certain moment, but the target vehicle does not record the second data at the same moment. Therefore, although the first and second data are time-aligned, the second data is missing, and the first and second data at the same moment cannot be compared. Therefore, to enable comparison and calculation of data at the same moment, linear interpolation can be used to process the time-aligned data of the master vehicle and the target vehicle separately, i.e., spatial alignment. Preferably, interpolation is performed at a time interval of 0.01s to ensure that the data time is aligned after interpolation, and the frequency is 100Hz. Assume the data to be interpolated is data y at time T′, and the corresponding data points before and after time T′ are y(i) and y(i+1), with corresponding aligned timestamps as follows:

[0050] t(i) and t(i+1), then

[0051]

[0052] y(T′) is the calculated value of the data y at time T′.

[0053] By aligning the spatiotemporal data of the main vehicle and the target vehicle in both time and space, the data collected by the main vehicle and the target vehicle are synchronized in time and space. This allows two independent data sources to be compared and calculated in the same coordinate dimension, thereby obtaining accurate information such as the relative distance, speed, and position of the two vehicles, which can then be compared with the recognition results of the perception system.

[0054] In some optional implementations, determining the target time axis includes: selecting the first UTC time received among at least one UTC time received by the master vehicle as the starting UTC time of the master vehicle, and selecting the first UTC time received among at least one UTC time received by the target vehicle as the starting UTC time of the target vehicle; comparing the starting UTC time of the master vehicle and the starting UTC time of the target vehicle to determine the earlier starting UTC time; determining the difference between the UTC time of the master vehicle and the target vehicle and the earlier starting UTC time respectively, and determining the origin of the target time axis based on the difference.

[0055] Since the data frequencies of different signals may vary, and the corresponding vehicle power-on timestamps may also have slight differences, an interpolation algorithm is needed to unify the data timestamps to ensure convenient analysis and calculation. In some embodiments, the UTC start time of the set with the earlier start time among the two sets of data is taken as the earlier UTC time and denoted as t_offset. The UTC times of the two sets of data are denoted as t_UTC. Then, the target time axis is T = t_UTC - t_offset. As an example, the start time of the main vehicle's UTC time is less than the start time of the target vehicle's UTC time. Therefore, the start time of the main vehicle's UTC time is denoted as t_offset. Then, the difference between the main vehicle's UTC time and the target vehicle's UTC time is calculated and t_offset is used to determine the target time axis.

[0056] In some optional implementations, the first array and the second array are respectively converted to the target time axis, including: determining the first UTC time corresponding to the first data based on the first time data and at least one UTC time received by the master vehicle; determining the second UTC time corresponding to the second data based on the second time data and at least one UTC time of the target vehicle; and subtracting the first UTC time and the second UTC time from the earlier starting UTC time to convert the first / second data to the target time axis.

[0057] As an example, the first array is [v1, v2, UTC3, UTC4], and the corresponding first time data is [t1, t2, t3, t4]. Here, v1 is the speed of the main vehicle monitored by the main vehicle at time t1, v2 is the speed of the main vehicle monitored by the main vehicle at time t2, UTC3 is the UTC time received by the main vehicle at time t3, and UTC4 is the UTC time received by the main vehicle at time t4. If there is a 1-second difference between t1, t2, t3, and t4, then UTC1 is the earlier starting UTC time. Since there is a 1-second difference between t1, t2, t3, and t4, UTC3 and UTC4 also differ by 1 second. Therefore, (UTC3-1) seconds is the main vehicle UTC time corresponding to v2, and (UTC3-2) seconds is the main vehicle UTC time corresponding to v1. Thus, [(UTC3-2), (UTC3-1)] is the first UTC time corresponding to the first data. Similarly, the second UTC time corresponding to the second data can be obtained. By subtracting the first UTC time from the earlier starting UTC time, we can obtain the times of v1 and v2 on the target timeline, i.e., v1 and v2 correspond to (UTC3-2-t_offset) and (UTC3-1-t_offset) respectively. Similarly, by subtracting the second UTC time from the earlier starting UTC time, we can obtain the time of the first data on the target timeline. Translating to the target timeline completes the data time alignment.

[0058] In some alternative implementations, the method further includes converting the aligned IMU and GPS measurements of the master vehicle / target vehicle into data in a planar coordinate system to determine the relative position between the master vehicle and the target vehicle.

[0059] The aligned IMU and GPS measurements of the master vehicle and target vehicle are then converted from latitude and longitude to planar coordinates using coordinate transformation. Preferably, the latitude and longitude of the IMU and GPS measurements are transformed to the UTM coordinate system. After coordinate transformation, the data of the master vehicle and target vehicle are aligned in time and space, allowing for subsequent numerical calculations. For example, calculating relative distance and speed: assuming the master vehicle's coordinates are (x, y) and speed is (vx, vy), and the target vehicle's coordinates are (x′, y′) and speed is (vx′, vy′), then:

[0060] Relative distance between the two vehicles

[0061] Relative speed of the two vehicles

[0062] Figure 4 This is a schematic diagram of an embodiment of a data processing device for target recognition in intelligent vehicles according to the present invention. Figure 4 As shown, the device includes:

[0063] The first processing module 401 is used to acquire data to be processed. The data to be processed is the driving data that has been measured and pre-stored in the master vehicle and the target vehicle. The data to be processed includes the spatiotemporal data of the master vehicle and the spatiotemporal data of the target vehicle.

[0064] The second processing module 402 is used to align the spatiotemporal data of the main vehicle and the spatiotemporal data of the target vehicle in time and space to obtain aligned data. The aligned data is used to determine the relative position information between the main vehicle and the target vehicle.

[0065] Optionally, the spatiotemporal data of the main vehicle includes first data and corresponding first time data. The first data includes data determined by fusing the IMU measurement value and the satellite positioning system measurement value of the main vehicle, as well as at least one UTC time received by the main vehicle. The first time data is a timestamp corresponding to the first data, determined by the power-on time of the main vehicle. The spatiotemporal data of the target vehicle includes second data and corresponding second time data. The second data includes data determined by fusing the IMU measurement value and the satellite positioning system measurement value of the target vehicle, as well as at least one UTC time received by the target vehicle. The second time data is a timestamp corresponding to the second data, determined by the power-on time of the target vehicle. Wherein, the IMU measurement value represents the measurement value of the inertial measurement unit, and the UTC time represents the Universal Time.

[0066] Optionally, the second processing module 402 is further configured to: store the first data and the corresponding first time data in a first array, store the second data and the corresponding second time data in a second array; determine a target time axis, convert the first array and the second array onto the target time axis respectively and perform linear interpolation processing to obtain an aligned first array and second array, wherein the aligned first array and second array are used to verify the deviation of the data generated by the main vehicle and the target vehicle during the measurement driving process, so as to accurately measure the accuracy of target recognition.

[0067] Optionally, the second processing module 402 is further configured to: select the first UTC time received from at least one UTC time received by the main vehicle as the starting UTC time of the main vehicle, and select the first UTC time received from at least one UTC time received by the target vehicle as the starting UTC time of the target vehicle; compare the starting UTC time of the main vehicle and the starting UTC time of the target vehicle to determine the earlier starting UTC time; determine the difference between the UTC time of the main vehicle and the target vehicle and the earlier starting UTC time respectively, and determine the origin of the target time axis based on the difference.

[0068] Optionally, the second processing module 402 is further configured to: determine a first UTC time corresponding to the first data based on the first time data and at least one UTC time received by the master vehicle; determine a second UTC time corresponding to the second data based on the second time data and at least one UTC time of the target vehicle; and subtract the first UTC time and the second UTC time from the earlier starting UTC time respectively to convert the first / second data onto the target time axis.

[0069] Optionally, the device further includes a third processing module for converting the aligned IMU and GPS measurements of the master vehicle / target vehicle into data in a planar coordinate system to determine the relative position information between the master vehicle and the target vehicle.

[0070] For example:

[0071] Figure 5 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 5 The electronic device may include a processor 510, a communications interface 520, a memory 530, and a communication bus 540. The processor 510, communications interface 520, and memory 530 communicate with each other via the communication bus 540. The processor 510 can call logical instructions in the memory 530 to execute the following methods: acquiring data to be processed, which is pre-stored, measured driving data of the main vehicle and the target vehicle, including spatiotemporal data of the main vehicle and the target vehicle; aligning the spatiotemporal data of the main vehicle and the target vehicle in time and space to obtain aligned data, which is used to determine the relative position information between the main vehicle and the target vehicle.

[0072] Furthermore, the logical instructions in the aforementioned memory 530 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0073] On the other hand, embodiments of the present invention also provide a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, and when the program instructions are executed by the computer, the computer can execute a data processing method for intelligent vehicle target recognition provided in the above embodiments, for example including: acquiring data to be processed, the data to be processed being driving data that has been measured and pre-stored in advance by the main vehicle and the target vehicle, the data to be processed including the spatiotemporal data of the main vehicle and the spatiotemporal data of the target vehicle; aligning the spatiotemporal data of the main vehicle and the spatiotemporal data of the target vehicle in time and space to obtain aligned data, the aligned data being used to determine the relative position information between the main vehicle and the target vehicle.

[0074] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program is implemented to perform a data processing method for intelligent vehicle target recognition provided in the above embodiments. For example, it includes: acquiring data to be processed, which is driving data that has been measured and pre-stored by the main vehicle and the target vehicle, respectively. The data to be processed includes the spatiotemporal data of the main vehicle and the spatiotemporal data of the target vehicle; aligning the spatiotemporal data of the main vehicle and the spatiotemporal data of the target vehicle in time and space to obtain aligned data, which is used to determine the relative position information between the main vehicle and the target vehicle.

[0075] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0076] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0077] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A data processing method for intelligent vehicle target recognition, characterized in that, Applications in intelligent driving testing include: Acquire data to be processed, which is the driving data of the master vehicle and the target vehicle that have been pre-stored and measured. It does not rely on the real-time communication between the master vehicle and the target vehicle during the measurement driving and does not require a communication system. The data to be processed includes the spatiotemporal data of the master vehicle and the spatiotemporal data of the target vehicle. The spatiotemporal data of the main vehicle includes first data and corresponding first time data. The first data includes data determined by fusing the IMU measurement value of the main vehicle and the measurement value of the satellite positioning system of the main vehicle, as well as at least one UTC time received by the main vehicle. The first time data is the timestamp corresponding to the first data, which is determined by the power-on time of the main vehicle. The spatiotemporal data of the target vehicle includes second data and corresponding second time data. The second data includes data determined by fusing the IMU measurement value of the target vehicle and the measurement value of the target vehicle's satellite positioning system, as well as at least one UTC time received by the target vehicle. The second time data is a timestamp corresponding to the second data, determined by the power-on time of the target vehicle. After aligning the spatiotemporal data of the main vehicle and the target vehicle in time, spatial alignment is performed using interpolation to obtain aligned data. This aligned data is used to determine the relative position between the main vehicle and the target vehicle, including: Store the first data and its corresponding first time data in the first array, and store the second data and its corresponding second time data in the second array; A target time axis is determined, and the first array and the second array are respectively converted onto the target time axis and linear interpolation is performed to obtain the aligned first array and the second array. The aligned first array and the second array are used to verify the deviation of the data generated by the main vehicle and the target vehicle during the driving measurement, so as to accurately measure the accuracy of target recognition.

2. The data processing method for intelligent vehicle target recognition according to claim 1, characterized in that, The IMU measurement value represents the inertial measurement unit measurement value, and the UTC time represents the Universal Time.

3. The data processing method for intelligent vehicle target recognition according to claim 1, characterized in that, The determination of the target timeline includes: The first UTC time received by the master vehicle is selected from at least one UTC time received by the master vehicle as the starting UTC time of the master vehicle, and the first UTC time received by the target vehicle is selected from at least one UTC time received by the target vehicle as the starting UTC time of the target vehicle. Compare the starting UTC time of the master vehicle with the starting UTC time of the target vehicle, and determine the earlier starting UTC time; The difference between the UTC time of the main vehicle and the target vehicle and the earlier starting UTC time is determined, and the origin of the target time axis is determined based on the difference.

4. The data processing method for intelligent vehicle target recognition according to claim 3, characterized in that, The step of respectively projecting the first array and the second array onto the target time axis includes: Based on the first time data and at least one UTC time received by the master vehicle, determine the first UTC time corresponding to the first data; based on the second time data and at least one UTC time of the target vehicle, determine the second UTC time corresponding to the second data. The first UTC time and the second UTC time are subtracted from the earlier starting UTC time, respectively, to convert the first / second data onto the target time axis.

5. The data processing method for intelligent vehicle target recognition according to claim 1, characterized in that, The method further includes: The aligned IMU and GPS measurements of the host vehicle and target vehicle are converted into data in a plane coordinate system to determine the relative position between the host vehicle and the target vehicle.

6. A data processing device for target recognition in intelligent vehicles, characterized in that, Applications in intelligent driving testing include: The first processing module is used to acquire data to be processed. The data to be processed is the driving data of the main vehicle and the target vehicle that have been pre-stored and measured. It does not rely on the real-time communication between the main vehicle and the target vehicle during the measurement driving and does not require a communication system. The data to be processed includes the spatiotemporal data of the main vehicle and the spatiotemporal data of the target vehicle. The spatiotemporal data of the main vehicle includes first data and corresponding first time data. The first data includes data determined by fusing the IMU measurement value of the main vehicle and the measurement value of the satellite positioning system of the main vehicle, as well as at least one UTC time received by the main vehicle. The first time data is the timestamp corresponding to the first data, which is determined by the power-on time of the main vehicle. The spatiotemporal data of the target vehicle includes second data and corresponding second time data. The second data includes data determined by fusing the IMU measurement value of the target vehicle and the measurement value of the target vehicle's satellite positioning system, as well as at least one UTC time received by the target vehicle. The second time data is a timestamp corresponding to the second data, determined by the power-on time of the target vehicle. The second processing module is used to align the spatiotemporal data of the main vehicle and the target vehicle in time, and then align them in space using interpolation to obtain aligned data. This aligned data is used to determine the relative position information between the main vehicle and the target vehicle, including: Store the first data and its corresponding first time data in the first array, and store the second data and its corresponding second time data in the second array; A target time axis is determined, and the first array and the second array are respectively converted onto the target time axis and linear interpolation is performed to obtain the aligned first array and the second array. The aligned first array and the second array are used to verify the deviation of the data generated by the main vehicle and the target vehicle during the driving measurement, so as to accurately measure the accuracy of target recognition.

7. An electronic device, characterized in that, include: Processor, memory, and bus, among which, The processor and the memory communicate with each other via the bus; The memory stores program instructions that can be executed by the processor, which can invoke the program instructions to perform the steps of the data processing method for intelligent vehicle target recognition as described in any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer instructions that cause the computer to perform the steps of the data processing method for intelligent vehicle target recognition as described in any one of claims 1 to 5.

9. A computer program product, the computer program product comprising computer-executable instructions, characterized in that, When executed, the instructions are used to perform the steps of the data processing method for intelligent vehicle target recognition as described in any one of claims 1 to 5.

Images