A target scene classification method and related apparatus

Abstract

The application discloses a target scene classification method and related device, and relates to the field of vehicles.The method comprises the following steps: obtaining a target scene to be classified; determining trajectory point combinations according to vehicle trajectory points in vehicle driving data and obstacle trajectory points in obstacle driving data; determining a vehicle lane sequence corresponding to the vehicle trajectory points in each trajectory point combination, and determining an obstacle lane sequence corresponding to the obstacle trajectory points in each trajectory point combination; and classifying the target scene to be classified according to the vehicle lane sequence and the obstacle lane sequence, to obtain a classification result. The vehicle lane sequence is determined according to the vehicle trajectory points, and the obstacle lane sequence is determined according to the obstacle trajectory points, so that trajectory-related information of the vehicle and the obstacle can be accurately captured. By analyzing the trajectory-related information, the target scene to be classified can be effectively classified, so that the accuracy of the classification result is ensured.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method and related apparatus for classifying target scenarios. Background Technology

[0002] With the development of autonomous driving technology, vehicles need to identify various dynamic targets in the surrounding environment, such as other vehicles, pedestrians, and traffic signs, through dynamic target scene classification.

[0003] Currently, dynamic target scene classification mainly relies on manual annotation. This process requires staff to meticulously review the trajectories of vehicles and dynamic targets, along with their impact data, and classify them according to target type. However, due to the limitations of manual processing, data omissions or gaps often occur, especially when dealing with complex scenes or long-term data sets. It may be impossible to accurately capture the trajectories and related information of all dynamic targets. This not only affects the completeness of the data but also the accuracy of the classification results.

[0004] Therefore, ensuring the accuracy of classification results has become an urgent problem to be solved in this field. Summary of the Invention

[0005] In view of the above problems, this application provides a method and related apparatus for classifying target scenes to ensure the accuracy of classification results. The specific solution is as follows:

[0006] The first aspect of this application provides a method for classifying target scenes, including:

[0007] Obtain the target scene to be classified; the target scene to be classified includes vehicle driving data and obstacle driving data;

[0008] Based on the vehicle trajectory points in the vehicle driving data and the obstacle trajectory points in the obstacle driving data, one or more trajectory point combinations are determined; the trajectory point combination consists of vehicle trajectory points and obstacle trajectory points.

[0009] Based on the vehicle trajectory points in each of the trajectory point combinations, determine the vehicle lane sequence corresponding to the vehicle trajectory points, and based on the obstacle trajectory points in each of the trajectory point combinations, determine the obstacle lane sequence corresponding to the obstacle trajectory points.

[0010] The target scene to be classified is classified based on the vehicle lane sequence and the obstacle lane sequence to obtain the classification result.

[0011] In one possible implementation, obtaining the target scene to be classified includes:

[0012] Acquire initial map data, initial vehicle driving data, and initial obstacle driving data;

[0013] Spatial matching is performed between the initial map data and the initial vehicle driving data to obtain the map data corresponding to the initial vehicle driving data.

[0014] Spatial matching is performed between the initial map data and the initial obstacle driving data to obtain the map data corresponding to the initial obstacle driving data;

[0015] Spatial matching is performed between the map data corresponding to the initial vehicle driving data and the map data corresponding to the initial obstacle driving data to obtain map area data, and the map area data is determined as the target scene to be classified.

[0016] In one possible implementation, determining one or more trajectory point combinations based on vehicle trajectory points in the vehicle driving data and obstacle trajectory points in the obstacle driving data includes:

[0017] For each vehicle trajectory point in the vehicle driving data, calculate the absolute value of the difference between the timestamp of the vehicle trajectory point and the timestamp of each obstacle trajectory point in the obstacle driving data.

[0018] The smallest absolute difference is selected from all the absolute differences, and the initial trajectory point combination corresponding to the smallest absolute difference is obtained; the initial trajectory point combination consists of vehicle trajectory points and obstacle trajectory points.

[0019] Select initial trajectory point combinations from all initial trajectory point combinations whose absolute difference is not greater than a preset difference, and mark them as trajectory point combinations.

[0020] In one possible implementation, determining the vehicle lane sequence corresponding to each vehicle trajectory point based on the vehicle trajectory points in each combination of trajectory points, and determining the obstacle lane sequence corresponding to each obstacle trajectory point based on the obstacle trajectory points in each combination of trajectory points, includes:

[0021] Obtain the vehicle lane data corresponding to the vehicle driving data and the obstacle lane data corresponding to the obstacle driving data;

[0022] Get the timestamps corresponding to all combinations of trajectory points;

[0023] According to the timestamps from earliest to latest, the vehicle lane identifier of each trajectory point in each combination of trajectory points is obtained from the vehicle lane data, and the obstacle lane identifier of each trajectory point in each combination of trajectory points is obtained from the obstacle lane data.

[0024] Based on all vehicle lane markings, generate vehicle lane sequences corresponding to vehicle trajectory points.

[0025] Based on all obstacle lane markings, generate obstacle lane sequences corresponding to obstacle trajectory points.

[0026] In one possible implementation, obtaining the vehicle lane data corresponding to the vehicle driving data and the obstacle lane data corresponding to the obstacle driving data includes:

[0027] Obtain map lane data;

[0028] Spatial matching is performed between the vehicle trajectory points in the vehicle driving data and the map lane data to obtain the vehicle lane data corresponding to the vehicle driving data.

[0029] The obstacle trajectory points in the obstacle driving data are spatially matched with the map lane data to obtain the obstacle lane data corresponding to the obstacle driving data.

[0030] In one possible implementation, classifying the target scene to be classified based on the vehicle lane sequence and the obstacle lane sequence to obtain a classification result includes:

[0031] The first total length is obtained by adding the number of elements in the vehicle lane sequence to the number of elements in the obstacle lane sequence.

[0032] The elements in the vehicle lane sequence and the obstacle lane sequence under the same sequence index are compared to obtain the same elements under the same sequence index; the same sequence index refers to the elements at the same position in the vehicle lane sequence and the obstacle lane sequence.

[0033] The second total length is determined based on the identical elements under the same sequence index; the second total length is the difference between the first total length and the number of identical elements.

[0034] Calculate the ratio between the second total length and the first total length;

[0035] The target scene to be classified is classified according to the ratio to obtain the classification result.

[0036] In one possible implementation, determining the second total length based on the same elements under the same sequence index includes:

[0037] Based on the same elements under the same sequence index, the vehicle lane sequence is deduplicated to obtain the deduplicated vehicle lane sequence.

[0038] The second total length is obtained by adding the number of elements in the deduplicated vehicle lane sequence to the number of elements in the obstacle lane sequence.

[0039] In one possible implementation, determining the second total length based on the same elements under the same sequence index includes:

[0040] Based on the same elements under the same sequence index, the obstacle lane sequence is deduplicated to obtain the deduplicated obstacle lane sequence.

[0041] The second total length is obtained by adding the number of elements in the vehicle lane sequence and the number of elements in the deduplicated obstacle lane sequence.

[0042] In one possible implementation, classifying the target scene to be classified based on the ratio to obtain a classification result includes:

[0043] When the ratio is not less than the first threshold, the classification result is determined to be a scenario with no collision risk.

[0044] When the ratio is less than the first threshold and greater than the second threshold, the classification result is determined to be a low collision risk scenario;

[0045] When the ratio is not greater than the second threshold, the classification result is determined to be a high collision risk scenario.

[0046] A second aspect of this application provides a classification device for a target scene, comprising:

[0047] An acquisition unit is used to acquire a target scene to be classified; the target scene to be classified includes vehicle driving data and obstacle driving data.

[0048] The first determining unit is configured to determine one or more combinations of trajectory points based on vehicle trajectory points in the vehicle driving data and obstacle trajectory points in the obstacle driving data; the combination of trajectory points consists of vehicle trajectory points and obstacle trajectory points.

[0049] The second determining unit is used to determine the vehicle lane sequence corresponding to the vehicle trajectory point based on the vehicle trajectory point in each of the trajectory point combinations, and to determine the obstacle lane sequence corresponding to the obstacle trajectory point based on the obstacle trajectory point in each of the trajectory point combinations.

[0050] The classification unit is used to classify the target scene to be classified based on the vehicle lane sequence and the obstacle lane sequence, and obtain the classification result.

[0051] A third aspect of this application provides a computer program product including computer-readable instructions that, when executed on an electronic device, cause the electronic device to implement the target scenario classification method described in the first aspect or any implementation thereof.

[0052] A fourth aspect of this application provides an electronic device, including at least one processor and a memory connected to the processor, wherein:

[0053] The memory is used to store computer programs;

[0054] The processor is used to execute the computer program so that the electronic device can implement the classification method of the target scenario of the first aspect or any implementation of the first aspect.

[0055] The fifth aspect of this application provides a computer storage medium carrying one or more computer programs, which, when executed by an electronic device, enable the electronic device to classify target scenarios according to the first aspect or any implementation thereof.

[0056] Using the above technical solution, this application provides a method for acquiring a target scene to be classified. The target scene includes vehicle driving data and obstacle driving data. Based on vehicle trajectory points in the vehicle driving data and obstacle trajectory points in the obstacle driving data, one or more trajectory point combinations are determined. Each trajectory point combination consists of vehicle trajectory points and obstacle trajectory points. Based on the vehicle trajectory points in each trajectory point combination, a vehicle lane sequence corresponding to the vehicle trajectory points is determined, and based on the obstacle trajectory points in each trajectory point combination, an obstacle lane sequence corresponding to the obstacle trajectory points is determined. The target scene to be classified is then classified based on the vehicle lane sequence and the obstacle lane sequence to obtain the classification result. By determining the vehicle lane sequence through vehicle trajectory points and the obstacle lane sequence based on obstacle trajectory points, the trajectory-related information of vehicles and obstacles can be accurately captured. By analyzing this trajectory-related information, the target scene to be classified can be effectively classified, thereby ensuring the accuracy of the classification result. Attached Figure Description

[0057] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0058] Figure 1 A schematic diagram of a system architecture is provided for this application;

[0059] Figure 2 A schematic diagram of an optional hardware structure provided for this application;

[0060] Figure 3 A schematic diagram of the structure of a server provided in this application;

[0061] Figure 4 A flowchart illustrating a target scene classification method provided in this application;

[0062] Figure 5 A flowchart illustrating a method for obtaining a target scene to be classified, as provided in this application;

[0063] Figure 6 A flowchart illustrating a method for determining a combination of trajectory points provided in this application;

[0064] Figure 7 A flowchart illustrating a lane sequence determination method provided in this application;

[0065] Figure 8 A flowchart illustrating a lane data acquisition method provided in this application;

[0066] Figure 9 A flowchart illustrating a scene classification method provided in this application;

[0067] Figure 10 A schematic diagram of the structure of a target scene classification device provided in this application;

[0068] Figure 11 This is a schematic diagram of the structure of an electronic device provided in this application. Detailed Implementation

[0069] The embodiments of this application are described below with reference to the accompanying drawings. The terminology used in the implementation section of this application is for explaining specific embodiments only and is not intended to limit the scope of this application.

[0070] The embodiments of this application will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided in the embodiments of this application are equally applicable to similar technical problems.

[0071] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms are interchangeable where appropriate; this is merely a way of distinguishing objects with the same attributes in the embodiments of this application. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a series of elements is not necessarily limited to those elements, but may include other elements not explicitly listed or inherent to those processes, methods, products, or apparatuses.

[0072] See Figure 1 , Figure 1A schematic diagram of a system architecture is shown. The system may include a terminal 100 and a server 200. The server 200 may include one or more servers (…). Figure 1 (The example includes a server), and the server 200 can provide the method provided in the embodiments of this application to one or more terminals.

[0073] The terminal 100 may have a target scene classification application installed on it. The application and webpage can provide an interface. The terminal 100 can receive relevant parameters entered by the user on the input interface and send the parameters to the server 200. The server 200 can obtain the processing result based on the received parameters and return the processing result to the terminal 100.

[0074] It should be understood that in some optional implementations, the terminal 100 can also complete the action of obtaining the processing result based on the received parameters on its own, without the need for the server to cooperate. This application embodiment is not limited to this.

[0075] The following description Figure 1 The product form of the mid-terminal 100;

[0076] The terminal 100 in this application embodiment can be a mobile phone, tablet computer, wearable device, vehicle device, augmented reality (AR) / virtual reality (VR) device, laptop computer, ultra-mobile personal computer (UMPC), netbook, personal digital assistant (PDA), etc., and this application embodiment does not impose any restrictions on it.

[0077] Figure 2 A schematic diagram of an optional hardware structure for terminal 100 is shown.

[0078] refer to Figure 2 As shown, the terminal 100 may include a radio frequency unit 110, a memory 120, an input unit 130, a display unit 140, a camera 150 (optional), an audio circuit 160 (optional), a speaker 161 (optional), a microphone 162 (optional), a headphone jack 163 (optional), a processor 170, an external interface 180, a power supply 190, and other components. Those skilled in the art will understand that... Figure 2 These are merely examples of terminals or multi-functional devices and do not constitute a limitation on terminals or multi-functional devices. They may include more or fewer components than shown in the illustration, or combine certain components, or use different components.

[0079] The input unit 130 can be used to receive input numerical or character information, and to generate key signal inputs related to user settings and function control of the portable multi-functional device. Specifically, the input unit 130 may include a touchscreen 131 (optional) and / or other input devices 132. The touchscreen 131 can collect touch operations performed by the user on or near it (such as operations performed by the user using fingers, knuckles, styluses, or any suitable object on or near the touchscreen), and drive the corresponding connection devices according to a pre-set program. The touchscreen can detect the user's touch actions, convert the touch actions into touch signals and send them to the processor 170, and can receive and execute commands sent by the processor 170; the touch signal includes at least touch point coordinate information. The touchscreen 131 can provide an input interface and an output interface between the terminal 100 and the user. In addition, various types of touchscreens, such as resistive, capacitive, infrared, and surface acoustic wave, can be used to implement the touchscreen. Besides the touchscreen 131, the input unit 130 may also include other input devices. Specifically, other input devices 132 may include, but are not limited to, one or more of the following: physical keyboard, function keys (such as volume control buttons, power buttons, etc.), trackball, mouse, joystick, etc.

[0080] Other input devices 132 can receive input data, etc.

[0081] The display unit 140 can be used to display information input by the user or information provided to the user, various menus of the terminal 100, interactive interfaces, file display, and / or playback of any multimedia file. In this embodiment, the display unit 140 can be used to display an interface for classifying results, processing results, etc.

[0082] The memory 120 can be used to store instructions and data. The memory 120 may primarily include an instruction storage area and a data storage area. The data storage area can store various types of data, such as multimedia files and text. The instruction storage area can store software units such as operating systems, applications, and instructions required for at least one function, or subsets or extended sets thereof. It may also include non-volatile random access memory. It provides the processor 170 with hardware, software, and data resources for managing the computing device, supporting control software and applications. It is also used for storing multimedia files, as well as storing running programs and applications.

[0083] The processor 170 is the control center of the terminal 100. It connects various parts of the terminal 100 via various interfaces and lines. By running or executing instructions stored in the memory 120 and calling data stored in the memory 120, it performs various functions and processes data of the terminal 100, thereby controlling the terminal device as a whole. Optionally, the processor 170 may include one or more processing units; preferably, the processor 170 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 170. In some embodiments, the processor and memory can be implemented on a single chip; in some embodiments, they can also be implemented separately on independent chips. The processor 170 can also be used to generate corresponding operation control signals, send them to the corresponding components of the computing processing device, read and process data in the software, especially read and process data and programs in the memory 120, so that the various functional modules therein perform corresponding functions, thereby controlling the corresponding components to act according to the instructions.

[0084] The memory 120 can be used to store software code related to the classification method of the target scene, and the processor 170 can execute the steps of the classification method of the target scene, and can also schedule other units (such as the above-mentioned input unit 130 and display unit 140) to achieve the corresponding functions.

[0085] The radio frequency unit 110 (optional) can be used for receiving and transmitting signals during information transmission or calls. For example, it can receive downlink information from the base station and process it for the processor 170; additionally, it can transmit uplink data to the base station. Typically, the RF circuit includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low-noise amplifier (LNA), a duplexer, etc. Furthermore, the radio frequency unit 110 can also communicate wirelessly with network devices and other devices. This wireless communication can use any communication standard or protocol, including but not limited to Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), etc.

[0086] In this embodiment of the application, the radio frequency unit 110 can send data to the server 200 and receive the processing results sent by the server 200.

[0087] It should be understood that the radio frequency unit 110 is optional and can be replaced with other communication interfaces, such as a network port.

[0088] The terminal 100 also includes a power supply 190 (such as a battery) that supplies power to various components. Preferably, the power supply can be logically connected to the processor 170 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system.

[0089] Terminal 100 also includes an external interface 180, which can be a standard Micro USB interface or a multi-pin connector, and can be used to connect terminal 100 to other devices for communication, or to connect a charger to charge terminal 100.

[0090] Although not shown, terminal 100 may also include a flash, a wireless fidelity (WiFi) module, a Bluetooth module, sensors with various functions, etc., which will not be described in detail here. Some or all of the methods described below can be applied to, for example... Figure 2 In the terminal 100 shown.

[0091] The following description Figure 1 The product form of the mid-range server 200;

[0092] Figure 3 A structural diagram of a server 200 is provided, as follows: Figure 3 As shown, server 200 includes bus 201, processor 202, communication interface 203, and memory 204. Processor 202, memory 204, and communication interface 203 communicate with each other via bus 201.

[0093] Bus 201 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0094] The processor 202 can be any one or more of the following processors: central processing unit (CPU), graphics processing unit (GPU), microprocessor (MP), or digital signal processor (DSP).

[0095] Memory 204 may include volatile memory, such as random access memory (RAM). Memory 204 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0096] The memory 204 can be used to store software code related to the classification method of the target scene, and the processor 202 can execute the steps of the chip's classification method of the target scene, and can also schedule other units to achieve the corresponding functions.

[0097] It should be understood that the aforementioned terminal 100 and server 200 can be centralized or distributed devices. The processors (e.g., processor 170 and processor 202) in the aforementioned terminal 100 and server 200 can be hardware circuits (such as application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), general-purpose processors, digital signal processors (DSPs), microprocessors or microcontrollers, etc.) or combinations of these hardware circuits. For example, the processor can be a hardware system with instruction execution capabilities, such as a CPU or DSP, or a hardware system without instruction execution capabilities, such as an ASIC or FPGA, or a combination of the aforementioned hardware systems without instruction execution capabilities and hardware systems with instruction execution capabilities.

[0098] With the continuous advancement of autonomous driving technology, vehicles need to identify various dynamic targets in the surrounding environment, such as other vehicles, pedestrians, and traffic signs, through dynamic target scene classification.

[0099] Currently, dynamic target scene classification mainly relies on manual annotation. This process requires staff to meticulously examine the trajectories and related data of vehicles and dynamic targets, classifying them according to target type. However, due to the limitations of manual processing, data omissions or gaps often occur, especially when dealing with complex scenes or long-term data sets, making it impossible to comprehensively capture the trajectories and information of all dynamic targets. This not only affects data integrity but may also reduce the accuracy of classification results.

[0100] To address the aforementioned problems, embodiments of this application provide a method for classifying target scenes. The method for classifying target scenes according to embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0101] Reference Figure 4 , Figure 4 This application provides a flowchart illustrating a target scene classification method. This target scene classification method can be performed via a computer, vehicle terminal, server, etc. Figure 4 As shown in the figure, the target scene classification method provided in this application embodiment may include steps S401 to S403, which are described in detail below.

[0102] S401. Obtain the target scene to be classified.

[0103] Among them, the target scene to be classified is the target scene where the vehicle is located, which includes vehicle driving data and obstacle driving data.

[0104] Optionally, in another embodiment of this application, the specific implementation of step S401 is as follows: Figure 5 As shown, it includes the following steps:

[0105] S501. Obtain initial map data, initial vehicle driving data, and initial obstacle driving data.

[0106] The initial map data includes, but is not limited to, bird's-eye view map data, and the initial vehicle driving data includes, but is not limited to, vehicle autonomous driving navigation driving data.

[0107] Optionally, the initial obstacle driving data includes, but is not limited to, driving data for other vehicles.

[0108] S502. Spatial matching is performed between the initial map data and the initial vehicle driving data to obtain the map data corresponding to the initial vehicle driving data.

[0109] This involves spatial matching of the initial map data and the initial vehicle driving data. This means mapping the latitude and longitude of the initial vehicle driving data onto the coordinate system of the initial map data. If there is spatial intersection, they are considered to be matched, thus obtaining the map data corresponding to the initial vehicle driving data.

[0110] S503. Spatial matching is performed between the initial map data and the initial obstacle driving data to obtain the map data corresponding to the initial obstacle driving data.

[0111] This involves spatial matching of the initial map data and the initial obstacle driving data, which means mapping the latitude and longitude of the initial obstacle driving data to the coordinate system in the initial map data, and using the intersecting map data as the map data corresponding to the initial obstacle driving data.

[0112] S504. Spatial matching is performed between the map data corresponding to the initial vehicle driving data and the map data corresponding to the initial obstacle driving data to obtain map area data, and the map area data is determined as the target scene to be classified.

[0113] Understandably, spatial matching is performed between the map data corresponding to the initial vehicle driving data and the map data corresponding to the initial obstacle driving data. This involves aligning the two into a unified spatial coordinate system. The overlapping areas in the same lane and / or intersecting areas in adjacent lanes of the initial vehicle driving data and initial obstacle driving data are identified as the target scene to be classified. This coordinate system includes both vehicle and obstacle information to facilitate the subsequent identification of hazardous situations within the target scene to be classified.

[0114] S402. Determine one or more combinations of trajectory points based on the vehicle trajectory points in the vehicle driving data and the obstacle trajectory points in the obstacle driving data.

[0115] The trajectory point combination consists of vehicle trajectory points and obstacle trajectory points.

[0116] Understandably, since vehicle driving data contains multiple vehicle trajectory points and obstacle driving data contains multiple obstacle trajectory points, multiple initial trajectory point combinations can be constructed from vehicle trajectory points and obstacle trajectory points. It is also necessary to select the trajectory point combination that meets the preset conditions from the multiple initial trajectory point combinations.

[0117] Optionally, in another embodiment of this application, the specific implementation of step S402 is as follows: Figure 6 As shown, it includes the following steps:

[0118] S601. For each vehicle trajectory point in the vehicle driving data, calculate the absolute value of the difference between the timestamp of the vehicle trajectory point and the timestamp of each obstacle trajectory point in the obstacle driving data.

[0119] For example, there are two vehicle trajectory points, namely the first vehicle trajectory point and the second vehicle trajectory point. The obstacle driving data includes two obstacle trajectory points, namely the first obstacle trajectory point and the second obstacle trajectory point. Calculate the absolute value of the difference between the timestamp of the first vehicle trajectory point and the timestamp of the first obstacle trajectory point; calculate the absolute value of the difference between the timestamp of the first vehicle trajectory point and the timestamp of the second obstacle trajectory point; calculate the absolute value of the difference between the timestamp of the second vehicle trajectory point and the timestamp of the second obstacle trajectory point.

[0120] S602. Select the smallest absolute difference from all the absolute differences and obtain the initial trajectory point combination corresponding to the smallest absolute difference.

[0121] The initial trajectory point combination consists of vehicle trajectory points and obstacle trajectory points.

[0122] Understandably, for each vehicle trajectory point, the smallest absolute difference is selected from all the absolute differences corresponding to the vehicle trajectory point, and the vehicle trajectory point and obstacle trajectory point corresponding to the smallest absolute difference are obtained as the initial trajectory point combination.

[0123] For example, if the absolute value of the difference between the timestamp of the first vehicle trajectory point and the first obstacle trajectory point is 0.7, the absolute value of the difference between the timestamp of the first vehicle trajectory point and the second obstacle trajectory point is 0.6, the absolute value of the difference between the timestamp of the second vehicle trajectory point and the first obstacle trajectory point is 0.3, and the absolute value of the difference between the timestamp of the second vehicle trajectory point and the second obstacle trajectory point is 0.7, then for the first vehicle trajectory point, the smallest absolute value of the difference is selected from all the absolute values ​​of the difference corresponding to the first trajectory point, which is 0.6, and the initial trajectory point combination corresponding to 0.6 is obtained as: the first vehicle trajectory point and the second obstacle trajectory point; for the second vehicle trajectory point, the smallest absolute value of the difference is selected from all the absolute values ​​of the difference corresponding to the second trajectory point, which is 0.3, and the initial trajectory point combination corresponding to 0.3 is obtained as the second vehicle trajectory point and the first obstacle trajectory point.

[0124] S603. Select initial trajectory point combinations from all initial trajectory point combinations whose absolute difference is not greater than a preset difference, and mark them as trajectory point combinations.

[0125] Optionally, the preset difference may include, but is not limited to, 0.5.

[0126] For example, with a preset difference of 0.5, there are three initial trajectory point combinations: a first initial trajectory point combination, a second initial trajectory point combination, and a third initial trajectory point combination. The first initial trajectory point combination includes the trajectory point of the first vehicle and the trajectory point of the second obstacle (with an absolute difference of 0.6), the second initial trajectory point combination includes the trajectory point of the second vehicle and the trajectory point of the first obstacle (with an absolute difference of 0.3), and the third initial trajectory point combination includes the trajectory point of the third vehicle and the trajectory point of the first obstacle (with an absolute difference of 0.4). From all the initial trajectory point combinations, the initial trajectory point combinations with an absolute difference not greater than the preset difference are selected as the second initial trajectory point combination and the third initial trajectory point combination, and these two initial trajectory point combinations are identified as trajectory point combinations.

[0127] S403. Based on the vehicle trajectory points in each trajectory point combination, determine the vehicle lane sequence corresponding to the vehicle trajectory points, and based on the obstacle trajectory points in each trajectory point combination, determine the obstacle lane sequence corresponding to the obstacle trajectory points.

[0128] The vehicle lane sequence includes multiple lane markings, and the obstacle lane sequence includes multiple lane markings.

[0129] Understandably, based on the vehicle trajectory points in each trajectory point combination, the vehicle lane sequence corresponding to the vehicle trajectory points is determined. Specifically, the vehicle lane identifier corresponding to the vehicle trajectory points in each trajectory point combination is obtained, and the vehicle lane sequence is constructed based on the vehicle lane identifier. Based on the obstacle trajectory points in each trajectory point combination, the obstacle lane sequence corresponding to the obstacle trajectory points is determined. Specifically, the obstacle lane identifier corresponding to the obstacle trajectory points in each trajectory point combination is obtained, and the obstacle lane sequence is constructed based on the obstacle lane identifier.

[0130] Optionally, in another embodiment of this application, the specific implementation of step S403 is as follows: Figure 7 As shown, it includes the following steps:

[0131] S701. Obtain vehicle lane data corresponding to vehicle driving data and obstacle lane data corresponding to obstacle driving data.

[0132] Among them, vehicle lane data indicates the lane data in which the vehicle is traveling, and obstacle lane data is the lane data in which the obstacle is located.

[0133] Optionally, in another embodiment of this application, the specific implementation of step S701 is as follows: Figure 8 As shown, it includes the following steps:

[0134] S801, Obtain map lane data.

[0135] The map lane data is the aerial view map lane data.

[0136] S802. Spatial matching of vehicle trajectory points in vehicle driving data with map lane data to obtain vehicle lane data corresponding to vehicle driving data.

[0137] It is understandable that spatial matching is performed between vehicle trajectory points in vehicle driving data and map lane data, that is, mapping the latitude and longitude of vehicle trajectory points to the coordinate system in map lane data, and identifying the intersecting lanes as the vehicle lane data corresponding to the vehicle driving data.

[0138] S803. Spatial matching is performed between the obstacle trajectory points in the obstacle driving data and the map lane data to obtain the obstacle lane data corresponding to the obstacle driving data.

[0139] Specifically, spatial matching is performed between obstacle trajectory points in obstacle driving data and map lane data. This involves mapping the latitude and longitude of obstacle trajectory points to the coordinate system in map lane data, and identifying the intersecting lanes as the obstacle lane data corresponding to the obstacle driving data.

[0140] S702. Obtain the timestamps corresponding to all trajectory point combinations.

[0141] It should be noted that each trajectory point combination contains vehicle trajectory points, and each vehicle trajectory point has a corresponding timestamp. Therefore, obtaining the timestamps corresponding to all trajectory point combinations is equivalent to obtaining the timestamps corresponding to the vehicle trajectory points within the trajectory point combinations.

[0142] S703. According to the timestamp from earliest to latest, sequentially obtain the vehicle lane identifier of the vehicle trajectory point in each trajectory point combination from the vehicle lane data, and sequentially obtain the obstacle lane identifier of the obstacle trajectory point in each trajectory point combination from the obstacle lane data.

[0143] For example, there are three trajectory point combinations: the first trajectory point combination, the second trajectory point combination, and the third trajectory point combination. The timestamp of the first trajectory point combination is earlier than that of the second trajectory point combination, and the timestamp of the second trajectory point combination is earlier than that of the third trajectory point combination. According to the order of the timestamps from earliest to latest, the vehicle lane identifiers of the vehicle trajectory points in the first, second, and third trajectory point combinations are obtained from the vehicle lane data in sequence, and the obstacle lane identifiers of the obstacle trajectory points in the first, second, and third trajectory point combinations are obtained from the obstacle lane data in sequence.

[0144] S704. Based on all vehicle lane markings, generate the vehicle lane sequence corresponding to the vehicle trajectory points.

[0145] For example, the vehicle lane identifier of the vehicle trajectory point in the first trajectory point combination is a, the vehicle lane identifier of the vehicle trajectory point in the second trajectory point combination is a, and the vehicle lane identifier of the vehicle trajectory point in the third trajectory point combination is b. Based on all vehicle lane identifiers, the generated vehicle lane sequence corresponding to the vehicle trajectory point is: [a, a, b].

[0146] S705. Based on all obstacle lane markings, generate the obstacle lane sequence corresponding to the obstacle trajectory points.

[0147] For example, the obstacle lane identifier of the obstacle trajectory point in the first trajectory point combination is b, the obstacle lane identifier of the obstacle trajectory point in the second trajectory point combination is a, and the obstacle lane identifier of the obstacle trajectory point in the third trajectory point combination is b. Based on all obstacle lane identifiers, the generated obstacle lane sequence corresponding to the obstacle trajectory point is: [b, a, b].

[0148] S404. Classify the target scene to be classified based on the vehicle lane sequence and obstacle lane sequence to obtain the classification result.

[0149] The classification results include, but are not limited to, high collision risk scenarios, low collision risk scenarios, and no collision risk scenarios.

[0150] Optionally, in another embodiment of this application, the specific implementation of step S404 is as follows: Figure 9 As shown, it includes the following steps:

[0151] S901. Add the number of elements in the vehicle lane sequence to the number of elements in the obstacle lane sequence to obtain the first total length.

[0152] Both the vehicle lane sequence and the obstacle lane sequence are arrays, and the array length is the number of elements in the array. The first total length is obtained by adding the number of elements in the vehicle lane sequence and the number of elements in the obstacle lane sequence. For example, if the vehicle lane sequence is [a,a,a,b,b] and the obstacle lane sequence is [a,a,b,b,a], the first total length is 10.

[0153] S902. Compare the elements in the vehicle lane sequence and the obstacle lane sequence under the same sequence index to obtain the same elements under the same sequence index.

[0154] Here, the same sequence index refers to elements at the same position in both the vehicle lane sequence and the obstacle lane sequence.

[0155] It is understandable that the elements in the vehicle lane sequence and the obstacle lane sequence under the same sequence index are compared. Specifically, the vehicle lane sequence and the obstacle lane sequence are arranged according to the same time index. At the same time point, their elements (i.e., the lane information of the vehicle and the obstacle at that time point) will be compared to obtain the same elements under the same sequence index.

[0156] For example, if the vehicle lane sequence is [a,a,a,b,b] and the obstacle lane sequence is [a,a,b,b,a], then comparing the elements in the vehicle lane sequence and the obstacle lane sequence under the same sequence index will show the same elements. At index 0, both the vehicle lane sequence and the obstacle lane sequence contain the element 'a'. At index 1, both the vehicle lane sequence and the obstacle lane sequence contain the element 'a'.

[0157] S903: Determine the second total length based on the same elements under the same sequence index.

[0158] The second total length is the difference between the first total length and the number of identical elements.

[0159] Optionally, the specific implementation process for determining the second total length based on the same elements under the same sequence index is as follows: Based on the same elements under the same sequence index, the vehicle lane sequence is deduplicated to obtain the deduplicated vehicle lane sequence; the number of elements in the deduplicated vehicle lane sequence is added to the number of elements in the obstacle lane sequence to obtain the second total length.

[0160] Optionally, the specific implementation process for determining the second total length based on the same elements under the same sequence index is as follows: based on the same elements under the same sequence index, the obstacle lane sequence is deduplicated to obtain the deduplicated obstacle lane sequence; the number of elements in the vehicle lane sequence and the number of elements in the deduplicated obstacle lane sequence are added together to obtain the second total length.

[0161] As can be seen from the above, it is possible to delete identical elements under the same sequence index in the vehicle lane sequence and retain identical elements under the same sequence index in the obstacle lane sequence, or to delete identical elements under the same sequence index in the obstacle lane sequence and retain identical elements under the same sequence index in the vehicle lane sequence.

[0162] For example, if the vehicle lane sequence is [a,a,a,b,b] and the obstacle lane sequence is [a,a,b,b,a], deduplicating the vehicle lane sequence yields the deduplicated vehicle lane sequence [a,b], while the obstacle lane sequence remains unchanged. Alternatively, deduplicating the obstacle lane sequence yields the deduplicated obstacle lane sequence [b,a], while the vehicle lane sequence remains unchanged. The second total length is obtained by adding the number of elements in the deduplicated vehicle lane sequence to the number of elements in the obstacle lane sequence, resulting in a length of 7. Alternatively, the second total length is obtained by adding the number of elements in the deduplicated obstacle lane sequence to the number of elements in the vehicle lane sequence, also resulting in a length of 7.

[0163] It's understandable that adding the number of elements in the deduplicated vehicle lane sequence to the number of elements in the obstacle lane sequence, or vice versa, yields the same second total length. This is because when deduplicating the vehicle lane sequence and obstacle lane sequence separately, we eliminate duplicate lane information, ensuring that each lane sequence retains only a unique lane element. Whether we count the number of elements in the deduplicated vehicle lane sequence and obstacle lane sequence separately, or merge the deduplicated information from both, the final sum is the same, meaning that we considered the uniqueness of each lane information during the summation, thus avoiding duplicate calculations.

[0164] S904. Calculate the ratio between the second total length and the first total length.

[0165] The specific form of calculating the ratio between the second total length and the first total length is: k = i / h, where k is the ratio (i.e., collision sparsity), i is the second total length, and h is the first total length.

[0166] S905. Classify the target scene to be classified according to the ratio to obtain the classification result.

[0167] Optionally, the specific implementation process of classifying the target scene to be classified according to the ratio to obtain the classification result is as follows: when the ratio is not less than the first threshold, the classification result is determined to be a scene with no collision risk; when the ratio is less than the first threshold but greater than the second threshold, the classification result is determined to be a scene with low collision risk; when the ratio is not greater than the second threshold, the classification result is determined to be a scene with high collision risk.

[0168] The first threshold includes, but is not limited to, 0.9, and the second threshold includes, but is not limited to, 0.5.

[0169] In summary, by determining vehicle lane sequences based on vehicle trajectory points and obstacle lane sequences based on obstacle trajectory points, the trajectory-related information of vehicles and obstacles can be accurately captured. Analyzing this trajectory-related information allows for effective classification of the target scene, ensuring the accuracy of the classification results.

[0170] The above describes a target scene classification method provided by the embodiments of this application. The following describes the apparatus for performing the above target scene classification method.

[0171] Please see Figure 10 , Figure 10 This is a schematic diagram of the structure of a target scene classification device provided in an embodiment of this application. Figure 10 As shown, the target scene classification device includes: an acquisition unit 100, a first determination unit 200, a second determination unit 300, and a classification unit 400.

[0172] The acquisition unit 100 is used to acquire the target scene to be classified; the target scene to be classified includes vehicle driving data and obstacle driving data.

[0173] The acquisition unit 100 is specifically used for: acquiring initial map data, initial vehicle driving data, and initial obstacle driving data; performing spatial matching between the initial map data and the initial vehicle driving data to obtain map data corresponding to the initial vehicle driving data; performing spatial matching between the initial map data and the initial obstacle driving data to obtain map data corresponding to the initial obstacle driving data; performing spatial matching between the map data corresponding to the initial vehicle driving data and the map data corresponding to the initial obstacle driving data to obtain map area data, and determining the map area data as the target scene to be classified.

[0174] The first determining unit 200 is used to determine one or more combinations of trajectory points based on vehicle trajectory points in vehicle driving data and obstacle trajectory points in obstacle driving data; the combination of trajectory points consists of vehicle trajectory points and obstacle trajectory points.

[0175] The first determining unit 200 is specifically used for: for each vehicle trajectory point in the vehicle driving data, calculating the absolute value of the difference between the timestamp of the vehicle trajectory point and the timestamp of each obstacle trajectory point in the obstacle driving data; selecting the smallest absolute value of the difference from all the absolute values ​​of the difference, and obtaining the initial trajectory point combination corresponding to the smallest absolute value of the difference; the initial trajectory point combination consists of vehicle trajectory points and obstacle trajectory points; selecting initial trajectory point combinations whose absolute value of the difference is not greater than a preset difference from all the initial trajectory point combinations, and marking them as trajectory point combinations.

[0176] The second determining unit 300 is used to determine the vehicle lane sequence corresponding to the vehicle trajectory point based on the vehicle trajectory point in each trajectory point combination, and to determine the obstacle lane sequence corresponding to the obstacle trajectory point based on the obstacle trajectory point in each trajectory point combination.

[0177] The second determining unit 300 is specifically used for: acquiring vehicle lane data corresponding to vehicle driving data and obstacle lane data corresponding to obstacle driving data; acquiring timestamps corresponding to all trajectory point combinations; sequentially acquiring vehicle lane identifiers for each trajectory point combination from the vehicle lane data and obstacle lane identifiers for each trajectory point combination from the obstacle lane data, in order of timestamps from earliest to latest; generating vehicle lane sequences corresponding to vehicle trajectory points based on all vehicle lane identifiers; and generating obstacle lane sequences corresponding to obstacle trajectory points based on all obstacle lane identifiers.

[0178] The second determining unit 300 is specifically used for: acquiring map lane data; spatially matching vehicle trajectory points in vehicle driving data with map lane data to obtain vehicle lane data corresponding to vehicle driving data; and spatially matching obstacle trajectory points in obstacle driving data with map lane data to obtain obstacle lane data corresponding to obstacle driving data.

[0179] Classification unit 400 is used to classify the target scene to be classified based on the vehicle lane sequence and obstacle lane sequence to obtain the classification result.

[0180] The classification unit 400 is specifically used to: determine the classification result as a scenario with no collision risk when the ratio is not less than the first threshold; determine the classification result as a scenario with low collision risk when the ratio is less than the first threshold but greater than the second threshold; and determine the classification result as a scenario with high collision risk when the ratio is not greater than the second threshold.

[0181] In summary, by determining vehicle lane sequences based on vehicle trajectory points and obstacle lane sequences based on obstacle trajectory points, the trajectory-related information of vehicles and obstacles can be accurately captured. Analyzing this trajectory-related information allows for effective classification of the target scene, ensuring the accuracy of the classification results.

[0182] Combination Figure 10 The classification unit 400, as shown, includes: an addition module, a comparison module, a determination module, a calculation module, and a classification module.

[0183] The addition module is used to add the number of elements in the vehicle lane sequence to the number of elements in the obstacle lane sequence to obtain the first total length.

[0184] The comparison module is used to compare elements in the vehicle lane sequence and the obstacle lane sequence under the same sequence index to obtain the same elements under the same sequence index; the same sequence index refers to elements at the same position in the vehicle lane sequence and the obstacle lane sequence.

[0185] The determination module is used to determine the second total length based on the same elements under the same sequence index; the second total length is the difference between the first total length and the number of the same elements.

[0186] The determination module is specifically used to: perform deduplication on the vehicle lane sequence based on the same elements under the same sequence index to obtain the deduplicated vehicle lane sequence; add the number of elements in the deduplicated vehicle lane sequence to the number of elements in the obstacle lane sequence to obtain the second total length.

[0187] The determination module is specifically used to: perform deduplication processing on the obstacle lane sequence based on the same elements under the same sequence index to obtain the deduplicated obstacle lane sequence; and add the number of elements in the vehicle lane sequence and the number of elements in the deduplicated obstacle lane sequence to obtain the second total length.

[0188] The calculation module is used to calculate the ratio between the second total length and the first total length.

[0189] The classification module is used to classify the target scene to be classified based on the ratio and obtain the classification result.

[0190] This application also provides an electronic device in its embodiments. (See reference...) Figure 11The diagram illustrates a structural schematic suitable for implementing the electronic device in the embodiments of this application. The electronic device in the embodiments of this application may include, but is not limited to, fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 11 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0191] like Figure 11 As shown, the electronic device may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 1101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1102 or a program loaded from a storage device 1108 into a random access memory (RAM) 1103. When the electronic device is powered on, the RAM 1103 also stores various programs and data required for the operation of the electronic device. The processing unit 1101, ROM 1102, and RAM 1103 are interconnected via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0192] Typically, the following devices can be connected to I / O interface 1105: input devices 1106 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 1107 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1108 including, for example, memory cards, hard drives, etc.; and communication devices 1109. Communication device 1109 allows electronic devices to exchange data via wireless or wired communication with other devices. Although Figure 11 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have instead.

[0193] This application also provides a computer program product including computer-readable instructions, which, when executed on an electronic device, cause the electronic device to implement any of the target scenario classification methods provided in this application.

[0194] This application also provides a computer-readable storage medium that carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any of the target scenario classification methods provided in this application.

[0195] It should also be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. In addition, in the device embodiment drawings provided in this application, the connection relationship between modules indicates that they have a communication connection, which can be implemented as one or more communication buses or signal lines.

[0196] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware, or it can be implemented by special-purpose hardware including application-specific integrated circuits, special-purpose CPUs, special-purpose memory, special-purpose components, etc. Generally, any function performed by a computer program can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be diverse, such as analog circuits, digital circuits, or special-purpose circuits. However, for this application, software program implementation is more often the preferred implementation method. Based on this understanding, the technical solution of this application, 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 is stored in a readable storage medium, such as a computer floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk, or optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, training equipment, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0197] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product.

[0198] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

Claims

1. A method for classifying target scenes, characterized in that, include: Obtain the target scene to be classified; The target scenarios to be classified include vehicle driving data and obstacle driving data; Based on the vehicle trajectory points in the vehicle driving data and the obstacle trajectory points in the obstacle driving data, one or more trajectory point combinations are determined; the trajectory point combination consists of vehicle trajectory points and obstacle trajectory points. Based on the vehicle trajectory points in each of the trajectory point combinations, determine the vehicle lane sequence corresponding to the vehicle trajectory points, and based on the obstacle trajectory points in each of the trajectory point combinations, determine the obstacle lane sequence corresponding to the obstacle trajectory points. The target scene to be classified is classified based on the vehicle lane sequence and the obstacle lane sequence to obtain the classification result.

2. The method according to claim 1, characterized in that, The process of obtaining the target scene to be classified includes: Acquire initial map data, initial vehicle driving data, and initial obstacle driving data; Spatial matching is performed between the initial map data and the initial vehicle driving data to obtain the map data corresponding to the initial vehicle driving data. Spatial matching is performed between the initial map data and the initial obstacle driving data to obtain the map data corresponding to the initial obstacle driving data; Spatial matching is performed between the map data corresponding to the initial vehicle driving data and the map data corresponding to the initial obstacle driving data to obtain map area data, and the map area data is determined as the target scene to be classified.

3. The method according to claim 1 or 2, characterized in that, The step of determining one or more trajectory point combinations based on vehicle trajectory points in the vehicle driving data and obstacle trajectory points in the obstacle driving data includes: For each vehicle trajectory point in the vehicle driving data, calculate the absolute value of the difference between the timestamp of the vehicle trajectory point and the timestamp of each obstacle trajectory point in the obstacle driving data. The smallest absolute difference is selected from all the absolute differences, and the initial trajectory point combination corresponding to the smallest absolute difference is obtained; the initial trajectory point combination consists of vehicle trajectory points and obstacle trajectory points. Select initial trajectory point combinations from all initial trajectory point combinations whose absolute difference is not greater than a preset difference, and mark them as trajectory point combinations.

4. The method according to any one of claims 1 to 3, characterized in that, The step of determining the vehicle lane sequence corresponding to each vehicle trajectory point based on the vehicle trajectory points in each combination of trajectory points, and determining the obstacle lane sequence corresponding to each obstacle trajectory point based on the obstacle trajectory points in each combination of trajectory points, includes: Obtain the vehicle lane data corresponding to the vehicle driving data and the obstacle lane data corresponding to the obstacle driving data; Get the timestamps corresponding to all combinations of trajectory points; According to the timestamps from earliest to latest, the vehicle lane identifier of each trajectory point in each combination of trajectory points is obtained from the vehicle lane data, and the obstacle lane identifier of each trajectory point in each combination of trajectory points is obtained from the obstacle lane data. Based on all vehicle lane markings, generate vehicle lane sequences corresponding to vehicle trajectory points. Based on all obstacle lane markings, generate obstacle lane sequences corresponding to obstacle trajectory points.

5. The method according to claim 4, characterized in that, The step of obtaining the vehicle lane data corresponding to the vehicle driving data and the obstacle lane data corresponding to the obstacle driving data includes: Obtain map lane data; Spatial matching is performed between the vehicle trajectory points in the vehicle driving data and the map lane data to obtain the vehicle lane data corresponding to the vehicle driving data. The obstacle trajectory points in the obstacle driving data are spatially matched with the map lane data to obtain the obstacle lane data corresponding to the obstacle driving data.

6. The method according to any one of claims 1 to 5, characterized in that, The step of classifying the target scene to be classified based on the vehicle lane sequence and the obstacle lane sequence to obtain the classification result includes: The first total length is obtained by adding the number of elements in the vehicle lane sequence to the number of elements in the obstacle lane sequence. The elements in the vehicle lane sequence and the obstacle lane sequence under the same sequence index are compared to obtain the same elements under the same sequence index; the same sequence index refers to the elements at the same position in the vehicle lane sequence and the obstacle lane sequence. The second total length is determined based on the identical elements under the same sequence index; the second total length is the difference between the first total length and the number of identical elements. Calculate the ratio between the second total length and the first total length; The target scene to be classified is classified according to the ratio to obtain the classification result.

7. The method according to claim 6, characterized in that, The step of determining the second total length based on the same elements under the same sequence index includes: Based on the same elements under the same sequence index, the vehicle lane sequence is deduplicated to obtain the deduplicated vehicle lane sequence. The second total length is obtained by adding the number of elements in the deduplicated vehicle lane sequence to the number of elements in the obstacle lane sequence.

8. The method according to claim 6, characterized in that, The step of determining the second total length based on the same elements under the same sequence index includes: Based on the same elements under the same sequence index, the obstacle lane sequence is deduplicated to obtain the deduplicated obstacle lane sequence. The second total length is obtained by adding the number of elements in the vehicle lane sequence and the number of elements in the deduplicated obstacle lane sequence.

9. The method according to claim 6, characterized in that, The step of classifying the target scene to be classified according to the ratio to obtain the classification result includes: When the ratio is not less than the first threshold, the classification result is determined to be a scenario with no collision risk. When the ratio is less than the first threshold and greater than the second threshold, the classification result is determined to be a low collision risk scenario; When the ratio is not greater than the second threshold, the classification result is determined to be a high collision risk scenario.

10. A target scene classification device, characterized in that, include: The acquisition unit is used to acquire the target scene to be classified. The target scenarios to be classified include vehicle driving data and obstacle driving data; The first determining unit is configured to determine one or more combinations of trajectory points based on vehicle trajectory points in the vehicle driving data and obstacle trajectory points in the obstacle driving data; the combination of trajectory points consists of vehicle trajectory points and obstacle trajectory points. The second determining unit is used to determine the vehicle lane sequence corresponding to the vehicle trajectory point based on the vehicle trajectory point in each of the trajectory point combinations, and to determine the obstacle lane sequence corresponding to the obstacle trajectory point based on the obstacle trajectory point in each of the trajectory point combinations. The classification unit is used to classify the target scene to be classified based on the vehicle lane sequence and the obstacle lane sequence, and obtain the classification result.

11. A computer program product, characterized in that, It includes computer-readable instructions that, when executed on an electronic device, cause the electronic device to implement the target scene classification method as described in any one of claims 1 to 9.

12. An electronic device, characterized in that, It includes at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program to enable the electronic device to implement the target scene classification method as described in any one of claims 1 to 9.

13. A computer storage medium, characterized in that, The storage medium carries one or more computer programs, which, when executed by an electronic device, enable the electronic device to implement the target scene classification method as described in any one of claims 1 to 9.

Images