Environment model construction method and device, computer equipment and storage medium

Abstract

The invention discloses an environment model construction method and device, computer equipment and a storage medium. The method comprises the steps that lane line information corresponding to a first target vehicle and first distance information between the first target vehicle and multiple second target vehicles are acquired; performing target screening on the plurality of second target vehicles based on the lane line information and the first distance information to obtain lane attribution information of a plurality of third target vehicles; and constructing environment model information corresponding to the first target vehicle based on the lane attribution information and the lane line information. According to the method, the lane lines sensed by the camera and the millimeter-wave radar sensor and the target vehicle can be utilized to construct the environment model information, and the safety and comfort of vehicle auxiliary driving are guaranteed.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to an environment model construction method, device, computer equipment and storage medium. Background Art

[0002] With the development of Advanced Driving Assistance System (ADAS) technology, more and more vehicles are equipped with ADAS systems to assist drivers in driving. Building environmental model information that ADAS systems can understand is one of the key technologies of ADAS systems. However, existing technologies cannot use lane lines and target vehicles sensed by cameras and millimeter-wave radar sensors to build environmental model information. Summary of the invention

[0003] The embodiments of the present application provide an environment model construction method, apparatus, computer equipment and storage medium, which can use lane lines and target vehicles sensed by cameras and millimeter-wave radar sensors to construct environment model information to ensure the safety and comfort of vehicle assisted driving.

[0004] The technical solution adopted by the present invention to solve the problem is as follows:

[0005] In one aspect, the present application provides a method for constructing an environment model, comprising:

[0006] Acquire lane line information corresponding to the first target vehicle and first distance information between the first target vehicle and a plurality of second target vehicles;

[0007] Performing target screening on the plurality of second target vehicles based on the lane line information and the first distance information to obtain lane affiliation information of the plurality of third target vehicles;

[0008] Based on the lane attribution information and the lane line information, the environment model information corresponding to the first target vehicle is constructed.

[0009] In some embodiments of the present application, the lane line information includes first lane line information corresponding to the first lane line and second lane line information corresponding to the second lane line, and obtaining the lane line information corresponding to the first target vehicle includes:

[0010] Acquire a vehicle environment image corresponding to the first target vehicle, and perform lane line recognition on the vehicle environment image to obtain a lane line recognition result; the lane line recognition result includes a recognition state of the first lane line and a recognition state of the second lane line;

[0011] When the recognition state of the first lane line is a valid state and the recognition state of the second lane line is an invalid state, obtaining the first lane line information from the lane line recognition result, and determining the second lane line information based on the first lane line information;

[0012] When the recognition state of the first lane line is an invalid state and the recognition state of the second lane line is a valid state, obtaining the second lane line information from the lane line recognition result, and determining the first lane line information based on the second lane line information;

[0013] When the recognition state of the first lane line and the recognition state of the second lane line are both invalid states, the first lane line information and the second lane line information are determined based on the linear velocity and the angular velocity of the first target vehicle.

[0014] In some embodiments of the present application, determining the first lane line information and the second lane line information based on the linear velocity and angular velocity of the first target vehicle includes:

[0015] Performing trajectory prediction based on the linear velocity and angular velocity of the first target vehicle to obtain a predicted trajectory point of the first target vehicle;

[0016] The predicted trajectory point is shifted to the left according to the preset second distance information to obtain the first discrete curve point, and the predicted trajectory point is shifted to the right according to the preset third distance information to obtain the second discrete curve point;

[0017] The first discrete curve point and the second discrete curve point are respectively fitted to obtain first lane line information and second lane line information.

[0018] In some embodiments of the present application, target screening is performed on multiple second target vehicles based on lane line information and first distance information to obtain lane attribution information of multiple third target vehicles, including:

[0019] Screening the plurality of second target vehicles based on the first distance information to obtain a plurality of fourth target vehicles;

[0020] Based on the position information and width of each fourth target vehicle, determining the first edge point position and the second edge point position corresponding to each fourth target vehicle;

[0021] Determine lane affiliation information of each fourth target vehicle based on the first edge point position, the second edge point position and the lane line information;

[0022] The plurality of fourth target vehicles are screened based on the lane affiliation information of each fourth target vehicle and the first distance information of each fourth target vehicle to obtain the lane affiliation information of the plurality of third target vehicles.

[0023] In some embodiments of the present application, the lane line information includes first lane line information corresponding to the first lane line and second lane line information corresponding to the second lane line, and based on the first edge point position, the second edge point position and the lane line information, determining the lane attribution information of each fourth target vehicle includes:

[0024] Based on the first edge point position, the second edge point position, the first lane line information, and the second lane line information, determining whether a first edge point corresponding to the first edge point position or a second edge point corresponding to the second edge point position is located between the first lane line and the second lane line;

[0025] If the first edge point or the second edge point is located between the first lane line and the second lane line, the lane belonging information of the fourth target vehicle is determined to be the main lane;

[0026] If the first edge point and the second edge point are not located between the first lane line and the second lane line, determining third lane line information corresponding to the third lane line and fourth lane line information corresponding to the fourth lane line based on the first lane line information and the second lane line information;

[0027] Determine whether the first edge point and the second edge point are both located between the first lane line and the third lane line, or whether the first edge point and the second edge point are both located between the second lane line and the fourth lane line, based on the first edge point position, the second edge point position, the first lane line information, the second lane line information, the third lane line information, and the fourth lane line information;

[0028] If the first edge point and the second edge point are both located between the first lane line and the third lane line, the lane belonging information of the fourth target vehicle is determined to be the left lane;

[0029] If the first edge point and the second edge point are both located between the second lane line and the fourth lane line, it is determined that the lane belonging information of the fourth target vehicle is the right lane.

[0030] In some embodiments of the present application, the environment model information includes main lane information and behavior category information of a plurality of third target vehicles, and the lane line information includes first lane line information corresponding to the first lane line and second lane line information corresponding to the second lane line;

[0031] Based on the lane attribution information and the lane line information, the environment model information corresponding to the first target vehicle is constructed, including:

[0032] Determine main lane information corresponding to the first target vehicle based on the first lane line information and the second lane line information;

[0033] Based on the first lane line information, the second lane line information and the lane attribution information, behavior category information of multiple third target vehicles is determined.

[0034] In some embodiments of the present application, based on the first lane line information, the second lane line information and the lane attribution information, determining the behavior category information of multiple third target vehicles includes:

[0035] For any third target vehicle among the plurality of third target vehicles, determining fourth distance information between the third target vehicle and the first lane line based on the first lane line information and determining fifth distance information between the third target vehicle and the second lane line based on the second lane line information;

[0036] If the lane affiliation information of the third target vehicle is the main lane, the distance value corresponding to the fourth distance information is greater than the preset first distance threshold, and the distance value corresponding to the fifth distance information is greater than the preset second distance threshold, it is determined that the behavior category information of the third target vehicle is the first behavior category;

[0037] If the lane affiliation information of the third target vehicle is the main lane, the distance value corresponding to the fourth distance information is less than or equal to the first distance threshold, and the driving speed of the third target vehicle is greater than the driving speed of the first target vehicle, the behavior category information of the third target vehicle is determined based on the vehicle heading angle of the third target vehicle and the lane heading angle of the first lane line;

[0038] If the lane affiliation information of the third target vehicle is the main lane, the distance value corresponding to the fifth distance information is less than or equal to the second distance threshold, and the driving speed of the third target vehicle is greater than the driving speed of the first target vehicle, the behavior category information of the third target vehicle is determined based on the vehicle heading angle of the third target vehicle and the lane heading angle of the second lane line;

[0039] If the lane affiliation information of the third target vehicle is the left lane or the right lane and the distance value corresponding to the fourth distance information is less than the preset third distance threshold, or the lane affiliation information of the third target vehicle is the left lane or the right lane and the distance value corresponding to the fifth distance information is less than the preset fourth distance threshold, determine that the behavior category information of the third target vehicle is the second behavior category;

[0040] If the lane affiliation information of the third target vehicle is the left lane or the right lane, the distance value corresponding to the fourth distance information is greater than or equal to the third distance threshold, and the distance value corresponding to the fifth distance information is greater than or equal to the fourth distance threshold, the behavior category information of the third target vehicle is determined based on the driving speed of the third target vehicle and the driving speed of the first target vehicle.

[0041] In a second aspect, an embodiment of the present invention further provides an environment model building device, comprising:

[0042] An information acquisition module, used to acquire lane line information corresponding to a first target vehicle and first distance information between the first target vehicle and a plurality of second target vehicles;

[0043] An information determination module, used for performing target screening on a plurality of second target vehicles based on the lane line information and the first distance information, and obtaining lane affiliation information of a plurality of third target vehicles;

[0044] The model building module is used to build the environment model information corresponding to the first target vehicle based on the lane attribution information and the lane line information.

[0045] In a third aspect, the present application further provides a computer device, the computer device comprising:

[0046] one or more processors;

[0047] Memory; and

[0048] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement any one of the environmental model building methods in the first aspect.

[0049] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and the computer program is loaded by a processor to execute the steps in any one of the environmental model building methods in the first aspect.

[0050] The beneficial effects of the present invention are as follows: based on the lane line information and the first distance information, multiple second target vehicles are screened to obtain the lane affiliation information of multiple third target vehicles, and the environmental model information corresponding to the first target vehicle is constructed based on the lane affiliation information and the lane line information. The lane lines and target vehicles sensed by the camera and the millimeter-wave radar sensor can be used to construct the environmental model information. Through the description of the vehicle driving environment by the environmental model information, the ADAS system can easily use the environmental model information to control the vehicle driving, so as to ensure the safety and comfort of the vehicle assisted driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 is a flow chart of an environment model building system provided by an embodiment of the present invention;

[0053] Figure 2 It is a flowchart of an embodiment of the method for constructing an environment model provided by an embodiment of the present invention;

[0054] Figure 3 is a schematic diagram of a specific scenario of multiple third target vehicles provided by an embodiment of the present invention;

[0055] Figure 4It is a schematic diagram of a specific embodiment flow of obtaining lane line information provided by an embodiment of the present invention;

[0056] Figure 5 It is a schematic diagram of a specific embodiment of target screening of multiple second target vehicles provided by an embodiment of the present invention;

[0057] Figure 6 It is a schematic diagram of a specific embodiment of the process of constructing environment model information provided by an embodiment of the present invention;

[0058] Figure 7 is a schematic diagram of a specific scenario of the behavior category information of the third target vehicle provided by an embodiment of the present invention;

[0059] Figure 8 is a principle block diagram of an environment model building device provided by an embodiment of the present invention;

[0060] Fig. 9 It is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0062] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, features defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0063] In this application, the word "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described in this application as "exemplary" is not necessarily to be construed as being preferred or advantageous over other embodiments. The following description is given to enable any technician in the field to implement and use the present application. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present application can be implemented without using these specific details. In other instances, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present application with unnecessary details. Therefore, the present application is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0064] It should be noted that since the method of the embodiment of the present application is executed in a computer device, the processing objects of each computer device exist in the form of data or information. For example, time is actually time information. It can be understood that if size, quantity, position, etc. are mentioned in subsequent embodiments, they are all corresponding data for processing by the computer device. The details will not be repeated here.

[0065] The embodiments of the present application provide an environment model construction method, apparatus, computer equipment, and storage medium, which are described in detail below.

[0066] See also Figure 1 , Figure 1 Schematic diagram of a scenario of an environment model construction system provided in an embodiment of the present application. The environment model construction system may include a computer device 100, in which an environment model construction device is integrated, such as Figure 1 Computer equipment in.

[0067] In the embodiment of the present application, the computer device 100 is mainly used to obtain lane line information corresponding to the first target vehicle and first distance information between the first target vehicle and multiple second target vehicles; based on the lane line information and the first distance information, multiple second target vehicles are screened to obtain lane affiliation information of multiple third target vehicles; based on the lane affiliation information and lane line information, environmental model information corresponding to the first target vehicle is constructed, and the lane lines and target vehicles perceived by the camera and millimeter wave radar sensor can be used to construct the environmental model information to ensure the safety and comfort of vehicle assisted driving.

[0068] In the embodiment of the present application, the computer device 100 may be an independent server, or a server network or server cluster composed of servers. For example, the computer device 100 described in the embodiment of the present application includes but is not limited to a computer, a network host, a single network server, a plurality of network server sets or a cloud server composed of a plurality of servers. The cloud server is composed of a large number of computers or network servers based on cloud computing.

[0069] It is understandable that the computer device 100 used in the embodiment of the present application may be a device including both receiving and transmitting hardware, that is, a device having receiving and transmitting hardware capable of performing two-way communication on a two-way communication link. Such a device may include: a cellular or other communication device having a single-line display or a multi-line display or a cellular or other communication device without a multi-line display. The computer device 100 may specifically be a desktop terminal or a mobile terminal, and the computer device 100 may specifically be a central control device of a vehicle, which is not limited in this embodiment.

[0070] Those skilled in the art will understand that Figure 1 The application environment shown in the figure is only one application scenario of the present application solution and does not constitute a limitation on the application scenario of the present application solution. Other application environments may also include Figure 1 More or less computer equipment as shown in Figure 1 Only one computer device is shown. It can be understood that the environment model building system can also include one or more other services, which are not specifically limited here.

[0071] In addition, if Figure 1 As shown, the environment model building system may further include a memory 200 for storing data, such as lane line information, such as first lane line information, second lane line information, etc., such as position information, such as first edge point position, second edge point position, etc.

[0072] It should be noted that Figure 1 The scenario diagram of the environmental model construction system shown is merely an example. The environmental model construction system and scenario described in the embodiment of the present application are intended to more clearly illustrate the technical solution of the embodiment of the present application, and do not constitute a limitation on the technical solution provided in the embodiment of the present application. A person of ordinary skill in the art can appreciate that with the evolution of the environmental model construction system and the emergence of new business scenarios, the technical solution provided in the embodiment of the present application is equally applicable to similar technical problems.

[0073] First, an environment model construction method is provided in an embodiment of the present application. The executor of the environment model construction method is an environment model construction device. The environment model construction device is applied to a computer device. The environment model construction method includes: obtaining lane line information corresponding to a first target vehicle and first distance information between the first target vehicle and multiple second target vehicles; performing target screening on multiple second target vehicles based on the lane line information and the first distance information to obtain lane affiliation information of multiple third target vehicles; and constructing environment model information corresponding to the first target vehicle based on the lane affiliation information and the lane line information.

[0074] like Figure 2 FIG. 2 is a flow chart of an embodiment of the method for constructing an environment model in an embodiment of the present application. The method for constructing an environment model may include the following steps S201 to S203, which are as follows:

[0075] Step S201: Acquire lane line information corresponding to a first target vehicle and first distance information between the first target vehicle and a plurality of second target vehicles.

[0076] In this embodiment, the first target vehicle is the vehicle driven by the target user, the lane line information is the lane line information of the lane in which the first target vehicle is currently traveling, determined based on the vehicle environment image corresponding to the first target vehicle, and the vehicle environment image is an image obtained by photographing the surrounding environment of the first target vehicle through an imaging module (for example, a camera).

[0077] In a specific embodiment, the lane in which the first target vehicle is currently traveling includes a first lane line and a second lane line, and the lane line information includes first lane line information corresponding to the first lane line and / or second lane line information corresponding to the second lane line. For example, the first lane line and the second lane line are respectively the left lane line and the right lane line of the lane in which the first target vehicle is currently traveling, and the lane line information includes first lane line information corresponding to the left lane line and / or second lane line information corresponding to the right lane line.

[0078] It should be noted that the left lane marking and right lane marking described here are relative to the first target vehicle, that is, the left lane marking is the lane marking located on the left side of the first target vehicle, and the right lane marking is the lane marking located on the right side of the first target vehicle.

[0079] In this embodiment, the multiple second target vehicles are vehicles around the first target vehicle. The first distance information between the first target vehicle and the multiple second target vehicles can be sensed and acquired by a millimeter wave radar sensor installed on the first target vehicle. The millimeter wave radar sensor is a radar that works in the millimeter wave band (millimeter wave) for detection. Usually, millimeter waves refer to the 30-300 GHz frequency domain. Compared with infrared, laser and other sensors, millimeter wave radar sensors have strong ability to penetrate fog, smoke, and dust, can distinguish and identify very small targets, and can identify multiple targets at the same time. They have imaging capabilities, small size, good maneuverability and concealment.

[0080] Step S202: Target screening is performed on multiple second target vehicles based on the lane line information and the first distance information to obtain lane affiliation information of multiple third target vehicles.

[0081] In this embodiment, the plurality of third target vehicles are target vehicles selected from the plurality of second target vehicles based on the lane line information and the first distance information. The lane affiliation information of the plurality of third target vehicles represents the lanes in which the plurality of third target vehicles are currently traveling relative to the first target vehicle. The lane affiliation information of the plurality of second target vehicles may be the main lane, the left lane or the right lane, wherein the main lane is the lane in which the first target vehicle is currently traveling, the left lane is the lane to the left of the main lane, and the right lane is the lane to the right of the main lane. For example, referring to Figure 3 As shown, multiple third target vehicles include target vehicle 1 to target vehicle 6, the lane affiliation information of target vehicle 1 and target vehicle 2 is the main lane, the lane affiliation information of target vehicle 3 and target vehicle 5 is the left lane, and the lane affiliation information of target vehicle 4 and target vehicle 6 is the right lane.

[0082] Step S203: constructing environment model information corresponding to the first target vehicle based on the lane attribution information and the lane line information.

[0083] In a specific embodiment, the environment model information includes main lane information and behavior category information of multiple third target vehicles, the main lane information refers to the center line information of the main lane, that is, the center line information of the lane where the first target vehicle is currently traveling. The behavior category information represents the driving behavior category of the third target vehicle relative to the first target vehicle. For example, the behavior category information may include at least one of the first behavior category, the second behavior category, the third behavior category, the fourth behavior category, the fifth behavior category, the sixth behavior category and the seventh behavior category. The first behavior category represents that the third target vehicle and the first target vehicle are traveling straight in the same lane and in the same direction. The second behavior category represents that the third target vehicle is about to cut into the main lane or is close to the main lane. The third behavior category represents that the third target vehicle enters the main lane from the left and right adjacent lanes. The fourth behavior category represents that the third target vehicle moves out of the main lane. The fifth behavior category represents that the third target vehicle and the first target vehicle are traveling in the same direction and the relative position remains basically unchanged. The sixth behavior category represents that the third target vehicle and the first target vehicle are traveling in the same direction and the first target vehicle is being overtaken by the third target vehicle. The seventh behavior category represents that the third target vehicle and the first target vehicle are traveling in the same direction and the third target vehicle is being overtaken by the first target vehicle.

[0084] This embodiment performs target screening on multiple second target vehicles based on lane line information and the first distance information to obtain lane affiliation information of multiple third target vehicles, and constructs environmental model information corresponding to the first target vehicle based on the lane affiliation information and lane line information. The environmental model information can be constructed using lane lines and target vehicles sensed by cameras and millimeter-wave radar sensors. Through the description of the vehicle driving environment by the environmental model information, the ADAS system can easily use the environmental model information to control the vehicle's driving to ensure the safety and comfort of vehicle assisted driving.

[0085] In a specific implementation, the lane line information includes first lane line information corresponding to the first lane line and second lane line information corresponding to the second lane line. Figure 4 As shown, the acquisition of lane line information corresponding to the first target vehicle in step S201 may include steps S301 to S304, which are specifically as follows:

[0086] Step S301, obtaining a vehicle environment image corresponding to a first target vehicle, and performing lane line recognition on the vehicle environment image to obtain a lane line recognition result; the lane line recognition result includes a recognition state of a first lane line and a recognition state of a second lane line.

[0087] In a specific embodiment, the vehicle environment image is an image obtained by photographing the surrounding environment of the first target vehicle through an imaging module (for example, a camera), and the lane line recognition result is the lane line recognition information obtained by performing lane line recognition on the vehicle environment image. Lane line recognition on the vehicle environment image can adopt existing image perception algorithms, such as Canny edge detection algorithm, Otsu algorithm, deep learning algorithm, etc., which is not limited in this embodiment.

[0088] Furthermore, the lane line recognition result includes the recognition status of the first lane line and the recognition status of the second lane line, the recognition status includes a valid state and / or an invalid state, when the recognition status of the first lane line is a valid state, the lane line recognition result also includes first lane line information corresponding to the first lane line, when the recognition status of the second lane line is a valid state, the lane line recognition result also includes second lane line information corresponding to the second lane line.

[0089] Step S302: when the recognition state of the first lane line is a valid state and the recognition state of the second lane line is an invalid state, obtain the first lane line information from the lane line recognition result, and determine the second lane line information based on the first lane line information.

[0090] In a specific embodiment, when the recognition status of the first lane line is a valid state and the recognition status of the second lane line is an invalid state, the lane line recognition result includes first lane line information corresponding to the first lane line but does not include second lane line information corresponding to the second lane line. At this time, in order to construct the environmental model information, the first lane line information can be obtained from the lane line recognition result, and the second lane line information can be determined based on the first lane line information, thereby completing the second lane line information.

[0091] In a specific embodiment, the step of determining the second lane line information based on the first lane line information specifically includes: determining the third discrete curve point corresponding to the first lane line based on the first lane line information; performing translation processing on the third discrete curve point according to the preset sixth distance information to obtain the fourth discrete curve point; performing fitting processing on the fourth discrete curve point to obtain the second lane line information. The distance value corresponding to the sixth distance information is the lane width corresponding to the main lane.

[0092] For example, the first lane line information is the lane line information corresponding to the left lane line of the main lane, and the second lane line information is the lane line information corresponding to the right lane line of the main lane. The third discrete curve point is translated to the right by the width of the main lane to obtain the fourth discrete curve point corresponding to the second lane line. The second lane line information can be obtained by performing a cubic polynomial fitting on the fourth discrete curve point.

[0093] For another example, the first lane line information is the lane line information corresponding to the right lane line of the main lane, and the second lane line information is the lane line information corresponding to the left lane line of the main lane. By translating the third discrete curve point to the left by the width of the main lane, the fourth discrete curve point corresponding to the second lane line can be obtained, and by performing cubic polynomial fitting on the fourth discrete curve point, the second lane line information can be obtained.

[0094] Step S303: when the recognition state of the first lane line is an invalid state and the recognition state of the second lane line is a valid state, obtain the second lane line information from the lane line recognition result, and determine the first lane line information based on the second lane line information.

[0095] In a specific embodiment, when the recognition state of the first lane line is an invalid state and the recognition state of the second lane line is a valid state, the lane line recognition result includes second lane line information corresponding to the second lane line but does not include first lane line information corresponding to the first lane line. At this time, in order to construct the environmental model information, the second lane line information can be obtained from the lane line recognition result, and the first lane line information can be determined based on the second lane line information, thereby completing the first lane line information.

[0096] In a specific embodiment, the above-mentioned step of determining the first lane line information based on the second lane line information specifically includes: determining the fifth discrete curve point corresponding to the second lane line based on the second lane line information; translating the fifth discrete curve point according to the sixth distance information to obtain the sixth discrete curve point; and fitting the sixth discrete curve point to obtain the first lane line information.

[0097] For example, the first lane line information is the lane line information corresponding to the left lane line of the main lane, and the second lane line information is the lane line information corresponding to the right lane line of the main lane. The fifth discrete curve point is translated to the left by the width of the main lane to obtain the sixth discrete curve point corresponding to the first lane line. The first lane line information can be obtained by performing cubic polynomial fitting on the sixth discrete curve point.

[0098] For another example, the first lane line information is the lane line information corresponding to the right lane line of the main lane, and the second lane line information is the lane line information corresponding to the left lane line of the main lane. By translating the fifth discrete curve point to the right by the width of the main lane, the sixth discrete curve point corresponding to the first lane line can be obtained, and by performing cubic polynomial fitting on the sixth discrete curve point, the first lane line information can be obtained.

[0099] Step S304: when the recognition status of the first lane line and the recognition status of the second lane line are both in invalid states, determining the first lane line information and the second lane line information based on the linear velocity and angular velocity of the first target vehicle.

[0100] In a specific embodiment, when the recognition status of the first lane line is an invalid state and the recognition status of the second lane line is also an invalid state, the first lane line information and the second lane line information are missing in the lane line recognition result. In this case, in order to construct the environmental model information, it is necessary to determine the first lane line information and the second lane line information based on the linear velocity and angular velocity of the first target vehicle, thereby completing the first lane line information and the second lane line information.

[0101] In a specific embodiment, the above-mentioned step of determining the first lane line information and the second lane line information based on the linear velocity and angular velocity of the first target vehicle specifically includes: performing trajectory prediction based on the linear velocity and angular velocity of the first target vehicle to obtain a predicted trajectory point of the first target vehicle; performing a left translation on the predicted trajectory point according to a preset second distance information to obtain a first discrete curve point, and performing a right translation on the predicted trajectory point according to a preset third distance information to obtain a second discrete curve point; performing fitting processing on the first discrete curve point and the second discrete curve point respectively to obtain the first lane line information and the second lane line information.

[0102] In a specific embodiment, the step of performing trajectory prediction based on the linear velocity and angular velocity of the first target vehicle to obtain the predicted trajectory points of the first target vehicle specifically includes: inputting the linear velocity and angular velocity of the first target vehicle into a kinematic model, performing trajectory prediction based on the linear velocity and angular velocity through the kinematic model, and obtaining the predicted trajectory points of the first target vehicle.

[0103] In a specific implementation, referring to Figure 5 As shown, in step S202, multiple second target vehicles are screened based on the lane line information and the first distance information to obtain lane affiliation information of multiple third target vehicles, which may include steps S401 to S404, which are specifically as follows:

[0104] Step S401: screening multiple second target vehicles based on first distance information to obtain multiple fourth target vehicles.

[0105] In this embodiment, the plurality of fourth target vehicles are target vehicles whose distance values ​​corresponding to the first distance information are less than or equal to the preset fifth distance threshold value among the plurality of second target vehicles. The fifth distance threshold value can be set as needed, for example, the fifth distance threshold value can be set to 200 meters, and the plurality of fourth target vehicles are target vehicles whose distance values ​​corresponding to the first distance information are less than or equal to 200 meters among the plurality of second target vehicles.

[0106] Step S402: Based on the position information and width of each fourth target vehicle, determine the first edge point position and the second edge point position corresponding to each fourth target vehicle.

[0107] In this embodiment, the first edge point position is the position corresponding to the left edge point of the fourth target vehicle, and the second edge point position is the position corresponding to the right edge point of the fourth target vehicle, or, the first edge point position is the position corresponding to the right edge point of the fourth target vehicle, and the second edge point position is the position corresponding to the left edge point of the fourth target vehicle.

[0108] Step S403: Determine lane affiliation information of each fourth target vehicle based on the first edge point position, the second edge point position and the lane line information.

[0109] In a specific embodiment, the lane line information includes first lane line information corresponding to the first lane line and second lane line information corresponding to the second lane line. The above-mentioned step of determining the lane affiliation information of each fourth target vehicle based on the first edge point position, the second edge point position and the lane line information specifically includes: determining whether the first edge point corresponding to the first edge point position or the second edge point corresponding to the second edge point position is located between the first lane line and the second lane line based on the first edge point position, the second edge point position, the first lane line information and the second lane line information; if the first edge point or the second edge point is located between the first lane line and the second lane line, determining the lane affiliation information of the fourth target vehicle is the main lane; if neither the first edge point nor the second edge point is located between the first lane line and the second lane line, Determine the third lane line information corresponding to the third lane line and the fourth lane line information corresponding to the fourth lane line based on the first lane line information and the second lane line information; determine whether the first edge point and the second edge point are both located between the first lane line and the third lane line, or whether the first edge point and the second edge point are both located between the second lane line and the fourth lane line based on the first edge point position, the second edge point position, the first lane line information, the second lane line information, the third lane line information and the fourth lane line information; if the first edge point and the second edge point are both located between the first lane line and the third lane line, determine that the lane affiliation information of the fourth target vehicle is the left lane; if the first edge point and the second edge point are both located between the second lane line and the fourth lane line, determine that the lane affiliation information of the fourth target vehicle is the right lane.

[0110] In a specific embodiment, the first edge point or the second edge point is located between the first lane line and the second lane line, including the following three situations: ① The first edge point and the second edge point are both located between the first lane line and the second lane line; ② The first edge point and the second edge point are respectively located on the left side of the first lane line and on the right side of the first lane line; ③ The first edge point and the second edge point are respectively located on the left side of the second lane line and on the right side of the second lane line, that is, when the first edge point and the second edge point are determined to be any one of the above three situations, the lane attribution information of the fourth target vehicle is determined to be the main lane.

[0111] In a specific embodiment, in combination Figure 3As shown, the first lane line is the left lane line (i.e., the L lane line) of the lane where the first target vehicle is driving, the second lane line is the right lane line (i.e., the R lane line) of the lane where the first target vehicle is driving, the third lane line is the lane line on the left side of the first lane line (i.e., the LL lane line), and the fourth lane line is the lane line on the right side of the second lane line (i.e., the RR lane line). The steps of determining the third lane line information corresponding to the third lane line and the fourth lane line information corresponding to the fourth lane line based on the first lane line information and the second lane line information are the same as the steps of determining the second lane line based on the first lane line and determining the first lane line based on the second lane line. For details, reference may be made to the steps of determining the second lane line based on the first lane line and determining the first lane line based on the second lane line. To avoid repetition, this embodiment does not make any limitation.

[0112] In a specific embodiment, if the first edge point and the second edge point are both located between the first lane line and the third lane line, that is, the left and right edge points of the fourth target vehicle are both located in the left lane of the main lane, then the lane belonging information of the fourth target vehicle is determined to be the left lane. If the first edge point and the second edge point are both located between the second lane line and the fourth lane line, that is, the left and right edge points of the fourth target vehicle are both located in the right lane of the main lane, then the lane belonging information of the fourth target vehicle is determined to be the right lane.

[0113] Step S404: screening multiple fourth target vehicles based on the lane affiliation information of each fourth target vehicle and the first distance information of each fourth target vehicle to obtain lane affiliation information of multiple third target vehicles.

[0114] In a specific embodiment, when a plurality of fourth target vehicles are screened based on the lane affiliation information of each fourth target vehicle and the first distance information of each fourth target vehicle, the fourth target vehicles whose lane affiliation information is the main lane, the fourth target vehicles whose lane affiliation information is the left lane, and the fourth target vehicles whose lane affiliation information is the right lane can be sorted respectively based on the first distance information, and then the fourth target vehicles with the highest sorting are selected as the third target vehicles, and the lane affiliation information corresponding to the fourth target vehicles with the highest sorting is the lane affiliation information of the third target vehicle. For example, two fourth target vehicles with the highest sorting are selected from the fourth target vehicles with the lane affiliation information of the main lane, the left lane, and the right lane, respectively, and the six fourth target vehicles are the third target vehicles, and the lane affiliation information of the six fourth target vehicles is the lane affiliation information of the plurality of third target vehicles.

[0115] In a specific implementation, the environment model information includes main lane information and behavior category information of multiple third target vehicles, and the lane line information includes first lane line information corresponding to the first lane line and second lane line information corresponding to the second lane line. Figure 6As shown, in step S203, based on the lane attribution information and the lane line information, the environment model information corresponding to the first target vehicle is constructed, which may include steps S501 to S502, which are specifically as follows:

[0116] Step S501: Determine main lane information corresponding to a first target vehicle based on first lane line information and second lane line information.

[0117] In a specific embodiment, the first lane line information is the lane line information corresponding to the left lane of the lane where the first target vehicle is traveling, the second lane line information is the lane line information corresponding to the right lane of the lane where the first target vehicle is traveling, and the main lane information corresponding to the first target vehicle is the center line information of the lane where the first target vehicle is traveling. The first lane line information can be expressed as: L =x L- coeff[0]+x L- coeff[1]*t+x L- coeff[2]*t 2 +x L- coeff[3]*t 3 ,y L =y L- coeff[0]+y L- coeff[1]*t+y L- coeff[2]*t 2 +y L- coeff[3]*t 3 , the second lane line information can be expressed as: x R =x R- coeff[0]+x R- coeff[1]*t+x R- coeff[2]*t 2 +x R- coeff[3]*t 3 ,y R =y R- coeff[0]+y R- coeff[1]*t+y R- coeff[2]*t 2 +y R- coeff[3]*t 3 , then the main lane information can be expressed as: x C =x C- coeff[0]+x C- coeff[1]*t+x C- coeff[2]*t 2 +x C- coeff[3]*t 3 ,yC =y C- coeff[0]+y C- coeff[1]*t+y C- coeff[2]*t 2 +y C- coeff[3]*t 3 , where x C- coeff=(x L- coeff+x R- coeff) / 2,y C- coeff=(y L- coeff+y R- coeff) / 2.

[0118] Step S502: Determine behavior category information of multiple third target vehicles based on the first lane line information, the second lane line information and the lane attribution information.

[0119] In a specific embodiment, the step of determining the behavior category information of multiple third target vehicles based on the first lane line information, the second lane line information and the lane attribution information specifically includes: for any third target vehicle among the multiple third target vehicles, determining the fourth distance information between the third target vehicle and the first lane line based on the first lane line information and determining the fifth distance information between the third target vehicle and the second lane line based on the second lane line information; if the lane attribution information of the third target vehicle is the main lane, the distance value corresponding to the fourth distance information is greater than the preset first distance threshold and the distance value corresponding to the fifth distance information is greater than the preset second distance threshold, determining the behavior category information of the third target vehicle to be the first behavior category; if the lane attribution information of the third target vehicle is the main lane, the distance value corresponding to the fourth distance information is less than or equal to the first distance threshold and the driving speed of the third target vehicle is greater than the driving speed of the first target vehicle, determining the behavior category information of the third target vehicle based on the vehicle orientation angle of the third target vehicle and the lane orientation angle of the first lane line information; if the lane belonging information of the third target vehicle is the main lane, the distance value corresponding to the fifth distance information is less than or equal to the second distance threshold, and the driving speed of the third target vehicle is greater than the driving speed of the first target vehicle, the behavior category information of the third target vehicle is determined based on the vehicle orientation angle of the third target vehicle and the lane orientation angle of the second lane line; if the lane belonging information of the third target vehicle is the left lane or the right lane and the distance value corresponding to the fourth distance information is less than the preset third distance threshold or the lane belonging information of the third target vehicle is the left lane or the right lane and the distance value corresponding to the fifth distance information is less than the preset fourth distance threshold, the behavior category information of the third target vehicle is determined to be the second behavior category; if the lane belonging information of the third target vehicle is the left lane or the right lane, the distance value corresponding to the fourth distance information is greater than or equal to the third distance threshold, and the distance value corresponding to the fifth distance information is greater than or equal to the fourth distance threshold, the behavior category information of the third target vehicle is determined based on the driving speed of the third target vehicle and the driving speed of the first target vehicle.

[0120] Among them, the first behavior category indicates that the third target vehicle and the first target vehicle are traveling in the same lane and in the same direction. If the lane affiliation information of the third target vehicle is the main lane, the distance value corresponding to the fourth distance information is greater than the preset first distance threshold, and the distance value corresponding to the fifth distance information is greater than the preset second distance threshold, that is, the distance between the third target vehicle and the lane line of the main lane is greater than the threshold, the behavior category information of the third target vehicle is determined to be the first behavior category. For example, referring to Figure 7 As shown, the behavior category information of the third target vehicle directly in front of the first target vehicle (the block labeled ego) is the first behavior category (MOVING).

[0121] In a specific embodiment, the first lane line is the left lane line of the main lane, and the distance value corresponding to the fourth distance information is less than or equal to the first distance threshold, indicating that the third target vehicle is close to the left lane line of the main lane. When the lane attribution information of the third target vehicle is the main lane, the third target vehicle is close to the left lane line of the main lane, and the driving speed of the third target vehicle is greater than the driving speed of the first target vehicle, the behavior category information of the third target vehicle is further determined based on the vehicle heading angle of the third target vehicle and the lane heading angle of the first lane line.

[0122] In a specific embodiment, the step of determining the behavior category information of the third target vehicle based on the vehicle heading angle of the third target vehicle and the lane heading angle of the first lane line specifically includes: if the vehicle heading angle of the third target vehicle is smaller than the lane heading angle of the first lane line and the angle difference between the vehicle heading angle of the third target vehicle and the lane heading angle of the first lane line is greater than a preset first angle threshold, determining that the behavior category information of the third target vehicle is a third behavior category; if the vehicle heading angle of the third target vehicle is greater than the lane heading angle of the first lane line and the angle difference between the vehicle heading angle of the third target vehicle and the lane heading angle of the first lane line is greater than a preset second angle threshold, determining that the behavior category information of the third target vehicle is a fourth behavior category.

[0123] The third behavior category represents that the third target vehicle enters the main lane from the left or right adjacent lanes, and the fourth behavior category represents that the third target vehicle moves out of the main lane. Figure 7 As shown, MOVING_IN indicates that the third target vehicle enters the main lane from the left and right adjacent lanes, and MOVING_OUT indicates that the third target vehicle is moving out of the main lane.

[0124] In a specific embodiment, the second lane line is the right lane line of the main lane, and the distance value corresponding to the fifth distance information is less than or equal to the second distance threshold, indicating that the third target vehicle is close to the right lane line of the main lane. When the lane attribution information of the third target vehicle is the main lane, the third target vehicle is close to the right lane line of the main lane and the driving speed of the third target vehicle is greater than the driving speed of the first target vehicle, the behavior category information of the third target vehicle is further determined based on the vehicle orientation angle of the third target vehicle and the lane orientation angle of the second lane line.

[0125] In a specific embodiment, the step of determining the behavior category information of the third target vehicle based on the vehicle heading angle of the third target vehicle and the lane heading angle of the second lane line specifically includes: if the vehicle heading angle of the third target vehicle is greater than the lane heading angle of the second lane line and the angle difference between the vehicle heading angle of the third target vehicle and the lane heading angle of the second lane line is greater than a preset third angle threshold, determining that the behavior category information of the third target vehicle is the third behavior category; if the vehicle heading angle of the third target vehicle is less than the lane heading angle of the second lane line and the angle difference between the vehicle heading angle of the third target vehicle and the lane heading angle of the second lane line is greater than a preset fourth angle threshold, determining that the behavior category information of the third target vehicle is the fourth behavior category.

[0126] In this embodiment, the second behavior category indicates that the second target vehicle is about to cut into the main lane or approach the main lane. If the lane affiliation information of the third target vehicle is the left lane or the right lane and the distance value corresponding to the fourth distance information is less than the preset third distance threshold or the lane affiliation information of the third target vehicle is the left lane or the right lane and the fifth distance information is less than the preset fourth distance threshold, that is, the lane affiliation information of the third target vehicle is the left lane or the right lane and the third target vehicle is close to the left lane line or the right lane line of the main lane, the behavior category information of the third target vehicle is determined to be the second behavior category. For example, continue to refer to Figure 7 As shown, CLOSE_CUT_IN indicates that the second target vehicle is cutting into the main lane or is close to the main lane.

[0127] In a specific embodiment, the step of determining the behavior category information of the third target vehicle based on the driving speed of the third target vehicle and the driving speed of the first target vehicle specifically includes: if the difference between the driving speed of the third target vehicle and the driving speed of the first target vehicle is less than a preset first speed threshold, determining that the behavior category information of the third target vehicle is the fifth behavior category; if the driving speed of the third target vehicle is greater than the driving speed of the first target vehicle and the difference between the driving speed of the third target vehicle and the driving speed of the first target vehicle is greater than a preset second speed threshold, determining that the behavior category information of the third target vehicle is the sixth behavior category; if the driving speed of the third target vehicle is less than the driving speed of the first target vehicle and the difference between the driving speed of the third target vehicle and the driving speed of the first target vehicle is greater than the preset third speed threshold, determining that the behavior category information of the third target vehicle is the seventh behavior category.

[0128] Among them, the fifth behavior category represents that the third target vehicle and the first target vehicle are traveling in the same direction and their relative positions remain basically unchanged, the sixth behavior category represents that the third target vehicle and the first target vehicle are traveling in the same direction and the first target vehicle is being overtaken by the third target vehicle, and the seventh behavior category represents that the third target vehicle and the first target vehicle are traveling in the same direction and the third target vehicle is being overtaken by the first target vehicle. Figure 7 As shown, PASSING / IN indicates that the third target vehicle is traveling in the same direction as the first target vehicle and the first target vehicle is being overtaken by the third target vehicle, and PASSING_OUT indicates that the third target vehicle is traveling in the same direction as the first target vehicle and the third target vehicle is being overtaken by the first target vehicle.

[0129] In order to better implement the environmental model construction method in the embodiment of the present application, based on the environmental model construction method, an environmental model construction device is also provided in the embodiment of the present application, such as Figure 8 As shown, the environment model building device 700 includes:

[0130] An information acquisition module 710 is used to acquire lane line information corresponding to a first target vehicle and first distance information between the first target vehicle and a plurality of second target vehicles;

[0131] An information determination module 720, configured to perform target screening on a plurality of second target vehicles based on the lane line information and the first distance information, and obtain lane attribution information of a plurality of third target vehicles;

[0132] The model building module 730 is used to build the environment model information corresponding to the first target vehicle based on the lane attribution information and the lane line information.

[0133] In an embodiment of the present application, multiple second target vehicles are screened based on lane line information and first distance information to obtain lane affiliation information of multiple third target vehicles, and environmental model information corresponding to the first target vehicle is constructed based on the lane affiliation information and lane line information. The environmental model information can be constructed using lane lines and target vehicles sensed by cameras and millimeter-wave radar sensors. Through the description of the vehicle driving environment by the environmental model information, the ADAS system can easily use the environmental model information to control the vehicle's driving to ensure the safety and comfort of vehicle assisted driving.

[0134] In some embodiments of the present application, the lane line information includes first lane line information corresponding to the first lane line and second lane line information corresponding to the second lane line. The information acquisition module 710 acquires the lane line information corresponding to the first target vehicle, including:

[0135] Acquire a vehicle environment image corresponding to the first target vehicle, and perform lane line recognition on the vehicle environment image to obtain a lane line recognition result; the lane line recognition result includes a recognition state of the first lane line and a recognition state of the second lane line;

[0136] When the recognition state of the first lane line is a valid state and the recognition state of the second lane line is an invalid state, obtaining the first lane line information from the lane line recognition result, and determining the second lane line information based on the first lane line information;

[0137] When the recognition state of the first lane line is an invalid state and the recognition state of the second lane line is a valid state, obtaining the second lane line information from the lane line recognition result, and determining the first lane line information based on the second lane line information;

[0138] When the recognition state of the first lane line and the recognition state of the second lane line are both invalid states, the first lane line information and the second lane line information are determined based on the linear velocity and the angular velocity of the first target vehicle.

[0139] In some embodiments of the present application, the information acquisition module 710 determines the first lane line information and the second lane line information based on the linear velocity and angular velocity of the first target vehicle, including:

[0140] Performing trajectory prediction based on the linear velocity and angular velocity of the first target vehicle to obtain a predicted trajectory point of the first target vehicle;

[0141] The predicted trajectory point is shifted to the left according to the preset second distance information to obtain the first discrete curve point, and the predicted trajectory point is shifted to the right according to the preset third distance information to obtain the second discrete curve point;

[0142] The first discrete curve point and the second discrete curve point are respectively fitted to obtain first lane line information and second lane line information.

[0143] In some embodiments of the present application, the information determination module 720 performs target screening on multiple second target vehicles based on the lane line information and the first distance information to obtain lane attribution information of multiple third target vehicles, including:

[0144] Screening the plurality of second target vehicles based on the first distance information to obtain a plurality of fourth target vehicles;

[0145] Based on the position information and width of each fourth target vehicle, determining the first edge point position and the second edge point position corresponding to each fourth target vehicle;

[0146] Determine lane affiliation information of each fourth target vehicle based on the first edge point position, the second edge point position and the lane line information;

[0147] The plurality of fourth target vehicles are screened based on the lane affiliation information of each fourth target vehicle and the first distance information of each fourth target vehicle to obtain the lane affiliation information of the plurality of third target vehicles.

[0148] In some embodiments of the present application, the lane line information includes first lane line information corresponding to the first lane line and second lane line information corresponding to the second lane line. The information determination module 720 determines the lane attribution information of each fourth target vehicle based on the first edge point position, the second edge point position and the lane line information, including:

[0149] Based on the first edge point position, the second edge point position, the first lane line information, and the second lane line information, determining whether a first edge point corresponding to the first edge point position or a second edge point corresponding to the second edge point position is located between the first lane line and the second lane line;

[0150] If the first edge point or the second edge point is located between the first lane line and the second lane line, the lane belonging information of the fourth target vehicle is determined to be the main lane;

[0151] If the first edge point and the second edge point are not located between the first lane line and the second lane line, determining third lane line information corresponding to the third lane line and fourth lane line information corresponding to the fourth lane line based on the first lane line information and the second lane line information;

[0152] Determine whether the first edge point and the second edge point are both located between the first lane line and the third lane line, or whether the first edge point and the second edge point are both located between the second lane line and the fourth lane line, based on the first edge point position, the second edge point position, the first lane line information, the second lane line information, the third lane line information, and the fourth lane line information;

[0153] If the first edge point and the second edge point are both located between the first lane line and the third lane line, the lane belonging information of the fourth target vehicle is determined to be the left lane;

[0154] If the first edge point and the second edge point are both located between the second lane line and the fourth lane line, it is determined that the lane belonging information of the fourth target vehicle is the right lane.

[0155] In some embodiments of the present application, the environment model information includes main lane information and behavior category information of multiple third target vehicles, the lane line information includes first lane line information corresponding to the first lane line and second lane line information corresponding to the second lane line, and the model construction module 730 constructs the environment model information corresponding to the first target vehicle based on the lane attribution information and the lane line information, including:

[0156] Determine main lane information corresponding to the first target vehicle based on the first lane line information and the second lane line information;

[0157] Based on the first lane line information, the second lane line information and the lane attribution information, behavior category information of multiple third target vehicles is determined.

[0158] In some embodiments of the present application, the model building module 730 determines the behavior category information of multiple third target vehicles based on the first lane line information, the second lane line information and the lane attribution information, including:

[0159] For any third target vehicle among the plurality of third target vehicles, determining fourth distance information between the third target vehicle and the first lane line based on the first lane line information and determining fifth distance information between the third target vehicle and the second lane line based on the second lane line information;

[0160] If the lane affiliation information of the third target vehicle is the main lane, the distance value corresponding to the fourth distance information is greater than the preset first distance threshold, and the distance value corresponding to the fifth distance information is greater than the preset second distance threshold, it is determined that the behavior category information of the third target vehicle is the first behavior category;

[0161] If the lane affiliation information of the third target vehicle is the main lane, the distance value corresponding to the fourth distance information is less than or equal to the first distance threshold, and the driving speed of the third target vehicle is greater than the driving speed of the first target vehicle, the behavior category information of the third target vehicle is determined based on the vehicle heading angle of the third target vehicle and the lane heading angle of the first lane line;

[0162] If the lane affiliation information of the third target vehicle is the main lane, the distance value corresponding to the fifth distance information is less than or equal to the second distance threshold, and the driving speed of the third target vehicle is greater than the driving speed of the first target vehicle, the behavior category information of the third target vehicle is determined based on the vehicle heading angle of the third target vehicle and the lane heading angle of the second lane line;

[0163] If the lane affiliation information of the third target vehicle is the left lane or the right lane and the distance value corresponding to the fourth distance information is less than the preset third distance threshold, or the lane affiliation information of the third target vehicle is the left lane or the right lane and the distance value corresponding to the fifth distance information is less than the preset fourth distance threshold, determine that the behavior category information of the third target vehicle is the second behavior category;

[0164] If the lane affiliation information of the third target vehicle is the left lane or the right lane, the distance value corresponding to the fourth distance information is greater than or equal to the third distance threshold, and the distance value corresponding to the fifth distance information is greater than or equal to the fourth distance threshold, the behavior category information of the third target vehicle is determined based on the driving speed of the third target vehicle and the driving speed of the first target vehicle.

[0165] The embodiment of the present application further provides a computer device, which integrates any one of the environment model building devices provided in the embodiment of the present application, and the computer device includes:

[0166] one or more processors;

[0167] Memory; and

[0168] One or more applications, wherein the one or more applications are stored in a memory and are configured to be executed by a processor to execute the steps of the environment model building method in any of the above-mentioned environment model building method embodiments.

[0169] The present application also provides a computer device that integrates any one of the environment model building devices provided in the present application. Fig. 9 As shown, it shows a schematic diagram of the structure of the computer device involved in the embodiment of the present application, specifically:

[0170] The computer device may include one or more processing core processors 801, one or more computer-readable storage media memories 802, a power supply 803, an input unit 804 and other components. Those skilled in the art will appreciate that Fig. 9 The computer device structure shown in the figure does not constitute a limitation on the computer device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. Among them:

[0171] The processor 801 is the control center of the computer device. It uses various interfaces and lines to connect various parts of the entire computer device. By running or executing software programs and / or modules stored in the memory 802 and calling data stored in the memory 802, it executes various functions of the computer device and processes data, thereby monitoring the computer device as a whole. Optionally, the processor 801 may include one or more processing cores; preferably, the processor 801 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 801.

[0172] The memory 802 can be used to store software programs and modules. The processor 801 executes various functional applications and data processing by running the software programs and modules stored in the memory 802. The memory 802 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 802 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 802 may also include a memory controller to provide the processor 801 with access to the memory 802.

[0173] The computer device also includes a power supply 803 for supplying power to each component. Preferably, the power supply 803 can be logically connected to the processor 801 through a power management system, so that the power management system can manage charging, discharging, power consumption and other functions. The power supply 803 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components.

[0174] The computer device may further include an input unit 804, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0175] Although not shown, the computer device may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 801 in the computer device will load the executable files corresponding to the processes of one or more application programs into the memory 802 according to the following instructions, and the processor 801 will run the application programs stored in the memory 802, thereby realizing various functions, as follows:

[0176] Acquire lane line information corresponding to the first target vehicle and first distance information between the first target vehicle and a plurality of second target vehicles;

[0177] Performing target screening on the plurality of second target vehicles based on the lane line information and the first distance information to obtain lane affiliation information of the plurality of third target vehicles;

[0178] Based on the lane attribution information and the lane line information, the environment model information corresponding to the first target vehicle is constructed.

[0179] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0180] To this end, the embodiment of the present application provides a computer-readable storage medium, which may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc. A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in any one of the environmental model construction methods provided in the embodiment of the present application. For example, the computer program can be loaded by the processor to execute the following steps:

[0181] Acquire lane line information corresponding to the first target vehicle and first distance information between the first target vehicle and a plurality of second target vehicles;

[0182] Performing target screening on the plurality of second target vehicles based on the lane line information and the first distance information to obtain lane affiliation information of the plurality of third target vehicles;

[0183] Based on the lane attribution information and the lane line information, the environment model information corresponding to the first target vehicle is constructed.

[0184] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the detailed description of other embodiments above, and will not be repeated here.

[0185] In specific implementation, the above units or structures can be implemented as independent entities, or can be arbitrarily combined to be implemented as the same or several entities. The specific implementation of the above units or structures can refer to the previous method embodiments, which will not be repeated here.

[0186] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0187] The above is a detailed introduction to an environmental model construction method, device, computer equipment and storage medium provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for constructing an environment model, characterized in that: include: Acquire lane line information corresponding to a first target vehicle and first distance information between the first target vehicle and a plurality of second target vehicles; Performing target screening on a plurality of the second target vehicles based on the lane line information and the first distance information to obtain lane affiliation information of a plurality of third target vehicles; Based on the lane attribution information and the lane line information, environmental model information corresponding to the first target vehicle is constructed.

2. The method according to claim 1, characterized in that The lane line information includes first lane line information corresponding to the first lane line and second lane line information corresponding to the second lane line, and acquiring the lane line information corresponding to the first target vehicle includes: Acquire a vehicle environment image corresponding to the first target vehicle, and perform lane line recognition on the vehicle environment image to obtain a lane line recognition result; the lane line recognition result includes a recognition state of the first lane line and a recognition state of the second lane line; When the recognition state of the first lane line is a valid state and the recognition state of the second lane line is an invalid state, acquiring the first lane line information from the lane line recognition result, and determining the second lane line information based on the first lane line information; When the recognition state of the first lane line is an invalid state and the recognition state of the second lane line is a valid state, acquiring the second lane line information from the lane line recognition result, and determining the first lane line information based on the second lane line information; When the recognition state of the first lane line and the recognition state of the second lane line are both invalid states, the first lane line information and the second lane line information are determined based on the linear velocity and angular velocity of the first target vehicle.

3. The method according to claim 2, characterized in that The determining the first lane line information and the second lane line information based on the linear velocity and angular velocity of the first target vehicle includes: Performing trajectory prediction based on the linear velocity and angular velocity of the first target vehicle to obtain a predicted trajectory point of the first target vehicle; According to the preset second distance information, the predicted trajectory point is shifted to the left to obtain a first discrete curve point, and according to the preset third distance information, the predicted trajectory point is shifted to the right to obtain a second discrete curve point; The first discrete curve point and the second discrete curve point are respectively fitted to obtain the first lane line information and the second lane line information.

4. The method according to claim 1, characterized in that The target screening of the plurality of second target vehicles based on the lane line information and the first distance information to obtain lane affiliation information of the plurality of third target vehicles includes: Screening the plurality of second target vehicles based on the first distance information to obtain a plurality of fourth target vehicles; Based on the position information and width of each of the fourth target vehicles, determining the first edge point position and the second edge point position corresponding to each of the fourth target vehicles; Determine lane affiliation information of each of the fourth target vehicles based on the first edge point position, the second edge point position and the lane line information; The plurality of fourth target vehicles are screened based on the lane affiliation information of each of the fourth target vehicles and the first distance information of each of the fourth target vehicles to obtain lane affiliation information of a plurality of third target vehicles.

5. The method according to claim 4, characterized in that The lane line information includes first lane line information corresponding to the first lane line and second lane line information corresponding to the second lane line, and the determining the lane affiliation information of each of the fourth target vehicles based on the first edge point position, the second edge point position and the lane line information includes: Based on the first edge point position, the second edge point position, the first lane line information, and the second lane line information, determining whether a first edge point corresponding to the first edge point position or a second edge point corresponding to the second edge point position is located between the first lane line and the second lane line; If the first edge point or the second edge point is located between the first lane line and the second lane line, determining the lane belonging information of the fourth target vehicle as the main lane; If neither the first edge point nor the second edge point is located between the first lane line and the second lane line, determining third lane line information corresponding to the third lane line and fourth lane line information corresponding to the fourth lane line based on the first lane line information and the second lane line information; Determine whether the first edge point and the second edge point are both located between the first lane line and the third lane line, or whether the first edge point and the second edge point are both located between the second lane line and the fourth lane line, based on the first edge point position, the second edge point position, the first lane line information, the second lane line information, the third lane line information, and the fourth lane line information; If the first edge point and the second edge point are both located between the first lane line and the third lane line, determining that the lane belonging information of the fourth target vehicle is the left lane; If the first edge point and the second edge point are both located between the second lane line and the fourth lane line, it is determined that the lane belonging information of the fourth target vehicle is the right lane.

6. The method according to claim 1, characterized in that The environment model information includes main lane information and behavior category information of a plurality of third target vehicles, and the lane line information includes first lane line information corresponding to the first lane line and second lane line information corresponding to the second lane line; The step of constructing environment model information corresponding to the first target vehicle based on the lane attribution information and the lane line information includes: Determine main lane information corresponding to the first target vehicle based on the first lane line information and the second lane line information; Based on the first lane line information, the second lane line information and the lane attribution information, behavior category information of the plurality of third target vehicles is determined.

7. The method according to claim 6, characterized in that The determining, based on the first lane line information, the second lane line information and the lane attribution information, behavior category information of the plurality of third target vehicles comprises: For any third target vehicle among the plurality of third target vehicles, determining fourth distance information between the third target vehicle and the first lane line based on the first lane line information and determining fifth distance information between the third target vehicle and the second lane line based on the second lane line information; If the lane affiliation information of the third target vehicle is the main lane, the distance value corresponding to the fourth distance information is greater than the preset first distance threshold, and the distance value corresponding to the fifth distance information is greater than the preset second distance threshold, it is determined that the behavior category information of the third target vehicle is the first behavior category; If the lane affiliation information of the third target vehicle is a main lane, the distance value corresponding to the fourth distance information is less than or equal to the first distance threshold, and the driving speed of the third target vehicle is greater than the driving speed of the first target vehicle, the behavior category information of the third target vehicle is determined based on the vehicle heading angle of the third target vehicle and the lane heading angle of the first lane line; If the lane affiliation information of the third target vehicle is a main lane, the distance value corresponding to the fifth distance information is less than or equal to the second distance threshold, and the driving speed of the third target vehicle is greater than the driving speed of the first target vehicle, the behavior category information of the third target vehicle is determined based on the vehicle heading angle of the third target vehicle and the lane heading angle of the second lane line; If the lane affiliation information of the third target vehicle is the left lane or the right lane and the distance value corresponding to the fourth distance information is less than the preset third distance threshold, or the lane affiliation information of the third target vehicle is the left lane or the right lane and the distance value corresponding to the fifth distance information is less than the preset fourth distance threshold, determine that the behavior category information of the third target vehicle is the second behavior category; If the lane affiliation information of the third target vehicle is the left lane or the right lane, the distance value corresponding to the fourth distance information is greater than or equal to the third distance threshold, and the distance value corresponding to the fifth distance information is greater than or equal to the fourth distance threshold, the behavior category information of the third target vehicle is determined based on the driving speed of the third target vehicle and the driving speed of the first target vehicle.

8. An environment model building device, characterized in that: include: An information acquisition module, used to acquire lane line information corresponding to a first target vehicle and first distance information between the first target vehicle and a plurality of second target vehicles; An information determination module, configured to perform target screening on a plurality of second target vehicles based on the lane line information and the first distance information, and obtain lane attribution information of a plurality of third target vehicles; A model building module is used to build environment model information corresponding to the first target vehicle based on the lane attribution information and the lane line information.

9. A computer device, characterized in that: The computer device comprises: one or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the environment model building method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in the environmental model building method according to any one of claims 1 to 7.

Images