CN117284300A

CN117284300A - Road model generation method and device, electronic equipment and storage medium

Info

Publication number: CN117284300A
Application number: CN202210689265.1A
Authority: CN
Inventors: 卢二松; 李国栋; 王君银; 常仕伟; 王天培; 甄龙豹
Original assignee: Haomo Zhixing Technology Co Ltd
Current assignee: Haomo Zhixing Technology Co Ltd
Priority date: 2022-06-17
Filing date: 2022-06-17
Publication date: 2023-12-26

Abstract

The embodiment of the invention provides a method, a device, electronic equipment and a storage medium for generating a road model, wherein the method comprises the following steps: acquiring road detection information at the current moment; judging whether a preset storage condition is met or not according to the interested vehicle at the current moment; judging whether the interested vehicles recorded in the cache space meet preset loss conditions or not according to the interested vehicles at the current moment; if the preset loss condition is met, setting loss record information for the interested vehicle recorded in the cache space; screening target vehicles according to the missing record information and the track point number of the interested vehicles stored in the cache space; and generating a road model by adopting the track points of the target vehicle. The target vehicles with less loss times and more track points are screened out through the loss condition of the interested vehicle and the number of the corresponding track points, so that the problem of inaccurate road model construction based on the historical track of the target vehicles is solved.

Description

Road model generation method and device, electronic equipment and storage medium

Technical Field

The present invention relates to the field of automatic driving technology, and in particular, to a method for generating a road model, a device for generating a road model, an electronic device, and a computer-readable storage medium.

Background

With the popularization of vehicles, the vehicle-mounted camera and the sensor are utilized to improve the distinguishing capability of the vehicle on objects on a road, so that the safety of an automatic driving technology is improved. By acquiring the road track, the automatic driving vehicle can accurately and safely run on the road.

In the prior art, in order to construct an accurate road model, the following methods are generally included: and calculating the curvature of the road according to the front wheel rotation angle and the yaw rate of the vehicle, predicting the track of the vehicle, constructing a road model based on the predicted track of the vehicle, constructing the road model based on the historical track of the moving target vehicle, or fusing the visual road track information based on the camera with map information to construct the road model. In some special scenes (no lane lines, lane changing of vehicles, turning at crossroads and the like), it is necessary to construct a real-time and accurate road model through the historical track of the moving target vehicle, so that the screening of the target vehicle determines the real-time performance and accuracy of the road model.

Disclosure of Invention

In view of the above problems, embodiments of the present invention have been made to provide a road model generation method, a road model generation apparatus, an electronic device, and a computer-readable storage medium that overcome or at least partially solve the above problems.

In order to solve the above problems, an embodiment of the present invention discloses a method for generating a road model, which includes:

acquiring road detection information at the current moment; the road detection information at the current moment comprises a vehicle of interest and track points of the vehicle of interest;

judging whether a preset storage condition is met or not according to the interested vehicle at the current moment;

if the preset storage condition is met, storing the track points of the vehicle of interest at the current moment into a cache space;

judging whether the interested vehicles recorded in the cache space meet preset loss conditions or not according to the interested vehicles at the current moment;

if the preset loss condition is met, setting loss record information for the interested vehicle recorded in the cache space;

screening target vehicles according to the lost record information and the track point number of the interested vehicles stored in the cache space;

and generating a road model by adopting the track points of the target vehicle.

Optionally, the determining, for the vehicle of interest at the current moment, whether the preset storage condition is met includes:

judging whether the vehicle of interest detected at the current moment is stored in a cache space or not;

If the vehicle of interest detected at the current moment is stored in the cache space and the coordinate difference between the current track point of the vehicle of interest and the track point detected last time is greater than a preset difference threshold, determining that the preset storage condition is met;

and if the interested vehicle detected at the current moment is not stored in the cache space and the idle cache space exists, determining that the preset storage condition is met.

Optionally, if the preset storage condition is met, storing the track point of the vehicle of interest at the current moment in the cache space, including:

if the vehicle of interest detected at the current moment is stored in the cache space, storing the track point of the vehicle of interest into the corresponding cache space;

if the interested vehicle detected at the current moment is not stored in the cache space, setting a corresponding cache space for the interested vehicle and storing the interested vehicle and the current track point of the interested vehicle.

Optionally, the determining, according to the vehicle of interest at the current time, whether the vehicle of interest recorded in the cache space meets a preset loss condition includes:

according to the interested vehicles at the current moment, judging whether the interested vehicles stored in the cache space are detected at the current moment;

And if the interested vehicle stored in the cache space is not detected currently, determining that the preset loss condition is met.

Optionally, the loss record information includes a number of losses, and if the preset loss condition is met, the step of setting the loss record information for the interested vehicle recorded in the cache space includes:

and if the preset loss condition is met and the number of track points of the interested vehicle recorded in the cache space is greater than a preset number threshold, adding one to the number of losses of the interested vehicle recorded in the cache space.

Optionally, the method further comprises:

and if the number of times of loss of the interested vehicle stored in the cache space is greater than a preset number of times threshold, the cache space of the interested vehicle is emptied and set to be in an idle state.

Optionally, the method further comprises:

and if the preset loss condition is met and the number of track points of the vehicle of interest recorded in the cache space is smaller than or equal to the preset number threshold, the cache space of the vehicle of interest is emptied and set to be in an idle state.

The embodiment of the invention also discloses a device for generating the road model, which comprises the following steps:

The information acquisition module is used for acquiring road detection information at the current moment; the road detection information at the current moment comprises a vehicle of interest and track points of the vehicle of interest;

the storage judging module is used for judging whether a preset storage condition is met or not according to the interested vehicle at the current moment;

the track storage module is used for storing track points of the vehicle of interest at the current moment into the cache space if the preset storage conditions are met;

the loss judging module is used for judging whether the interested vehicle recorded in the cache space meets the preset loss condition or not according to the interested vehicle at the current moment;

the loss setting module is used for setting loss record information for the interested vehicle recorded in the cache space if the preset loss condition is met;

the target screening module is used for screening target vehicles according to the lost record information and the track point number of the interested vehicles stored in the cache space;

and the road generation module is used for generating a road model by adopting the track points of the target vehicle.

Optionally, the storage judgment module includes:

the first judging submodule is used for judging whether the vehicle of interest detected at the current moment is stored in the cache space or not;

A first determining submodule, configured to determine that a preset storage condition is met if a vehicle of interest detected at a current moment is already stored in a cache space and a coordinate difference between a current track point of the vehicle of interest and a track point detected last time is greater than a preset difference threshold;

and the detection sub-module is used for determining that the preset storage condition is met if the interested vehicle detected at the current moment is not stored in the cache space and the idle cache space exists.

Optionally, the track storage module includes:

the storage sub-module is used for storing the track points of the interested vehicles into the corresponding cache space if the interested vehicles detected at the current moment are already stored in the cache space;

and the setting sub-module is used for setting a corresponding cache space for the interested vehicle and storing the interested vehicle and the current track point of the interested vehicle if the interested vehicle detected at the current moment is not stored in the cache space.

Optionally, the loss determination module includes:

the second judging submodule is used for judging whether the interested vehicle stored in the cache space is detected at the current moment or not according to the interested vehicle at the current moment;

And the third determining submodule is used for determining that the preset loss condition is met if the interested vehicle stored in the cache space is not detected currently.

Optionally, the loss record information includes a number of losses, and the loss setting module includes:

and the loss number sub-module is used for adding one to the loss number of the interested vehicles recorded in the cache space if the preset loss condition is met and the track point number of the interested vehicles recorded in the cache space is larger than a preset number threshold value.

Optionally, the loss setting module further includes:

and the emptying sub-module is used for emptying the cache space of the interested vehicle and setting the cache space into an idle state if the lost times of the interested vehicle stored in the cache space is greater than a preset time threshold.

Optionally, the apparatus further comprises:

and the loss emptying module is used for emptying the cache space of the interested vehicle and setting the cache space into an idle state if the preset loss condition is met and the number of track points of the interested vehicle recorded in the cache space is smaller than or equal to the preset number threshold value.

The embodiment of the invention also discloses electronic equipment, which comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;

The memory is used for storing a computer program;

the processor is configured to implement the method according to the embodiment of the present invention when executing the program stored in the memory.

Embodiments of the invention also disclose one or more computer-readable media having instructions stored thereon, which when executed by one or more processors, cause the processors to perform the methods described in the embodiments of the invention.

The embodiment of the invention has the following advantages:

in the embodiment of the invention, road detection information at the current moment is acquired; storing track points of the interested vehicles meeting preset storage conditions into a cache space by detecting the interested vehicles at the current moment; acquiring lost record information of the interested vehicle recorded in the cache space according to the interested vehicle at the current moment; screening target vehicles according to the missing record information and the track point number of the interested vehicles stored in the cache space; and generating a road model by adopting the track points of the target vehicle. In the embodiment of the invention, the target vehicles with less loss times and more track points are screened out by the loss condition of the interested vehicle and the number of the corresponding track points, and the problems of the target vehicles with less loss, frequent change and fewer track points can be solved, thereby solving the problem of inaccurate road model construction based on the historical track of the target vehicles.

Drawings

FIG. 1 is a schematic diagram of a vehicle hardware arrangement provided by an embodiment of the present invention;

FIG. 2 is a flow chart of an assisted driving system according to an embodiment of the present invention;

FIG. 3 is a flowchart of steps of a method for generating a road model according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of constructing a road model according to an embodiment of the present invention;

FIG. 5 is a block diagram of a ring memory provided by an embodiment of the present invention;

FIG. 6 is a flowchart of a method for generating a road model according to an embodiment of the present invention;

FIG. 7 is a flowchart showing the steps of loss determination and storage determination according to an embodiment of the present invention;

fig. 8 is a block diagram of a road model generating device according to an embodiment of the present invention.

Detailed Description

In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.

In the process of automatic driving, due to some special scenes on a road, such as no lane line, lane change of a vehicle, turning at an intersection and the like, a road model needs to be built through the historical track of a target vehicle, so that the vehicle driven automatically can run according to the built road model.

On the road, the moving object vehicles are frequently lost and appear, and the track points of the moving object vehicles are relatively few, so that the accuracy of obtaining the road model is reduced.

One of the core ideas of the embodiment of the invention is that road detection information is acquired, and a target vehicle is screened according to the stored loss record information and the number of track points to generate a road model, wherein the loss record information is used for detecting whether a stored vehicle of interest is lost in real time.

The road detection information is obtained depending on the hardware arrangement of the own vehicle, and the hardware arrangement of the own vehicle is described below with reference to fig. 1, which is a schematic diagram of a hardware arrangement of the own vehicle according to an embodiment of the invention. The hardware arrangement of the target vehicle is the same as that of a vehicle that can be own. The vehicle hardware arrangement may include:

(1) The image pickup unit 1 provides lane lines and vehicle information within a certain range in front of and behind the current vehicle position.

(2) The radar unit 2 is used for detecting and extracting obstacle information around an autonomous vehicle, and preferably all-weather sensor detection equipment is selected to avoid unstable object target detection caused by rain, snow, fog, illumination and the like, the radar unit 2 is not limited to the current installation position but also limited to the current number, radar sensors (laser radar or millimeter wave radar equipment and the like) and vision sensors can be arranged in front of and at the side of the vehicle to improve the object detection accuracy, and radar equipment can be installed at two left and right corners in front of the vehicle in the same way, and the conditions of false detection, missed detection and the like of the object target are reduced through equipment redundancy.

(3) The ADAS (Advanced Driver Assistance System: advanced driver assistance system) unit 3 is configured to receive different sensor information and send control information to the vehicle, and the ADAS unit 3 is also configured to store the motion trail of a target vehicle screened from the vehicles of interest in real time.

In order to facilitate accurate construction of the road model, thereby timely and accurate selection of the target, meeting the requirements of the planning control function, the target vehicle may further comprise a driving assistance system, wherein the driving assistance system is as shown with reference to fig. 2. The following description will be given taking an auxiliary driving system as an example, and the functions of the auxiliary driving system may include:

(1) Vehicle Camera (Camera): the camera mainly comprises an internal view camera, a rear view camera, a front camera, a side view camera, a surrounding view camera and the like, and can be used for presenting video and audio in real time.

(2) Vehicle radar, laser, etc. (Lidar): is a mobile three-dimensional laser scanning system which can be used for constructing road models in longer and more distant ranges.

(3) High precision map, navigation positioning (EHR): the method is used for accurately and comprehensively displaying road characteristics, has higher real-time requirement, is a characteristic of remarkable high-precision map nozzles, and is also used for recording specific details of driving behaviors, including typical driving behaviors, optimal acceleration points and braking points, road condition complexity, labels of signal receiving conditions of different road segments and the like.

(4) Target fusion and road fusion: the vehicle data fusion device is used for fusing vehicle data and road data acquired by the vehicle-mounted camera, the radar and the like through the sensor.

(5) Road model: and constructing a road model by updating the acquired road information and the target vehicle in real time.

(6) And (3) target selection: for updating the target vehicle in real time while the road is being traveled.

(7) Planning control: for planning and controlling the travel of the own vehicle according to the target vehicle and the road information.

(8) Vehicle: and the control signal is used for receiving the planning control in real time and sending the vehicle information to the road model in real time.

Referring to fig. 3, a step flowchart of a method for generating a road model according to an embodiment of the present invention is shown, where the method specifically may include the following steps:

step 301, obtaining road detection information at the current moment; the road detection information at the current moment comprises a vehicle of interest and track points of the vehicle of interest;

in the embodiment of the invention, the road detection information at the current moment can be acquired through the sensor of the vehicle, and the road detection information at the current moment can be acquired through the image capturing unit and the radar unit by way of example. The road detection information at the present time may include a vehicle of interest and a track point of the vehicle of interest within a certain range from the front and rear of the vehicle. The road detection information also includes, for example, a lane line of the current road, and obstacle information of the vehicle on the current road, etc., and specifically, may be determined according to actual conditions, to which the embodiment of the present invention is not limited.

Step 302, judging whether a preset storage condition is met or not according to the interested vehicle at the current moment;

in the embodiment of the invention, whether the vehicle of interest at the current moment meets the preset storage condition is detected to determine whether the track point corresponding to the vehicle of interest at the current moment is stored in the corresponding cache space. The preset storage condition can be used for judging whether the vehicle of interest detected at the current moment needs to be stored or not.

Specifically, whether the preset storage condition is satisfied may be determined according to the storage condition of the cache space detected at the current time and the coordinate difference between the current track point of the vehicle of interest and the track point detected last time. The storage condition of the buffer space may be whether the vehicle of interest and the track point of the vehicle of interest are stored.

In one embodiment of the present invention, the step 302 may include the following substeps S11-S13:

step S11, judging whether the vehicle of interest detected at the current moment is stored in a cache space or not;

step S12, if the vehicle of interest detected at the current moment is stored in the cache space and the coordinate difference between the current track point of the vehicle of interest and the track point detected last time is greater than a preset difference threshold, determining that the preset storage condition is met;

And S13, if the vehicle of interest detected at the current moment is not stored in the cache space and an idle cache space exists, determining that the preset storage condition is met.

In the embodiment of the invention, if the vehicle of interest at the current moment is already stored in the cache space and the coordinate difference between the last track point and the current track point of the vehicle of interest is greater than the preset difference threshold, the preset storage condition is determined to be met, wherein the magnitude of the preset difference threshold can be adjusted according to the speed of the vehicle of interest. For example, the speed of the vehicle of interest is proportional to a preset difference threshold, e.g., the larger the speed of the vehicle of interest, the larger the preset difference threshold, the magnitude of the preset difference threshold may be adjusted in real time, which is not limited by embodiments of the present invention.

If the vehicle of interest at the current moment is already stored in the cache space and the coordinate difference value between the last track point and the current track point of the vehicle of interest is smaller than or equal to a preset difference value threshold, determining that the preset storage condition is not met.

If the interested vehicle corresponding to the current moment is not stored, detecting whether other idle cache spaces exist, and if so, determining that the preset storage condition is met. Specifically, the number of the buffer spaces can be set according to actual requirements, and those skilled in the art are not limited herein.

In the embodiment of the invention, if no free cache space exists, judging whether a free storage position exists in the cache space which is used for storing other interested vehicles, and if the free storage position exists in the cache space which is used for storing other interested vehicles, determining that a preset storage condition is met; if no free storage locations exist in the cache space already used for storing other interested vehicles, determining that the preset storage condition is not met.

Step 303, if the preset storage condition is met, storing the track point of the vehicle of interest at the current moment into a cache space;

for example, a plurality of cache spaces may be pre-allocated to store vehicles of interest and track points; when a newly detected vehicle of interest needs to be stored, a buffer space can be selected to establish a corresponding relation with the vehicle of interest. For example, an ID identifier is assigned to the vehicle of interest, and the ID identifier of the vehicle of interest is stored in the buffer space to establish a correspondence.

In one embodiment of the present invention, the step 303 may include the following substeps S21 to S22:

step S21, if the vehicle of interest detected at the current moment is stored in the cache space, storing the track point of the vehicle of interest in the corresponding cache space;

And S22, if the vehicle of interest detected at the current moment is not stored in the cache space, setting a corresponding cache space for the vehicle of interest and storing the vehicle of interest and the current track point of the vehicle of interest.

In an embodiment of the present invention, whether the vehicle of interest is stored may be checked by whether the own vehicle stores an ID identification of the vehicle of interest. And the track points of the interested vehicles comprise a starting point and a stopping point, and the starting point and the stopping point are respectively stored to the starting position and the stopping position of the buffer space of the corresponding interested vehicle. The number of track points corresponding to the vehicle of interest can be multiple, and the maximum range of the storage number is determined by the size of the corresponding cache space.

In the embodiment of the invention, the buffer space can be an annular memory, wherein the annular memory can comprise a set number of storage positions, and the annular memory is characterized in that stored data can be stored according to the sequence of the storage positions, and the sequential storage can be represented by numbers; when the ring memory is full, but currently there is data to be stored, the stored data of one storage position stored first is covered; in particular, the structure of the ring memory may refer to fig. 5.

In the embodiment of the invention, aiming at the interested vehicle meeting the storage condition, if the interested vehicle has a corresponding cache space, when determining to store the current track point of the interested vehicle, judging whether the corresponding cache space is full, if the corresponding cache space of the interested vehicle is full at the current moment, setting the ending position of the corresponding cache space of the interested vehicle as 1, and adding 1 to the starting position of the corresponding cache space. If the buffer space corresponding to the interested vehicle is not stored fully, the starting position is unchanged, and the ending position of the buffer space corresponding to the interested vehicle is increased by 1. For example, assuming that the number of bits that can be stored in the ring memory is 30, the order of the positions is 1 to 30, when the start position of the corresponding buffer space of the vehicle of interest is 1 and the end position is 30, if a track point is further stored, the start position of the corresponding buffer space of the vehicle of interest is 2 and the end position is 1. If the starting position of the corresponding buffer space of the interested vehicle is 1 and the ending position is 15, and a track point is needed to be stored, the track point needed to be stored is taken as the ending point, and the ending position is 16 and the starting position is unchanged.

If the corresponding cache space does not exist, setting the corresponding cache space for the interested vehicle to store the interested vehicle and the current track point corresponding to the interested vehicle.

In the embodiment of the invention, if no free cache space exists and the track points of the interested vehicle to be stored exist, a cache space with a smaller number of stored historical track points is preferentially selected for storage, and the starting point, the ending point and the number of corresponding track points of the interested vehicle are correspondingly updated.

Step 304, judging whether the interested vehicle recorded in the cache space meets a preset loss condition or not according to the interested vehicle at the current moment;

in the embodiment of the present invention, the vehicle of interest that has been recorded in the buffer space refers to a vehicle of interest that has been previously detected and is provided with a corresponding buffer space for storing the vehicle of interest and the track point. The preset loss condition is a condition for judging whether or not the vehicle of interest (vehicle of interest that has been detected previously) that has been recorded in the buffer space is currently lost.

In one embodiment of the present invention, the step 304 may include the following substeps S31-S32:

step S31, judging whether the interested vehicle stored in the cache space is detected at the current moment according to the interested vehicle at the current moment;

In the substep S32, if the vehicle of interest stored in the cache space is not currently detected, it is determined that the preset loss condition is satisfied.

In the embodiment of the invention, whether the interested vehicle is lost or not is judged by judging whether the interested vehicle stored in the cache space is detected at the current moment or not; if the interested vehicle stored in the cache space is not detected at the current moment, determining that the interested vehicle stored in the cache space is in a lost state.

Illustratively, assume that the vehicle ID identifications of interest that have been stored in the cache space are A, B, C, D, respectively; the vehicle of interest ID that can be detected within a certain range of the front and rear of the own vehicle at the present time is identified as a, that is, the vehicle of interest B, C, D at the present time is not detected, indicating that the vehicle of interest B, C, D at the present time is in a lost state.

Step 305, if the preset loss condition is met, setting loss record information for the interested vehicle recorded in the cache space;

in the embodiment of the present invention, the loss record information includes the number of losses, and the step 305 may include the following substeps S41 to S42:

in the substep S41, if the preset loss condition is satisfied and the number of track points of the vehicle of interest recorded in the cache space is greater than a preset number threshold, one is added to the number of losses of the vehicle of interest recorded in the cache space.

In the substep S42, if the number of lost vehicles of interest stored in the cache space is greater than the preset number threshold, the cache space of the vehicles of interest is emptied and set to be in an idle state.

In the embodiment of the present invention, if the vehicle of interest at the current moment is in a lost state, the lost record information is correspondingly set and the number of times of loss is recorded, and specifically, the lost record information may include the number of times of loss of the vehicle of interest, the time of loss of the vehicle of interest, and the like, which is not limited in the embodiment of the present invention.

Illustratively, the buffer space corresponding to the vehicle of interest stores the loss record information, the number of losses is recorded in the buffer space by the loss record information, and the number of losses is increased by one each time the vehicle of interest detects a loss. In particular, depending on the actual situation,

in the embodiment of the invention, if the number of times of losing the vehicle of interest stored in the cache space is greater than the preset number of times threshold, the vehicle of interest is unstable, and the cache space of the vehicle of interest is emptied and set to be in an idle state. Specifically, the magnitude of the preset number of times threshold is determined according to practical situations, and embodiments of the present invention are not limited herein.

Illustratively, assume that vehicle of interest a, vehicle of interest B, vehicle of interest C, and vehicle of interest D, have corresponding loss times of 1, 3, 5, 7, respectively; the method comprises the steps that at the current moment, an interested vehicle B, an interested vehicle C and an interested vehicle D meet preset loss conditions, and the number of track points of the interested vehicles recorded in a cache space is larger than a preset number threshold, so that the loss times of the interested vehicle A are kept unchanged at the moment; adding one to the number of times of losing the vehicle B of interest to be 4; adding one to the number of times of losing the vehicle C of interest to become 6; adding one to the number of times of losing the vehicle D of interest to become 8; and if the preset frequency threshold value is 7, the buffer space corresponding to the interested vehicle D is emptied and is set to be in an idle state.

In an embodiment of the present invention, the method may further include: and if the preset loss condition is met and the number of track points of the vehicle of interest recorded in the cache space is smaller than or equal to the preset number threshold, the cache space of the vehicle of interest is emptied and set to be in an idle state.

In the embodiment of the invention, if the vehicle of interest at the current moment is in a lost state, and the number of track points of the vehicle of interest recorded in the cache space is greater than a preset number threshold. The current track points of the interested vehicle are stored, so that the number of track points of the screened target vehicle is relatively large, and the road model formed by the track points is more accurate. Specifically, the magnitude of the preset number of thresholds may be determined according to practical situations, which is not limited by the embodiment of the present invention.

If the number of the historical track points of the interested vehicle is smaller than or equal to a preset number threshold, the corresponding buffer space of the interested vehicle is emptied and set to be in an idle state, so that the interested vehicle with a relatively large reserved track point number is realized.

Step 306, screening the target vehicles according to the lost record information and the track point number of the interested vehicles stored in the cache space;

in the embodiment of the invention, the lost record information and the track point number of a plurality of interested vehicles can be stored in a plurality of cache spaces, and the target vehicles can be screened according to the lost condition of the interested vehicles and the corresponding stored track point number. Specifically, the number of losses is inversely proportional to the stability of the corresponding vehicle of interest; the fewer losses may indicate that the vehicle of interest is more stable; the greater the number of losses, the more unstable the vehicle of interest may be. The storage quantity of the track points is in direct proportion to the stability of the motion track of the corresponding interested vehicle, and the more the storage quantity of the track points is, the more stable the motion track of the interested vehicle can be represented; the fewer the number of track points stored, the more unstable the motion track of the vehicle of interest can be represented, and therefore, the vehicle of interest with fewer losses and a greater number of track points stored can be selected as the target vehicle. For example, the number of target vehicles may be one or more;

Screening out target vehicles according to the number of lost times and the number of track points corresponding to the interested vehicles stored in the cache space; specifically, a score can be calculated for the number of times of loss and the number of track points of the vehicle of interest, and the target vehicle can be screened out through the score. For example, the vehicles of interest may be ranked according to their corresponding scores, and the target vehicles may be screened according to the ranking results. For another example, the score corresponding to the vehicle of interest may be compared with a score threshold, and the target vehicle may be screened based on the comparison. The score threshold may be set according to experimental data.

For example, the score corresponding to the vehicle of interest may be calculated by multiplying the number of lost times and the number of track points by the respective weights, and then adding the obtained scores.

And 307, generating a road model by adopting the track points of the target vehicle.

In the embodiment of the invention, the track points corresponding to the target vehicle are acquired according to the target vehicle, and the road model is generated by adopting the track points of the target vehicle. Specifically, how to generate the road model, first, fitting the track points of the target vehicle stored and updated in the buffer space to obtain fitting parameters, and then, performing filtering processing on the parameters based on track point fitting to generate the road model. In particular, how to fit the track points of the target vehicle and perform the filtering process after the fitting, which can be implemented by those skilled in the art according to the prior art, the embodiment of the present invention is not limited thereto.

In the embodiment of the invention, road detection information at the current moment is acquired; storing track points of the interested vehicles meeting preset storage conditions into a cache space by detecting the interested vehicles at the current moment; acquiring lost record information of the interested vehicle recorded in the cache space according to the interested vehicle at the current moment; screening target vehicles according to the missing record information and the track point number of the interested vehicles stored in the cache space; and generating a road model by adopting the track points of the target vehicle. In the embodiment of the invention, the target vehicles with less loss times and more track points are screened out through the loss condition of the interested vehicle and the corresponding track points, and the problems of the target vehicles with frequent loss and change and the fewer track points are solved, so that the problem of inaccurate road model construction based on the historical track of the target vehicles is solved.

It should be noted that, for simplicity of description, the method embodiments are shown as a series of acts, but it should be understood by those skilled in the art that the embodiments are not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred embodiments, and that the acts are not necessarily required by the embodiments of the invention.

In order to enable those skilled in the art to better understand the process of implementing vehicle control according to embodiments of the present invention, a complete example is described below. Referring to fig. 6, a flowchart of a method for generating a road model according to an embodiment of the present invention may specifically include the following steps:

in step 601, road detection information is acquired, the road detection information including a vehicle of interest and a track point of the vehicle of interest. Within a certain range in front of and behind the vehicle, the interested vehicle in running can be screened out according to the data acquired by the camera or the sensor.

Step 602, performing coordinate transformation on track points of a vehicle of interest; which is converted into coordinates based on a vehicle coordinate system as a reference. The detected coordinates of the locus of the vehicle of interest are relative to the vehicle coordinate system, which translates and rotates dynamically during the travel of the vehicle. The coordinates of the track points of the vehicle of interest detected at different locations will be based on different vehicle coordinate systems due to the change in the vehicle coordinate systems. The road model is generated by using the coordinates of the track points with respect to the same vehicle coordinate system, so that the vehicle coordinate system of the vehicle at a certain position can be selected as a reference. When the position of the vehicle is changed, the offset of the current vehicle coordinate system relative to the reference vehicle coordinate system can be calculated first, and then the coordinates of the current track point are converted according to the offset, so that the coordinates of the current track point relative to the reference vehicle coordinate system can be obtained.

Step 603, storing track points of the vehicle of interest; and creating a corresponding cache space for each vehicle of interest, and storing the track points of the vehicles of interest into the corresponding cache spaces. Typically, the amount of cache space is limited. The track points of the interested vehicles are correspondingly stored in the cache space, the track points comprise a starting point and a stopping point, and the starting point and the stopping point are respectively stored in the starting position and the stopping position of the cache space of the corresponding interested vehicle. The number of track points corresponding to the vehicle of interest can be multiple, and the maximum range of the storage number is determined by the size of the corresponding cache space.

Step 604, determining the existence of the vehicle of interest, which specifically includes: carrying out loss judgment on the vehicle of interest which is detected in advance, and judging whether to keep the historical track points of the vehicle of interest according to the result of the loss judgment; and performing storage judgment on the currently detected vehicle of interest, and storing the current track point of the currently detected vehicle of interest according to the result of the storage judgment. Thus, the target vehicle is screened out based on the presence determination. Specifically, please refer to fig. 7 for a step of performing the loss determination and the storage determination.

Step 605, after fitting the track points stored in the target vehicle, filtering the fitting parameters, thereby generating a road model.

Referring to fig. 7, a flowchart of a step of loss determination and storage determination according to an embodiment of the present invention may specifically include the following steps:

in step 701, it is determined whether the previously detected vehicle of interest is detected at the current time, and if the detected vehicle of interest is not detected at the current time, the previously detected vehicle of interest is considered to be lost at the current time.

Step 702, if the previously detected interested vehicle is not lost at the current time, the corresponding lost flag position is 0, the number of times of loss is 0, and the ID information of the interested vehicle stored at the corresponding position at the previous time is reserved, wherein the track point storage number, the start point and the end point storage positions are stored.

In step 703, if the previously detected vehicle of interest is lost at the current time, it is further determined whether the number of the historical track points already stored in the buffer space corresponding to the vehicle of interest is greater than a preset number threshold.

And step 704, if the number of the historical track points is smaller than the preset number threshold, clearing the data in the cache space corresponding to the interested vehicle, and not reserving the historical track points of the interested vehicle.

Step 705, if the number of the history track points is greater than the preset number threshold, reserving a buffer space which is created in advance and corresponds to the interested vehicle, and setting lost record information, and recording the lost times.

Step 706, determining whether the vehicle of interest at the current time has stored a history track point in the corresponding buffer space.

Step 707, if the interested vehicle at the current moment has stored the history track point in the corresponding buffer space, judging whether the coordinate difference between the current track point and the last history track point is greater than a preset difference threshold;

step 708, if the coordinate difference between the current track point and the last history track point is less than or equal to the preset difference threshold, the current track point is not stored, and the previously stored history track point is reserved;

step 709, if the coordinate difference between the current track point and the last history track point is greater than a preset difference threshold, determining whether the corresponding cache space is full;

step 710, if the buffer space corresponding to the interested vehicle at the current moment is not full, storing the current track points, wherein the starting position is unchanged, the ending position is added with 1, and the number of the stored track points is added with 1; the track points of the interested vehicles are correspondingly stored in the cache space, the track points comprise a starting point and a stopping point, and the starting point and the stopping point are respectively stored in the starting position and the stopping position of the cache space of the corresponding interested vehicle. The number of the track points stored correspondingly for the interested vehicle can be more than one, so that if the corresponding cache space of the interested vehicle is not full at the current moment, the new track points are stored in the corresponding cache space, the number of the stored track points is increased by 1, and the initial position is unchanged;

Step 711, if the cache space corresponding to the interested vehicle at the current moment is already stored fully, storing the current track point; because, in this example, the buffer space is a ring memory, and the number of bits in the corresponding storage position is a fixed value, in order to store a new track point, the end position is set as the first bit, the start position is added with 1, and the number of stored track points is unchanged;

step 712, if the interested vehicle at the current moment does not store the history track points in the corresponding cache space, judging whether an idle cache space exists;

in step 713, if there is free buffer space, the free buffer space is set to correspond to the currently newly detected vehicle of interest.

Step 714, if there is no free cache space, determining whether there is a free storage location in the cache space already used for storing other vehicles of interest;

if there are more free storage locations in the cache space that has been used to store other vehicles of interest, step 715 selects a cache space with more free storage locations from the cache spaces that have been used to store other vehicles of interest, and stores the currently newly detected trajectory point of the vehicle of interest in the cache space with more free storage locations.

If the buffer space used to store other interested vehicles does not have any free storage locations, step 716 is performed to discard the track points of the interested vehicles newly detected currently (i.e. there are more target storage currently, and the track points may be temporarily not stored).

Referring to fig. 8, a structural block diagram of a road model generating device provided by an embodiment of the present invention may specifically include the following modules:

an information obtaining module 801, configured to obtain road detection information at a current moment; the road detection information at the current moment comprises a vehicle of interest and track points of the vehicle of interest;

a storage judging module 802, configured to judge, for a vehicle of interest at a current moment, whether a preset storage condition is satisfied;

the track storage module 803 is configured to store a track point of the vehicle of interest at the current moment into a cache space if the preset storage condition is satisfied;

the loss judging module 804 is configured to judge, according to the vehicle of interest at the current time, whether the vehicle of interest recorded in the cache space meets a preset loss condition;

a loss setting module 805, configured to set loss record information for the interested vehicle recorded in the cache space if the preset loss condition is satisfied;

A target screening module 806, configured to screen a target vehicle according to the missing record information and the track point number of the vehicle of interest stored in the cache space;

and a road generating module 807, configured to generate a road model using the track points of the target vehicle.

In one embodiment, the storage determination module includes:

In one embodiment, the track storage module includes:

In one embodiment, the loss determination module includes:

In one embodiment, the loss record information includes a number of losses, and the loss setting module includes:

In one embodiment, the loss setting module further includes:

In one embodiment, the apparatus further comprises:

In summary, in the embodiment of the present invention, road detection information at the current moment is obtained; storing track points of the interested vehicles meeting preset storage conditions into a cache space by detecting the interested vehicles at the current moment; acquiring lost record information of the interested vehicle recorded in the cache space according to the interested vehicle at the current moment; screening target vehicles according to the missing record information and the track point number of the interested vehicles stored in the cache space; and generating a road model by adopting the track points of the target vehicle. In the embodiment of the invention, the target vehicles with less loss times and more track points are screened out by the loss condition of the interested vehicle and the number of the corresponding track points, so that the problems of the target vehicles that the target vehicles are lost, the change is frequent and the track points are fewer can be solved, and the problem of inaccurate road model construction based on the historical track of the target vehicles is solved.

For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.

The embodiment of the invention also provides electronic equipment, which comprises:

the road model generation method comprises a processor, a memory and a computer program which is stored in the memory and can run on the processor, wherein the computer program realizes the processes of the road model generation method embodiment when being executed by the processor, can achieve the same technical effects, and is not repeated here.

The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, realizes the processes of the above-mentioned embodiment of the road model generating method, and can achieve the same technical effects, so that repetition is avoided, and no further description is given here.

In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.

It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the invention may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the invention.

Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.

The above description of the method for generating a road model and the device for generating a road model provided by the present invention applies specific examples to illustrate the principles and embodiments of the present invention, and the description of the above examples is only used to help understand the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.

Claims

1. A method of generating a road model, the method comprising:

and generating a road model by adopting the track points of the target vehicle.

2. The method according to claim 1, wherein the determining whether the preset storage condition is satisfied for the vehicle of interest at the current time includes:

3. The method according to claim 2, wherein storing the track point of the vehicle of interest at the current time in the buffer space if the preset storage condition is satisfied comprises:

4. The method according to claim 1, wherein the determining whether the vehicle of interest recorded in the buffer space satisfies a preset loss condition according to the vehicle of interest at the current time, comprises:

5. The method according to claim 1, wherein the missing record information includes a number of losses, and the setting the missing record information for the vehicle of interest that has been recorded in the cache space if the preset loss condition is satisfied includes:

6. The method of claim 5, wherein the method further comprises:

7. The method according to claim 1, wherein the method further comprises:

8. A road model generation apparatus, characterized in that the apparatus comprises:

the track point storage module is used for storing track points of the vehicle of interest at the current moment into a cache space if the preset storage conditions are met;

9. An electronic device, comprising: a processor, a memory and a computer program stored on the memory and capable of running on the processor, which when executed by the processor performs the steps of the method according to any one of claims or 1-7.

10. A computer readable storage medium, characterized in that it has stored thereon a computer program which, when executed by a processor, implements the steps of the method according to any of claims 1-7.