CN114743395B

CN114743395B - Signal lamp detection method, device, equipment and medium

Info

Publication number: CN114743395B
Application number: CN202210279875.4A
Authority: CN
Inventors: 李丰军; 周剑光; 高列
Original assignee: China Automotive Innovation Co Ltd
Current assignee: China Automotive Innovation Co Ltd
Priority date: 2022-03-21
Filing date: 2022-03-21
Publication date: 2024-03-08
Anticipated expiration: 2042-03-21
Also published as: CN114743395A

Abstract

The application relates to a signal lamp detection method, a device, equipment and a medium, wherein by acquiring lane line information, signal lamp information and vehicle pose information, lane information of a target lane where a vehicle is located is acquired according to the vehicle pose information and the lane line information, so that more accurate lane information can be obtained; according to the pose information of the vehicle and the signal lamp information, determining target signal lamp information, wherein the target signal lamp information is information of a target signal lamp closest to the vehicle, and determining target sub-signal lamp information corresponding to lane information from at least one sub-signal lamp information corresponding to the target signal lamp information, so that the accuracy of the signal lamp information can be improved while the time delay of sensing signal lamp elements is reduced.

Description

Signal lamp detection method, device, equipment and medium

Technical Field

The present invention relates to the field of automatic driving technologies, and in particular, to a signal lamp detection method, device, equipment, and medium.

Background

The automatic driving core technical system is divided into perception, decision and execution. With the continuous development of autopilot technology, the perception module becomes particularly important as an "eye" of an autopilot car. Meanwhile, traffic elements such as lane lines, signal lamps and the like are taken as indispensable identification objects of a sensing module, can be correctly and quickly searched and identified, and can provide basis for later planning and control. In the related art, real-time image data can be collected through a front-view camera installed on an automatic driving vehicle, and signal lamp states are analyzed according to the real-time image data. However, by image-capturing real-time image data, it is susceptible to disturbance in rainy and snowy weather, and signal lamp information is not accurate enough.

Disclosure of Invention

In order to solve the technical problems, the invention provides a signal lamp detection method, a device, equipment and a medium, which can improve the accuracy of signal lamp information while reducing the time delay of sensing signal lamp elements.

According to a first aspect of an embodiment of the present disclosure, there is provided a signal lamp detection method, including:

acquiring lane line information, signal lamp information and vehicle pose information;

acquiring target lane information of a target lane where a vehicle is located according to the vehicle pose information and the lane line information;

determining target signal lamp information according to the vehicle pose information and the signal lamp information, wherein the target signal lamp information is information of a target signal lamp nearest to the vehicle;

and determining target sub-signal lamp information corresponding to the target lane information from the sub-signal lamp information corresponding to the target signal lamp information.

In one possible implementation manner, the lane line information includes lane stop line information corresponding to each of a plurality of lanes, and each lane stop line information includes first point set information of a plurality of points; the step of obtaining the target lane information of the target lane where the vehicle is located according to the vehicle pose information and the lane line information comprises the following steps:

Determining first target point information closest to the vehicle from the first point set information according to the vehicle pose information;

determining the target lane according to the first target point information;

and acquiring the target lane information of the target lane.

In one possible implementation manner, the lane line information includes structural information and second point set information of lane boundaries corresponding to lanes respectively; the structure information represents the position structure relation of the boundary line of each lane, and the second point set information represents the position relation of a plurality of points on the boundary line of each lane;

the obtaining the target lane information of the target lane where the vehicle is located according to the vehicle pose information and the lane line information comprises:

according to the pose information of the vehicle, the second point set information and the structure information, a second target point and a third target point which are nearest to the vehicle are respectively determined, wherein the second target point and the third target point are respectively points on the boundary lines of two adjacent lanes;

determining the target lane according to the second target point and the third target point;

and acquiring the target lane information of the target lane.

In one possible implementation manner, the determining target signal light information according to the vehicle pose information and the signal light information includes:

extracting the vehicle position information and the vehicle heading information from the vehicle pose information;

determining target signal lamp information closest to the vehicle within a preset yaw angle of the vehicle based on the vehicle position information, the vehicle course information and the signal lamp information; the preset yaw angle is a positive preset angle and a negative preset angle deviating from the heading.

In one possible implementation, the method further includes:

collecting point set information of a lane stop line in advance;

constructing multidimensional tree information corresponding to the lane stop line based on the point set information of the lane stop line;

the determining a first target point nearest to the vehicle according to the pose information of the vehicle and the point set information of the lane stop line comprises:

and based on the vehicle pose information, performing nearest neighbor search processing on the multidimensional tree information corresponding to the lane stop line to obtain the first target point nearest to the vehicle.

In one possible implementation, the method further includes:

The method comprises the steps of collecting point set information of a signal lamp in advance;

constructing multidimensional tree information corresponding to the signal lamp based on the point set information of the signal lamp;

the determining, based on the vehicle position information, the heading information, and the signal light information, target signal light information closest to the vehicle within a preset yaw angle of the vehicle includes:

based on the vehicle position information, multi-dimensional tree information in a preset yaw angle of the vehicle is screened out from the multi-dimensional tree information corresponding to the signal lamp;

and carrying out nearest neighbor search processing on the multidimensional tree information in the preset yaw angle of the vehicle to obtain the target signal lamp information.

In one possible implementation manner, the target signal lamp information includes corresponding relations between different lane identification information and sub signal lamp identification information, and sub signal lamp state information corresponding to different sub signal lamp identification information;

the matching of the target sub-signal lamp information corresponding to the lane information where the vehicle is located from the target signal lamp information comprises the following steps:

extracting the identification information of the lane where the vehicle is located from the lane information;

matching target sub-signal lamp identification information corresponding to the identification information of the lane where the vehicle is located from the corresponding relation;

And extracting target sub-signal lamp state information corresponding to the target sub-signal lamp identification information from the target signal lamp information.

In one possible implementation manner, after determining the target sub-signal lamp information corresponding to the lane information from the sub-signal lamp information corresponding to the target signal lamp information, the method further includes:

acquiring path planning information of the vehicle;

and carrying out automatic driving control on the vehicle based on the target sub-signal lamp information and the path planning information.

In one possible implementation manner, after determining the target sub-signal light information corresponding to the lane information from the at least one sub-signal light information corresponding to the target signal light information, the method further includes:

transmitting the target sub-signal lamp information to an associated vehicle of the vehicle so that the associated vehicle performs automatic driving control based on the target sub-signal lamp information and path planning information of the associated vehicle; the associated vehicle refers to a vehicle that is in the same lane as the vehicle.

According to a second aspect of embodiments of the present disclosure, there is provided a signal lamp detection apparatus, which may include:

The first information acquisition module is used for acquiring at least one lane line information, signal lamp information and vehicle pose information;

the second information acquisition module is used for acquiring lane information of a target lane where the vehicle is located according to the vehicle pose information and the at least one lane line information;

the target signal lamp information determining module is used for determining target signal lamp information according to the vehicle pose information and the signal lamp information, wherein the target signal lamp information is information of a target signal lamp nearest to the vehicle;

and the target sub-signal lamp information determining module is used for determining target sub-signal lamp information corresponding to the lane information from at least one piece of sub-signal lamp information corresponding to the target signal lamp information.

According to a third aspect of embodiments of the present disclosure, there is provided an electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the method of any of the first aspects above.

According to a fourth aspect of the disclosed embodiments, there is provided a computer readable storage medium, which when executed by a processor of an electronic device, causes the electronic device to perform the method of any of the first aspects of the disclosed embodiments.

According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product for causing a computer to perform the method according to any one of the first aspects of embodiments of the present disclosure.

By implementing the application, the method has the following beneficial effects:

according to the method and the device, the lane line information, the signal lamp information and the vehicle pose information are obtained, and the lane information of the target lane where the vehicle is located is obtained according to the vehicle pose information and the lane line information, so that more accurate lane information can be obtained; according to the pose information of the vehicle and the signal lamp information, determining target signal lamp information, wherein the target signal lamp information is information of a target signal lamp closest to the vehicle, and determining target sub-signal lamp information corresponding to lane information from at least one sub-signal lamp information corresponding to the target signal lamp information, so that the accuracy of the signal lamp information can be improved while the time delay of sensing signal lamp elements is reduced.

Drawings

In order to more clearly illustrate the technical solutions of the present application, the following description will briefly introduce the drawings that are needed in the embodiments or the description of the prior art, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic view of an implementation environment provided in an embodiment of the present application;

FIG. 2 is a flow chart illustrating a signal detection method according to an exemplary embodiment;

fig. 3 is a flowchart of a method for obtaining lane information of a target lane where a vehicle is located according to an embodiment of the present application;

fig. 4 is a schematic view of a lane line according to an embodiment of the present application;

fig. 5 is a schematic view of a lane line according to an embodiment of the present application;

fig. 6 is a flowchart of acquiring lane information of a target lane where a vehicle is located according to an embodiment of the present application;

fig. 7 is a flowchart for determining target signal light information according to vehicle pose information and signal light information according to an embodiment of the present application;

fig. 8 is a schematic diagram of determining target signal lamp information according to an embodiment of the present application;

fig. 9 is a flowchart of a signal lamp detection method according to an embodiment of the present application;

fig. 10 is a flowchart of a signal lamp detection method according to an embodiment of the present disclosure;

fig. 11 is a flowchart of a method for determining target sub-signal information corresponding to lane information from at least one sub-signal information corresponding to the target signal information according to an embodiment of the present application;

Fig. 12 is a diagram of a signal light detection device according to an embodiment of the present application;

fig. 13 is a block diagram of an electronic device for signal light detection according to an embodiment of the present application.

Detailed Description

In order to better understand the technical solutions in the present application, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

In order to implement the technical solution of the present application, more engineering technicians can easily understand and apply the present application, and the working principle of the present application will be further explained with reference to specific embodiments.

The application can be applied to automatic driving control of a vehicle, and particularly relates to a signal lamp detection method, a signal lamp detection device, signal lamp detection equipment and a signal lamp detection medium.

Referring to fig. 1, a schematic diagram of an implementation environment provided by an embodiment of the disclosure is shown, where the implementation environment may include:

at least one terminal 01 and at least one server 02. The at least one terminal 01 and the at least one server 02 may communicate data over a network.

In an alternative embodiment, the terminal 01 may be an executor of the signal light detection method. The terminal 01 may include, but is not limited to, vehicle-mounted terminals, smart phones, desktop computers, tablet computers, notebook computers, smart speakers, digital assistants, augmented Reality (AR)/Virtual Reality (VR) devices, smart wearable devices, and the like. The operating system running on terminal 01 may include, but is not limited to, an android system, an IOS system, linux, windows, unix, and the like. The server 02 may provide lane line information and traffic light information to the terminal 01. Optionally, the server 02 may be an independent physical server, or may be a server cluster or a distributed system formed by a plurality of physical servers, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs (Content Delivery Network, content delivery networks), and basic cloud computing services such as big data and artificial intelligence platforms.

In an alternative embodiment, the terminal 01 may provide the vehicle pose information to the server 02, and the terminal 01 may refer to an on-board terminal of the vehicle pose information. The server 02 may be an executor of the signal light detection method. Optionally, the server 02 may be an independent physical server, or may be a server cluster or a distributed system formed by a plurality of physical servers, and may also be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network servers, cloud communication middleware services, domain name services, security services, CDNs (Content DeliveryNetwork, content delivery networks), and basic cloud computing services such as big data and artificial intelligence platforms.

It should be noted that, a possible sequence of steps is shown in the following figures, and is not limited to the strict order of the sequence. Some steps may be performed in parallel without mutual dependency. User information (including, but not limited to, user device information, user personal information, user behavior information, etc.) referred to in this disclosure is information that is authorized by the user or sufficiently authorized by the parties.

Fig. 2 is a flow chart illustrating a signal light detection method according to an exemplary embodiment. As shown in fig. 2, the signal lamp detection method includes the steps of:

In step S201, lane line information, traffic light information, and vehicle pose information are acquired.

In this embodiment of the present disclosure, the lane line information may be at least one of a plurality of pieces of preset lane line information, and the preset lane line information may refer to information of a preset lane line, and may include, for example, identification information of the preset lane line. The preset lane line herein may refer to a lane line for forming a preset lane, for example, a lane stop line, a lane dividing line, and the like.

In one possible implementation, at least one preset lane line information within a preset range may be acquired as the lane line information. As one example, the at least one may be a preset number. The preset range may be a range with the vehicle as a center and the radius as a preset length, and the preset length is only required to be enough to acquire a sufficient amount of lane line information, which is not limited in the present disclosure.

Alternatively, when the high-precision map information includes lane line association information, the lane line information may be obtained by acquiring the high-precision map information. Specifically, after the high-precision map information is obtained, the lane line related information in the high-precision map information is extracted and integrated to obtain the lane line information.

In this embodiment of the present disclosure, the signal light information may be at least one of a plurality of signal light information, and the plurality of signal light information may refer to information of a plurality of signal lights, for example, may include identification information, status information, and the like of the plurality of signal lights, where the status information may include information about whether to allow traffic and second reading information.

In one possible implementation, a plurality of signal light information within a preset range may be acquired as the signal light information. As an example, the preset range may be a sector range formed by offsetting the yaw angle of the vehicle by a preset angle around the vehicle. The number of signal lamps acquired in this range may be a preset number.

Optionally, when the high-precision map information includes signal lamp related information, after the high-precision map information is obtained, the signal lamp related information in the high-precision map information may be extracted and integrated to obtain signal lamp information. It should be noted that, the high-precision map information is updated in real time, and according to the high-precision map information updated in real time, real-time signal lamp information can be obtained, so that timeliness of the signal lamp information in application is ensured.

In the embodiment of the present specification, the vehicle pose information may include position information and pose information of the vehicle. Specifically, the position information of the vehicle may be two-dimensional or three-dimensional vehicle coordinates, for example, the position information of the vehicle may be global satellite positioning data obtained by the vehicle using the positioning module, and the global satellite positioning data may be longitude and latitude information of the vehicle. The attitude information of the vehicle may be heading angle information of the vehicle, and may characterize a traveling direction of the vehicle.

In step S202, lane information of a target lane in which the vehicle is located is acquired according to the vehicle pose information and the lane line information.

In the embodiment of the present disclosure, the lane information of the target lane may refer to lane information corresponding to a lane in which the vehicle is located, and may be, for example, lane identification information of the target lane, a driving direction of the target lane, and the like. The lane line information corresponding to the vehicle can be determined according to the vehicle pose information and the lane line information, and the target lane where the vehicle is located is determined based on the lane line information corresponding to the vehicle, so that the lane information is correspondingly acquired.

In some exemplary embodiments, the lane line information may include lane stop line information corresponding to each of the plurality of lanes, and each lane stop line information may include first point set information of the plurality of points. The first point set information may be position information of a plurality of points, such as latitude and longitude information or abscissa information in a self-built coordinate system. On this basis, as shown in fig. 3, step S202 may include:

In step S301, first target point information closest to the vehicle is determined from the first point set information according to the vehicle pose information.

In the embodiment of the present specification, the distances of the plurality of points in the vehicle and the first point set information may be determined based on the vehicle pose information and the first point set information, respectively. First target point information closest to the vehicle is determined from the distances of the vehicle and the plurality of points.

In step S302, a target lane is determined from the first target point information.

In the embodiment of the present disclosure, based on the correspondence between the plurality of points in the first point set information and the lanes, after the first target point information is obtained, the target lanes may be searched in a matching manner. Specifically, the correspondence between the plurality of points in the first point set information and the lane may be in a form of mapping the position information of the plurality of points with the lane identification information.

In step S303, lane information of a target lane is acquired.

In the embodiment of the present specification, the lane information of the target lane may be lane identification information of the target lane.

The vehicle pose information is the two-dimensional coordinates (x ₁₄ ，y _m ) The three lanes are left-turn lanes L shown in fig. 4, respectively ₁ Straight-going lane L ₂ And right turn lane L ₃ For example, the three lanes respectively correspond to lane stop line information L _l1 Lane stop line information L _l2 And lane stop line L _l3 The lane line information may be as shown in the following table:

TABLE 1

Where x represents the coordinates of the vehicle or point in the x direction and y represents the coordinates of the vehicle or point in the y direction. According to the two-dimensional coordinates (x ₁₄ ，y _m ) And first point set information (including points (x ₁₄ ，y ₁₄ ) A lane stop line identification information corresponding to the vehicle can be determined as L _l1 Based on lane stop line identification information-L corresponding to the vehicle _l1 It can be determined that the lane identification information corresponding to the vehicle is L ₁ I.e. lane information of the target lane in which the vehicle is located.

By acquiring lane stop line information corresponding to each of a plurality of lanes, each lane stop line information comprises first point set information of a plurality of points, first target point information closest to the vehicle can be determined from the first point set information according to vehicle pose information, and lane information of a target lane where the vehicle is located can be accurately obtained at a position far from the lane stop line.

In some exemplary embodiments, the lane line information may include structural information of lane boundaries and second point set information. The point set information of the lane boundaries can represent the position structure relationship of each lane boundary, and the second point set information can represent the position relationship of a plurality of points on each lane boundary, such as longitude and latitude information or abscissa information in a self-built coordinate system. In particular, the lane lines may include lane lines between adjacent two lanes, as well as lane lines between motor lanes and non-motor lanes. The structural information of lane boundaries refers to the positional relationship between different lane boundaries, and the structural information can characterize the mapping relationship between lane boundaries and lanes, for example, in fig. 5, there are lane boundaries L respectively ₄₁ Lane dividing line L ₄₂ Lane dividing line L ₅₁ Lane boundary line L ₅₂ The structure information of the lane dividing line and the second point set information may be as follows:

from the structural information of the lane line and the second point set information, the lane line L ₄₁ Lane boundary line L ₄₂ Constituting the lane L ₄ Lane dividing line L ₄₂ Lane boundary line L ₅₁ Constituting the lane L ₅ Lane dividing line L ₅₁ Lane boundary line L ₅₂ Constituting the lane L ₆ Lane L ₄ And lane L ₅ All include lane dividing lines L ₄₂ Lanes L5 and L ₆ All include lane dividing lines L ₅₁ . Here, a way of acquiring the structure information of the lane departure line and the second point set information in combination is exemplified, that is, the structure information of the lane departure line and the second point set information can be acquired from the above-described information table. In addition, the structure information of the lane line and the second point set information may be divided into two parts, and the structure information of the lane line may be obtained from the information table 1 and the second point set information of the lane line may be obtained from the information table 2. The lane line information can be deployed according to actual conditions.

Specifically, when the lane line information includes the structure information and the second point set information of the lane boundary, as shown in fig. 6, the obtaining the lane information of the target lane in which the vehicle is located according to the vehicle pose information and the lane line information may include the steps of:

In step S601, a second target point and a third target point closest to the vehicle are determined based on the vehicle pose information, the second point set information, and the structure information, respectively.

In the embodiment of the present disclosure, the second target point and the third target point are points on the boundary line of two adjacent lanes, respectively.

Optionally, according to the pose information of the vehicle, the second point set information and the structure information, a second target point and a third target point closest to the vehicle are respectively determined, and according to the pose information of the vehicle and the second point set information, the second target point closest to the vehicle can be determined; determining a lane boundary corresponding to the second target point according to the second point set information and the structure information, and marking the lane boundary as a lane boundary L _M The method comprises the steps of carrying out a first treatment on the surface of the Lane dividing line L _M And determining a third target point closest to the vehicle from points other than the upper full-quantity point.

Alternatively, the second target point and the third target point closest to the vehicle are determined according to the vehicle pose information, the second point set information and the structure information, respectively, and the point closest to the vehicle on each lane boundary line may be determined from lane boundaries near the vehicle according to the vehicle pose information and the second point set information, for example, the point D on four different lane boundary lines is determined from lane boundary lines within a preset range of the vehicle ₁ 、D ₂ 、D ₃ And D ₄ The four points are all the points closest to the vehicle on the lane boundaries; based on point D ₁ 、D ₂ 、D ₃ 、D ₄ The distance to the vehicle may be determined for each of the first and second short points, i.e. the second and third target points, ordered by distance to the vehicle.

In step S602, a target lane is determined from the second target point and the third target point.

In the embodiment of the present disclosure, based on the structural information of the lane dividing line, the target lane formed by the lane dividing line corresponding to the second target point and the third target point may be determined.

In this embodiment of the present disclosure, if the closest point to the vehicle on the boundary line of two lanes is determined, and the two points are not points on the boundary line of adjacent lanes, the pose information of the vehicle may be obtained again, and the steps of determining the second target point and the third target point are repeated until the second target point and the third target point are obtained. If the vehicle pose information is repeatedly acquired, determining that the times of the steps of the second target point and the third target point reach the preset times, and generating an error prompt instruction so as to avoid the safety problem caused by vehicle positioning or lane line information errors.

In step S603, lane information of a target lane is acquired.

In the embodiment of the present specification, the structural information of the lane dividing line may include lane identification information. After the target lane is determined, lane identification information of the target lane, that is, lane information of the target lane, may be extracted from the structural information of the lane dividing line.

According to the embodiment, the second target point and the third target point can be accurately obtained according to the vehicle pose information, the second point set information and the structural information; according to the second target point and the third target point, the target lane is determined, so that the determination processing of the target lane corresponding to the vehicle is not influenced by factors such as rainy and snowy weather, night and the like, and the target lane can be accurately determined at any distance from the intersection.

In step S203, target traffic light information is determined from the vehicle pose information and the traffic light information.

In the embodiment of the present disclosure, the target signal light information may be information of a target signal light nearest to the vehicle. The target signal lamp closest to the vehicle may be in the traveling direction of the vehicle, so as to avoid the signal lamp behind the vehicle from interfering with the signal lamp detection process of the vehicle. Specifically, the vehicle pose information may include position information and pose information of the vehicle, wherein the pose information may characterize a traveling direction of the vehicle. By the position information and the posture information of the vehicle, it is possible to determine the target signal lamp nearest to the vehicle in the traveling direction of the vehicle and obtain the target signal lamp information. The target signal light information may be identification information of the target signal light.

In step S204, target sub-signal light information corresponding to the lane information is determined from at least one sub-signal light information corresponding to the target signal light information.

In this embodiment of the present disclosure, the sub-signal light information may refer to information of sub-signal lights in signal lights, where signal lights with sub-signal lights may indicate whether traffic is allowed by lane division at the same time, for example, signal lights with a left turn indicator light, a straight run indicator light, and a right turn indicator light may indicate that a left turn lane green light remains 15 seconds, a straight run lane red light remains 55 seconds, and a right turn lane red light at one time.

Optionally, the signal light information may include signal light identification information, sub signal light identification information, signal light status information, sub signal light status information, and signal light to sub signal light relationship information. Specifically, the sub-signal lamp information may include identification information of at least one sub-signal lamp, whether the sub-signal lamp allows traffic information, sub-signal lamp second reading information, and the like. The determining of the target sub-signal lamp information corresponding to the lane information from the at least one sub-signal lamp information corresponding to the target signal lamp information may be extracting target sub-signal lamp identification information and sub-signal lamp state information corresponding to the lane information from the target signal lamp information.

Alternatively, the signal light information may include signal light identification information and signal light status information. After the target signal lamp information is determined, at least one piece of sub signal lamp information corresponding to the target signal lamp information can be obtained according to the corresponding relation between the signal lamp and the sub signal lamp. Sub-signal lamp status information and signal lamp-to-sub-signal lamp relationship information.

According to the embodiment, the lane line information, the signal lamp information and the vehicle pose information are obtained, and the lane information of the target lane where the vehicle is located is obtained according to the vehicle pose information and the lane line information, so that more accurate lane information can be obtained; according to the pose information of the vehicle and the signal lamp information, determining target signal lamp information, wherein the target signal lamp information is information of a target signal lamp closest to the vehicle, and determining target sub-signal lamp information corresponding to lane information from at least one sub-signal lamp information corresponding to the target signal lamp information, so that the accuracy of the signal lamp information can be improved while the time delay of sensing signal lamp elements is reduced.

In some exemplary embodiments, as shown in fig. 7, determining the target signal information from the vehicle pose information and the signal information may include:

In step S701, vehicle position information and vehicle heading information are extracted from vehicle pose information.

In this embodiment of the present disclosure, the heading information of the vehicle may be heading information measured by a gyroscope in the vehicle, which characterizes a driving direction of the vehicle.

In step S702, target traffic light information closest to the vehicle within a preset yaw angle of the vehicle is determined based on the vehicle position information, the vehicle heading information, and the traffic light information.

In the embodiment of the present disclosure, the preset yaw angle may be a positive or negative preset angle deviating from the heading, as shown in fig. 8, taking the yaw angle as positive or negative α as an example, the vehicle forms a signal lamp S nearest to the vehicle in a sector area formed by the positive or negative α ₁ Is the information of the target signal lamp.

According to the embodiment, the vehicle position information and the vehicle heading information are extracted from the vehicle pose information, the signal lamp information closest to the vehicle in the preset yaw angle of the vehicle is determined based on the vehicle position information, the vehicle heading information and the signal lamp information, the accuracy of the signal lamp information corresponding to the vehicle can be improved, the target signal lamp information can be determined and processed at any distance from the intersection, and the method is wide in application scene.

In some exemplary embodiments, in a case where first target point information closest to the vehicle is determined from the first point set information according to the vehicle pose information, and a target lane is determined according to the first target point information, thereby acquiring lane information of the target lane, as shown in fig. 9, the method may further include:

in step S901, point set information of a lane stop line is acquired in advance.

In step S902, multi-dimensional tree information corresponding to the lane stop line is constructed based on the point set information of the lane stop line.

In the embodiment of the present disclosure, index information of the lane stop line and the point set information may be constructed, and multidimensional tree information corresponding to the lane stop line may be constructed in combination with a structural relationship of the lane stop line.

Based on this, step S301, determining, from the first set of point information, first target point information closest to the vehicle according to the vehicle pose information may include the steps of:

in step S903, based on the vehicle pose information, nearest neighbor search processing is performed on the multi-dimensional tree information corresponding to the lane stop line, so as to obtain a first target point nearest to the vehicle.

In the embodiment of the present disclosure, after the multidimensional tree information corresponding to the lane stop line is constructed, an area having a certain range from the vehicle may be determined based on the vehicle pose information and the multidimensional tree information, and the first target point closest to the vehicle may be further determined under the area.

According to the embodiment, the multi-dimensional tree information corresponding to the lane stop line is constructed, the nearest neighbor search processing is carried out on the multi-dimensional tree information corresponding to the lane stop line based on the vehicle pose information, the lane stop line and the point set information can be stored conveniently, and a first target point nearest to the vehicle can be obtained quickly through gradual search when the vehicle is used.

In some exemplary embodiments, as shown in fig. 10, the method may further include:

in step S1001, point set information of the signal lamps is acquired in advance.

In the embodiment of the present specification, the point set information of the signal lamp may refer to position information of points characterizing the signal lamp. The point set information of the signal lamp may include identification information of the signal lamp, position information of points characterizing the signal lamp, identification information of the sub signal lamp, and status information of the sub signal lamp.

In step S1002, multidimensional tree information corresponding to the signal lamp is constructed based on the point set information of the signal lamp.

In the embodiment of the specification, index information of the signal lamp and the signal lamp state can be established according to the identification information of the signal lamp and the position information of the point representing the signal lamp. And generating multidimensional tree information according to the index information of the signal lamp and the signal lamp state. Wherein different dimensions of the multi-dimensional tree information may characterize different types of index information, e.g., one dimension of the multi-dimensional tree information may characterize index information of identification information of the signal lamp and position information of a point of the signal lamp, and another dimension may characterize index information of the signal lamp and signal lamp state.

Based on this, step S702 may include, based on the vehicle position information, heading information, and signal information, determining target signal information closest to the vehicle within a preset yaw angle of the vehicle:

in step S1003, based on the vehicle position information, multi-dimensional tree information within a preset yaw angle of the vehicle is selected from the multi-dimensional tree information corresponding to the traffic lights.

In the embodiment of the present disclosure, after the multidimensional tree information corresponding to the signal lamp is constructed, the multidimensional tree information corresponding to the signal lamp in the preset yaw angle range of the vehicle may be screened from the multidimensional tree information corresponding to the signal lamp based on the vehicle position information and the heading information.

In step S1004, nearest neighbor search processing is performed on the multidimensional tree information within the preset yaw angle of the vehicle, so as to obtain target signal lamp information.

In the embodiment of the present disclosure, matching with the vehicle position information may be performed on each point in the multidimensional tree information within the preset yaw angle of the vehicle, and information of a point closest to the vehicle position information, that is, the target signal lamp information, may be determined.

Through the point set information of the signal lamp is collected in advance, the multidimensional tree information corresponding to the signal lamp is constructed based on the point set information of the signal lamp, and the nearest neighbor search processing can be carried out on the multidimensional tree information in a preset yaw angle in actual use, so that the target signal lamp information is obtained rapidly and accurately, the data processing amount is reduced, and the overall efficiency of signal lamp detection processing is improved.

In some exemplary embodiments, the target traffic light information may include correspondence of different lane identification information and sub-traffic light identification information, and sub-traffic light status information corresponding to the different sub-traffic light identification information. On this basis, as shown in fig. 11, step S204, determining target sub-signal light information corresponding to lane information from at least one sub-signal light information corresponding to the target signal light information may include:

in step S1101, identification information of a lane in which the vehicle is located is extracted from the lane information.

In the embodiment of the present specification, the lane information may further include identification information of at least one lane. After determining the lane in which the vehicle is located, the identification information of the lane in which the vehicle is located may be extracted from the lane information.

In step S1102, sub-signal lamp identification information corresponding to the identification information of the lane in which the vehicle is located is matched from the correspondence.

In this embodiment of the present disclosure, the target signal lamp information may include correspondence between different lane identification information and sub signal lamp identification information, and the identification information based on the lane where the vehicle is located may be matched to the corresponding sub signal lamp identification information.

In step S1103, target sub-signal state information corresponding to the target sub-signal identification information is extracted from the target signal information.

In this embodiment of the present disclosure, the target signal lamp information further includes sub signal lamp status information corresponding to different sub signal lamp identification information. After the sub-signal lamp identification information is obtained, the corresponding sub-signal lamp state information can be extracted.

Optionally, in some embodiments, the point set information of the signal lamp may further include identification information of the sub signal lamp and status information of the sub signal lamp. On the basis, index information of signal lamp and signal lamp states, index information of sub signal lamps and sub signal lamp states and index information of signal lamps and sub signal lamps can be established according to the identification information of signal lamps, the position information of points representing the signal lamps, the identification information of sub signal lamps and the state information of the sub signal lamps. Wherein, different dimensions of the multi-dimensional tree information can represent index information of different rationalities, for example, one dimension of the multi-dimensional tree information can represent index information of signal lamps and sub-signal lamps, and one dimension can represent index information of states of the sub-signal lamps and the sub-signal lamps.

By extracting the identification information of the lane where the vehicle is located from the lane information and matching the target sub-signal lamp identification information corresponding to the identification information of the lane where the vehicle is located from the corresponding relation between different lane identification information and sub-signal lamp identification information, the target sub-signal lamp identification information can be conveniently and efficiently obtained, the target sub-signal lamp state information corresponding to the target sub-signal lamp identification information is extracted from the target signal lamp information, the processing efficiency of determining the target sub-signal lamp state information can be improved, the target sub-signal lamp state information can be determined at any distance from the intersection, and the application scene is wide.

In some exemplary embodiments, acquiring lane line information and traffic light information may include: and acquiring high-precision map information, and carrying out serialization processing on the high-precision map information to obtain lane line information and signal lamp information.

In the embodiment of the present specification, the information in the high-precision map information may be adjusted according to the actual situation. For example, lane line information in the high-definition map information may be adjusted periodically according to a change of a lane, and signal lamp information may be updated in real time.

Specifically, after the high-precision map information is acquired, the high-precision map information may be subjected to serialization processing. Specifically, the high-precision map information may be decoded, and the decoded data may be serialized. Specifically, the serialization processing may be to store the decoded data according to a preset field, so as to obtain lane line information and signal lamp information that can be directly called.

Optionally, after the serialization processing, data compression can be performed on the data obtained after the serialization processing according to the lane information attribute and the signal lamp information attribute, so that the space occupied by data storage is saved, and the data storage is optimized.

By acquiring the high-precision map information and carrying out serialization processing on the high-precision map information to obtain the lane line information and the signal lamp information, a convenient manner for acquiring the lane line information and the signal lamp information can be provided, and timeliness of the lane line information and the signal lamp information is ensured.

In some exemplary embodiments, after determining the target sub-signal information corresponding to the lane information from at least one sub-signal information corresponding to the target signal information, the method may further include: and acquiring path planning information of the vehicle, and performing automatic driving control on the vehicle based on the target sub-signal lamp information and the path planning information. In the embodiment, the target sub-signal lamp information can provide accurate real-time results of traffic elements for automatic driving control, and the accuracy of automatic driving control and the safety of automatic driving can be improved based on the accurate and real-time target sub-signal lamp information and the path planning information.

In some exemplary embodiments, after determining the target sub-signal information corresponding to the lane information from at least one sub-signal information corresponding to the target signal information, the method may further include: and transmitting the target sub-signal lamp information to the associated vehicle of the vehicle so that the associated vehicle performs automatic driving control based on the target sub-signal lamp information and the path planning information of the associated vehicle. Specifically, the associated vehicle may refer to a vehicle that is in the same lane as the vehicle in the present application. The associated vehicle can compare and screen the sub-signal lamp information determined based on the vehicle position information with the received target sub-signal lamp information so as to ensure the accuracy of the sub-signal lamp information corresponding to the current lane; or the related vehicle can use the target sub-signal lamp information and the path planning information of the own vehicle to carry out automatic driving control after determining the same lane as the current vehicle.

The present application further provides a signal lamp detection device, as shown in fig. 12, the device may include:

a first information acquisition module 1201, configured to acquire lane line information, signal lamp information, and vehicle pose information;

a second information obtaining module 1202, configured to obtain lane information of a target lane where the vehicle is located according to the vehicle pose information and the lane line information;

the target signal lamp information determining module 1203 is configured to determine target signal lamp information according to the vehicle pose information and the signal lamp information, where the target signal lamp information is information of a target signal lamp closest to the vehicle;

the target sub-signal lamp information determining module 1204 is configured to determine target sub-signal lamp information corresponding to the lane information from at least one sub-signal lamp information corresponding to the target signal lamp information.

In some exemplary embodiments, the second information acquisition module 1202 may include:

a first target point information determining unit configured to determine, from the first point set information, first target point information closest to the vehicle, based on the vehicle pose information;

a target lane determining unit configured to determine the target lane according to the first target point information;

a lane information acquisition unit configured to acquire the lane information of the target lane.

In some exemplary embodiments, the lane line information includes structural information of lane boundaries and second point set information; the structure information represents the position structure relation of the boundary line of each lane, and the second point set information represents the position relation of a plurality of points on the boundary line of each lane; the second information acquisition module 1202 may include:

a second target point determining unit configured to determine a second target point and a third target point closest to the vehicle, respectively, according to the vehicle pose information, the second point set information, and the structure information, the second target point and the third target point being points on a boundary line of two adjacent lanes, respectively;

a target lane determining unit configured to determine the target lane according to the second target point and the third target point;

In some exemplary embodiments, the target signal information determination module 1203 may include:

an information extraction unit for extracting the vehicle position information and the vehicle heading information from the vehicle pose information;

a target signal light information determining unit configured to determine target signal light information closest to the vehicle within a preset yaw angle of the vehicle based on the vehicle position information, the vehicle heading information, and the signal light information; the preset yaw angle is a positive preset angle and a negative preset angle deviating from the heading.

In some exemplary embodiments, the apparatus may further include:

the first point set information acquisition module is used for acquiring point set information of the lane stop line in advance;

the first multidimensional tree information construction module is used for constructing multidimensional tree information corresponding to the lane stop line based on the point set information of the lane stop line;

the first target point information determining unit is further configured to perform nearest neighbor search processing on the multidimensional tree information corresponding to the lane stop line based on the vehicle pose information, so as to obtain the first target point closest to the vehicle.

In some exemplary embodiments, the apparatus may further include:

the second point set information acquisition module is used for acquiring point set information of the signal lamp in advance;

the second multidimensional tree information construction module is used for constructing multidimensional tree information corresponding to the signal lamp based on the point set information of the signal lamp;

the target signal lamp information determining unit can be further used for screening multi-dimensional tree information in a preset yaw angle of the vehicle from the multi-dimensional tree information corresponding to the signal lamp based on the vehicle position information;

In some exemplary embodiments, the target signal lamp information includes correspondence between different lane identification information and sub signal lamp identification information, and sub signal lamp status information corresponding to the different sub signal lamp identification information; the target sub-signal lamp information determination module 1204 may include:

an identification information extraction unit for extracting identification information of a lane where the vehicle is located from the lane information;

the matching unit is used for matching target sub-signal lamp identification information corresponding to the identification information of the lane where the vehicle is located from the corresponding relation;

And the target sub-signal lamp state information extraction unit is used for extracting target sub-signal lamp state information corresponding to the target sub-signal lamp identification information from the target signal lamp information.

In some exemplary embodiments, the first information obtaining module 1201 may also be configured to obtain high-precision map information; and carrying out serialization processing on the high-precision map information to obtain the lane line information and the signal lamp information.

In some exemplary embodiments, the apparatus may further include:

the path planning information acquisition module is used for acquiring the path planning information of the vehicle;

and the automatic driving control module is used for carrying out automatic driving control on the vehicle based on the target sub-signal lamp information and the path planning information.

In some exemplary embodiments, the apparatus may further include:

the target sub-signal lamp information sending module is used for sending the target sub-signal lamp information to an associated vehicle of the vehicle so that the associated vehicle can perform automatic driving control based on the target sub-signal lamp information and path planning information of the associated vehicle; the associated vehicle refers to a vehicle that is in the same lane as the vehicle.

Fig. 13 is a block diagram of an electronic device, which may be a server or an interrupt, for signal light detection according to an exemplary embodiment, and an internal structure diagram thereof may be as shown in fig. 13. The electronic device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the electronic device is configured to provide computing and control capabilities. The memory of the electronic device includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the electronic device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a signal detection method. The display screen of the electronic equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the electronic equipment, and can also be an external keyboard, a touch pad or a mouse and the like.

It will be appreciated by those skilled in the art that the structure shown in fig. 13 is merely a block diagram of a portion of the structure associated with the disclosed aspects and is not limiting of the electronic device to which the disclosed aspects apply, and that a particular electronic device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

The present application additionally provides an electronic device, which may include: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the executable instructions to implement the detection method of any of the embodiments described above.

The present application additionally provides a computer readable storage medium, which when executed by a processor of an electronic device, enables the electronic device to implement the detection method in any of the above embodiments.

The present application additionally provides a computer program product comprising a computer program/instruction which, when executed by a processor, implements the detection method of any of the embodiments described above.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that while the embodiments described herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the claims of the present invention, any of the claimed embodiments may be used in any combination.

The present invention may also be embodied as a device or system program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present invention may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order, and the words may be interpreted as names.

Claims

1. A method of signal lamp detection, the method comprising:

determining target sub-signal lamp information corresponding to the target lane information from the sub-signal lamp information corresponding to the target signal lamp information;

the lane line information comprises structure information and second point set information of lane boundaries corresponding to at least one lane respectively; the structure information represents the position structure relation of the boundary line of each lane, and the second point set information represents the position relation of a plurality of points on the boundary line of each lane;

and acquiring the target lane information of the target lane.

2. The method of claim 1, wherein the lane line information comprises lane stop line information for respective lanes, each lane stop line information comprising first point set information for a plurality of points; the step of obtaining the target lane information of the target lane where the vehicle is located according to the vehicle pose information and the lane line information comprises the following steps:

determining the target lane according to the first target point information;

and acquiring the target lane information of the target lane.

3. The method of claim 1, wherein said determining target signal information based on said vehicle pose information and said signal information comprises:

4. The method according to claim 2, wherein the method further comprises:

collecting point set information of a lane stop line in advance;

according to the vehicle pose information and the point set information of the lane stop line, determining a first target point nearest to the vehicle comprises:

5. A method according to claim 3, characterized in that the method further comprises:

the determining, based on the vehicle position information, the vehicle heading information, and the signal light information, target signal light information closest to the vehicle within a preset yaw angle of the vehicle includes:

6. The method of claim 1, wherein the target signal light information includes correspondence of different lane identification information and sub signal light identification information, and sub signal light status information corresponding to the different sub signal light identification information;

the determining the target sub-signal lamp information corresponding to the target lane information from the sub-signal lamp information corresponding to the target signal lamp information comprises the following steps:

extracting the identification information of the lane where the vehicle is located from the target lane information;

7. The method of claim 1, wherein after determining the target sub-signal light information corresponding to the target lane information from the sub-signal light information corresponding to the target signal light information, the method further comprises:

Acquiring path planning information of the vehicle;

8. The method of claim 1, wherein after determining the target sub-signal light information corresponding to the target lane information from the sub-signal light information corresponding to the target signal light information, the method further comprises:

9. A signal lamp detection apparatus, the apparatus comprising:

the first information acquisition module is used for acquiring lane line information, signal lamp information and vehicle pose information;

the second information acquisition module is used for acquiring target lane information of a target lane where the vehicle is located according to the vehicle pose information and the lane line information;

The target sub-signal lamp information determining module is used for determining target sub-signal lamp information corresponding to the target lane information from at least one piece of sub-signal lamp information corresponding to the target signal lamp information;

the second information acquisition module includes:

a lane information acquisition unit configured to acquire the target lane information of the target lane.

10. An electronic device, comprising:

A processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the signal detection method of any one of claims 1 to 8.

11. A computer readable storage medium, characterized in that instructions in the computer readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the signal detection method according to any one of claims 1 to 8.