CN115544189A

CN115544189A - Semantic map updating method, device and computer storage medium

Info

Publication number: CN115544189A
Application number: CN202210004626.4A
Authority: CN
Inventors: 何鹏; 周光; 蔡一奇
Original assignee: DeepRoute AI Ltd
Current assignee: DeepRoute AI Ltd
Priority date: 2022-01-04
Filing date: 2022-01-04
Publication date: 2022-12-30

Abstract

The application relates to a semantic map updating method, a semantic map updating device and a computer storage medium. The method comprises the following steps: when the semantic map corresponding to the acquisition area exists in the updated acquisition area, determining a first point cloud object of the crowdsourcing map newly acquired by the acquisition area and corresponding first semantic information; when a matching point cloud object with the first point cloud object exists in the semantic map, acquiring second semantic information of the matching point cloud object; performing semantic average processing on the first semantic information and the second semantic information to obtain average semantic information of the updated point cloud object; and updating the semantic map according to the average semantic information. By adopting the method, the map updating precision can be improved.

Description

Semantic map updating method, device and computer storage medium

Technical Field

The present application relates to the field of automatic driving maps and positioning technologies, and in particular, to a semantic map updating method, apparatus, and computer storage medium.

Background

In the fields of automatic driving, high-precision maps and the like, compared with the fields of professional collection and map building, the method has the advantages of low updating frequency, relatively time and labor consumption, high updating frequency and small calculation amount, and is more and more favored by the industrial and academic fields.

Professional collection methods are conventional and generally require a large number of professional data collection personnel, mapping equipment, collection vehicles, and the like. When a high-precision map is collected, information including road network data, lane network data, road traffic facility data and the like is required, so that the data are often collected on a road back and forth for multiple times to ensure the accuracy of the data. After the acquisition is completed, the system also needs to go through various links such as data fusion, data processing, release and delivery.

Crowd-sourced collection, which can be understood as that a user collects road data through a sensor of an automatic driving vehicle or other low-cost sensors and transmits the road data to a cloud for data fusion, and data precision is improved through the fusion mode to complete the production of a crowd-sourced high-precision map or a semantic map, and the crowd-sourced high-precision map or the semantic map is mainly divided into modes of vision, radar and the like; the visual crowdsourcing acquisition scheme is a main acquisition scheme of the current drawing or automatic driving companies at home and abroad; according to the crowd-sourcing acquisition scheme based on the radar three-dimensional point cloud, point cloud data is large compared with visual image data, and data transmission cost is high.

However, in the current crowdsourcing acquisition and mapping method, errors of sensors of a plurality of vehicles are different, and errors of the same object acquired by the same vehicle are also different, so that the precision is easily lost.

Disclosure of Invention

In view of the foregoing, it is necessary to provide a semantic map updating method, apparatus, computer device, computer readable storage medium and computer program product capable of improving map accuracy.

In a first aspect, the present application provides a semantic information method for a semantic map. The method comprises the following steps:

when the semantic map corresponding to the updated acquisition area exists, determining a first point cloud object and corresponding first semantic information of a crowdsourcing map newly acquired by the acquisition area;

when a matching point cloud object with the first point cloud object exists in the semantic map, acquiring second semantic information of the matching point cloud object;

performing semantic averaging processing on the first semantic information and the second semantic information to obtain average semantic information of the updated point cloud object;

and updating the semantic map according to the average semantic information.

In one embodiment, the obtaining updated average semantic information of the first point cloud object by performing semantic average processing on the first semantic information and the second semantic information includes:

performing semantic average processing according to the first semantic information and the second semantic information, updating the first semantic information of the first point cloud object, and obtaining updated average semantic information of the first point cloud object; the average semantic information at least comprises any one of the updated PCA coordinate system direction, the updated point cloud center, the vertex coordinates of the updated bounding box, the updated point cloud convex hull and the updated histogram.

In one embodiment, the performing semantic averaging processing according to the first semantic information and the second semantic information, updating the first semantic information of the first point cloud object, and obtaining the updated average semantic information of the first point cloud object includes:

performing interpolation processing on the direction of the PCA coordinate system in the first semantic information and the direction of the PCA coordinate system in the second semantic information to obtain the updated direction of the PCA coordinate system;

and obtaining the updated average semantic information of the first point cloud object according to the updated PCA coordinate system direction.

In one embodiment, the performing semantic average processing according to the first semantic information and the second semantic information, updating the first semantic information of the first point cloud object, and obtaining updated average semantic information of the first point cloud object includes:

carrying out mean value processing on the point cloud center in the first semantic information and the point cloud center in the second semantic information to obtain the updated point cloud center;

and obtaining the updated average semantic information of the first point cloud object according to the updated PCA coordinate system direction and the updated point cloud center.

carrying out mean value processing and coordinate conversion processing on the point cloud minimum bounding box in the first semantic information and the point cloud minimum bounding box in the second semantic information to obtain the vertex coordinates of the updating bounding box;

and obtaining the updated average semantic information of the first point cloud object according to the updated PCA coordinate system direction, the updated point cloud center and the vertex coordinates of the updated surrounding frame.

In one embodiment, the performing mean processing and coordinate conversion processing on the point cloud minimum bounding box in the first semantic information and the point cloud minimum bounding box in the second semantic information to obtain vertex coordinates of an updated bounding box includes:

carrying out mean processing on the point cloud minimum bounding box in the first semantic information and the point cloud minimum bounding box in the second semantic information to obtain the updated point cloud minimum bounding box;

based on the updated PCA coordinate system direction, performing coordinate conversion on the updated point cloud center, and converting the updated point cloud center to an updated object coordinate system to obtain a target point cloud center coordinate;

and obtaining the vertex coordinates of the updating bounding box according to the target point cloud central coordinates and the updating point cloud minimum bounding box.

In one embodiment, the obtaining the vertex coordinates of the updated bounding box according to the target point cloud center coordinates and the updated point cloud minimum bounding box includes:

determining the vertex coordinates according to the target point cloud center coordinates and the size information of the updated point cloud minimum bounding box; the dimensional information includes a width, a height, and a depth;

obtaining the vertex coordinates of the updating enclosing frame on the x axis according to the x axis coordinates of the center of the target point cloud and the width;

obtaining the vertex coordinates of the updating surrounding frame on the y axis according to the y axis coordinates of the center of the target point cloud and the height; and

and obtaining the vertex coordinates of the updating surrounding frame on the z axis according to the z axis coordinates of the target point cloud center and the depth.

performing translation rotation and coordinate conversion processing on the point cloud convex hull in the first semantic information and the point cloud convex hull in the second semantic information to obtain the updated point cloud convex hull;

and obtaining the updated average semantic information of the first point cloud object according to the updated PCA coordinate system direction, the updated point cloud center, the vertex coordinates of the updated bounding box and the updated point cloud convex hull.

performing coordinate system conversion according to the object point cloud of the first point cloud object to update the histogram in the second semantic information to obtain the updated histogram;

and obtaining the updated average semantic information of the first point cloud object according to the updated PCA coordinate system direction, the updated point cloud center, the updated vertex coordinates of the bounding box, the updated point cloud convex hull and the updated histogram.

In a second aspect, the application further provides a semantic map updating device. Comprising a memory storing a computer program and a processor implementing the following steps when executing the computer program:

when the semantic map corresponding to the acquisition area exists in the updated acquisition area, determining a first point cloud object of the crowdsourcing map newly acquired by the acquisition area and corresponding first semantic information;

performing semantic averaging processing on the first semantic information and the second semantic information to obtain updated average semantic information of the first point cloud object;

and updating the semantic map according to the average semantic information.

In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the following steps when executing the computer program:

and updating the semantic map according to the average semantic information.

In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:

performing semantic average processing on the first semantic information and the second semantic information to obtain updated average semantic information of the first point cloud object;

and updating the semantic map according to the average semantic information.

In a fifth aspect, the present application further provides a computer program product. The computer program product comprising a computer program which when executed by a processor performs the steps of:

and updating the semantic map according to the average semantic information.

According to the semantic map updating method, the semantic information of the point cloud object is extracted when the corresponding semantic map exists in the updated acquisition area, when the matched point cloud object exists in the newly acquired crowdsourcing map in the corresponding semantic map, the semantic information of the acquired point cloud object and the semantic information of the object in the corresponding semantic map are subjected to semantic average processing to obtain the updated average semantic information of the point cloud object, the semantic map is updated according to the average semantic information, so that the crowdsourcing data information is retained to the maximum extent, and the problem that the map precision and the subsequent positioning precision are influenced due to the fact that data with the largest error are stored in the map singly is avoided.

Drawings

FIG. 1 is a diagram of an application environment of a semantic map update method in one embodiment;

FIG. 2 is a flow diagram illustrating a semantic map update method according to one embodiment;

FIG. 3a illustrates an embodiment of partial semantic information for objects in a local three-dimensional crowd-sourced semantic map;

FIG. 3b is a diagram of matching point cloud objects, in accordance with one embodiment;

FIG. 4 is a flow diagram illustrating a method for semantic distance determination according to one embodiment;

FIG. 5 is a flow diagram illustrating a method for map matching in one embodiment;

FIG. 6 is a flow chart illustrating a semantic information average processing method according to an embodiment;

FIG. 7 is a flow diagram illustrating a method for determining vertex coordinates of a bounding box in one embodiment;

FIG. 8 is a flowchart illustrating a semantic map update method according to another embodiment;

FIG. 9 is a flow chart illustrating a semantic map update method according to another embodiment;

fig. 10 is an internal structural diagram of a computer device in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.

The semantic map updating method provided by the embodiment of the application can be applied to the application environment shown in fig. 1. Wherein the acquisition device 102 communicates with the terminal 104 via a network. The data storage system may store data that the terminal 104 needs to process. The data storage system may be integrated on the terminal 104, or may be placed on a cloud or other network server. When updating the semantic map corresponding to the acquisition area, the terminal 104 determines a first point cloud object and corresponding first semantic information of a crowdsourcing map newly acquired by the acquisition area; when a matching point cloud object with the first point cloud object exists in the semantic map, acquiring second semantic information of the matching point cloud object; carrying out semantic average processing on the first semantic information and the second semantic information to obtain average semantic information of the updated point cloud object; and updating the semantic map according to the average semantic information. The terminal 104 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, or autonomous driving computing platforms. The acquisition equipment can be a laser radar, a millimeter wave radar, an ultrasonic radar or the like, and can also be integrated on the terminal. It is understood that the method can also be applied to a server, and can also be applied to a system comprising a terminal and a server, and is realized through the interaction of the terminal and the server.

In an embodiment, as shown in fig. 2, a semantic map updating method is provided, which is described by taking the method as an example applied to the terminal in fig. 1, and includes the following steps:

step 202, when the semantic map corresponding to the updated acquisition area exists, determining a first point cloud object and corresponding first semantic information of a crowdsourcing map newly acquired by the acquisition area.

The crowdsourcing map or the crowdsourcing type map refers to a map which is acquired by the terminal through the cloud and acquired by other vehicles and uploaded to the cloud. A first point cloud object of a crowdsourcing map newly acquired in an acquisition area is acquired by carrying out denoising and clustering processing construction on target object point clouds in the crowdsourcing map; the target object point cloud refers to a point cloud of objects (such as traffic indication objects) required for building a semantic map, wherein the objects required for the semantic map include, but are not limited to, traffic lights, traffic signs, lane lines, sidewalks and other objects carrying necessary traffic information. The extraction of the point cloud of the target object can be carried out by the existing method, including feature extraction and selection and classification.

For example, extracting the target object point cloud may be to project a 3D point cloud acquired by a laser radar into a corresponding 2D image, extract a 2D point in an object calibration frame, and restore the 2D point to a 3D point; or determining object perception identification points through deep learning to obtain point clouds of corresponding objects; the object calibration frame is identified through a pre-trained perception deep learning model; perception identification points in the point cloud are also obtained through a deep learning method; for example, 2D traffic light calibration frames are identified by a perceptual deep learning model; projecting the 3D point cloud of the laser radar into the 2D image, extracting points in a calibration frame, and then recovering 3D, wherein the points are regarded as points of a traffic light; for another example, the perception identification points of the traffic sign in the point cloud obtained by the deep learning method, and the points marked as the traffic sign can be directly taken as the traffic sign point cloud.

The first semantic information includes a point cloud object identifier, a point cloud PCA (Principal Components Analysis) coordinate system direction, a point cloud main direction, a point cloud object center, an object point Bounding Box (OBB), a point cloud convex hull, and a point cloud histogram of the first point cloud object. It is understood that the number of the first point cloud objects is not limited to 1, and may be more than one; the OBB has better compactness, can greatly reduce the number of bounding boxes participating in the intersection test, and has better overall performance than the AABB. When the geometric object rotates, the same rotation is only needed for the OBB.

Further, the point cloud object identification for each object is different, i.e., unique. The point cloud PCA is decomposed through a point cloud covariance matrix eigenvalue, the directions of three dimensions are determined through eigenvectors, and the coordinate system is defined as a local coordinate system of an object. And the point cloud main direction is the main direction of the point cloud object by selecting the eigenvector corresponding to the minimum eigenvalue after PCA calculation. For example, a common traffic sign is that a point cloud approximates to a plane (in a drawing, a threshold value is given, and if the threshold value is smaller than the threshold value, a minimum width (width) is given to ensure that the point cloud object is a three-dimensional object), then a characteristic value corresponding to a normal direction of the plane is minimum, and the normal direction is defined as a main direction.

The center of the point cloud object is determined according to the maximum value and the minimum value of the coordinate of the midpoint of the point cloud, namely the maximum value and the minimum value on different axes are determined under a local coordinate system, and the maximum value and the minimum value are determined according toAfter the weighted average processing is carried out on the small values, the obtained coordinates are converted to world coordinates to obtain the small values; for example, the maximum value and the minimum value of the point cloud midpoint of the first point cloud object in the directions of the x, y and z axes are x respectively _max ,y _max ,Z _max ,x _min ,y _min ,Z _min Obtaining the center of the point cloud object as C = [ C ] _x ,C _y ,C _Z ] ^T Wherein, C _x =(x _max +x _min )/2，C _y =(y _max +y _min )/2，C _Z =(Z _max +Z _min )/2。

The bounding box size of the point cloud minimum bounding box OBB is width (width), height (height) and depth (depth), wherein width < height < depth can be expressed by eight vertexes in a world coordinate system; the point cloud convex hull is the minimum convex hull containing all points of an object; the point cloud histogram stores the x, y and z three-dimensional histogram in a one-dimensional vector. As shown in fig. 3a, is partial semantic information (including OBB and PCA coordinate systems) of some objects in the local three-dimensional crowd-sourced semantic map in one embodiment.

Specifically, when a semantic map corresponding to an acquisition area exists in an updated acquisition area, the matching condition of point cloud objects between a newly acquired crowdsourcing map and the semantic map corresponding to the newly acquired crowdsourcing map needs to be judged, objects needed for building the semantic map are determined, target object point clouds used for representing traffic indication objects are extracted from the crowdsourcing map, denoising and clustering are carried out on the target object point clouds, first point cloud objects in the crowdsourcing map are obtained, and first semantic information of all the first point cloud objects in the crowdsourcing map is extracted.

And 204, when a matching point cloud object with the first point cloud object exists in the semantic map, acquiring second semantic information of the matching point cloud object.

Specifically, all second point cloud objects in the semantic map are obtained, and second semantic information of each second point cloud object is extracted; and determining a semantic distance according to the second semantic information of the second point cloud object and the first semantic information of the first point cloud object, determining a matching point cloud object matched with the first point cloud object from a semantic map according to the semantic distance, and acquiring second semantic information of the matching point cloud object.

And step 206, performing semantic averaging processing on the first semantic information and the second semantic information to obtain average semantic information of the updated point cloud object.

The first semantic information and the second semantic information respectively comprise a PCA coordinate system direction, a point cloud center, a point cloud minimum bounding box, a point cloud convex hull and a histogram, and the first semantic information refers to the newly acquired semantic information of a first point cloud object; the second semantic information refers to semantic information of a second point cloud object existing in the corresponding semantic map.

Specifically, the average semantic information of the updated point cloud object is obtained by performing semantic average processing on the PCA coordinate system direction, the point cloud center, the point cloud minimum bounding box, the point cloud convex hull and the histogram in the first semantic information and the PCA coordinate system direction, the point cloud center, the point cloud minimum bounding box, the point cloud convex hull and the histogram in the second semantic information.

And step 208, updating the semantic map according to the average semantic information.

According to the semantic map updating method, when a corresponding semantic map exists in an updated acquisition area, semantic information of point cloud objects is extracted, when matched point cloud objects exist in a newly acquired crowdsourcing map in the corresponding semantic map, semantic average processing is carried out on the semantic information of the acquired point cloud objects and the semantic information of the objects in the corresponding semantic map, so that the average semantic information of the updated point cloud objects is obtained, the semantic map is updated according to the average semantic information, information of crowdsourcing data is retained to the maximum extent, and the problem that map precision and subsequent positioning precision are influenced due to the fact that data with the largest errors are stored in the map in a single mode is avoided.

In one embodiment, as shown in fig. 4, a method for semantic distance of a point cloud object is provided, which is described by taking the method as an example for being applied to the terminal in fig. 1, and includes the following steps:

step 402, determining a central position coordinate distance difference value according to the point cloud center coordinates of the first point cloud object and the second point cloud object.

The first point cloud object is obtained according to a target object point cloud structure extracted from a newly acquired crowd-sourced map, and the first semantic information is physical geometric information of a point cloud extracted from the first point cloud object and comprises point cloud object identification, a point cloud center, a point cloud convex hull, a point cloud minimum calibration frame OBB, a point cloud PCA coordinate system direction, a point cloud main direction, a point cloud histogram and other information.

Specifically, extracting a target object point cloud from a crowd-sourced map, constructing a corresponding first point cloud object, and extracting first semantic information of the first point cloud object; and determining a second point cloud object from the semantic map with the corresponding semantic information and second semantic information of the second point cloud object. For example, in a local map (crowd-sourced acquisition), the object center coordinates of the first point cloud object are (x) ₁ ，y ₁ ，z ₁ ) The main direction of the point cloud is a, and the size of the calibration frame is (w) ₁ ，h ₁ ，d ₁ ) The shape feature is a 30-dimensional vector s1, and the number of the original point clouds is n1. On the other hand, the center coordinate of the object of the second point cloud in the semantic map is (x) ₂ ， _y2 ，z ₂ ) B is the main direction of the point cloud, and w is the size of the calibration frame ₂ ，h ₂ ，d ₂ ) The shape feature is a 30-dimensional vector s2, and the number of the original point clouds is n2; the calibration box size may be understood as the size of the smallest bounding box of the point cloud.

Wherein, according to the point cloud center coordinate (x) of the first point cloud object ₁ ，y ₁ ，z ₁ ) And point cloud center coordinates (x) of the second point cloud object ₂ ，y ₂ ，z ₂ ) Determining the distance difference value distance1 of the center position coordinates can be expressed as:

and step 404, determining a point cloud object direction difference value according to the point cloud main direction of the first point cloud object and the point cloud main direction of the second point cloud object.

Wherein, the point cloud object direction difference value distance2 can be expressed as:

cos (θ) = a · b/(| a | · | b |); the larger the included angle is, the larger the difference is, and the smaller the cos value is; the smaller the included angle, the smaller the difference, and the larger the cos value;

distance2=1-cos (θ), the smaller the difference, the smaller the directional distance.

And 406, determining a difference value of the sizes of the calibration frames according to the size of the calibration frame of the first point cloud object and the size of the calibration frame of the second point cloud object.

Wherein the size of the calibration frame of the first point cloud object is (w) ₁ ，h ₁ ，d ₁ ) The calibration frame size of the second point cloud object is (w) ₂ ，h ₂ ，d ₂ ) (ii) a The calibration box size difference value distance3 can be expressed as:

step 408, determining an appearance feature difference value according to the shape elements of the point cloud histograms of the first point cloud object and the second point cloud object.

Wherein, the appearance characteristic difference value can be expressed as:

and step 410, weighting the distance difference value of the central position coordinates, the direction difference value of the point cloud object, the dimension difference value of the calibration frame and the appearance characteristic difference value to obtain the semantic distance between each first point cloud object and a second point cloud object in the semantic map.

Specifically, a weight value w corresponding to a center position coordinate distance difference value 1, a point cloud object direction difference value distance2, a calibration frame size difference value distance3 and an appearance feature difference value distance4 is obtained ₁ 、w ₂ 、w ₃ 、w ₄ (ii) a With w ₁ 、w ₂ 、w ₃ 、w ₄ The semantic distance score is obtained by weighting and summing the weight values, wherein the weight value range is 0-1. That is to say by each oneAdding a weight to the difference value, and then linearly adding the difference value to form a final semantic distance; i.e. semantic distance = w ₁ *distance1+w ₂ *distance2+w ₃ *distance3+w ₄ *distance4。

Based on a map matching algorithm, matching the acquired crowdsourcing map with the semantic map with which the corresponding semantic map exists according to the determined semantic distance between each first point cloud object and the second point cloud object in the semantic map, and determining the matching condition between the crowdsourcing map and the point cloud object with which the corresponding semantic map exists, wherein the matching condition comprises that the first point cloud object in the crowdsourcing map has a matched second point cloud object in the semantic map, that the first point cloud object in the crowdsourcing map does not have a matched second point cloud object in the semantic map (namely, the first point cloud object is a newly added point cloud object), that the second point cloud object in the semantic map does not have a matched first point cloud object in the crowdsourcing map (namely, the second point cloud object disappears), and the like.

According to the method for determining the semantic distance of the point cloud object, the semantic distance between the point cloud object in the crowdsourcing map and the point cloud object in the semantic map is determined according to the object geometric information by extracting the semantic information of the first point cloud object in the crowdsourcing map and the semantic information of the second point cloud object in the semantic map, so that the map matching updating is guaranteed.

In one embodiment, as shown in fig. 5, a map matching method is provided, which is described by taking the method as an example for being applied to the terminal in fig. 1, and includes the following steps:

step 502, extracting a target object point cloud from a crowdsourcing map corresponding to a current acquisition area.

Step 504, a first point cloud object is constructed according to the target object point cloud, and corresponding first semantic information is extracted.

Specifically, denoising and clustering are carried out on the extracted target object point cloud, at least one first point cloud object is constructed, and first semantic information of each first point cloud object is extracted.

Step 506, all second point cloud objects in the semantic map and corresponding second semantic information are obtained.

Step 508, determining semantic distances between the first point cloud object and each second point cloud object according to the first semantic information and the second semantic information.

Specifically, a central position coordinate distance difference value is determined according to a point cloud center coordinate of a first point cloud object and a point cloud center coordinate of a second point cloud object; determining a point cloud object direction difference value according to the point cloud main direction of the first point cloud object and the point cloud main direction of the second point cloud object; determining a difference value of the sizes of the calibration frames according to the size of the calibration frame of the first point cloud object and the size of the calibration frame of the second point cloud object; determining an appearance characteristic difference value according to the shape elements of the point cloud histograms of the first point cloud object and the second point cloud object; and weighting the difference score of the coordinate distance of the central position, the difference score of the direction of the point cloud object, the difference score of the size of the calibration frame and the difference score of the appearance characteristic to obtain the semantic distance between each first point cloud object and a second point cloud object in the semantic map.

Step 510, obtaining the number n of the first point cloud objects in the crowdsourcing map and the number m of the second point cloud objects in the semantic map to obtain an n × m association matrix.

Step 512, the semantic distance is used as an element of the incidence matrix.

It can be appreciated that each element in the correlation matrix represents a semantic distance between a first point cloud object in the crowd-sourced map and a second point cloud object in the semantic map; for example, the number of the first point cloud objects in the crowd-sourced map and the second point cloud objects in the semantic map is 3, which constitutes a 3 × 3 association matrix, and each element in the association matrix is a semantic distance between the first point cloud object and the second point cloud object in the semantic map.

Step 514, obtaining a matching result of the first point cloud object in the crowdsourcing map and the second point cloud object in the semantic map according to the predetermined threshold and the correlation matrix.

And if the semantic distance is smaller than a preset threshold value, the fact that the corresponding first point cloud object and the second point cloud object are associated is indicated.

Specifically, the semantic distance is used as an element of a correlation matrix, and when a first element is greater than or equal to a preset threshold value in the correlation matrix, a first point cloud object and a second point cloud object corresponding to the first element are determined not to be a point cloud object matching pair; the first point cloud object and the second point cloud object corresponding to the first element are not matched with the point cloud object, and the first point cloud object is a newly added point cloud object or the second point cloud object is a lost point cloud object.

When at least one second element in the correlation matrix is smaller than a preset threshold value, determining that at least one matched second point cloud object exists in the first point cloud object corresponding to the second element; segmenting the incidence matrix based on the second element to obtain a plurality of subgraphs; respectively carrying out bipartite graph matching on each subgraph, and determining a second point cloud object matched with the first point cloud object; namely, bipartite graph matching is carried out on each sub-graph, and the matching cost value of the first point cloud object and each second point cloud object in the sub-graphs is determined; and determining the second point cloud object corresponding to the matching cost value with the minimum value as the matching point cloud object of the first point cloud object. The bipartite graph matching is realized by using a Hungarian algorithm, and the bipartite graph matching is performed by using the Hungarian algorithm, so that an object connection pair (object, crowd _ object) with the minimum cost is obtained and is used as a point cloud object matching pair. FIG. 3b is a diagram illustrating an embodiment of a matching point cloud object.

For example, the crowd-sourced acquisition map includes first point cloud objects 1, 2, and 3, and there are second point cloud objects 4, 5, and 6 in the corresponding semantic map, where semantic distances between the first point cloud object 2 and the second point cloud object 4 and between the first point cloud object 2 and the second point cloud object 5 are greater than a predetermined value, and are unmatched point cloud objects, and semantic distances between the first point cloud object 1 and the second point cloud object 4, and between the first point cloud object 1 and the second point cloud object 5 are smaller than a predetermined threshold, the semantic distances between the first point cloud object 1 and the second point cloud object 4, and between the first point cloud object 1 and the second point cloud object 5 need to be partitioned into a sub-graph, and the existing whichary matching algorithm is applied to the first point cloud object 1 and the second point cloud object 4, and between the first point cloud object 1 and the second point cloud object 5 to obtain a matching cost, and the smallest point cloud cost is determined as the final matching object of the first point cloud object 1.

According to the map matching method, the target object point cloud is extracted from crowd-sourced data, semantic information is further extracted on the basis of the extracted object point cloud, and more information is obtained while the size of the data is compressed; the size of the whole map data is extremely small, and all required information is contained; a matching algorithm is added in the map updating process, and whether the map updating process is the same object is not judged only by the distance of the semantic distance; in the local map, when the number of objects exceeds a certain threshold, the map updating precision is higher due to the semantic distance-based matching algorithm.

In one embodiment, as shown in fig. 6, a semantic information averaging processing method is provided, which is described by taking the method as an example applied to the terminal in fig. 1, and includes the following steps:

step 602, performing interpolation processing on the PCA coordinate system direction in the first semantic information and the PCA coordinate system direction in the second semantic information to obtain an updated PCA coordinate system direction.

The PCA coordinate system direction in the first semantic information and the PCA coordinate system direction in the second semantic information are quaternions, that is, the PCA coordinate system direction in the first semantic information is quaternion q ₁ The direction of the PCA coordinate system in the second semantic information is a quaternion q ₂ And the direction of the obtained updated PCA coordinate system is a quaternion q _update 。

From quaternion q ₁ And quaternion q ₂ And the direction of the obtained updated PCA coordinate system is a quaternion q _update The method is determined by calculating an interpolation value of quaternion slerp, and comprises the following steps of:

calculating q ₁ And q is ₂ Relative rotation Δ q therebetween

Δq＝q ₁ ^-1 *q ₂ ＝[Δq _w Δq _x Δq _y Δq _z ] ^T (ii) a Wherein, Δ q _w ，Δq _x ，Δq _y ，Δq _z These four are the four components of the quaternion.

Calculating a rotation angle theta between point cloud centers of the first point cloud object and the second point cloud object

θ＝2*arccos(Δq _w )

Interpolated value of slerp of

q _update ＝(q ₁ *sin((1-t)θ/2)+q2*sin(tθ/2))/sin(θ/2)

Wherein t is ∈ [0,1]. T =0.5 in the present embodiment.

Specifically, interpolation processing is performed on the PCA coordinate system direction in the first semantic information and the PCA coordinate system direction in the second semantic information to obtain an updated PCA coordinate system direction, the point cloud principal direction is updated according to the updated PCA coordinate system direction, and the same axis (such as an x axis, or a y axis, or a z axis) of the updated PCA coordinate system direction is used as the update principal direction.

Step 604, performing mean processing on the point cloud center in the first semantic information and the point cloud center in the second semantic information to obtain an updated point cloud center.

Specifically, for a point cloud center (cx) in first semantic information of a first point cloud object in a local coordinate system ₁ ，cy ₁ ，cz ₁ ) And the point cloud center (cx) in the second semantic information under the local coordinate system of the second point cloud object ₂ ，cy ₂ ，cz ₂ ) Carrying out mean value processing and then carrying out coordinate conversion to obtain an updated point cloud center c under world coordinates _update This can be expressed by:

c _update ＝[cx _update cy _update cz _update ] ^T (ii) a Wherein, cx _update ＝(cx ₁ +cx ₂ )/2；

cy _update ＝(cy ₁ +cy ₂ )/2；cz _update ＝(cz ₁ +cz ₂ )/2；

And 606, carrying out mean processing on the point cloud minimum bounding box in the first semantic information and the point cloud minimum bounding box in the second semantic information to obtain an updated point cloud minimum bounding box.

And 608, performing coordinate conversion on the center of the updated point cloud based on the updated PCA coordinate system direction, and converting the center of the updated point cloud to an updated object coordinate system to obtain the center coordinate of the target point cloud.

The bounding box size of the point cloud minimum bounding box is wide width, high height and deep depth, wherein width is more than height and less than depth; according to the point cloud minimum bounding box (w) in the first semantic information ₁ ，h ₁ ，d ₁ ) And point cloud minimum bounding box (w) in the second semantic information ₂ ，h ₂ ，d ₂ ) Performing mean processing to obtain the updated bounding box size (w) of the point cloud minimum bounding _update ，h _update ，d _update ). Wherein:

w _update ＝(w ₁ +w ₂ )/2

h _update ＝(h ₁ +h ₂ )/2

d _update ＝(d ₁ +d ₂ )/2

based on updated PCA coordinate system direction q _update Will update the point cloud center c _update ＝[cx _update cy _update cz _update ] ^T Performing coordinate conversion, and converting to an updated object coordinate system calculated by PCA to obtain a target point cloud center coordinate c _local ＝[cx _local cy _local cz _local ] ^T 。

And step 610, obtaining the vertex coordinates of the updated bounding box according to the central coordinates of the target point cloud and the updated point cloud minimum bounding box.

Specifically, determining a vertex coordinate according to a target point cloud center coordinate and size information of the updated point cloud minimum bounding box; wherein the dimension information comprises width, height and depth; the method specifically comprises the following steps:

step 702, obtaining the vertex coordinates of the updating enclosing frame on the x axis according to the x axis coordinates and the width of the target point cloud center.

And step 704, obtaining the vertex coordinates of the updating surrounding frame on the y axis according to the y axis coordinates and the height of the target point cloud center.

And step 706, obtaining the vertex coordinates of the updating surrounding frame in the z axis according to the z axis coordinates and the depth of the center of the target point cloud.

Step 708, obtaining the vertex coordinates of the updated bounding box according to the vertex coordinates of the updated bounding box in the x axis, the vertex coordinates of the updated bounding box in the y axis and the vertex coordinates of the updated bounding box in the z axis.

That is, the maximum value and the minimum value on the x axis of the local coordinate system are obtained according to the x axis coordinate and the width of the center of the target point cloud; obtaining the maximum value and the minimum value on the y axis of a local coordinate system according to the y axis coordinate and the height of the center of the target point cloud; obtaining the maximum value and the minimum value on the z axis of a local coordinate system according to the z axis coordinate and the depth of the center of the target point cloud; and determining the vertex coordinates of the updating surrounding box according to the maximum value and the minimum value on the x axis, the maximum value and the minimum value on the y axis and the maximum value and the minimum value on the z axis.

Specifically, the maximum value and the minimum value on the x axis, the maximum value and the minimum value on the y axis, and the maximum value and the minimum value on the z axis of the local coordinate system are inverted to the world coordinate, so as to obtain the maximum value and the minimum value on the x axis, the maximum value and the minimum value on the y axis, and the maximum value and the minimum value on the z axis of the corresponding coordinate system, and further obtain 8 vertex coordinates of the update bounding box. I.e. according to the updated point cloud minimum bounding box (w) _utpdate ，h _update ，d _update ) And c in the local coordinate system _local ＝[cx _local cy _local cz _local ] ^T Determining the maximum value and the minimum value in the x, y and z directions under the local coordinate system

Wherein:

obtained under the above-mentioned local coordinate system

The coordinate is inverted to the world coordinate to obtain the maximum value and the minimum value x of the x, y and z directions under the corresponding coordinate _min ，x _max ，y _min ，y _max ，z _min ，z _max And obtaining 8 vertex coordinates of the updating bounding box as follows:

1(x _max ，y _max ，z _max )，2(x _max ，y _max ，z _min )，

3(x _max ，y _min ，z _min )，4(x _max ，y _min ，z _max )，

5(x _min ，y _max ，z _max )，6(x _min ，y _max ，z _min )，

7(x _min ，y _min ，z _min )，8(x _min ，y _min ，z _max )。

and step 612, performing translation rotation and coordinate conversion processing on the point cloud convex hull in the first semantic information and the point cloud convex hull in the second semantic information to obtain an updated point cloud convex hull.

In particular, the direction q is determined from the updated PCA coordinate system _update And updating the point cloud center c _update The point cloud convex hull M in the first semantic information is processed ₁ And a point cloud convex hull M in the second semantic information ₂ Translationally rotated to c _update Is a center, q _update Obtaining a fused point cloud convex hull M of the two point cloud convex hulls under the local coordinate of the rotation direction _local Recalculating the fused point cloud convex hull M by adopting the existing point cloud convex hull calculation mode _local The convex hull of (c) is updated to the point cloud minimum bounding box (w) _update ，h _update ，d _update ) For the convex hull M of the fused point cloud _local Filtering the convex hull to obtain a filtered point cloud convex hull M _local+update The convex hull M of the point cloud _local+update Is updated by converting the coordinate system into the world coordinate systemPoint cloud convex hull M _update 。

And 614, converting the coordinate system according to the object point cloud of the first point cloud object to update the histogram in the second semantic information to obtain an updated histogram.

In the semantic map, the object point cloud itself does not need to be stored, and the histogram can be determined again according to the object point cloud data of the newly acquired crowd-sourced map.

In particular, the direction q is according to the PCA coordinate system _update Updating the center c of the point cloud _update And the PCA coordinate system direction q of the first point cloud object ₁ Point cloud center c ₁ Relative relation between the first point cloud object and the second point cloud object, and the object point cloud PLC of the first point cloud object ₁ Conversion to q _update And c _update PLC under the local coordinate system _local Obtaining PLC by converting to world coordinate system _update (ii) a Using the updated point cloud minimum bounding box (w) _update ，h _update ，d _update ) Filtering the updated object point cloud in the point cloud minimum bounding box (w) _update ，h _update ，d _update ) And after the external points are detected, recalculating the histogram to obtain an updated histogram of the same object in the crowdsourcing map and the semantic map.

And 616, updating the point cloud center, the vertex coordinates, the point cloud convex hull and the histogram according to the updated PCA coordinate system direction to obtain the updated average semantic information of the first point cloud object.

In the semantic information average processing method, new data are collected in a crowdsourcing mode, the new data are matched with a corresponding semantic map, and semantic average processing is carried out on semantic information such as the distance of the central point of the matched point cloud object, the direction difference of the object, the size difference of the bounding box, the size difference of the histogram and the like, instead of simply retaining an old object or using a new object, so that the information of the crowdsourcing data is retained to the maximum extent, and the map updating precision is improved.

In another embodiment, as shown in fig. 8, a semantic map updating method is provided, which is described by taking the method as an example applied to the terminal in fig. 1, and includes the following steps:

step 802, when the semantic map corresponding to the updated acquisition area exists, determining a first point cloud object and corresponding first semantic information of a crowdsourcing map newly acquired by the acquisition area.

And step 804, when a matching point cloud object with the first point cloud object exists in the semantic map, acquiring second semantic information of the matching point cloud object.

And 806, performing semantic average processing according to the first semantic information and the second semantic information, updating the first semantic information of the first point cloud object, and obtaining updated average semantic information of the first point cloud object.

The average semantic information at least comprises any one of the updated PCA coordinate system direction, the updated point cloud center, the vertex coordinates of the updated bounding box, the updated point cloud convex hull and the updated histogram.

Specifically, semantic averaging is performed according to the first semantic information and the second semantic information, the first semantic information of the first point cloud object is updated, and any one of average semantic information of the updated PCA coordinate system direction, the updated point cloud center, the updated vertex coordinates of the bounding box, the updated point cloud convex hull and the updated histogram of the updated first point cloud object is obtained.

Optionally, in an embodiment, interpolation processing is performed on a PCA coordinate system direction in the first semantic information and a PCA coordinate system direction in the second semantic information to obtain an updated PCA coordinate system direction; and obtaining the updated average semantic information of the first point cloud object according to the updated PCA coordinate system direction.

Optionally, in an embodiment, after determining the updated PCA coordinate system direction, performing mean processing on the point cloud center in the first semantic information and the point cloud center in the second semantic information to obtain an updated point cloud center; and obtaining the updated average semantic information of the first point cloud object according to the updated PCA coordinate system direction and the updated point cloud center.

Optionally, in an embodiment, after determining the updated PCA coordinate system direction and updating the point cloud center, performing mean processing and coordinate conversion processing on the point cloud minimum bounding box in the first semantic information and the point cloud minimum bounding box in the second semantic information to obtain vertex coordinates of the updated bounding box; and obtaining the updated average semantic information of the first point cloud object according to the updated PCA coordinate system direction, the updated point cloud center and the updated vertex coordinates of the surrounding frame.

Optionally, in an embodiment, after determining the updated PCA coordinate system direction, updating the point cloud center, and updating the vertex coordinates of the bounding box, the translation rotation and coordinate conversion processing are further performed on the point cloud convex hull in the first semantic information and the point cloud convex hull in the second semantic information to obtain an updated point cloud convex hull; and obtaining the updated average semantic information of the first point cloud object according to the updated PCA coordinate system direction, the updated point cloud center, the updated vertex coordinates of the bounding box and the updated point cloud convex hull.

Optionally, in an embodiment, the updated PCA coordinate system direction, the updated point cloud center, the vertex coordinates of the update bounding box, and the updated point cloud convex hull are determined, and coordinate system conversion is performed according to the object point cloud of the first point cloud object to update the histogram in the second semantic information, so as to obtain an updated histogram; and according to the updated PCA coordinate system direction, the point cloud center, the vertex coordinates of the surrounding frame, the point cloud convex hull and the histogram, obtaining the updated average semantic information of the first point cloud object.

And 808, updating the semantic map according to the average semantic information.

According to the semantic map updating method, when a corresponding semantic map exists in an updated acquisition area, semantic information of point cloud objects is extracted, when matched point cloud objects exist in a newly acquired crowd-sourced map in the corresponding semantic map, semantic average processing is performed on the semantic information of the acquired point cloud objects and the semantic information of the objects in the corresponding semantic map, so that any one of the updated PCA coordinate system direction, the updated point cloud center, the vertex coordinates of an updated bounding box, the updated point cloud convex hull and an updated histogram is obtained, the semantic map is updated according to the average semantic information, so that crowd-sourced data information is retained to the maximum extent, and the problem that the map accuracy and the subsequent positioning accuracy are influenced because data with the largest error are stored in the map singly is avoided; the safety of automatic driving is further improved.

In another embodiment, as shown in fig. 9, a semantic map updating method is provided, which is described by taking the method as an example applied to the terminal in fig. 1, and includes the following steps:

step 902, when the semantic map corresponding to the updated acquisition area exists, determining a first point cloud object and corresponding first semantic information of a crowdsourcing map newly acquired by the acquisition area.

Step 904, when a matching point cloud object exists in the semantic map, acquiring second semantic information of the matching point cloud object.

Step 906, performing interpolation processing on the PCA coordinate system direction in the first semantic information and the PCA coordinate system direction in the second semantic information to obtain an updated PCA coordinate system direction.

Step 908, performing mean processing on the point cloud center in the first semantic information and the point cloud center in the second semantic information to obtain an updated point cloud center.

Step 910, performing mean value processing and coordinate conversion processing on the point cloud minimum bounding box in the first semantic information and the point cloud minimum bounding box in the second semantic information to obtain the vertex coordinates of the updated bounding box.

And 912, performing translation rotation and coordinate conversion processing on the point cloud convex hull in the first semantic information and the point cloud convex hull in the second semantic information to obtain an updated point cloud convex hull.

And 914, performing coordinate system conversion according to the object point cloud of the first point cloud object to update the histogram in the second semantic information to obtain an updated histogram.

And 916, updating the point cloud center, the vertex coordinates, the point cloud convex hull and the histogram according to the updated PCA coordinate system direction to obtain the updated average semantic information of the first point cloud object.

Step 918, updating the semantic map according to the average semantic information.

And 920, positioning based on the updated semantic map obtained after updating the semantic map.

Performing loop detection and positioning according to the updated semantic map; the methods of positioning and loop detection can be implemented by the existing methods, and are not described herein. The loop detection is also called closed loop detection, and refers to the ability of the device to identify that a scene has been reached, so that the map is closed, that is, the map generated at the moment can be matched with the map just generated.

That is, after the updated semantic map is obtained, the semantic map is positioned and loop detection is performed, and an object and a lane line can be matched to obtain a positioning result; for example, the surrounding traffic environment where the current position is located is obtained; generating a prompt according to the surrounding traffic environment, updating the planned route in real time according to the destination, and improving the punctuality rate of reaching the destination and the safety of automatic driving; that is to say, the detection capability of loop detection is improved based on the updated semantic map, the accumulated error is reduced, and the positioning precision and speed obstacle avoidance are further improved.

According to the semantic map updating method, when a corresponding semantic map exists in an updated acquisition area, semantic information of point cloud objects is extracted, when a matching point cloud object exists in a newly acquired crowdsourcing map in the corresponding semantic map, the semantic information of the acquired point cloud objects and the semantic information of the objects in the corresponding semantic map are subjected to semantic average processing to obtain the updated average semantic information of the point cloud objects, the semantic map is updated according to the average semantic information, so that crowdsourcing data information is retained to the maximum extent, and the problem that map precision and subsequent positioning precision are influenced due to the fact that certain data with the largest error is stored in the map in a single mode is avoided; the safety of automatic driving is further improved.

It should be understood that, although the steps in the flowcharts related to the embodiments are shown in sequence as indicated by the arrows, the steps are not necessarily executed in sequence as indicated by the arrows. The steps are not limited to being performed in the exact order illustrated and, unless explicitly stated herein, may be performed in other orders. Moreover, at least a part of the steps in the flowcharts related to the above embodiments may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of the steps or stages in other steps.

Based on the same inventive concept, the embodiment of the application also provides a semantic map updating device for realizing the semantic map updating method. The implementation scheme for solving the problem provided by the apparatus is similar to the implementation scheme described in the above method, so the specific limitations in one or more semantic map updating apparatus embodiments provided below may refer to the limitations on the semantic map updating method in the above description, and details are not repeated here.

A semantic map updating apparatus comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:

when the semantic map corresponding to the acquisition area exists in the updated acquisition area, a first point cloud object of the crowdsourcing map newly acquired by the acquisition area and corresponding first semantic information are determined.

And when a matching point cloud object with the first point cloud object exists in the semantic map, acquiring second semantic information of the matching point cloud object.

And performing semantic average processing on the first semantic information and the second semantic information to obtain updated average semantic information of the first point cloud object.

And updating the semantic map according to the average semantic information.

When a corresponding semantic map exists in an updated acquisition area, the semantic information of the point cloud object is extracted, when a matching point cloud object exists in a newly acquired crowdsourcing map in the corresponding semantic map, the semantic information of the acquired point cloud object and the semantic information of the object in the corresponding semantic map are subjected to semantic average processing to obtain the updated average semantic information of the point cloud object, and the semantic map is updated according to the average semantic information, so that crowdsourcing data information is retained to the maximum extent, and the problem that map precision and subsequent positioning precision are influenced because data with the largest error is stored in the map singly is avoided; the safety of automatic driving is further improved.

In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 10. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises 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 an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a semantic map update method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on a shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.

Those skilled in the art will appreciate that the architecture shown in fig. 10 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is further provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method embodiments when executing the computer program.

In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.

In an embodiment, a computer program product is provided, comprising a computer program which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.

It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include a Read-Only Memory (ROM), a magnetic tape, a floppy disk, a flash Memory, an optical Memory, a high-density embedded nonvolatile Memory, a resistive Random Access Memory (ReRAM), a Magnetic Random Access Memory (MRAM), a Ferroelectric Random Access Memory (FRAM), a Phase Change Memory (PCM), a graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, and these are all within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A semantic map updating method, comprising:

and updating the semantic map according to the average semantic information.

2. The method according to claim 1, wherein obtaining updated average semantic information of the first point cloud object by performing semantic average processing on the first semantic information and the second semantic information comprises:

3. The method according to claim 2, wherein performing semantic averaging processing according to the first semantic information and the second semantic information to update the first semantic information of the first point cloud object, and obtaining updated average semantic information of the first point cloud object includes:

4. The method according to claim 3, wherein performing semantic averaging processing according to the first semantic information and the second semantic information to update the first semantic information of the first point cloud object, and obtaining updated average semantic information of the first point cloud object includes:

5. The method according to claim 4, wherein the performing semantic averaging processing according to the first semantic information and the second semantic information to update the first semantic information of the first point cloud object to obtain updated average semantic information of the first point cloud object includes:

6. The method of claim 5, wherein performing an averaging process and a coordinate transformation process on the point cloud minimum bounding box in the first semantic information and the point cloud minimum bounding box in the second semantic information to obtain vertex coordinates of an updated bounding box comprises:

and obtaining the vertex coordinates of the updated bounding box according to the target point cloud central coordinates and the updated point cloud minimum bounding box.

7. The method of claim 6, wherein obtaining vertex coordinates of an updated bounding box according to the target point cloud center coordinates and the updated point cloud minimum bounding box comprises:

determining the vertex coordinates according to the target point cloud center coordinates and the size information of the updated point cloud minimum bounding box; the dimension information comprises a width, a height and a depth;

obtaining the vertex coordinates of the updating surrounding frame on the x axis according to the x axis coordinates of the center of the target point cloud and the width;

and obtaining the vertex coordinates of the updating surrounding frame in the z axis according to the z axis coordinates of the center of the target point cloud and the depth.

8. The method according to claim 5, wherein the performing semantic averaging processing according to the first semantic information and the second semantic information to update the first semantic information of the first point cloud object to obtain updated average semantic information of the first point cloud object includes:

9. The method according to claim 8, wherein performing semantic averaging processing according to the first semantic information and the second semantic information to update the first semantic information of the first point cloud object, and obtaining updated average semantic information of the first point cloud object includes:

10. A semantic map updating apparatus comprising a memory and a processor, the memory storing a computer program, wherein the processor when executing the computer program performs the steps of:

and updating the semantic map according to the average semantic information.

11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 9.