CN113568997A

CN113568997A - Point cloud map updating method and device, electronic equipment and computer readable medium

Info

Publication number: CN113568997A
Application number: CN202110874148.8A
Authority: CN
Inventors: 李�浩
Original assignee: Jingdong Kunpeng Jiangsu Technology Co Ltd
Current assignee: Jingdong Kunpeng Jiangsu Technology Co Ltd
Priority date: 2021-07-30
Filing date: 2021-07-30
Publication date: 2021-10-29

Abstract

The embodiment of the disclosure discloses a point cloud map updating method, a point cloud map updating device, electronic equipment and a computer readable medium. One embodiment of the method comprises: in the process of moving from a first place to a second place in a target area, acquiring a real-time point cloud set corresponding to the target area; screening at least one real-time point cloud representing scene change from the real-time point cloud set as a point cloud set to be processed; and updating the point cloud map associated with the target area according to the point cloud set to be processed. The method and the device can quickly and efficiently determine the cloud set of the points to be processed. Furthermore, the point cloud map can be updated, so that the point cloud map is more accurate.

Description

Point cloud map updating method and device, electronic equipment and computer readable medium

Technical Field

The embodiment of the disclosure relates to the technical field of computers, in particular to a point cloud map updating method, a point cloud map updating device, electronic equipment and a computer readable medium.

Background

At present, a point cloud map is an indispensable map tool for stable operation of an unmanned distribution vehicle. The construction process of the point cloud map is often: the target scene is scanned in all directions and the image is built by using an image acquisition device which is provided with sensors such as a laser radar and an inertial navigation sensor with higher precision in advance. When the target scene is changed, the point cloud map of the target scene needs to be updated in time. Otherwise, the point cloud map which is not updated in time may cause problems of positioning offset, perception misdetection and the like of a subsequent unmanned distribution vehicle. For updating the point cloud map, the following methods are generally adopted: the method comprises the steps of determining a region where a target scene is transformed in a manual monitoring mode, and accordingly comprehensively detecting the region where the target scene is transformed through a map collecting device to update a point cloud map.

However, when the map is updated in the above manner, there are often technical problems as follows:

the accuracy of determining the transformation area through manual monitoring is low, and problems of missing report, delay and the like can be caused. Therefore, the accuracy of the subsequent point cloud map is low. In addition, the manual monitoring is time and labor consuming.

Disclosure of Invention

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

Some embodiments of the present disclosure propose a point cloud map updating method, apparatus, electronic device and computer readable medium to solve one or more of the technical problems mentioned in the background section above.

In a first aspect, some embodiments of the present disclosure provide a point cloud map updating method, including: acquiring a real-time point cloud set corresponding to a target area in the process of moving from a first place to a second place in the target area; screening at least one real-time point cloud representing scene change from the real-time point cloud set to serve as a point cloud set to be processed; and updating the point cloud map associated with the target area according to the point cloud set to be processed.

Optionally, the screening, from the real-time point cloud set, at least one real-time point cloud representing scene changes to serve as a point cloud set to be processed includes: removing at least one of the first and second subsets of real-time point clouds from the real-time point cloud set to obtain a removed real-time point cloud set; and determining the removed real-time point cloud set as the point cloud set to be processed.

Optionally, the removing at least one of the first and second subsets of real-time point clouds from the set of real-time point clouds to obtain a removed set of real-time point clouds includes: determining the point cloud set which is the static point cloud in the real-time point cloud set as the first real-time point cloud subset; in response to detecting that a dynamic point cloud exists in the real-time point cloud set, determining the point cloud set in which the real-time point cloud set is a dynamic point cloud as the second real-time point cloud subset; and removing the first real-time point cloud subset and the second real-time point cloud subset in the real-time point cloud set to obtain the removed real-time point cloud set.

Optionally, the determining the point cloud set in which the real-time point cloud set is a static point cloud as the first real-time point cloud subset includes: in response to detecting that the point cloud sets corresponding to the point cloud map and the real-time point cloud sets have the same point cloud, determining at least one point cloud corresponding to the point cloud map and the same point cloud set between the real-time point cloud sets as a target point cloud set; and determining a point cloud set associated with a target ground in a point cloud set corresponding to the point cloud map and the target point cloud set as the first real-time point cloud subset.

Optionally, the updating the point cloud map associated with the target area according to the cloud set of points to be processed includes: acquiring a voxel grid information set corresponding to the target area and area information corresponding to each voxel grid information in the voxel grid information set; determining voxel grid information corresponding to each point cloud to be processed in the point cloud set to be processed according to the area information corresponding to each voxel grid information in the voxel grid information set to obtain a voxel grid information subset; determining point cloud change area information in the target area according to the voxel grid information subset; and updating the point cloud map according to the point cloud change area information.

Optionally, the determining a point cloud variation region in the target region according to the voxel grid information subset includes: acquiring index information corresponding to each voxel grid information in the voxel grid information set; according to the index information corresponding to each voxel grid information in the voxel grid information set, determining the index information corresponding to each voxel grid information in the voxel grid information subset to obtain an index information set; determining the point cloud association times corresponding to each index information in the index information set; in response to the fact that the point cloud association times corresponding to at least one index information in the index information set are larger than a first target value, determining the index information of which the point cloud association times meet a preset condition in the at least one index information as target index information to obtain a target index information set; and determining the voxel grid information set corresponding to the target index information set as the first target voxel grid information set.

Optionally, the method further includes: and determining the addition result of the point cloud association times corresponding to the index information and a second target value as the point cloud association times corresponding to the index information for each index information in the index information set.

Optionally, the determining a point cloud variation region in the target region according to the voxel grid information subset includes: determining the point cloud association times corresponding to each voxel grid information in the voxel grid information subset; and in response to the fact that the point cloud association times corresponding to at least one piece of voxel grid information in the voxel grid information subset are larger than a first target value, determining the voxel grid information of which the point cloud association times meet a preset condition in the at least one piece of voxel grid information as first target voxel grid information to obtain a first target voxel grid information set.

Optionally, the method further includes: and determining the addition result of the point cloud association times corresponding to the voxel grid information and a second target value as the point cloud association times corresponding to the voxel grid information for each voxel grid information in the voxel grid information subset.

Optionally, the method further includes: and storing the first target voxel grid information set, and determining a region corresponding to the first target voxel grid information set as a point cloud change region in the target region.

Optionally, the determining, according to the area information corresponding to each voxel grid information in the voxel grid information set, voxel grid information corresponding to each point cloud to be processed in the point cloud set to be processed to obtain a voxel grid information subset includes: performing coordinate conversion on each point cloud to be processed in the point cloud set to be processed to generate a corresponding map coordinate to obtain a map coordinate set; and determining voxel grid information corresponding to each point cloud to be processed in the point cloud set to be processed according to the map coordinate set and the area information corresponding to each voxel grid information in the voxel grid information set to obtain a voxel grid information subset.

In a second aspect, some embodiments of the present disclosure provide a point cloud map updating apparatus, including: the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is configured to acquire a real-time point cloud set corresponding to a target area in the process of moving from a first place to a second place in the target area; a screening unit configured to screen at least one real-time point cloud representing scene variation from the real-time point cloud set as a point cloud set to be processed; and the updating unit is configured to update the point cloud map associated with the target area according to the point cloud set to be processed.

Optionally, the screening unit is further configured to: removing at least one of the first and second subsets of real-time point clouds from the real-time point cloud set to obtain a removed real-time point cloud set; and determining the removed real-time point cloud set as the point cloud set to be processed.

Optionally, the screening unit is further configured to: determining the point cloud set which is the static point cloud in the real-time point cloud set as the first real-time point cloud subset; in response to detecting that a dynamic point cloud exists in the real-time point cloud set, determining the point cloud set in which the real-time point cloud set is a dynamic point cloud as the second real-time point cloud subset; and removing the first real-time point cloud subset and the second real-time point cloud subset in the real-time point cloud set to obtain the removed real-time point cloud set.

Optionally, the screening unit is further configured to: in response to detecting that the point cloud sets corresponding to the point cloud map and the real-time point cloud sets have the same point cloud, determining at least one point cloud corresponding to the point cloud map and the same point cloud set between the real-time point cloud sets as a target point cloud set; and determining a point cloud set associated with a target ground in a point cloud set corresponding to the point cloud map and the target point cloud set as the first real-time point cloud subset.

Optionally, the update unit is further configured to: acquiring a voxel grid information set corresponding to the target area and area information corresponding to each voxel grid information in the voxel grid information set; determining voxel grid information corresponding to each point cloud to be processed in the point cloud set to be processed according to the area information corresponding to each voxel grid information in the voxel grid information set to obtain a voxel grid information subset; determining point cloud change area information in the target area according to the voxel grid information subset; and updating the point cloud map according to the point cloud change area information.

Optionally, the update unit is further configured to: acquiring index information corresponding to each voxel grid information in the voxel grid information set; according to the index information corresponding to each voxel grid information in the voxel grid information set, determining the index information corresponding to each voxel grid information in the voxel grid information subset to obtain an index information set; determining the point cloud association times corresponding to each index information in the index information set; in response to the fact that the point cloud association times corresponding to at least one index information in the index information set are larger than a first target value, determining the index information of which the point cloud association times meet a preset condition in the at least one index information as target index information to obtain a target index information set; and determining the voxel grid information set corresponding to the target index information set as the first target voxel grid information set.

Optionally, the update unit is further configured to: and determining the addition result of the point cloud association times corresponding to the index information and a second target value as the point cloud association times corresponding to the index information for each index information in the index information set.

Optionally, the update unit is further configured to: determining the point cloud association times corresponding to each voxel grid information in the voxel grid information subset; and in response to the fact that the point cloud association times corresponding to at least one piece of voxel grid information in the voxel grid information subset are larger than a target value, determining the voxel grid information of which the point cloud association times meet a preset condition in the at least one piece of voxel grid information as first target voxel grid information to obtain a first target voxel grid information set.

Optionally, the update unit is further configured to: and determining the addition result of the point cloud association times corresponding to the voxel grid information and the target value as the point cloud association times corresponding to the voxel grid information for each voxel grid information in the voxel grid information subset.

Optionally, the update unit is further configured to: and storing the first target voxel grid information set, and determining a region corresponding to the first target voxel grid information set as a point cloud change region in the target region.

Optionally, the update unit is further configured to: performing coordinate conversion on each point cloud to be processed in the point cloud set to be processed to generate a corresponding map coordinate to obtain a map coordinate set; and determining voxel grid information corresponding to each point cloud to be processed in the point cloud set to be processed according to the map coordinate set and the area information corresponding to each voxel grid information in the voxel grid information set to obtain a voxel grid information subset.

In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors, cause the one or more processors to implement the method as described in any of the implementations of the first aspect.

In a fourth aspect, some embodiments of the disclosure provide a computer readable medium having a computer program stored thereon, where the program when executed by a processor implements a method as described in any of the implementations of the first aspect.

The above embodiments of the present disclosure have the following beneficial effects: according to the point cloud map updating method of some embodiments of the disclosure, the point cloud set to be processed can be determined quickly and efficiently. Furthermore, the point cloud map can be updated, so that the point cloud map is more accurate. Specifically, the accuracy of determining the transformation area through human monitoring is low, which may cause problems such as missing reports and delay. Therefore, the accuracy of the subsequent point cloud map is low. In addition, the manual monitoring is time and labor consuming. Based on this, the point cloud map updating method according to some embodiments of the present disclosure may obtain the real-time point cloud set corresponding to the target area in the process of moving from the first location to the second location in the target area. Here, a real-time point cloud set corresponding to the target area is obtained as data support for subsequently determining an area in the point cloud map where scene change occurs. And then, screening at least one real-time point cloud representing scene change from the real-time point cloud set to serve as a point cloud set to be processed. By determining the point cloud set to be processed, the area of the point cloud map where the scene is changed can be determined more accurately in the follow-up process. And the subsequent point cloud map is updated more pertinently. The side surface also improves the updating efficiency of the point cloud map. And finally, updating the point cloud map associated with the target area according to the point cloud set to be processed so as to enable the point cloud map to be more accurate.

Drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and elements are not necessarily drawn to scale.

1-2 are schematic diagrams of one application scenario of a point cloud map update method according to some embodiments of the present disclosure;

fig. 3 is a flow diagram of some embodiments of a point cloud map updating method according to the present disclosure;

FIG. 4 is a flow diagram of further embodiments of a point cloud map updating method according to the present disclosure;

FIG. 5 is a schematic structural diagram of some embodiments of a point cloud map updating apparatus according to the present disclosure;

FIG. 6 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.

It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.

The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Fig. 1-2 are schematic diagrams of an application scenario of a point cloud map update method according to some embodiments of the present disclosure.

In the application scenarios of fig. 1-2, during the process of moving from the first location 103 to the second location 104 within the target area 102, the electronic device 101 may first acquire the real-time point cloud 105 corresponding to the target area 102. In this application scenario, the real-time cloud set 105 may include: real-time point cloud 1051, real-time point cloud 1052, real-time point cloud 1053, real-time point cloud 1054, and real-time point cloud 1055. Each real-time point cloud in the real-time point cloud set 105 may be a point cloud corresponding to each object in a scene corresponding to the target area 102. Then, at least one real-time point cloud 106 representing scene changes is screened from the real-time point cloud set 105 to serve as a point cloud set 107 to be processed. In the present application scenario, a real-time point cloud 1052, a real-time point cloud 1053, and a real-time point cloud 1054 are screened from the real-time point cloud set 105. The real-time point cloud 1052, the real-time point cloud 1053, and the real-time point cloud 1054 in the at least one real-time point cloud 106 may be point clouds corresponding to at least one object in a scene that changes in the target area 102. The real-time point cloud 1052 is determined as the point cloud 1071 to be processed. The real-time point cloud 1053 is determined as the point cloud 1072 to be processed. The real-time point cloud 1054 is determined as the point cloud 1073 to be processed. Finally, according to the point cloud set 107 to be processed, the point cloud map 108 associated with the target area 102 is updated, so that an updated point cloud map 109 can be obtained.

The electronic device 101 may be hardware or software. When the electronic device is hardware, the electronic device may be implemented as a distributed cluster formed by a plurality of servers or terminal devices, or may be implemented as a single server or a single terminal device. When the electronic device is embodied as software, it may be installed in the above-listed hardware devices. It may be implemented, for example, as multiple software or software modules to provide distributed services, or as a single software or software module. And is not particularly limited herein.

It should be understood that the number of electronic devices in fig. 1-2 is merely illustrative. There may be any number of electronic devices, as desired for implementation.

With continued reference to fig. 3, a flow 300 of some embodiments of a point cloud map updating method according to the present disclosure is shown. The point cloud map updating method comprises the following steps:

step 301, in the process of moving from a first location to a second location in a target area, acquiring a real-time point cloud set corresponding to the target area.

In some embodiments, an executing entity (e.g., the electronic device shown in fig. 1 or fig. 2) of the point cloud map updating method may acquire a real-time point cloud set corresponding to a target area during a process of moving from a first location to a second location within the target area. The target area may be a predetermined area in which whether a scene to be checked is changed or not. The first location may be a starting location of a route in the target area. The second location may be a termination location of a route within the target area. It should be noted that, in the process of moving from the first location to the second location in the target area, a real-time point cloud set corresponding to each of multiple times needs to be acquired to determine an area in the target area where the scene change occurs. The real-time point cloud set corresponding to a certain moment can reflect scene layout information of a current scene.

As an example, the executing entity may receive the real-time point cloud set sent by the point cloud collecting terminal in the process of moving from a first location to a second location in the target area. The point cloud collection terminal may be a drawing device equipped with a high-precision laser radar, an inertial navigation sensor, and other sensors, such as an unmanned distribution vehicle, an unmanned vehicle, and the like.

And 302, screening at least one real-time point cloud representing scene change from the real-time point cloud set to serve as a point cloud set to be processed.

In some embodiments, the executing subject may filter at least one real-time point cloud representing scene changes from the real-time point cloud set as a point cloud set to be processed. Each of the at least one real-time point cloud may be a point cloud map, where a scene in the target area may change.

As an example, the executing entity may filter at least one real-time point cloud representing the scene change from the real-time point cloud set as the point cloud set to be processed in various ways.

And 303, updating the point cloud map associated with the target area according to the point cloud set to be processed.

In some embodiments, the executing entity may update the point cloud map associated with the target area according to the cloud set of points to be processed.

As an example, the updating, by the executing entity, the point cloud map associated with the target area according to the cloud set of points to be processed may include the following steps:

and step one, determining a region set to be processed according to the point cloud set to be processed. The area to be processed may be an area formed by taking the point cloud to be processed as a center and taking the target value as a radius.

And secondly, performing real-time point cloud rescanning on each to-be-processed area in the to-be-processed area set in the point cloud map so as to update the point cloud map.

According to the point cloud map updating method of some embodiments of the disclosure, the point cloud set to be processed can be determined quickly and efficiently. Furthermore, the point cloud map can be updated, so that the point cloud map is more accurate. Specifically, the accuracy of determining the transformation area through human monitoring is low, which may cause problems such as missing reports and delay. Therefore, the accuracy of the subsequent point cloud map is low. In addition, the manual monitoring is time and labor consuming. Based on this, the point cloud map updating method according to some embodiments of the present disclosure may obtain the real-time point cloud set corresponding to the target area in the process of moving from the first location to the second location in the target area. Here, a real-time point cloud set corresponding to the target area is obtained as data support for subsequently determining an area in the point cloud map where scene change occurs. And then, screening at least one real-time point cloud representing scene change from the real-time point cloud set to serve as a point cloud set to be processed. By determining the point cloud set to be processed, the area of the point cloud map where the scene is changed can be determined more accurately in the follow-up process. And the subsequent point cloud map is updated more pertinently. The side surface also improves the updating efficiency of the point cloud map. And finally, updating the point cloud map associated with the target area according to the point cloud set to be processed so as to enable the point cloud map to be more accurate.

With further reference to fig. 4, a flow 400 of further embodiments of a point cloud map updating method according to the present disclosure is shown. The point cloud map updating method comprises the following steps:

step 401, in the process of moving from a first location to a second location in a target area, acquiring a real-time point cloud set corresponding to the target area.

In some embodiments, the specific implementation of step 401 and the technical effect thereof may refer to step 301 in the embodiment corresponding to fig. 3, which is not described herein again.

And 402, removing at least one of the first real-time point cloud subset, the second real-time point cloud subset and the third real-time point cloud subset from the real-time point cloud set to obtain a removed real-time point cloud set.

In some embodiments, an executing subject (e.g., the electronic device shown in fig. 1) may remove at least one of the first and second subsets of real-time point clouds from the set of real-time point clouds, resulting in a removed set of real-time point clouds.

As an example, the executing entity may remove the first subset of real-time point clouds from the set of real-time point clouds, resulting in a removed set of real-time point clouds.

In some optional implementations of some embodiments, the removing at least one of the first and second subsets of real-time point clouds from the set of real-time point clouds to obtain a removed set of real-time point clouds may include:

in a first step, the executing agent may determine the point cloud set that is the static point cloud from the real-time point cloud set as the first real-time point cloud subset. The point cloud set that is a static point cloud in the point cloud map may be a point cloud set corresponding to at least one object in a scene that does not change in the target area.

And a second step of determining, by the executing agent, the point cloud set that is the real-time point cloud set and is a dynamic point cloud as the second real-time point cloud subset in response to detecting that the dynamic point cloud exists in the real-time point cloud set. The point cloud set in the point cloud map, which is a dynamic point cloud, may be a point cloud set corresponding to at least one object in a scene that changes in a target area for a short time. The executing body can detect whether a dynamic point cloud exists in the real-time point cloud set or not through the perception module. For example, the at least one object in the short-time scene may include: pedestrians and automobiles.

And thirdly, the executing body can remove the first real-time point cloud subset and the second real-time point cloud subset in the real-time point cloud set to obtain the removed real-time point cloud set.

Optionally, the determining the point cloud set in which the real-time point cloud set is a static point cloud as the first real-time point cloud subset may include:

in the first step, in response to detecting that the same point cloud exists between the point cloud set corresponding to the point cloud map and the real-time point cloud set, the executing entity may determine at least one point cloud that is the same between the point cloud set corresponding to the point cloud map and the real-time point cloud set as a target point cloud set.

And secondly, the executing body can determine a point cloud set and a target point cloud set associated with a target ground in a point cloud set corresponding to the point cloud map as the first real-time point cloud subset. Wherein, the point cloud set associated with the target ground can be a point cloud set representing target ground information.

And 403, determining the removed real-time point cloud set as the point cloud set to be processed.

In some embodiments, the executing entity may determine the removed real-time point cloud set as the to-be-processed point cloud set.

Step 404, obtaining a voxel grid information set corresponding to the target region and region information corresponding to each voxel grid information in the voxel grid information set.

In some embodiments, the executing body may obtain a voxel grid information set corresponding to the target region and region information corresponding to each voxel grid information in the voxel grid information set. Wherein the target region may be divided into a plurality of voxel grids. Each voxel grid corresponds to voxel grid information. The voxel grid information may be information of the location where the voxel grid is located. For example, the position information may be coordinates corresponding to a voxel grid. Each of the plurality of voxel grids may be a three-dimensional volumetric region. For example, the voxel grid may be a fixed size cube. Thus, each voxel grid corresponds to a cubic region. The region information of the voxel grid may be information of a region surrounded by respective coordinates corresponding to the voxel grid. As an example, the set of coordinates corresponding to the voxel grid may include: (1,1),(1,3),(4,1),(4,3). The region information corresponding to the voxel grid may be: the values of the abscissa are between 1 and 4 and the values of the ordinate are between 1 and 3.

It should be noted that the target region may be divided into each voxel grid by the following steps:

firstly, determining a map coordinate system corresponding to the point cloud map.

And secondly, determining a target point from the map coordinate system as a reference center divided into each voxel grid. For example, the target point may be a center point in the moving process from the first location to the second location in the target area.

And thirdly, determining the size of the edge in the voxel grid.

As an example, the size of the edges in the voxel grid may be set in accordance with the resolution of the reference point cloud map and the real-time point cloud. As an example, the size of the edges of the voxel grid may be in the range of 0.15-0.3 meters.

And fourthly, dividing the target area into each voxel grid according to the size of the edges in the voxel grid and the reference center.

Step 405, determining voxel grid information corresponding to each point cloud to be processed in the point cloud set to be processed according to the area information corresponding to each voxel grid information in the voxel grid information set, and obtaining a voxel grid information subset.

In some embodiments, the executing body may determine, according to area information corresponding to each voxel grid information in the voxel grid information set, voxel grid information corresponding to each point cloud to be processed in the point cloud set to be processed, to obtain a voxel grid information subset.

As an example, the executing entity may compare the coordinates of each point cloud to be processed in the point cloud set to be processed with the region information of each voxel grid in the voxel grid set, so as to obtain a voxel grid information subset.

In some optional implementation manners of some embodiments, the determining, according to the area information corresponding to each voxel grid information in the voxel grid information set, voxel grid information corresponding to each point cloud to be processed in the point cloud set to be processed to obtain a voxel grid information subset includes:

firstly, performing coordinate conversion on each point cloud to be processed in the point cloud set to be processed to generate a corresponding map coordinate, and obtaining a map coordinate set. And the coordinates of each real-time point cloud in the acquired real-time point cloud set are coordinates under a real-time point cloud coordinate system. Therefore, the point cloud to be processed is also the coordinate under the real-time point cloud coordinate system. Therefore, the point cloud to be processed needs to be subjected to coordinate conversion and converted into coordinates in a map coordinate system, so that the subsequent voxel grid information can be determined.

And secondly, determining voxel grid information corresponding to each point cloud to be processed in the point cloud set to be processed according to the map coordinate set and the area information corresponding to each voxel grid information in the voxel grid information set to obtain a voxel grid information subset.

As an example, the execution subject may compare each map coordinate in the map coordinate set with the region information of each voxel grid in the voxel grid set, and may obtain the voxel grid information subset.

And 406, determining point cloud change area information in the target area according to the voxel grid information subset.

In some embodiments, the execution subject may determine point cloud change region information in the target region according to the voxel grid information subset.

For example, the executing entity may first fuse the region information corresponding to each voxel grid in the voxel grid subset to obtain fused region information. Then, the fused area information is determined as point cloud change area information in the target area.

In some optional implementations of some embodiments, the determining a point cloud variation region in the target region according to the voxel grid information subset may include:

first, index information corresponding to each voxel grid information in the voxel grid information set is acquired. The index information corresponding to the voxel grid information may be determined according to each coordinate corresponding to the voxel grid. The index information may be an index value.

As an example, the respective coordinates corresponding to the voxel grid information are (1,1), (1,3), (4,1), (4, 3). Thus, the index value corresponding to the voxel grid information may be: 2.25.

and secondly, determining the index information corresponding to each voxel grid information in the voxel grid information subset according to the index information corresponding to each voxel grid information in the voxel grid information set to obtain an index information set.

And thirdly, determining the point cloud association times corresponding to each index information in the index information set. The point cloud association times are times associated with each real-time point cloud in a real-time point cloud set group corresponding to at least one moment before the current moment.

As an example, the execution subject may determine the point cloud association times corresponding to each index information in the index information set by querying a table representing the association relationship between the index information and the point cloud association times.

It should be noted that, in order to improve the efficiency of the search and the search, the voxel grid information may be stored by using a hash table. The key in the hash table may be index information of the voxel grid. The key value in the hash table may be the point cloud association number.

And fourthly, in response to the fact that the point cloud association times corresponding to at least one index information in the index information set are larger than a first target value, determining the index information of which the point cloud association times meet a preset condition in the at least one index information as target index information to obtain a target index information set. For example, the first target value may be "0".

As an example, in response to determining that at least one index information set has a point cloud association frequency greater than a first target value, the executing entity may determine, as target index information, index information whose point cloud association frequency is greater than a predetermined threshold value, and obtain the target index information set.

And fifthly, determining the voxel grid information set corresponding to the target index information set as the first target voxel grid information set.

Optionally, the foregoing steps further include: for each index information in the index information set, the execution body may determine an addition result of the point cloud association frequency corresponding to the index information and the second target value as the point cloud association frequency corresponding to the index information. As an example, the above-mentioned second target value may be 1.

firstly, determining the point cloud association times corresponding to each voxel grid information in the voxel grid information subset.

As an example, the executing body may determine the point cloud association times corresponding to each voxel grid information in the voxel grid information subset by querying a pre-constructed table representing the association relationship between the voxel grid information and the point cloud association times.

And secondly, in response to the fact that the point cloud association times corresponding to at least one piece of voxel grid information in the voxel grid information subset are larger than a first target value, determining the voxel grid information of which the point cloud association times meet a preset condition in the at least one piece of voxel grid information as first target voxel grid information to obtain a first target voxel grid information set.

As an example, in response to that the point cloud association number corresponding to at least one voxel grid information in the voxel grid information subset is greater than a first target value, the executing entity may determine, as the first target voxel grid information, voxel grid information in which the point cloud association number is greater than a predetermined threshold in the at least one voxel grid information, to obtain a first target voxel grid information set.

Optionally, the foregoing steps further include: for each voxel grid information in the voxel grid information subset, the executing body may determine the point cloud association frequency corresponding to the voxel grid information as the point cloud association frequency corresponding to the voxel grid information. As an example, the above-described second target value may be "1".

Optionally, the foregoing steps further include: the executing body may store the first target voxel grid information set, and determine a region corresponding to the first target voxel grid information set as a point cloud variation region in the target region.

As an example, the execution subject may store the first target voxel grid information set in a cache.

Step 407, updating the point cloud map according to the point cloud change area information.

In some embodiments, the executing entity may update the point cloud map according to the point cloud change area information.

As an example, the executing entity may perform point cloud update on a point cloud change area corresponding to point cloud change area information in a point cloud map.

As can be seen from fig. 4, compared with the description of some embodiments corresponding to fig. 3, the flow 400 of the point cloud map updating method in some embodiments corresponding to fig. 4 highlights the specific steps of determining the point cloud set to be processed and determining the point cloud change area information. Therefore, the solutions described in the embodiments can determine the point cloud sets to be processed more accurately and efficiently, and can determine the point cloud change area information in the target area more accurately according to the point cloud sets to be processed. Therefore, the point cloud map is updated according to the point cloud change area information, so that the point cloud map is more accurate.

With further reference to fig. 5, as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a point cloud map updating apparatus, which correspond to those shown in fig. 3, and which may be applied in various electronic devices.

As shown in fig. 5, a point cloud map updating apparatus 500 includes: an acquisition unit 501, a screening unit 502 and an updating unit 503. The acquiring unit 501 is configured to acquire a real-time point cloud set corresponding to a target area in the process of moving from a first location to a second location in the target area; a screening unit 502 configured to screen at least one real-time point cloud representing scene variation from the real-time point cloud set as a point cloud set to be processed; the updating unit 503 is configured to update the point cloud map associated with the target area according to the to-be-processed point cloud set.

In some optional implementations of some embodiments, the filtering unit 502 in the point cloud map updating apparatus 500 is further configured to: removing at least one of the first and second subsets of real-time point clouds from the real-time point cloud set to obtain a removed real-time point cloud set; and determining the removed real-time point cloud set as the point cloud set to be processed.

In some optional implementations of some embodiments, the filtering unit 502 in the point cloud map updating apparatus 500 is further configured to: determining the point cloud set which is the static point cloud in the real-time point cloud set as the first real-time point cloud subset; in response to detecting that a dynamic point cloud exists in the real-time point cloud set, determining the point cloud set in which the real-time point cloud set is a dynamic point cloud as the second real-time point cloud subset; and removing the first real-time point cloud subset and the second real-time point cloud subset in the real-time point cloud set to obtain the removed real-time point cloud set.

In some optional implementations of some embodiments, the filtering unit 502 in the point cloud map updating apparatus 500 is further configured to: in response to detecting that the point cloud sets corresponding to the point cloud map and the real-time point cloud sets have the same point cloud, determining at least one point cloud corresponding to the point cloud map and the same point cloud set between the real-time point cloud sets as a target point cloud set; and determining a point cloud set associated with a target ground in a point cloud set corresponding to the point cloud map and the target point cloud set as the first real-time point cloud subset.

In some optional implementations of some embodiments, the updating unit 503 in the point cloud map updating apparatus 500 is further configured to: acquiring a voxel grid information set corresponding to the target area and area information corresponding to each voxel grid information in the voxel grid information set; determining voxel grid information corresponding to each point cloud to be processed in the point cloud set to be processed according to the area information corresponding to each voxel grid information in the voxel grid information set to obtain a voxel grid information subset; determining point cloud change area information in the target area according to the voxel grid information subset; and updating the point cloud map according to the point cloud change area information.

In some optional implementations of some embodiments, the updating unit 503 in the point cloud map updating apparatus 500 is further configured to: acquiring index information corresponding to each voxel grid information in the voxel grid information set; according to the index information corresponding to each voxel grid information in the voxel grid information set, determining the index information corresponding to each voxel grid information in the voxel grid information subset to obtain an index information set; determining the point cloud association times corresponding to each index information in the index information set; in response to the fact that the point cloud association times corresponding to at least one index information in the index information set are larger than a first target value, determining the index information of which the point cloud association times meet a preset condition in the at least one index information as target index information to obtain a target index information set; and determining the voxel grid information set corresponding to the target index information set as the first target voxel grid information set.

In some optional implementations of some embodiments, the point cloud map updating apparatus 500 further includes: a first determination unit (not shown). Wherein the first determination unit may be configured to: and determining the addition result of the point cloud association times corresponding to the index information and a second target value as the point cloud association times corresponding to the index information for each index information in the index information set.

In some optional implementations of some embodiments, the updating unit 503 in the point cloud map updating apparatus 500 is further configured to: determining the point cloud association times corresponding to each voxel grid information in the voxel grid information subset; and in response to the fact that the point cloud association times corresponding to at least one piece of voxel grid information in the voxel grid information subset are larger than a first target value, determining the voxel grid information of which the point cloud association times meet a preset condition in the at least one piece of voxel grid information as first target voxel grid information to obtain a first target voxel grid information set.

In some optional implementations of some embodiments, the point cloud map updating apparatus 500 further includes: a second determination unit (not shown). Wherein the second determination unit may be configured to: and determining the addition result of the point cloud association times corresponding to the voxel grid information and a second target value as the point cloud association times corresponding to the voxel grid information for each voxel grid information in the voxel grid information subset.

In some optional implementations of some embodiments, the point cloud map updating apparatus 500 further includes: a storage determination unit (not shown in the figure). Wherein the storage determination unit may be configured to: and storing the first target voxel grid information set, and determining a region corresponding to the first target voxel grid information set as a point cloud change region in the target region.

In some optional implementations of some embodiments, the updating unit 503 in the point cloud map updating apparatus 500 is further configured to: performing coordinate conversion on each point cloud to be processed in the point cloud set to be processed to generate a corresponding map coordinate to obtain a map coordinate set; and determining voxel grid information corresponding to each point cloud to be processed in the point cloud set to be processed according to the map coordinate set and the area information corresponding to each voxel grid information in the voxel grid information set to obtain a voxel grid information subset.

It will be understood that the elements described in the apparatus 500 correspond to various steps in the method described with reference to fig. 3. Thus, the operations, features and resulting advantages described above with respect to the method are also applicable to the apparatus 500 and the units included therein, and are not described herein again.

Referring now to FIG. 6, a block diagram of an electronic device (e.g., the electronic device of FIG. 1) 600 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 6, electronic device 600 may include a processing means (e.g., central processing unit, graphics processor, etc.) 601 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data necessary for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM 602, and the RAM603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

Generally, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While fig. 6 illustrates an electronic device 600 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 6 may represent one device or may represent multiple devices as desired.

In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In some such embodiments, the computer program may be downloaded and installed from a network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. The computer program, when executed by the processing device 601, performs the above-described functions defined in the methods of some embodiments of the present disclosure.

It should be noted that the computer readable medium described above in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring a real-time point cloud set corresponding to a target area in the process of moving from a first place to a second place in the target area; screening at least one real-time point cloud representing scene change from the real-time point cloud set to serve as a point cloud set to be processed; and updating the point cloud map associated with the target area according to the point cloud set to be processed.

Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in some embodiments of the present disclosure may be implemented by software, and may also be implemented by hardware. The described units may also be provided in a processor, and may be described as: a processor includes an acquisition unit, a filtering unit, and an updating unit. The names of the units do not limit the units themselves in some cases, for example, the acquiring unit may also be described as a "unit acquiring a real-time point cloud set corresponding to a target area during moving from a first location to a second location in the target area".

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.

Claims

1. A point cloud map updating method comprises the following steps:

the method comprises the steps that in the process of moving from a first place to a second place in a target area, a real-time point cloud set corresponding to the target area is obtained;

screening at least one real-time point cloud representing scene change from the real-time point cloud set to serve as a point cloud set to be processed;

and updating the point cloud map associated with the target area according to the point cloud set to be processed.

2. The method of claim 1, wherein the screening of the set of real-time point clouds for at least one real-time point cloud characterizing scene changes as a set of point clouds to be processed comprises:

removing at least one of the first and second subsets of real-time point clouds from the real-time point cloud set to obtain a removed real-time point cloud set;

and determining the removed real-time point cloud set as the point cloud set to be processed.

3. The method of claim 2, wherein removing at least one of the first and second subsets of real-time point clouds from the set of real-time point clouds, resulting in a removed set of real-time point clouds comprises:

determining the point cloud set which is static point cloud in the real-time point cloud set as the first real-time point cloud subset;

in response to detecting the presence of a dynamic point cloud in the set of real-time point clouds, determining a set of point clouds that is a dynamic point cloud in the set of real-time point clouds as the second subset of real-time point clouds;

and removing the first real-time point cloud subset and the second real-time point cloud subset in the real-time point cloud set to obtain the removed real-time point cloud set.

4. The method of claim 3, wherein the determining the set of point clouds that is a static point cloud as the first subset of real-time point clouds comprises:

in response to detecting that the same point cloud exists between the point cloud set corresponding to the point cloud map and the real-time point cloud set, determining at least one point cloud which is the same between the point cloud set corresponding to the point cloud map and the real-time point cloud set as a target point cloud set;

and determining a target point cloud set and a target point cloud set associated with a target ground in a point cloud set corresponding to the point cloud map as the first real-time point cloud subset.

5. The method of claim 2, wherein the updating the point cloud map associated with the target area according to the cloud set of points to be processed comprises:

acquiring a voxel grid information set corresponding to the target area and area information corresponding to each voxel grid information in the voxel grid information set;

determining voxel grid information corresponding to each point cloud to be processed in the point cloud set to be processed according to the region information corresponding to each voxel grid information in the voxel grid information set to obtain a voxel grid information subset;

determining point cloud change region information in the target region according to the voxel grid information subset;

and updating the point cloud map according to the point cloud change area information.

6. The method of claim 5, wherein the determining a point cloud variation region in the target region from the subset of voxel grid information comprises:

acquiring index information corresponding to each voxel grid information in the voxel grid information set;

according to index information corresponding to each voxel grid information in the voxel grid information set, determining the index information corresponding to each voxel grid information in the voxel grid information subset to obtain an index information set;

determining the point cloud association times corresponding to each index information in the index information set;

in response to the fact that the point cloud association times corresponding to at least one index information in the index information set are larger than a first target value, determining the index information of which the point cloud association times meet a preset condition in the at least one index information as target index information to obtain a target index information set;

and determining the voxel grid information set corresponding to the target index information set as the first target voxel grid information set.

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

and determining the addition result of the point cloud association times corresponding to the index information and the second target numerical value as the point cloud association times corresponding to the index information for each index information in the index information set.

8. The method of claim 5, wherein the determining a point cloud variation region in the target region from the subset of voxel grid information comprises:

determining the point cloud association times corresponding to each voxel grid information in the voxel grid information subset;

and in response to the fact that the point cloud association times corresponding to at least one piece of voxel grid information in the voxel grid information subset are larger than a first target numerical value, determining the voxel grid information of which the point cloud association times meet a preset condition in the at least one piece of voxel grid information as first target voxel grid information to obtain a first target voxel grid information set.

9. The method of claim 8, wherein the method further comprises:

and determining the addition result of the point cloud association times corresponding to the voxel grid information and a second target value as the point cloud association times corresponding to the voxel grid information for each voxel grid information in the voxel grid information subset.

10. The method of claim 6 or 8, wherein the method further comprises:

and storing the first target voxel grid information set, and determining a region corresponding to the first target voxel grid information set as a point cloud change region in the target region.

11. The method according to claim 5, wherein the determining voxel grid information corresponding to each point cloud to be processed in the point cloud set to be processed according to the region information corresponding to each voxel grid information in the voxel grid information set to obtain a voxel grid information subset comprises:

performing coordinate conversion on each point cloud to be processed in the point cloud set to be processed to generate a corresponding map coordinate to obtain a map coordinate set;

and determining voxel grid information corresponding to each point cloud to be processed in the point cloud set to be processed according to the map coordinate set and the area information corresponding to each voxel grid information in the voxel grid information set to obtain a voxel grid information subset.

12. A point cloud map updating apparatus comprising:

the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is configured to acquire a real-time point cloud set corresponding to a target area in the process of moving from a first place to a second place in the target area;

a screening unit configured to screen at least one real-time point cloud characterizing scene changes from the set of real-time point clouds as a set of point clouds to be processed;

and the updating unit is configured to update the point cloud map associated with the target area according to the point cloud set to be processed.

13. An electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon,

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-11.

14. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any one of claims 1-11.