Point cloud map construction method, device and electronic device

Abstract

The present application discloses a point cloud map construction method, device and electronic device, belonging to the field of point cloud map construction technology. The method includes: when the driverless vehicle moves along a preset route, collecting environmental point cloud information to generate a first local point cloud map; filtering out preset static targets in the first local point cloud map to obtain a second local point cloud map; filtering out dynamic targets in the second local point cloud map to obtain a third local point cloud map; and constructing a target point cloud map based on each third local point cloud map generated during the driverless vehicle's movement along the preset route. Through the point cloud map construction scheme disclosed in the present application, dynamic targets and static targets with less reference value in the point cloud map can be filtered out to obtain a high-quality point cloud map, so that more accurate location information can be obtained during subsequent positioning.

Description

Technical Field

[0001] Embodiments of the present invention relate to the technical field of point cloud map construction, and in particular to a point cloud map construction method, device and electronic device. Background Art

[0002] In the field of unmanned vehicle driving, point cloud maps are often used to express scene information. Point cloud maps usually include multiple point cloud points with semantic information, as well as the three-dimensional position information of each point cloud point in the world coordinate system; these point cloud points can indicate the specific distribution of different objects in a scene in space.

[0003] In actual application, the driverless car builds a point cloud map based on the previously collected environmental point cloud information, and uses the characteristics of the currently collected point cloud information to match the point cloud map to achieve the purpose of positioning. However, there is a problem with this positioning method. When the driverless car builds a point cloud map, the surrounding environment is dynamic. If there are dynamic targets, the positioning accuracy will be low in the subsequent positioning process. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a point cloud map construction method, device and electronic device, which can solve the problem of low positioning accuracy of the point cloud map created by the unmanned vehicle in the subsequent positioning process existing in the prior art.

[0005] In order to solve the above technical problems, this application is implemented as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for constructing a point cloud map, comprising:

[0007] When the driverless car moves along a preset route, environmental point cloud information is collected to generate a first local point cloud map;

[0008] Filtering out the preset static target in the first local point cloud map to obtain a second local point cloud map;

[0009] Filtering out dynamic targets in the second partial point cloud map to obtain a third partial point cloud map;

[0010] A target point cloud map is constructed based on the third local point cloud maps generated during the movement of the unmanned vehicle along the preset route.

[0011] Optionally, the step of collecting environmental point cloud information to generate a first local point cloud map while the unmanned vehicle moves along a preset route includes:

[0012] When the unmanned vehicle moves along a preset route, the laser radar installed on the unmanned vehicle determines the distance between the unmanned vehicle and each object in the surrounding environment based on the time interval between the transmitted and received pulse signals, as the collected environmental point cloud information;

[0013] A first local point cloud map is generated based on the collected environmental point cloud information, wherein the first local point cloud map is used to represent the environmental information around the unmanned vehicle at a certain moment.

[0014] Optionally, the step of filtering out the preset static target in the first local point cloud map to obtain the second local point cloud map includes:

[0015] Performing target segmentation processing on the first local point cloud map to obtain objects contained in the first local point cloud map, and then performing color marking processing on each of the objects, wherein each of the objects corresponds to a plurality of point cloud information, each of the point cloud information corresponds to a distance value, and when performing color marking, color marking is performed on each of the objects contained in the first local point cloud map based on a predetermined correspondence between color and distance;

[0016] The preset static targets in each of the color-coded objects are filtered out to obtain the second local point cloud map.

[0017] Optionally, the step of filtering out dynamic targets in the second local point cloud map to obtain a third local point cloud map includes:

[0018] Determine the dynamic target based on the point cloud information in the first partial point cloud map collected twice successively;

[0019] Dynamic targets in the second local point cloud map are filtered out to obtain a third local point cloud map.

[0020] Optionally, the step of determining the dynamic target based on the point cloud information in the first partial point cloud map collected twice successively includes:

[0021] After a preset time interval, the environment point cloud information is collected again to generate a first local point cloud map, and static targets in the first local point cloud map are filtered out to obtain a fourth local point cloud map;

[0022] Determine the position change information of the unmanned vehicle when collecting the first local point cloud map twice;

[0023] updating the point cloud information of each object contained in the fourth partial point cloud map according to the position change information to obtain a fifth partial point cloud map;

[0024] By comparing the fifth partial point cloud map with the second partial point cloud map, objects whose point cloud information change is outside a preset range are determined as dynamic targets.

[0025] In a second aspect, an embodiment of the present application provides a point cloud map construction device, comprising:

[0026] A collection module, used to collect environmental point cloud information and generate a first local point cloud map when the unmanned vehicle moves along a preset route;

[0027] A first filtering module, used to filter out preset static targets in the first local point cloud map to obtain a second local point cloud map;

[0028] A second filtering module, used for filtering out dynamic targets in the second local point cloud map to obtain a third local point cloud map;

[0029] A construction module is used to construct a target point cloud map based on each of the third local point cloud maps generated during the movement of the unmanned vehicle along the preset route.

[0030] Optionally, the acquisition module includes:

[0031] The first submodule is used to determine the distance between the unmanned vehicle and each object in the surrounding environment based on the time interval of the transmitted and received pulse signals by the laser radar installed on the unmanned vehicle during the movement of the unmanned vehicle along the preset route, as the collected environmental point cloud information;

[0032] The second submodule is used to generate a first local point cloud map based on the collected environmental point cloud information, wherein the first local point cloud map is used to represent the environmental information around the unmanned vehicle at a certain moment.

[0033] Optionally, the first filtering module includes:

[0034] The third submodule is used to perform target segmentation processing on the first local point cloud map to obtain each object contained in the first local point cloud map, and then perform color marking processing on each of the objects, wherein each of the objects corresponds to a point cloud information, each of the point cloud information corresponds to a distance value, and when performing color marking, the objects contained in the first local point cloud map are color marked based on a predetermined correspondence between color and distance;

[0035] The fourth submodule is used to filter out the preset static targets in each of the color-coded objects to obtain the second local point cloud map.

[0036] Optionally, the second filtering module includes:

[0037] A fifth submodule is used to determine a dynamic target based on point cloud information in the first partial point cloud map collected twice successively;

[0038] The sixth submodule is used to filter out dynamic targets in the second local point cloud map to obtain a third local point cloud map.

[0039] Optionally, the fifth submodule includes:

[0040] A collection unit, configured to collect environmental point cloud information again after a preset time interval to generate a first local point cloud map, and filter out static targets in the first local point cloud map to obtain a fourth local point cloud map;

[0041] A position change information determining unit, used to determine the position change information of the unmanned vehicle when the first local point cloud map is collected twice in succession;

[0042] an updating unit, configured to update the point cloud information of each object contained in the fourth partial point cloud map according to the position change information, so as to obtain a fifth partial point cloud map;

[0043] The comparison unit is used to compare the fifth local point cloud map with the second local point cloud map, and determine the object whose point cloud information change is outside a preset range as a dynamic target.

[0044] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect.

[0045] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0046] By adopting the above technical solution, compared with the prior art, the technical effects of this application are as follows:

[0047] The point cloud map construction method provided in the embodiment of the present application collects environmental point cloud information to generate a first local point cloud map when the driverless car moves along a preset route; filters out preset static targets in the first local point cloud map to obtain a second local point cloud map; filters out dynamic targets in the second local point cloud map to obtain a third local point cloud map; and constructs a target point cloud map based on each third local point cloud map generated during the movement of the driverless car along the preset route. This solution can filter out dynamic targets and static targets with low reference value in the point cloud map to obtain a high-quality point cloud map, so that more accurate location information can be obtained during subsequent positioning. Specifically, on the one hand, it avoids dynamic targets interfering with positioning, thereby improving the accuracy of positioning results; on the other hand, it avoids static targets with low reference value to increase the amount of calculation, which is conducive to improving positioning speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0049] Figure 1 is a flowchart showing the steps of a method for constructing a point cloud map according to an embodiment of the present application;

[0050] Figure 2 is a schematic diagram showing the correspondence between distance and color in an embodiment of the present application;

[0051] Figure 3 is a structural block diagram of a point cloud map construction device according to an embodiment of the present application;

[0052] Figure 4 is a structural block diagram of an electronic device according to an embodiment of the present application;

[0053] Figure 5 It is a structural block diagram of another electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0055] The device detection method provided in the embodiment of the present application is described in detail below through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0056] Reference Figure 1 , showing a step flow chart of a point cloud map construction method according to an embodiment of the present application.

[0057] The point cloud map construction method of the embodiment of the present application includes the following steps:

[0058] Step 101: While the driverless vehicle is moving along a preset route, environmental point cloud information is collected to generate a first local point cloud map.

[0059] In the actual implementation process, a laser radar can be set on the unmanned vehicle, and the laser radar is used to collect information during the construction of the point cloud map. The specific collection method can be: when the unmanned vehicle moves along the preset route, the laser radar installed on the unmanned vehicle determines the distance between each object in the surrounding environment based on the time interval of the transmitted and received pulse signals, as the collected environmental point cloud information; based on the collected environmental point cloud information, a first local point cloud map is generated, wherein the first local point cloud map is used to characterize the environmental information around the unmanned vehicle at a certain moment. Through the point cloud information in the first local point cloud map, it is possible to determine the objects contained in the surrounding environment of the unmanned vehicle when collecting, as well as the distance between each object and the laser radar.

[0060] The preset time interval can be flexibly set by those skilled in the art, and is not specifically limited in this application. Among them, the time interval between the pulse signal emitted by the laser radar transmitter and the reflected pulse signal received by the receiver is proportional to the distance between the laser radar and the target object.

[0061] In the embodiment of the present application, the laser radar installed on the unmanned vehicle is selected to collect information during the point cloud map construction process because the laser radar is low in cost and can reduce the cost of the unmanned vehicle, and the data collected by the laser radar is highly accurate.

[0062] Step 102: Filter out the preset static targets in the first local point cloud map to obtain a second local point cloud map.

[0063] That is, the point cloud map construction method provided in the embodiment of the present application is aimed at the problem that when the driverless car builds the point cloud map, the surrounding environment is dynamic. If there are dynamic targets, it will lead to low positioning accuracy in the subsequent positioning process. After creative labor and comprehensive consideration of various factors, a solution is determined to exclude dynamic targets in the environment when constructing the point cloud map to ensure positioning accuracy. Not only that, in addition to dynamic targets, there are also some static targets in the point cloud map, such as the ground. These static targets provide less effective information for the positioning process, and will cause the positioning process to have a large amount of calculation, affecting the real-time performance of the positioning process. Therefore, in the embodiment of the present application, static targets with less reference value in the environment, that is, the aforementioned preset static targets, will be excluded when constructing the point cloud map, thereby reducing the amount of calculation consumed by positioning.

[0064] After filtering out the preset static targets in the first partial point cloud map, the dynamic targets in the point cloud map are identified and the identified dynamic targets are filtered out. A feasible method may be: determining the dynamic targets based on the point cloud information in the first partial point cloud map collected twice successively; filtering out the dynamic targets in the second partial point cloud map to obtain the third partial point cloud map.

[0065] In the actual implementation process, the laser radar installed on the driverless car collects point cloud information once at a preset interval, and the processor generates a first local point cloud map based on the point cloud information collected by the laser radar. That is, during the overall process of the driverless car moving on the preset route, if point cloud information is collected N times, the processor will generate N first local point cloud maps.

[0066] When determining a dynamic target contained in a local point cloud map, it is necessary to combine it with the first local point cloud map generated immediately afterwards and compare the two to determine it.

[0067] Step 103: Filter out dynamic targets in the second local point cloud map to obtain a third local point cloud map.

[0068] In the process of constructing the point cloud map, for each second local point cloud map, dynamic targets in the environment are excluded, which can effectively avoid dynamic targets interfering with positioning, and can improve the accuracy of the positioning results obtained when positioning is performed subsequently based on the constructed point cloud map.

[0069] It should be noted that step 101 to step 103 is a process of filtering out dynamic targets and static targets from a single first local point cloud map, and obtaining a third local point cloud map after filtering. In the actual implementation process, it is necessary to repeatedly execute the above process to process each first local point cloud map generated during the driving of the unmanned vehicle along the preset route to obtain the corresponding third local point cloud map.

[0070] Step 104: construct a target point cloud map based on the third local point cloud maps generated when the driverless vehicle moves along the preset route.

[0071] When constructing the target point cloud map based on each third local point cloud map, any appropriate map synthesis method can be used, and this embodiment of the present application does not impose any specific restrictions on this. For example, a simple splicing method, a method of integrating after checking the same point cloud information, etc. can be used.

[0072] The point cloud map construction method provided in the embodiment of the present application collects environmental point cloud information to generate a first local point cloud map during the movement of the unmanned vehicle along a preset route; filters out preset static targets in the first local point cloud map to obtain a second local point cloud map; filters out dynamic targets in the second local point cloud map to obtain a third local point cloud map; and constructs a target point cloud map based on each third local point cloud map generated during the movement of the unmanned vehicle along the preset route. This solution can filter out dynamic targets and static targets with less reference value, i.e., preset static targets, in the point cloud map to obtain a high-quality point cloud map, so that more accurate location information can be obtained during subsequent positioning. Specifically, on the one hand, it avoids dynamic targets interfering with positioning, thereby improving the accuracy of positioning results; on the other hand, it avoids static targets with less reference value to increase the amount of calculation, which is conducive to improving positioning speed.

[0073] In an optional embodiment, filtering out the preset static target in the first local point cloud map to obtain the second local point cloud map includes the following steps:

[0074] Step 1: performing target segmentation processing on the first local point cloud map to obtain each object contained in the first local point cloud map, and then performing color marking processing on each object;

[0075] The objects in the first partial point cloud map may be referred to as environmental objects, including static objects and dynamic objects. The objects in the first partial point cloud map may include, but are not limited to, vehicles, pedestrians, bicycles, signs, lamp poles, and the ground.

[0076] Each object corresponds to multiple point cloud information, each point cloud information corresponds to a distance value, and each object contained in the first local point cloud map is color-coded based on the pre-set correspondence between color and distance. For example, in the first local point cloud map collected, each car can be regarded as an object, and the car corresponds to hundreds or thousands of laser points, each point has a distance value, and these hundreds or thousands of laser points form a laser cluster to represent the car.

[0077] The schematic diagram of the relationship between distance and color is as follows Figure 2 As shown, different distance ranges correspond to different colors. The correspondence between distance and color can be regarded as a distance and color comparison information matrix. In this application, the correspondence between distance and color is predefined for coloring objects contained in the local point cloud map. It should be noted that the specific correspondence between distance and color can be flexibly set by those skilled in the art, and no specific restrictions are made in the embodiments of this application. For example: 2 cm corresponds to dark red, 4 cm corresponds to light red, 6 cm corresponds to blue, etc.

[0078] Step 2: Filter out the preset static targets in each color-coded object to obtain a second local point cloud map.

[0079] The preset static target is a static object with a small reference value for positioning, such as a ground point. Since the preset static target has a small reference value during positioning, the preset static target is filtered out.

[0080] This method of optionally color-coding the objects and then filtering out the preset static targets has a small amount of calculation and an accurate filtering result.

[0081] In an optional embodiment, based on the point cloud information in the first partial point cloud map collected twice successively, the method of determining the dynamic target includes the following steps:

[0082] Step 1: After a preset time interval, the environment point cloud information is collected again to generate a first local point cloud map, and static targets in the first local point cloud map are filtered out to obtain a fourth local point cloud map;

[0083] The preset duration can be flexibly set by those skilled in the art, and no specific limitation is imposed on this in the embodiments of the present application.

[0084] For example: the first local point cloud map generated by the environmental point cloud information collected in step 101 is A, then the environmental point cloud information collection time point 1 of the first local point cloud map B in this step is separated from the environmental point cloud information collection time point 2 of A by a preset time length, and no environmental point cloud information is collected between time point 1 and time point 2.

[0085] Step 2: Determine the position change information of the driverless car when collecting the first local point cloud map twice;

[0086] Step 3: updating the point cloud information of each object contained in the fourth partial point cloud map according to the position change information to obtain a fifth partial point cloud map;

[0087] When the point cloud information of each object included in the fourth partial point cloud map is updated according to the position change information, for each point cloud information, the difference between the coordinate value corresponding to the point cloud information and the coordinate value indicated by the position change information can be calculated.

[0088] Step 4: Compare the fifth local point cloud map with the second local point cloud map, and determine the objects whose point cloud information change is outside the preset range as dynamic targets.

[0089] Within the preset range, the object is a static target, and outside the preset range, the object is a dynamic target.

[0090] The second local point cloud map is the point cloud information collected and preprocessed at time t1; the fourth local point cloud map is the point cloud information collected and preprocessed at time t2; the preset time length is t2-t1, and the position change information represents the position change of the unmanned vehicle within the preset time length.

[0091] If the target object is a static target, the position information of the target object at time t1 and time t2 is fixed, and the point cloud information reflects the distance between the driverless car and the target object. Therefore, in theory, the second local point cloud map = the fourth local point cloud map - position transformation information. However, considering the existence of errors, as long as the error between the "second local point cloud map" and the "fourth local point cloud map - position transformation information" is within the preset range, the object is considered to be a static target, otherwise it is a dynamic target.

[0092] More preferably, the moving direction and moving speed of the dynamic target can also be determined based on the fifth local point cloud map and the second local point cloud map, which can be used as a reference factor when determining the dynamic target in the subsequent local point cloud map.

[0093] This method of optionally combining the position change information of the unmanned vehicle to identify dynamic targets has a high accuracy of the recognition result.

[0094] Figure 3 A structural block diagram of a point cloud map construction device for implementing an embodiment of the present application.

[0095] The point cloud map construction device of the embodiment of the present application includes the following modules:

[0096] The acquisition module 301 is used to collect environmental point cloud information and generate a first local point cloud map when the unmanned vehicle moves along a preset route;

[0097] A first filtering module 302, used to filter out the preset static targets in the first local point cloud map to obtain a second local point cloud map;

[0098] A second filtering module 303, used to filter out dynamic targets in the second local point cloud map to obtain a third local point cloud map;

[0099] The construction module 304 is used to construct a target point cloud map based on each third local point cloud map generated when the unmanned vehicle moves along a preset route.

[0100] Optionally, the acquisition module includes:

[0101] The first submodule is used to determine the distance between the unmanned vehicle and each object in the surrounding environment based on the time interval of the pulse signal transmitted and received by the laser radar on the unmanned vehicle when the unmanned vehicle moves along the preset route, as the collected environmental point cloud information;

[0102] The second submodule is used to generate a first local point cloud map based on the collected environmental point cloud information, wherein the first local point cloud map is used to represent the environmental information around the unmanned vehicle at a certain moment.

[0103] Optionally, the first filtering module includes:

[0104] The third submodule is used to perform target segmentation processing on the first local point cloud map to obtain each object contained in the first local point cloud map, and then perform color marking processing on each of the objects, wherein each object corresponds to a plurality of point cloud information, each point cloud information corresponds to a distance value, and when performing color marking, the objects contained in the first local point cloud map are color marked based on a predetermined correspondence between color and distance;

[0105] The fourth submodule is used to filter out the preset static targets in each of the color-coded objects to obtain a second local point cloud map.

[0106] Optionally, the second filtering module includes:

[0107] A fifth submodule is used to determine a dynamic target based on point cloud information in the first partial point cloud map collected twice successively;

[0108] The sixth submodule is used to filter out dynamic targets in the second local point cloud map to obtain a third local point cloud map.

[0109] Optionally, the fifth submodule includes:

[0110] A collection unit, configured to collect environmental point cloud information again after a preset time interval to generate a first local point cloud map, and filter out static targets in the first local point cloud map to obtain a fourth local point cloud map;

[0111] A position change information determination unit, used to determine the position change information of the unmanned vehicle when the first local point cloud map is collected twice in succession;

[0112] an updating unit, configured to update the point cloud information of each object contained in the fourth partial point cloud map according to the position change information, so as to obtain a fifth partial point cloud map;

[0113] The comparison unit is used to compare the fifth local point cloud map with the second local point cloud map, and determine the object whose point cloud information change amount is outside the preset range as a dynamic target.

[0114] The point cloud map construction device provided in the embodiment of the present application can filter out dynamic targets and static targets with low reference value, i.e., preset static targets, in the point cloud map to obtain a high-quality point cloud map, so that more accurate location information can be obtained during subsequent positioning. Specifically, on the one hand, dynamic targets are prevented from interfering with positioning, thereby improving the accuracy of positioning results, and on the other hand, static targets with low reference value are prevented from increasing the amount of calculation, which is conducive to improving positioning speed.

[0115] In the present application embodiment Figure 2 The point cloud map construction device shown can be a device, or a component, integrated circuit, or chip in a server. Figure 2 The point cloud map construction device shown may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiments of the present application.

[0116] The embodiments of the present application provide Figure 3 The point cloud map construction device shown can achieve Figure 1 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0117] Alternatively, if Figure 4 As shown, the embodiment of the present application also provides an electronic device 400, including a processor 401, a memory 402, and a program or instruction stored in the memory 402 and executable on the processor 401. When the program or instruction is executed by the processor 401, each process of the above-mentioned point cloud map construction method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0118] It should be noted that the electronic device in the embodiment of the present application includes the server described above.

[0119] Figure 5 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of the present application.

[0120] The electronic device 500 includes, but is not limited to, components such as a radio frequency unit 501, a network module 502, an audio output unit 503, an input unit 504, a sensor 505, a display unit 506, a user input unit 507, an interface unit 508, a memory 509, and a processor 510. Those skilled in the art will appreciate that the electronic device 500 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 510 through a power management system, so that the power management system can realize functions such as managing charging, discharging, and power consumption management. Figure 5The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.

[0121] The processor 510 is used to execute the process of the above-mentioned point cloud map construction method.

[0122] It should be understood that in the embodiment of the present application, the input unit 504 may include a graphics processor (Graphics Processing Unit, GPU) 5041 and a microphone 5042, and the graphics processor 5041 processes the image data of the static picture or video obtained by the image capture device (such as a camera) in the video capture mode or the image capture mode. The display unit 506 may include a display panel 5061, and the display panel 5061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 507 includes a touch panel 5071 and other input devices 5072. The touch panel 5071 is also called a touch screen. The touch panel 5071 may include two parts: a touch detection device and a touch controller. Other input devices 5072 may include but are not limited to a physical keyboard, a function key (such as a volume control button, a switch button, etc.), a trackball, a mouse, and a joystick, which will not be repeated here. The memory 509 can be used to store software programs and various data, including but not limited to applications and operating systems. The processor 510 can integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, the user interface, and the application program, etc., and the modem processor mainly processes wireless communication. It is understandable that the above-mentioned modem processor may not be integrated into the processor 510.

[0123] The embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned point cloud map construction method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0124] The processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0125] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned point cloud map construction method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0126] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0127] It should be noted that, in this article, the term "comprises", "includes" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the method and device in the embodiment of the present application is not limited to performing functions in the order shown or discussed, and may include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0128] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0129] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A point cloud map construction method, characterized in that: The method comprises: When the driverless car moves along a preset route, environmental point cloud information is collected to generate a first local point cloud map; Filtering out the preset static target in the first local point cloud map to obtain a second local point cloud map; Filtering out dynamic targets in the second partial point cloud map to obtain a third partial point cloud map; Constructing a target point cloud map based on the third local point cloud maps generated during the movement of the unmanned vehicle along the preset route; The step of filtering out the dynamic targets in the second partial point cloud map to obtain a third partial point cloud map includes: Determine the dynamic target based on the point cloud information in the first partial point cloud map collected twice successively; Filtering out dynamic targets in the second partial point cloud map to obtain a third partial point cloud map; The step of determining the dynamic target based on the point cloud information in the first partial point cloud map collected twice successively includes: After a preset time interval, the environment point cloud information is collected again to generate a first local point cloud map, and static targets in the first local point cloud map are filtered out to obtain a fourth local point cloud map; Determine the position change information of the unmanned vehicle when collecting the first local point cloud map twice; updating the point cloud information of each object contained in the fourth partial point cloud map according to the position change information to obtain a fifth partial point cloud map; By comparing the fifth partial point cloud map with the second partial point cloud map, objects whose point cloud information change is outside a preset range are determined as dynamic targets.

2. The method according to claim 1, characterized in that: The step of collecting environmental point cloud information to generate a first local point cloud map while the unmanned vehicle moves along a preset route includes: When the unmanned vehicle moves along a preset route, the laser radar installed on the unmanned vehicle determines the distance between the unmanned vehicle and each object in the surrounding environment based on the time interval between the transmitted and received pulse signals, as the collected environmental point cloud information; A first local point cloud map is generated based on the collected environmental point cloud information, wherein the first local point cloud map is used to represent the environmental information around the unmanned vehicle at a certain moment.

3. The method according to claim 1, characterized in that The step of filtering out the preset static target in the first local point cloud map to obtain the second local point cloud map includes: Performing target segmentation processing on the first local point cloud map to obtain objects contained in the first local point cloud map, and then performing color marking processing on each of the objects, wherein each object corresponds to a plurality of point cloud information, each point cloud information corresponds to a distance value, and when performing color marking, color marking is performed on each of the objects contained in the first local point cloud map based on a predetermined correspondence between color and distance; The preset static targets in each of the color-coded objects are filtered out to obtain a second local point cloud map.

4. A point cloud map construction device, characterized in that: include: A collection module, used to collect environmental point cloud information and generate a first local point cloud map when the unmanned vehicle moves along a preset route; A first filtering module, used to filter out preset static targets in the first local point cloud map to obtain a second local point cloud map; A second filtering module, used for filtering out dynamic targets in the second local point cloud map to obtain a third local point cloud map; A construction module, configured to construct a target point cloud map based on each of the third local point cloud maps generated during the movement of the unmanned vehicle along the preset route; The second filtering module comprises: A fifth submodule is used to determine a dynamic target based on point cloud information in the first partial point cloud map collected twice successively; a sixth submodule, configured to filter out dynamic targets in the second local point cloud map to obtain a third local point cloud map; The fifth submodule comprises: A collection unit, configured to collect environmental point cloud information again after a preset time interval to generate a first local point cloud map, and filter out static targets in the first local point cloud map to obtain a fourth local point cloud map; A position change information determining unit, used to determine the position change information of the unmanned vehicle when the first local point cloud map is collected twice in succession; an updating unit, configured to update the point cloud information of each object contained in the fourth partial point cloud map according to the position change information, so as to obtain a fifth partial point cloud map; The comparison unit is used to compare the fifth local point cloud map with the second local point cloud map, and determine the object whose point cloud information change is outside a preset range as a dynamic target.

5. The device according to claim 4, characterized in that The acquisition module comprises: The first submodule is used to determine the distance between the unmanned vehicle and each object in the surrounding environment based on the time interval of the transmitted and received pulse signals by the laser radar installed on the unmanned vehicle during the movement of the unmanned vehicle along the preset route, as the collected environmental point cloud information; The second submodule is used to generate a first local point cloud map based on the collected environmental point cloud information, wherein the first local point cloud map is used to represent the environmental information around the unmanned vehicle at a certain moment.

6. The device according to claim 4, characterized in that The first filtering module comprises: The third submodule is used to perform target segmentation processing on the first local point cloud map to obtain each object contained in the first local point cloud map, and then perform color marking processing on each of the objects, wherein each object corresponds to a plurality of point cloud information, each point cloud information corresponds to a distance value, and when performing color marking, the objects contained in the first local point cloud map are color marked based on a predetermined correspondence between color and distance; The fourth submodule is used to filter out the preset static targets in each of the color-coded objects to obtain a second local point cloud map.

7. An electronic device comprising a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the point cloud map construction method as described in any one of claims 1 to 3.

Images