Terrain data detection method and device, processor and electronic equipment

Abstract

The invention discloses a topographic data detection method and device, a processor and electronic equipment. The method comprises the following steps: acquiring attribute information of mobile equipment in a current geographical environment and state information of components deployed on the mobile equipment; determining reference information between the mobile device and the component based on the attribute information and the state information; based on the reference information, reconstructing the initial topographic data collected by the component to obtain first target topographic data, and reconstructing the initial topographic data to obtain second target topographic data; and performing error detection on the first target topographic data and the second target topographic data according to the topographic type to which the current geographical environment belongs to obtain an error detection result. The technical problem of low accuracy of terrain data detection is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of terrain detection, in particular to a terrain data detection method and device, a processor and an electronic device. BACKGROUND

[0002] At present, when the existing mobile robot walks in an outdoor environment or a semi-structured environment, it usually relies on the robot body perception data collected by an inertial measurement unit (IMU) to perform a three-dimensional mapping operation and a location positioning operation on terrain data.

[0003] However, the terrain data collected by the depth sensor usually has errors, and the errors cannot be evaluated by a unified error evaluation standard, thereby causing the technical problem of low accuracy of detecting terrain data.

[0004] At present, there is no effective solution to the technical problem of low accuracy of detecting terrain data. SUMMARY

[0005] The embodiments of the present application provide a terrain data detection method, device, processor and electronic device to at least partially solve the technical problem of low accuracy of detecting terrain data.

[0006] According to an aspect of the embodiments of the present application, a terrain data detection method is provided, which comprises: obtaining attribute information of a mobile device in a current geographical environment and state information of a component deployed on the mobile device, wherein the attribute information is used to represent the attribute of the mobile device when the component is controlled by the mobile device to enter a working state, and the state information is used to represent the motion state of the component in the working state when the mobile device moves; determining reference information between the mobile device and the component based on the attribute information and the state information, wherein the reference information is used to represent the reference relationship between the coordinate system in which the mobile device is located and the coordinate system in which the component is located; reconstructing initial terrain data collected by the component based on the reference information to obtain first target terrain data, and reconstructing the initial terrain data to obtain second target terrain data, wherein the initial terrain data is described by the radial distance between the component and a plurality of geographical positions in the current geographical environment, the coordinate system in which the first target terrain data is located is different from the coordinate system in which the initial terrain data is located, and the second target terrain data is described by the longitudinal height of the plurality of geographical positions relative to the reference plane of the current geographical environment; and performing error detection on the first target terrain data and the second target terrain data according to the terrain type to which the current geographical environment belongs to obtain an error detection result.

[0007] Optionally, the reference information between the mobile device and the component is determined based on the attribute information and the state information, including: performing reference processing on the attribute information and the state information to obtain initial reference information between the mobile device and the component, wherein the initial reference information is used to represent an initial reference relationship between a coordinate system in which the mobile device is located and a coordinate system in which the component is located; and performing link transformation on the initial reference information to obtain the reference information.

[0008] Optionally, the initial terrain data collected by the component is reconstructed based on the reference information to obtain the first target terrain data, including: performing point cloud conversion on the initial terrain data to obtain first point cloud terrain data; and combining the first point cloud terrain data and the reference information to obtain the first target terrain data.

[0009] Optionally, the terrain type includes a first terrain type and a second terrain type, and the complexity of the first terrain type is lower than that of the second terrain type, wherein the error detection result is obtained by performing error detection on the first target terrain data and the second target terrain data according to the terrain type of the current geographic environment, including: performing terrain identification on the initial terrain data to obtain the terrain type; in a case where the terrain type is the first terrain type, performing error detection on the first target terrain data and the second target terrain data according to a first error detection strategy corresponding to the first terrain type to obtain the error detection result, wherein the first error detection strategy is used to represent a rule of performing error detection on the first target terrain data and the second target terrain data based on a plane fitting algorithm; and in a case where the terrain type is the second terrain type, performing error detection on the first target terrain data and the second target terrain data according to a second error detection strategy corresponding to the second terrain type to obtain the error detection result, wherein the second error detection strategy is used to represent a rule of performing error detection on the first target terrain data and the second target terrain data based on a registration algorithm.

[0010] Optionally, the method further includes: performing point cloud conversion on the second target terrain data to obtain second point cloud terrain data; in a case where the terrain type is the first terrain type, performing error detection on the first target terrain data and the second target terrain data according to the first error detection strategy corresponding to the first terrain type to obtain the error detection result, including: in a case where the terrain type is the first terrain type, performing plane fitting on the first target terrain data by using a plane fitting algorithm corresponding to the first error detection strategy to obtain a plane fitting result of the current geographic environment, wherein the plane fitting result is used to represent a state in which a plurality of geographic positions present in a fitting plane corresponding to the current geographic environment; and performing error detection on the plane fitting result and the second point cloud terrain data to obtain the error detection result.

[0011] Optionally, in the case that the terrain type is the second terrain type, the first target terrain data and the second target terrain data are subjected to error detection according to a second error detection strategy corresponding to the second terrain type, to obtain an error detection result, including: in the case that the terrain type is the second terrain type, using a registration algorithm corresponding to the second error detection strategy to register the first target terrain data and the second target terrain data, to obtain a registration result, wherein the registration result is used to indicate a registration degree between the first target terrain data and the second target terrain data; based on the registration result, determining error data between the first target terrain data and the second target terrain data, wherein the error data is used to indicate errors of the first target terrain data and the second target terrain data in different dimensions; based on the error data, performing error detection on the first target terrain data and the second target terrain data, to obtain the error detection result.

[0012] Optionally, the method further includes: outputting the error detection result as a target file of different types; calling the target file to perform defect positioning on the second target terrain data, to obtain defect positioning information, wherein the defect positioning information is used to indicate a position of the defect terrain data in the second target terrain data.

[0013] According to another aspect of the embodiments of the present application, a device for detecting terrain data is further provided, which includes: an acquisition unit configured to acquire attribute information of a mobile device in a current geographic environment and state information of a component disposed on the mobile device, wherein the attribute information is used to indicate an attribute of the mobile device when the component is in a working state, and the state information is used to indicate a motion state of the component in the working state when the mobile device moves; a determination unit configured to determine reference information between the mobile device and the component based on the attribute information and the state information, wherein the reference information is used to indicate a reference relationship between a coordinate system in which the mobile device is located and a coordinate system in which the component is located; a reconstruction and reconfiguration unit configured to reconstruct initial terrain data collected by the component based on the reference information, to obtain first target terrain data, and to reconfigure the initial terrain data, to obtain second target terrain data, wherein the initial terrain data is described by radial distances between the component and a plurality of geographic positions in the current geographic environment, a coordinate system in which the first target terrain data is located is different from a coordinate system in which the initial terrain data is located, and the second target terrain data is described by longitudinal heights of the plurality of geographic positions relative to a reference plane of the current geographic environment; and a detection unit configured to perform error detection on the first target terrain data and the second target terrain data according to a terrain type to which the current geographic environment belongs, to obtain an error detection result.

[0014] According to still another aspect of the embodiments of the present application, a processor is further provided, which is used to run a program, wherein the program is executed by the processor to implement the method of any one of the above.

[0015] According to a further aspect of the embodiments of the present application, an electronic device is provided, comprising a memory storing an executable program; and a processor configured to execute the program, wherein the program, when executed, performs any of the methods described above.

[0016] According to another aspect of the embodiments of the present application, a computer readable storage medium is provided, comprising a stored executable program, wherein the executable program, when executed, controls a device on which the storage medium is located to perform any of the methods described above.

[0017] According to a further aspect of the embodiments of the present application, a computer program product is provided, comprising a computer program, wherein the computer program, when executed by a processor, implements any of the methods described above.

[0018] In the embodiments of the present application, when detecting the terrain data, the attribute information of the mobile device in the current geographic environment and the state information of the component deployed on the mobile device can be acquired; based on the attribute information and the state information, the reference information between the mobile device and the component is determined; based on the reference information, the initial terrain data collected by the component is reconstructed to obtain the first target terrain data, and the initial terrain data is reconstructed to obtain the second target terrain data; and the error detection is performed on the first target terrain data and the second target terrain data according to the terrain type to which the current geographic environment belongs, to obtain the error detection result. In the embodiments of the present application, based on the attribute information and the state information, the reference information between the mobile device and the component can be determined, that is, the reference relationship between the coordinate system in which the mobile device is located and the coordinate system in which the component is located can be determined, then based on the determined reference information, the initial terrain data collected is reconstructed to obtain the first target terrain data, and the initial terrain data collected is reconstructed to obtain the second target terrain data, finally, the error detection is performed on the obtained first target terrain data and second target terrain data according to the error detection strategy corresponding to the terrain type, to obtain the error detection result, thereby achieving the purpose that the error of the terrain data can be evaluated with a unified measurement standard, thereby solving the technical problem that the accuracy of detecting the terrain data is low, and further achieving the technical effect that the accuracy of detecting the terrain data can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0019] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

[0020] FIG. 1(a) is a schematic diagram of an application scenario of a terrain data detection method according to an embodiment of the present application;

[0021] Fig. 1(b) is a flow chart of a method for detecting terrain data according to an embodiment of the present application;

[0022] Figure 2 Fig. 2 is a flow chart of a method for supporting multi-source multi-terrain robot deep perception and reconstruction quality evaluation according to an embodiment of the present application;

[0023] Figure 3 Fig. 3 is a structural block diagram of a device for detecting terrain data according to an embodiment of the present application;

[0024] Figure 4 Fig. 4 is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the personnel in the art better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work should belong to the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] According to an embodiment of the present application, a method for detecting terrain data is provided.

[0028] As an optional implementation, the above terrain data detection method can be applied to, but is not limited to, the application scenario shown in FIG. 1(a). FIG. 1(a) is a schematic diagram of an application scenario of a terrain data detection method according to an embodiment of the present application. As shown in FIG. 1(a), in the application scenario, the mobile terminal 10 can communicate with the server 13 through the network 11, and the server 13 can perform operations on a database, such as a data writing operation or a data reading operation. The mobile terminal 10 can be a terminal device, which can include, but is not limited to, a human-computer interaction screen, a processor, and a memory.

[0029] The human-computer interaction screen can be used to display a virtual machine on the mobile terminal 10. The mobile device 12 can be used to respond to the human-computer interaction operation, perform a corresponding operation, or generate a corresponding instruction and send the generated instruction to the server 13. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here: step S102, obtaining attribute information of the mobile device in the current geographic environment and state information of components deployed on the mobile device; step S104, determining reference information between the mobile device and the components based on the attribute information and the state information; step S106, reconstructing initial terrain data collected by the components based on the reference information to obtain first target terrain data, and reconstructing the initial terrain data to obtain second target terrain data; and step S108, performing error detection on the first target terrain data and the second target terrain data according to the terrain type to which the current geographic environment belongs, to obtain an error detection result.

[0030] FIG. 1(b) is a flowchart of a terrain data detection method according to an embodiment of the present application. As shown in FIG. 1(b), the method can include the following steps:

[0031] Step S112, obtaining attribute information of the mobile device in the current geographic environment and state information of components deployed on the mobile device, wherein the attribute information is used to indicate the attribute of the mobile device when the mobile device controls the components to enter a working state, and the state information is used to indicate the motion state of the components in the working state when the mobile device moves.

[0032] In the technical solution provided in the step S112 of the present application, the attribute information can be used to represent the attribute of the mobile device when the mobile device control component enters the working state. The mobile device can be a mobile robot, the component can include a plurality of rigid body components, and the rigid body component can be a depth camera mounted on the mobile robot. The attribute information can be joint information of each joint of the mobile robot when the mobile robot controls the depth camera to enter the working state. The joint information can include the angle and torque of the corresponding joint.

[0033] In this embodiment, the state information can be used to represent the motion state of the component in the working state when the mobile device moves. For example, the motion state can include the pose, speed, angular velocity, and acceleration of the component in the working state when the mobile device moves. This is only an example and is not limited.

[0034] In this embodiment, the attribute information of the mobile device in the current geographic environment is obtained. Optionally, the encoder is used to encode the sub-attribute of the mobile device in the current geographic environment, and a plurality of sub-attribute information can be obtained. The sub-attribute information can be used to represent the attribute of a part of the mobile device when the mobile device controls the component to enter the working state. The plurality of sub-attribute information is fused to obtain the attribute information of the mobile device in the current geographic environment.

[0035] In this embodiment, the state information of the component deployed on the mobile device is obtained. Optionally, the IMU can directly collect the sub-state information of the plurality of components deployed on the mobile device to obtain a plurality of sub-state information. The sub-state information can be used to represent the motion state of the component in the working state when the mobile device moves. The plurality of sub-state information is fused to obtain the state information.

[0036] It should be noted that if the mobile device is a mobile robot, the encoder can be a joint encoder. The joint encoder is used to encode the angle and torque of each joint of the mobile robot in the current geographic environment to obtain a plurality of sub-joint information. The sub-joint information can be used to represent the joint information of a joint of the mobile robot when the mobile robot controls the depth camera to enter the working state. The plurality of sub-joint information is fused to obtain the sub-joint information.

[0037] In step S114, the reference information between the mobile device and the component is determined based on the attribute information and the state information. The reference information is used to represent the reference relationship between the coordinate system in which the mobile device is located and the coordinate system in which the component is located.

[0038] In the technical solution provided in the step S114 of the present application, the reference information can be used to represent the reference relationship between the coordinate system in which the mobile device is located and the coordinate system in which the component is located. For example, the coordinate system in which the mobile device is located can be a motion coordinate system, the coordinate system in which the component is located can be a depth coordinate system, and the reference relationship can be described by a coordinate system transformation matrix between the motion coordinate system and the depth coordinate system, which can also be referred to as a kinematic transformation matrix. This is only an example and is not limited in a specific manner.

[0039] In this embodiment, after obtaining the attribute information of the mobile device in the current geographic environment and the state information of the component deployed on the mobile device, the reference information between the mobile device and the component is determined based on the attribute information and the state information. Alternatively, based on the obtained attribute information and state information, the initial reference information between the mobile device and the component can be determined according to the obtained attribute information and state information, wherein the initial reference information is used to represent the initial reference relationship between the coordinate system in which the mobile device is located and the coordinate system in which the component is located. The initial reference information determined can be transformed to obtain the reference information, thereby achieving the purpose of determining the reference relationship between the coordinate system in which the mobile device is located and the coordinate system in which the component is located.

[0040] Alternatively, the initial reference information between the mobile device and the component can be determined according to the obtained attribute information and state information. For example, the obtained attribute information and state information are described in a unified robot description format (URDF), and the described attribute information and state information are part-transformed according to each part of the mobile device to obtain the initial reference information.

[0041] In step S116, the initial terrain data collected by the component is reconstructed based on the reference information to obtain first target terrain data, and the initial terrain data is reconstructed to obtain second target terrain data, wherein the initial terrain data is described by the radial distance between the component and a plurality of geographic positions in the current geographic environment, the coordinate system in which the first target terrain data is located is different from the coordinate system in which the initial terrain data is located, and the second target terrain data is described by the longitudinal height of the plurality of geographic positions relative to the reference plane of the current geographic environment.

[0042] In the technical solution provided in the step S116 of the present application, the initial terrain data can be described by the radial distance between the component and a plurality of geographic positions in the current geographic environment. For example, the initial terrain data can be a depth map collected by a depth camera, which can also be referred to as an original depth map. This is only an example and is not limited in a specific manner.

[0043] In this embodiment, the coordinate system in which the first target terrain data described above is located is different from the coordinate system in which the initial terrain data is located. For example, the first target terrain data described above can be depth point cloud data, which is 3D (3 Dimension, 3D for short) point cloud data in a target coordinate system. The target coordinate system can be a motion coordinate system.

[0044] In this embodiment, the second target terrain data described above can be described in terms of the longitudinal height of a plurality of geographic positions relative to the reference plane of the current geographic environment. For example, the second target terrain data described above can be a reconstructed height map.

[0045] In this embodiment, after determining the reference information between the mobile device and the component based on the attribute information and the state information, the initial terrain data collected by the component is reconstructed based on the reference information to obtain the first target terrain data, and the initial terrain data is reconstructed to obtain the second target terrain data. Alternatively, based on the determination of the reference information, the initial terrain data collected by the component is converted to point cloud data, and the first point cloud terrain data is obtained. According to the determined reference information and the converted first point cloud terrain data, the first target terrain data can be determined, and the initial terrain data is reconstructed using a pre-trained depth estimation network to obtain the second target terrain data. Thus, the purpose of being able to perform reconstruction and reconstruction operations on the initial terrain data is achieved.

[0046] It should be noted that the method of obtaining the first target terrain data and the second target terrain data described above is only for illustration, and is not specifically limited herein. As long as the process and method of being able to reconstruct the initial terrain data and reconstruct the initial terrain data to obtain the first target terrain data and the second target terrain data are within the protection scope of the embodiments of the present application, they will not be illustrated one by one here.

[0047] In step S118, the first target terrain data and the second target terrain data are error detected according to the terrain type of the current geographic environment to obtain an error detection result.

[0048] In the technical solution provided by the above step S118 of the present application, the terrain type can include a first terrain type and a second terrain type. The first terrain type is a simple terrain type, which can include a flat terrain type and a slope terrain type, etc. The second terrain type is a complex terrain type, which can include a stepped terrain type, a rugged terrain type, and a pit terrain type, etc.

[0049] In this embodiment, the error detection result can be used to represent the terrain error between the first target terrain data and the second target terrain data.

[0050] In this embodiment, after reconstructing the initial terrain data collected by the component based on the reference information to obtain the first target terrain data and reconstructing the initial terrain data to obtain the second target terrain data, the error detection is performed on the first target terrain data and the second target terrain data according to the terrain type to which the current geographical environment belongs, and the error detection result is obtained. Alternatively, based on the first target terrain data and the second target terrain data, the terrain type to which the current geographical environment belongs can be determined according to the collected initial terrain data, and the error detection strategy corresponding to the terrain type is determined. The error detection is performed on the first target terrain data and the second target terrain data according to the error detection strategy corresponding to the terrain type, and the error detection result can be obtained. Thus, the purpose of determining the terrain error between the first target terrain data and the second target terrain data is achieved.

[0051] It should be noted that the error detection strategy can include error detection strategies corresponding to different terrain types. For example, the error detection strategy can include a first error detection strategy and a second error detection strategy. The first error detection strategy can be used to represent the rules for performing error detection on the first target terrain data and the second target terrain data based on a plane fitting algorithm. The second error detection strategy can be used to represent the rules for performing error detection on the first target terrain data and the second target terrain data based on a registration algorithm. This is only an example and is not limited in detail.

[0052] In the steps S112-S118 described above, when detecting the terrain data, attribute information of the mobile device in the current geographic environment and state information of the component deployed on the mobile device can be acquired; reference information between the mobile device and the component is determined based on the attribute information and the state information; the initial terrain data collected by the component is reconstructed based on the reference information to obtain first target terrain data, and the initial terrain data is reconstructed to obtain second target terrain data; and error detection is performed on the first target terrain data and the second target terrain data according to the terrain type to which the current geographic environment belongs to obtain an error detection result. In the embodiment, the reference information between the mobile device and the component can be determined based on the attribute information and the state information, that is, the reference relationship between the coordinate system in which the mobile device is located and the coordinate system in which the component is located can be determined, then the initial terrain data collected is reconstructed based on the determined reference information to obtain the first target terrain data, and the initial terrain data collected is reconstructed to obtain the second target terrain data, finally, error detection is performed on the first target terrain data and the second target terrain data according to the error detection strategy corresponding to the terrain type to obtain the error detection result, thereby achieving the purpose of evaluating the error of the terrain data with a unified measurement standard, solving the technical problem of low accuracy of detecting the terrain data, and achieving the technical effect of improving the accuracy of detecting the terrain data.

[0053] The above method of the embodiment will be further described below.

[0054] As an optional embodiment, in step S114, the reference information between the mobile device and the component is determined based on the attribute information and the state information, including: performing reference processing on the attribute information and the state information to obtain initial reference information between the mobile device and the component, wherein the initial reference information is used to indicate the initial reference relationship between the coordinate system in which the mobile device is located and the coordinate system in which the component is located; and performing link transformation on the initial reference information to obtain the reference information.

[0055] In the embodiment, the initial reference information can be used to indicate the initial reference relationship between the coordinate system in which the mobile device is located and the coordinate system in which the component is located.

[0056] In this embodiment, after the attribute information of the mobile device in the current geographic environment and the state information of the components deployed on the mobile device are acquired, the attribute information and the state information are subjected to reference processing to obtain initial reference information between the mobile device and the components. Alternatively, based on the acquired attribute information and state information, the acquired attribute information and state information are described in URDF, and the described attribute information and state information are subjected to reference processing to obtain the initial reference information between the mobile device and the components, for example, the described attribute information and state information are subjected to part transformation according to each part of the mobile device, and the initial reference information is obtained, thereby achieving the purpose of determining the initial reference relationship between the coordinate system in which the mobile device is located and the coordinate system in which the components are located.

[0057] In this embodiment, the above linkage transformation can be a matrix transformation based on a kinematics algorithm. For example, if the mobile device is a robot with an open-chain structure, the above linkage transformation can be an open-chain transformation; if the mobile device is a robot with a closed-chain structure, the above linkage transformation can be a closed-chain transformation, which is only illustrative and not limited.

[0058] In this embodiment, after the attribute information and the state information are subjected to reference processing to obtain the initial reference information between the mobile device and the components, the initial reference information is subjected to linkage transformation to obtain the reference information. Alternatively, based on the obtained initial reference information, the initial reference information is subjected to linkage transformation corresponding to the structure of the mobile device, and the reference information can be obtained, thereby achieving the purpose of determining the reference relationship between the coordinate system in which the mobile device is located and the coordinate system in which the components are located, and further achieving the technical effect of improving the accuracy of the reference information.

[0059] The above step of reconstructing the initial terrain data collected by the components based on the reference information to obtain the first target terrain data in this embodiment will be further described below.

[0060] As an optional embodiment, in step S116, the initial terrain data collected by the components is reconstructed based on the reference information to obtain the first target terrain data, including: performing point cloud conversion on the initial terrain data to obtain first point cloud terrain data; and combining the first point cloud terrain data with the reference information to obtain the first target terrain data.

[0061] In this embodiment, the above first point cloud terrain data is 3D point cloud data in the camera coordinate system.

[0062] In this embodiment, after determining the reference information between the mobile device and the component based on the attribute information and the state information, the initial terrain data is subjected to point cloud conversion to obtain first point cloud terrain data. Optionally, based on the determination of the reference information, the initial terrain data collected by the component is subjected to point cloud conversion to obtain the first point cloud terrain data, that is, 3D point cloud data in the camera coordinate system can be obtained.

[0063] In this embodiment, after the initial terrain data is subjected to point cloud conversion to obtain the first point cloud terrain data, the first point cloud terrain data and the reference information are combined to obtain the first target terrain data. Optionally, based on the first point cloud terrain data, the first point cloud terrain data and the reference information are combined to obtain the first target terrain data, that is, 3D point cloud data in the target coordinate system can be obtained, thereby achieving the purpose of reconstructing the initial terrain data, and thus achieving the technical effect of improving the accuracy of the first target terrain data.

[0064] The step of detecting errors in the first target terrain data and the second target terrain data according to the terrain type to which the current geographic environment belongs to obtain an error detection result will be further described below.

[0065] As an optional embodiment, the terrain type includes a first terrain type and a second terrain type, and the complexity of the first terrain type is lower than that of the second terrain type. In step S118, the errors in the first target terrain data and the second target terrain data are detected according to the terrain type to which the current geographic environment belongs to obtain an error detection result, including: performing terrain identification on the initial terrain data to obtain the terrain type; in the case where the terrain type is the first terrain type, the errors in the first target terrain data and the second target terrain data are detected according to a first error detection strategy corresponding to the first terrain type to obtain an error detection result, wherein the first error detection strategy is used to represent a rule for detecting errors in the first target terrain data and the second target terrain data based on a plane fitting algorithm; and in the case where the terrain type is the second terrain type, the errors in the first target terrain data and the second target terrain data are detected according to a second error detection strategy corresponding to the second terrain type to obtain an error detection result, wherein the second error detection strategy is used to represent a rule for detecting errors in the first target terrain data and the second target terrain data based on a registration algorithm.

[0066] In this embodiment, the terrain type can include a first terrain type and a second terrain type, and the complexity of the first terrain type is lower than that of the second terrain type.

[0067] In this embodiment, the first error detection strategy described above can be used to represent a rule of performing error detection on the first target terrain data and the second target terrain data based on a plane fitting algorithm. For example, the plane fitting algorithm described above can be a plane fitting algorithm based on Random Sample Consensus (RANSAC).

[0068] In this embodiment, the terrain type is obtained by performing terrain identification on the initial terrain data. In the case where the terrain type is the first terrain type, the first error detection strategy corresponding to the first terrain type is used to perform error detection on the first target terrain data and the second target terrain data, and the error detection result is obtained. Optionally, based on the first target terrain data and the second target terrain data, the terrain type is obtained by performing terrain identification on the collected initial terrain data. The relationship between the obtained terrain type and the first terrain type and the second terrain type is judged. If it is judged that the terrain type is the first terrain type, the first error detection strategy corresponding to the first terrain type is used to perform error detection on the first target terrain data and the second target terrain data, and the error detection result is obtained. Thus, the purpose of determining the terrain error between the first target terrain data and the second target terrain data is achieved, and the technical effect of improving the accuracy of detecting terrain data is realized.

[0069] In this embodiment, the second error detection strategy described above can be used to represent a rule of performing error detection on the first target terrain data and the second target terrain data based on a registration algorithm. For example, the registration algorithm described above can be a registration algorithm executed based on an Iterative Closest Point (ICP) algorithm.

[0070] In this embodiment, after the terrain type is obtained by performing terrain identification on the initial terrain data, in the case where the terrain type is the second terrain type, the second error detection strategy corresponding to the second terrain type is used to perform error detection on the first target terrain data and the second target terrain data, and the error detection result is obtained. Optionally, based on the first target terrain data and the second target terrain data, the terrain type is obtained by performing terrain identification on the collected initial terrain data. The relationship between the obtained terrain type and the first terrain type and the second terrain type is judged. If it is judged that the terrain type is the second terrain type, the second error detection strategy corresponding to the second terrain type is used to perform error detection on the first target terrain data and the second target terrain data, and the error detection result is obtained. Thus, the purpose of determining the terrain error between the first target terrain data and the second target terrain data is achieved, and the technical effect of improving the accuracy of detecting terrain data is realized.

[0071] The step of performing error detection on the first target terrain data and the second target terrain data according to the first error detection strategy corresponding to the first terrain type to obtain an error detection result, in the case that the terrain type is the first terrain type, is described in further detail as follows.

[0072] As an optional embodiment, the method further comprises: performing point cloud conversion on the second target terrain data to obtain second point cloud terrain data; and in the case that the terrain type is the first terrain type, performing error detection on the first target terrain data and the second target terrain data according to the first error detection strategy corresponding to the first terrain type to obtain an error detection result, comprising: in the case that the terrain type is the first terrain type, performing plane fitting on the first target terrain data by using a plane fitting algorithm corresponding to the first error detection strategy to obtain a plane fitting result of the current geographical environment, wherein the plane fitting result is used to represent a state in which a plurality of geographical positions appear in a fitting plane corresponding to the current geographical environment; and performing error detection on the plane fitting result and the second point cloud terrain data to obtain the error detection result.

[0073] In this embodiment, the second point cloud terrain data is regular gridded three-dimensional point cloud data.

[0074] In this embodiment, the point cloud conversion is performed on the second target terrain data to obtain the second point cloud terrain data. Alternatively, the point cloud conversion can be performed on the second target terrain data to obtain the second point cloud terrain data, i.e., regular gridded three-dimensional point cloud data, on the basis of obtaining the second target terrain data.

[0075] In this embodiment, the plane fitting result can be used to represent a state in which a plurality of geographical positions appear in a fitting plane corresponding to the current geographical environment.

[0076] In this embodiment, after the point cloud conversion is performed on the second target terrain data to obtain the second point cloud terrain data, in the case where the terrain type is the first terrain type, a plane fitting algorithm corresponding to the first error detection strategy is used to perform plane fitting on the first target terrain data to obtain a plane fitting result of the current geographic environment; and error detection is performed on the plane fitting result and the second point cloud terrain data to obtain an error detection result. Optionally, based on the obtained second point cloud terrain data, a relationship between the obtained terrain type and the first terrain type and the second terrain type is determined. If it is determined that the terrain type is the first terrain type, a plane fitting algorithm corresponding to the first error detection strategy is used to perform plane fitting on the first target terrain data to obtain a plane fitting result of the current geographic environment, and then error detection is performed on the plane fitting result and the second point cloud terrain data to obtain an error detection result. In this way, the terrain error between the first target terrain data and the second target terrain data can be determined, and the technical effect of improving the accuracy of detected terrain data can be achieved.

[0077] The step of performing error detection on the first target terrain data and the second target terrain data according to the second error detection strategy corresponding to the second terrain type in the case where the terrain type is the second terrain type to obtain an error detection result will be further described below.

[0078] As an optional embodiment, in the case where the terrain type is the second terrain type, performing error detection on the first target terrain data and the second target terrain data according to the second error detection strategy corresponding to the second terrain type to obtain an error detection result includes: in the case where the terrain type is the second terrain type, using a registration algorithm corresponding to the second error detection strategy to perform registration on the first target terrain data and the second target terrain data to obtain a registration result, where the registration result is used to indicate a registration degree between the first target terrain data and the second target terrain data; determining error data between the first target terrain data and the second target terrain data based on the registration result, where the error data is used to indicate errors of the first target terrain data and the second target terrain data in different dimensions; and performing error detection on the first target terrain data and the second target terrain data based on the error data to obtain an error detection result.

[0079] In this embodiment, the registration result can be used to indicate the registration degree between the first target terrain data and the second target terrain data.

[0080] In this embodiment, when the terrain type is the second terrain type, the first target terrain data and the second target terrain data are registered by using the registration algorithm corresponding to the second error detection strategy, and a registration result is obtained. Optionally, the relationship between the obtained terrain type and the first terrain type and the second terrain type is determined. If it is determined that the terrain type is the second terrain type, the first target terrain data and the second target terrain data are registered by using the registration algorithm corresponding to the second error detection strategy, and a registration result is obtained, that is, the registration degree between the first target terrain data and the second target terrain data is obtained.

[0081] In this embodiment, the error data can be used to represent the error of the first target terrain data and the second target terrain data in different dimensions. For example, the error data can include matching error data and pose error data. The matching error data can be used to represent the error of the first target terrain data and the second target terrain data in the data dimension, and the pose error data can be used to represent the error of the first target terrain data and the second target terrain data in the pose dimension.

[0082] In this embodiment, after the first target terrain data and the second target terrain data are registered by using the registration algorithm corresponding to the second error detection strategy, the error data between the first target terrain data and the second target terrain data is determined based on the registration result, and the error detection of the first target terrain data and the second target terrain data is performed based on the error data, and an error detection result is obtained. Optionally, based on the obtained registration result, the error data between the first target terrain data and the second target terrain data can be extracted, and the distance data between the first target terrain data and the second target terrain data can also be determined. According to the extracted error data and the determined distance data, the error detection of the first target terrain data and the second target terrain data is performed, and an error detection result is obtained. Thus, the terrain error between the first target terrain data and the second target terrain data can be determined, and the technical effect of improving the accuracy of detecting terrain data can be achieved.

[0083] It should be noted that the distance data can include different types of distance data, for example, different types of distance data can include point-to-set distance measurement data (Chamfer distance) and set-to-set maximum distance measurement data (Hausdorff distance), which are only used as examples and are not limited.

[0084] The above terrain data detection method of this embodiment will be further described below.

[0085] As an optional embodiment, the method further comprises: outputting the error detection result as a target file of different types; and calling the target file to perform defect positioning on the second target terrain data to obtain defect positioning information, wherein the defect positioning information is used to indicate a position of the defect terrain data in the second target terrain data.

[0086] In this embodiment, the target file of different types can include an image type target file, a video type target file, a document type target file and a chart type target file. For example, the image type target file can be an image file shown in a three-dimensional visualization image, the video type target file can be a video file shown in a frame sequence video, the document type target file can be a text file shown in a document format or a text file shown in a report format, and the chart type target file can be a chart file shown in an error scatter plot format. These are only examples and are not limited in a specific manner.

[0087] In this embodiment, the error detection result is output as a target file of different types. Alternatively, based on the error detection result, the error detection result is made into a file according to different types, and the target file of different types is obtained and then output.

[0088] In this embodiment, the defect positioning information can be used to indicate the position of the defect terrain data in the second target terrain data.

[0089] In this embodiment, after the error detection result is output as a target file of different types, the target file is called to perform defect positioning on the second target terrain data to obtain defect positioning information. Alternatively, based on the error detection result being output as a target file of different types, the target file is called to perform defect positioning on the second target terrain data, and the defect positioning information is obtained. Thus, the position of the defect terrain data in the second target terrain data can be obtained, and the accuracy of defect positioning can be improved.

[0090] In the embodiment of the present application, when detecting the terrain data, the attribute information of the mobile device in the current geographic environment and the state information of the components deployed on the mobile device can be acquired; the reference information between the mobile device and the components is determined based on the attribute information and the state information; the initial terrain data collected by the components is reconstructed based on the reference information to obtain the first target terrain data, and the initial terrain data is reconstructed to obtain the second target terrain data; and the error detection is performed on the first target terrain data and the second target terrain data according to the terrain type to which the current geographic environment belongs to obtain the error detection result. Since in the embodiment of the present application, the reference information between the mobile device and the components can be determined based on the attribute information and the state information, that is, the reference relationship between the coordinate system in which the mobile device is located and the coordinate system in which the components are located can be determined, then the initial terrain data collected is reconstructed based on the determined reference information to obtain the first target terrain data, and the initial terrain data collected is reconstructed to obtain the second target terrain data, finally the error detection is performed on the obtained first target terrain data and second target terrain data according to the error detection strategy corresponding to the terrain type to obtain the error detection result, thereby achieving the purpose of evaluating the error existing in the terrain data with a unified measurement standard, thereby solving the technical problem of low accuracy of detecting the terrain data, and further realizing the technical effect of improving the accuracy of detecting the terrain data.

[0091] The technical solutions of the embodiments of the present application will be illustrated below in combination with preferred embodiments.

[0092] At present, the existing mobile robots usually rely on the robot body perception data collected by the IMU when walking in outdoor environments or semi-structured environments to perform three-dimensional mapping operations and location positioning operations on the terrain data.

[0093] However, the above terrain data collected by the depth sensor usually has errors, and the errors cannot be evaluated with a unified error evaluation standard, thereby causing the technical problem of low accuracy of detecting the terrain data.

[0094] However, the embodiment of the present application proposes a terrain data detection method, on the basis of obtaining the attribute information and the state information, the reference information between the mobile device and the component can be determined, that is, the reference relationship between the coordinate system where the mobile device is located and the coordinate system where the component is located can be determined, then the initial terrain data collected is reconstructed based on the determined reference information, the first target terrain data can be obtained, and the initial terrain data collected is reconstructed, the second target terrain data can be obtained, finally, the error detection is performed on the first target terrain data and the second target terrain data obtained according to the error detection strategy corresponding to the terrain type, and the error detection result can be obtained, thereby achieving the purpose of evaluating the error of the terrain data with a unified measurement standard, thereby solving the technical problem of low accuracy of detecting terrain data, and further realizing the technical effect of improving the accuracy of detecting terrain data.

[0095] In this embodiment, by performing the robot depth perception and reconstruction quality evaluation method supporting multi-source and multi-terrain, error detection can be performed on the terrain data. For example, Figure 2 is a flowchart of a robot depth perception and reconstruction quality evaluation method supporting multi-source and multi-terrain according to an embodiment of the present application, as Figure 2 shown, the method can include the following steps:

[0096] Step S201, building a real scene and creating a simulation terrain.

[0097] After building a real scene and creating a simulation terrain, step S202 is performed to collect robot body perception data and terrain real data.

[0098] In the technical solution provided in the above step S202 of the present application, a plurality of terrain real value acquisition schemes are designed, including indoor motion capture device terrain acquisition, outdoor 3D vision dense point cloud reconstruction scheme, and simulation terrain real value reading interface design. The robot body perception data can include data collected by the IMU, joint encoders, and vision images, etc. The robot body perception data can be directly read from the sensor at a certain frequency and stored. The time stamps of the terrain real value and the robot body perception data need to be aligned to facilitate subsequent multi-sensor fusion.

[0099] After collecting the robot body perception data and the terrain real data, step S203 is performed to fuse the robot body perception data and the terrain real data using a multi-sensor fusion algorithm.

[0100] In the technical solution provided in the above step S203 of the present application, the multi-sensor fusion algorithm can be used to estimate the joint information of the robot and the motion state of each rigid body component in real time. Since the depth sensor moves with the robot, a robot model file (for example, URDF) and a kinematics algorithm are needed to obtain an accurate coordinate system transformation matrix and achieve nanosecond-level time alignment between the "depth frame" and the "pose frame" to ensure the consistency of the data timing.

[0101] After the multi-sensor fusion algorithm is used to fuse the robot body perception data and the terrain real data, step S204 is performed to use a pre-trained depth estimation network to reconstruct the original depth map into a height map.

[0102] In the technical solution provided in the above step S204 of the present application, the pre-trained depth estimation network is used to reconstruct the original depth map into a height map, and the reconstructed height map is further converted into a regular rasterized three-dimensional point cloud representation, thereby achieving the purpose of enhancing the consistency of the terrain geometry modeling.

[0103] After step S205 is performed to integrate the robot body perception data and the sensor data, step S206 is performed to convert the depth map into 3D point cloud data in the camera coordinate system and convert it to the target coordinate system in combination with the kinematics transformation matrix.

[0104] After the pre-trained depth estimation network is used to reconstruct the original depth map into a height map and the depth map is converted into 3D point cloud data in the camera coordinate system and converted to the target coordinate system in combination with the kinematics transformation matrix, step S207 is performed to evaluate the error of the terrain data by using different evaluation strategies for different terrains.

[0105] In the technical solution provided in the above step S207 of the present application, for simple terrain types, RANSAC plane fitting and point-to-plane distance statistics are combined to output indicators such as Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). For complex terrain types, the ICP algorithm is used to register the depth point cloud and the height map to calculate the matching error and the pose deviation, and in addition, more comprehensive error indicators such as Chamfer distance and Hausdorff distance are calculated to improve the evaluation granularity.

[0106] After the error of the terrain data is evaluated by using different evaluation strategies for different terrains, step S208 is performed to output the three-dimensional visualization image, the frame sequence video, the error scatter plot and the summary report.

[0107] In the technical solution provided in step S208 of the present application, the result visualization and report generation system can be used to automatically output the three-dimensional visualization image, the frame sequence video, the error scatter plot and the summary report, wherein the result visualization and report generation system supports online (real-time) and offline (batch) operation modes, and the output data can be used to quickly locate the reconstruction defects.

[0108] In this embodiment, on the basis of the attribute information and the state information, the reference information between the mobile device and the component can be determined, that is, the reference relationship between the coordinate system in which the mobile device is located and the coordinate system in which the component is located can be determined, then the initial terrain data collected is reconstructed based on the determined reference information, the first target terrain data can be obtained, and the initial terrain data collected is reconstructed, the second target terrain data can be obtained, finally, the first target terrain data and the second target terrain data are subjected to error detection according to the error detection strategy corresponding to the terrain type, and the error detection result can be obtained, thereby achieving the purpose that the error existing in the terrain data can be evaluated by using a unified measurement standard, thereby solving the technical problem that the accuracy of the detected terrain data is low, and further achieving the technical effect that the accuracy of the detected terrain data can be improved.

[0109] According to another aspect of the embodiments of the present application, a processor is also provided, which is used to run a program, wherein the program is run by the processor to execute the method of any one of the above.

[0110] According to another aspect of the embodiments of the present application, a computer readable storage medium is also provided, which includes a stored executable program, wherein the executable program is run to control the device where the storage medium is located to execute the method of any one of the above.

[0111] According to another aspect of the embodiments of the present application, a computer program product is also provided, which includes a computer program, wherein the computer program is executed by a processor to implement the method of any one of the above.

[0112] According to another aspect of the embodiments of the present application, an electronic device is also provided, which includes a memory storing an executable program, and a processor running the program, wherein the program is run to execute the method of any one of the above.

[0113] Figure 3 is a structural block diagram of a terrain data detection device according to an embodiment of the present application, as shown inFigure 3 As shown, the terrain data detection apparatus 300 can include an acquisition unit 301, a determination unit 302, a reconstruction and reestablishment unit 303, and a detection unit 304.

[0114] The acquisition unit 301 is configured to acquire attribute information of the mobile device in the current geographic environment and state information of the components deployed on the mobile device, wherein the attribute information is used to represent the attribute of the mobile device when the mobile device controls the components to enter a working state, and the state information is used to represent the motion state of the components in the working state when the mobile device moves.

[0115] The determination unit 302 is configured to determine reference information between the mobile device and the components based on the attribute information and the state information, wherein the reference information is used to represent the reference relationship between the coordinate system in which the mobile device is located and the coordinate system in which the components are located.

[0116] The reconstruction and reestablishment unit 303 is configured to reconstruct initial terrain data collected by the components based on the reference information to obtain first target terrain data, and reestablish the initial terrain data to obtain second target terrain data, wherein the initial terrain data is described by radial distances between the components and a plurality of geographic positions in the current geographic environment, respectively, the coordinate system in which the first target terrain data is located is different from the coordinate system in which the initial terrain data is located, and the second target terrain data is described by longitudinal heights of the plurality of geographic positions relative to a reference plane of the current geographic environment.

[0117] The detection unit 304 is configured to perform error detection on the first target terrain data and the second target terrain data according to a terrain type to which the current geographic environment belongs, to obtain an error detection result.

[0118] Optionally, the determination unit 302 can include a processing module configured to perform reference processing on the attribute information and the state information to obtain initial reference information between the mobile device and the components, wherein the initial reference information is used to represent an initial reference relationship between the coordinate system in which the mobile device is located and the coordinate system in which the components are located; and a transformation module configured to perform link transformation on the initial reference information to obtain the reference information.

[0119] Optionally, the reconstruction and reestablishment unit 303 can include a conversion module configured to perform point cloud conversion on the initial terrain data to obtain first point cloud terrain data; and a combination module configured to combine the first point cloud terrain data and the reference information to obtain the first target terrain data.

[0120] Optionally, the terrain type includes a first terrain type and a second terrain type, the first terrain type has a lower complexity than the second terrain type, and the detection unit 304 can include: an identification module, configured to perform terrain identification on the initial terrain data to obtain the terrain type; a first detection module, configured to, when the terrain type is the first terrain type, perform error detection on the first target terrain data and the second target terrain data according to a first error detection strategy corresponding to the first terrain type to obtain the error detection result, where the first error detection strategy is used to represent a rule of performing error detection on the first target terrain data and the second target terrain data based on a plane fitting algorithm; and a second detection module, configured to, when the terrain type is the second terrain type, perform error detection on the first target terrain data and the second target terrain data according to a second error detection strategy corresponding to the second terrain type to obtain the error detection result, where the second error detection strategy is used to represent a rule of performing error detection on the first target terrain data and the second target terrain data based on a registration algorithm.

[0121] Optionally, the terrain data detection apparatus 300 can further include a conversion unit, configured to perform point cloud conversion on the second target terrain data to obtain second point cloud terrain data; and the first detection module can include: a fitting sub-module, configured to, when the terrain type is the first terrain type, perform plane fitting on the first target terrain data by using a plane fitting algorithm corresponding to the first error detection strategy to obtain a plane fitting result of the current geographic environment, where the plane fitting result is used to represent a state of a plurality of geographic positions in a fitting plane corresponding to the current geographic environment; and a first detection sub-module, configured to perform error detection on the plane fitting result and the second point cloud terrain data to obtain the error detection result.

[0122] Optionally, the second detection module can include: a registration sub-module, configured to, when the terrain type is the second terrain type, perform registration on the first target terrain data and the second target terrain data by using a registration algorithm corresponding to the second error detection strategy to obtain a registration result, where the registration result is used to represent a registration degree between the first target terrain data and the second target terrain data; a determination sub-module, configured to determine error data between the first target terrain data and the second target terrain data based on the registration result, where the error data is used to represent errors of the first target terrain data and the second target terrain data in different dimensions; and a second detection sub-module, configured to perform error detection on the first target terrain data and the second target terrain data based on the error data to obtain the error detection result.

[0123] Optionally, the error detection device 300 for the terrain data can further comprise an output unit configured to output the error detection result as a target file of different types; and a positioning unit configured to call the target file, and perform defect positioning on the second target terrain data to obtain defect positioning information, wherein the defect positioning information is used to indicate the position of the defective terrain data in the second target terrain data.

[0124] Figure 4 is a structural block diagram of an electronic device according to an embodiment of the present application, as shown in the figure, the components of the electronic device 400 include but are not limited to a memory 410 and a processor 420. The processor 420 is connected with the memory 410 through a bus 430, and a database 450 is used to save data. Figure 4

[0125] The electronic device 400 can further comprise an access device 440, which enables the electronic device 400 to communicate via one or more networks 460. Examples of these networks include the Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the Internet. The access device 440 can include one or more of any type of network interface (for example, a network interface card (NIC)) such as an IEEE 802.11 Wireless Local Area Network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC) interface, and the like.

[0126] In one embodiment of the present disclosure, the above-mentioned components of the electronic device 400 and other components not shown in Figure 4 may be connected with each other, for example, through a bus. It should be understood that, Figure 4 The electronic device structural block diagram shown in the figure is only for the purpose of example, and is not a limitation on the scope of the present disclosure. Those skilled in the art can add or replace other components as needed.​

[0127] It should be noted that the above-mentioned embodiment numbers of the application are only for description, not representing the advantages and disadvantages of the embodiments.

[0128] In the above-mentioned embodiments of the application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0129] In the several embodiments of the present application, it should be understood that the disclosed technology can be implemented in other ways. Of course, the unit embodiment described above is only illustrative, and for example, the division of units can be a logical function division, and there can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, unit or module, which can be electrical or other forms.

[0130] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they can be located in one place, or they can be distributed on multiple units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0131] In addition, each functional unit in each embodiment of the application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0132] If the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the embodiments of the method of the application. The aforementioned storage medium includes: a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0133] The above merely is the preferred embodiment of the present application, it should be pointed out that, for ordinary skilled in the art, without departing from the principles of the present application, can also make a number of improvements and refinements, these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A method for detecting terrain data, characterized in that, include: The system acquires attribute information of the mobile device in the current geographic environment and status information of components deployed on the mobile device. The attribute information is used to represent the attributes of the mobile device when the mobile device controls the component to enter the working state, and the status information is used to represent the movement state of the component in the working state when it moves with the mobile device. Based on the attribute information and the state information, reference information between the mobile device and the component is determined, wherein the reference information is used to represent the reference relationship between the coordinate system of the mobile device and the coordinate system of the component; Based on the reference information, the initial terrain data collected by the component is reconstructed to obtain first target terrain data, and the initial terrain data is reconstructed to obtain second target terrain data. The initial terrain data is described by the radial distance between the component and multiple geographical locations in the current geographic environment. The coordinate system of the first target terrain data is different from the coordinate system of the initial terrain data. The second target terrain data is described by the longitudinal height of the multiple geographical locations relative to the reference plane of the current geographic environment. Based on the terrain type of the current geographical environment, error detection is performed on the first target terrain data and the second target terrain data to obtain the error detection result.

2. The method according to claim 1, characterized in that, Based on the attribute information and the status information, determining the reference information between the mobile device and the component includes: The attribute information and the state information are processed by reference to obtain initial reference information between the mobile device and the component, wherein the initial reference information is used to represent the initial reference relationship between the coordinate system of the mobile device and the coordinate system of the component; The initial reference information is subjected to a link transformation to obtain the reference information.

3. The method according to claim 1, characterized in that, Based on the reference information, the initial terrain data collected by the component is reconstructed to obtain the first target terrain data, including: The initial terrain data is converted into point cloud data to obtain the first point cloud terrain data; The first point cloud terrain data is combined with the reference information to obtain the first target terrain data.

4. The method according to claim 1, characterized in that, The terrain types include a first terrain type and a second terrain type. The complexity of the first terrain type is lower than that of the second terrain type. Error detection is performed on the first target terrain data and the second target terrain data according to the terrain type of the current geographical environment to obtain error detection results, including: The initial terrain data is subjected to terrain identification to obtain the terrain type; When the terrain type is the first terrain type, the first target terrain data and the second target terrain data are subjected to error detection according to the first error detection strategy corresponding to the first terrain type, and the error detection result is obtained. The first error detection strategy is used to represent the rules for error detection of the first target terrain data and the second target terrain data based on the plane fitting algorithm. When the terrain type is the second terrain type, the first target terrain data and the second target terrain data are subjected to error detection according to the second error detection strategy corresponding to the second terrain type, and the error detection result is obtained. The second error detection strategy is used to represent the rules for error detection of the first target terrain data and the second target terrain data based on the registration algorithm.

5. The method according to claim 4, characterized in that, The method further includes: The second target terrain data is converted into point cloud data to obtain the second point cloud terrain data. When the terrain type is the first terrain type, error detection is performed on the first target terrain data and the second target terrain data according to the first error detection strategy corresponding to the first terrain type, and the error detection result is obtained, including: When the terrain type is the first terrain type, the plane fitting algorithm corresponding to the first error detection strategy is used to perform plane fitting on the first target terrain data to obtain the plane fitting result of the current geographic environment, wherein the plane fitting result is used to represent the state of the multiple geographic locations in the fitting plane corresponding to the current geographic environment. Error detection is performed on the plane fitting result and the second point cloud terrain data to obtain the error detection result.

6. The method according to claim 4, characterized in that, When the terrain type is the second terrain type, error detection is performed on the first target terrain data and the second target terrain data according to the second error detection strategy corresponding to the second terrain type, and the error detection result is obtained, including: When the terrain type is the second terrain type, the registration algorithm corresponding to the second error detection strategy is used to register the first target terrain data and the second target terrain data to obtain a registration result, wherein the registration result is used to represent the degree of registration between the first target terrain data and the second terrain data; Based on the registration result, error data between the first target terrain data and the second target terrain data is determined, wherein the error data is used to represent the error between the first target terrain data and the second target terrain data in different dimensions; Based on the error data, error detection is performed on the first target terrain data and the second target terrain data to obtain the error detection result.

7. The method according to any one of claims 1 to 5, characterized in that, The method further includes: The error detection results are output as different types of target files; The target file is invoked to locate defects in the second target terrain data, thereby obtaining defect location information, wherein the defect location information is used to indicate the location of the defect terrain data in the second target terrain data.

8. A terrain data detection device, characterized in that, include: The acquisition unit is used to acquire attribute information of the mobile device in the current geographic environment and state information of the components on the mobile device. The attribute information is used to represent the attributes of the mobile device when the mobile device controls the components to enter the working state, and the state information is used to represent the motion state of the components in the working state when they move with the mobile device. The determining unit is configured to determine reference information between the mobile device and the component based on the attribute information and the state information, wherein the reference information is used to represent the reference relationship between the coordinate system where the mobile device is located and the coordinate system where the component is located; The reconstruction and rebuilding unit is used to reconstruct the initial terrain data collected by the component based on the reference information to obtain first target terrain data, and to rebuild the initial terrain data to obtain second target terrain data. The initial terrain data is described by the radial distance between the component and multiple geographical locations in the current geographic environment. The coordinate system of the first target terrain data is different from the coordinate system of the initial terrain data. The second target terrain data is described by the longitudinal height of the multiple geographical locations relative to the reference plane of the current geographic environment. The detection unit is used to perform error detection on the first target terrain data and the second target terrain data according to the terrain type of the current geographical environment, and obtain the error detection result.

9. A processor, characterized in that, The processor is used to run a program, wherein the program is executed by the processor to perform the terrain data detection method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, executes the method for detecting terrain data according to any one of claims 1 to 7.

Images