Data processing method and related device

Abstract

The invention provides a data processing method and a related device, and the method comprises the steps: enabling a sensing node to carry out the judgment of a first reconstruction surface and a second reconstruction surface, which are obtained through the processing of a point cloud obtained through sensing, and respectively comparing the angle difference and / or the distance difference between the first reconstruction surface and the second reconstruction surface with a first threshold value and / or a second threshold value so as to determine whether the first reconstruction surface and the second reconstruction surface are the same surface. And under the condition that the first reconstruction surface and the second reconstruction surface are determined to be the same surface through judgment, obtaining a third reconstruction surface based on the first reconstruction surface and the second reconstruction surface. According to the scheme, the over-segmentation problem caused by electromagnetic wave characteristics and a segmentation algorithm can be effectively solved, the precision loss of environment reconstruction is reduced, and the sensing accuracy is improved.

Description

A data processing method and related device Technical Field

[0001] The present application relates to the field of communications, and in particular to a data processing method and related devices. Background Art

[0002] With the development of integrated sensing and communication (ISAC), the capabilities of base stations and terminals have gradually improved, combining communication and perception functions. In an ISAC system, communication devices with perception capabilities are called sensing nodes. Sensing nodes can perceive the environment by acquiring perception data (such as point clouds).

[0003] Currently, sensing nodes can transmit radio frequency signals to acquire point clouds for environmental perception. Due to the large volume of point clouds, they are typically clustered to obtain reconstructed surfaces, which are then used to reconstruct the environment. However, the propagation characteristics of electromagnetic waves can lead to increased errors in point clouds. Furthermore, when using algorithms to segment point clouds with errors, coupled with the algorithm's inherent limitations, the reconstructed surfaces can become over-segmented, resulting in a loss of accuracy in environmental reconstruction.

[0004] Summary of the Invention

[0005] The present application provides a data processing method and related devices to solve the over-segmentation problem caused by the propagation characteristics of electromagnetic waves and the algorithm itself when segmenting point clouds, and to improve the accuracy of environment reconstruction.

[0006] On the first aspect, the present application provides a method for data processing, which can be executed by a perception node. Unless otherwise specified, the perception node in the present application can refer to a communication device (for example, a network device, a terminal device), or a component in the communication device (for example, a chip, a chip system, or a processor, etc.), or it can also refer to a logic module or software that can realize all or part of the functions of the perception node.

[0007] Exemplarily, the method includes: determining whether a first reconstructed surface and a second reconstructed surface are the same surface based on a judgment criterion, the first reconstructed surface and the second reconstructed surface are obtained by processing the point cloud perceived by the perception node, and the judgment criterion includes one or more of the following: the angle difference between the first reconstructed surface and the second reconstructed surface is less than a first threshold, or the distance difference between the first reconstructed surface and the second reconstructed surface is less than a second threshold; in the case that the first reconstructed surface and the second reconstructed surface are the same surface, obtaining a third reconstructed surface based on the first reconstructed surface and the second reconstructed surface; sending first information to the computing node, the first information being used to indicate the perception data of the target object, and the target object includes the third reconstructed surface.

[0008] The sensing node can determine whether the result obtained after processing the point cloud is two-dimensional or three-dimensional based on a predefined third threshold and the depth information of the point cloud. When the depth information of the point cloud is greater than (or greater than or equal to) the third threshold, it can be determined that the result obtained after processing the point cloud is three-dimensional, that is, a scatterer; when the depth information of the sensed point cloud is less than or equal to (or less than) the third threshold, it can be determined that the result obtained after processing the point cloud is two-dimensional, that is, a reconstructed surface.

[0009] The sensing node obtains the third reconstructed surface based on the first reconstructed surface and the second reconstructed surface, which is like updating the first reconstructed surface and the second reconstructed surface into the third reconstructed surface, which can solve the over-segmentation problem caused by the characteristics of the electromagnetic wave and the segmentation algorithm itself. The first reconstructed surface and the second reconstructed surface can be two reconstructed surfaces obtained by processing the point cloud, or the main surfaces of two scatterers (such as the first scatterer and the second scatterer) obtained by processing the point cloud, or a reconstructed surface and the main surface of a scatterer obtained by processing the point cloud. The main surface of a scatterer can be the surface with the largest area in the scatterer.

[0010] The third reconstructed surface can be an independent surface obtained by the sensing node based on the first and second reconstructed surfaces, or it can be the main surface of a scatterer (referred to as the third scatterer) obtained based on the first and second scatterers, and processed. For ease of explanation, this article will refer to this independent surface or scatterer as the target object.

[0011] The determination criteria may include one or more of the following: Criterion 1) the angular difference between the first reconstructed surface and the second reconstructed surface is less than a first threshold, or Criterion 2) the distance difference between the first reconstructed surface and the second reconstructed surface is less than a second threshold. In other words, the sensing node can determine whether the first reconstructed surface and the second reconstructed surface are the same surface based on the determination criteria. Whether the determination criteria specifically include Criterion 1) or Criterion 2) or both can be indicated by the computing node or predefined by the protocol.

[0012] In this judgment criterion, it is assumed that the normal vector of the first reconstructed surface is w1, and the normal vector of the second reconstructed surface is w2. The angle between the normal vector w1 of the first reconstructed surface and the normal vector w2 of the second reconstructed surface is the angle difference between the first reconstructed surface and the second reconstructed surface.

[0013] Assume that the center point of the first reconstructed surface is O1, the center point of the second reconstructed surface is O2, the distance from the center point O1 of the first reconstructed surface to the second reconstructed surface is recorded as l1, and the distance from the center point O2 of the second reconstructed surface to the first reconstructed surface is recorded as l2. The distance difference between the first reconstructed surface and the second reconstructed surface includes any one of the following items: the minimum value of the distance l1 from the center point O1 of the first reconstructed surface to the second reconstructed surface and the distance l2 from the center point O2 of the second reconstructed surface to the first reconstructed surface, the maximum value of the distance l1 from the center point O1 of the first reconstructed surface to the second reconstructed surface and the distance l2 from the center point O2 of the second reconstructed surface to the first reconstructed surface, and the average value of the distance l1 from the center point O1 of the first reconstructed surface to the second reconstructed surface and the distance l2 from the center point O2 of the second reconstructed surface to the first reconstructed surface, that is, (l1+l2) / 2. The minimum value may be recorded as min(l1, l2), the maximum value may be recorded as max(l1, l2), and the average value may be recorded as avg(l1, l2).

[0014] In other words, the distance difference between the first reconstructed surface and the second reconstructed surface includes any one of the following items: min(l1, l2), max(l1, l2) and avg(l1, l2).

[0015] Based on this solution, the perception node processes the two reconstructed surfaces obtained through perception, and then determines whether the two reconstructed surfaces are the same by comparing the angle difference and / or distance difference between the two reconstructed surfaces with different thresholds. If the two reconstructed surfaces are determined to be the same, a third reconstructed surface is derived based on the two reconstructed surfaces. This effectively solves the problem of over-segmentation caused by the characteristics of electromagnetic waves and the segmentation algorithm itself, reduces the precision loss of environmental reconstruction, and improves the accuracy of perception.

[0016] In combination with the first aspect, in some possible implementations of the first aspect, the perception data of the target object includes location information of the target object.

[0017] Optionally, the position information of the target object includes vertex coordinates of the target object.

[0018] When the target object is an independent surface (i.e., a third reconstructed surface), the perception data of the target object includes position information of the surface (i.e., the third reconstructed surface), such as the coordinates of multiple vertices of the surface. The perception node sends the vertex coordinates of the third reconstructed surface to the computing node, and the computing node can determine the position of the third reconstructed surface based on the vertex coordinates of the third reconstructed surface.

[0019] When the target object is a scatterer (i.e., a third scatterer), the scatterer may be obtained based on two or more scatterers obtained through processing of the point cloud, i.e., the scatterer may be the third scatterer. The perception data of the target object includes position information of the scatterer, such as the coordinates of multiple vertices of the scatterer. The perception node sends the vertex coordinates of the third scatterer to the computing node. The computing node may determine the information included in the third scatterer based on the vertex coordinates of the third scatterer.

[0020] It should be understood that the vertex coordinates of the target object are only one possible form for representing the position information of the target object, and should not constitute any limitation to this application. For example, in another implementation, when the target object is a surface or body of different shapes, its position information can also be represented by data in different forms. For example, when the target object is a rectangular surface, the position information of the target object can also be represented by the center of the rectangular surface and the coordinates of some of its vertices; for another example, when the target object is a cube, the position information of the target object can also be represented by the center of the cube and the coordinates of one of its vertices; for another example, when the target object is a sphere, the position information of the target object can be represented by the center of the sphere and the radius (or diameter). This application does not limit the specific content of the perception data.

[0021] In combination with the first aspect, in some possible implementations of the first aspect, the first information is further used to indicate an identification of the target object.

[0022] Each identifier can be used to identify a target object, and different identifiers can be used to identify different targets. This allows computing nodes to distinguish different targets using identifiers. Furthermore, the sensing node can also use the target object's identifier to update the previously reported perception data for the target object. For example, if the sensing node discovers that the previously reported perception data for two or more targets is determined to be the same target object based on a judgment criterion, it can update the identifiers of the two or more targets to the identifier of any one of the two or more targets.

[0023] In conjunction with the first aspect, in certain possible implementations of the first aspect, second information is received from a computing node, where the second information is used to determine the decision criterion. The computing node indicates the decision criterion using the second information, which facilitates the sensing node's determination of the decision criterion. Furthermore, the computing node can dynamically adjust the decision criterion based on the sensing capabilities of different sensing nodes, thereby enabling different sensing nodes to make decisions based on different decision criteria, providing high flexibility.

[0024] In combination with the first aspect, in some possible implementations of the first aspect, the second information is used to indicate the first threshold and / or the second threshold.

[0025] When the second information indicates the first threshold but not the second threshold, the criterion for determining whether the first reconstructed surface and the second reconstructed surface are the same surface is the above-mentioned criterion 1), that is, the angle difference between the first reconstructed surface and the second reconstructed surface is less than the first threshold.

[0026] When the second information indicates the second threshold but not the first threshold, the criterion for determining whether the first reconstructed surface and the second reconstructed surface are the same surface is the above-mentioned criterion 2), that is, the distance difference between the first reconstructed surface and the second reconstructed surface is less than the second threshold.

[0027] When the second information indicates the first threshold and the second threshold, the judgment criterion for determining whether the first reconstructed surface and the second reconstructed surface are the same surface is a combination of criterion 1) and criterion 2), that is, the angle difference between the first reconstructed surface and the second reconstructed surface is less than the first threshold, and the distance difference between the first reconstructed surface and the second reconstructed surface is less than the second threshold.

[0028] In combination with the first aspect, in some possible implementations of the first aspect, the second information is used to indicate the beam width of the detection signal emitted by the perception node, the incident angle of the detection signal, and one or more of the following: the distance between the perception node and the obstacle, the first constant or the second constant, the first coefficient or the second coefficient, the beam width, the incident angle, the first constant and the first coefficient are used to determine the first threshold, and the beam width, the incident angle, the distance between the perception node and the obstacle, the second constant and the second coefficient are used to determine the second threshold.

[0029] The second information indicates the beam width of the detection signal transmitted by the sensing node, the incident angle of the detection signal, the first constant, and the first coefficient, which can be used to determine the first threshold. In this case, the criteria for determining whether the first reconstructed surface and the second reconstructed surface are the same surface specifically include: Criterion 1) The angular difference between the first reconstructed surface and the second reconstructed surface is less than the first threshold.

[0030] The beam width, incident angle, distance between the sensing node and the obstacle, second constant, and second coefficient indicated by the second information are used to determine the second threshold. In this case, the criteria for determining whether the first reconstructed surface and the second reconstructed surface are the same surface specifically include: Criterion 2) The distance difference between the first reconstructed surface and the second reconstructed surface is less than the second threshold.

[0031] The beam width, incident angle, first constant and first coefficient indicated by the second information are used to determine the first threshold, and the beam width, incident angle, distance between the sensing node and the obstacle, second constant and second coefficient indicated by the second information are used to determine the second threshold.

[0032] It can be understood that in this case, the judgment criteria for determining whether the first reconstructed surface and the second reconstructed surface are the same surface specifically include: criterion 1) the angle difference between the first reconstructed surface and the second reconstructed surface is less than a first threshold, and criterion 2) the distance difference between the first reconstructed surface and the second reconstructed surface is less than a second threshold.

[0033] With reference to the first aspect, in some possible implementations of the first aspect, the first threshold s satisfies:

[0034] The θ represents the beam width of the detection signal emitted by the sensing node, the β represents the incident angle of the detection signal, and the incident angle is used to indicate the angle between the incident direction of the detection signal emitted by the sensing node and the obstacle, the ε1 is the first constant, and the k1 is the first coefficient.

[0035] When the first constant ε1 is 0, or the second information does not indicate the first constant ε1, the first threshold s may be transformed into:

[0036] Furthermore, when the first coefficient k1 is 1, the first threshold s can be transformed into:

[0037] It can be seen from the formula that when the incident angle β of the detection signal is constant, the first threshold value increases as the beam width θ of the detection signal transmitted by the sensing node increases; when the beam width of the detection signal transmitted by the sensing node is constant, the first threshold value increases as the incident angle β of the detection signal increases.

[0038] Furthermore, when the beamwidth of the detection signal approaches zero, Then the first threshold can be transformed into:

[0039] With reference to the first aspect, in some possible implementations of the first aspect, the second threshold d satisfies:

[0040] The r represents the distance between the sensing node and the obstacle, the θ represents the beam width of the detection signal emitted by the sensing node, the β represents the incident angle of the detection signal, the ε2 is the second constant, and the k2 is the second coefficient.

[0041] When the second constant ε2 is 0, or the second information does not indicate the second constant ε2, the second threshold d may be transformed into:

[0042] Furthermore, when the second coefficient k2 is 1, the second threshold d can be transformed into:

[0043] It can be seen from the formula that when the incident angle β of the detection signal is constant, the second threshold value increases as the beam width θ of the detection signal transmitted by the sensing node increases; when the beam width of the detection signal transmitted by the sensing node is constant, the second threshold value increases as the incident angle β of the detection signal increases.

[0044] Furthermore, when the beamwidth of the detection signal approaches zero, Then the second threshold can be transformed into:

[0045] The distance between the sensing node and the obstacle may be indicated by the second information or determined by the sensing node.

[0046] Optionally, in combination with the first aspect, in some possible implementations of the first aspect, the method further includes: acquiring a first reconstructed surface and a second reconstructed surface.

[0047] When the perception node obtains a reconstructed surface after processing the point cloud obtained by perception, no judgment is required; when the perception node obtains multiple reconstructed surfaces after processing the point cloud obtained by perception, the multiple reconstructed surfaces are first divided to obtain at least one pair of reconstructed surfaces, each pair of reconstructed surfaces can be respectively recorded as the first reconstructed surface and the second reconstructed surface, and then each pair of reconstructed surfaces is judged based on the judgment criteria to confirm whether each pair of reconstructed surfaces is the same surface.

[0048] When a perception node processes a point cloud acquired through perception and obtains a single scatterer, no judgment is required. However, when a perception node processes a point cloud acquired through perception and obtains multiple scatterers, the principal surface of each scatterer is recorded as a reconstructed surface of each scatterer, resulting in multiple reconstructed surfaces. These multiple reconstructed surfaces can be first divided into at least one pair of reconstructed surfaces, each of which can be recorded as a first reconstructed surface and a second reconstructed surface. Each pair of reconstructed surfaces is then judged based on a judgment criterion to determine whether each pair of reconstructed surfaces is the same surface, and further to determine whether each pair of scatterers corresponding to each pair of reconstructed surfaces is the same scatterer.

[0049] Secondly, the present application provides a method for data processing, which can be executed by a data computing node. Unless otherwise specified, the computing node in the present application can refer to the computing node itself (for example, a server, a network device), or a component in the computing node (for example, a chip, a chip system, or a processor, etc.), or it can also be a logic module or software that can realize all or part of the functions of the receiving device.

[0050] Exemplarily, the method includes: generating second information, the second information is used to determine a judgment criterion, the judgment criterion is used to determine whether two reconstructed surfaces are the same surface, and the two reconstructed surfaces are obtained by processing the point cloud perceived by the perception node; and sending the second information to the perception node.

[0051] Based on the above scheme, the computing node sends the generated second information to the sensing node, helping the sensing node determine a judgment criterion for determining whether two reconstructed surfaces, obtained after processing the sensed point cloud, are the same. Compared to not using this judgment criterion, if the two reconstructed surfaces determined by the judgment criterion are the same, a third reconstructed surface can be derived based on these two reconstructed surfaces. This reduces over-segmentation caused by electromagnetic wave characteristics and the segmentation algorithm itself, improving the accuracy of environmental reconstruction.

[0052] In combination with the second aspect, in some possible implementations of the second aspect, the second information is used to indicate the first threshold and / or the second threshold.

[0053] In combination with the second aspect, in some possible implementations of the second aspect, the second information is used to indicate the beam width of the detection signal emitted by the perception node, the incident angle of the detection signal, and one or more of the following: the distance between the perception node and the obstacle, the first constant or the second constant, the first coefficient or the second coefficient, the beam width, the incident angle, the first constant and the first coefficient are used to determine the first threshold, and the beam width, the incident angle, the distance between the perception node and the obstacle, the second constant and the second coefficient are used to determine the second threshold.

[0054] With reference to the second aspect, in some possible implementations of the second aspect, the first threshold s satisfies:

[0055] The θ represents the beam width of the detection signal emitted by the sensing node, the β represents the incident angle of the detection signal, and the incident angle is used to indicate the angle between the incident direction of the detection signal emitted by the sensing node and the obstacle, the ε1 is the first constant, and the k1 is the first coefficient.

[0056] With reference to the second aspect, in some possible implementations of the second aspect, the second threshold d satisfies:

[0057] The r represents the distance between the sensing node and the obstacle, the θ represents the beam width of the detection signal emitted by the sensing node, the β represents the incident angle of the detection signal, the ε2 is the second constant, and the k2 is the second coefficient.

[0058] The first threshold and the second threshold in the determination criteria can be specifically referred to the description in the first aspect, which will not be repeated here.

[0059] In a third aspect, the present application provides a data processing device, comprising modules or units for implementing the method in the first aspect and any possible implementation of the first aspect. Each module or unit can implement the corresponding function by executing a computer program.

[0060] In a fourth aspect, the present application provides a data processing device, comprising a processor, wherein the processor is configured to execute the data processing method described in the first aspect and any possible implementation of the first aspect.

[0061] The apparatus may further include a memory for storing instructions and data. The memory is coupled to the processor, and when the processor executes the instructions stored in the memory, the methods described in the above aspects may be implemented. The apparatus may further include a communication interface for communicating between the apparatus and other devices. Exemplarily, the communication interface may be a transceiver, circuit, bus, module, or other type of communication interface.

[0062] Exemplarily, the device in the third aspect or the fourth aspect is a sensing node.

[0063] In a fifth aspect, the present application provides a chip system comprising at least one processor for supporting the implementation of the functions involved in the above-mentioned first aspect and any possible implementation of the first aspect, for example, receiving or processing the data and / or information involved in the above-mentioned method.

[0064] In one possible design, the chip system further includes a memory, which is used to store program instructions and data, and the memory is located inside or outside the processor.

[0065] The chip system can be composed of chips, or can include chips and other discrete devices.

[0066] In a sixth aspect, the present application provides a data processing device, comprising modules or units for implementing the method in the second aspect and any possible implementation of the second aspect. Each module or unit can implement the corresponding function by executing a computer program.

[0067] In a seventh aspect, the present application provides a data processing device, comprising a processor, wherein the processor is configured to execute the data processing method described in the second aspect and any possible implementation of the second aspect.

[0068] The apparatus may further include a memory for storing instructions and data. The memory is coupled to the processor, and when the processor executes the instructions stored in the memory, the methods described in the above aspects may be implemented. The apparatus may further include a communication interface for communicating between the apparatus and other devices. Exemplarily, the communication interface may be a transceiver, circuit, bus, module, or other type of communication interface.

[0069] Exemplarily, the device in the sixth aspect or the seventh aspect is a computing node.

[0070] In an eighth aspect, the present application provides a chip system comprising at least one processor for supporting the implementation of the functions involved in the above-mentioned second aspect and any possible implementation of the second aspect, for example, receiving or processing the data and / or information involved in the above-mentioned method.

[0071] In one possible design, the chip system further includes a memory, which is used to store program instructions and data, and the memory is located inside or outside the processor.

[0072] The chip system can be composed of chips, or can include chips and other discrete devices.

[0073] In a ninth aspect, the present application provides a computer-readable storage medium comprising a computer program, which, when executed on a computer, enables the computer to implement the method in the first or second aspect and any possible implementation of the first or second aspect.

[0074] In the tenth aspect, the present application provides a computer program product, which includes: a computer program (also referred to as code, or instructions), which, when run, enables a computer to execute the method in the first or second aspect and any possible implementation of the first or second aspect.

[0075] In the eleventh aspect, an embodiment of the present application provides a communication system, including the aforementioned perception node and computing node.

[0076] The third to eleventh aspects of this application correspond to the technical solutions of the first and second aspects of this application. The beneficial effects achieved by each aspect and the corresponding feasible implementation methods are similar and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] FIG1 is a schematic diagram of a scatterer provided in an embodiment of the present application;

[0078] FIG2 is a schematic diagram of a communication system applicable to the method provided in an embodiment of the present application;

[0079] FIG3 is a schematic diagram of an environment reconstruction result under electromagnetic wave characteristics provided by an embodiment of the present application;

[0080] FIG4 is a schematic diagram of the beam width and incident angle of the detection signal provided in an embodiment of the present application;

[0081] FIG5 is a schematic diagram of point cloud distribution of a base station integrated with a transmitter and receiver under different beam widths provided in an embodiment of the present application;

[0082] FIG6 is a schematic flow chart of the data processing method provided by the present application;

[0083] FIG7 is a schematic diagram of a first reconstructed surface and a second reconstructed surface provided in an embodiment of the present application;

[0084] 8 and 9 are schematic diagrams of a data processing device provided in an embodiment of the present application;

[0085] FIG10 is a schematic diagram of the structure of a terminal device provided in an embodiment of the present application;

[0086] FIG11 is a schematic diagram of the structure of a network device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0087] The technical solution in this application will be described below with reference to the accompanying drawings.

[0088] To facilitate understanding of the embodiments of the present application, the following points are first explained:

[0089] First, to facilitate a clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, terms such as "first" and "second" are used to distinguish between identical or similar items with substantially identical functions and effects. For example, the first information and the second information are merely used to distinguish different information and do not limit their order or the number of signaling messages. Those skilled in the art will understand that terms such as "first" and "second" do not limit the number or execution order, and that terms such as "first" and "second" do not necessarily define differences.

[0090] Second, the "sending" and "receiving" in the embodiments of the present application indicate the direction of signal transmission. For example, "sending information to a computing node" can be understood as the destination end of the information being the computing node, which can include direct sending through the air interface, and also includes indirect sending through the air interface by other units or modules. "Receiving information from a computing node" can be understood as the source end of the information being the computing node, which can include direct receiving from the computing node through the air interface, and also includes indirect receiving from the computing node through the air interface from other units or modules. "Sending" can also be understood as the "output" of the chip interface, and "receiving" can also be understood as the "input" of the chip interface.

[0091] Third, in the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a; b; c; a and b; a and c; b and c; or a and b and c. Among them, a, b, and c can be single or multiple.

[0092] Fourth, in the embodiments of the present application, "when", "if" and "if" all mean that the device will perform corresponding processing under certain objective circumstances, which does not limit the time, nor does it require that the device must perform a judgment action when it is implemented, nor does it mean that there are other limitations.

[0093] In order to better understand the embodiment of the present application, several terms involved in the embodiment of the present application are explained below in conjunction with Figure 6.

[0094] 1. Communication and perception integration: This refers to the joint design of a single system to support both communication and perception. This means that communication devices can reuse the communication system's radio frequency signals for environmental perception. Therefore, this integration can enable the sharing of software and hardware resources or information. Compared to separately deployed communication and perception systems, it offers advantages in terms of size, weight, power consumption, cost, and efficiency (including spectrum efficiency, hardware efficiency, and information processing efficiency).

[0095] 2. Point cloud: A point cloud is a collection of a large number of data points representing the surface characteristics of an obstacle. These data points contain a wealth of information, including the obstacle's coordinate position (x, y, z) in a three-dimensional coordinate system, color information, object reflection intensity values, normal vectors, time, and other information. Point clouds are generally acquired using three-dimensional imaging sensors, such as binocular stereo cameras, 3D scanners, or red, green, blue (RGB)-depth (RGB-D) cameras. Furthermore, point clouds can be acquired using laser detection and ranging (LiDAR), a method widely used in fields such as autonomous driving and surveying.

[0096] 3. Scatterers: The sensing node can obtain sensing data, i.e., point clouds, by sending radio frequency signals for scanning. Then, after denoising the point clouds, the point clouds are segmented to obtain subsets of multiple data points. The data points in each subset have the same or similar features, and the features of different subsets are different. For example, the point cloud is segmented according to certain rules (such as Euclidean distance) through a clustering algorithm to obtain different classes or clusters. The features of point clouds in the same cluster are the same or similar, and the features of point clouds not in the same cluster are different. A bounding box is further drawn for the point cloud subset obtained after segmentation to obtain a scatterer, thereby completing the environmental reconstruction. Each scatterer has a unique identifier. Figure 1 is a schematic diagram of a scatterer provided in an embodiment of the present application. As shown in Figure 1, the identifiers of the seven scatterers are 1, 2, 3, 4, 5, 6, and 7, respectively.

[0097] The vertex format of the point cloud data describing the scatterer is expressed as:

[0098] Among them, [x n.m ,y n,m , z n,m ] represents the three-dimensional coordinates of the m-th vertex of the n-th scatterer. Each scatterer can be determined by eight vertex coordinates or by multiple vertex coordinates, which is not limited in this application.

[0099] The technical solution provided in this application can be applied to various communication systems, such as: long term evolution (LTE) system, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD) system, universal mobile telecommunication system (UMTS), world-wide interoperability for microwave access (WiMAX) communication system, fifth generation (5G) communication system, and future sixth generation (6G) communication system. Of course, the technical solution provided in this application can also be applied to other possible communication systems, for example, to the Internet of Things (IoT) network, a wireless local area network system that supports the 802.11 series of protocols, and can also be applied to a wireless personal area network system based on ultra wide band (UWB), and can also be applied to a sensing system, and can also be applied to vehicle to everything (V2X), machine type communication (MTC), machine-to-machine information interaction (long term evolution-machine, LTE-M), machine to machine (M2M) communication, vehicle to vehicle (V2V) communication, vehicle network communication (long term evolution-vehicle, LTE-V), satellite communication system, etc. The above-mentioned communication system applicable to this application is only an example, and the communication system applicable to this application is not limited to this. They are uniformly explained here and will not be repeated below.

[0100] The terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile equipment (ME), user terminal, terminal, wireless communication device, user agent or user device.

[0101] A terminal device is a device with wireless transceiver capabilities. It communicates with one or more core network (CN) devices (also called core devices) via access network equipment (or access devices) within the radio access network (RAN). Terminal devices can be deployed on land, indoors or outdoors, handheld or in vehicles; on water (such as ships); or in the air (such as aircraft, balloons, and satellites). In the embodiments of the present application, a terminal device may also be referred to as user equipment (UE), and may be a mobile phone, a mobile station (MS), a tablet computer, a computer with wireless transceiver capabilities, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical care, a wireless terminal device in smart grids, a wireless terminal device in transportation safety, a wireless terminal device in smart cities, a wireless terminal device in smart homes, a subscriber unit, a cellular phone, a wireless data card, a personal digital assistant (PDA), a tablet computer, a laptop computer, an MTC terminal device, a drone, etc. The terminal device may include various handheld devices with wireless communication capabilities, vehicle-mounted devices, wearable devices, computing devices, or other processing devices connected to a wireless modem. Optionally, the terminal device can be a handheld device (handset) with wireless communication function, a terminal device in the Internet of Things or the Internet of Vehicles, a terminal device of any form in 5G and communication systems evolved after 5G, etc., and this application does not limit this.

[0102] Furthermore, terminal devices can also be end devices in an IoT system, also known as IoT nodes. IoT is a crucial component of future information technology development. Its primary technical feature is connecting objects to the network through communication technologies, thereby enabling intelligent networks that interconnect humans and machines, and objects and things. Connections can be achieved through broadband or narrowband (NB) technology. IoT technology, for example, utilizes narrowband technology to achieve massive connections, deep coverage, and power-saving terminals.

[0103] In addition, terminal devices can also include sensors such as smart printers, train detectors, and gas stations. Their main functions include collecting data, receiving control information and downlink data from network devices, and sending electromagnetic waves to transmit uplink data to network devices.

[0104] In the embodiments of the present application, the device for realizing the function of the terminal device can be a terminal device, or a device capable of supporting the terminal device to realize the function, such as a chip system, which can be installed in the terminal device or used in combination with the terminal device. In the embodiments of the present application, the chip system can be composed of a chip, or it can include a chip and other discrete devices. In the embodiments of the present application, only the terminal device is used as an example for description, and the embodiments of the present application are not limited to the solutions of the embodiments of the present application.

[0105] A network device can be any device with wireless transceiver capabilities that can communicate with a terminal device, such as a RAN node that connects the terminal device to a wireless network. Currently, some examples of RAN nodes include: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, auxiliary station, multi-standard radio (motor slide retainer, MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, etc. The base station can be a macro base station, a micro base station, a relay node, a donor node or the like, or a combination thereof, or a wireless controller in a cloud radio access network (CRAN) scenario, a node in an open radio access network (O-RAN or ORAN) scenario, etc. The base station can also refer to a communication module, modem or chip used to be set in the aforementioned device or apparatus. The base station can also be a mobile switching center and a device that performs the base station function in D2D, V2X, and M2M communications, a network side device in a 6G network, a device that performs the base station function in future communication systems, etc. The base station can support networks with the same or different access technologies. Optionally, the RAN node can also be a server, a wearable device, a vehicle or an on-board device, etc. For example, the access network device in the vehicle to everything (V2X) technology can be a road side unit (RSU). The embodiments of the present application do not limit the specific technology and specific device form adopted by the network equipment.In some deployments, the network devices mentioned in the embodiments of the present application may include a CU, a DU, or both a CU and a DU, or a control plane CU node (central unit-control plane (CU-CP)), a user plane CU node (central unit-user plane (CU-UP)), and a DU node. For example, the network devices may include a gNB-CU-CP, a gNB-CU-UP, and a gNB-DU.

[0106] In some deployments, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes implementing portions of the base station's functionality. For example, a RAN node can be a CU, DU, CU-CP, CU-UP, or RU. The CU and DU can be separate or included in the same network element, such as the BBU. The RU can be included in a radio frequency device or radio unit, such as an RRU, AAU, or RRH.

[0107] In one possible design, the processing unit for implementing baseband functions in the BBU is called a baseband high layer (BBH) unit, and the processing unit for implementing baseband functions in the RRU / AAU / RRH is called a baseband low layer (BBL) unit.

[0108] In different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in the ORAN system, CU may also be called O-CU (Open CU), DU may also be called O-DU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. Any unit of CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0109] In the embodiments of the present application, the device for implementing the functions of the network device can be a network device; it can also be a device that can support the network device to implement the functions, such as a chip system, a hardware circuit, a software module, or a hardware circuit and a software module. The device can be installed in the network device or used in conjunction with the network device. In the embodiments of the present application, only the device for implementing the functions of the network device is used as an example to illustrate, and does not constitute a limitation on the solutions of the embodiments of the present application.

[0110] The network device and / or terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; it can also be deployed on the water surface; it can also be deployed on aircraft, balloons and satellites in the air. The embodiments of this application do not limit the scenarios in which the network device and the terminal device are located. In addition, the terminal device and the network device can be hardware devices, or they can be software functions running on dedicated hardware, software functions running on general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities including dedicated or general-purpose hardware devices and software functions. This application does not limit the specific forms of the terminal device and the network device.

[0111] To support artificial intelligence (AI) technology in wireless networks, AI nodes can be introduced into the network. The AI ​​nodes can be AI network elements or AI modules.

[0112] Optionally, the AI ​​node can be deployed in one or more of the following locations in the communication system: access network equipment, terminal equipment, or core network equipment. Alternatively, the AI ​​node can be deployed separately, for example, in a location other than any of the above devices, such as a host or cloud server in an over-the-top (OTT) system. The AI ​​node can communicate with other devices in the communication system, such as one or more of the following: network equipment, terminal equipment, or core network elements.

[0113] This application does not limit the number of AI nodes. For example, when there are multiple AI nodes, the multiple AI nodes can be divided based on function, such as different AI nodes are responsible for different functions.

[0114] AI nodes can be independent devices, or they can be integrated into the same device to implement different functions. They can also be network elements in hardware devices, software functions running on dedicated hardware, or virtualized functions instantiated on a platform (for example, a cloud platform). This application does not limit the specific form of the above-mentioned AI nodes.

[0115] Figure 2 is a schematic diagram of a communication system applicable to the method provided in an embodiment of the present application. The communication system shown in Figure 2 may include: a server 210, a network device 220, and a terminal device 230. Specifically, server 210 may be a computing node, network device 220 may be a sensing node or a computing node, and terminal device 230 may be a sensing node. In other words, a computing node may be a server or a network device, and a sensing node may be a network device or a terminal device, and this embodiment of the present application does not limit this.

[0116] The network device 220 and the terminal device 230 can scan by sending radio frequency signals to obtain point cloud data, and then perceive the surrounding environment by processing and analyzing the point cloud data. Optionally, the network device and / or the terminal device 230 can also be configured with a sensing device, such as a radar, a camera, etc., for sensing the environment. This application does not limit this. Since the network device 220 and the terminal device 230 exist as sensing nodes, whether the signal they send is a radio frequency signal in the communication system or a signal sent by a radar, it can be used for environmental perception in this application. Therefore, the signal is collectively referred to as a detection signal below.

[0117] In the communication system, the server 210 can be connected to the network device 220 via a wired or wireless manner, and the network device 220 can be connected to the obstacle via a wired or wireless manner. For example, the network device 220 can be a base station.

[0118] The computing node (such as the server 210 and / or the network device 220) can send a sensing task to the sensing node (such as the network device 220 and / or the terminal device 230), and the sensing node can transmit a detection signal in multiple directions to scan the surrounding environment. When the detection signal emitted by the sensing node reaches an obstacle and is reflected back, the sensing node can receive the reflected echo signal and use the reflected echo signal to obtain sensing data, and then process the sensing data and send the processed result to the computing node. Among them, the sensing data includes but is not limited to point clouds. For example, the sensing data can also be images, etc., which is not limited in this application.

[0119] For example, server 210 can act as a computing node and send a sensing task to network device 220, as shown in step 1 in the figure. After receiving the sensing task, network device 220, as a sensing node, can transmit a detection signal for scanning, as shown in step 2 in the figure. After the detection signal transmitted by network device 220 reaches obstacle 1 and is reflected back, network device 220 can receive the reflected echo signal, as shown in step 3 in the figure. Network device 220 can use the received echo signal to obtain sensing data, process the sensing data, and then send the processed data to server 210, as shown in step 4 in the figure. In this process, the computing node is server 210 and the sensing node is network device 220.

[0120] For another example, network device 220 can act as a computing node and send a sensing task to terminal node 230, as shown in ⑧ in the figure. After receiving the sensing task, terminal node 230, as a sensing node, can transmit a detection signal to scan, as shown in ⑨ in the figure. After the detection signal transmitted by terminal device 230 reaches obstacle 2 and is reflected back, terminal device 230 can receive the reflected echo signal, as shown in ⑥ in the figure. Terminal device 230 can use the received echo signal to obtain sensing data, process the sensing data, and then send the processed data to network device 220, as shown in ⑩ in the figure. In this process, the computing node is network device 220, and the sensing node is terminal device 230.

[0121] The sensing node can be an integrated transmitter and receiver. Integrated transmitter and receiver means that the device that transmits the signal and the device that receives the signal are the same device, that is, the transmitting device and the receiving device are the same device. As shown in Figure 2, the server 210 can send a sensing task to the network device 220, as shown in ① in the figure. After receiving the sensing task, the network device 220 can act as a transmitting device to transmit a detection signal for scanning, as shown in ② in the figure. The detection signal transmitted by the network device 220 reaches the obstacle 1 and is reflected back. The network device 220 can receive the reflected echo signal, as shown in ③ in the figure. The network device 220 can use the received echo signal to obtain sensing data, process the sensing data, and then send the processed data to the server 210, as shown in ④ in the figure. In this process, the transmitting device and the receiving device are the same device, that is, the network device 220. This method of obtaining sensing data through an integrated transmitter and receiver can also be called self-transmission and self-reception.

[0122] Sensing nodes can also have separate transmitters and receivers. Separate transmitters and receivers mean that the device that sends the signal and the device that receives the signal are different devices, i.e., the transmitting and receiving devices are different devices. As shown in Figure 2, server 210 can send a sensing task to network device 220, as shown in step 1. After receiving the sensing task, network device 220 can act as a transmitter to transmit a detection signal for scanning, as shown in step 5. The detection signal transmitted by network device 220 is reflected by obstacle 2, and terminal device 230, as a receiver, can receive the reflected echo signal, as shown in step 6. Terminal device 230 can use the received echo signal to obtain sensing data, process the sensing data, and then send the processed results to server 210, as shown in step 7. Alternatively, it can send the processed results to network device 220, as shown in step 10, which can then send the processed results to server 210, as shown in step 4. In this process, the transmitting and receiving devices are different devices, i.e., the transmitting device is network device 220, and the receiving device is terminal device 230. Among them, the separation of sending and receiving can also be called sending by oneself and receiving by others, or one sending and one receiving.

[0123] It should be understood that what is shown in the figure is only an example, and this application does not limit the specific form and quantity of the network device 210, the network device 220, the terminal device 230 and the obstacles.

[0124] With the development of integrated communication and perception, base stations and terminals can now perceive their surroundings around the clock and in all weather conditions. Network equipment or terminals can then transmit detection signals to scan and, from the received echo signals, generate a point cloud of obstacles. Because the amount of point clouds acquired is enormous, these scanned point clouds can be de-noised, segmented, and bounded by minimum bounding boxes, resulting in scatterers and complete environmental reconstruction.

[0125] Figure 3 is a schematic diagram of the environmental reconstruction results under the electromagnetic wave characteristics provided by an embodiment of the present application. As shown in Figure 3, in the electromagnetic simulation scenario, the base station is placed 3 meters away from the target wall, and the target wall is 5 meters long. The base station sends a detection signal, scans the target wall, and obtains a point cloud based on the original echo signal. The point cloud is then segmented to obtain three scattering surfaces, as shown in scattering surfaces 1, 2, and 3 in the figure. This completes the reconstruction of the target wall.

[0126] Due to the propagation characteristics of electromagnetic waves, when the beam width is constant, the incident angle of the detection signal sent by the base station increases, and the error of the point cloud obtained by the base station using the echo signal also increases accordingly.

[0127] The beamwidth of the detection signal transmitted by the sensing node may refer to the angle between the two half-power points of the beam, that is, the angle between the two directions where the radiation power drops by 3 decibels (dB) on either side of the maximum radiation direction of the detection signal. The incident angle of the detection signal may refer to the angle between the incident direction of the detection signal and the reconstruction plane.

[0128] For ease of understanding, Figure 4 shows a schematic diagram of the beamwidth and incident angle of the detection signal. The beamwidth of the detection signal is shown as θ in Figure 4, and the incident angle of the detection signal is shown as β in Figure 4. It can be understood that the incident angle of the detection signal can be calculated based on the position of the sensing node, the position of the reconstruction surface, and the sensing range of the detection signal.

[0129] Exemplarily, Figure 5 is a schematic diagram of the point cloud distribution of the base station transceiver under different beam widths provided by this application. In the electromagnetic simulation scenario, the base station is placed 3 meters away from the target wall, and the length of the target wall is 5 meters. The base station sends a detection signal, scans the target wall, and obtains a point cloud through the original echo signal. As shown in (a) in Figure 5, when the beam width of the detection signal emitted by the base station is 2°, the point cloud distribution is obtained; as shown in (b) in Figure 5, when the beam width of the detection signal emitted by the base station is 10°, the point cloud distribution is obtained.

[0130] As previously mentioned, due to the characteristics of electromagnetic waves, the point cloud obtained from the echo signal contains errors. As shown in Figures 5(a) and 5(b), when the incident angle of the detection signal is constant, the beamwidth of the detection signal increases, and the error of the point cloud obtained by the base station using the echo signal increases accordingly.

[0131] The inventors of this application discovered that when sensor nodes process erroneous point clouds, coupled with inherent algorithmic errors, over-segmentation of the point clouds can occur during environment reconstruction, resulting in a loss of accuracy. In other words, the target object reconstructed from the point cloud obtained by the sensor nodes differs from the actual environment.

[0132] The so-called over-segmentation is excessive segmentation. For example, the point cloud that actually belongs to the same surface is divided into multiple surfaces, or the point cloud that actually belongs to the same body is divided into multiple bodies.

[0133] In light of this, this application provides a data processing method that determines whether two reconstructed surfaces are the same by comparing their angular difference (or included angle) and / or distance difference with different thresholds. This method can address the over-segmentation problem caused by electromagnetic wave characteristics and the segmentation algorithm itself, reduce the precision loss of environmental reconstruction, and improve perception accuracy.

[0134] The method provided in the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0135] Figure 6 is a schematic flow chart of the data processing method provided by the present application. Figure 6 describes the data processing method provided by the present application by taking the interaction between the computing node and the perception node as an example. As an example, the computing node can be a server or a network device, or a component configured in the server or network device (such as a chip, a chip system, a processor, etc.), or a logic module or software that can realize all or part of the functions of the computing node; the perception node can be a network device or a terminal device, or a component configured in the network device or terminal device (such as a chip, a chip system, a processor, etc.), or a logic module or software that can realize all or part of the functions of the perception node.

[0136] The method 600 shown in FIG6 may include steps 610 to 670 . Each step in the method 600 is described in detail below.

[0137] In step 610, the computing node sends a sensing signaling to the sensing node, where the sensing signaling is used to instruct the sensing node to sense the surrounding environment. Correspondingly, the sensing node receives the sensing signaling from the computing node.

[0138] In other words, the computing node sends the sensing task to the sensing node in step 610 .

[0139] Although the figure only shows the step of the computing node sending perception signaling to one perception node, it can be understood that the computing node can send perception signaling to more perception nodes, or in other words, issue perception tasks.

[0140] In response to the sensing signaling, the sensing node may begin environmental sensing. The sensing node may perform scanning based on a sensing range. The sensing range may refer to the maximum angular range over which the sensing node transmits a detection signal, or the maximum angular range over which the detection signal scans. The angular range may further include a horizontal angular range and / or a vertical angular range.

[0141] One possible situation is that the sensing range is determined by the sensing node itself, for example, the sensing node determines the sensing range according to its own sensing capability.

[0142] Another possible case is that the sensing range is indicated by a computing node.

[0143] Optionally, the method further includes:

[0144] Step 620: The sensing node sends sensing capability information to the computing node, where the sensing capability information indicates the sensing capability of the sensing node. Accordingly, the computing node receives the sensing capability information from the sensing node; and

[0145] In step 630, the computing node sends sensing range information to the sensing node, where the sensing range information is used to indicate the sensing range. Accordingly, the computing node receives the sensing range information from the sensing node.

[0146] In step 620, the sensing capability information of the sensing node may illustratively include: sensing performance parameters of the sensing node. The sensing performance parameters of the sensing node may include, but are not limited to, resolution, accuracy, and latency. Resolution indicates the closest distance between two adjacent objects that can be distinguished, and includes range resolution, velocity resolution, and angle resolution. For example, a range resolution of 5 meters indicates that measurements are performed with a maximum granularity of 5 meters; for example, all objects within a 5-meter range are considered a single object. Accuracy indicates the degree of closeness between the measured and true values ​​of the obstacle's position, angle, distance, or velocity. For example, an accuracy of 1 meter indicates that the position error cannot exceed 1 meter. Alternatively, accuracy can be described using root mean square error (RMS) or mean square error (MSE). Latency indicates the time or upper limit from a signal transmitter to a signal receiver, the time or upper limit from a signal receiver to the transmission of a sensing result, or the time or upper limit from a signal transmitter to a signal receiver. For example, a latency of 1 second indicates that the delay from the receiving end receiving the signal to reporting the sensing result cannot exceed 1 second.

[0147] Optionally, the sensing capability information of a sensing node may further include the sensing devices configured for the sensing node. The sensing performance parameters of the sensing node may specifically refer to the sensing performance parameters of each sensing device configured for the sensing node. For example, the sensing devices may include, but are not limited to, lidar, millimeter-wave radar, ultrasonic radar (ultrasonic sensor), camera, and sensor.

[0148] Furthermore, in order to facilitate the computing node to distinguish the sensing capability information of different sensing nodes, the sensing capability information may also carry the identification of the sensing node. The identification of the sensing node is used to uniquely identify a sensing node, and each sensing node corresponds to one identification.

[0149] In step 630, the computing node may determine the perception range of the perception task assigned to the perception node based on the perception capability information received from the perception node, and then indicate the perception range to the perception node via perception range information. For example, the perception range information may include the upper and lower limits of the maximum angular range. This application does not limit the specific manner and content of the perception range information used to indicate the perception range.

[0150] In step 640 , the sensing node determines whether the first reconstructed surface and the second reconstructed surface are the same surface based on a determination criterion.

[0151] In other words, when the perception node determines whether an image is over-segmented, it uses two reconstructed surfaces as a pair. For ease of distinction and explanation, the objects being judged are referred to as the first reconstructed surface and the second reconstructed surface. The first and second reconstructed surfaces are obtained by performing denoising, segmentation, and bounding box drawing on the point cloud perceived by the perception node.

[0152] In practical applications, after processing the point cloud acquired by the sensing node through processes such as denoising, segmentation, and bounding box drawing, the resulting image may be two-dimensional or three-dimensional, depending on the depth information of the perceived point cloud. In this article, for ease of distinction and explanation, the two-dimensional result obtained from point cloud processing is referred to as a reconstructed surface, and the three-dimensional result obtained from point cloud processing is referred to as a scatterer. Furthermore, through perception and processing, multiple surfaces of an obstacle may be obtained, and these multiple surfaces can be combined to form a three-dimensional scatterer.

[0153] The sensing node can determine whether the result obtained after processing the point cloud is two-dimensional or three-dimensional based on a predefined third threshold and the depth information of the point cloud. When the depth information of the point cloud is greater than (or greater than or equal to) the third threshold, it can be determined that the result obtained after processing the point cloud is three-dimensional, that is, a scatterer; when the depth information of the sensed point cloud is less than or equal to (or less than) the third threshold, it can be determined that the result obtained after processing the point cloud is two-dimensional, that is, a reconstructed surface.

[0154] It is understood that after the perception node performs denoising, segmentation, and bounding box processing on the perceived point cloud, the resulting reconstructed surface or scatterer has different shapes. For example, the reconstructed surface can be a polygon or an irregular shape, and the scatterer can be a polyhedron or a geometrically irregular solid figure, etc., which are not limited in this application.

[0155] The first reconstructed surface and the second reconstructed surface in this application can be two reconstructed surfaces obtained by processing a point cloud, or can be the principal surfaces of two scatterers (e.g., the first scatterer and the second scatterer) obtained by processing a point cloud, or can be one reconstructed surface and the principal surface of one scatterer obtained by processing a point cloud. The principal surface of a scatterer can be the surface with the largest area in the scatterer.

[0156] The determination criteria in this application may include one or more of the following: Criterion 1) the angular difference between the first reconstructed surface and the second reconstructed surface is less than a first threshold, or Criterion 2) the distance difference between the first reconstructed surface and the second reconstructed surface is less than a second threshold. In other words, the sensing node can determine whether the first reconstructed surface and the second reconstructed surface are the same surface based on this determination criterion. Whether the determination criterion specifically includes Criterion 1) or Criterion 2) or both can be indicated by the computing node or predefined by the protocol.

[0157] Among them, criterion 1) is to determine whether the first reconstructed surface and the second reconstructed surface are the same surface based on the angle difference between the two surfaces.

[0158] Assuming that the normal vector of the first reconstructed surface is w1 and the normal vector of the second reconstructed surface is w2, the angle between the normal vector w1 of the first reconstructed surface and the normal vector w2 of the second reconstructed surface is the angle difference between the first reconstructed surface and the second reconstructed surface.

[0159] Figure 7 is a schematic diagram of a first reconstructed surface and a second reconstructed surface provided in an embodiment of the present application. As shown in Figure 7(a), the first reconstructed surface is labeled "1" and the second reconstructed surface is labeled "2." The angle between the normal vector w1 of the first reconstructed surface and the normal vector w2 of the second reconstructed surface is denoted as α, where α is the angular difference between the first and second reconstructed surfaces.

[0160] Criterion 2) determines whether the first reconstructed surface and the second reconstructed surface are the same surface based on the distance difference between the two surfaces.

[0161] Assume that the center point of the first reconstructed surface is O1, the center point of the second reconstructed surface is O2, the distance from the center point O1 of the first reconstructed surface to the second reconstructed surface is recorded as l1, and the distance from the center point O2 of the second reconstructed surface to the first reconstructed surface is recorded as l2. The distance difference between the first reconstructed surface and the second reconstructed surface includes any one of the following items: the minimum value of the distance l1 from the center point O1 of the first reconstructed surface to the second reconstructed surface and the distance l2 from the center point O2 of the second reconstructed surface to the first reconstructed surface, the maximum value of the distance l1 from the center point O1 of the first reconstructed surface to the second reconstructed surface and the distance l2 from the center point O2 of the second reconstructed surface to the first reconstructed surface, and the average value of the distance l1 from the center point O1 of the first reconstructed surface to the second reconstructed surface and the distance l2 from the center point O2 of the second reconstructed surface to the first reconstructed surface, that is, (l1+l2) / 2. The minimum value may be recorded as min(l1, l2), the maximum value may be recorded as max(l1, l2), and the average value may be recorded as avg(l1, l2).

[0162] As shown in Figure 7(b), the first reconstructed surface is labeled "1" and the second reconstructed surface is labeled "2." The distance l1 from the center point O1 of the first reconstructed surface to the second reconstructed surface, and the distance l2 from the center point O2 of the second reconstructed surface to the first reconstructed surface, are considered. The distance difference between the first and second reconstructed surfaces can be any of the following: min(l1, l2), max(l1, l2), and avg(l1, l2).

[0163] The determination criterion may be indicated by the computing node, or may be predefined by the protocol, which is not limited in this application.

[0164] If the decision criterion is indicated by the computing node, the method may further include step 650: the sensing node receives second information from the computing node, the second information being used to determine the decision criterion. Accordingly, the computing node sends the second information to the sensing node.

[0165] A possible implementation manner of using the second information to determine the decision criterion is that the second information is used to indicate the first threshold and / or the second threshold.

[0166] When the second information indicates the first threshold but not the second threshold, the criterion for determining whether the first reconstructed surface and the second reconstructed surface are the same surface is criterion 1), that is, the angle difference between the first reconstructed surface and the second reconstructed surface is less than the first threshold.

[0167] When the second information indicates the second threshold but not the first threshold, the criterion for determining whether the first reconstructed surface and the second reconstructed surface are the same surface is criterion 2), that is, the distance difference between the first reconstructed surface and the second reconstructed surface is less than the second threshold.

[0168] When the second information indicates the first threshold and the second threshold, the judgment criterion for determining whether the first reconstructed surface and the second reconstructed surface are the same surface is a combination of criterion 1) and criterion 2), that is, the angle difference between the first reconstructed surface and the second reconstructed surface is less than the first threshold, and the distance difference between the first reconstructed surface and the second reconstructed surface is less than the second threshold.

[0169] Another possible implementation method of using the second information to determine the judgment criteria is that the second information is used to indicate the beam width of the detection signal emitted by the sensing node, the incident angle of the detection signal, and one or more of the following: the distance between the sensing node and the obstacle, the first constant or the second constant, the first coefficient or the second coefficient.

[0170] In one possible design, the second information is used to indicate the beam width of the detection signal transmitted by the sensing node, the incident angle of the detection signal, the first constant and the first coefficient.

[0171] The first threshold can be determined based on the beam width of the detection signal transmitted by the sensing node indicated by the second information, the incident angle of the detection signal, the first constant and the first coefficient.

[0172] When the second information is used to indicate the beam width of the detection signal emitted by the sensing node, the incident angle of the detection signal, the first constant and the first coefficient, the judgment criteria for determining whether the first reconstructed surface and the second reconstructed surface are the same surface specifically include: Criterion 1) The angle difference between the first reconstructed surface and the second reconstructed surface is less than the first threshold.

[0173] Optionally, the first threshold s satisfies:

[0174] Among them, θ represents the beam width of the detection signal emitted by the sensing node, β represents the incident angle of the detection signal, and the incident angle is used to indicate the angle between the incident direction of the detection signal emitted by the sensing node and the obstacle, ε1 is the first constant, and k1 is the first coefficient.

[0175] When the first constant ε1 is 0, or the second information does not indicate the first constant ε1, the first threshold s may be transformed into:

[0176] Furthermore, when the first coefficient k1 is 1, the first threshold s can be transformed into:

[0177] It can be seen from the formula that when the incident angle β of the detection signal is constant, the first threshold value increases as the beam width θ of the detection signal transmitted by the sensing node increases; when the beam width of the detection signal transmitted by the sensing node is constant, the first threshold value increases as the incident angle β of the detection signal increases.

[0178] Furthermore, when the beamwidth of the detection signal approaches zero, Then the first threshold can be transformed into:

[0179] In one possible design, the second information is used to indicate the beam width of the detection signal transmitted by the sensing node, the incident angle of the detection signal, the distance between the sensing node and the obstacle, the second constant and the second coefficient.

[0180] The second threshold is determined according to the beam width, the incident angle, the distance between the sensing node and the obstacle, the second constant and the second coefficient indicated by the second information.

[0181] When the second information indicates the beam width of the detection signal emitted by the sensing node, the incident angle of the detection signal, the second constant and the second coefficient, the judgment criteria for determining whether the first reconstructed surface and the second reconstructed surface are the same surface specifically include: Criterion 2) The distance difference between the first reconstructed surface and the second reconstructed surface is less than the second threshold.

[0182] Optionally, the second threshold d satisfies:

[0183] Wherein, r represents the distance between the sensing node and the obstacle, θ represents the beam width of the detection signal emitted by the sensing node, β represents the incident angle of the detection signal, ε2 is the second constant, and k2 is the second coefficient.

[0184] When the second constant ε2 is 0, or the second information does not indicate the second constant ε2, the second threshold d may be transformed into:

[0185] Furthermore, when the second coefficient k2 is 1, the second threshold d can be transformed into:

[0186] It can be seen from the formula that when the incident angle β of the detection signal is constant, the second threshold value increases as the beam width θ of the detection signal transmitted by the sensing node increases; when the beam width of the detection signal transmitted by the sensing node is constant, the second threshold value increases as the incident angle β of the detection signal increases.

[0187] Furthermore, when the beamwidth of the detection signal approaches zero, Then the second threshold can be transformed into:

[0188] The distance between the sensing node and the obstacle can be indicated by the second information or determined by the sensing node. For example, the sensing node can be equipped with a positioning system to obtain the sensing node's location, and the obstacle can be equipped with a positioning system to obtain the obstacle's location. The distance between the sensing node and the obstacle can be obtained based on the positions of the sensing node and the obstacle. In this case, the second information may not indicate the distance between the sensing node and the obstacle.

[0189] In one possible design, the second information is used to indicate the beam width of the detection signal transmitted by the sensing node, the incident angle of the detection signal, the distance between the sensing node and the obstacle, the first constant or the second constant, the first coefficient or the second coefficient.

[0190] The beam width, incident angle, first constant and first coefficient indicated by the second information are used to determine the first threshold, and the beam width, incident angle, distance between the sensing node and the obstacle, second constant and second coefficient indicated by the second information are used to determine the second threshold.

[0191] It can be understood that in this case, the judgment criteria for determining whether the first reconstructed surface and the second reconstructed surface are the same surface specifically include: criterion 1) the angle difference between the first reconstructed surface and the second reconstructed surface is less than a first threshold, and criterion 2) the distance difference between the first reconstructed surface and the second reconstructed surface is less than a second threshold.

[0192] An example of a sensing node determining whether a first reconstructed surface and a second reconstructed surface are the same surface based on a determination criterion is to determine whether the first reconstructed surface and the second reconstructed surface are the same surface based on an angle difference between the first reconstructed surface and the second reconstructed surface. When the angle difference α between the first reconstructed surface and the second reconstructed surface is less than a first threshold, it can be determined that the first reconstructed surface and the second reconstructed surface are the same reconstructed surface. When the angle difference α between the first reconstructed surface and the second reconstructed surface is greater than or equal to the first threshold, it can be determined that the first reconstructed surface and the second reconstructed surface are not the same reconstructed surface.

[0193] Another example of a sensing node determining whether a first reconstructed surface and a second reconstructed surface are the same surface based on a determination criterion is to determine whether the first reconstructed surface and the second reconstructed surface are the same surface based on a distance difference between the first reconstructed surface and the second reconstructed surface. When the distance difference l between the first reconstructed surface and the second reconstructed surface is less than a second threshold, it can be determined that the first reconstructed surface and the second reconstructed surface are the same reconstructed surface. When the distance difference l between the first reconstructed surface and the second reconstructed surface is greater than or equal to a second threshold, it can be determined that the first reconstructed surface and the second reconstructed surface are not the same reconstructed surface.

[0194] Another example of a sensing node determining whether a first reconstructed surface and a second reconstructed surface are the same surface based on a determination criterion is to determine whether the first reconstructed surface and the second reconstructed surface are the same surface based on an angle difference between the first reconstructed surface and the second reconstructed surface and a distance difference between the first reconstructed surface and the second reconstructed surface. When the angle difference α between the first reconstructed surface and the second reconstructed surface is less than a first threshold value, and the distance difference l between the first reconstructed surface and the second reconstructed surface is less than a second threshold value, it can be determined that the first reconstructed surface and the second reconstructed surface are the same reconstructed surface. When the angle difference α between the first reconstructed surface and the second reconstructed surface is greater than or equal to the first threshold value, or when the distance difference l between the first reconstructed surface and the second reconstructed surface is greater than or equal to a second threshold value, it can be determined that the first reconstructed surface and the second reconstructed surface are not the same reconstructed surface.

[0195] After step 640, the perception node can determine that the first reconstructed surface and the second reconstructed surface may be the same surface or different surfaces. When the first reconstructed surface and the second reconstructed surface are different surfaces, the perception node can report the perception data of the first reconstructed surface and the second reconstructed surface to the computing node according to the method provided in the prior art. When the first reconstructed surface and the second reconstructed surface are the same surface, the perception node can further perform the following step 660.

[0196] In step 660 , when the first reconstructed surface and the second reconstructed surface are the same surface, the sensing node obtains a third reconstructed surface based on the first reconstructed surface and the second reconstructed surface.

[0197] In one possible scenario, the point cloud acquired through perception is processed to obtain a reconstructed surface. The perception node determines, based on a judgment criterion, that the first reconstructed surface and the second reconstructed surface are the same surface. Therefore, a third reconstructed surface can be obtained based on the point cloud of the first reconstructed surface and the point cloud of the second reconstructed surface. In one implementation, the perception node can merge the point cloud of the first reconstructed surface with the point cloud of the second reconstructed surface and perform processing based on some or all of the data points in the merged point cloud, such as denoising and drawing a bounding box, to obtain the third reconstructed surface.

[0198] Another possible scenario is that after processing the point cloud acquired through perception, a scatterer is obtained. When the perception node determines, based on a judgment criterion, that the first reconstructed surface corresponding to the first scatterer and the second reconstructed surface corresponding to the second scatterer are the same surface, it can further determine that the first scatterer and the second scatterer are the same scatterer. Therefore, a third scatterer can be obtained based on the point cloud of the first scatterer and the point cloud of the second scatterer. In one implementation, the perception node can merge the point cloud of the first scatterer and the point cloud of the second scatterer, and perform processing based on some or all of the data points in the merged point cloud, such as denoising and drawing a bounding box, to finally obtain the third scatterer. The main surface of the third scatterer can be recorded as the third reconstructed surface. It should be understood that the specific implementation method of obtaining the third reconstructed surface based on the first reconstructed surface and the second reconstructed surface illustrated above is merely an example and should not constitute any limitation to this application. This application does not limit the specific method of obtaining the third reconstructed surface based on the first reconstructed surface and the second reconstructed surface.

[0199] In step 670, the sensing node sends first information to the computing node, where the first information is used to indicate the sensing data of the target object. Correspondingly, the computing node receives the first information from the sensing node.

[0200] The third reconstructed surface may be an independent surface or a surface in a scatterer. For the convenience of explanation, the independent surface or scatterer is referred to as the target object. The sensing node may report the sensing data of the target object to the computing node through the first information.

[0201] Exemplarily, when the target object is a two-dimensional surface, the perception data of the target object includes position information of the surface (ie, the third reconstructed surface), such as coordinates of multiple vertices of the surface.

[0202] When the target object is a three-dimensional scatterer, the scatterer can, for example, be obtained based on two or more scatterers obtained through processing of the point cloud, that is, the scatterer can be a third scatterer, and the perception data of the target object includes the position information of the scatterer, such as the coordinates of multiple vertices of the scatterer.

[0203] Optionally, the perception data of the target object includes location information of the target object.

[0204] The position information of the target object may include, for example, vertex coordinates of the target object.

[0205] In one possible scenario, when the target object is an independent surface (ie, the third reconstructed surface), the sensing node sends the vertex coordinates of the third reconstructed surface to the computing node. The computing node can determine the position of the third reconstructed surface based on the vertex coordinates of the third reconstructed surface.

[0206] It can be understood that the third reconstruction surface can be a rectangle or an irregular two-dimensional shape.

[0207] As an example, when the third reconstructed surface is a rectangle, the perception node may send the coordinates of four vertices of the third reconstructed surface to the computing node. The vertex coordinates may determine information such as the specific position of the third reconstructed surface.

[0208] In another example, when the third reconstructed surface is an irregular two-dimensional shape, the perception node performs contour extraction on the third reconstructed surface to obtain contour information of the third reconstructed surface. Based on the obtained contour information, the perception node extracts the position information of the contour point set of the third reconstructed surface. The perception node can send the coordinates of the contour point set of the third reconstructed surface and the coordinates of one or more points within the third reconstructed surface to the computation node. These coordinates can be used to determine information such as the spatial contour and specific position of the third reconstructed surface.

[0209] It is understood that the vertex coordinates of the third reconstructed surface sent by the sensing node to the computing node may include one or more of the following: coordinates of four vertices of the third reconstructed surface, coordinates of a set of contour points of the third reconstructed surface, and coordinates of one or more points within the third reconstructed surface. The vertex coordinates of the third reconstructed surface may determine information such as the spatial contour and specific position of the third reconstructed surface.

[0210] In one possible scenario, when the target object is a scatterer (ie, a third scatterer), the sensing node sends the vertex coordinates of the third scatterer to the computing node. The computing node can determine the information included in the third scatterer based on the vertex coordinates of the third scatterer.

[0211] It can be understood that the third scatterer can be a hexahedron or a geometrically irregular solid shape.

[0212] In one example, when the third scatterer is a hexahedron, the sensing node can send the eight vertex coordinates of the third scattering surface to the computing node. The vertex coordinates can indicate the specific location of the third scatterer and other information. For example, in Figure 1, each of the seven scatterers is represented by eight vertex coordinates.

[0213] In another example, when the third scatterer is a geometrically irregular solid figure, the sensing node performs contour extraction on the third scatterer to obtain contour information of the third scatterer, and then extracts the position information of the contour point set of the third scatterer based on the obtained contour information. The sensing node can send the coordinates of the contour point set of the third scatterer and the coordinates of one or more points within the third scatterer to the computing node. These coordinates can be used to determine information such as the specific location and spatial contour of the third scatterer.

[0214] It is understood that the vertex coordinates of the third scatterer sent by the sensing node to the computing node may include one or more of the following: eight vertex coordinates of the third scatterer, coordinates of a contour point set of the third scatterer, and coordinates of one or more points within the third scatterer. The vertex coordinates of the third scatterer may indicate information such as the spatial contour and specific position of the third scatterer.

[0215] Optionally, the first information is also used to indicate the identification of the target object.

[0216] It can be understood that the sensing node sends first information to the computing node, where the first information is used to indicate the identification of the target object. Correspondingly, the computing node receives the first information from the sensing node.

[0217] Each target object has a unique identifier. For example, after a sensing node processes the perceived point cloud, the identifiers of the three scatterers can be represented as "1," "2," and "3," or as "001," "010," and "011," respectively. The above representation of the unique identifiers of the scatterers is only an example and is not limited in this application.

[0218] One possible situation is that if the perception node processes the point cloud obtained through perception to obtain a reconstructed surface or a scatterer, the identification of the reconstructed surface or the scatterer is not limited.

[0219] One possible situation is that if the perception node processes the point cloud obtained through perception to obtain two surfaces or two scatterers, and the judgment criteria determine that the two surfaces are the same surface or the two scatterers are the same scatterer, the identification of the target object can be updated to the identification of any one of the current two surfaces or the identification of any one of the current two scatterers.

[0220] As an example, when the target object is an independent surface, the identifier of the target object (ie, the third reconstructed surface) may be the identifier of the first reconstructed surface or the identifier of the second reconstructed surface.

[0221] In another example, when the target object is a scatterer, the identifier of the target object (ie, the third scatterer) may be the identifier of the first scatterer or the identifier of the second scatterer.

[0222] Exemplarily, when the target object is the third reconstructed surface, the sensing node sends the identifier of the third reconstructed surface to the computing node. For example, the identifier of the first reconstructed surface is recorded as "1," and the identifier of the second reconstructed surface is recorded as "2." After the judgment criterion determines that the first reconstructed surface and the second reconstructed surface are the same surface, a third reconstructed surface is obtained based on the first and second reconstructed surfaces. The identifier of the third reconstructed surface can be recorded as "1" or "2."

[0223] The computing node receives the first information from the sensing node, and the sensing node completes the reporting of the reconstructed surface or scatterer. It is understandable that the reconstructed surface or scatterer obtained by processing the point cloud obtained by the sensing node is not necessarily exactly two. The reconstructed surface and / or scatterer obtained by processing the point cloud obtained by the sensing node may be one, two, or more. Since the sensing node makes judgments based on the reconstructed surface, the following will explain the situation of obtaining different numbers of reconstructed surfaces. It should be understood that the reconstructed surface mentioned here can refer to the reconstructed surface obtained by processing the point cloud, or it can be the main surface of the scatterer.

[0224] When one reconstructed surface is obtained, the perception node can directly report the perception data of the target object to which the reconstructed surface belongs (such as the reconstructed surface itself or a scatterer); when two reconstructed surfaces are obtained, the perception node can make a judgment based on the aforementioned step 640, and in the case of over-segmentation, merge the point cloud based on steps 660 and 670, and report the perception data of the target object; when three or more reconstructed surfaces are obtained, the perception node can first obtain the first reconstructed surface and the second reconstructed surface from the N reconstructed surfaces, and then execute the subsequent process based on the aforementioned steps 640, 660 and 670.

[0225] Optionally, before step 640 , the method further includes: acquiring a first reconstructed surface and a second reconstructed surface.

[0226] One possible situation is that after processing the point cloud acquired by perception, N (N is an integer greater than 2) reconstructed surfaces are obtained.

[0227] If the point cloud acquired through perception is processed to obtain N reconstructed surfaces, the N reconstructed surfaces can be first segmented to obtain at least one pair of reconstructed surfaces, and then a determination can be made for each pair of reconstructed surfaces based on the determination criteria. Alternatively, the perception node can repeatedly perform step 640 to determine whether two or more reconstructed surfaces obtained through processing are over-segmented. Assume that the number of reconstructed surfaces obtained through processing of the point cloud is N, and the N reconstructed surfaces are identified as 1, 2, ..., N.

[0228] In one possible implementation, the sensing node may arbitrarily select two reconstructed surfaces from the N reconstructed surfaces as a pair and make a determination based on a determination criterion. For any pair of reconstructed surfaces, one surface is an instance of the first reconstructed surface, and the other surface is an instance of the second reconstructed surface.

[0229] Another possible implementation method is that the perception node can use one of the reconstructed surfaces as a reference surface to determine whether the reference surface and the other reconstructed surface are the same surface. That is, taking two reconstructed surfaces as a pair, it is determined whether each pair of reconstructed surfaces is the same surface. Among them, when the judgment is made based on the judgment criteria in the first round, the reconstructed surface selected as the reference surface can be polled from any reconstructed surface, and judged in turn with the other (N-1) reconstructed surfaces among the N reconstructed surfaces obtained by processing; when the judgment is made based on the judgment criteria in the second round, the next reconstructed surface polled is used as the reconstructed surface selected as the reference surface, and judged in turn with the other (N-2) reconstructed surfaces among the N reconstructed surfaces obtained by processing. Similarly, when the perception node traverses all (N-1) reconstructed surfaces among the N reconstructed surfaces obtained by processing, the judgment of the N reconstructed surfaces is completed.

[0230] For example, N is 4, and the four reconstructed surfaces are reconstructed surface 1, reconstructed surface 2, reconstructed surface 3, and reconstructed surface 4. Assuming that polling starts from reconstructed surface 1, in the first round of judgment based on the judgment criteria, with reconstructed surface 1 as the reference surface, the cases where it is necessary to determine whether two reconstructed surfaces are the same surface based on the judgment criteria include: reconstructed surface 1 and reconstructed surface 2, reconstructed surface 1 and reconstructed surface 3, and reconstructed surface 1 and reconstructed surface 4. Among them, in the case where it is determined based on the judgment criteria whether reconstructed surface 1 and reconstructed surface 2 are the same surface, reconstructed surface 1 is an example of the first reconstructed surface, and reconstructed surface 2 is an example of the second reconstructed surface. In the second round of judgment based on the judgment criteria, with reconstructed surface 2 as the reference surface, the cases where it is necessary to determine whether two reconstructed surfaces are the same surface based on the judgment criteria include: reconstructed surface 2 and reconstructed surface 3, and reconstructed surface 2 and reconstructed surface 4. In the third round of judgment based on the judgment criteria, with reconstructed surface 3 as the reference surface, the cases where it is necessary to determine whether two reconstructed surfaces are the same surface based on the judgment criteria include: reconstructed surface 3 and reconstructed surface 4. In this case, reconstruction surface 3 is an example of the first reconstruction surface, and reconstruction surface 4 is an example of the second reconstruction surface. It should be understood that the method provided above is only an example, and this application does not limit the number of reconstruction surfaces and how to divide multiple reconstruction surfaces.

[0231] Another possible situation is that after processing the point cloud acquired by perception, N (N is an integer greater than 2) scatterers are obtained.

[0232] If N scatterers are obtained after processing the point cloud acquired through perception, the main surface of each scatterer is recorded as the reconstructed surface of each scatterer, and N reconstructed surfaces can be obtained. The N reconstructed surfaces can be first divided to obtain at least one pair of reconstructed surfaces. Then, based on a judgment criterion, each pair of reconstructed surfaces can be judged to determine whether each pair of reconstructed surfaces is the same surface, and further determine whether each pair of scatterers corresponding to each pair of reconstructed surfaces is the same scatterer.

[0233] Since several possible implementations of how to divide N reconstruction surfaces have been described above with examples, they will not be repeated here for the sake of brevity.

[0234] It is understandable that the perception node can perform steps 640, 660, and 670 once each time a pair of reconstructed surfaces is obtained. For example, the perception node obtains N (N is an integer greater than 2) reconstructed surfaces after processing the point cloud obtained by perception, selects two of the reconstructed surfaces as a pair, respectively as the first reconstructed surface and the second reconstructed surface, and then judges the first reconstructed surface and the second reconstructed surface based on the judgment criterion. If the first reconstructed surface and the second reconstructed surface meet the judgment criterion, it is determined that the first reconstructed surface and the second reconstructed surface are the same surface, and then the point clouds of the first reconstructed surface and the second reconstructed surface are merged, and then some or all of the data points in the merged point cloud are processed to obtain a third reconstructed surface. The perception node reports the perception data of the third reconstructed surface to the computing node, and further, the perception node reports the vertex coordinates or identifiers of the third reconstructed surface to the computing node.

[0235] Furthermore, in the next determination of whether there is an over-segmentation problem, the third reconstruction surface can be used as the first reconstruction surface or the second reconstruction surface, and the reconstruction surface closer to the third reconstruction surface among the remaining (N-2) reconstruction surfaces can be used as the second reconstruction surface or the first reconstruction surface. The above two reconstruction surfaces are used as a pair, and steps 640, 660 and 670 are executed again.

[0236] This process continues in this way until any two of the reconstructed surfaces form a pair of reconstructed surfaces. The sensing node can then repeat step 640, judging each pair of reconstructed surfaces based on the judgment criterion. If no pair of reconstructed surfaces satisfies the judgment criterion, the process stops, and it can be determined that the two or more reconstructed surfaces obtained through processing do not suffer from over-segmentation.

[0237] Based on the above technical solution, the perception node judges the first reconstructed surface and the second reconstructed surface obtained after processing the point cloud obtained through perception based on the judgment criteria, and by comparing the angle difference and / or distance difference between the first reconstructed surface and the second reconstructed surface with the first threshold and / or the second threshold respectively, it can be determined whether the first reconstructed surface and the second reconstructed surface are the same surface. Furthermore, the first reconstructed surface and the second reconstructed surface can be reconstructed surfaces obtained after processing the point cloud obtained through perception, or they can be the main surface on the scatterer obtained after processing the point cloud obtained through perception. After the perception node judges the reconstructed surface obtained after processing the point cloud obtained through perception based on the judgment criteria, it can effectively solve the over-segmentation problem caused by the characteristics of electromagnetic waves and the segmentation algorithm itself, improve the accuracy of environmental reconstruction, and improve the accuracy of perception.

[0238] The method provided by the embodiment of the present application is described in detail above with reference to a plurality of drawings. The device provided by the embodiment of the present application is described below with reference to the drawings.

[0239] Figures 8 to 11 are schematic diagrams of possible devices provided by embodiments of the present application. These devices can be used to implement the functions of the sensing nodes in the above method embodiments, and thus can also achieve the beneficial effects of the above method embodiments.

[0240] FIG8 is a schematic block diagram of a data processing device according to an embodiment of the present application. As shown in FIG8 , the device 800 includes a transceiver module 810 and a processing module 820 .

[0241] One possible design is that the apparatus 800 is used to implement the functions of the sensing node in the method embodiment shown in Figure 6. For example, the apparatus 800 may correspond to the sensing node in Figure 6.

[0242] Exemplarily, the processing module 820 is used to determine whether the first reconstructed surface and the second reconstructed surface are the same surface based on a judgment criterion, and the first reconstructed surface and the second reconstructed surface are obtained by processing the point cloud perceived by the perception node, and the judgment criterion includes one or more of the following: the angle difference between the first reconstructed surface and the second reconstructed surface is less than a first threshold, or the distance difference between the first reconstructed surface and the second reconstructed surface is less than a second threshold. Optionally, the processing module 820 is also used to obtain a third reconstructed surface based on the first reconstructed surface and the second reconstructed surface when the first reconstructed surface and the second reconstructed surface are the same surface. Optionally, the device 800 also includes a transceiver module 810, which can be used to send first information to the computing node, and the first information is used to indicate the perception data of the target object, and the target object includes the third reconstructed surface.

[0243] Optionally, the perception data of the target object includes location information of the target object.

[0244] Optionally, the first information is also used to indicate the identification of the target object.

[0245] Optionally, the transceiver module 810 is further configured to receive second information from a computing node, where the second information is used to determine the determination criterion.

[0246] Optionally, the second information is used to indicate the first threshold and / or the second threshold. Optionally, the second information is used to indicate the beam width of the detection signal transmitted by the sensing node, the incident angle of the detection signal, and one or more of the following: the distance between the sensing node and the obstacle, the first constant or the second constant, the first coefficient or the second coefficient, the beam width, the incident angle, the first constant and the first coefficient are used to determine the first threshold, and the beam width, the incident angle, the distance between the sensing node and the obstacle, the second constant and the second coefficient are used to determine the second threshold.

[0247] Optionally, the first threshold s satisfies:

[0248] The θ represents the beam width of the detection signal emitted by the sensing node, the β represents the incident angle of the detection signal, and the incident angle is used to indicate the angle between the incident direction of the detection signal emitted by the sensing node and the obstacle, the ε1 is the first constant, and the k1 is the first coefficient.

[0249] Optionally, the second threshold d satisfies:

[0250] The r represents the distance between the sensing node and the obstacle, the θ represents the beam width of the detection signal emitted by the sensing node, the β represents the incident angle of the detection signal, the ε2 is the second constant, and the k2 is the second coefficient.

[0251] A more detailed description of the transceiver module 810 and the processing module 820 can be directly obtained by referring to the relevant description in the embodiment shown in FIG6 , and will not be repeated here.

[0252] It should be noted that the device 800 may include a sending module or a receiving module, depending on whether the device 800 performs the sending action and the receiving action in the above solution. It is understandable that since the device 800 has a communication function, it can also be called a communication device.

[0253] Another possible design is that the device 800 is used to implement the functions of the computing node in the method embodiment shown in Figure 6. For example, the device 800 may correspond to the computing node in Figure 6.

[0254] Exemplarily, the processing module 820 is configured to generate second information, which is used to determine a determination criterion for determining whether two reconstructed surfaces are the same surface, the two reconstructed surfaces being obtained by processing the point cloud perceived by the sensing node. Optionally, the apparatus 800 further includes a transceiver module 810, which is configured to transmit the second information to the sensing node.

[0255] Optionally, the second information is used to indicate the first threshold and / or the second threshold.

[0256] Optionally, the second information is used to indicate the beam width of the detection signal emitted by the sensing node, the incident angle of the detection signal, and one or more of the following: the distance between the sensing node and the obstacle, the first constant or the second constant, the first coefficient or the second coefficient; the beam width, the incident angle, the first constant and the first coefficient are used to determine the first threshold; the beam width, the incident angle, the distance between the sensing node and the obstacle, the second constant and the second coefficient are used to determine the second threshold.

[0257] Optionally, the first threshold s satisfies:

[0258] The θ represents the beam width of the detection signal emitted by the sensing node, the β represents the incident angle of the detection signal, and the incident angle is used to indicate the angle between the incident direction of the detection signal emitted by the sensing node and the obstacle, the ε1 is the first constant, and the k1 is the first coefficient.

[0259] Optionally, the second threshold d satisfies:

[0260] The r represents the distance between the sensing node and the obstacle, the θ represents the beam width of the detection signal emitted by the sensing node, the β represents the incident angle of the detection signal, the ε2 is the second constant, and the k2 is the second coefficient.

[0261] A more detailed description of the transceiver module 810 and the processing module 820 can be directly obtained by referring to the relevant description in the embodiment shown in FIG6 , and will not be repeated here.

[0262] It should be noted that the device 800 may include a sending module or a receiving module, depending on whether the device 800 performs the sending action and the receiving action in the above solution. It is understandable that since the device 800 has a communication function, it can also be called a communication device.

[0263] FIG9 is another schematic block diagram of a data processing device provided in an embodiment of the present application. As shown in FIG9 , device 900 includes one or more processors 910. The processor 910 may be a general-purpose processor or a dedicated processor. For example, it may be a baseband processor or a central processing unit. The baseband processor may be used to process communication protocols and communication data, and the central processing unit may be used to control a device (e.g., a terminal device, a network device, or a chip), execute software programs, and process data from the software programs.

[0264] Optionally, in one design, the processor 910 may include a program (also referred to as code or instructions), which may be executed on the processor 910 to cause the apparatus 900 to perform the method performed by the computing node or sensing node in the above method embodiments. In another possible design, the apparatus 900 includes circuitry (not shown in FIG. 9 ), which is configured to implement the functionality of the computing node or sensing node in the above method embodiments.

[0265] Exemplarily, the processor 910 may be configured to execute computer programs or instructions in the memory to implement the steps performed by the perception node or computing node in the method embodiment shown in the embodiment of FIG. 6 .

[0266] Optionally, the device 900 may include one or more memories 920 on which programs (sometimes also referred to as codes or instructions) are stored. The programs can be run on the processor 910, so that the device 900 executes the method performed by the perception node or computing node in the above embodiment.

[0267] Optionally, the processor 910 and / or the memory 920 may include an artificial intelligence (AI) module, which is used to implement AI-related functions. The AI ​​module may be implemented through software, hardware, or a combination of software and hardware. For example, the AI ​​module may include a wireless intelligent controller (RIC) module. For example, the AI ​​module may be a near real-time RIC or a non-real-time RIC.

[0268] Optionally, data may be stored in the processor 910 and / or the memory 920. The processor and memory may be provided separately or integrated together.

[0269] Optionally, the apparatus 900 may further include a communication interface 930. The processor 910 may also be sometimes referred to as a processing unit, which controls the apparatus (e.g., a RAN node or terminal). The communication interface 930 may also be sometimes referred to as a transceiver unit, a transceiver, a transceiver circuit, or a transceiver, etc., which is used to implement the transceiver function of the apparatus.

[0270] Optionally, the apparatus 900 further includes a communication interface 930. The processor 910 and the communication interface 930 are coupled to each other. It is understood that the communication interface 930 may be a transceiver or an input / output interface.

[0271] It can be understood that since the data processing device 900 has a communication function, it can also be called a communication device.

[0272] When the apparatus 900 is used to implement the method shown in FIG6 , the processor 910 is used to perform the functions of the processing unit described above, and the communication interface 930 is used to perform the functions of the transceiver module described above. Whether the communication interface 930 is used for sending or receiving can be determined by whether it is used to perform a sending action or a receiving action in the solution implemented by the apparatus 900.

[0273] When the device 900 is a chip, the chip can be used to implement the functions of the sensing node or computing node in the above method embodiment. The communication interface 930 can be an input and output circuit, wherein the input circuit can be used for receiving and the output interface can be used for sending.

[0274] When the chip is used to implement the function of the perception node in the above method embodiment, it can receive signals from other modules in the device to which it belongs (such as a radio frequency module or antenna), and the signal can be sent by the perception node to the computing node; or, the chip sends signals to other modules in the device to which it belongs (such as a radio frequency module or antenna), and the signal can be sent by the perception node to the computing node.

[0275] When the chip is used to implement the function of the computing node in the above method embodiment, it can receive signals from other modules in the device to which it belongs (such as a radio frequency module or antenna), and the signal can be sent by the perception node to the computing node; or, the chip sends signals to other modules in the device to which it belongs (such as a radio frequency module or antenna), and the signal can be sent by the computing node to the perception node.

[0276] When the apparatus 900 is a communication device, the communication device can be used to implement the functions of the sensing node or computing node in the above method embodiments. The communication interface 930 can be a transceiver, specifically including a transmitter and a receiver, wherein the transmitter is used to send signals and the receiver is used to receive signals.

[0277] Figure 10 is a schematic diagram of the structure of a terminal device provided in an embodiment of the present application. As shown in Figure 10, the terminal device 1000 can be applied to the system shown in Figure 2 to perform the function of the sensing node in the method embodiment shown in Figure 6. As shown in the figure, the terminal device 1000 includes a processor 1001 and a transceiver 1002. Optionally, the terminal device 1000 also includes a memory 1003. The processor 1001, the transceiver 1002 and the memory 1003 can communicate with each other through an internal connection path to transmit control and / or data signals. The memory 1003 is used to store computer programs, and the processor 1001 is used to call and run the computer program from the memory 1003 to control the transceiver 1002 to send and receive signals. Optionally, the terminal device 1000 may also include an antenna 1004 for transmitting the uplink data or uplink control signaling output by the transceiver 1002 via wireless signals.

[0278] The processor 1001 and the memory 1003 may be combined into a processing device, and the processor 1001 is configured to execute program code stored in the memory 1003 to implement the aforementioned functions. In a specific implementation, the memory 1003 may also be integrated into the processor 1001 or independent of the processor 1001. The processor 1001 may correspond to the processing module in FIG. 8 or the processor in FIG. 9 .

[0279] The transceiver 1002 may correspond to the transceiver module in FIG8 or the communication interface in FIG9 , and may also be referred to as a transceiver unit. The transceiver 1002 may include a receiver (or receiver, receiving circuit) and a transmitter (or transmitter, transmitting circuit). The receiver is used to receive signals, and the transmitter is used to transmit signals.

[0280] It should be understood that the terminal device 1000 shown in Figure 10 is capable of implementing the various processes involving the sensing node in the method embodiment shown in Figure 6. The operations and / or functions of the various modules in the terminal device 1000 are respectively for implementing the corresponding processes in the above method embodiment. For details, please refer to the description of the above method embodiment. To avoid repetition, detailed description is omitted here.

[0281] The processor 1001 can be used to execute the actions implemented within the sensing node described in the previous method embodiments, while the transceiver 1002 can be used to execute the actions of the sensing node sending to or receiving from the computing node described in the previous method embodiments. For details, please refer to the description of the previous method embodiments and will not be repeated here.

[0282] Optionally, the terminal device 1000 may further include a power supply 1005 for providing power to various devices or circuits in the sensing node.

[0283] In addition, in order to make the functions of the perception node more complete, the terminal device 1000 can also include one or more of an input unit 1006, a display unit 1007, an audio circuit 1008, a camera 1009 and a sensor 1010, and the audio circuit can also include a speaker 1008a, a microphone 1008b, etc.

[0284] Figure 11 is a schematic diagram of the structure of a network device provided in an embodiment of the present application, for example, a base station. Base station 1100 can be used in the system shown in Figure 2 to perform the functions of a computing node in the method embodiment shown in Figure 6 . As shown, base station 1100 may include one or more of the following: one or more (DU+RU) units 1110 and one or more CUs 1120. CU 1120 can communicate with a next-generation core (NG core). The DU may include at least one antenna 1111, at least one radio frequency unit 1112, at least one processor 1113, and at least one memory 1114. The DU portion is primarily used for transmitting and receiving radio frequency signals, converting radio frequency signals into baseband signals, and performing partial baseband processing. CU 1120 may include at least one processor 1122 and at least one memory 1121. CU 1120 and the DU may communicate via an interface. The control plane (CP) interface may be an Fs-C, such as F1-C, and the user plane (UP) interface may be an Fs-U, such as F1-U. The DU and RU can work together to implement the functions of the physical (PHY) layer. A DU can be connected to one or more RUs. The functions of the DU and RU can be configured in various ways according to the design. For example, the DU is configured to implement the baseband function, and the RU is configured to implement the mid-RF function. For another example, the DU is configured to implement the high-layer functions in the PHY layer, and the RU is configured to implement the low-layer functions and RF functions in the PHY layer. The high-layer functions in the PHY layer may include a part of the functions of the PHY layer, which is closer to the MAC layer, and the low-layer functions in the PHY layer may include another part of the functions of the PHY layer, which is closer to the mid-RF side.

[0285] The CU 1120 is primarily used for baseband processing and base station control. The DU and CU 1120 may be physically located together or physically separated, i.e., a distributed base station. The CU 1120 is the control center of the base station and may correspond to the processing module in FIG8 or the processor in FIG9 , and may also be referred to as a processing unit, primarily for performing baseband processing functions. For example, the CU 1120 may be used to control the base station to execute the operational procedures for the access network device in the above-described method embodiment.

[0286] Specifically, baseband processing on the CU and DU can be divided according to the protocol layers of the wireless network. For example, the functions of the packet data convergence protocol (PDCP) layer and above are set in the CU, while the functions of the protocol layers below PDCP, such as the RLC layer and the MAC layer, are set in the DU. For another example, the CU implements the functions of the RRC layer and the PDCP layer, while the DU implements the functions of the RLC layer, the MAC layer, and the PHY layer.

[0287] In addition, optionally, the base station 1100 may include one or more radio frequency units (RUs), one or more DUs, and one or more CUs. The DU may include at least one processor 1113 and at least one memory 1114, the RU may include at least one antenna 1111 and at least one radio frequency unit 1112, and the CU may include at least one processor 1122 and at least one memory 1121.

[0288] In one example, the CU 1120 may be composed of one or more single boards, and the multiple single boards may jointly support a wireless access network with a single access indication (such as a 5G network), or may respectively support wireless access networks with different access standards (such as an LTE network, a 5G network, or other networks). The memory 1121 and the processor 1122 may serve one or more single boards. That is, a memory and a processor may be separately set on each single board. It is also possible that multiple single boards share the same memory and processor. In addition, necessary circuits may be provided on each single board. The DU may be composed of one or more single boards, and the multiple single boards may jointly support a wireless access network with a single access indication (such as a 5G network), or may respectively support wireless access networks with different access standards (such as an LTE network, a 5G network, or other networks). The memory 1114 and the processor 1113 may serve one or more single boards. That is, a memory and a processor may be separately set on each single board. It is also possible that multiple single boards share the same memory and processor. In addition, necessary circuits may be provided on each single board.

[0289] It should be understood that base station 1100 shown in Figure 11 is capable of implementing the various processes involving computing nodes or sensing nodes in the method embodiment shown in Figure 6 . The operations and / or functions of the various modules in base station 1100 are respectively for implementing the corresponding processes in the aforementioned method embodiment. For details, please refer to the description of the aforementioned method embodiment; to avoid repetition, detailed descriptions are omitted here.

[0290] It should be understood that the base station 1100 shown in FIG11 is only one possible architecture of a network device and does not constitute any limitation to this application. The method provided in this application is applicable to network devices of other architectures. For example, network devices including CU, DU, and AAU. This application does not limit the specific architecture of the network device.

[0291] It should be understood that FIG11 is merely an example and not a limitation, and the network device may not rely on the structure shown in FIG11. For example, the network device may include an AAU, a CU, and / or a DU, or a BBU and an adaptive radio unit (ARU). This application is not limited to this.

[0292] The CU and / or DU described above can be used to perform the actions implemented within the computing node described in the previous method embodiments, while the AAU can be used to perform the actions described in the previous method embodiments where the computing node sends information to or receives information from the sensing node. For details, please refer to the description in the previous method embodiments and will not be repeated here.

[0293] Alternatively, the CU and / or DU described above can be used to perform the actions implemented internally by the perception node described in the previous method embodiments, while the AAU can be used to perform the actions described in the previous method embodiments where the perception node sends data to or receives data from the computing node. For details, please refer to the description in the previous method embodiments and will not be repeated here.

[0294] It should be noted that the above method embodiments can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiments can be completed by hardware integrated logic circuits in the processor or by software instructions.

[0295] The processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0296] The steps of the method disclosed in the embodiments of this application can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.

[0297] The memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0298] The present application also provides a chip system, which includes at least one processor for supporting the implementation of the functions of the perception node or the computing node involved in any one of the above method embodiments, for example, sending, receiving or processing the data and / or information involved in the above method.

[0299] In one possible design, the chip system further includes a memory, which is used to store program instructions and data, and the memory is located inside or outside the processor.

[0300] The chip system can be composed of chips, or can include chips and other discrete devices.

[0301] The present application also provides a computer program product, which includes: a computer program (also referred to as code, or instructions). When the computer program is run, the method executed by the perception node in the embodiment shown in Figure 6 is executed, or the method executed by the computing node is executed.

[0302] The present application also provides a computer-readable storage medium storing a computer program (also referred to as code or instructions). When the computer program is executed, the method executed by the sensing node in the embodiment shown in FIG6 is executed, or the method executed by the computing node is executed.

[0303] The present application also provides a communication system, which includes the aforementioned sensing node and computing node.

[0304] The methods provided in the above embodiments can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, they can be implemented in whole or in part in the form of a computer program product. The computer program product may include one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic disk), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0305] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0306] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0307] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0308] 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 may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0309] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0310] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk, or an optical disk.

Claims

1. A data processing method, characterized in that: Applied to a sensing node, the method comprises: Determining whether a first reconstructed surface and a second reconstructed surface are the same surface based on a determination criterion, wherein the first reconstructed surface and the second reconstructed surface are obtained by processing the point cloud sensed by the sensing node, and the determination criterion includes one or more of the following: an angle difference between the first reconstructed surface and the second reconstructed surface is less than a first threshold, or a distance difference between the first reconstructed surface and the second reconstructed surface is less than a second threshold; When the first reconstructed surface and the second reconstructed surface are the same surface, obtaining a third reconstructed surface based on the first reconstructed surface and the second reconstructed surface; First information is sent to a computing node, where the first information is used to indicate perception data of a target object, where the target object includes the third reconstructed surface.

2. The method according to claim 1, characterized in that The sensing data of the target object includes location information of the target object.

3. The method according to claim 1 or 2, characterized in that The first information is also used to indicate the identity of the target object.

4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: Second information is received from a computing node, where the second information is used to determine the decision criterion.

5. The method according to claim 4, characterized in that The second information is used to indicate the first threshold and / or the second threshold.

6. The method according to claim 4, characterized in that The second information is used to indicate the beam width of the detection signal emitted by the sensing node, the incident angle of the detection signal, and one or more of the following: the distance between the sensing node and the obstacle, the first constant or the second constant, the first coefficient or the second coefficient; the beam width, the incident angle, the first constant and the first coefficient are used to determine the first threshold; the beam width, the incident angle, the distance between the sensing node and the obstacle, the second constant and the second coefficient are used to determine the second threshold.

7. The method according to any one of claims 1 to 6, characterized in that The first threshold s satisfies: The θ represents the beam width of the detection signal emitted by the sensing node, the β represents the incident angle of the detection signal, and the incident angle is used to indicate the angle between the incident direction of the detection signal emitted by the sensing node and the obstacle, the ε1 is the first constant, and the k1 is the first coefficient.

8. The method according to any one of claims 1 to 6, characterized in that The second threshold d satisfies: The r represents the distance between the sensing node and the obstacle, the θ represents the beam width of the detection signal emitted by the sensing node, the β represents the incident angle of the detection signal, the ε2 is the second constant, and the k2 is the second coefficient.

9. A data processing method, characterized in that: Applied to a computing node, the method comprises: generating second information, the second information being used to determine a determination criterion, the determination criterion being used to determine whether two reconstructed surfaces are the same surface, the two reconstructed surfaces being obtained by processing the point cloud sensed by the sensing node; Send the second information to the sensing node.

10. The method according to claim 9, characterized in that The second information is used to indicate the first threshold and / or the second threshold.

11. The method according to claim 9, characterized in that The second information is used to indicate the beam width of the detection signal emitted by the sensing node, the incident angle of the detection signal, and one or more of the following: the distance between the sensing node and the obstacle, the first constant or the second constant, the first coefficient or the second coefficient; the beam width, the incident angle, the first constant and the first coefficient are used to determine the first threshold; the beam width, the incident angle, the distance between the sensing node and the obstacle, the second constant and the second coefficient are used to determine the second threshold.

12. The method according to any one of claims 9 to 11, characterized in that The first threshold s satisfies: The θ represents the beam width of the detection signal emitted by the sensing node, the β represents the incident angle of the detection signal, and the incident angle is used to indicate the angle between the incident direction of the detection signal emitted by the sensing node and the obstacle, the ε1 is the first constant, and the k1 is the first coefficient.

13. The method according to any one of claims 9 to 11, characterized in that The second threshold d satisfies: The r represents the distance between the sensing node and the obstacle, the θ represents the beam width of the detection signal emitted by the sensing node, the β represents the incident angle of the detection signal, the ε2 is the second constant, and the k2 is the second coefficient.

14. A data processing device, characterized in that: The method comprises a module for executing the method according to any one of claims 1 to 8, or the method comprises a module for executing the method according to any one of claims 9 to 13.

15. A data processing device, characterized in that: comprising a processor and a memory, wherein: The memory is used to store computer programs; The processor is configured to call the computer program so that the method according to any one of claims 1 to 8 is executed, or the method according to any one of claims 9 to 13 is executed.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is executed, or the method according to any one of claims 9 to 13 is executed.

17. A computer program product, characterized in that The invention comprises a computer program, which, when being executed, causes the method according to any one of claims 1 to 8 to be performed, or causes the method according to any one of claims 9 to 13 to be performed.

Images