Point cloud data processing method, device, program product, medium and home appliance

Abstract

The application discloses a point cloud data processing method, device, program product, medium and household appliance. The method comprises the following steps: acquiring current point cloud data of a target object in a target environment collected by a point cloud data collection device in a current period, wherein the point cloud data collection device is installed at a set position in the target environment; acquiring historical point cloud data of the target object collected by the point cloud data collection device in a historical period; and determining whether the posture of the point cloud data collection device changes based on the current point cloud data and the historical point cloud data. The technical scheme provided by the application can improve the detection efficiency of the posture of the point cloud data collection device.

Description

Technical Field

[0001] This application belongs to the field of point cloud data processing technology, and particularly relates to a point cloud data processing method, apparatus, program product, medium and household appliance. Background Technology

[0002] In modern homes, to enhance user experience, home appliances (such as air conditioners and smart fans) are typically equipped with devices for identifying user location, such as radar sensors and Time-of-Flight (TOF) sensors. These devices analyze point cloud data of objects in the target environment (such as inside a room) to identify the user's location, thereby enabling precise services, such as preventing air conditioner air from blowing directly on the user. However, because point cloud data acquisition devices are often suspended, their posture may deform due to gravity, making it difficult to accurately identify the position of objects in the target environment. Current technologies typically require professionals to manually detect these posture changes, but this process is inefficient and inconvenient. Therefore, improving the efficiency of posture detection for point cloud data acquisition devices has become a pressing technical problem. Summary of the Invention

[0003] Embodiments of this application provide a point cloud data processing method, apparatus, computer program product, computer-readable storage medium, and home appliance, which can at least to some extent improve the attitude detection efficiency of the point cloud data acquisition device.

[0004] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0005] According to a first aspect of the embodiments of this application, a point cloud data processing method is provided, the method comprising: acquiring current point cloud data of a target object in a target environment collected by a point cloud data acquisition device in a current period, the point cloud data acquisition device being installed at a set position in the target environment; acquiring historical point cloud data of the target object collected by the point cloud data acquisition device in a historical period; and determining whether the attitude of the point cloud data acquisition device has changed based on the current point cloud data and the historical point cloud data.

[0006] In some embodiments of this application, based on the aforementioned scheme, the target object is an object moving along a fixed path in the target environment. Determining whether the attitude of the point cloud data acquisition device has changed based on the current point cloud data and the historical point cloud data includes: determining the current point cloud distribution characteristics of the target object during its movement in the target environment based on the current point cloud data; determining the historical point cloud distribution characteristics of the target object during its movement in the target environment based on the historical point cloud data; and determining whether the attitude of the point cloud data acquisition device has changed based on the current point cloud distribution characteristics and the historical point cloud distribution characteristics.

[0007] In some embodiments of this application, based on the foregoing scheme, determining whether the attitude of the point cloud data acquisition device has changed according to the current point cloud distribution characteristics and the historical point cloud distribution characteristics includes: determining a current point cloud trajectory segment that meets a first preset condition based on the current point cloud distribution characteristics, and determining the current trajectory direction angle of the current point cloud trajectory segment; determining a historical point cloud trajectory segment that meets the first preset condition based on the historical point cloud distribution characteristics, and determining the historical trajectory direction angle of the historical point cloud trajectory segment; and determining whether the attitude of the point cloud data acquisition device has changed according to the current trajectory direction angle and the historical trajectory direction angle.

[0008] In some embodiments of this application, based on the aforementioned scheme, determining the current point cloud trajectory segment that satisfies the first preset condition based on the current point cloud distribution characteristics includes: determining the velocity direction angle of each point cloud based on the current point cloud distribution characteristics; grouping the point clouds based on the velocity direction angle to obtain multiple point cloud groups, wherein the difference between the maximum and minimum velocity direction angles of the point clouds in the same point cloud group is less than a preset difference; clustering the point clouds in each point cloud group according to the clustering condition that the distance between adjacent point clouds is less than a preset distance to obtain multiple point cloud sets; connecting adjacent point clouds in each point cloud set to obtain the point cloud trajectory segment corresponding to each point cloud set; determining the target point cloud trajectory segment in each point cloud group whose length is greater than a preset length, and determining the point cloud group with the most target point cloud trajectory segments as the target point cloud group; and determining the target point cloud trajectory segment in the target point cloud group as the current point cloud trajectory segment that satisfies the first preset condition.

[0009] In some embodiments of this application, based on the foregoing scheme, determining the current trajectory direction angle of the current point cloud trajectory segment includes: determining the average value of the trajectory direction angles of each current point cloud trajectory segment as the current trajectory direction angle of the current point cloud trajectory segment; or, determining the average value of the velocity direction angles of each point cloud in each current point cloud trajectory segment as the current trajectory direction angle of the current point cloud trajectory segment.

[0010] In some embodiments of this application, based on the foregoing scheme, determining whether the attitude of the point cloud data acquisition device has changed according to the current trajectory direction angle and the historical trajectory direction angle includes: if the deviation between the current trajectory direction angle and the historical trajectory direction angle meets a second preset condition, then it is determined that the attitude of the point cloud data acquisition device has changed.

[0011] In some embodiments of this application, based on the foregoing scheme, after determining that the attitude of the point cloud data acquisition device has changed, the method further includes: correcting the point cloud data of each object in the target environment acquired by the point cloud data acquisition device in the current period based on the deviation between the current trajectory direction angle and the historical trajectory direction angle.

[0012] In some embodiments of this application, based on the foregoing scheme, determining whether the attitude of the point cloud data acquisition device has changed according to the current point cloud distribution characteristics and the historical point cloud distribution characteristics includes: connecting each group of adjacent point clouds based on the current point cloud distribution characteristics to obtain the current point cloud trajectory; connecting each group of adjacent point clouds based on the historical point cloud distribution characteristics to obtain the historical point cloud trajectory; and determining whether the attitude of the point cloud data acquisition device has changed according to the current point cloud trajectory and the historical point cloud trajectory.

[0013] In some embodiments of this application, based on the foregoing scheme, determining whether the attitude of the point cloud data acquisition device has changed according to the current point cloud distribution characteristics and the historical point cloud distribution characteristics includes: determining the current point cloud distribution contour based on the current point cloud distribution characteristics; determining the historical point cloud distribution contour based on the historical point cloud distribution characteristics; and determining whether the attitude of the point cloud data acquisition device has changed according to the geometric features of the current point cloud distribution contour and the geometric features of the historical point cloud distribution contour.

[0014] In some embodiments of this application, based on the aforementioned scheme, the target object is an object fixed in the target environment. Determining whether the attitude of the point cloud data acquisition device has changed based on the current point cloud data and the historical point cloud data includes: determining the current point cloud distribution pattern and the historical point cloud distribution pattern of the target object based on the current point cloud data and the historical point cloud data, respectively; and determining whether the attitude of the point cloud data acquisition device has changed based on the current point cloud distribution pattern and the historical point cloud distribution pattern.

[0015] In some embodiments of this application, based on the aforementioned scheme, the target object is a robotic vacuum cleaner.

[0016] In some embodiments of this application, based on the foregoing scheme, the point cloud data acquisition device is a multiple-transmitter, multiple-receiver radar.

[0017] According to a second aspect of the embodiments of this application, a point cloud data processing apparatus is provided, the apparatus comprising: a first acquisition unit, configured to acquire current point cloud data of a target object in a target environment collected by a point cloud data acquisition device in a current period, the point cloud data acquisition device being installed at a predetermined position in the target environment; a second acquisition unit, configured to acquire historical point cloud data of the target object collected by the point cloud data acquisition device in a historical period; and a determination unit, configured to determine whether the attitude of the point cloud data acquisition device has changed based on the current point cloud data and the historical point cloud data.

[0018] According to a third aspect of the embodiments of this application, a computer program product is provided, the computer program product including computer instructions stored in a computer-readable storage medium and adapted to be read and executed by a processor to cause a computer device having the processor to perform an operation as described in any of the first aspects above.

[0019] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided, the computer-readable storage medium storing at least one computer program instruction, the at least one computer program instruction being loaded and executed by a processor to perform the operation as described in any of the first aspects above.

[0020] According to a fifth aspect of the embodiments of this application, a home appliance is provided, the home appliance including one or more processors and one or more memories, the one or more memories storing at least one computer program instruction, the at least one computer program instruction being loaded and executed by the one or more processors to perform the operation as described in any of the first aspects above.

[0021] Based on the technical solution proposed in this application, the current point cloud data and historical point cloud data of the target object in the target environment can be acquired, and the attitude of the point cloud data acquisition device can be quickly identified by comparing the current point cloud data and historical point cloud data. Specifically, since the point cloud data of the target object acquired by the point cloud data acquisition device under different attitudes will be different, historical point cloud data can be used as a reference. By analyzing the changes between the current point cloud data and historical point cloud data, the amount of computation can be effectively reduced, making the attitude change detection response faster, thereby quickly determining the attitude change of the point cloud data acquisition device. Based on this, the technical solution proposed in this application automates the attitude detection process of the point cloud data acquisition device, reduces the need for manual intervention, avoids manual detection, and reduces the possibility of errors in manual detection, thereby improving the efficiency and accuracy of attitude detection of the acquisition device.

[0022] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0023] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0024] Figure 1 The following diagram illustrates an application scenario of the point cloud data processing method in this application embodiment;

[0025] Figure 2 A flowchart of a point cloud data processing method in an embodiment of this application is shown;

[0026] Figure 3 The following diagram illustrates an application scenario of the point cloud data processing method in this application embodiment;

[0027] Figure 4 The point cloud distribution feature map of the sweeping robot in the embodiment of this application is shown.

[0028] Figure 5 A comparison diagram of the current point cloud and historical point cloud of the sweeping robot in the embodiments of this application is shown;

[0029] Figure 6 A block diagram of a point cloud data processing apparatus according to an embodiment of this application is shown;

[0030] Figure 7A schematic diagram of the structure of a household appliance in an embodiment of this application is shown. Detailed Implementation

[0031] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0032] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0033] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices. It should also be noted that, for the sake of simplicity, certain components in the drawings that do not affect the interpretation of the technical solution of this application have been appropriately omitted.

[0034] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0035] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "multiple" means two or more.

[0036] To enable those skilled in the art to better understand this application, firstly, in conjunction with Figure 1A brief description of the application scenarios involved in this application is provided. It should be noted that the accompanying drawings are merely to assist those skilled in the art in better understanding this application, and the structural features of the various components illustrated in the drawings are only exemplary. Furthermore, to ensure the simplicity of the drawings, certain components that do not affect the explanation of the technical solution of this application have been appropriately omitted.

[0037] See Figure 1 The diagram illustrates an application scenario of the point cloud data processing method in this embodiment.

[0038] like Figure 1 As shown, a target environment 100 (e.g., a room) can be equipped with home appliances 102 (e.g., air conditioners, smart fans, etc.). These appliances 102 can be configured with point cloud data acquisition devices 101 (e.g., radar sensors, TOF sensors, etc.). The point cloud data acquisition device 101 is used to collect point cloud data of objects in the target environment 100, and to identify the location of the user 103 within the target environment 100 by analyzing this point cloud data. In one scenario, if the air conditioner 100 is operating in cooling mode, it can adjust the airflow direction of its vents based on the identified location of the user 103, preventing the cold air from blowing directly onto the user 103. This significantly improves the intelligence of the air conditioner during operation, thereby enhancing the user experience.

[0039] However, since the point cloud data acquisition device 101 is suspended for extended periods, its posture may deform due to gravity. When the point cloud data acquisition device 101 is deformed, the point cloud data it acquires will contain errors, resulting in the inability to correctly identify the position of the user 103 within the target environment 100. To address this, existing technologies typically require professionals to manually check for changes in the posture of the point cloud data acquisition device 103. If a change is found, the device is adjusted. The drawback of existing solutions is their low efficiency and lack of convenience. Therefore, this application proposes a point cloud data processing method to improve the efficiency of posture detection for the point cloud data acquisition device.

[0040] Next, this application will combine Figure 2 The proposed point cloud data processing solution is described in detail.

[0041] See Figure 2 The flowchart of a point cloud data processing method according to an embodiment of this application is shown. This point cloud data processing method can be executed by a device with computing capabilities, and includes at least steps 210 to 230, detailed below:

[0042] In step 210, the current point cloud data of the target object in the target environment is acquired by the point cloud data acquisition device in the current period, wherein the point cloud data acquisition device is installed at a set position in the target environment.

[0043] In this application, the target object may be an object that moves along a fixed path in the target environment.

[0044] To enable those skilled in the art to better understand this application, the following is combined with Figure 3 The following is an example using a specific application scenario. See [link / reference] Figure 3 The diagram illustrates an application scenario of the point cloud data processing method in this embodiment.

[0045] like Figure 3 As shown in sub-figure (a), the target object can be object 301, specifically, for example, a robotic vacuum cleaner. It is understood that the robotic vacuum cleaner moves along a fixed cleaning path each time it performs a cleaning task in the room. While the target object 301 moves along this fixed path in the target environment, the point cloud data acquisition device 101 can collect the point cloud data of the target object.

[0046] In this application, it should be noted that point cloud data is a collection of three-dimensional coordinate points used to represent the shape and structure of an object or space. Each point cloud contains X, Y, and Z coordinates, and may also include color and intensity information. Point cloud data is widely used in 3D modeling, computer vision, autonomous driving, and robot navigation. It can be understood that the current point cloud data refers to the point cloud data D of the target object in the target environment collected by the point cloud data acquisition device in the current period. t .

[0047] In this application, it should be noted that the point cloud data acquisition device can be a radar sensor, laser scanner, depth camera, TOF sensor, or other similar devices. In a specific embodiment, the point cloud data acquisition device can be a Multiple-Input Multiple-Output Radar (MIMO Radar), which utilizes multiple transmitting antennas and multiple receiving antennas to transmit and receive signals. Compared to traditional radar, MIMO radar can simultaneously transmit multiple waveforms and receive signals through multiple channels, thereby achieving higher spatial resolution and target detection capabilities.

[0048] In this application, the target object may also be an object fixed in the target environment.

[0049] To enable those skilled in the art to better understand this application, the following will continue to combine... Figure 3 The following is an example of a specific application scenario.

[0050] like Figure 3 As shown in sub-figure (b), the target object can be object 302. Specifically, object 302 can be a television set mounted on a wall, a dining table placed in a restaurant, or a refrigerator placed in a corner. It is understood that any object fixedly placed in the target environment can be used as the target object, and this application does not make any specific limitation in this regard.

[0051] Continue to refer to Figure 2 In step 220, historical point cloud data of the target object collected by the point cloud data acquisition device in historical periods is obtained.

[0052] In this application, historical point cloud data refers to the point cloud data of target objects in the target environment collected by the point cloud data acquisition device over historical periods. For example, using... Figure 3 Taking the scenario shown in neutron diagram (a) as an example, after the point cloud data acquisition device 101 is initially installed and calibrated, each time the point cloud data acquisition device 101 acquires point cloud data of the target object 301 during its movement, it can be considered as a period of point cloud data acquisition. It can be understood that, up to the present, the point cloud data acquired by the point cloud data acquisition device in each period are D1, D2, D3, ..., D... t-2 D t-1 D t .

[0053] In this application, the current point cloud data can be D t The historical point cloud data can be D1, D2, or D1, D2, D3, ..., D t-2 D t-1 It is understood that the range of the historical point cloud data can be limited according to actual needs, and this application does not make any specific limitations in this regard.

[0054] Continue to refer to Figure 2 In step 230, based on the current point cloud data and the historical point cloud data, it is determined whether the attitude of the point cloud data acquisition device has changed.

[0055] In this application, the current and historical point cloud data of a target object in the target environment can be acquired, and the pose of the point cloud data acquisition device can be quickly identified by comparing the current and historical point cloud data. Specifically, since the point cloud data of the target object acquired by the point cloud data acquisition device under different poses will differ, historical point cloud data can be used as a reference. By analyzing the changes between the current and historical point cloud data, the computational load can be effectively reduced, making the pose change detection response faster, thereby quickly determining the pose change of the point cloud data acquisition device. Based on this, the technical solution proposed in this application automates the pose detection process of the point cloud data acquisition device, reduces the need for manual intervention, avoids manual detection, and reduces the possibility of errors in manual detection, thereby improving the efficiency and accuracy of pose detection of the acquisition device.

[0056] Furthermore, in the application scenarios of home appliances, the technical solution proposed in this application can be used to detect whether there is a change in the attitude of the point cloud data acquisition device in the home appliance. For example, for air conditioning equipment, the radar sensor configured in the air conditioner can collect point cloud data of a robot vacuum cleaner moving along a fixed cleaning path in the room. Since the cleaning path of the robot vacuum cleaner is fixed, the point cloud data of the robot vacuum cleaner will not show significant differences in different cycles if the attitude of the radar sensor does not change. Therefore, by comparing the degree of difference between the point cloud data of the robot vacuum cleaner during its movement in historical cycles and the point cloud data of the robot vacuum cleaner during its movement in the current cycle, it is possible to accurately and efficiently determine whether there is a change in the attitude of the radar sensor configured in the air conditioning equipment.

[0057] Next, this application will address two scenarios: the target object is an object moving along a fixed path in the target environment, and the target object is an object fixed in the target environment. Figure 2 Step 230 is explained in detail.

[0058] In this application, when the target object is an object moving along a fixed path in the target environment, such as Figure 2 Step 230, as shown, involves determining whether the pose of the point cloud data acquisition device has changed based on the current point cloud data and the historical point cloud data. This can be performed according to steps 231 to 233 as follows:

[0059] Step 231: Based on the current point cloud data, determine the current point cloud distribution characteristics of the target object during its movement in the target environment.

[0060] Step 232: Based on the historical point cloud data, determine the historical point cloud distribution characteristics of the target object during its movement in the target environment.

[0061] Step 233: Determine whether the attitude of the point cloud data acquisition device has changed based on the current point cloud distribution characteristics and the historical point cloud distribution characteristics.

[0062] In this application, point cloud distribution features can be the arrangement and density features of point cloud data, which can describe the shape, size, and surface properties of an object. Point cloud distribution features are typically extracted by analyzing the distance between point clouds, the direction of the normal vector, and the density of the points. This information can be used for object identification, classification, and reconstruction. In this application, during the entire process of a target object moving along a fixed path in a target environment (e.g., a robotic vacuum cleaner performing a cleaning task along a fixed path), the point cloud data acquisition device can identify the target object and collect point cloud data of the target object as it moves to various positions. This allows the point cloud distribution features of the target object during its movement in the target environment to be determined based on the point cloud data of the target object at each position. See also... Figure 4 The diagram shows the point cloud distribution features of the sweeping robot in the embodiments of this application during its movement.

[0063] like Figure 4 As shown, taking a robotic vacuum cleaner as an example, the point cloud data received by the point cloud data acquisition device can be filtered. For example, a moving target object whose point cloud height is lower than a preset height (the preset height can be set according to actual needs, and this application does not make specific limitations on it) can be identified as a robotic vacuum cleaner, thereby obtaining the point cloud data 400 of the robotic vacuum cleaner during its movement in the target environment.

[0064] In one embodiment of step 233 above, determining whether the pose of the point cloud data acquisition device has changed based on the current point cloud distribution characteristics and the historical point cloud distribution characteristics can be performed according to the following steps 2331 to 2333:

[0065] Step 2331: Based on the current point cloud distribution characteristics, determine the current point cloud trajectory segment that meets the first preset condition, and determine the current trajectory direction angle of the current point cloud trajectory segment.

[0066] Step 2332: Based on the historical point cloud distribution characteristics, determine the historical point cloud trajectory segment that meets the first preset condition, and determine the historical trajectory direction angle of the historical point cloud trajectory segment.

[0067] Step 2333: Determine whether the attitude of the point cloud data acquisition device has changed based on the current trajectory direction angle and the historical trajectory direction angle.

[0068] In one embodiment of step 2331 above, determining the current point cloud trajectory segment that satisfies the first preset condition based on the current point cloud distribution characteristics can be performed according to the following steps 23311 to 23316:

[0069] Step 23311: Based on the current point cloud distribution characteristics, determine the velocity direction angle of each point cloud.

[0070] Step 23312: Based on the velocity direction angle, group the point clouds to obtain multiple point cloud groups, wherein the difference between the maximum and minimum velocity direction angles of the point clouds in the same point cloud group is less than a preset difference.

[0071] Step 23313: Cluster the point clouds in each point cloud group according to the clustering condition that the distance between adjacent point clouds is less than a preset distance, and obtain multiple point cloud sets.

[0072] Step 23314: Connect adjacent point clouds in each point cloud set to obtain the point cloud trajectory segment corresponding to each point cloud set.

[0073] Step 23315: Determine the target point cloud trajectory segments in each point cloud group whose length is greater than the preset length, and determine the point cloud group with the most target point cloud trajectory segments as the target point cloud group.

[0074] Step 23316: Determine the target point cloud trajectory segment in the target point cloud group as the current point cloud trajectory segment that satisfies the first preset condition.

[0075] To enable those skilled in the art to better understand this embodiment, the following will continue to refer to... Figure 3 The subgraph (a) in the diagram is illustrated using a specific application scenario example.

[0076] like Figure 3 As shown in sub-figure (a), during the current cycle, the sweeping robot 301 moves along a fixed cleaning path in the target environment. The point cloud data acquisition device 101 continuously collects point cloud data of the sweeping robot 301 during its movement. Based on the collected point cloud data, the current point cloud distribution characteristics of the sweeping robot 301 during its movement in the target environment can be determined. Furthermore, the velocity direction angle of each point cloud can be determined based on the current point cloud distribution characteristics. For example... Figure 3The velocity direction angles of point clouds A1, A2, B1, B2, B3, and B4 shown in subgraph (a) are (the velocity direction angle is the angle between the velocity direction of the robot vacuum cleaner 301 at a certain point cloud position and the reference direction set in the point cloud coordinate system. It can be understood that the velocity direction angle of a certain point cloud can be used to characterize the velocity direction of the robot vacuum cleaner 301 at that point cloud position).

[0077] After determining the velocity direction angle of each point cloud, the point clouds can be grouped. Specifically, point clouds with the same or similar velocity direction angles can be grouped together. For example... Figure 3 As shown in sub-figure (a), point clouds A1 and A2 can be divided into point cloud group A, and point clouds B1, B2, B3, and B4 can be divided into point cloud group B. In this way, the difference between the maximum velocity direction angle and the minimum velocity direction angle of the point clouds in the same point cloud group can be less than a preset difference (the preset difference can be set according to actual needs, and this application does not make specific limitations on it).

[0078] After obtaining multiple point cloud groups, the point clouds in each point cloud group can be clustered according to the clustering condition that the distance between adjacent point clouds is less than a preset distance (the preset distance can be set according to actual needs, and this application does not specifically limit it), thus obtaining multiple point cloud sets. For example Figure 3 As shown in subgraph (a) in point cloud group B, the distance between point cloud B2 and point cloud B3 is relatively small (less than a preset distance). Therefore, point clouds B2 and B3 can be grouped into a single point cloud set. For example... Figure 3 As shown in subgraph (a), in point cloud group B, the distance between point cloud B1 and point cloud B3 is relatively large (greater than or equal to the preset distance), so point cloud B1 and point cloud B3 cannot be divided into a point cloud set.

[0079] After obtaining multiple point cloud sets, adjacent point clouds in each set can be connected to obtain the point cloud trajectory segment corresponding to each point cloud set. For example... Figure 3 As shown in subgraph (a), connecting the various point clouds in the point cloud set containing point cloud B2 yields the point cloud trajectory segment L3 (i.e., the point cloud trajectory segment of point cloud group B), as shown in the figure. Figure 3 As shown in subgraph (a), the point cloud trajectory segment can also include point cloud trajectory segments L1 and L2 of point cloud group B, and L4 and L5 of point cloud group B.

[0080] Furthermore, after obtaining the point cloud trajectory segments corresponding to each point cloud set, the target point cloud trajectory segments in each point cloud group whose length is greater than a preset length (the preset length can be set according to actual needs, and this application does not specifically limit it) are identified, and the point cloud group with the most target point cloud trajectory segments is determined as the target point cloud group. For example Figure 3 As shown in subgraph (a), the point cloud trajectory segments L1, L2, L3 of point cloud group B, and for example... Figure 3 As shown in subgraph (a), the point cloud trajectory segments L4 and L5 of point cloud group A. It can be seen that, in... Figure 3 In subgraph (a), point cloud group B has the most target point cloud trajectory segments, so point cloud group B can be identified as the target point cloud group.

[0081] Finally, the target point cloud trajectory segment in the target point cloud group can be determined as the current point cloud trajectory segment that satisfies the first preset condition. For example... Figure 3 As shown in subgraph (a), the point cloud trajectory segments L1, L2, and L3 in point cloud group B can be determined as the current point cloud trajectory segments that satisfy the first preset condition.

[0082] In this embodiment, the advantage lies in the fact that by grouping and clustering the point cloud, the point cloud data can be effectively organized and simplified, facilitating subsequent point cloud data analysis and processing. Specifically, grouping by velocity direction angle can reduce the complexity of the point cloud data and improve the accuracy of point cloud recognition when the sweeping robot moves in the same direction. Distance-based clustering can effectively group related point clouds together, thus using the point cloud trajectory segment with the most target point cloud trajectory segments as the current point cloud trajectory segment used in subsequent data processing to determine whether the attitude of the point cloud data acquisition device has changed.

[0083] In another embodiment of step 2331 above, determining the current point cloud trajectory segment that satisfies the first preset condition based on the current point cloud distribution characteristics can also be based on the current point cloud distribution characteristics, fitting each point cloud to obtain a line segment whose curve length is greater than a preset length and whose curve curvature is less than a preset curvature (the preset curvature can be set according to actual needs, and this application does not specifically limit it), as the current point cloud trajectory segment that satisfies the first preset condition.

[0084] In this application, it will be understood by those skilled in the art that, in step 2332 above, determining the historical point cloud trajectory segment that meets the first preset condition based on the historical point cloud distribution characteristics can also be performed with reference to the technical logic in the above embodiments, and this application will not elaborate further on this.

[0085] In one embodiment of step 2331 above, determining the current trajectory direction angle of the current point cloud trajectory segment can be performed according to step 23317 or step 23318 as follows:

[0086] Step 23317: The average value of the trajectory direction angles of each current point cloud trajectory segment is determined as the current trajectory direction angle of the current point cloud trajectory segment.

[0087] In this step, the trajectory direction angle of the current point cloud trajectory segment can be the angle between the extension direction of the current point cloud trajectory segment and a reference direction set in the point cloud coordinate system. Specifically, for example... Figure 3 As shown in subgraph (a), the current point cloud trajectory segment includes point cloud trajectory segments L1, L2, and L3, and their corresponding trajectory direction angles are β1, β2, and β3. Then, the current trajectory direction angle of the current point cloud trajectory segment can be θt = (β1 + β2 + β3) / 3.

[0088] Step 23318: The average value of the velocity direction angle of each point cloud in each current point cloud trajectory segment is determined as the current trajectory direction angle of the current point cloud trajectory segment.

[0089] In this step, specifically, for example Figure 3 As shown in subgraph (a), the point cloud in the current point cloud trajectory segment includes point cloud B1, point cloud B2, point cloud B3, and point cloud B4, and their corresponding velocity direction angles are λ1, λ2, λ3, and λ4. Then, the current trajectory direction angle of the current point cloud trajectory segment can be θt = (λ1 + λ2 + λ3 + λ4) / 4.

[0090] In this application, it will be understood by those skilled in the art that the determination of the historical trajectory direction angle of the current point cloud trajectory segment in step 2332 above can also be performed with reference to the technical logic in step 23317 or step 23318 above, and this application will not elaborate on this further.

[0091] In one embodiment of step 2333 above, determining whether the attitude of the point cloud data acquisition device has changed based on the current trajectory direction angle and the historical trajectory direction angle can be performed according to the following step 23331:

[0092] Step 23331: If the deviation between the current trajectory direction angle and the historical trajectory direction angle meets the second preset condition, then it is determined that the attitude of the point cloud data acquisition device has changed.

[0093] Furthermore, after step 23331 above, that is, after determining that the attitude of the point cloud data acquisition device has changed, step 23332 can be executed as follows:

[0094] Step 23332: Based on the deviation between the current trajectory direction angle and the historical trajectory direction angle, the point cloud data of each object in the target environment collected by the point cloud data acquisition device in the current period is corrected.

[0095] Specifically, in one embodiment of this application, the historical trajectory direction angle can be the trajectory direction angle θ1 corresponding to the historical point cloud data D1 (i.e., the point cloud data of the target object in the target environment collected by the point cloud data acquisition device in the first historical cycle), and the current trajectory direction angle is the current point cloud data D1. t The corresponding trajectory direction angle θt.

[0096] In this embodiment, the deviation between the current trajectory direction angle and the historical trajectory direction angle can be △θ=|θt-θ1|.

[0097] In this embodiment, the deviation Δθ between the current trajectory direction angle and the historical trajectory direction angle can be directly judged. If Δθ is greater than or equal to a preset deviation value (the preset deviation value can be set according to actual needs, and this application does not specifically limit it), then the second preset condition is met, and it is determined that the attitude of the point cloud data acquisition device has changed.

[0098] To enable those skilled in the art to better understand this application, the following is combined with Figure 5 Please provide an explanation. See also... Figure 5 This image shows a comparison of the current point cloud and historical point cloud of the sweeping robot in an embodiment of this application. Figure 5 The difference between the trajectory direction angle corresponding to the current point cloud data 502 and the trajectory direction angle corresponding to the historical point cloud data 501 is shown as △θ.

[0099] In another embodiment of this application, the historical trajectory direction angle can be historical point cloud data D1, D2, D3, ..., D t-2 D t-1 The corresponding trajectory direction angles θ1, θ2, θ3, ..., θ t-2 θ t-1 Find the average trajectory direction angle (θ1+θ2+θ3+……+θ) t-2 +θ t-1 ) / t-1, where the current trajectory direction angle is the current point cloud data D t The corresponding trajectory direction angle θt.

[0100] In this embodiment, the deviation between the current trajectory direction angle and the historical trajectory direction angle can be Δθ = |θt - (θ1 + θ2 + θ3 + ... + θt) t-2 +θ t-1 ) / t-1|.

[0101] In this embodiment, the deviation Δθ between the current trajectory direction angle and the historical trajectory direction angle can be directly judged. If Δθ is greater than or equal to a preset deviation value, the second preset condition is met, and it is determined that the attitude of the point cloud data acquisition device has changed.

[0102] In this embodiment, it can also be to calculate historical point cloud data D1, D2, D3, ..., D t-2 D t-1 The corresponding trajectory direction angles θ1, θ2, θ3, ..., θ t-2 θ t-1 The variance σ, if θt-θ t-1 If α×σ > β×σ and Δθ > β×σ, then the second preset condition is satisfied, and it is determined that the attitude of the point cloud data acquisition device has changed.

[0103] Furthermore, in this embodiment, based on the deviation between the current trajectory direction angle and the historical trajectory direction angle, the point cloud data of each object in the target environment collected by the point cloud data acquisition device in the current period can be corrected using the following formula (1):

[0104]

[0105] Where (x,y) represents the point cloud data of objects in the target environment collected by the point cloud data acquisition device in the current period; △θ represents the deviation between the current trajectory direction angle and the historical trajectory direction angle; This represents the point cloud data after correction of the point cloud data of objects in the target environment collected by the point cloud data acquisition device in the current period. Here, α and β are set parameters.

[0106] In this application, if it is determined that the attitude of the point cloud data acquisition device has changed, the point cloud data of each object in the target environment collected by the point cloud data acquisition device in the current period is corrected based on the deviation between the current trajectory direction angle and the historical trajectory direction angle. Taking an air conditioning device as an example, the advantage is that the air conditioning device can accurately identify the user's position and adjust the airflow direction of the air conditioning device's vent to avoid the air conditioning device blowing air directly at the user. In this way, the intelligence level of the air conditioning device during operation can be greatly improved, thereby enhancing the user experience.

[0107] In another embodiment of step 233 above, determining whether the pose of the point cloud data acquisition device has changed based on the current point cloud distribution characteristics and the historical point cloud distribution characteristics can also be performed according to steps 2334 to 2336 as follows:

[0108] Step 2334: Based on the current point cloud distribution characteristics, connect each group of adjacent point clouds to obtain the current point cloud trajectory.

[0109] Step 2335: Based on the historical point cloud distribution characteristics, connect each group of adjacent point clouds to obtain the historical point cloud trajectory.

[0110] Step 2336: Determine whether the attitude of the point cloud data acquisition device has changed based on the current point cloud trajectory and the historical point cloud trajectory.

[0111] Specifically, in this embodiment, determining whether the attitude of the point cloud data acquisition device has changed based on the geometric features of the current point cloud distribution contour and the geometric features of the historical point cloud distribution contour can be achieved by comparing the current point cloud trajectory with the historical trajectory and observing whether there are significant differences in their shape, direction, and position. For example, if the current trajectory shows a significant offset or rotation compared to the historical trajectory, it can be determined that the attitude of the point cloud data acquisition device has changed.

[0112] In this embodiment, the attitude of the point cloud data acquisition device can also be determined based on the geometric features of the current point cloud distribution contour and the geometric features of the historical point cloud distribution contour. Alternatively, the distance between the current point cloud trajectory and the historical point cloud trajectory can be calculated. If the distance between the two exceeds a certain threshold, it can be determined that the attitude of the point cloud data acquisition device has changed.

[0113] In this embodiment, the angle change between the current point cloud trajectory and the historical point cloud trajectory can also be calculated by analyzing the tangent direction of the point cloud trajectory. If the angle change exceeds a certain preset value, it can be determined that the attitude of the point cloud data acquisition device has changed.

[0114] In this embodiment, features such as curvature and smoothness of the current point cloud trajectory and the historical point cloud trajectory can also be extracted and compared. If the feature changes are significant, it can be determined that the attitude of the point cloud data acquisition device has changed.

[0115] In this embodiment, machine learning algorithms (such as support vector machines, neural networks, etc.) can also be used to determine whether there is a change in attitude between the current point cloud trajectory and the historical point cloud trajectory.

[0116] It is understood that, in this embodiment, there are multiple ways to determine whether the attitude of the point cloud data acquisition device has changed based on the current point cloud trajectory and the historical point cloud trajectory, and this application does not make a specific limitation on this.

[0117] In another embodiment of step 233 above, the step of determining whether the attitude of the point cloud data acquisition device has changed based on the current point cloud distribution characteristics and the historical point cloud distribution characteristics can also be performed according to the following steps 2337 to 2339:

[0118] Step 2337: Determine the current point cloud distribution contour based on the current point cloud distribution features.

[0119] Step 2338: Determine the historical point cloud distribution outline based on the historical point cloud distribution characteristics.

[0120] Step 2339: Determine whether the attitude of the point cloud data acquisition device has changed based on the geometric features of the current point cloud distribution contour and the geometric features of the historical point cloud distribution contour.

[0121] Specifically, in this embodiment, the attitude of the point cloud data acquisition device is determined to have changed based on the geometric features of the current point cloud distribution contour and the geometric features of the historical point cloud distribution contour. This can be done by comparing the contour shapes of the two, such as calculating the overlapping area or overlap ratio of the current point cloud distribution contour and the historical point cloud distribution contour. If the degree of overlap is lower than a certain threshold, it can be determined that the attitude of the point cloud data acquisition device has changed.

[0122] In this embodiment, the attitude of the point cloud data acquisition device is determined to have changed based on the geometric features of the current point cloud distribution contour and the geometric features of the historical point cloud distribution contour. Alternatively, the boundary features (such as boundary length, boundary curvature, etc.) of the current point cloud distribution contour and the historical point cloud distribution contour can be extracted and compared. If these features show significant changes, it can be determined that the attitude of the point cloud data acquisition device has changed.

[0123] In this embodiment, the attitude of the point cloud data acquisition device is determined to have changed based on the geometric features of the current point cloud distribution contour and the geometric features of the historical point cloud distribution contour. Alternatively, principal component analysis can be performed on the current and historical point cloud distribution contours to compare the orientation and variance of the principal components. If the orientation of the principal components changes significantly, it can be determined that the attitude of the point cloud data acquisition device has changed.

[0124] In this embodiment, the attitude of the point cloud data acquisition device is determined to have changed based on the geometric features of the current point cloud distribution contour and the geometric features of the historical point cloud distribution contour. Alternatively, key points can be extracted from the current point cloud distribution contour and the historical point cloud distribution contour, and the relative positions and angles between the key points can be compared. If the distribution of the key points changes significantly, it can be determined that the attitude of the point cloud data acquisition device has changed.

[0125] It is understood that, in this embodiment, there are multiple ways to determine whether the pose of the point cloud data acquisition device has changed based on the geometric features of the current point cloud distribution contour and the geometric features of the historical point cloud distribution contour, and this application does not make any specific limitation on this.

[0126] In this application, when the target object is an object fixedly located in the target environment, such as Figure 2Step 230, as shown, which involves determining whether the pose of the point cloud data acquisition device has changed based on the current point cloud data and the historical point cloud data, can be executed according to the following steps 234 to 235:

[0127] Step 234: Based on the current point cloud data and the historical point cloud data, determine the current point cloud distribution pattern and the historical point cloud distribution pattern (i.e., shape and orientation) of the target object.

[0128] Step 235: Determine whether the attitude of the point cloud data acquisition device has changed based on the current point cloud distribution pattern and the historical point cloud distribution pattern.

[0129] To enable those skilled in the art to better understand this embodiment, the following will continue to refer to... Figure 3 Subgraph (b) in the diagram is illustrated using a specific application scenario example.

[0130] like Figure 3 As shown in sub-figure (b), since the target object 302 (such as a television set mounted on a wall) is a static object, the current point cloud distribution pattern and the historical point cloud distribution pattern of the target object can be directly determined based on the current point cloud data and the historical point cloud data, respectively. If there are significant changes in the current point cloud distribution pattern and the historical point cloud distribution pattern, it can be determined that the attitude of the point cloud data acquisition device has changed.

[0131] Based on the technical solution proposed in this application, historical point cloud data can be used as a reference. By analyzing the changes between the current point cloud data and historical point cloud data, the response of the point cloud data acquisition device in detecting attitude changes is made more rapid, thereby quickly determining the attitude changes of the point cloud data acquisition device. Especially in the application scenario of air conditioning equipment, point cloud data of a robotic vacuum cleaner moving along a fixed cleaning path in a room can be collected by its configured radar sensors. By comparing the difference between the point cloud data of the robotic vacuum cleaner during its movement in a historical period and the point cloud data of the robotic vacuum cleaner during its movement in the current period, it is possible to accurately and efficiently determine whether there are any changes in the attitude of the radar sensors configured in the air conditioning equipment, and to perform timely self-calibration of radar sensors with attitude changes, thereby improving the self-calibration efficiency of the radar sensors.

[0132] The following describes an apparatus embodiment of this application, which can be used to execute the point cloud data processing method in the above embodiments of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the point cloud data processing method described above.

[0133] See Figure 6 The diagram shows a block diagram of a point cloud data processing apparatus according to an embodiment of this application.

[0134] like Figure 6 As shown, the point cloud data processing device 600 according to an embodiment of this application includes: a first acquisition unit 601, a second acquisition unit 602, and a determination unit 603.

[0135] The first acquisition unit 601 is used to acquire the current point cloud data of a target object in the target environment collected by the point cloud data acquisition device in the current period, wherein the point cloud data acquisition device is installed at a set position in the target environment; the second acquisition unit 602 is used to acquire the historical point cloud data of the target object collected by the point cloud data acquisition device in the historical period; and the determination unit 603 is used to determine whether the attitude of the point cloud data acquisition device has changed based on the current point cloud data and the historical point cloud data.

[0136] In some embodiments of this application, based on the foregoing scheme, the target object is an object moving along a fixed path in the target environment, and the determining unit 603 is configured to: determine the current point cloud distribution characteristics of the target object during its movement in the target environment based on the current point cloud data; determine the historical point cloud distribution characteristics of the target object during its movement in the target environment based on the historical point cloud data; and determine whether the attitude of the point cloud data acquisition device has changed according to the current point cloud distribution characteristics and the historical point cloud distribution characteristics.

[0137] In some embodiments of this application, based on the aforementioned scheme, the determining unit 603 is configured to: determine a current point cloud trajectory segment that satisfies a first preset condition based on the current point cloud distribution characteristics, and determine the current trajectory direction angle of the current point cloud trajectory segment; determine a historical point cloud trajectory segment that satisfies the first preset condition based on the historical point cloud distribution characteristics, and determine the historical trajectory direction angle of the historical point cloud trajectory segment; and determine whether the attitude of the point cloud data acquisition device has changed based on the current trajectory direction angle and the historical trajectory direction angle.

[0138] In some embodiments of this application, based on the aforementioned scheme, the determining unit 603 is configured to: determine the velocity direction angle of each point cloud based on the current point cloud distribution characteristics; group the point clouds based on the velocity direction angle to obtain multiple point cloud groups, wherein the difference between the maximum and minimum velocity direction angles of the point clouds in the same point cloud group is less than a preset difference; cluster the point clouds in each point cloud group according to the clustering condition that the distance between adjacent point clouds is less than a preset distance to obtain multiple point cloud sets; connect adjacent point clouds in each point cloud set to obtain the point cloud trajectory segment corresponding to each point cloud set; determine the target point cloud trajectory segment in each point cloud group whose length is greater than a preset length, and determine the point cloud group with the most target point cloud trajectory segments as the target point cloud group; determine the target point cloud trajectory segment in the target point cloud group as the current point cloud trajectory segment that satisfies the first preset condition.

[0139] In some embodiments of this application, based on the foregoing scheme, the determining unit 603 is configured to: determine the average value of the trajectory direction angles of each current point cloud trajectory segment as the current trajectory direction angle of the current point cloud trajectory segment; or, determine the average value of the velocity direction angles of each point cloud in each current point cloud trajectory segment as the current trajectory direction angle of the current point cloud trajectory segment.

[0140] In some embodiments of this application, based on the foregoing scheme, the determining unit 603 is configured to: if the deviation between the current trajectory direction angle and the historical trajectory direction angle meets a second preset condition, then determine that the attitude of the point cloud data acquisition device has changed.

[0141] In some embodiments of this application, based on the foregoing scheme, the device further includes: a correction unit, used to correct the point cloud data of each object in the target environment collected by the point cloud data acquisition device in the current period based on the deviation between the current trajectory direction angle and the historical trajectory direction angle after determining that the attitude of the point cloud data acquisition device has changed.

[0142] In some embodiments of this application, based on the aforementioned scheme, the determining unit 603 is configured to: connect each group of adjacent point clouds based on the current point cloud distribution characteristics to obtain the current point cloud trajectory; connect each group of adjacent point clouds based on the historical point cloud distribution characteristics to obtain the historical point cloud trajectory; and determine whether the attitude of the point cloud data acquisition device has changed according to the current point cloud trajectory and the historical point cloud trajectory.

[0143] In some embodiments of this application, based on the foregoing scheme, the determining unit 603 is configured to: determine the current point cloud distribution contour based on the current point cloud distribution features; determine the historical point cloud distribution contour based on the historical point cloud distribution features; and determine whether the attitude of the point cloud data acquisition device has changed according to the geometric features of the current point cloud distribution contour and the geometric features of the historical point cloud distribution contour.

[0144] In some embodiments of this application, based on the foregoing scheme, the target object is an object fixed in the target environment, and the determining unit 603 is configured to: determine the current point cloud distribution pattern and the historical point cloud distribution pattern of the target object based on the current point cloud data and the historical point cloud data; and determine whether the attitude of the point cloud data acquisition device has changed according to the current point cloud distribution pattern and the historical point cloud distribution pattern.

[0145] In some embodiments of this application, based on the aforementioned scheme, the target object is a robotic vacuum cleaner.

[0146] In some embodiments of this application, based on the foregoing scheme, the point cloud data acquisition device is a multiple-transmitter, multiple-receiver radar.

[0147] Based on the same inventive concept, embodiments of this application provide a computer program product, the computer program product including computer instructions stored in a computer-readable storage medium and adapted to be read and executed by a processor, so as to cause a computer device having the processor to perform the operations performed by the point cloud data processing method as described above.

[0148] Based on the same inventive concept, embodiments of this application provide a computer-readable storage medium storing at least one computer program instruction, which is loaded and executed by a processor to implement the operations performed by the point cloud data processing method described above.

[0149] Based on the same inventive concept, this application also provides a household appliance, see reference. Figure 7 The diagram shows a structural schematic of a home appliance in an embodiment of this application. The home appliance includes one or more memories 704, one or more processors 702, and at least one computer program (computer program instruction) stored in the memory 704 and executable on the processor 702. When the processor 702 executes the computer program, it implements the point cloud data processing method as described above.

[0150] Among them, Figure 7In this document, a bus architecture (represented by bus 700) is used. Bus 700 may include any number of interconnected buses and bridges, linking various circuits including one or more processors represented by processor 702 and memory represented by memory 704. Bus 700 may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 705 provides an interface between bus 700 and receiver 701 and transmitter 703. Receiver 701 and transmitter 703 may be the same element, i.e., a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 702 is responsible for managing bus 700 and general processing, while memory 704 can be used to store data used by processor 702 during operation.

[0151] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and embodiments are within the scope and spirit of this application and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination thereof. Furthermore, the functional units may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit.

[0152] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0153] The units described as separate components may or may not be physically separate. Similarly, the components of the control device may or may not be physical units; they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0154] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing computer program instructions, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0155] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A point cloud data processing method, characterized in that, The method includes: Acquire current point cloud data of a target object in a target environment, which is collected by a point cloud data acquisition device in the current period. The point cloud data acquisition device is installed at a set position in the target environment. Acquire historical point cloud data of the target object collected by the point cloud data acquisition device in historical periods; Based on the current point cloud data and the historical point cloud data, determine whether there is a change in the attitude of the point cloud data acquisition device.

2. The method according to claim 1, characterized in that, The target object is an object moving along a fixed path in the target environment. Determining whether the pose of the point cloud data acquisition device has changed based on the current point cloud data and the historical point cloud data includes: Based on the current point cloud data, determine the current point cloud distribution characteristics of the target object during its movement in the target environment; Based on the historical point cloud data, the historical point cloud distribution characteristics of the target object during its movement in the target environment are determined; Based on the current point cloud distribution characteristics and the historical point cloud distribution characteristics, determine whether the attitude of the point cloud data acquisition device has changed.

3. The method according to claim 2, characterized in that, The step of determining whether the pose of the point cloud data acquisition device has changed based on the current point cloud distribution characteristics and the historical point cloud distribution characteristics includes: Based on the current point cloud distribution characteristics, determine the current point cloud trajectory segment that meets the first preset condition, and determine the current trajectory direction angle of the current point cloud trajectory segment; Based on the historical point cloud distribution characteristics, determine the historical point cloud trajectory segment that meets the first preset condition, and determine the historical trajectory direction angle of the historical point cloud trajectory segment; Based on the current trajectory direction angle and the historical trajectory direction angle, determine whether the attitude of the point cloud data acquisition device has changed.

4. The method according to claim 3, characterized in that, The step of determining the current point cloud trajectory segment that satisfies the first preset condition based on the current point cloud distribution characteristics includes: Based on the current point cloud distribution characteristics, determine the velocity direction angle of each point cloud; Based on the velocity direction angle, the point clouds are grouped to obtain multiple point cloud groups, wherein the difference between the maximum and minimum velocity direction angles of the point clouds in the same point cloud group is less than a preset difference. Based on the clustering condition that the distance between adjacent point clouds is less than a preset distance, the point clouds in each point cloud group are clustered to obtain multiple point cloud sets; Connect adjacent point clouds in each point cloud set to obtain the point cloud trajectory segment corresponding to each point cloud set; Identify the target point cloud trajectory segments in each point cloud group whose point cloud trajectory segment length is greater than the preset length, and determine the point cloud group with the most target point cloud trajectory segments as the target point cloud group; The target point cloud trajectory segment in the target point cloud group is determined as the current point cloud trajectory segment that meets the first preset condition.

5. The method according to claim 4, characterized in that, Determining the current trajectory direction angle of the current point cloud trajectory segment includes: The average value of the trajectory direction angles of each current point cloud trajectory segment is determined as the current trajectory direction angle of the current point cloud trajectory segment; or, The average value of the velocity direction angle of each point cloud in each current point cloud trajectory segment is determined as the current trajectory direction angle of the current point cloud trajectory segment.

6. The method according to claim 3, characterized in that, Determining whether the attitude of the point cloud data acquisition device has changed based on the current trajectory direction angle and the historical trajectory direction angle includes: If the deviation between the current trajectory direction angle and the historical trajectory direction angle meets the second preset condition, then it is determined that the attitude of the point cloud data acquisition device has changed.

7. The method according to claim 6, characterized in that, After determining that the pose of the point cloud data acquisition device has changed, the method further includes: Based on the deviation between the current trajectory direction angle and the historical trajectory direction angle, the point cloud data of each object in the target environment collected by the point cloud data acquisition device in the current period is corrected.

8. The method according to claim 2, characterized in that, The step of determining whether the pose of the point cloud data acquisition device has changed based on the current point cloud distribution characteristics and the historical point cloud distribution characteristics includes: Based on the current point cloud distribution characteristics, connect each group of adjacent point clouds to obtain the current point cloud trajectory; Based on the historical point cloud distribution characteristics, connect each group of adjacent point clouds to obtain the historical point cloud trajectory; Based on the current point cloud trajectory and the historical point cloud trajectory, determine whether the attitude of the point cloud data acquisition device has changed.

9. The method according to claim 2, characterized in that, The step of determining whether the pose of the point cloud data acquisition device has changed based on the current point cloud distribution characteristics and the historical point cloud distribution characteristics includes: Based on the current point cloud distribution characteristics, determine the current point cloud distribution outline; Based on the aforementioned historical point cloud distribution characteristics, the historical point cloud distribution outline is determined; Based on the geometric features of the current point cloud distribution contour and the geometric features of the historical point cloud distribution contour, determine whether the attitude of the point cloud data acquisition device has changed.

10. The method according to claim 1, characterized in that, The target object is an object fixed in the target environment. Determining whether the pose of the point cloud data acquisition device has changed based on the current point cloud data and the historical point cloud data includes: Based on the current point cloud data and the historical point cloud data, the current point cloud distribution pattern and the historical point cloud distribution pattern of the target object are determined respectively. Based on the current point cloud distribution pattern and the historical point cloud distribution pattern, determine whether the attitude of the point cloud data acquisition device has changed.

11. The method according to any one of claims 2 to 9, characterized in that, The target object is a robotic vacuum cleaner.

12. The method according to any one of claims 1 to 10, characterized in that, The point cloud data acquisition device is a multi-transmitter, multi-receiver radar.

13. A point cloud data processing device, characterized in that, The device includes: The first acquisition unit is used to acquire the current point cloud data of the target object in the target environment collected by the point cloud data acquisition device in the current period. The point cloud data acquisition device is installed at a set position in the target environment. The second acquisition unit is used to acquire historical point cloud data of the target object collected by the point cloud data acquisition device in a historical period. The determining unit is used to determine whether the attitude of the point cloud data acquisition device has changed based on the current point cloud data and the historical point cloud data.

14. A computer program product, characterized in that, The computer program product includes computer instructions stored in a computer-readable storage medium and adapted to be read and executed by a processor to cause a computer device having the processor to perform the method as claimed in any one of claims 1 to 12.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one piece of program code, which is loaded and executed by a processor to perform the operations performed by the method as described in any one of claims 1 to 12.

16. A household appliance, characterized in that, The home appliance includes one or more processors and one or more memories, wherein the one or more memories store at least one piece of program code, which is loaded and executed by the one or more processors to implement the method as claimed in any one of claims 1 to 12.

Images