Point cloud data screening method and device

Abstract

The present disclosure provides a point cloud data screening method and device, comprising: acquiring point cloud data to be identified, wherein the point cloud data to be identified is obtained by a radar device deployed on a vehicle scanning a first area; determining point cloud data corresponding to a static object in the point cloud data to be identified according to attribute information of each map grid; wherein each map grid is obtained by dividing the first area, and the attribute information of each map grid is determined according to parameter information of the vehicle and positioning data collected by a positioning device deployed on the vehicle during the vehicle traveling in the first area; the attribute information of the map grid includes state information of the map grid, and the state information includes a passable state and an impassable state.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a point cloud data screening method and device. Background Art

[0002] When driving, the autonomous vehicle will match the point cloud data collected at the current moment with the pre-built point cloud map to achieve the positioning of the autonomous vehicle. If there are too many point cloud data of dynamic objects in the point cloud map, or too many dynamic objects in the point cloud data collected by the autonomous vehicle, the matching accuracy will be affected when matching the point cloud data of the autonomous vehicle with the point cloud map, which will in turn affect the positioning accuracy of the autonomous vehicle.

[0003] In related technologies, in order to remove the point cloud data of dynamic objects in the point cloud data and obtain the point cloud data corresponding to static objects only, the point cloud data at different times are collected, and then based on the point cloud data at different times, the coordinates of the same object in the world coordinate system are calculated respectively, and the objects with changed coordinates are determined as dynamic objects. However, if the object moves slowly, this method may miss the detection and the accuracy is low. Summary of the invention

[0004] The embodiments of the present disclosure at least provide a method and device for screening point cloud data.

[0005] In a first aspect, an embodiment of the present disclosure provides a point cloud data screening method, comprising:

[0006] Acquire point cloud data to be identified, where the point cloud data to be identified is obtained by a radar device deployed on the vehicle scanning a first area;

[0007] Determining point cloud data corresponding to a static object in the point cloud data to be identified according to the attribute information of each map grid;

[0008] Among them, each map grid is obtained by dividing the first area, and the attribute information of each map grid is determined according to the parameter information of the vehicle and the positioning data collected by the positioning device deployed on the vehicle when the vehicle is traveling in the first area; the attribute information of the map grid includes the state information of the map grid, and the state information includes a passable state and an impassable state.

[0009] The point cloud data screening method provided by the embodiment of the present disclosure pre-divides the map grid, and then determines the attribute information of the map grid according to the positioning data and parameter information of the vehicle during the driving process, wherein the attribute information can indicate whether the state of the map grid is passable or impassable, and then determines the point cloud data corresponding to the static object in the point cloud data to be identified according to the attribute information of the map grid; here, since the point cloud data located in the area (passable area) passed by the vehicle during the driving process, except for the point cloud data on the ground, must be the point cloud data of non-static objects (because in the passable area for the vehicle, there is no static object that always blocks the passage of the vehicle), therefore, based on the method provided by the present embodiment, the screening accuracy of the static object point cloud data can be improved.

[0010] In an optional implementation manner, the parameter information of the vehicle includes: external dimension parameter information of the vehicle body relative to the positioning device;

[0011] The method further includes determining the attribute information of each map grid based on the following method:

[0012] Based on the positioning data collected by the positioning device and the external dimension parameter information, determine the passage area information passed by the vehicle during driving;

[0013] Based on the passable area information and the position information of each pre-divided map grid, the attribute information of each map grid is determined; wherein the state information of the map grid located in the passable area is a passable state.

[0014] Here, the positioning data collected by the positioning device is the positioning data of the positioning device itself. Combined with the external dimension parameter information of the vehicle body relative to the positioning device, the coordinate information of the location area passed by the vehicle body can be obtained, that is, the pass area information, and the state of the map grid covered by the pass area can be further determined as a passable state.

[0015] In an optional implementation manner, determining the passage area information passed by the vehicle during driving based on the positioning data collected by the positioning device and the external dimension parameter information includes:

[0016] Determine the position and posture data of the positioning device in the world coordinate system based on the positioning data collected by the positioning device;

[0017] The passage area information is determined based on the position and posture data of the positioning device and the external dimension parameter information.

[0018] Here, the positioning data collected by the positioning device can be calculated and converted into the posture data of the positioning device in the world coordinate system, and then the pass area information in the world coordinate system can be determined based on the posture data of the positioning device and the external dimension parameter information, and then the attribute information of the map grid in the world coordinate system can be determined based on the pass area information.

[0019] In an optional implementation manner, the attribute information of the map grid further includes height information of the map grid relative to sea level; the parameter information of the vehicle includes: external dimension parameter information of the vehicle body relative to the positioning device;

[0020] The method further includes determining the attribute information of each map grid based on the following method:

[0021] Based on the positioning data and the external dimension parameter information, the height information of each pre-divided map grid relative to the sea level is determined.

[0022] In an optional implementation manner, the external dimension parameter information includes vertex coordinates of a rectangular frame surrounding the body of the vehicle in a coordinate system with the positioning device as the coordinate origin;

[0023] The determining, based on the positioning data and the external dimension parameter information, the height information of each pre-divided map grid relative to the sea level comprises:

[0024] A bilinear interpolation operation is performed based on the altitude information in the positioning data and the vertex coordinates to obtain the altitude information of the map grid relative to the sea level.

[0025] In an optional implementation, the parameter information of the vehicle includes: relative position information between the positioning device and the radar device;

[0026] The step of determining the point cloud data corresponding to the static object in the point cloud data to be identified according to the attribute information of each map grid comprises:

[0027] According to the relative position information, coordinate transformation processing is performed on the point cloud data to be identified to obtain transformed point cloud data;

[0028] Based on the attribute information of each map grid and the position information corresponding to each map grid, the point cloud data corresponding to the static object in the converted point cloud data is determined.

[0029] Here, since the position information of the map grid is the position information in the world coordinate system, and the coordinates of the point cloud data (i.e., each radar scanning point) are the coordinates in the coordinate system with the radar device as the coordinate origin, based on the relative position information, the accuracy of point cloud data screening can be improved by converting the point cloud data into point cloud data in the world coordinate system.

[0030] In an optional implementation, performing coordinate transformation processing on the point cloud data to be identified according to the relative position information to obtain transformed point cloud data includes:

[0031] Determining position data of a radar device on the vehicle based on positioning data of a positioning device on the vehicle and the relative position information;

[0032] Based on the position and posture data of the radar device, coordinate transformation processing is performed on the point cloud data to be identified to obtain transformed point cloud data.

[0033] In an optional implementation, determining the point cloud data corresponding to the static object in the converted point cloud data based on the determined attribute information of each map grid and the position information corresponding to each map grid includes:

[0034] Based on the coordinate information of the radar scanning points in the converted point cloud data and the position information corresponding to each map grid, determining the map grid into which each radar scanning point falls;

[0035] Determine the radar scanning point that falls into the map grid and is in an inaccessible state as the first radar scanning point;

[0036] Determine as a second radar scanning point a radar scanning point in which a map grid falls into a passable state and a difference between a corresponding height and a height of the map grid relative to the sea level that is less than a set threshold;

[0037] The first radar scanning point and the second radar scanning point are determined as point cloud data corresponding to static objects in the point cloud data to be identified.

[0038] Here, among the radar scanning points in the passable area, the objects corresponding to the other radar scanning points except the radar scanning points on the ground must not be static objects that hinder the passage of vehicles. Therefore, the non-ground radar scanning points in the passable area are dynamic objects. Correspondingly, the radar scanning points in the inaccessible area, that is, the first radar scanning points mentioned above, are static objects (including radar scanning points on the ground and radar scanning points of static objects on the ground). In addition, in the passable area, the radar scanning points whose corresponding height difference with the height of the map grid relative to the sea level is less than a set threshold can be determined as ground radar scanning points, that is, the second radar scanning points. These ground radar scanning points are also point cloud data of static objects.

[0039] In a possible implementation manner, after determining the point cloud data corresponding to the static object in the point cloud data to be identified, the method further includes:

[0040] A map corresponding to the first area is constructed based on the point cloud data corresponding to the static object.

[0041] In a second aspect, the present disclosure also provides a point cloud data screening device, comprising:

[0042] An acquisition module, used for acquiring point cloud data to be identified, wherein the point cloud data to be identified is obtained by a radar device deployed on the vehicle scanning the first area;

[0043] A determination module, used to determine the point cloud data corresponding to the static object in the point cloud data to be identified according to the attribute information of each map grid;

[0044] Among them, each map grid is obtained by dividing the first area, and the attribute information of each map grid is determined according to the parameter information of the vehicle and the positioning data collected by the positioning device deployed on the vehicle when the vehicle is traveling in the first area; the attribute information of the map grid includes the state information of the map grid, and the state information includes a passable state and an impassable state.

[0045] In a third aspect, an embodiment of the present disclosure further provides a computer device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the above-mentioned first aspect, or any possible implementation of the first aspect are performed.

[0046] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned first aspect or any possible implementation of the first aspect are executed.

[0047] For a description of the effects of the above-mentioned point cloud data screening device, computer equipment, and computer-readable storage medium, please refer to the description of the above-mentioned point cloud data screening method, which will not be repeated here.

[0048] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following is a brief introduction to the drawings required for use in the embodiments. The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used together with the specification to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can also be obtained based on these drawings without creative work.

[0050] Figure 1 A flow chart of a point cloud data screening method provided by an embodiment of the present disclosure is shown;

[0051] Figure 2 A schematic diagram of a rectangular frame including a vehicle body provided by an embodiment of the present disclosure is shown;

[0052] Figure 3 A flow chart of a method for determining attribute information of a map grid provided by an embodiment of the present disclosure is shown;

[0053] Figure 4 A schematic diagram showing a method for converting vertex coordinates of a rectangular frame provided by an embodiment of the present disclosure into a first coordinate system in a world coordinate system is shown;

[0054] Figure 5 A flow chart of a method for determining point cloud data corresponding to a static object in point cloud data to be identified provided by an embodiment of the present disclosure is shown;

[0055] Figure 6 A schematic diagram of a point cloud data screening device provided by an embodiment of the present disclosure is shown;

[0056] Figure 7 A schematic diagram of the structure of a computer device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical scheme and advantages of the embodiments of the present disclosure clearer, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the present disclosure for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present disclosure.

[0058] When matching the point cloud data collected by the autonomous driving vehicle during driving with the point cloud map, the point cloud data of dynamic objects in the point cloud data will affect the matching results. For example, if there is no object on the road at a certain location when the point cloud map is constructed, but there is a pedestrian at that location in the point cloud data collected by the autonomous driving vehicle during driving, then at this time, when matching the point cloud data with the point cloud map, the matching accuracy will be affected by the influence of the pedestrian's point cloud data.

[0059] Similarly, when constructing a point cloud map, if there is a vehicle at a certain location, the constructed point cloud map will contain the point cloud data of the vehicle. When the autonomous driving vehicle collects point cloud data at that location during driving, the parked vehicle has already left. At this time, the point cloud data collected by the autonomous driving vehicle does not include the vehicle. Therefore, when matching the point cloud data with the point cloud map, the point cloud data of the vehicle's parking location will affect the matching accuracy.

[0060] In related technologies, in order to eliminate the influence of dynamic objects in point cloud data on matching, point cloud data at different times are collected, and then the coordinates of the same object in the world coordinate system are calculated based on the point cloud data at different times. Since the coordinates of static objects in the world coordinate system should be unchanged at different times, objects whose position coordinates change at different times can be determined as dynamic objects, and the point cloud data of dynamic objects are eliminated. However, if the object moves slowly in this method, the dynamic object does not move when collecting point cloud data at different times, and it is easy to miss the dynamic object, thereby affecting the screening accuracy of the point cloud data of dynamic objects.

[0061] In another method, the point cloud data of dynamic objects can be identified through machine learning methods. However, since this method needs to train different neural networks for different driving scenarios, the generalization ability is poor and a large number of samples are required to train the neural network, the screening accuracy and efficiency are relatively low.

[0062] Based on this, the disclosed embodiment provides a point cloud data screening method, which divides the map grid in advance, and then determines the attribute information of the map grid according to the positioning data and parameter information of the vehicle during the driving process, and the attribute information can indicate whether the state of the map grid is passable or impassable, and then determines the point cloud data corresponding to the static object in the point cloud data to be identified according to the attribute information of the map grid; here, since the point cloud data located in the area passed by the vehicle during the driving process (the passable area), except for the point cloud data on the ground, must be the point cloud data of non-static objects (because in the passable area for the vehicle, there is no static object that always blocks the passage of the vehicle), therefore, based on the method provided by this embodiment, the screening accuracy of the static object point cloud data can be improved.

[0063] The defects existing in the above solutions are the results obtained by the inventor after practice and careful research. Therefore, the discovery process of the above problems and the solutions proposed by the present disclosure for the above problems below should be the contributions made by the inventor to the present disclosure during the disclosure process.

[0064] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0065] To facilitate understanding of the present embodiment, a point cloud data screening method disclosed in the present embodiment is first introduced in detail. The execution subject of the point cloud data screening method provided in the present embodiment is generally a computer device with certain computing capabilities, and the computer device includes, for example: a terminal device or a server or other processing device, and the terminal device can be a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the point cloud data screening method can be implemented by a processor calling a computer-readable instruction stored in a memory.

[0066] See also Figure 1 FIG. 1 is a flowchart of a point cloud data screening method provided by an embodiment of the present disclosure, and the method includes the following steps:

[0067] Step 101: Acquire point cloud data to be identified, where the point cloud data to be identified is obtained by a radar device deployed on a vehicle scanning a first area.

[0068] Step 102: Determine the point cloud data corresponding to the static object in the point cloud data to be identified according to the attribute information of each map grid.

[0069] The following is a detailed description of the above steps.

[0070] In a possible implementation, when collecting point cloud data to be identified, the vehicle can traverse all passable areas in the first area, and the radar device deployed on the vehicle can scan the first area at a set frequency to obtain the point cloud data to be identified.

[0071] In a possible implementation, the areas of different map grids may be the same, and for example, may all be N*N squares, where N is a preset length. In practical applications, the first area may be divided into a plurality of interconnected map grids according to the above size.

[0072] The positioning data of the vehicle during driving can be collected by a positioning device installed on the vehicle (for example, a combined inertial navigation sensor, including a global positioning system (GPS) and an inertial measurement unit (IMU)). The positioning data can be collected once every preset time during the driving of the vehicle. The positioning data includes the latitude and longitude of the vehicle's location, the altitude, and the three-axis attitude angle and acceleration measured by the IMU, and the altitude is the height of the positioning device relative to the sea level.

[0073] The parameter information of the vehicle includes: the external dimension parameter information of the vehicle body relative to the positioning device. Specifically, the external dimension parameter information may include the vertex coordinates of a rectangular frame including the vehicle body in a coordinate system with the positioning device as the coordinate origin.

[0074] For example, Figure 2 As shown, the rectangular frame including the vehicle body is the smallest rectangular frame covering the vertical projection of the vehicle body on the ground. Figure 2 The midpoint O is the vertical projection of the positioning device on the vehicle body on the ground. With point O as the origin, a plane direct coordinate system is established, and then the coordinates of the four vertices of the rectangular box are determined.

[0075] Taking the executor of the present solution as a terminal device as an example, in a possible implementation mode, after collecting the positioning data, the positioning device can transmit it to the terminal device, and then the terminal device executes the processing of steps 101 to 102, wherein the method of transmitting data between the positioning device and the terminal device may include wired transmission and wireless transmission, and the wireless transmission method may be, for example, Bluetooth transmission, wireless network transmission, etc.

[0076] The step of acquiring positioning data may be performed after the vehicle has traveled through all passable areas in the first area, or may be performed in real time while the vehicle is traveling; the parameter information of the vehicle may be pre-set.

[0077] In a possible implementation, when determining the attribute information of each map grid, the following method can be used: Figure 3 The method shown includes the following steps:

[0078] Step 301: Based on the positioning data collected by the positioning device and the external dimension parameter information, determine the passage area information passed by the vehicle during driving.

[0079] The passable area information may be a coordinate range of the passable area in the first area in the world coordinate system. For each moment, the coordinate range of the passable area in the world coordinate system when the positioning data is collected at that moment may be determined based on the positioning data collected at that moment.

[0080] Specifically, when determining the passage area information, the position data of the positioning device in the world coordinate system can be determined based on the positioning data collected by the positioning device. The position data includes the coordinates (x, y, z) of the positioning device in the world coordinate system and the pitch angle pitch, yaw angle yaw, and roll angle roll; then, the passage area information passed by the vehicle during driving is determined based on the position data of the positioning device in the world coordinate system and the external dimension parameter information.

[0081] In a possible implementation, the external dimension parameter information includes the vertex coordinates of a rectangular frame including the vehicle body in a coordinate system with the positioning device as the coordinate origin. The vertex coordinates of the rectangular frame can be converted to the first coordinates in the world coordinate system based on the posture data of the positioning device, and then the area formed by the first coordinates of the vertices of the rectangular frame can be determined as the passage area information passed by the vehicle during driving.

[0082] Specifically, when the vertex coordinates of the rectangular frame are converted to the first coordinates in the world coordinate system based on the position and posture data of the positioning device, the calculation can be performed by the following formula:

[0083] Pg_tl=T(R)*Ptl+T(t)

[0084] Pg_tr=T(R)*Ptr+T(t)

[0085] Pg_bl=T(R)*Pbl+T(t)

[0086] Pg_br=T(R)*Pbr+T(t)

[0087] Among them, Ptl, Ptr, Pbl, and Pbr respectively represent the coordinates of the four vertices of the rectangular box in the coordinate system with the positioning device as the coordinate origin; Pg_tl, Pg_tr, Pg_bl, and Pg_br respectively represent the first coordinates of the vertices of the rectangular box in the world coordinate system, T represents the pose matrix after the pose data of the positioning device is converted based on the preset transformation matrix, T(R) and T(t) are the R part and t part of the pose matrix respectively, and the pose matrix can be expressed as follows:

[0088]

[0089] Step 302: Determine the attribute information of each map grid based on the traffic area information and the position information of each pre-divided map grid.

[0090] The attribute information of the map grid includes state information of the map grid, and the state information includes a passable state and an impassable state.

[0091] After the coordinate conversion in step 301, the determined passage area information is the coordinate information of the area formed by the first coordinates of the rectangular box corresponding to different data collection moments during the vehicle driving process; since the first coordinate is the coordinate in the world coordinate system, the passage area information is the information in the world coordinate system.

[0092] When determining the attribute information of each map grid based on the passable area information and the position information of each pre-divided map grid, the state information of the map grid located in the passable area can be determined as a passable state, and the state information of the map grid located outside the passable area can be determined as an inaccessible state.

[0093] Here, the positioning data collected by the positioning device is the positioning data of the positioning device itself. Combined with the external dimension parameter information of the vehicle body relative to the positioning device, the coordinate information of the location area passed by the vehicle body can be obtained, that is, the pass area information, and the state of the map grid covered by the pass area can be further determined as a passable state.

[0094] In another possible implementation, the attribute information of the map grid also includes height information of the map grid relative to the sea level. Since the ground is not an absolute plane, there may be sunken ground and inclined ground, so the height information of different map grids relative to the sea level is different.

[0095] At this time, when determining the height information of each pre-divided map grid relative to the sea level, the height information of each pre-divided map grid relative to the sea level can be determined based on the positioning data and the external size parameter information.

[0096] In an optional implementation, when determining the height information of each map grid relative to the sea level, bilinear interpolation can be performed on the far end based on the height information in the positioning data and the vertex coordinates of the rectangular box surrounding the vehicle body in a coordinate system with the positioning device as the coordinate origin to obtain the height information of the map grid relative to the sea level.

[0097] Specifically, the vertex coordinates of the rectangular frame can be converted into the first coordinates in the world coordinate system according to the above method, and then based on Figure 4 In the schematic diagram shown, the coordinate value of point Pg_br in the world coordinate system is (x1, y1), the coordinate value of Pg_tr in the world coordinate system is (x2, y2), the coordinate value of Pg_tl in the world coordinate system is (x3, y3), and the coordinate value of Pg_bl in the world coordinate system is (x4, y4); C represents the map grid, (x, y) represents the coordinates of the intersection of the diagonal lines of the map grid (or any point of the map grid) in the world coordinate system, R1 and R2 represent the intersection points passing through the map grid C and parallel to two sides of the rectangular frame and the other two sides, respectively, (x R1 ,y R1 ) represents the coordinates of R1, (x R2 ,y R2 ) represents the coordinates of R2.

[0098] The following formula is used to calculate the height of the map grid relative to sea level:

[0099]

[0100] Among them, f(Pg_tl), f(Pg_tr), f(Pg_bl), and f(Pg_br) respectively represent the heights of points Pg_tl, Pg_tr, Pg_bl, and Pg_br relative to the sea level, z4=z3=z2=z1, respectively represent the heights of points Pg_tl, Pg_tr, Pg_bl, and Pg_br in the world coordinate system, and the height values ​​are equal to the height information in the positioning data collected by the positioning device, and H represents the installation height of the positioning device, which is a preset value.

[0101] Based on the above formula, we can get:

[0102]

[0103] Among them, f(R1) represents the height of the position corresponding to point R1 relative to the sea level, and f(R2) represents the height of the position corresponding to point R2 relative to the sea level.

[0104]

[0105] f(c) is the height of the map grid relative to sea level.

[0106] In a possible implementation, the parameter information of the vehicle may include relative position information between a positioning device on the vehicle and a radar device that collects point cloud data.

[0107] When determining the point cloud data corresponding to the static object in the point cloud data to be identified based on the determined attribute information of each map grid, the following method can be used: Figure 5 The method shown includes the following steps:

[0108] Step 501: perform coordinate conversion processing on the point cloud data to be identified according to the relative position information between the positioning device and the radar device on the vehicle to obtain converted point cloud data.

[0109] Specifically, when performing coordinate transformation processing on the point cloud data to be identified according to the relative position information, the posture data of the radar device on the vehicle can be determined based on the positioning data of the positioning device and the relative position information, and then the coordinate transformation processing is performed on the point cloud data to be identified based on the posture data of the radar device to obtain the converted point cloud data.

[0110] In a possible implementation, the position data of the positioning device on the vehicle that collects point cloud data can be first determined in the world coordinate system based on the position data of the positioning device on the vehicle, and then the position data of the radar device on the vehicle in the world coordinate system can be determined based on the relative position information.

[0111] It should be noted that the point cloud data and position data can be collected by the same vehicle at different time points. For example, vehicle A can collect position data first and then point cloud data, or point cloud data first and then position data. During the data collection process, the relative position information of the positioning device and the radar device remains unchanged.

[0112] The point cloud data to be identified includes coordinate information of multiple radar scanning points, and the coordinate information is the coordinates in a coordinate system with the radar device as the coordinate origin; the coordinate conversion processing of the point cloud data to be identified based on the posture data of the radar device is to convert the coordinate information of the radar scanning point in the coordinate system with the radar device as the coordinate origin into coordinate information in the world coordinate system.

[0113] Step 502: Based on the determined attribute information of each map grid and the position information corresponding to each map grid, determine the point cloud data corresponding to the static object in the converted point cloud data.

[0114] Here, since the position information of the map grid is the position information in the world coordinate system, and the coordinates of each radar scanning point in the point cloud data to be identified are the coordinates in the coordinate system with the radar device as the coordinate origin, therefore, based on the relative position information, by converting the point cloud data to be identified into point cloud data in the world coordinate system, the accuracy of point cloud data screening can be improved.

[0115] Specifically, when determining the point cloud data corresponding to the static object in the converted point cloud data based on the determined attribute information of each map grid and the position information corresponding to each map grid, the map grid in which each radar scanning point falls can be determined based on the coordinate information of the radar scanning point in the converted point cloud data and the position information corresponding to each map grid, and then the radar scanning point that falls into the map grid that is in an impassable state is determined as the first radar scanning point, and the radar scanning point that falls into the map grid that is in a passable state and the difference between the corresponding height and the height of the map grid relative to the sea level is less than a set threshold is determined as the second radar scanning point, and then the first radar scanning point and the second radar scanning point are determined as the point cloud data corresponding to the static object in the point cloud data to be identified.

[0116] In this solution, when collecting the point cloud data to be identified, the vehicle has traveled through all the passable areas in the first area. Therefore, the grid attribute corresponding to the location area where the dynamic object appears in the subsequent point cloud data collection must be the passable area, while for the radar scanning points in other areas outside the passable area, they are the point cloud data of static objects, that is, the first radar scanning point is the point cloud data of the static object.

[0117] When the map grid where the radar scanning point falls is in a passable state, that is, when the radar scanning point is located in the passable area, there may be two situations. One situation is that the radar scanning point is a radar scanning point corresponding to the ground, and the other situation is that the radar scanning point is a radar scanning point corresponding to a dynamic object.

[0118] For the first case, since the radar scanning point corresponding to the ground should be close to the ground, the radar scanning point corresponding to the ground can be screened out by judging whether the difference between the height of the radar scanning point and the height of the map grid corresponding to the radar scanning point relative to the sea level is less than the set threshold. The radar scanning point on the ground is the radar scanning point corresponding to the static object.

[0119] For the second case, since the acquisition of point cloud data is completed after the map grid attribute information is determined, the height information relative to the sea level in the map grid attribute information is fixed. Therefore, if the height difference between the height of the point cloud data of a certain location area and the height information of the map grid of the location area relative to the sea level is detected to be greater than the set threshold, it means that there are other objects in the location area, and the object appears in the location area after the vehicle collects positioning data and drives through the location area. Therefore, it can be directly determined that the object is a dynamic object.

[0120] In a possible implementation, after the point cloud data corresponding to the static object in the point cloud data to be identified is determined, a map corresponding to the first area may also be constructed based on the point cloud data corresponding to the static object.

[0121] The point cloud data screening method provided by the embodiment of the present disclosure pre-divides the map grid, and then determines the attribute information of the map grid according to the positioning data and parameter information of the vehicle during the driving process, wherein the attribute information can indicate whether the state of the map grid is passable or impassable, and then determines the point cloud data corresponding to the static object in the point cloud data to be identified according to the attribute information of the map grid; here, since the point cloud data located in the area (passable area) passed by the vehicle during the driving process, except for the point cloud data on the ground, must be the point cloud data of non-static objects (because in the passable area for the vehicle, there is no static object that always blocks the passage of the vehicle), therefore, based on the method provided by the present embodiment, the screening accuracy of the static object point cloud data can be improved.

[0122] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0123] Based on the same inventive concept, a point cloud data screening device corresponding to the point cloud data screening method is also provided in the embodiment of the present disclosure. Since the principle of solving the problem by the device in the embodiment of the present disclosure is similar to the above-mentioned point cloud data screening method in the embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0124] Reference Figure 6, which is a schematic diagram of a point cloud data screening device provided by an embodiment of the present disclosure, the device comprises: an acquisition module 601, a determination module 602; wherein,

[0125] An acquisition module 601 is used to acquire point cloud data to be identified, where the point cloud data to be identified is obtained by a radar device deployed on a vehicle scanning a first area;

[0126] A determination module 602 is used to determine the point cloud data corresponding to the static object in the point cloud data to be identified according to the attribute information of each map grid;

[0127] Among them, each map grid is obtained by dividing the first area, and the attribute information of each map grid is determined according to the parameter information of the vehicle and the positioning data collected by the positioning device deployed on the vehicle when the vehicle is traveling in the first area; the attribute information of the map grid includes the state information of the map grid, and the state information includes a passable state and an impassable state.

[0128] In a possible implementation manner, the parameter information of the vehicle includes: external dimension parameter information of the vehicle body relative to the positioning device;

[0129] The determination module 602 is further configured to determine the attribute information of each map grid based on the following method:

[0130] Based on the positioning data collected by the positioning device and the external dimension parameter information, determine the passage area information passed by the vehicle during driving;

[0131] Based on the passable area information and the position information of each pre-divided map grid, the attribute information of each map grid is determined; wherein the state information of the map grid located in the passable area is a passable state.

[0132] In a possible implementation manner, the determination module 602, when determining the passage area information passed by the vehicle during driving based on the positioning data collected by the positioning device and the external dimension parameter information, is used to:

[0133] Determine the position and posture data of the positioning device in the world coordinate system based on the positioning data collected by the positioning device;

[0134] The passage area information is determined based on the position and posture data of the positioning device and the external dimension parameter information.

[0135] In a possible implementation manner, the attribute information of the map grid further includes height information of the map grid relative to the sea level; the parameter information of the vehicle includes: external dimension parameter information of the vehicle body relative to the positioning device;

[0136] The determination module 602 is further configured to determine the attribute information of each map grid based on the following method:

[0137] Based on the positioning data and the external dimension parameter information, the height information of each pre-divided map grid relative to the sea level is determined.

[0138] In a possible implementation manner, the external dimension parameter information includes vertex coordinates of a rectangular frame surrounding the body of the vehicle in a coordinate system with the positioning device as a coordinate origin;

[0139] The determination module 602, when determining the height information of each pre-divided map grid relative to the sea level based on the positioning data and the external dimension parameter information, is used to:

[0140] A bilinear interpolation operation is performed based on the altitude information in the positioning data and the vertex coordinates to obtain the altitude information of the map grid relative to the sea level.

[0141] In a possible implementation manner, the parameter information of the vehicle includes: relative position information between the positioning device and the radar device;

[0142] The determination module 602, when determining the point cloud data corresponding to the static object in the point cloud data to be identified according to the attribute information of each map grid, is used to:

[0143] According to the relative position information, coordinate transformation processing is performed on the point cloud data to be identified to obtain transformed point cloud data;

[0144] Based on the attribute information of each map grid and the position information corresponding to each map grid, the point cloud data corresponding to the static object in the converted point cloud data is determined.

[0145] In a possible implementation manner, the determination module 602, when performing coordinate transformation processing on the point cloud data to be identified according to the relative position information to obtain transformed point cloud data, is used to:

[0146] Determining position data of a radar device on the vehicle based on positioning data of a positioning device on the vehicle and the relative position information;

[0147] Based on the position and posture data of the radar device, coordinate transformation processing is performed on the point cloud data to be identified to obtain transformed point cloud data.

[0148] In a possible implementation, the determination module 602, when determining the point cloud data corresponding to the static object in the converted point cloud data based on the determined attribute information of each map grid and the position information corresponding to each map grid, is used to:

[0149] Based on the coordinate information of the radar scanning points in the converted point cloud data and the position information corresponding to each map grid, determining the map grid into which each radar scanning point falls;

[0150] Determine the radar scanning point that falls into the map grid and is in an inaccessible state as the first radar scanning point;

[0151] Determine as a second radar scanning point a radar scanning point in which a map grid falls into a passable state and a difference between a corresponding height and a height of the map grid relative to the sea level that is less than a set threshold;

[0152] The first radar scanning point and the second radar scanning point are determined as point cloud data corresponding to static objects in the point cloud data to be identified.

[0153] In a possible implementation, the device further includes: a construction module 603, which is used to construct a map corresponding to the first area based on the point cloud data corresponding to the static object after determining the point cloud data corresponding to the static object in the point cloud data to be identified.

[0154] For descriptions of the processing flow of each module in the device and the interaction flow between each module, reference may be made to the relevant descriptions in the above method embodiment, which will not be described in detail here.

[0155] Based on the same technical concept, the embodiment of the present application also provides a computer device. Figure 7 As shown, it is a schematic diagram of the structure of a computer device 700 provided in an embodiment of the present application, including a processor 701, a memory 702, and a bus 703. Among them, the memory 702 is used to store execution instructions, including a memory 7021 and an external memory 7022; the memory 7021 here is also called an internal memory, which is used to temporarily store the operation data in the processor 701, and the data exchanged with the external memory 7022 such as a hard disk. The processor 701 exchanges data with the external memory 7022 through the memory 7021. When the computer device 700 is running, the processor 701 communicates with the memory 702 through the bus 703, so that the processor 701 executes the following instructions:

[0156] Acquire point cloud data to be identified, where the point cloud data to be identified is obtained by a radar device deployed on the vehicle scanning a first area;

[0157] Determining point cloud data corresponding to a static object in the point cloud data to be identified according to the attribute information of each map grid;

[0158] Among them, each map grid is obtained by dividing the first area, and the attribute information of each map grid is determined according to the parameter information of the vehicle and the positioning data collected by the positioning device deployed on the vehicle when the vehicle is traveling in the first area; the attribute information of the map grid includes the state information of the map grid, and the state information includes a passable state and an impassable state.

[0159] The present disclosure also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the point cloud data screening method described in the above method embodiment are executed. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0160] The computer program product of the point cloud data screening method provided in the embodiment of the present disclosure includes a computer-readable storage medium storing program code, and the instructions included in the program code can be used to execute the steps of the point cloud data screening method described in the above method embodiment. For details, please refer to the above method embodiment, which will not be repeated here.

[0161] The present disclosure also provides a computer program, which implements any one of the methods of the aforementioned embodiments when executed by a processor. The computer program product can be implemented in hardware, software, or a combination thereof. In an optional embodiment, the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK), etc.

[0162] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, 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 communication interfaces, and the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0163] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0164] In addition, each functional unit in each embodiment of the present disclosure 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.

[0165] 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 non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. 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 (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0166] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed in the present disclosure, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A point cloud data screening method, characterized in that: include: Acquire point cloud data to be identified, where the point cloud data to be identified is obtained by a radar device deployed on the vehicle scanning a first area; Determining point cloud data corresponding to a static object in the point cloud data to be identified according to the attribute information of each map grid; Wherein, each map grid is obtained by dividing the first area, and the attribute information of each map grid is determined according to the parameter information of the vehicle and the positioning data collected by the positioning device deployed on the vehicle during the driving of the vehicle in the first area; the attribute information of the map grid includes the state information of the map grid, and the state information includes the passable state and the impassable state, and the parameter information of the vehicle includes: the relative position information between the positioning device and the radar device; The step of determining the point cloud data corresponding to the static object in the point cloud data to be identified according to the attribute information of each map grid comprises: Determining position data of a radar device on the vehicle based on positioning data of a positioning device on the vehicle and the relative position information; Based on the position and posture data of the radar device, coordinate transformation processing is performed on the point cloud data to be identified to obtain transformed point cloud data; Based on the coordinate information of the radar scanning points in the converted point cloud data and the position information corresponding to each map grid, determining the map grid into which each radar scanning point falls; Determine the radar scanning point that falls into the map grid and is in an inaccessible state as the first radar scanning point; Determine as a second radar scanning point a radar scanning point in which a map grid falls into a passable state and a difference between a corresponding height and a height of the map grid relative to the sea level that is less than a set threshold; The first radar scanning point and the second radar scanning point are determined as point cloud data corresponding to static objects in the point cloud data to be identified.

2. The method according to claim 1, characterized in that The parameter information of the vehicle includes: external dimension parameter information of the vehicle body relative to the positioning device; The method further includes determining the attribute information of each map grid based on the following method: Based on the positioning data collected by the positioning device and the external dimension parameter information, determine the passage area information passed by the vehicle during driving; Based on the passable area information and the position information of each pre-divided map grid, the attribute information of each map grid is determined; wherein the state information of the map grid located in the passable area is a passable state.

3. The method according to claim 2, characterized in that The determining of the passage area information passed by the vehicle during driving based on the positioning data collected by the positioning device and the external dimension parameter information includes: Determine the position and posture data of the positioning device in the world coordinate system based on the positioning data collected by the positioning device; The passage area information is determined based on the position and posture data of the positioning device and the external dimension parameter information.

4. The method according to claim 1, characterized in that: The attribute information of the map grid also includes the height information of the map grid relative to the sea level; the parameter information of the vehicle includes: the external dimension parameter information of the vehicle body relative to the positioning device; The method further includes determining the attribute information of each map grid based on the following method: Based on the positioning data and the external dimension parameter information, the height information of each pre-divided map grid relative to the sea level is determined.

5. The method according to claim 4, characterized in that The external dimension parameter information includes vertex coordinates of a rectangular frame surrounding the body of the vehicle in a coordinate system with the positioning device as the coordinate origin; The determining, based on the positioning data and the external dimension parameter information, the height information of each pre-divided map grid relative to the sea level comprises: A bilinear interpolation operation is performed based on the altitude information in the positioning data and the vertex coordinates to obtain the altitude information of the map grid relative to the sea level.

6. The method according to any one of claims 1 to 5, characterized in that: After determining the point cloud data corresponding to the static object in the point cloud data to be identified, the method further includes: A map corresponding to the first area is constructed based on the point cloud data corresponding to the static object.

7. A point cloud data screening device, characterized in that: include: An acquisition module, used for acquiring point cloud data to be identified, wherein the point cloud data to be identified is obtained by a radar device deployed on the vehicle scanning the first area; A determination module, used to determine the point cloud data corresponding to the static object in the point cloud data to be identified according to the attribute information of each map grid; Wherein, each map grid is obtained by dividing the first area, and the attribute information of each map grid is determined according to the parameter information of the vehicle and the positioning data collected by the positioning device deployed on the vehicle when the vehicle is traveling in the first area; the attribute information of the map grid includes the state information of the map grid, and the state information includes the passable state and the impassable state. The parameter information of the vehicle includes: the relative position information between the positioning device and the radar device The determining module is used to: Determining position data of a radar device on the vehicle based on positioning data of a positioning device on the vehicle and the relative position information; Based on the position and posture data of the radar device, coordinate transformation processing is performed on the point cloud data to be identified to obtain transformed point cloud data; Based on the coordinate information of the radar scanning points in the converted point cloud data and the position information corresponding to each map grid, determining the map grid into which each radar scanning point falls; Determine the radar scanning point that falls into the map grid and is in an inaccessible state as the first radar scanning point; Determine as a second radar scanning point a radar scanning point in which a map grid falls into a passable state and a difference between a corresponding height and a height of the map grid relative to the sea level that is less than a set threshold; The first radar scanning point and the second radar scanning point are determined as point cloud data corresponding to static objects in the point cloud data to be identified.

8. A computer device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the point cloud data screening method as described in any one of claims 1 to 6 are performed.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the point cloud data screening method according to any one of claims 1 to 6 are executed.

Images