Point cloud position processing method and device, vehicle and storage medium

Abstract

The invention provides a point cloud position processing method and device, a vehicle and a storage medium, and the method comprises the steps: obtaining the detection positions of a plurality of point clouds detected by a laser radar at a first moment of a target scanning period, and the vehicle speed of the vehicle, and carrying out the position compensation of the detection positions of the point clouds at the first moment according to the vehicle speed, obtaining a first position of the point clouds at a second moment, obtaining speed information of an object and information of a detection frame sensed in a historical scanning period, and performing position compensation on the first position of the plurality of point clouds at the second moment according to the speed information of the object and the information of the detection frame to obtain a second position of the second moment; through the sensed information and speed information of the detection frame of the object, the first position of the point cloud at the second moment obtained through self-vehicle motion compensation is subjected to position compensation again to obtain the second position at the second moment, the distortion influence of the self-vehicle motion and the object motion on the collected point cloud is fully considered, and the accuracy of the point cloud is improved. And the distortion of the point cloud is reduced through position compensation.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a method, device, vehicle and storage medium for processing point cloud positions. Background Art

[0002] The detection of objects (obstacles) in the environment is gradually being applied to more and more fields, such as robotics, or artificial intelligence fields such as autonomous vehicles. In related technologies, the perception of objects in a periodic environment is usually based on laser radar. However, when the vehicle is driving, obstacles may also be moving, resulting in distortion of the point cloud data detected by the laser radar. Therefore, how to reduce the distortion of the measured point cloud is a technical problem that needs to be solved. Summary of the invention

[0003] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0004] To this end, the present application proposes a point cloud position processing method, device, vehicle and storage medium, which compensates the position of the collected point cloud to eliminate the distortion of the collected point cloud caused by the movement of obstacles.

[0005] In one aspect, an embodiment of the present application provides a method for processing a point cloud position, including:

[0006] Obtain the detection positions of multiple point clouds detected by the laser radar at the first moment of the target scanning cycle, as well as the speed of the vehicle;

[0007] Performing position compensation on the detected position of the point cloud at the first moment according to the vehicle speed to obtain a first position of the point cloud at a second moment;

[0008] Acquire detection frame information and speed information of the object sensed in the historical scanning cycle before the target scanning cycle;

[0009] According to the information of the detection frame and the speed information of the object, position compensation is performed on the first positions of the multiple point clouds at the second moment to obtain the second positions of the multiple point clouds at the second moment.

[0010] Another aspect of the present application provides a point cloud position processing device, including:

[0011] A first acquisition module is used to acquire the detection positions of multiple point clouds detected by the laser radar at the first moment of the target scanning cycle, and the speed of the vehicle;

[0012] A first compensation module, configured to perform position compensation on a detection position of the point cloud at the first moment according to the vehicle speed, so as to obtain a first position of the point cloud at a second moment;

[0013] A second acquisition module, used for acquiring the detection frame information and speed information of the object sensed in the historical scanning cycle before the target scanning cycle;

[0014] The second compensation module is used to perform position compensation on the first positions of the multiple point clouds at the second moment according to the detection frame information and speed information of the object, so as to obtain the second positions of the multiple point clouds at the second moment.

[0015] Another aspect of the present application provides a vehicle, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in the above aspect is implemented.

[0016] Another aspect of the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method described in the aforementioned aspect is implemented.

[0017] Another aspect of the present application provides a computer program product on which a computer program is stored. When the program is executed by a processor, the method described in the above aspect is implemented.

[0018] The point cloud position processing method, device, vehicle and storage medium proposed in the present application obtain the detection positions of multiple point clouds detected by the laser radar at the first moment of the target scanning cycle and the speed of the vehicle, perform position compensation on the detection positions of the point clouds at the first moment according to the speed, and obtain the first position of the point cloud at the second moment, obtain the detection frame information and the speed information of the object perceived in the historical scanning cycle before the target scanning cycle, perform position compensation on the first positions of the multiple point clouds at the second moment according to the detection frame information and the speed information of the object, and obtain the second positions of the multiple point clouds at the second moment, and perform position compensation again on the first position of the point cloud at the second moment obtained based on the self-vehicle motion compensation through the perceived detection frame information and speed information of the objects around the vehicle to convert it to the second moment, and obtain the second position at the second moment, which fully considers the distortion effect of the self-vehicle motion and the object motion on the collected point cloud data, reduces the distortion of the point cloud through position compensation, and improves the accuracy of the collected point cloud data.

[0019] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0021] Figure 1 A schematic diagram of a process for processing a point cloud position provided in an embodiment of the present application;

[0022] Figure 2 A schematic diagram of a flow chart of another method for processing point cloud positions provided in an embodiment of the present application;

[0023] Figure 3 A schematic diagram of a flow chart of another method for processing point cloud positions provided in an embodiment of the present application;

[0024] Figure 4 A schematic diagram of the structure of a point cloud position processing device provided in an embodiment of the present application;

[0025] Figure 5 It is a structural schematic diagram of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0027] The following describes the point cloud position processing method, device, vehicle and storage medium of the embodiments of the present application with reference to the accompanying drawings.

[0028] Figure 1 A flowchart of a method for processing point cloud positions provided in an embodiment of the present application.

[0029] The execution body of the point cloud position processing method in the embodiment of the present application is a point cloud position processing device, which can be set in an on-board device of a vehicle and is not limited in this embodiment.

[0030] like Figure 1 As shown, the method may include the following steps:

[0031] Step 101, obtaining the detection positions of multiple point clouds detected by the laser radar at the first moment of the target scanning cycle, and the speed of the vehicle.

[0032] The target scanning cycle is one of the multiple scanning cycles of the laser radar. One scanning cycle is a frame collected by the laser radar. One frame of data is used for target detection, that is, detecting the position and size of the target. The target scanning cycle contains multiple moments of capturing point clouds, and the first moment is any one of them.

[0033] In one implementation of the embodiment of the present application, the laser radar includes multiple laser emitting and receiving devices, which can form a laser beam. By controlling the rotation of the laser radar, the corresponding laser beam can be obtained at each moment in the target scanning cycle, thereby completing the scanning of a target scanning cycle. The point cloud is composed of laser reflection points, and the information of the laser reflection points includes the three-dimensional coordinates of each point cloud, and the three-dimensional coordinates of the point cloud are the detection position of the point cloud.

[0034] The vehicle is a vehicle installed with the laser radar, and the speed of the vehicle at the first moment can be determined through the dead reckoning (DR) positioning technology.

[0035] Step 102 : Compensate the detected position of the point cloud at the first moment according to the vehicle speed to obtain the first position of the point cloud at the second moment.

[0036] In an embodiment of the present application, motion compensation is performed on the detection position of the point cloud detected at the first moment according to the speed of the vehicle, so as to compensate the detection position of the point cloud at the first moment to the second moment, that is, to obtain the first position of each point cloud at the second moment, so as to reduce the distortion of the point cloud measurement caused by the different positions of the point cloud corresponding to the detection object following the vehicle at different moments when the vehicle moves at high speed.

[0037] Step 103: Acquire the detection frame information of the object sensed in the historical scanning cycle before the target scanning cycle and the speed information of the object.

[0038] Among them, the historical scanning cycle is the cycle before the target scanning cycle, for example, the historical scanning cycle is the previous cycle adjacent to the target scanning cycle. According to the point cloud data collected in the previous cycle, the objects around the vehicle can be perceived. The objects can be indicated by the detection box surrounding the objects. The objects include obstacles, and the obstacles include other vehicles, lamp poles and other ground elements.

[0039] The information of the object's detection frame, including the position and size of the detection frame, where the position can be the center of the detection frame or the positions of the four vertices of the detection frame. The size is the length and width of the detection frame. The speed information, including speed and acceleration, can indicate whether the object is a stationary object or a moving object.

[0040] Step 104 , based on the information of the detection frame of the object and the speed information of the object, position compensation is performed on the first positions of the plurality of point clouds at the second moment to obtain the second positions of the plurality of point clouds at the second moment.

[0041] The second moment is a set moment in the target scanning cycle, for example, the second moment is the first acquisition moment in the target scanning cycle, or the second moment is the last acquisition moment in the target scanning cycle.

[0042] In an embodiment of the present application, during the operation of the vehicle, the objects around the vehicle are not necessarily stationary, and the objects may be in motion. In this case, the movement of the objects will also cause distortion of the point cloud collected by the lidar, and this distortion cannot be eliminated by motion compensation of the vehicle's own motion. Therefore, it is necessary to perform position compensation on the first position of each point cloud at the first moment to obtain the second position of each point cloud at the second moment. As an implementation method, according to the information of the detection frame of each object, the target point cloud in each detection frame is determined from the multiple point clouds detected at the first moment. For each object, according to the speed information of the object, the target point cloud in the detection frame of the object is position compensated at the first position at the second moment to obtain the target point cloud in the detection frame of the object at the second moment, thereby reducing the point cloud distortion caused by the movement of obstacles. Furthermore, the position and size of the object are detected based on the processed point cloud data, which can improve the detection accuracy.

[0043] It should be understood that each point cloud detected at the first moment usually belongs to a certain object. According to the information of the detection frame of each object and the position of each point cloud, the point cloud in each detection frame can be determined. For the point cloud that does not belong to any detection frame, it is regarded as noise data, and the position compensation is not performed based on the speed information of any detection frame. Among them, different objects may be moving objects or stationary objects. According to the speed information of each object, the point cloud in each detection frame is position compensated again. In the case where the object is a stationary object, the speed information of the stationary object is zero, and the position compensation value of the point cloud in the detection frame is also zero, that is, no position compensation is required again. In the case where the object is a moving object, based on the speed of the moving object, the position of the point cloud in the detection frame is compensated again to convert it to the position at the same set moment, thereby improving the accuracy of the position compensation of each point cloud.

[0044] It should be noted that the processing method of the detection position of the point cloud collected at other times in the target scanning cycle is the same as the processing method of the detection position of the point cloud collected at the first time, and is not described one by one in this embodiment. It is realized that the point clouds collected at each time in the target scanning cycle are converted to the same time in the target cycle, that is, the position corresponding to the second time, through position compensation, thereby avoiding the distortion effect between the point clouds collected at different times.

[0045] In the point cloud position processing method of the embodiment of the present application, the detection positions of multiple point clouds detected by the laser radar at the first moment of the target scanning cycle and the speed of the vehicle are obtained, and the detection positions of the point clouds at the first moment are position compensated according to the speed to obtain the first position of the point cloud at the second moment, and the detection frame information of the object perceived in the historical scanning cycle before the target scanning cycle and the speed information of the object are obtained. According to the detection frame information and the speed information of the object, the first positions of the multiple point clouds at the second moment are position compensated to obtain the second positions of the multiple point clouds at the second moment, and the detection frame information and speed information of the objects around the vehicle are perceived. The first position of the point cloud at the second moment obtained based on the self-vehicle motion compensation is position compensated again to convert it to the second moment to obtain the second position at the second moment, which fully considers the distortion effect of the self-vehicle motion and the object motion on the collected point cloud data, reduces the distortion of the point cloud through position compensation, and improves the accuracy of the collected point cloud data.

[0046] Based on the above embodiments, Figure 2 A flowchart of another method for processing point cloud positions provided in an embodiment of the present application is shown as follows: Figure 2 As shown, the method comprises the following steps:

[0047] Step 201, obtaining the detection positions of multiple point clouds detected by the laser radar at the first moment of the target scanning cycle, and the speed of the vehicle.

[0048] Among them, step 201 can refer to the explanation in the above-mentioned embodiment, and the principle is the same, which will not be repeated here.

[0049] Step 202, determining the displacement of the vehicle between the second moment and the first moment according to the time difference between the first moment and the second moment and the vehicle speed.

[0050] Step 203 , compensating the detection position of each point cloud detected at the first moment according to the displacement of the vehicle to obtain the first position at the second moment.

[0051] As an example, taking a 128-line laser radar as an example, during a target scanning cycle of the laser radar scanning, the data of each point cloud line beam will be returned at different times according to the rotation speed of the radar device. This data includes the coordinates of the laser points received on this point cloud line beam. For any moment, that is, the data on the point cloud line beam at the first moment, the second moment is the moment when the laser radar starts scanning. Through DR positioning technology, the speed of the vehicle at this time is obtained, and the detection position of the point cloud collected at the first moment is converted to the second moment, that is, the position at the moment when the laser radar starts scanning, which satisfies the following formula:

[0052] The first position at the second moment = the detected position at the first moment - (first moment - second moment) * vehicle speed;

[0053] The positions of all point cloud data within the target scanning cycle of the laser radar are uniformly compensated to the start time of the laser radar scanning, completing the first motion compensation.

[0054] Step 204 : obtaining information of a detection frame of an object sensed in a historical scanning cycle before the target scanning cycle and information of the speed of the object.

[0055] Step 205 , based on the information of the detection frame of the object and the speed information of the object, position compensation is performed on the first positions of the multiple point clouds at the second moment to obtain the second positions of the multiple point clouds at the second moment.

[0056] Among them, step 204 and step 205 can refer to the explanation in the above-mentioned embodiment, and the principles are the same, which will not be repeated here.

[0057] In the point cloud position processing method of the embodiment of the present application, the detection positions of multiple point clouds detected by the laser radar at the first moment of the target scanning cycle and the speed of the vehicle are obtained, and the detection positions of the point clouds at the first moment are position compensated according to the speed to obtain the first position of the point cloud at the second moment, and the detection frame information and speed information of the object perceived in the historical scanning cycle before the target scanning cycle are obtained. According to the detection frame information and the speed information of the object, the first positions of the multiple point clouds at the second moment are position compensated to obtain the second positions of the multiple point clouds at the second moment, and the point cloud obtained based on the self-vehicle motion compensation at the first position at the second moment by the information of the detection frame and the speed information of the object around the vehicle is position compensated again to convert to the second moment, and obtain the second position at the second moment, which fully considers the distortion effect of the self-vehicle motion and the object motion on the collected point cloud data, reduces the distortion of the point cloud through position compensation, reduces the influence of the obstacle motion on the detection performance, and the optimization of the current moment will further optimize the next moment, thereby improving the accuracy of the collected point cloud data, and then, the position and size of the target are detected based on the processed point cloud data, which can improve the detection accuracy.

[0058] Based on the above embodiments, the present application provides another method for processing point cloud positions. Figure 3 A flowchart of another method for processing point cloud positions provided in an embodiment of the present application is shown as follows: Figure 3 As shown, the method comprises the following steps:

[0059] Step 301, obtaining the detection positions of multiple point clouds detected by the laser radar at the first moment of the target scanning cycle, and the speed of the vehicle.

[0060] Step 302, determining the displacement of the vehicle between the second moment and the first moment according to the time difference between the first moment and the second moment and the vehicle speed.

[0061] Step 303 , compensating the detection position of each point cloud detected at the first moment according to the displacement of the vehicle to obtain the first position at the second moment.

[0062] Step 304: Acquire information of detection frames of multiple objects sensed in a historical scanning cycle before the target scanning cycle and information on the speed of the objects.

[0063] Among them, steps 301 to 304 can refer to the explanations in the aforementioned embodiments, and the principles are the same, so they will not be repeated here.

[0064] Step 305 , based on the information of the detection frames of the respective objects, determine the target point cloud in the detection frames of the respective objects from the plurality of point clouds detected at the first moment.

[0065] The information of the detection frame includes the size and position of the detection frame, and the position may be the center point position of the detection frame.

[0066] In an embodiment of the present application, according to the position and size of the detection frame included in the information of each detection frame, the position of each detection frame is converted to the first moment, and the position of each detection frame at the first moment is obtained, so that the position of each detected object is mapped to the same moment. Then, according to the position of each detection frame at the first moment, the size of each detection frame, and the detection position of multiple point clouds at the first moment, the target point cloud in each detection frame at the first moment is determined. As an implementation method, according to the position of each detection frame at the first moment and the size of each detection frame, the coordinates of all positions in the area corresponding to each detection frame can be determined, that is, the coordinates of each position point included in the area enclosed by each detection frame. For each detection frame, the coordinates corresponding to the detection positions of multiple point clouds at the first moment are compared with the coordinates of each position point in the area enclosed by the detection frame. If the coordinates corresponding to the detection position of a point cloud at the first moment are in the area enclosed by the detection frame, it is determined that the detection position of the point cloud at the first moment is in the detection frame. Similarly, it can be determined whether all point clouds are in the detection frame. Similarly, the target point cloud included in each detection frame can also be determined.

[0067] Step 306 , for each object, based on the speed information of the object, position compensation is performed on the first position of the target point cloud in the detection frame of the object at the second moment to obtain the second position of the target point cloud in the detection frame of the object at the second moment.

[0068] In an embodiment of the present application, for each object, the position change amount corresponding to the target point cloud in the detection frame of the object between the first moment and the second moment is determined based on the speed and acceleration of the object included in the speed information of the object, and the time difference between the first moment and the second moment. Based on the position change amount corresponding to the target point cloud in the detection frame of the object, position compensation is performed on the first position of the target point cloud in the detection frame of the object at the second moment to obtain the second position of the target point cloud in the detection frame of the object at the second moment. This realizes the conversion of the first position of the target point cloud in the detection frame of the object at the first moment to the second moment to obtain the second position at the second moment. This can achieve the unified conversion of all point clouds to the same moment, thereby avoiding the distortion of point clouds collected at different moments due to the movement of the object.

[0069] As an example, the second moment is the moment when the laser radar starts scanning. For one of the detection frames, the second position of the target point cloud in the detection frame at the second moment satisfies the following formula:

[0070]

[0071] in, is the second position at the second moment, is the first position at the first moment, V 1 is the speed of the object corresponding to the detection box at the first moment, a 1 is the acceleration of the object corresponding to the detection box at the first moment, t 1 is the first moment, t 2 For the second moment.

[0072] Among them, based on the point cloud data of a target scanning cycle, target detection can be performed, that is, the position and size of the object corresponding to the point cloud data in the target scanning cycle are detected, thereby improving the accuracy of object detection.

[0073] In the point cloud position processing method of the embodiment of the present application, the detection frame information of the objects around the vehicle and the speed information of the objects are sensed, and the point cloud obtained based on the vehicle motion compensation is at the first position at the second moment, and the position compensation is performed again to convert it to the second moment to obtain the second position at the second moment. The distortion effect of the vehicle motion and the object motion on the collected point cloud data is fully considered. The distortion of the point clouds collected at different moments due to the vehicle motion and the object motion is reduced through position compensation, and the accuracy of the collected point cloud data is improved, thereby improving the accuracy of subsequent target detection based on the point cloud data of a target scanning cycle.

[0074] In order to implement the above embodiment, the embodiment of the present application also proposes a point cloud position processing device.

[0075] Figure 4 A schematic diagram of the structure of a point cloud position processing device provided in an embodiment of the present application.

[0076] like Figure 4 As shown, the device may include:

[0077] The first acquisition module 41 is used to execute acquisition of the detection positions of multiple point clouds detected by the laser radar at the first moment of the target scanning cycle, and the vehicle speed.

[0078] The first compensation module 42 is used to perform position compensation on the detected position of the point cloud at the first moment according to the vehicle speed to obtain a first position of the point cloud at a second moment.

[0079] The second acquisition module 43 is used to acquire the detection frame information of the object sensed in the historical scanning cycle before the target scanning cycle and the speed information of the object.

[0080] The second compensation module 44 is used to perform position compensation on the first positions of the multiple point clouds at the second moment according to the information of the detection frame of the object and the speed information of the object, so as to obtain the second positions of the multiple point clouds at the second moment.

[0081] Further, in an implementation of the embodiment of the present application, the object is multiple, and the second compensation module 44 is further used to execute:

[0082] Determine, according to the information of the detection frames of the respective objects, a target point cloud in the detection frames of the respective objects from the plurality of point clouds detected at the first moment;

[0083] For each of the objects, position compensation is performed on the first position of the target point cloud in the detection frame of the object at the second moment according to the speed information of the object, so as to obtain the second position of the target point cloud in the detection frame of the object at the second moment.

[0084] In an implementation of the embodiment of the present application, the second compensation module 44 is further configured to execute:

[0085] According to the position and size of the detection frame included in the information of the detection frame of each object, convert the position of the detection frame of each object to the first moment, so as to obtain the position of the detection frame of each object at the first moment;

[0086] According to the position of the detection frame of each of the objects at the first moment, the size of the detection frame of each of the objects, and the detection positions of the multiple point clouds at the first moment, the target point cloud that is in the detection frame of each of the objects at the first moment is determined.

[0087] In an implementation of the embodiment of the present application, the second compensation module 44 is further configured to execute:

[0088] Determine, according to the speed and acceleration included in the speed information of the object and the time difference between the first moment and the second moment, a position change amount corresponding to the target point cloud in the detection frame of the object between the first moment and the second moment;

[0089] According to the position change corresponding to the target point cloud in the detection frame of the object, position compensation is performed on the first position of the target point cloud in the detection frame of the object at the second moment to obtain the second position of the target point cloud in the detection frame of the object at the second moment.

[0090] In an implementation of the embodiment of the present application, the first compensation module 42 is further configured to execute:

[0091] Determine the displacement of the vehicle between the second moment and the first moment according to the time difference between the first moment and the second moment and the vehicle speed;

[0092] According to the displacement of the vehicle, the detection position of each of the point clouds detected at the first moment is compensated to obtain the first position at the second moment.

[0093] It should be noted that the above explanation of the method embodiment is also applicable to the device of this embodiment, and will not be repeated here.

[0094] In the point cloud position processing device of the embodiment of the present application, the detection positions of multiple point clouds detected by the laser radar at the first moment of the target scanning cycle and the speed of the vehicle are obtained, and the detection positions of the point clouds at the first moment are position compensated according to the speed to obtain the first position of the point cloud at the second moment, and the detection frame information of the object perceived in the historical scanning cycle before the target scanning cycle and the speed information of the object are obtained. According to the detection frame information and the speed information of the object, the first positions of the multiple point clouds at the second moment are position compensated to obtain the second positions of the multiple point clouds at the second moment, and the attribute information and speed information of the detection frame of the object around the vehicle are perceived. The first position of the point cloud at the second moment obtained based on the vehicle motion compensation is position compensated again to convert it to the second moment to obtain the second position at the second moment, and the distortion effect of the vehicle motion and the object motion on the collected point cloud data is fully considered, and the distortion of the point cloud is reduced by position compensation, thereby improving the accuracy of the collected point cloud data.

[0095] In order to implement the above embodiments, the present application also proposes a vehicle, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in the above method embodiments is implemented.

[0096] In order to implement the above embodiments, the present application also proposes a non-temporary computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method described in the above method embodiments is implemented.

[0097] In order to implement the above embodiments, the present application also proposes a computer program product on which a computer program is stored. When the computer program is executed by a processor, the method described in the above method embodiments is implemented.

[0098] Figure 5 5 is a schematic diagram of a vehicle structure provided by an embodiment of the present application. For example, vehicle 500 may be a hybrid vehicle, or a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicles. Vehicle 500 may be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.

[0099] Reference Figure 5 , the vehicle 500 may include various subsystems, for example, an infotainment system 510, a perception system 520, a decision control system 530, a drive system 540, and a computing platform 550. The vehicle 500 may also include more or fewer subsystems, and each subsystem may include multiple components. In addition, each subsystem and each component of the vehicle 500 may be interconnected by wire or wireless means.

[0100] In some embodiments, the infotainment system 510 may include a communication system, an entertainment system, and a navigation system, among others.

[0101] The perception system 520 may include several sensors for sensing information about the environment around the vehicle 500. For example, the perception system 520 may include a global positioning system (the global positioning system may be a GPS system, or a Beidou system or other positioning systems), an inertial measurement unit (IMU), a laser radar, a millimeter wave radar, an ultrasonic radar, and a camera.

[0102] The decision control system 530 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0103] The drive system 540 may include components that provide powered motion for the vehicle 500. In one embodiment, the drive system 540 may include an engine, an energy source, a transmission system, and wheels. The engine may be an internal combustion engine, an electric motor, an air compression engine, or a combination of one or more thereof. The engine is capable of converting energy provided by the energy source into mechanical energy.

[0104] Some or all functions of the vehicle 500 are controlled by a computing platform 550. The computing platform 550 may include at least one processor 551 and a memory 552, and the processor 551 may execute instructions 553 stored in the memory 552.

[0105] The processor 551 may be any conventional processor, such as a commercially available CPU. The processor may also include a graphics processor (Graphic Process Unit, GPU), a field programmable gate array (Field Programmable Gate Array, FPGA), a system on chip (System On Chip, SOC), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC) or a combination thereof.

[0106] The memory 552 may be implemented by any type of volatile or nonvolatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0107] In addition to instructions 553 , memory 552 may also store data, such as road maps, route information, vehicle location, direction, speed, etc. The data stored in memory 552 may be used by computing platform 550 .

[0108] In the embodiment of the present disclosure, the processor 551 may execute instruction 553 to complete all or part of the steps of the above method embodiment.

[0109] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0110] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0111] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0112] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0113] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0114] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0115] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0116] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for processing point cloud positions, characterized in that: include: Obtain the detection positions of multiple point clouds detected by the laser radar at the first moment of the target scanning cycle, as well as the speed of the vehicle; Performing position compensation on the detected position of the point cloud at the first moment according to the vehicle speed to obtain a first position of the point cloud at a second moment; Acquire information of a detection frame of an object sensed in a historical scanning cycle before the target scanning cycle and speed information of the object; According to the information of the detection frame of the object and the speed information of the object, position compensation is performed on the first positions of the multiple point clouds at the second moment to obtain the second positions of the multiple point clouds at the second moment.

2. The method according to claim 1, characterized in that There are multiple objects, and performing position compensation on the first positions of the multiple point clouds at the second moment according to the information of the detection frames of the objects and the speed information of the objects to obtain the second positions of the multiple point clouds at the second moment includes: Determine, according to the information of the detection frames of the respective objects, a target point cloud in the detection frames of the respective objects from the plurality of point clouds detected at the first moment; For each of the objects, position compensation is performed on the first position of the target point cloud in the detection frame of the object at the second moment according to the speed information of the object, so as to obtain the second position of the target point cloud in the detection frame of the object at the second moment.

3. The method according to claim 2, characterized in that The step of determining, according to the information of the detection frames of the objects, the target point cloud in the detection frames of the objects from the plurality of point clouds detected at the first moment, comprises: According to the position and size of the detection frame included in the information of the detection frame of each object, convert the position of the detection frame of each object to the first moment, so as to obtain the position of the detection frame of each object at the first moment; According to the position of the detection frame of each of the objects at the first moment, the size of the detection frame of each of the objects, and the detection position of the multiple point clouds at the first moment, the target point cloud in the detection frame of each of the objects at the first moment is determined.

4. The method according to claim 2, characterized in that According to the speed information of the object, position compensation is performed on a first position of a target point cloud in a detection frame of the object at a second moment to obtain a second position of the target point cloud in the detection frame of the object at the second moment, including: Determine, according to the speed and acceleration included in the speed information of the object and the time difference between the first moment and the second moment, a position change amount corresponding to the target point cloud in the detection frame of the object between the first moment and the second moment; According to the position change corresponding to the target point cloud in the detection frame of the object, position compensation is performed on the first position of the target point cloud in the detection frame of the object at the second moment to obtain the second position of the target point cloud in the detection frame of the object at the second moment.

5. The method according to claim 1, characterized in that The step of performing position compensation on the detected position of the point cloud at the first moment according to the vehicle speed to obtain the first position of the point cloud at the second moment includes: Determine the displacement of the vehicle between the second moment and the first moment according to the time difference between the first moment and the second moment and the vehicle speed; According to the displacement of the vehicle, the detection position of each of the point clouds detected at the first moment is compensated to obtain the first position at the second moment.

6. A point cloud position processing device, characterized in that: include: A first acquisition module is used to acquire the detection positions of multiple point clouds detected by the laser radar at the first moment of the target scanning cycle, and the speed of the vehicle; A first compensation module, configured to perform position compensation on a detection position of the point cloud at the first moment according to the vehicle speed, so as to obtain a first position of the point cloud at a second moment; A second acquisition module, configured to acquire attribute information and speed information of a detection frame of an object sensed in a historical scanning cycle before the target scanning cycle; The second compensation module is used to perform position compensation on the first positions of the multiple point clouds at the second moment according to the attribute information and speed information of the detection frame of the object, so as to obtain the second positions of the multiple point clouds at the second moment.

7. The device according to claim 6, characterized in that The object is multiple, and the second compensation module is further used to execute: Determine, according to the attribute information of each of the detection frames, a target point cloud in each of the detection frames from the plurality of point clouds detected at the first moment; For each of the detection frames, position compensation is performed on a first position of a target point cloud in the detection frame at a second moment according to speed information of the detection frame to obtain a second position of the target point cloud in the detection frame at the second moment.

8. The device according to claim 7, characterized in that The second compensation module is further used to execute: According to the position and size of the detection frame included in the attribute information of each detection frame, convert the position of each detection frame to the first moment to obtain the position of each detection frame at the first moment; According to the position of each detection frame at the first moment, the size of each detection frame and the detection position of the multiple point clouds at the first moment, the target point cloud in each detection frame at the first moment is determined.

9. A vehicle, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to: Implement the steps of the method according to any one of claims 1 to 5.

10. A non-transitory computer-readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of a mobile terminal, the mobile terminal is enabled to execute the steps of the method according to any one of claims 1 to 5.

Images