Sea surface scene-oriented unmanned ship point cloud data correction method

Abstract

The invention provides an unmanned ship point cloud data correction method for a sea surface scene, and the method comprises the steps: obtaining the original point cloud data and external parameter calibration data information of an unmanned ship in a motion state, the original point cloud data being the point cloud data collected in a time period of one frame of point cloud data of a laser radar, and the external parameter calibration data information being the point cloud data collected in the time period of one frame of point cloud data of the laser radar; acquiring auxiliary estimation correction information corresponding to the original point cloud data; wherein the auxiliary estimation correction information is IMU angular velocity information corresponding to the time period of one frame of point cloud data of the unmanned ship, and GPS information corresponding to the time period of one frame of point cloud data of the unmanned ship; based on the external parameter calibration data information and the auxiliary estimation correction information, performing correction processing on the original point cloud data to obtain corrected point cloud data; and performing noise reduction processing on the corrected point cloud data to obtain a clean point cloud. Therefore, an accurate and stable data source is provided for subsequent sensing tasks such as target detection and distance measurement depending on the point cloud information.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to the field of point cloud data processing. Background Art

[0002] As an active distance measurement device, laser radar measures the distance to the target object in real time by actively emitting laser beams, and has been widely used in the field of automobile autonomous driving. Based on the active distance measurement characteristics of laser radar, its application in the field of unmanned sea boats can provide data support for subsequent route planning, boat motion control and other tasks. Generally, scanning laser radars emit laser beams and rotate the laser transmitter 360 degrees at a uniform speed to detect objects in the surrounding environment. When the laser radar carrier moves, the laser echoes reflected by objects at different angles are received at different times, which will cause point cloud distortion. Therefore, in practical applications, point clouds need to be corrected. The motion correction methods of point clouds are mostly aimed at vehicle-mounted laser radars, and the specific adaptation situation is mainly flat roads, and vehicles rarely make large-scale turns in a short time due to road regulations and road planning restrictions. However, the sea environment is accompanied by waves, and the hull of a ship will move up and down irregularly with the waves during navigation; in the case of narrow waterways such as ships entering and leaving ports, large-scale turning maneuvers will be performed to avoid other ships or buoys. The above situation leads to the poor adaptability of general point cloud correction algorithms in the sea environment.

[0003] In particular, the climatic conditions of the sea environment are changeable, and rain, fog, etc. can easily lead to disordered point cloud noise. At the same time, sea clutter caused by the wakes of other ships is often encountered when entering and leaving the port. The sea clutter in the point cloud appears as a dense and irregular point cluster at the tail of the target ship, which will cause incorrect judgment and misclassification of the target ship's distance, thereby affecting safe navigation. Summary of the invention

[0004] In order to overcome the above technical defects, the present application provides a point cloud data correction method, storage medium and device.

[0005] To achieve the above objectives, this application is implemented according to the following technical solutions:

[0006] In a first aspect, the present application provides a method for correcting point cloud data.

[0007] In a second aspect, the present application provides a computer device, comprising a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by the processor to implement a method for correcting point cloud data as described in any one of the first aspects.

[0008] In a third aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by a processor to implement a method for correcting point cloud data as described in any one of the first aspects.

[0009] This application has the following beneficial effects:

[0010] In the present application, the original point cloud data scanned by the unmanned boat laser radar is corrected and denoised to remove the point cloud translation and directional motion distortion generated during the movement of the unmanned boat, the pitch and roll motion distortion caused by the up and down movement of the boat body with the waves, as well as the point cloud noise around objects caused by frequent climate changes on the sea surface and the sea clutter generated by the wake of ships, so as to obtain a clean point cloud, thereby providing an accurate and stable data source for subsequent perception tasks such as target detection and ranging that rely on point cloud information.

[0011] In addition to the above-described purposes, features and advantages, the present application also has other purposes, features and advantages. The present application will be further described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0013] Figure 1 It is a flow chart of the module components of the point cloud correction method of the present application.

[0014] Figure 2 It is a flow chart of a method for correcting point cloud data provided by the present application.

[0015] Figure 3 It is a schematic diagram of the network structure of the noise reduction module of this application. DETAILED DESCRIPTION

[0016] The embodiments of the present application are described in detail below with reference to the accompanying drawings; however, the present application can be implemented in many different ways as defined and covered by the claims.

[0017] The correction method of the point cloud data of the unmanned boat for the sea scene in this application is as follows: Figure 1 As shown, it is mainly achieved through the motion correction module and the noise reduction module, as follows:

[0018] The motion correction module obtains the original point cloud data obtained by the lidar scanning when the motion posture of the unmanned boat on the sea surface is complex and is accompanied by up and down pitch motion at all times. It then uses the IMU angular velocity information obtained by external parameter calibration to remove the motion distortion caused by angle changes. It then combines the GPS information to remove the translational motion distortion and obtains the corrected point cloud data. This correction process lays a solid foundation for subsequent point cloud denoising and subsequent perception applications.

[0019] The noise reduction module includes a sea clutter removal submodule and a denoising submodule. Since the corrected point cloud data also includes two sources of sea scene point cloud noise, such as weather changes and ship wakes, the point cloud attribute estimation network is used to identify the corrected point cloud data and remove the sea clutter. Then, the correction vector is estimated for the noise around the object, and the noise points are projected onto a clean surface to obtain a clean point cloud, which provides clean and accurate point cloud information for subsequent perception tasks such as target detection and ranging.

[0020] The following is a detailed description of the above correction process:

[0021] To solve the above mentioned technology, Figure 2 As shown, the present application proposes a method for correcting point cloud data, comprising:

[0022] Step S1: obtaining original point cloud data and external parameter calibration data information of the unmanned boat in motion, wherein the original point cloud data is point cloud data collected within a time period of one frame of point cloud data of the laser radar; the external parameter calibration data information includes the positional relationship between the calibrated IMU and the laser radar;

[0023] When the unmanned boat is moving, the laser radar installed on it will move with the movement of the unmanned boat. When the laser radar is working, it will scan and collect data at a certain frequency. The time period of one frame of point cloud data mentioned here is the time it takes for the laser radar to complete a complete scan and collect a set of point cloud data.

[0024] During the period when the unmanned boat is in motion, the laser radar continuously emits laser beams. When the laser beams hit the surface of surrounding objects (such as the water surface, other ships, shore scenery, etc.) and reflect back, the three-dimensional coordinates of the surface points of the objects can be calculated based on the laser round-trip time, emission angle and other information. Many such points constitute the original point cloud data of this frame. These original point cloud data can initially reflect the general situation of the environment around the unmanned boat during this specific time period, and provide basic data support for further analysis of the environment of the unmanned boat and path planning.

[0025] In addition to the laser radar, the unmanned boat will also be equipped with an inertial measurement unit (IMU), GPS and other sensors for external parameter calibration, and various types of information should be time-aligned. Therefore, the external parameter calibration data information includes the position relationship matrix from the calibrated IMU to the laser radar.

[0026] It should be noted that in the scenario where the unmanned boat needs to recalibrate the sensors, in order to avoid errors in subsequent corrections, the external parameter calibration data information needs to be corrected in time after each calibration of the sensors of the unmanned boat is completed.

[0027] Step S2: Acquire auxiliary estimation correction information corresponding to the original point cloud data; wherein the auxiliary estimation correction information includes IMU angular velocity information corresponding to a time period of one frame of point cloud data of the unmanned boat, and GPS information corresponding to a time period of one frame of point cloud data of the unmanned boat;

[0028] In this application, the correction of the original point cloud data is achieved by using auxiliary estimation correction information obtained by other sensors. The auxiliary estimation correction information generally includes IMU angular velocity information corresponding to the time period of one frame of point cloud data of the unmanned boat, and GPS information corresponding to the time period of one frame of point cloud data of the unmanned boat.

[0029] When the laser radar acquires the original point cloud data within a time period of one frame of point cloud data, the IMU simultaneously acquires the IMU angular velocity information corresponding to the time period of one frame of point cloud data of the unmanned boat, and the GPS simultaneously acquires the GPS information corresponding to the time period of one frame of point cloud data of the unmanned boat.

[0030] The IMU angular velocity information corresponding to the time period of one frame of point cloud data of the unmanned boat is the angular velocity information measured by the IMU within the time period of one frame of point cloud data of the unmanned boat. The angular velocity information reflects the rotation speed of the unmanned boat around each axis in this specific time period. When the unmanned boat moves on the water, it will rotate due to various factors such as its own steering and the influence of wind and waves. The angular velocity information of the IMU is a quantitative description of these rotational movements.

[0031] The GPS information corresponding to the time period of one frame of point cloud data of the unmanned boat is the information of the change of the position of the unmanned boat obtained by GPS within the time period of one frame of point cloud data. GPS information reflects the geographical location and related motion status data of the unmanned boat in this specific time period. It determines the position of the unmanned boat in the earth coordinate system by receiving satellite signals, including longitude, latitude and altitude, etc., and may also contain information such as the speed and heading of the unmanned boat.

[0032] Step S3: Based on the external parameter calibration data information and the auxiliary estimation correction information, the original point cloud data is corrected to obtain corrected point cloud data;

[0033] After obtaining the above-mentioned external parameter calibration data information and the auxiliary estimation correction information, the original point cloud data can be corrected to obtain the corrected point cloud data. This correction process is as follows: Figure 3 As shown, it is mainly completed in the motion correction module, and the correction process is described in detail below.

[0034] When the unmanned boat moves actively, it generates the distortion of the directional motion and the pitch and roll motion distortion caused by the up and down movement of the boat body with the waves. In the scenario where the sea surface is always accompanied by up and down pitch changes, the acceleration output by the IMU is very divergent and difficult to use. Here, the IMU angular velocity information and the external parameter calibration data information are used to remove the angle change motion distortion of the original point cloud data, so as to obtain the first corrected point cloud data. Therefore, it can be concluded that the first corrected point cloud data is the point cloud data after removing the angle change motion distortion of the original point cloud data. The original point cloud data and the point cloud data after removing the angle change distortion are described in detail below.

[0035] It should be noted that under normal circumstances, the frequency of the lidar (10Hz) is much lower than the frequency of the IMU (200Hz). The lidar frequency and the IMU frequency are not the same in different situations. This application adopts the frequency under normal circumstances.

[0036] The rotating scanning laser radar generates a point cloud by uniformly rotating the laser beam around. Specifically, for a point in the point cloud, the angle of the point relative to the initial position of the laser radar can be used to estimate the time from the current point to the final state of the laser radar. Specifically: for each point p in the original point cloud data i , determine each point p i At the initial position angle θ of the laser radar i ; Then according to the initial position angle θ i , determine the time difference between the current time of each point and the final state time of a frame of point cloud data time period, that is: (Unit is ms). Then we have:

[0037]

[0038] in t i The angle change at the moment t0 relative to the previous moment t0, They correspond to the angular velocity at the previous moment and the current moment respectively. The IMU data interval is That is 0.5ms, then IMU generates Data α i ,have:

[0039]

[0040] The calculation method described by formula (1)-(2) can be used to calculate the time difference ( time)IMU data α i Perform m-1 iterations and sum up, and we can get The IMU rotation angle α during the time period, that is, the IMU rotation angle α corresponding to the time difference, is transformed into the IMU rotation matrix corresponding to the time difference after matrix transformation.

[0041]

[0042] In the previous article, we obtained the position relationship matrix from the calibrated IMU to the lidar. After that, the inverse matrix of the position relationship can be obtained by inverse transformation.

[0043] Determine the IMU rotation matrix corresponding to the time difference And the position relationship matrix from the calibrated IMU to the lidar And the position relationship matrix from the calibrated IMU to the lidar The inverse matrix Then, according to the above three matrices, the rotation matrix of each point in the original point cloud data relative to the final state of the lidar is estimated As shown in formula (3).

[0044]

[0045] After determining each point in the original data, the rotation matrix relative to the final state of the laser radar is estimated, and then based on the rotation matrix estimate, the angle change motion distortion is removed for each point in the original point cloud data to obtain the first corrected point cloud data.

[0046] The first corrected point cloud data mentioned above only removes the angle change motion distortion of the original point cloud data. However, when the unmanned boat is moving, the point cloud data in the translation direction will also be distorted. Therefore, it is necessary to introduce the GPS information corresponding to the time period of one frame of point cloud data of the unmanned boat to remove the translation motion distortion of the first corrected point cloud data. The specific process is as follows:

[0047] The frequency of GPS information is generally 10Hz. In this application, the laser radar point cloud information is synchronized with the GPS information time, that is, the initial state and final state GPS coordinates can be obtained within a point cloud data time period. Specifically: Based on the GPS information, the GPS coordinate transformation information between the initial state and the final state of the laser radar within a frame of point cloud time period can be determined, and then the GPS coordinate transformation information can be calculated to obtain the first translation matrix between the initial state and the final state of the laser radar in the rectangular coordinate system. Converting the GPS coordinates to a unified rectangular coordinate system, we can obtain the radar initial state rectangular coordinates (x0, y0, z0) and final state coordinates (x1, y1, z1). The first translation matrix between the initial state and the final state is:

[0048]

[0049] The time interval of a point cloud cycle is short (100ms), so it can be approximately considered that the GPS coordinates change evenly within a point cloud cycle. i The time difference between the current moment and the end state moment of the point cloud cycle is (Unit: ms).

[0050] At this time, the first translation matrix and the time difference can be used to determine each point p i , the radar rectangular coordinates corresponding to the current moment. That is, point p i The radar rectangular coordinates at this moment are

[0051] After obtaining the radar rectangular coordinates, the second translation matrix from the current moment to the final state of the laser radar can be determined for each point in the first corrected point cloud data based on the radar rectangular coordinates and the first translation matrix. That is, the radar rectangular coordinates are (x i ,y i ,z i ), substituted into formula (4), we can get point p i The second translation matrix from time to the final state of the laser radar

[0052] After determining the second translation matrix After that, the translational motion distortion can be removed for each point in the first corrected point cloud data according to the second translation matrix to obtain second corrected point cloud data. The second corrected point cloud data is used as the corrected point cloud data, wherein the second corrected point cloud data is the point cloud data after removing the angle change motion distortion and the point cloud data after removing the translational motion distortion.

[0053] In summary, the current point coordinates can be converted to the coordinate system p in the final state of the laser radar by combining the rotation angle and translation vector of each point in the original point cloud data to the final state of the laser radar i-lidar , as shown in formula (5). All points in the original point cloud data can be corrected, and then the point cloud data after motion correction can be obtained. The correction process of the above point cloud data significantly improves the adaptability of the motion correction algorithm under different sea conditions. This process lays a solid foundation for point cloud denoising and subsequent perception applications.

[0054]

[0055] Step S4: performing noise reduction processing on the corrected point cloud data to obtain clean point cloud data.

[0056] The corrected point cloud data has completed the correction of the point cloud data caused by various distortions during the movement of the unmanned boat. Then, because the unmanned boat is moving on the sea surface, the sea surface environmental climate conditions are changeable, and rain, fog, etc. are easy to cause disordered point cloud noise; at the same time, in and out of the port, etc., sea clutter generated by the wake of other ships is often encountered. Therefore, it is also necessary to perform corresponding noise reduction processing on the above-mentioned point cloud noise and sea clutter to obtain clean point cloud data.

[0057] like Figure 3 As shown in the figure, the corrected point cloud data is processed using two submodules, namely the sea clutter removal submodule and the denoising submodule. Therefore, the specific composition of the above submodules is briefly described:

[0058] The input data format of the two submodules is the same (both are point clouds), so for the two submodule networks we divide the network into three processes. Figure 3 To ensure the pose and sequence stability of the point cloud and the efficiency of the network, the following are introduced: a point-by-point feature extraction model. In order to solve the pose stability problem of the point cloud, a four-element space transfer network is added to migrate the input point cloud data to a new pose state that is conducive to network learning; a feature fusion model. In order to solve the sequential stability problem, after obtaining the processed point-by-point feature vector, the network sums it in the dimension of the point and merges it into a feature vector. Regardless of the order of the input points, the commutative law of addition ensures the consistency of the merged feature vector; a regression module. In order to ensure the efficiency of the network, the fused feature vector is processed using several one-dimensional convolutional or fully connected layers to obtain the final result of the network output.

[0059] The feature extraction module and feature fusion module are the feature processing stage. The two submodules have the same structure in this stage. For the regression module, the output of the regression module in the sea clutter removal submodule network is point P' iis the probability of sea clutter is a specific value, and the structure is a number of one-dimensional convolutional layers; the output of the regression module in the denoising submodule network is a point Estimated offset d i , is a three-dimensional vector, and the structure is several fully connected layers.

[0060] Based on the above description of the component structure, the noise reduction processing of the corrected point cloud data is described in more detail:

[0061] The main sources of sea surface point cloud noise are sea clutter generated by other ship wakes and noise around objects caused by complex weather changes on the sea surface such as rain and fog. Sea clutter points are quite different from the other points and are generally located at the tail of the ship, so they can be represented and removed separately. The noise around objects is close to the surface points of the object and is caused by incorrect reflection of the laser beam caused by weather changes. It can be removed by relocating it to a suitable position on the edge of the object, while ensuring the accuracy and uniform distribution of the surface point cloud of the object. The noisy sea surface point cloud can be represented as:

[0062]

[0063] Where P' is the corrected point cloud data, each point is p' i ; O is the set of sea clutter points, each point is o j ;n i For each point p i The noise interference on the i are vectors of the same dimension.

[0064] That is to say, it is necessary to remove the sea clutter points from the corrected point cloud data to obtain the noisy point cloud data after the sea clutter points are removed. Figure 3 , the process of removing sea clutter is described in detail. The specific process is as follows:

[0065] like Figure 3 As shown in the upper network, the input is the corrected point cloud data P', that is, each point P' in the corrected point cloud output by the motion correction module i , the output is for each point P' in P' i is the probability of sea clutter Specifically, through the probability function g(Ρ' i ), to estimate each point p' in the corrected point cloud data i The probability of belonging to the sea clutter point is calculated, and then according to the set probability threshold, the probability of each point of the corrected point cloud data belonging to the sea clutter is compared with the probability threshold. If it exceeds the threshold, the point exceeding the probability threshold is regarded as a sea clutter point and filtered out. The point that does not exceed the probability threshold is regarded as a normal data point and retained, and finally the noise point cloud after the sea clutter points are removed is obtained. The specific value of the probability threshold can be set by yourself, and this article does not impose any specific restrictions on this.

[0066]

[0067] Among them, P' i for p' i The collection of points in the field. Indicates filtering out sea clutter points exceeding the threshold in P', such as Figure 3 Shown in the middle position.

[0068] After obtaining the noisy point cloud data after removing the sea clutter points, denoising is performed on the noisy point cloud data, such as Figure 3 This process is described in detail as shown below:

[0069] like Figure 3 The lower network shows that the input is the noisy point cloud after the sea clutter points are removed. Every point The output is Every point in Offset d i Specifically, the noise point cloud output by the sea clutter removal submodule Hit a point Estimated offset Then according to the noise point cloud data and the estimated offset d i , get a clean point cloud That is, the position of each point estimated by the denoising submodule network is right The same operation is performed on each point in the image to obtain a clean point cloud after noise reduction. As shown in formula (9), at this point, each point is placed at the correct position.

[0070]

[0071] in The clean point cloud estimated by the denoising module network, The set of sea clutter points estimated by the sea clutter removal submodule network, The noise point cloud after sea clutter points are removed can also be expressed as d i is the offset of each point learned by the denoising submodule network, d i Interference with noise i Related.

[0072] In summary, the present application corrects and reduces the noise of the original point cloud data scanned by the unmanned boat's laser radar, thereby removing the point cloud translation and directional motion distortion generated during the movement of the unmanned boat, the pitch and roll motion distortion caused by the up and down movement of the boat body with the waves, as well as the point cloud noise around objects caused by frequent climate changes on the sea surface and the sea clutter generated by the wake of ships, and obtains a clean point cloud, thereby providing an accurate and stable data source for subsequent perception tasks such as target detection and ranging that rely on point cloud information.

[0073] In some embodiments, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the point cloud data correction method provided in the first aspect.

[0074] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware implementation, the division between the functional blocks / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable storage medium, which may include a computer-readable storage medium (or a non-transitory medium) and a communication medium (or a temporary medium).

[0075] As is known to those of ordinary skill in the art, the term computer-readable storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules or other data). Computer-readable storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is known to those of ordinary skill in the art that communication media typically contain computer-readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and may include any information delivery medium.

[0076] Exemplarily, the computer-readable storage medium may be an internal storage unit of the network management device described in the foregoing embodiment, such as a hard disk or memory of the network management device. The computer-readable storage medium may also be an external storage device of the network management device, such as a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the network management device.

[0077] In some embodiments, a device is provided, including a processor and a memory, wherein the memory is used to store a computer program; the processor is used to execute the computer program and implement the point cloud data correction method provided in the first aspect of the present application when executing the computer program.

[0078] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0079] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for correcting point cloud data of an unmanned boat for sea scenes, characterized in that: include: Acquire original point cloud data and external parameter calibration data information of the unmanned boat in motion, wherein the original point cloud data is point cloud data collected within a time period of one frame of point cloud data of the laser radar; the external parameter calibration data information includes a position relationship matrix from the calibrated IMU to the laser radar; Acquire auxiliary estimation correction information corresponding to the original point cloud data; wherein the auxiliary estimation correction information is IMU angular velocity information corresponding to a time period of one frame of point cloud data of the unmanned boat, and GPS information corresponding to a time period of one frame of point cloud data of the unmanned boat; Based on the external parameter calibration data information and the auxiliary estimation correction information, the original point cloud data is corrected to obtain corrected point cloud data; The corrected point cloud data is subjected to noise reduction processing to obtain a clean point cloud.

2. The method according to claim 1, characterized in that: The correcting the original point cloud data based on the external parameter calibration data information and the auxiliary estimation correction information to obtain the corrected point cloud data includes: Using the IMU angular velocity information and the external parameter calibration data information, the original point cloud data is subjected to angle change motion distortion removal to obtain first corrected point cloud data, wherein the first corrected point cloud data is point cloud data obtained by removing angle change motion distortion from the original point cloud data; The GPS information is used to remove the translational motion distortion from the point cloud data after removing the angular change motion distortion to obtain second corrected point cloud data, and the second corrected point cloud data is used as the corrected point cloud data, wherein the second corrected point cloud data is the point cloud data after removing the angular change motion distortion and the translational motion distortion.

3. The method according to claim 2, characterized in that Using the IMU angular velocity information and the external parameter calibration data information, removing the angle change motion distortion from the original point cloud data to obtain the point cloud data after the angle change motion distortion is removed, including: Based on each point in the original point cloud data, determining an initial position angle of each point at the laser radar; Based on the initial position angle, determine the time difference between the current moment of each point and the final state moment of the time period of the one frame of point cloud data; Based on the time difference, determining the IMU angular velocity information corresponding to the time difference; Integrate the IMU angular velocity information to determine the IMU rotation angle corresponding to the time difference; Perform matrix changes based on the IMU rotation angle to determine the rotation matrix corresponding to the time difference; Based on the calibrated IMU-to-lidar position relationship matrix, determine an inverse matrix corresponding to the position relationship; Determine, based on the rotation matrix corresponding to the time difference, the position relationship matrix and the inverse matrix, a rotation matrix estimate of each point in the original point cloud data relative to the final state of the laser radar; Based on the rotation matrix estimation, for each point in the original point cloud data, the angle change motion distortion is removed to obtain first corrected point cloud data.

4. The method according to claim 3, characterized in that: The step of removing the translational motion distortion from the point cloud data after removing the angle change motion distortion based on the GPS information to obtain the second corrected point cloud data comprises: Based on the GPS information, determining GPS coordinate transformation information between an initial state and a final state of the laser radar within a time period of the one frame point cloud; Based on the GPS coordinate transformation information, determining a first translation matrix between an initial state and a final state of the laser radar in a rectangular coordinate system; Determine, based on the time difference and the first translation matrix, the radar rectangular coordinates corresponding to each point in the first corrected point cloud data at the current moment; Based on the radar rectangular coordinates and the first translation matrix, determine, for each point in the first corrected point cloud data, a second translation matrix from the current moment to the final state of the laser radar; Based on the second translation matrix, the translation motion distortion is removed for each point in the first corrected point cloud data to obtain second corrected point cloud data.

5. The method according to claim 4, characterized in that The step of performing noise reduction processing on the corrected point cloud data to obtain noise-reduced point cloud data includes: removing sea clutter points from the corrected point cloud data to obtain noisy point cloud data after the sea clutter points are removed; De-noising is performed on each point in the noisy point cloud data to obtain a clean point cloud.

6. The method according to claim 5, characterized in that For the corrected point cloud data, removing sea clutter points includes: Determining, based on each point in the corrected point cloud data, a first probability that each point in the point cloud data is sea clutter; Determining whether the first probability is greater than a probability threshold; If so, the point cloud corresponding to the first probability of sea clutter is regarded as a sea clutter point and filtered out.

7. The method according to claim 5, characterized in that The step of performing denoising on each point in the noisy point cloud data to obtain a clean point cloud comprises: determining, based on each point in the noisy point cloud data, an estimated offset from each point in the noisy point cloud data; A clean point cloud is obtained based on the estimated offset and the noisy point cloud data.

8. A computer device, characterized in that: The computer device includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by the processor to implement the point cloud data correction method as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: The readable storage medium stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by a processor to implement the point cloud data correction method as described in any one of claims 1 to 7.

Images