Method, device and equipment for measuring hinged angle and storage medium

Abstract

The application discloses a kind of measurement methods, device and equipment of hinged angle, and storage medium, involve vehicle safety technical field, comprising: the first point cloud data collected in the first vehicle body and the hinged place of second vehicle body in vehicle is acquired;Determine the target point cloud data matched with the first point cloud data in point cloud data sequence, multiple historical point cloud data are included in point cloud data sequence, and different historical point cloud data are point cloud data under different preset hinged angles, and the target point cloud data include at least one historical point cloud data between the first preset condition with the first point cloud data;According to the first pose transformation matrix between the first point cloud data and the target point cloud data, the first relative hinged angle is calculated;According to the first relative hinged angle and the preset hinged angle corresponding to the target point cloud data, determine the hinged angle between the first vehicle body and the second vehicle body.The embodiment of the application can improve the accuracy of hinged angle measurement.

Description

Technical Field

[0001] This application belongs to the field of vehicle safety technology, and in particular relates to a method, device, equipment and storage medium for measuring hinge angle. Background Technology

[0002] Currently, with the continuous development of the logistics and transportation industry, semi-trailers, as a heavy-duty transportation tool, are being used more and more widely in the modern freight field. Furthermore, with the popularization of intelligent assisted driving technology, real-time calculation of the articulation angle between the tractor and trailer greatly helps to enhance trailer driving safety and improve the accuracy of reversing operations.

[0003] The current method for measuring the articulation angle of trailers mainly involves acquiring point cloud data of the trailer by installing a lidar at the rear of the tractor, and then performing plane fitting processing on the point cloud data to measure the articulation angle.

[0004] However, this method is prone to failure when there is no container on the trailer or the container is of an irregular shape. At the same time, the measurement error of this method is also relatively large, resulting in low accuracy of the hinge angle measurement. Summary of the Invention

[0005] This application provides a method, apparatus, device, and storage medium for measuring hinge angles, which can improve the accuracy of hinge angle measurement.

[0006] One aspect of this application provides a method for measuring the hinge angle, comprising: Acquire the first point cloud data collected at the hinge point of the first and second vehicle bodies in the vehicle; In the point cloud data sequence, a target point cloud data matching the first point cloud data is determined. The point cloud data sequence includes multiple historical point cloud data, and the different historical point cloud data are located at different preset hinges. The point cloud data under the included angle, the target point cloud data includes at least one historical point cloud data that satisfies the first preset condition with the first point cloud data; The first relative hinge angle is calculated based on the first pose transformation matrix between the first point cloud data and the target point cloud data. The hinge angle between the first vehicle body and the second vehicle body is determined based on the first relative hinge angle and the preset hinge angle corresponding to the target point cloud data.

[0007] In one aspect of this application, a measuring device for hinge angle is provided, comprising: The data acquisition module is used to acquire the first point cloud data collected at the hinge point of the first and second vehicle bodies in the vehicle. The data determination module is used to determine the target point cloud data that matches the first point cloud data in the point cloud data sequence. The point cloud data sequence includes multiple historical point cloud data, and the different historical point cloud data are point cloud data under different preset hinge angles. The target point cloud data includes at least one historical point cloud data that satisfies the first preset condition with the first point cloud data. The included angle determination module is used to calculate the first relative hinge angle based on the first pose transformation matrix between the first point cloud data and the target point cloud data. The angle determination module is also used to determine the hinge angle between the first vehicle body and the second vehicle body based on the first relative hinge angle and the preset hinge angle corresponding to the target point cloud data.

[0008] In one aspect of this application, an electronic device is provided, the device comprising: a memory and a program or instructions stored in the memory and executable on a processor, wherein when the program or instructions are executed by the processor, the method for measuring the hinge angle as provided in any aspect of the above-described embodiments of this application is implemented.

[0009] In one aspect of the embodiments of this application, a readable storage medium is provided, on which a program or instruction is stored, and when the program or instruction is executed by a processor, it implements the method for measuring the hinge angle as provided in any aspect of the embodiments of this application described above.

[0010] In one aspect of the embodiments of this application, a computer program product is provided, wherein the instructions in the computer program product, when executed by the processor of an electronic device, cause the electronic device to perform the hinge angle measurement method provided in any aspect of the embodiments of this application described above.

[0011] The method for determining the hinge angle provided in this application involves setting historical point cloud data under different preset hinge angles as a point cloud data sequence, and then directly matching the first point cloud data with the point cloud data sequence to obtain the corresponding target point cloud data. This method only requires matching the first point cloud data with the point cloud data sequence, overcoming the problem of being unable to measure the hinge angle due to the absence of a container or the container having an irregular shape. Furthermore, this application also obtains the first relative hinge angle between the first point cloud data and the target point cloud data based on the first pose transformation matrix between them. Finally, based on the first relative hinge angle and the preset hinge angle corresponding to the target point cloud data, a more accurate hinge angle between the first vehicle body and the second vehicle body can be obtained. Thus, this application can overcome the problem of being unable to measure the angle due to the absence of a container or the container having an irregular shape, while also reducing the error in hinge angle measurement, thereby improving the accuracy of hinge angle measurement. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart illustrating a method for measuring the hinge angle provided in one embodiment of this application; Figure 2 This is a schematic diagram of the structure of a hinge angle measuring device provided in another embodiment of this application; Figure 3 This is a schematic diagram of the structure of a hinge angle measuring device provided in another embodiment of this application. Detailed Implementation

[0014] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0015] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0016] The technical solution of this application meets the requirements for data acquisition, storage, use, and processing.

[0017] As mentioned in the background and related technologies, existing methods for measuring the articulation angle of trailers are prone to failure when there is no container on the trailer or the container has an irregular shape. At the same time, the measurement error of this method is also relatively large, resulting in low accuracy of the articulation angle measurement.

[0018] Based on this, the purpose of this application is to provide a method, apparatus, device, and storage medium for measuring hinge angles. In the method for measuring hinge angles provided in this application, historical point cloud data under different preset hinge angles are set as point cloud data sequences, and then the first point cloud data is directly matched with the point cloud data sequence to obtain the corresponding target point cloud data. Only the first point cloud data needs to be matched with the point cloud data sequence, overcoming the problem of being unable to measure hinge angles due to the absence of containers or irregular container structures. Simultaneously, this application also obtains the first relative hinge angle between the first point cloud data and the target point cloud data based on the first pose transformation matrix between the first point cloud data and the target point cloud data. Finally, based on the first relative hinge angle and the preset hinge angle corresponding to the target point cloud data, a more accurate hinge angle between the first vehicle body and the second vehicle body can be obtained. Thus, this application can overcome the problem of being unable to measure angles due to the absence of containers or irregular container structures, while also reducing the error in hinge angle measurement, thereby improving the accuracy of hinge angle measurement.

[0019] The following describes specific embodiments of the hinge angle measurement method, apparatus, device, and storage medium provided in this application. The hinge angle measurement method will be described first.

[0020] Figure 1 A flowchart illustrating a method for measuring a hinge angle is provided. This method is applied to a server and may include the following steps S101 to S104.

[0021] S101, acquire the first point cloud data collected at the hinge point of the first and second vehicle bodies in the vehicle.

[0022] In this embodiment, the first vehicle body is the tractor body of the vehicle, and the second vehicle body is the towed vehicle body. For example, the vehicle may be a semi-trailer or a train.

[0023] When the vehicle is a semi-trailer, the first body can be the tractor unit of the semi-trailer, and the second body can be the carriage unit of the semi-trailer; when the vehicle is a train, the first body can be the first carriage of the train, and the second body can be the second carriage of the train.

[0024] The first point cloud data is a set of vectors recorded in the form of points and containing coordinate information. For example, the first point cloud data can be any of two-dimensional point cloud data, three-dimensional point cloud data, or higher-dimensional point cloud data.

[0025] The first point cloud data is collected through a data acquisition device. For example, the data acquisition device can be any one of a ToF camera, LiDAR, binocular camera, and RGBD camera.

[0026] For example, a ToF camera can be pre-installed at the center of the rear of the semi-trailer being tested. The ToF camera collects the first point cloud data at the hinge point between the first and second vehicle bodies. The server directly obtains the first point cloud data collected by the ToF camera.

[0027] S102, determine the target point cloud data that matches the first point cloud data in the point cloud data sequence. The point cloud data sequence includes multiple historical point cloud data, and the different historical point cloud data are point cloud data under different preset hinge angles. The target point cloud data includes at least one historical point cloud data that satisfies the first preset condition with the first point cloud data.

[0028] In this embodiment, the point cloud data sequence is a pre-generated sequence containing historical point cloud data under different pre-defined hinge angles.

[0029] The target point cloud data is historical point cloud data in the point cloud data sequence that meets a first preset condition with the first point cloud data. For example, the target point cloud data can be historical point cloud data whose matching error with the first point cloud data is within a preset threshold; the target point cloud data can also be a preset number of historical point cloud data with the smallest matching error with the first point cloud data.

[0030] For example, the vehicle first straightens its front end, then rotates the front end to the left in sequence, increasing the hinge angle between the first and second vehicle bodies until the hinge angle reaches its maximum value; then the vehicle straightens its front end again, and rotates the front end to the right in sequence, increasing the hinge angle between the first and second vehicle bodies until the hinge angle reaches its maximum value.

[0031] The corresponding historical point cloud data is collected sequentially using a ToF camera. Let the sequentially collected historical point cloud data be... The corresponding hinge angle is Based on the collected historical point cloud data, a point cloud data sequence is generated.

[0032] Then, when the server measures the hinge angle of the vehicle, it will match the first point cloud data collected at the hinge of the first and second vehicle bodies with the historical point cloud data in the point cloud data sequence in turn, and determine the historical point cloud data A with the smallest matching error on the left side of the first point cloud data and the historical point cloud data B with the smallest matching error on the right side of the first point cloud data as the target point cloud data.

[0033] S103, calculate the first relative hinge angle based on the first pose transformation matrix between the first point cloud data and the target point cloud data.

[0034] In this embodiment, the first pose transformation matrix is ​​used to characterize the movement relationship of the first point cloud data relative to the target point cloud data.

[0035] The first relative hinge angle is used to characterize the rotation angle of the first point cloud data relative to the target point cloud data.

[0036] For example, the server uses point cloud matching to calculate the first pose transformation matrix between the first point cloud data and historical point cloud data A, and the first pose transformation matrix between the first point cloud data and historical point cloud data B. The point cloud matching method can be any one of ICP, PL-ICP, NCP, IML-ICP, NDT, liosam, or a deep learning-based matching method.

[0037] Then, based on the obtained first pose transformation matrix, the first relative hinge angle A of the first point cloud data relative to the historical point cloud data A and the first relative hinge angle B of the first point cloud data relative to the historical point cloud data B are calculated respectively.

[0038] S104, determine the hinge angle between the first vehicle body and the second vehicle body based on the first relative hinge angle and the preset hinge angle corresponding to the target point cloud data.

[0039] In this embodiment, the preset hinge angle is a predetermined hinge angle corresponding to the target point cloud data.

[0040] For example, the preset hinge angle corresponding to historical point cloud data A is... The preset hinge angle corresponding to historical point cloud data B is By Add the first relative hinge angle A between the first point cloud data and the historical point cloud data A to obtain the hinge angle A; then... The hinge angle B is obtained by adding the first relative hinge angle B between the first point cloud data and the historical point cloud data B.

[0041] Finally, by calculating the average value of the hinge angle A and the hinge angle B, the final hinge angle between the first and second vehicle bodies can be obtained.

[0042] In this embodiment, historical point cloud data under different preset hinge angles are set as point cloud data sequences, and then the first point cloud data is directly matched with the point cloud data sequence to obtain the corresponding target point cloud data. Only the first point cloud data needs to be matched with the point cloud data sequence, overcoming the problem of being unable to measure the hinge angle due to the absence of a container or the container having an irregular shape. Simultaneously, this application also obtains the first relative hinge angle between the first point cloud data and the target point cloud data based on the first pose transformation matrix between them. Finally, based on the first relative hinge angle and the preset hinge angle corresponding to the target point cloud data, a more accurate hinge angle between the first vehicle body and the second vehicle body can be obtained. Thus, this embodiment can overcome the problem of being unable to measure the angle due to the absence of a container or the container having an irregular shape, while also reducing the error in hinge angle measurement, thereby improving the accuracy of hinge angle measurement.

[0043] As an optional embodiment, prior to S102, the method for measuring the hinge angle may further include: A point cloud data sequence is generated based on multiple historical point cloud data collected when the first vehicle body and the second vehicle body are at different preset hinge angles. Extract multiple target historical point cloud data that meet the second preset condition from the point cloud data sequence; Based on historical point cloud data of multiple targets, a key frame sequence is generated. The key frame sequence includes multiple key frames, and each key frame corresponds to a historical point cloud data of a target. S102 may specifically include: In the keyframe sequence, a target keyframe that matches the first point cloud data is determined, where the target point cloud data is the point cloud data corresponding to the target keyframe.

[0044] In this embodiment, the target historical point cloud data is the historical point cloud data in the point cloud data sequence that meets the second preset condition.

[0045] The target historical point cloud data can be historical point cloud data selected from the point cloud data sequence according to a preset interval number, for example, determining one target historical point cloud data every two historical point cloud data intervals; the target historical point cloud data can also be historical point cloud data selected from the point cloud data sequence according to a preset interval angle, for example, every interval Identify a target historical point cloud data.

[0046] For example, the server generates a point cloud data sequence based on multiple historical point cloud data collected by the ToF camera on the vehicle when the first and second vehicle bodies are at different preset hinge angles.

[0047] Then, a target historical point cloud data point is determined every two historical point cloud data points in the point cloud data sequence, until the entire point cloud data sequence is traversed, thus obtaining multiple target historical point cloud data points. Finally, each target historical point cloud data point is determined as a keyframe, thereby generating a keyframe sequence, and each target historical point cloud data point in the keyframe sequence and its corresponding hinge angle are persistently saved.

[0048] When measuring the hinge angle of a vehicle, it is only necessary to match the first point cloud data collected at the hinge point of the first and second vehicle bodies with the key frames in the key frame sequence to determine the target key frame that matches the first point cloud data.

[0049] In this embodiment, target historical point cloud data is selected as keyframes in the point cloud data sequence according to a preset interval number, thereby generating a keyframe sequence. When measuring the articulation angle of a vehicle, it is only necessary to match the first point cloud data with the keyframes in the keyframe sequence, without matching it with each historical point cloud data in the point cloud data sequence, thereby reducing the amount of computation and improving the measurement efficiency of the articulation angle.

[0050] As an optional embodiment, extracting multiple target historical point cloud data that meet a second preset condition from the point cloud data sequence includes: Obtain angle interval information; Based on angular interval information, historical point cloud data of multiple targets are extracted from the point cloud data sequence.

[0051] In this embodiment, the angle interval information is used to characterize the preset interval angle for extracting target historical point cloud data from the point cloud data sequence.

[0052] For example, the server generates a point cloud data sequence based on multiple historical point cloud data collected by the ToF camera on the vehicle when the first and second vehicle bodies are at different preset hinge angles.

[0053] Then, obtain the angle interval information and determine the preset interval angle based on the angle interval information. The process iterates through the point cloud data sequence, determining a target historical point cloud data point at preset angle intervals, thus obtaining multiple target historical point cloud data points. Finally, each target historical point cloud data point is designated as a keyframe, thereby generating a keyframe sequence.

[0054] In this embodiment, target historical point cloud data is selected as keyframes based on angle interval information in the point cloud data sequence, thereby generating a keyframe sequence. By setting multiple keyframes at equal intervals within the vehicle's rotation angle range, the technical problem of large hinge angle measurement errors in existing methods when handling large-angle turns can be overcome, thus improving the accuracy of hinge angle measurement.

[0055] As an optional embodiment, based on angular interval information, extracting multiple historical point cloud data of targets from the point cloud data sequence may specifically include: Obtain the k-th historical point cloud data in the point cloud data sequence, where k is not less than 2; Based on the (k-1)th historical point cloud data and the target historical point cloud data with the smallest matching error with the (k-1)th historical point cloud data, the second pose transformation matrix between the k-th historical point cloud data and the target historical point cloud data with the smallest matching error with the (k-1)th historical point cloud data is obtained. The second relative hinge angle is calculated based on the second pose transformation matrix between the target historical point cloud data with the smallest matching error between the k-th historical point cloud data and the (k-1)-th historical point cloud data. If the second relative hinge angle satisfies the angle interval information, the kth historical point cloud data is determined as the target historical point cloud data.

[0056] In this embodiment, the point cloud data sequence is arranged in ascending order according to the corresponding hinge angle, wherein the first historical point cloud data is the point cloud data corresponding to when the front of the car is straightened.

[0057] The second relative hinge angle is used to characterize the rotation angle of the k-th historical point cloud data relative to the target historical point cloud data with the smallest matching error with the (k-1)-th historical point cloud data.

[0058] For example, the server first presets the first historical point cloud data as the target historical point cloud data, and then sequentially obtains the kth historical point cloud data in the point cloud data sequence. Simultaneously, based on the k-th historical point cloud data, the (k-1)-th historical point cloud data is determined. And the target historical point cloud data with the smallest matching error to the (k-1)th historical point cloud data. .

[0059] Then according to as well as ,get and The second pose transformation matrix between them. Then, based on the transformation relationship between the transformation matrix and Euler angles, through... and The second pose transformation matrix between them is calculated to obtain Compared to The second relative hinge angle m.

[0060] The second relative hinge angle m satisfies the angle interval information, that is, m is not less than the preset interval angle. In the case of, determine For the target historical point cloud data, at the same time The sum of the corresponding hinge angle and the second relative hinge angle m is used as the k-th historical point cloud data. The corresponding hinge angle.

[0061] In this embodiment, the hinge angle of the k-th historical point cloud data is determined more accurately by using the (k-1)th historical point cloud data as reference data, which helps to accurately select the target historical point cloud data and thus improves the accuracy of hinge angle measurement.

[0062] As an optional embodiment, based on the (k-1)th historical point cloud data and the target historical point cloud data with the smallest matching error with the (k-1)th historical point cloud data, a second pose transformation matrix between the k-th historical point cloud data and the target historical point cloud data with the smallest matching error with the (k-1)th historical point cloud data is obtained, which may specifically include: Obtain the third pose transformation matrix between the k-th historical point cloud data and the (k-1)-th historical point cloud data; Based on the third pose transformation matrix, determine the initial second pose transformation matrix between the target historical point cloud data with the smallest matching error between the k-th historical point cloud data and the (k-1)-th historical point cloud data; Based on the initial second pose transformation matrix, point cloud matching is performed on the target historical point cloud data with the smallest matching error between the k-th historical point cloud data and the (k-1)-th historical point cloud data to obtain the final second pose transformation matrix.

[0063] In this embodiment, the server, based on the k-th historical point cloud data... Determine the (k-1)th historical point cloud data And the target historical point cloud data with the smallest matching error to the (k-1)th historical point cloud data. Then, the solution is obtained using point cloud matching methods. and The pose relationship yields the third pose transformation matrix. .

[0064] Then based on the third pose transformation matrix get and The initial second pose transformation matrix between ,in equal and The product of For the (k-1)th historical point cloud data Historical point cloud data of the target with the smallest matching error The pose transformation matrix between them.

[0065] Finally, the second pose transformation matrix is ​​used. For initial value pairs and Then, point cloud matching is performed to obtain a more accurate result. arrive The final second pose transformation matrix .

[0066] In this embodiment, using the (k-1)th historical point cloud data as reference data, the second relative hinge angle between the k-th historical point cloud data and the target historical point cloud data with the smallest matching error relative to the (k-1)th historical point cloud data is determined by the pose relationship between the k-th historical point cloud data and the (k-1)-th historical point cloud data. By using the closest target historical point cloud data as reference data for matching correction to reduce accumulated errors, the accuracy of hinge angle measurement can be improved.

[0067] As an optional embodiment, determining the target keyframe that matches the first point cloud data in the keyframe sequence includes: The first point cloud data is matched with each key frame in the key frame sequence to determine the matching error between the first point cloud data and each key frame. The keyframe with the smallest matching error is determined as the target keyframe that matches the first point cloud data.

[0068] In this embodiment, when the server measures the hinge angle of the vehicle, it will sequentially perform point cloud matching between the first point cloud data collected at the hinge point of the first vehicle body and the second vehicle body and each key frame in the key frame sequence to determine the matching error between the first point cloud data and each key frame in the key frame sequence.

[0069] Then, the keyframe with the smallest matching error is determined as the target keyframe that matches the first point cloud data. The pose transformation matrix between the first point cloud data and the target keyframe is then calculated using the point cloud matching method. Based on the obtained pose transformation matrix, the relative rotation angle between the first point cloud data and the target keyframe is calculated.

[0070] Finally, by adding the relative rotation angle to the hinge angle corresponding to the target keyframe, the final hinge angle between the first and second vehicle bodies can be obtained.

[0071] As an example, the hinge angle between the first vehicle body and the second vehicle body corresponding to the i-th first point cloud data. Given the given conditions, what is the hinge angle between the first and second vehicle bodies corresponding to the (i+1)th first point cloud data point? , can be done in sequence Each nearby keyframe is sequentially matched with the (i+1)th first point cloud data to determine the keyframe with the smallest matching error, eliminating the need to perform point cloud matching between the (i+1)th first point cloud data and each keyframe in the keyframe sequence.

[0072] In this embodiment, by determining the target keyframe with the smallest matching error to the first point cloud data, the relative rotation angle between the first point cloud data and the target keyframe is obtained based on the target keyframe. Finally, the relative rotation angle is added to the hinge angle corresponding to the target keyframe, thereby obtaining a more accurate hinge angle between the first vehicle body and the second vehicle body, and improving the accuracy of hinge angle measurement.

[0073] As an optional embodiment, before generating a point cloud data sequence based on multiple historical point cloud data collected when the first vehicle body and the second vehicle body are at different preset hinge angles, the method for measuring the hinge angle may further include: Acquire the installation angle information of the data acquisition device on the vehicle. The data acquisition device is used to collect historical point cloud data when the first and second bodies of the vehicle are at different preset hinge angles. Based on the installation angle information, the coordinate position information of historical point cloud data is updated; Historical point cloud data that meets the third preset condition is filtered out from the historical point cloud data after the coordinate position information is updated; Based on multiple historical point cloud data collected when the first and second vehicle bodies are at different preset hinge angles, a point cloud data sequence is generated, specifically including: A point cloud data sequence is generated based on the filtered historical point cloud data.

[0074] In this embodiment, the data acquisition device is used to collect historical point cloud data of the vehicle's first and second bodies when they are at different preset hinge angles. Coordinate position information is used to characterize the position corresponding to the historical point cloud data.

[0075] The third preset condition is used to characterize the conditions for filtering historical point cloud data. For example, the third preset condition can be to filter out historical point cloud data that does not belong to the hinge position of the first and second vehicle bodies in the vehicle; the third preset condition can also be to filter out historical point cloud data whose position is not within a preset range.

[0076] For example, after the server obtains multiple historical point cloud data collected when the first and second vehicle bodies are at different preset hinge angles, it will measure the installation angle of the ToF camera relative to the vehicle body, and transform each historical point cloud data from the ToF camera coordinate system to the vehicle body coordinate system according to the installation angle of the ToF camera relative to the vehicle body, thereby completing the update of the coordinate position information of each historical point cloud data.

[0077] Then, a point cloud processing algorithm is used to process each historical point cloud data, thereby filtering out historical point cloud data that does not belong to the hinge position of the first and second vehicle bodies in the updated historical point cloud data. Finally, a point cloud data sequence is generated based on the filtered historical point cloud data. The point cloud processing algorithm can be any one of the following: bilateral filtering algorithm, Gaussian filtering algorithm, conditional filtering algorithm, pass-through filtering algorithm, and random sample-consistent filtering algorithm.

[0078] As an example, after filtering out historical point cloud data that does not belong to vehicles, the trailer point cloud can be sparsified by voxel filtering, and a point cloud data sequence can be generated based on the multiple historical point cloud data after sparsification.

[0079] In this embodiment, the collected historical point cloud data is preprocessed, and the coordinate position information of the historical point cloud data is updated to obtain more accurate coordinate positions of the historical point cloud data. At the same time, historical point cloud data that meets the third preset condition is screened out to remove impurity data in each historical point cloud data, thereby obtaining a more accurate point cloud data sequence, which helps to improve the accuracy of hinge angle measurement.

[0080] A method for measuring hinge angles. Accordingly, this application also provides specific embodiments of a device for measuring hinge angles.

[0081] like Figure 2 As shown, the hinge angle measuring device provided in this application embodiment includes a data acquisition module 210, a data determination module 220, and an angle determination module 230.

[0082] The data acquisition module 210 is used to acquire the first point cloud data collected at the hinge point of the first and second vehicle bodies in the vehicle.

[0083] The data determination module 220 is used to determine the target point cloud data that matches the first point cloud data in the point cloud data sequence. The point cloud data sequence includes multiple historical point cloud data, and the different historical point cloud data are point cloud data under different preset hinge angles. The target point cloud data includes at least one historical point cloud data that satisfies the first preset condition with the first point cloud data.

[0084] The included angle determination module 230 is used to calculate the first relative hinge angle based on the first pose transformation matrix between the first point cloud data and the target point cloud data.

[0085] The angle determination module 230 is also used to determine the hinge angle between the first vehicle body and the second vehicle body based on the first relative hinge angle and the preset hinge angle corresponding to the target point cloud data.

[0086] As an optional embodiment, the measuring device for the hinge angle further includes the following modules: The sequence generation module is used to generate a point cloud data sequence based on multiple historical point cloud data collected when the first vehicle body and the second vehicle body are at different preset hinge angles. The data extraction module is used to extract multiple target historical point cloud data that meet the second preset conditions from the point cloud data sequence; The sequence generation module is also used to generate a key frame sequence based on multiple target historical point cloud data. The key frame sequence includes multiple key frames, and the key frames correspond to the target historical point cloud data. The data determination module 220 is specifically used for: In the keyframe sequence, a target keyframe that matches the first point cloud data is determined, where the target point cloud data is the point cloud data corresponding to the target keyframe.

[0087] As an optional embodiment, the data extraction module specifically includes the following sub-modules: The interval acquisition submodule is used to acquire angle interval information; The data extraction submodule is used to extract historical point cloud data of multiple targets from a point cloud data sequence based on angular interval information.

[0088] As an optional embodiment, the data extraction submodule specifically includes the following units: The data acquisition unit is used to acquire the kth historical point cloud data in the point cloud data sequence. The matrix generation unit is used to obtain the second pose transformation matrix between the k-th historical point cloud data and the target historical point cloud data with the smallest matching error with the k-1 historical point cloud data, based on the k-1 historical point cloud data and the target historical point cloud data with the smallest matching error with the k-1 historical point cloud data. Angle generation unit is used to calculate the second relative hinge angle based on the second pose transformation matrix between the target historical point cloud data with the smallest matching error between the k-th historical point cloud data and the (k-1)-th historical point cloud data. The data determination unit is used to determine the kth historical point cloud data as the target historical point cloud data when the second relative hinge angle satisfies the angle interval information.

[0089] As an optional embodiment, the matrix generation unit specifically includes the following sub-units: The matrix acquisition sub-unit is used to acquire the third pose transformation matrix between the k-th historical point cloud data and the (k-1)-th historical point cloud data; The matrix generation sub-unit is used to determine the initial second pose transformation matrix between the target historical point cloud data with the smallest matching error between the k-th historical point cloud data and the (k-1)-th historical point cloud data, based on the third pose transformation matrix. The matrix update sub-unit is used to perform point cloud matching on the target historical point cloud data with the smallest matching error between the k-th historical point cloud data and the (k-1)-th historical point cloud data, based on the initial second pose transformation matrix, to obtain the final second pose transformation matrix.

[0090] As an optional embodiment, the data determination module 220 specifically includes the following sub-modules: The error determination submodule is used to perform point cloud matching between the first point cloud data and each key frame in the key frame sequence, and determine the matching error between the first point cloud data and each key frame. The keyframe determination submodule is used to determine the keyframe with the smallest matching error as the target keyframe that matches the first point cloud data.

[0091] As an optional embodiment, the measuring device for the hinge angle further includes the following modules: Angle acquisition module is used to acquire the installation angle information of the data acquisition device on the vehicle. The data acquisition device is used to acquire historical point cloud data of the first and second bodies of the vehicle under different preset hinge angles. The position update module is used to update the coordinate position information of historical point cloud data based on the installation angle information; The data filtering module is used to filter out historical point cloud data that meets the third preset condition from the historical point cloud data after the coordinate position information is updated; The sequence generation module is specifically used for: A point cloud data sequence is generated based on the filtered historical point cloud data.

[0092] A method for measuring hinge angles. Accordingly, this application also provides specific embodiments of a device for measuring hinge angles.

[0093] Figure 3 A schematic diagram of the hardware structure of the hinge angle measuring device provided in an embodiment of this application is shown.

[0094] The device for measuring the hinge angle may include a processor 301 and a memory 302 storing computer program instructions.

[0095] Specifically, the processor 301 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0096] Memory 302 may include mass storage for data or instructions. For example, and not limitingly, memory 302 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 302 may include removable or non-removable (or fixed) media. Where appropriate, memory 302 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 302 is non-volatile solid-state memory.

[0097] Memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the methods according to one aspect of this disclosure.

[0098] The processor 301 reads and executes computer program instructions stored in the memory 302 to implement any of the hinge angle measurement methods in the above embodiments.

[0099] In one example, the device for measuring the hinge angle may also include a communication interface 303 and a bus 310. Wherein, as Figure 3 As shown, the processor 301, memory 302, and communication interface 303 are connected through bus 310 and complete communication with each other.

[0100] The communication interface 303 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0101] Bus 310 includes hardware, software, or both, that couples components of a device for measuring hinged angles together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 310 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0102] Furthermore, in conjunction with the hinge angle measurement method in the above embodiments, this application embodiment can provide a computer storage medium for implementation. This computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the hinge angle measurement methods in the above embodiments.

[0103] In addition, in conjunction with the hinge angle measurement method in the above embodiments, this application embodiment can provide a computer program product implementation. When the instructions in the computer program product are executed by the processor of an electronic device, the electronic device executes the hinge angle measurement method provided by any aspect of the above-described embodiments of this application.

[0104] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0105] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0106] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0107] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0108] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for measuring the included angle of a hinge, characterized in that, include: Acquire the first point cloud data collected at the hinge point of the first and second vehicle bodies in the vehicle; A point cloud data sequence is generated based on multiple historical point cloud data collected when the first vehicle body and the second vehicle body are at different preset hinge angles. Extract multiple target historical point cloud data that meet the second preset conditions from the point cloud data sequence; The step of extracting multiple target historical point cloud data that meet the second preset condition from the point cloud data sequence includes: Obtain angle interval information; Based on the angle interval information, multiple target historical point cloud data are extracted from the point cloud data sequence; Based on the angular interval information, the extraction of multiple target historical point cloud data from the point cloud data sequence includes: Obtain the kth historical point cloud data in the point cloud data sequence, where k is not less than 2; Based on the (k-1)th historical point cloud data and the target historical point cloud data with the smallest matching error with the (k-1)th historical point cloud data, a second pose transformation matrix is ​​obtained between the k-th historical point cloud data and the target historical point cloud data with the smallest matching error with the (k-1)th historical point cloud data. The second relative hinge angle is calculated based on the second pose transformation matrix between the target historical point cloud data with the smallest matching error between the kth historical point cloud data and the (k-1)th historical point cloud data. If the second relative hinge angle satisfies the angle interval information, the kth historical point cloud data is determined as the target historical point cloud data; Based on the multiple target historical point cloud data, a key frame sequence is generated, the key frame sequence including multiple key frames, and the key frames correspond to the target historical point cloud data; In the point cloud data sequence, a target point cloud data matching the first point cloud data is determined. The point cloud data sequence includes multiple historical point cloud data, and different historical point cloud data are point cloud data under different preset hinge angles. The target point cloud data includes at least one historical point cloud data that satisfies a first preset condition with the first point cloud data. The step of determining the target point cloud data that matches the first point cloud data in the point cloud data sequence includes: In the keyframe sequence, a target keyframe that matches the first point cloud data is determined, wherein the target point cloud data is the point cloud data corresponding to the target keyframe; The first relative hinge angle is calculated based on the first pose transformation matrix between the first point cloud data and the target point cloud data. The hinge angle between the first vehicle body and the second vehicle body is determined based on the first relative hinge angle and the preset hinge angle corresponding to the target point cloud data.

2. The method according to claim 1, characterized in that, The second pose transformation matrix between the (k-1)th historical point cloud data and the target historical point cloud data with the smallest matching error with the (k-1)th historical point cloud data is obtained, including: Obtain the third pose transformation matrix between the k-th historical point cloud data and the (k-1)-th historical point cloud data; Based on the third pose transformation matrix, an initial second pose transformation matrix is ​​determined between the target historical point cloud data with the smallest matching error between the k-th historical point cloud data and the (k-1)-th historical point cloud data. Based on the initial second pose transformation matrix, point cloud matching is performed on the target historical point cloud data with the smallest matching error between the k-th historical point cloud data and the (k-1)-th historical point cloud data to obtain the final second pose transformation matrix.

3. The method according to claim 1, characterized in that, The step of determining the target keyframe that matches the first point cloud data in the keyframe sequence includes: The first point cloud data is matched with each key frame in the key frame sequence to determine the matching error between the first point cloud data and each key frame. The keyframe with the smallest matching error is determined as the target keyframe that matches the first point cloud data.

4. The method according to claim 1, characterized in that, Before generating a point cloud data sequence based on multiple historical point cloud data collected when the first vehicle body and the second vehicle body are at different preset hinge angles, the method further includes: The installation angle information of the data acquisition device on the vehicle is obtained. The data acquisition device is used to collect historical point cloud data of the first and second vehicle bodies of the vehicle under different preset hinge angles. Based on the installation angle information, the coordinate position information of the historical point cloud data is updated; Historical point cloud data that meets the third preset condition are filtered out from the historical point cloud data after the coordinate position information is updated. The step of generating a point cloud data sequence based on multiple historical point cloud data collected when the first vehicle body and the second vehicle body are at different preset hinge angles includes: A point cloud data sequence is generated based on the filtered historical point cloud data.

5. A measuring device for hinged included angles, characterized in that, include: The data acquisition module is used to acquire the first point cloud data collected at the hinge point of the first and second vehicle bodies in the vehicle. The sequence generation module is used to generate a point cloud data sequence based on multiple historical point cloud data collected when the first vehicle body and the second vehicle body are at different preset hinge angles. The interval acquisition submodule is used to acquire angle interval information; The data extraction submodule is used to extract multiple target historical point cloud data from the point cloud data sequence based on the angle interval information. The data acquisition unit is used to acquire the kth historical point cloud data in the point cloud data sequence, where k is not less than 2; The matrix generation unit is used to obtain a second pose transformation matrix between the k-th historical point cloud data and the target historical point cloud data with the smallest matching error with the k-1 historical point cloud data, based on the (k-1)-th historical point cloud data and the target historical point cloud data with the smallest matching error with the (k-1)-th historical point cloud data. Angle generation unit is used to calculate the second relative hinge angle based on the second pose transformation matrix between the target historical point cloud data with the smallest matching error between the kth historical point cloud data and the (k-1)th historical point cloud data. The data determination unit is used to determine the kth historical point cloud data as the target historical point cloud data when the second relative hinge angle satisfies the angle interval information. The sequence generation module is further configured to generate a key frame sequence based on the plurality of target historical point cloud data, wherein the key frame sequence includes a plurality of key frames, and the key frames correspond to the target historical point cloud data. The data determination module is used to determine target point cloud data that matches the first point cloud data in the point cloud data sequence. The point cloud data sequence includes multiple historical point cloud data, and different historical point cloud data are point cloud data under different preset hinge angles. The target point cloud data includes at least one historical point cloud data that satisfies a first preset condition with the first point cloud data. The data determination module is specifically used to: determine a target keyframe that matches the first point cloud data in the keyframe sequence, wherein the target point cloud data is point cloud data corresponding to the target keyframe; Angle determination module is used to calculate the first relative hinge angle based on the first pose transformation matrix between the first point cloud data and the target point cloud data. The angle determination module is also used to determine the hinge angle between the first vehicle body and the second vehicle body based on the first relative hinge angle and the preset hinge angle corresponding to the target point cloud data.

6. A measuring device for hinged included angles, characterized in that, The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the method for measuring the hinge angle as described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, implement the method for measuring the hinge angle as described in any one of claims 1-4.

Images