Target size labeling method, device, equipment, storage medium and program product

Abstract

The application relates to the technical field of deep learning, in particular to a target size labeling method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring picture data collected by a vehicle-mounted camera and point cloud data collected by a laser radar; first target attribute information and second target attribute information are respectively generated based on the picture data and the point cloud data, and the first target attribute information and the second target attribute information are matched to obtain a target list; the observation corner point and the center point of each target in the target list are calculated, and the target observation frame corresponding to each target is calculated according to a target function, the observation corner point and the center point of each target, so as to label the size of the target based on the target observation frame. Therefore, the problems of low target size labeling efficiency and poor labeling quality in the related art are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of deep learning, and particularly relates to a target size labeling method and device, equipment, a storage medium and a program product. BACKGROUND

[0002] Currently, in the automatic driving industry, the true value of labeled data is mainly realized by training a deep learning detection model to pre-label a target, and then performing secondary quality inspection and error correction manually.

[0003] However, the quality of pre-labeling is highly related to the indicators of the pre-training model, and the variance of the model prediction is often large due to the observation angle of the same target size, and it is difficult for manual quality inspection to quantitatively confirm the optimal size attribute labeling value. For the same target in the same data set, consistent size labeling requires a great error correction cost, and the quality of the labeled data is also not high. SUMMARY

[0004] The present application provides a target size labeling method, device, equipment, storage medium and program product to solve the problems of low labeling efficiency and poor labeling quality in related technologies.

[0005] The first aspect of the present application provides a target size labeling method, comprising the following steps: obtaining picture data collected by a vehicle-mounted camera and point cloud data collected by a laser radar; generating first target attribute information and second target attribute information based on the picture data and the point cloud data, respectively, and matching the first target attribute information and the second target attribute information to obtain a target list; calculating an observation angle point and a center point of each target in the target list, calculating a target observation frame corresponding to each target according to a target function, the observation angle point and the center point of each target, and labeling the size of the target based on the target observation frame.

[0006] Optionally, in an embodiment of the present application, matching the first target attribute information and the second target attribute information to obtain the target list comprises: obtaining positioning information of the vehicle; and matching the first target attribute information and the second target attribute information based on the positioning information to obtain the target list.

[0007] Optionally, in an embodiment of the present application, calculating the target observation frame of each target according to the observation angle point, the center point and the target function comprises: calculating the observation angle point and the center point of each target in each frame; calculating an observation angle of each frame according to the observation angle point of each frame, and calculating the Euclidean distance between the target and the vehicle in each frame according to the center point of each frame; obtaining a maximum value of the observation angle and a minimum value of the Euclidean distance; and calculating the target observation frame corresponding to the target according to the maximum value of the observation angle, the minimum value of the Euclidean distance and the target function.

[0008] Optionally, in an embodiment of the present application, the target function is:

[0009] f(x) = Max(coeff) a *theta / theta max +coeff b *dist min / dist);

[0010] Among them, coeff a As the first weighting coefficient, coeff b Coeff is the second weighting coefficient. a +coeff b =1.0, theta is the observation angle, theta max The maximum value in the observation angle, where dist is the Euclidean distance between the target and the vehicle. min This is the minimum value of the Euclidean distance.

[0011] Optionally, in one embodiment of this application, after labeling the size of the target based on the target observation frame, the method further includes: obtaining the target observation frame corresponding to each target; storing the target observation frame corresponding to each target and the relevant information of the target observation frame in a preset database, wherein the relevant information includes at least one of target size, observation angle, and center point.

[0012] Optionally, in one embodiment of this application, after labeling the size of the target based on the target observation frame, the method further includes: obtaining basic information of the target to be labeled and / or the target to be inspected; querying a preset database based on the basic information of the target to be labeled and / or the target to be inspected to obtain the target observation frame and related information of the target observation frame corresponding to the target to be labeled and / or the target to be inspected.

[0013] A second aspect of this application provides a target size annotation device, comprising: an acquisition module for acquiring image data collected by a vehicle-mounted camera and point cloud data collected by a lidar; a matching module for generating first target attribute information and second target attribute information based on the image data and point cloud data respectively, and matching the first target attribute information and the second target attribute information to obtain a target list; and a calculation module for calculating the observation corner point and center point of each target in the target list, calculating the target observation frame corresponding to each target according to the objective function, the observation corner point and center point of each target, and annotating the size of the target based on the target observation frame.

[0014] Optionally, in one embodiment of this application, the matching module is further configured to: obtain the vehicle's location information; and obtain a target list by matching the first target attribute information and the second target attribute information based on the location information.

[0015] Optionally, in one embodiment of this application, the calculation module is further configured to: calculate the observation corner point and center point of each target in each frame; calculate the observation angle of each frame based on the observation corner point of each frame, and calculate the Euclidean distance between the target and the vehicle in each frame based on the center point of each frame; obtain the maximum value of the observation angle and the minimum value of the Euclidean distance; and calculate the target observation frame corresponding to the target based on the maximum value of the observation angle, the minimum value of the Euclidean distance, and the objective function.

[0016] Optionally, in one embodiment of this application, the objective function is:

[0017] f(x) = Max(coeff) a *theta / theta max +coeff b *dist min / dist);

[0018] Among them, coeff a As the first weighting coefficient, coeff b Coeff is the second weighting coefficient. a +coeff b =1.0, theta is the observation angle, theta max The maximum value in the observation angle, where dist is the Euclidean distance between the target and the vehicle. min This is the minimum value of the Euclidean distance.

[0019] Optionally, in one embodiment of this application, it further includes: a storage module, configured to obtain a target observation frame corresponding to each target after labeling the size of the target based on the target observation frame; and store the target observation frame corresponding to each target and related information of the target observation frame in a preset database, wherein the related information includes at least one of target size, observation angle, and center point.

[0020] Optionally, in one embodiment of this application, it further includes: a query module, used to obtain basic information of the target to be labeled and / or the target to be inspected after labeling the size of the target based on the target observation frame; and to query a preset database based on the basic information of the target to be labeled and / or the target to be inspected to obtain the target observation frame and related information of the target observation frame corresponding to the target to be labeled and / or the target to be inspected.

[0021] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to perform the target dimension annotation method as described in the above embodiments.

[0022] A fourth aspect of this application provides a computer-readable storage medium having a computer program or instructions stored thereon, which are executed by a processor to perform a target dimension annotation method, such as the one described above.

[0023] A fifth aspect of this application provides a computer program product, including a computer program or instructions, which, when executed, implement the target dimension annotation method as described in the above embodiments.

[0024] Therefore, this application has at least the following beneficial effects:

[0025] This application embodiment can generate first target attribute information and second target attribute information based on image data and point cloud data respectively, and match them to obtain a target list. Then, it calculates the observation corner point and center point of each target in the target list. Based on the objective function, the observation corner point and center point of each target, it calculates the target observation frame corresponding to each target, and marks the target size based on the target observation frame. This improves the efficiency and accuracy of target size marking and reduces the cost of manual marking. Thus, it solves the technical problems of low efficiency and poor marking quality in related technologies.

[0026] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0027] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0028] Figure 1 This is a flowchart of the target dimension annotation method provided according to an embodiment of this application;

[0029] Figure 2 This is a schematic diagram illustrating the calculation of the observation angle according to the embodiments of this application;

[0030] Figure 3 This is a schematic diagram illustrating the calculation of Euclidean distance according to an embodiment of this application;

[0031] Figure 4 This is a schematic diagram of a target dimension annotation method provided according to a specific embodiment of this application;

[0032] Figure 5 This is an example diagram of a target dimension marking device provided according to an embodiment of this application;

[0033] Figure 6 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0034] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0035] Before describing the solution of this application, the relevant technologies are described as follows:

[0036] Related technology 1 provides a method for acquiring target annotation data, a target tracking method, an intelligent device, and a medium, aiming to solve the problem of conveniently and accurately acquiring target annotation data. Specifically, it involves: acquiring first data frames collected by each sensor; acquiring the target's detection box, truth box, and tracking ID in the first data frame; modifying the truth boxes representing the same target in the first data frames of different sensors to have the same tracking ID, forming second data frames for each sensor; acquiring the truth box representing the same target as the detection box, and setting the tracking ID of the detection box according to the tracking ID of the truth box in the second data frame; and acquiring target annotation data based on the detection box and its tracking ID. However, this only solves the problem of ID unification for the same observed target by different sensors during the annotation process.

[0037] Related technology 2 performs target detection and tracking on point cloud sequences acquired by radar to obtain the motion trajectory of point cloud targets; it also performs target detection on images acquired by cameras to obtain the category of image targets; based on the motion trajectory of point cloud targets, it obtains the pose of point cloud targets at the time of image capture; based on the pose, it obtains image targets on the image that match the point cloud targets; and based on the category of the image targets and the trajectory information of the point cloud targets, it obtains annotation data. However, it cannot improve the detection efficiency and accuracy of subsequent manual secondary quality inspection.

[0038] Related technique 3 first parses multiple consecutive point cloud frames to obtain the first point cloud set and initial bounding box corresponding to the target in each point cloud frame. Then, it registers each first point cloud set to obtain the registration contour corresponding to the target and the registration matrix corresponding to each first point cloud set. Next, based on the second point cloud set corresponding to the registration contour, the first initial bounding box is adjusted to obtain the adjusted first bounding box. Finally, based on the adjusted first bounding box and each registration matrix, the other initial bounding boxes are adjusted respectively to obtain the second bounding box. However, this technique only involves the correction between consecutive frames and lacks a specific quantitative calculation process for the optimal correction value.

[0039] Related technology 4 first acquires a point cloud image, in which the initial target bounding box of the target to be detected is marked. Then, based on the point cloud distribution within the initial target bounding box, the completeness of the initial target bounding box in selecting the target to be detected is determined. Finally, based on the completeness, the initial target bounding box is adjusted to obtain a standard target bounding box. Therefore, by determining the completeness of the initial target bounding box based on the point cloud distribution, the fit between the initial target bounding box and the point cloud of the target to be detected can be judged. This allows for further adjustment of the initial target bounding box based on the completeness, improving the accuracy of target detection and thus enhancing the annotation quality and efficiency in the target detection process. However, it does not solve the problem of quantitative statistical analysis and recommendation of target sizes across multiple frames for the same target, and the time cost of manual secondary quality inspection and error correction remains relatively high.

[0040] To address this, this application provides a target size annotation method. In this method, first target attribute information and second target attribute information can be generated based on image data and point cloud data, respectively, and matched to obtain a target list. Then, the observation corner point and center point of each target in the target list are calculated. Based on the objective function, the observation corner point and center point of each target, the target observation frame corresponding to each target is calculated, and the target size is annotated based on the target observation frame. This improves the efficiency and accuracy of target size annotation and reduces the cost of manual annotation.

[0041] Specifically, Figure 1 This is a flowchart illustrating a target dimension annotation method provided in an embodiment of this application.

[0042] like Figure 1 As shown, the target dimensioning method includes the following steps:

[0043] In step S101, image data collected by the vehicle-mounted camera and point cloud data collected by the lidar are acquired.

[0044] In step S102, first target attribute information and second target attribute information are generated based on image data and point cloud data, respectively, and a target list is obtained by matching the first target attribute information and the second target attribute information.

[0045] It is understood that the embodiments of this application can generate first target attribute information and second target attribute information based on image data and point cloud data respectively, and match the first target attribute information and second target attribute information to obtain a target list, so as to merge the same target into one target when the vehicle camera and LiDAR detect the same target at the same time, thereby avoiding duplication and confusion.

[0046] Specifically, in this application embodiment, camera image data can be input into an offline cloud-based visual inference model to generate 2D / 3D target attribute information, i.e., first target attribute information. Point cloud information can be input into an offline cloud-based 3D point cloud inference model to generate 3D target attribute information, i.e. second target attribute information. The first target attribute information and the second target attribute information are matched to obtain a target list. In order to merge these detection results into a single tracking target when the vehicle-mounted camera and LiDAR detect the same target at the same time, this avoids duplication and confusion.

[0047] In this embodiment of the application, matching the first target attribute information and the second target attribute information to obtain a target list includes: obtaining the vehicle's location information; and matching the first target attribute information and the second target attribute information based on the location information to obtain a target list.

[0048] It is understood that the embodiments of this application can obtain the vehicle's location information and obtain a target list by matching the first target attribute information and the second target attribute information based on the location information.

[0049] Specifically, a target list can be obtained by using a multi-sensor fusion algorithm to combine location information, first target attribute information, and second target attribute information.

[0050] In step S103, the observation corner point and center point of each target in the target list are calculated. Based on the objective function, the observation corner point and center point of each target, the target observation frame corresponding to each target is calculated, so as to label the size of the target based on the target observation frame.

[0051] The target observation frame is also called the optimal observation frame.

[0052] It is understood that the embodiments of this application can calculate the observation corner point and centerline point of each target in the target list, and calculate the target observation frame corresponding to each target based on the objective function, the observation corner point and center point of each target, so as to label the size of the target based on the observation frame, so as to achieve the optimal labeling of the target size.

[0053] In this embodiment of the application, the target observation frame for each target is calculated based on the observation corner point, center point, and objective function, including: calculating the observation corner point and center point of each target in each frame; calculating the observation angle of each frame based on the observation corner point of each frame, and calculating the Euclidean distance between the target and the vehicle in each frame based on the center point of each frame; obtaining the maximum value of the observation angle and the minimum value of the Euclidean distance; and calculating the target observation frame corresponding to the target based on the maximum value of the observation angle, the minimum value of the Euclidean distance, and the objective function.

[0054] The objective function is:

[0055] f(x) = Max(coeff) a*theta / theta max +coeff b *dist min / dist);

[0056] Among them, coeff a As the first weighting coefficient, coeff b Coeff is the second weighting coefficient. a +coeff b =1.0, theta is the observation angle, theta max The maximum value in the observation angle, where dist is the Euclidean distance between the target and the vehicle. min This is the minimum value of the Euclidean distance.

[0057] Since the target is continuously observed and the vehicle is in a moving state, the observation corner point and center point of the target are different in each frame. Therefore, the embodiments of this application can calculate the observation corner point and center point of each target in each frame, calculate the observation angle of the target in each frame based on the observation corner point of each frame, calculate the Euclidean distance between the target and the vehicle in each frame based on the center point of each frame, and select the maximum value of the observation angle and the minimum value of the Euclidean distance in multiple frames. Furthermore, the maximum value of the observation angle, the minimum value of the Euclidean distance, and the objective function are used to calculate the target observation frame corresponding to the target.

[0058] The calculation of the observation angle theta in the embodiments of this application is as follows: Figure 2 As shown, taking the target vehicle as an example, for any target vehicle and the vehicle itself, the length l of the vehicle itself is known, and the coordinates of the vertices of the target vehicle's frame are known. Therefore, the distance m and n between the origin of the vehicle itself and the edge vertex AB of the target vehicle can be calculated.

[0059] By the Law of Cosines, we can obtain: theta = arccos((m 2 +n 2 -l 2 ) / 2mn);

[0060] Euclidean distance dist calculation as follows Figure 3 As shown, taking the target vehicle as an example, for any tracked target, the position of its center point is known (x). c y c ).

[0061] Therefore, the Euclidean distance between the target location and the vehicle is:

[0062] In this embodiment of the application, after labeling the size of the target based on the target observation frame, the method further includes: obtaining the target observation frame corresponding to each target; storing the target observation frame corresponding to each target and the relevant information of the target observation frame in a preset database, wherein the relevant information includes at least one of target size, observation angle, and center point.

[0063] It is understood that the embodiments of this application can obtain the target observation frame corresponding to each target and store the target observation frame corresponding to each target and related information of the target observation frame in a preset database so that subsequent annotators can find the target information they need based on the preset database.

[0064] In this embodiment of the application, after labeling the size of the target based on the target observation frame, the method further includes: obtaining basic information of the target to be labeled and / or the target to be inspected; querying a preset database based on the basic information of the target to be labeled and / or the target to be inspected to obtain the target observation frame and related information of the target observation frame corresponding to the target to be labeled and / or the target to be inspected.

[0065] It is understood that the embodiments of this application can also obtain the basic information of the target to be labeled and / or the target to be inspected, and query the preset database based on the basic information of the target to be labeled and / or the target to be inspected to obtain the target observation frame and related information of the target observation frame, thereby directly obtaining the optimal labeling value of the target to be labeled or the target to be inspected without complicated operations, reducing the time and cost of manual quality inspection and error correction.

[0066] The target dimension annotation method of this application is illustrated below through a specific embodiment, such as... Figure 4 As shown.

[0067] 1. The vehicle-mounted camera collects image data, the LiDAR collects point cloud data, and records RTK positioning information;

[0068] 2. Input point cloud information into the offline cloud-based 3D point cloud inference model to generate 3D target attribute information;

[0069] 3. Camera images are input into an offline cloud-based visual inference model to generate 2D / 3D target attribute information;

[0070] 4. Input the positioning information and 2D / 3D target attribute information into the offline multi-sensor fusion module to generate matching information between the sensor-detected target and the tracked target;

[0071] 5. For each tracking target matching chain, statistically calculate the observed corner points and target center points of each target;

[0072] 6. Calculate the observable angle theta based on the observation corner point, calculate the Euclidean distance dist between the target and the vehicle based on the center point, and calculate and obtain the maximum angle and minimum distance respectively;

[0073] 7. Let the objective function be f(x) = Max(coeff). a *theta / theta max +coeff b *dist min / dist), (coeff a +coeff b =1.0), the maximum value result frame calculated by this function is the optimal observation point;

[0074] 8. Cache the results from step 7 in the detection target file, and cache the best frame observation value from step 7 as new information in each matching chain target;

[0075] 9. Enter the basic information of the target to be labeled or inspected (dataset, specific frame, initial center position, etc.) in the interactive interface;

[0076] 10. Obtain the input information from step 9 in the matching and recommendation module, and query the optimal value based on the cached file from step 8 based on the input information;

[0077] 11. Output the recommended observation frame with the optimal target size.

[0078] The above embodiments integrate offline visual detection models, LiDAR detection models, and multi-sensor fusion for annotation data preprocessing. Furthermore, the preprocessed data is used for target-level statistics, and an objective function is designed based on the statistical results. The optimal observation frame of the pre-annotated tracking target relative to the vehicle size is quantitatively analyzed, the quantification results are cached, and further presented to the annotators through interactive queries. The annotators can obtain the recommended results of the optimal size annotation frame through interactive queries, thereby improving the efficiency and accuracy of target size quality inspection annotation and reducing labor costs.

[0079] According to the target size annotation method proposed in the embodiments of this application, first target attribute information and second target attribute information can be generated based on image data and point cloud data respectively, and matched to obtain a target list. Then, the observation corner point and center point of each target in the target list are calculated. Based on the objective function, the observation corner point and center point of each target, the target observation frame corresponding to each target is calculated, and the target size is annotated based on the target observation frame. This improves the efficiency, accuracy and quality of target size annotation and reduces the cost of manual annotation.

[0080] Next, the target dimension marking device according to the embodiments of this application is described with reference to the accompanying drawings.

[0081] Figure 5 This is a block diagram of the target dimension marking device according to an embodiment of this application.

[0082] like Figure 5 As shown, the target size marking device 10 includes: an acquisition module 100, a matching module 200, and a calculation module 300.

[0083] The acquisition module 100 is used to acquire image data collected by the vehicle-mounted camera and point cloud data collected by the lidar; the matching module 200 is used to generate first target attribute information and second target attribute information based on the image data and point cloud data respectively, and to match the first target attribute information and the second target attribute information to obtain a target list; the calculation module 300 is used to calculate the observation corner point and center point of each target in the target list, and to calculate the target observation frame corresponding to each target according to the objective function, the observation corner point and center point of each target, so as to label the size of the target based on the target observation frame.

[0084] In this embodiment of the application, the matching module 200 is further used to: obtain the positioning information of the vehicle; and obtain a target list by matching the first target attribute information and the second target attribute information based on the positioning information.

[0085] In this embodiment of the application, the calculation module 300 is further configured to: calculate the observation corner point and center point of each target in each frame; calculate the observation angle of each frame based on the observation corner point of each frame, and calculate the Euclidean distance between the target and the vehicle in each frame based on the center point of each frame; obtain the maximum value of the observation angle and the minimum value of the Euclidean distance; and calculate the target observation frame corresponding to the target based on the maximum value of the observation angle, the minimum value of the Euclidean distance, and the objective function.

[0086] In this embodiment of the application, the objective function is:

[0087] f(x) = Max(coeff) a *theta / theta max +coeff b *dist min / dist);

[0088] Among them, oeff a As the first weighting coefficient, coeff b Coeff is the second weighting coefficient. a +coeff b =1.0, theta is the observation angle, theta max The maximum value in the observation angle, where dist is the Euclidean distance between the target and the vehicle. min This is the minimum value of the Euclidean distance.

[0089] In this embodiment of the application, the device 10 further includes a storage module.

[0090] The storage module is used to obtain the target observation frame corresponding to each target after labeling the size of the target based on the target observation frame; and to store the target observation frame corresponding to each target and the relevant information of the target observation frame in a preset database, wherein the relevant information includes at least one of the target size, observation angle, and center point.

[0091] In this embodiment of the application, the apparatus 10 further includes a query module.

[0092] The query module is used to obtain basic information about the target to be labeled and / or the target to be inspected after labeling the size of the target based on the target observation frame; and to query a preset database based on the basic information of the target to be labeled and / or the target to be inspected to obtain the target observation frame and related information of the target observation frame corresponding to the target to be labeled and / or the target to be inspected.

[0093] It should be noted that the foregoing explanation of the target dimension annotation method embodiment also applies to the target dimension annotation device of this embodiment, and will not be repeated here.

[0094] According to the target size annotation device proposed in the embodiments of this application, a first target attribute information and a second target attribute information can be generated based on image data and point cloud data respectively, and the target list can be obtained by matching them. Then, the observation corner point and center point of each target in the target list are calculated. Based on the objective function, the observation corner point and center point of each target, the target observation frame corresponding to each target is calculated, and the target size is annotated based on the target observation frame, which improves the efficiency and accuracy of target size annotation and reduces the cost of manual annotation.

[0095] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include:

[0096] The memory 601, the processor 602, and the computer program stored on the memory 601 and capable of running on the processor 602.

[0097] When the processor 602 executes the program, it implements the target size annotation method provided in the above embodiments.

[0098] Furthermore, electronic devices also include:

[0099] Communication interface 603 is used for communication between memory 601 and processor 602.

[0100] The memory 601 is used to store computer programs that can run on the processor 602.

[0101] The memory 601 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0102] If the memory 601, processor 602, and communication interface 603 are implemented independently, then the communication interface 603, memory 601, and processor 602 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0103] Optionally, in a specific implementation, if the memory 601, processor 602, and communication interface 603 are integrated on a single chip, then the memory 601, processor 602, and communication interface 603 can communicate with each other through an internal interface.

[0104] The processor 602 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0105] This application also provides a computer-readable storage medium storing a computer program or instructions thereon, which, when executed by a processor, implements the target dimension annotation method described above.

[0106] This application also provides a computer program product, including a computer program or instructions, which, when executed, implement the target dimension annotation method described above.

[0107] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0108] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0109] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0110] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0111] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

Claims

1. A target size labeling method, characterized by, The method comprises the following steps: acquiring picture data collected by a vehicle-mounted camera and point cloud data collected by a laser radar; generating first target attribute information and second target attribute information based on the picture data and the point cloud data respectively, and matching the first target attribute information and the second target attribute information to obtain a target list; calculating an observation angle point and a center point of each target in the target list, and calculating a target observation frame corresponding to each target according to a target function, the observation angle point and the center point of each target, so as to label a size of the target based on the target observation frame; the calculation of the target observation frame of each target according to the observation angle point, the center point and the target function comprises: calculating an observation angle point and a center point of each target in each frame; calculating an observation angle of each frame according to the observation angle point of each frame, and calculating a Euclidean distance between the target and the vehicle in each frame according to the center point of each frame; obtaining a maximum value of the observation angle and a minimum value of the Euclidean distance; and calculating the target observation frame corresponding to the target according to the maximum value of the observation angle, the minimum value of the Euclidean distance and the target function, wherein the target function is: ； wherein, is a first weight coefficient, is a second weight coefficient, , is an observation angle, is a maximum value in the observation angle, is a Euclidean distance between the target and the host vehicle, is a minimum value of the Euclidean distance.

2. The target size labeling method according to claim 1, characterized by, the matching of the first target attribute information and the second target attribute information to obtain the target list comprises: acquiring positioning information of the vehicle; matching the first target attribute information and the second target attribute information based on the positioning information to obtain the target list.

3. The target size labeling method according to claim 1, characterized by, After the size of the target is labeled based on the target observation frame, the method further comprises: acquiring the target observation frame corresponding to each target; storing the target observation frame corresponding to each target and related information of the target observation frame in a preset database, wherein the related information comprises at least one of a target size, an observation angle and a center point.

4. The target size labeling method according to claim 3, characterized by, After the size of the target is labeled based on the target observation frame, the method further comprises: acquiring basic information of a target to be labeled and / or a target to be inspected; querying a preset database based on the basic information of the target to be labeled and / or the target to be inspected to obtain the target observation frame corresponding to the target to be labeled and / or the target to be inspected and related information of the target observation frame.

5. A target size labeling apparatus characterized by comprising: The method comprises: an acquisition module, configured to acquire picture data collected by a vehicle-mounted camera and point cloud data collected by a laser radar; a matching module, configured to generate first target attribute information and second target attribute information based on the picture data and the point cloud data respectively, and match the first target attribute information and the second target attribute information to obtain a target list; a calculation module, configured to calculate an observation angle point and a center point of each target in the target list, and calculate a target observation frame corresponding to each target according to a target function, the observation angle point and the center point of each target, so as to label a size of the target based on the target observation frame; The target observation frame of each target is calculated according to the observation angle point, the center point and a target function, and the method comprises the following steps: calculating the observation angle point and the center point of each target in each frame; calculating the observation angle of each frame according to the observation angle point of each frame, and calculating the Euclidean distance between the target and the vehicle in each frame according to the center point of each frame; obtaining the maximum value of the observation angle and the minimum value of the Euclidean distance; and calculating the target observation frame corresponding to the target according to the maximum value of the observation angle, the minimum value of the Euclidean distance and the target function, wherein the target function is: ； wherein, is a first weight coefficient, is a second weight coefficient, , is an observation angle, is a maximum value in the observation angle, is a Euclidean distance between the target and the host vehicle, is a minimum value of the Euclidean distance.

6. An electronic device, comprising: comprises: A memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the target size labeling method according to any one of claims 1-4.

7. A computer readable storage medium having stored thereon a computer program or instructions, characterized in that, The computer program or instructions are executed by the processor to implement the target size labeling method according to any one of claims 1-4.

8. A computer program product comprising computer programs or instructions, characterized in that, The computer program or instructions are executed to implement the target size labeling method according to any one of claims 1-4.

Images