Point cloud data enhancement method and device, storage medium and electronic equipment

Abstract

The invention relates to a point cloud data enhancement method and device, a storage medium and electronic equipment. The point cloud data enhancement method comprises the following steps: acquiring sample data to be subjected to data enhancement; based on the sample data, taking the target data set as a data enhancement target, and performing sample data expansion in a data enhancement mode to obtain enhanced data of the sample data; and down-sampling the enhanced data of the sample data according to a predetermined down-sampling mode to obtain down-sampled data. According to the method, the predetermined downsampling mode can be determined according to the need of data enhancement of the sample data, so that the purpose of sample data enhancement is achieved.

Description

Technical Field

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

[0002] In general, a large amount of data is required for model training in machine learning and deep learning. However, when collecting sample data, sometimes there is insufficient sample data, which will cause unsatisfactory model training results. In such cases, data enhancement can sometimes be used to expand sample data to meet the needs of model training. Summary of the invention

[0003] In view of this, the embodiments of the present disclosure are intended to provide a point cloud data enhancement method, device, storage medium and electronic device.

[0004] The technical solution of the present disclosure is achieved as follows:

[0005] In a first aspect, the present disclosure provides a point cloud data enhancement method.

[0006] The point cloud data enhancement method provided by the embodiment of the present disclosure includes:

[0007] Obtain sample data to be enhanced;

[0008] Based on the sample data, taking the target data set as the data enhancement target, the sample data is expanded by a data enhancement method to obtain enhanced data of the sample data;

[0009] The enhanced data of the sample data is downsampled according to a predetermined downsampling method to obtain downsampled data.

[0010] In some embodiments, the method of expanding the sample data by data enhancement based on the sample data and taking the target data set as the data enhancement target to obtain enhanced data of the sample data includes:

[0011] Based on the data enhancement scenario of point cloud data enhancement, determine the data enhancement method of point cloud data;

[0012] Based on the data enhancement method determined by the data enhancement scenario, the sample data is expanded to obtain enhanced data of the sample data.

[0013] In some embodiments, the data enhancement scene includes expansion of objects at predetermined locations on both sides of the road;

[0014] The data enhancement method of the point cloud data is a data enhancement method determined based on the expansion method of the target objects at predetermined positions on both sides of the road in the physical space;

[0015] The data enhancement method determined based on the data enhancement scenario, performing sample data expansion to obtain enhanced data of the sample data, includes:

[0016] The sample data is expanded based on the data enhancement method determined based on the expansion method of the target objects at the predetermined positions on both sides of the road in the physical space to obtain enhanced data of the sample data.

[0017] In some embodiments, downsampling the enhanced data of the sample data according to a predetermined downsampling method to obtain downsampled data includes:

[0018] Determine a sampling rule for data downsampling; based on the sampling rule for data downsampling, downsample the enhanced data of the sample data to obtain downsampled data; wherein the sampling rule for data downsampling includes:

[0019] Determine a data downsampling ratio corresponding to the enhanced data based on the depth of the location where the target object corresponding to the enhanced data is placed;

[0020] Based on the data downsampling ratio corresponding to the enhanced data, the enhanced data corresponding to the target object is downsampled.

[0021] In some embodiments, the data downsampling ratio corresponding to the enhanced data is:

[0022] Among them, d 0 is the original distance of the sample target;

[0023] Z is the depth of the target placement position corresponding to the enhanced data.

[0024] In a second aspect, the present disclosure provides a point cloud data enhancement device, comprising:

[0025] A data acquisition module, used to acquire sample data to be enhanced;

[0026] A data enhancement module is used to expand the sample data by a data enhancement method based on the sample data and taking the target data set as the data enhancement target to obtain enhanced data of the sample data;

[0027] The data downsampling module is used to downsample the enhanced data of the sample data according to a predetermined downsampling method to obtain downsampled data.

[0028] In some embodiments, the data enhancement module is used to

[0029] Based on the data enhancement scenario of point cloud data enhancement, determine the data enhancement method of point cloud data;

[0030] Based on the data enhancement method determined by the data enhancement scenario, the sample data is expanded to obtain enhanced data of the sample data.

[0031] In some embodiments, the data enhancement scene includes expansion of objects at predetermined locations on both sides of the road;

[0032] The data enhancement method of the point cloud data is a data enhancement method determined based on the expansion method of the target objects at predetermined positions on both sides of the road in the physical space;

[0033] The data enhancement module is used to

[0034] The sample data is expanded based on the data enhancement method determined based on the expansion method of the target objects at the predetermined positions on both sides of the road in the physical space to obtain enhanced data of the sample data.

[0035] In a third aspect, the present disclosure provides a computer-readable storage medium having a point cloud data enhancement program stored thereon. When the point cloud data enhancement program is executed by a processor, the point cloud data enhancement method described in the first aspect is implemented.

[0036] In a fourth aspect, the present disclosure provides an electronic device comprising a memory, a processor, and a point cloud data enhancement program stored in the memory and executable on the processor, wherein when the processor executes the point cloud data enhancement program, the point cloud data enhancement method described in the first aspect is implemented.

[0037] According to the point cloud data enhancement method of the embodiment of the present disclosure, the method includes: obtaining sample data to be enhanced; based on the sample data, taking the target data set as the data enhancement target, expanding the sample data by a data enhancement method to obtain enhanced data of the sample data; downsampling the enhanced data of the sample data according to a predetermined downsampling method to obtain downsampled data. The predetermined downsampling method in the present application can be determined according to the need for data enhancement of the sample data to achieve the purpose of satisfying the sample data enhancement.

[0038] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will be obvious from the following description or learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a flow chart of a point cloud data enhancement method according to an exemplary embodiment;

[0040] Figure 2 is a schematic diagram of an original point cloud according to an exemplary embodiment;

[0041] Figure 3 is a schematic diagram of enhancing the original point cloud data according to an exemplary embodiment Figure 1;

[0042] Figure 4 is a schematic diagram of enhancing the original point cloud data according to an exemplary embodiment Figure 2 ;

[0043] Figure 5 is a schematic diagram of enhancing the original point cloud data according to an exemplary embodiment Figure 3 ;

[0044] Figure 6 It is a schematic diagram of the structure of a point cloud data enhancement device according to an exemplary embodiment. DETAILED DESCRIPTION

[0045] Embodiments of the present disclosure are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0046] In general, a large amount of data is required for model training in machine learning and deep learning. However, when collecting sample data, sometimes there is insufficient sample data, which will cause unsatisfactory model training results. In such cases, data enhancement can sometimes be used to expand sample data to meet the needs of model training.

[0047] In view of the above situation, the present disclosure provides a point cloud data enhancement method. Figure 1 FIG. 1 is a flow chart of a method for enhancing point cloud data according to an exemplary embodiment. Figure 1 As shown, the point cloud data enhancement method includes:

[0048] Step 10: Obtain sample data to be enhanced;

[0049] Step 11: Based on the sample data, taking the target data set as the data enhancement target, the sample data is expanded by a data enhancement method to obtain enhanced data of the sample data;

[0050] Step 12: downsample the enhanced data of the sample data according to a predetermined downsampling method to obtain downsampled data.

[0051] In this exemplary embodiment, the sample data can be determined according to the need for data enhancement. The sample data can be feature data used to characterize the target object, etc. The target data set can be data corresponding to the target object that needs target expansion after data enhancement. The target data set is used to characterize the object features of the target object expanded after data enhancement.

[0052] In this exemplary embodiment, since the enhanced data may not completely conform to the required enhanced data, the enhanced data may be downsampled to obtain downsampled data. The data downsampling method may be determined as required.

[0053] According to the point cloud data enhancement method of the embodiment of the present disclosure, the method includes: obtaining sample data to be enhanced; based on the sample data, taking the target data set as the data enhancement target, expanding the sample data by a data enhancement method to obtain enhanced data of the sample data; downsampling the enhanced data of the sample data according to a predetermined downsampling method to obtain downsampled data. The predetermined downsampling method in the present application can be determined according to the need for data enhancement of the sample data to achieve the purpose of satisfying the sample data enhancement.

[0054] In some embodiments, the method of expanding the sample data by data enhancement based on the sample data and taking the target data set as the data enhancement target to obtain enhanced data of the sample data includes:

[0055] Based on the data enhancement scenario of point cloud data enhancement, determine the data enhancement method of point cloud data;

[0056] Based on the data enhancement method determined by the data enhancement scenario, the sample data is expanded to obtain enhanced data of the sample data.

[0057] In this exemplary embodiment, Figure 2 is a schematic diagram of an original point cloud according to an exemplary embodiment. Figure 2 As shown, the sample data is Figure 2 The target object that needs data enhancement is the car. Figure 3 is a schematic diagram of enhancing the original point cloud data according to an exemplary embodiment Figure 1 . Figure 4 is a schematic diagram of enhancing the original point cloud data according to an exemplary embodiment Figure 2 . Figure 5 is a schematic diagram of enhancing the original point cloud data according to an exemplary embodiment Figure 3 .like Figure 3 , 4 As shown in Figures 5 and 6, enhanced data 1, enhanced data 2, and enhanced data 3 in the figure are enhanced data based on the extension of the target object. The data enhancement scenario of point cloud data enhancement may include the extension of the target object in the spatial layout. When the data enhancement scenario of point cloud data enhancement is the extension of the target object in the spatial layout, the data enhancement method of the point cloud data is the extension of the target object in the spatial layout, so as to facilitate the data enhancement method determined by the data enhancement scenario to expand the sample data and obtain the enhanced data of the sample data. Among them, the data volume corresponding to enhanced data 1, enhanced data 2 to enhanced data 3 can decrease successively.

[0058] In some embodiments, the data enhancement scene includes expansion of objects at predetermined locations on both sides of the road;

[0059] The data enhancement method of the point cloud data is a data enhancement method determined based on the expansion method of the target objects at predetermined positions on both sides of the road in the physical space;

[0060] The data enhancement method determined based on the data enhancement scenario, performing sample data expansion to obtain enhanced data of the sample data, includes:

[0061] The sample data is expanded based on the data enhancement method determined based on the expansion method of the target objects at the predetermined positions on both sides of the road in the physical space to obtain enhanced data of the sample data.

[0062] In this exemplary embodiment, the target object may be, for example, a car.

[0063] Based on the data enhancement method determined by the expansion method of the cars at the predetermined positions on both sides of the road in the physical space, the sample data is expanded to obtain the enhanced data of the sample data. For example, there should be cars at the interface positions on both sides of the road, and the expansion method of the cars at the predetermined positions on both sides of the road in the physical space is determined to perform data enhancement corresponding to the cars at the intersections on both sides of the road, so as to add cars at the intersections on both sides of the road.

[0064] In some embodiments, downsampling the enhanced data of the sample data according to a predetermined downsampling method to obtain downsampled data includes:

[0065] Determine sampling rules for data downsampling;

[0066] Based on the sampling rule of the data downsampling, the enhanced data of the sample data is downsampled to obtain downsampled data; wherein the sampling rule of the data downsampling includes:

[0067] Determine a data downsampling ratio corresponding to the enhanced data based on the depth of the location where the target object corresponding to the enhanced data is placed;

[0068] Based on the data downsampling ratio corresponding to the enhanced data, the enhanced data corresponding to the target object is downsampled.

[0069] In this exemplary embodiment, the sampling rule of data downsampling can be determined as needed. For example, based on the depth of the location where the target object corresponding to the enhanced data is placed, the data downsampling ratio corresponding to the enhanced data is determined; based on the data downsampling ratio corresponding to the enhanced data, the enhanced data corresponding to the target object is downsampled.

[0070] Among them, the data downsampling rate dense_rate corresponding to the enhanced data is:

[0071] Among them, d 0 is the original distance of the sample target;

[0072] Z is the depth of the target placement position corresponding to the enhanced data.

[0073] In this exemplary embodiment, the depth of the target placement position corresponding to the enhanced data is understood as the distance between the target placement position and the object corresponding to the sample data. The downsampled data corresponding to the target is the enhanced data corresponding to the target * the data downsampling ratio. In this way, the downsampled enhanced data corresponding to each target can be obtained by downsampling. In this exemplary embodiment, when determining the placement position of the target, the coordinate position can be determined by a laser radar to locate the target. For example, when the target is a car, a laser radar can be installed on each car, and the coordinate system of each laser radar can be unified by calibration parameters, that is, each laser radar is unified into one coordinate system.

[0074] In this exemplary embodiment, data prediction can also be performed by using a model trained with the downsampled enhanced data to determine the validity of the downsampled enhanced data through the prediction results of the model. For example, the prediction accuracy of the trained model is:

[0075] TP means predicting the positive class as positive, and FP means predicting the negative class as positive.

[0076] The present disclosure provides a point cloud data enhancement device. Figure 6 FIG. 1 is a schematic diagram of a point cloud data enhancement device according to an exemplary embodiment. Figure 6 As shown, the point cloud data enhancement device includes:

[0077] A data acquisition module 60 is used to acquire sample data to be enhanced;

[0078] A data enhancement module 61 is used to expand the sample data by a data enhancement method based on the sample data and taking a target data set as a data enhancement target to obtain enhanced data of the sample data;

[0079] The data downsampling module 62 is used to downsample the enhanced data of the sample data according to a predetermined downsampling method to obtain downsampled data.

[0080] In this exemplary embodiment, the sample data can be determined according to the need for data enhancement. The sample data can be feature data used to characterize the target object, etc. The target data set can be data corresponding to the target object that needs target expansion after data enhancement. The target data set is used to characterize the object features of the target object expanded after data enhancement.

[0081] In this exemplary embodiment, since the enhanced data may not completely conform to the required enhanced data, the enhanced data may be downsampled to obtain downsampled data. The data downsampling method may be determined as required.

[0082] According to the point cloud data enhancement device of the embodiment of the present disclosure, it is used to: obtain sample data to be enhanced; based on the sample data, take the target data set as the data enhancement target, expand the sample data through the data enhancement method to obtain the enhanced data of the sample data; downsample the enhanced data of the sample data according to the predetermined downsampling method to obtain the downsampled data. The predetermined downsampling method in this application can be determined according to the need for data enhancement of the sample data to achieve the purpose of satisfying the sample data enhancement.

[0083] In some embodiments, the data enhancement module is used to

[0084] Based on the data enhancement scenario of point cloud data enhancement, determine the data enhancement method of point cloud data;

[0085] Based on the data enhancement method determined by the data enhancement scenario, the sample data is expanded to obtain enhanced data of the sample data.

[0086] In this exemplary embodiment, the data enhancement scenario of point cloud data enhancement may include the extension and expansion of the target object in the spatial layout. When the data enhancement scenario of point cloud data enhancement is the extension and expansion of the target object in the spatial layout, the data enhancement method of the point cloud data is the extension and expansion method of the target object in the spatial layout, so that it is convenient to expand the sample data through the data enhancement method determined by the data enhancement scenario to obtain enhanced data of the sample data.

[0087] In some embodiments, the data enhancement scene includes expansion of objects at predetermined locations on both sides of the road;

[0088] The data enhancement method of the point cloud data is a data enhancement method determined based on the expansion method of the target objects at predetermined positions on both sides of the road in the physical space;

[0089] The data enhancement module is used to

[0090] The sample data is expanded based on the data enhancement method determined based on the expansion method of the target objects at the predetermined positions on both sides of the road in the physical space to obtain enhanced data of the sample data.

[0091] In this exemplary embodiment, the target object may be, for example, a car.

[0092] Based on the data enhancement method determined by the expansion method of the cars at the predetermined positions on both sides of the road in the physical space, the sample data is expanded to obtain the enhanced data of the sample data. For example, if there should be cars at the interface positions on both sides of the road, then the expansion method of the cars at the predetermined positions on both sides of the road in the physical space is determined to be data enhancement corresponding to the cars at the intersections on both sides of the road, so as to increase the cars at the intersections on both sides of the road. In some embodiments, the data downsampling module is used to

[0093] Determine sampling rules for data downsampling;

[0094] Based on the sampling rule of the data downsampling, the enhanced data of the sample data is downsampled to obtain downsampled data; wherein the sampling rule of the data downsampling includes:

[0095] Determine a data downsampling ratio corresponding to the enhanced data based on the depth of the location where the target object corresponding to the enhanced data is placed;

[0096] Based on the data downsampling ratio corresponding to the enhanced data, the enhanced data corresponding to the target object is downsampled.

[0097] In this exemplary embodiment, the sampling rule of data downsampling can be determined as needed. For example, based on the depth of the location where the target object corresponding to the enhanced data is placed, the data downsampling ratio corresponding to the enhanced data is determined; based on the data downsampling ratio corresponding to the enhanced data, the enhanced data corresponding to the target object is downsampled.

[0098] Among them, the data downsampling rate dense_rate corresponding to the enhanced data is:

[0099] Among them, d 0 is the original distance of the sample target;

[0100] Z is the depth of the target placement position corresponding to the enhanced data.

[0101] In this exemplary embodiment, the depth of the target placement position corresponding to the enhanced data is understood as the distance between the target placement position and the object corresponding to the sample data. The downsampled data corresponding to the target is the enhanced data corresponding to the target * the data downsampling ratio. In this way, the downsampled enhanced data corresponding to each target can be obtained by downsampling. In this exemplary embodiment, when determining the placement position of the target, the coordinate position can be determined by a laser radar to locate the target. For example, when the target is a car, a laser radar can be installed on each car, and the coordinate system of each laser radar can be unified by calibration parameters, that is, each laser radar is unified into one coordinate system.

[0102] The present disclosure provides a computer-readable storage medium, on which a point cloud data enhancement program is stored. When the point cloud data enhancement program is executed by a processor, the point cloud data enhancement method described in the above embodiments is implemented.

[0103] The present disclosure provides an electronic device, including a memory, a processor, and a point cloud data enhancement program stored in the memory and executable on the processor. When the processor executes the point cloud data enhancement program, the point cloud data enhancement method described in the above embodiments is implemented.

[0104] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or otherwise processing in a suitable manner if necessary, and then stored in a computer memory.

[0105] It should be understood that the various parts of the present disclosure can be implemented in hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0106] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0107] In the description of the present disclosure, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present disclosure and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present disclosure.

[0108] In addition, the terms "first", "second", etc. used in the embodiments of the present disclosure are only used for descriptive purposes and should not be understood as indicating or implying relative importance, or implicitly indicating the number of technical features indicated in the embodiments. Therefore, the features defined by the terms "first", "second", etc. in the embodiments of the present disclosure may explicitly or implicitly indicate that at least one of the features is included in the embodiment. In the description of the present disclosure, the word "multiple" means at least two or two or more, such as two, three, four, etc., unless otherwise clearly and specifically defined in the embodiments.

[0109] In the present disclosure, unless otherwise clearly specified or limited in the embodiments, the terms "installed", "connected", "connected" and "fixed" etc. appearing in the embodiments should be understood in a broad sense. For example, the connection can be a fixed connection, a detachable connection, or an integrated connection. It can be understood that it can also be a mechanical connection, an electrical connection, etc.; of course, it can also be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal connection of two elements, or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present disclosure can be understood according to the specific implementation situation.

[0110] In the present disclosure, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0111] Although the embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present disclosure. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present disclosure.

Claims

1. A point cloud data enhancement method, characterized in that: include: Obtain sample data to be enhanced; Based on the sample data, taking the target data set as the data enhancement target, the sample data is expanded by a data enhancement method to obtain enhanced data of the sample data; The enhanced data of the sample data is downsampled according to a predetermined downsampling method to obtain downsampled data.

2. The point cloud data enhancement method according to claim 1, characterized in that: The method of taking the target data set as the data enhancement target based on the sample data and expanding the sample data by a data enhancement method to obtain enhanced data of the sample data includes: Based on the data enhancement scenario of point cloud data enhancement, determine the data enhancement method of point cloud data; Based on the data enhancement method determined by the data enhancement scenario, the sample data is expanded to obtain enhanced data of the sample data.

3. The point cloud data enhancement method according to claim 2, characterized in that: The data enhancement scenario includes the expansion of target objects at predetermined positions on both sides of the road; The data enhancement method of the point cloud data is a data enhancement method determined based on the expansion method of the target objects at predetermined positions on both sides of the road in the physical space; The data enhancement method determined based on the data enhancement scenario, performing sample data expansion to obtain enhanced data of the sample data, includes: The sample data is expanded based on the data enhancement method determined based on the expansion method of the target objects at the predetermined positions on both sides of the road in the physical space to obtain enhanced data of the sample data.

4. The point cloud data enhancement method according to claim 1, characterized in that: The downsampling the enhanced data of the sample data according to a predetermined downsampling method to obtain downsampled data includes: Determine a sampling rule for data downsampling; based on the sampling rule for data downsampling, downsample the enhanced data of the sample data to obtain downsampled data; wherein the sampling rule for data downsampling includes: Determine a data downsampling ratio corresponding to the enhanced data based on the depth of the location where the target object corresponding to the enhanced data is placed; Based on the data downsampling ratio corresponding to the enhanced data, the enhanced data corresponding to the target object is downsampled.

5. The point cloud data enhancement method according to claim 4, characterized in that: The data downsampling ratio corresponding to the enhanced data is: Where d0 is the original distance of the sample target; Z is the depth of the target placement position corresponding to the enhanced data.

6. A point cloud data enhancement device, characterized in that: include: A data acquisition module, used to acquire sample data to be enhanced; A data enhancement module is used to expand the sample data by a data enhancement method based on the sample data and taking the target data set as the data enhancement target to obtain enhanced data of the sample data; The data downsampling module is used to downsample the enhanced data of the sample data according to a predetermined downsampling method to obtain downsampled data.

7. The point cloud data enhancement device according to claim 6, characterized in that: The data enhancement module is used to Based on the data enhancement scenario of point cloud data enhancement, determine the data enhancement method of point cloud data; Based on the data enhancement method determined by the data enhancement scenario, the sample data is expanded to obtain enhanced data of the sample data.

8. The point cloud data enhancement device according to claim 7, characterized in that: The data enhancement scenario includes the expansion of target objects at predetermined positions on both sides of the road; The data enhancement method of the point cloud data is a data enhancement method determined based on the expansion method of the target objects at predetermined positions on both sides of the road in the physical space; The data enhancement module is used to The sample data is expanded based on the data enhancement method determined based on the expansion method of the target objects at the predetermined positions on both sides of the road in the physical space to obtain enhanced data of the sample data.

9. A computer-readable storage medium, characterized in that: A point cloud data enhancement program is stored thereon, and when the point cloud data enhancement program is executed by a processor, the point cloud data enhancement method described in any one of claims 1-5 is implemented.

10. An electronic device, characterized in that: The method comprises a memory, a processor and a point cloud data enhancement program stored in the memory and executable on the processor. When the processor executes the point cloud data enhancement program, the point cloud data enhancement method described in any one of claims 1 to 5 is implemented.

Images