CN112489105B - Structured parameter representation acquisition method and device - Google Patents
Structured parameter representation acquisition method and device Download PDFInfo
- Publication number
- CN112489105B CN112489105B CN201910786995.1A CN201910786995A CN112489105B CN 112489105 B CN112489105 B CN 112489105B CN 201910786995 A CN201910786995 A CN 201910786995A CN 112489105 B CN112489105 B CN 112489105B
- Authority
- CN
- China
- Prior art keywords
- target object
- parameter representation
- structural parameter
- point
- model parameters
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000005457 optimization Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 239000002131 composite material Substances 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 14
- 241000283070 Equus zebra Species 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 239000007787 solid Substances 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a method and a device for obtaining a structured parameter representation, wherein the method comprises the following steps: obtaining preset model parameters of a target object corresponding to the point cloud to be processed; calculating a first outer envelope point of the target object; fitting the target object in the point cloud to be processed according to preset model parameters of the target object to obtain a first structural parameter representation of the target object; adjusting the first structural parameter representation according to the first outer envelope point to obtain a second structural parameter representation of the target object, wherein the matching degree between the second structural parameter representation and the first outer envelope point meets a preset condition; the method has the advantages that the accurate and efficient structured parameter representation acquisition is realized, and the structured parameter representation of the target object with the accuracy meeting the requirement is obtained, so that the manual marking is replaced, the manual intervention is avoided, and the influence of the conditions of overlarge point cloud noise, key point missing and the like on the structured parameter representation is also avoided.
Description
Technical Field
The disclosure relates to the field of image processing, and in particular relates to a method and a device for acquiring structural parameter representation.
Background
When a high-precision point cloud map is manufactured, parameterization is usually required to be performed on the point cloud of the target object, so that a structured parameter representation of the target object is obtained.
Currently, the surrounding outline of the object is marked in the point cloud of the object mainly by means of manual marking, and then the geometric parameters of the marked surrounding outline are determined as the structural parameter representation of the object.
Disclosure of Invention
When the surrounding outline of the target object is marked in the point cloud of the target object in a manual marking mode, the manual intervention degree is extremely high, the phenomena of overlarge noise, key point missing and the like possibly exist in the point cloud of the target object, and the anchor points (corresponding to the outer surrounding control points of the target object) surrounding the outline are not easy to mark accurately, so that the accuracy of the geometric parameters of the subsequently obtained point cloud is low.
The present disclosure has been made in order to solve the above technical problems. The embodiment of the disclosure provides a method and a device for obtaining a structured parameter representation, and the obtained structured parameter representation is more accurate.
According to a first aspect of the present disclosure, there is provided a structured parameter representation acquisition method, comprising:
obtaining preset model parameters of a target object corresponding to the point cloud to be processed;
calculating a first outer envelope point of the target object;
fitting the target object in the point cloud to be processed according to preset model parameters of the target object to obtain a first structural parameter representation of the target object;
and adjusting the first structural parameter representation according to the first outer envelope point to obtain a second structural parameter representation of the target object, wherein the matching degree between the second structural parameter representation and the first outer envelope point meets a preset condition.
According to a second aspect of the present disclosure, there is provided a structured parameter representation acquisition apparatus comprising:
the standard value acquisition module is used for acquiring preset model parameters of the target object corresponding to the point cloud to be processed;
the calculating module is used for calculating a first outer envelope point of the target object;
the model construction module is used for fitting the target object in the point cloud to be processed according to preset model parameters of the target object to obtain a first structural parameter representation of the target object;
and the optimization processing module is used for adjusting the first structural parameter representation according to the first outer envelope point to obtain a second structural parameter representation of the target object, wherein the matching degree between the second structural parameter representation and the first outer envelope point meets a preset condition.
According to a third aspect of the present disclosure, there is provided a computer-readable storage medium storing a computer program for executing the structured parameter representation acquisition method described in the first aspect above.
According to a fourth aspect of the present disclosure, there is provided an electronic device comprising: a processor; a memory for storing the processor-executable instructions;
the processor is configured to read the executable instruction from the memory and execute the executable instruction to implement the method for obtaining the structured parameter representation in the first aspect.
Compared with the prior art, the method and the device for acquiring the structured parameter representation, provided by the disclosure, have the advantages that the first structured parameter representation is determined through the preset model parameters with universality for the specific target object, and then the first structured parameter representation is adjusted according to the first outer envelope point, so that the second structured parameter representation accurately representing the real form of the target object is obtained; the method has the advantages that the accurate and efficient structured parameter representation acquisition is realized, and the structured parameter representation of the target object with the accuracy meeting the requirement is obtained, so that the manual marking is replaced, the manual intervention is avoided, and the influence of the conditions of overlarge point cloud noise, key point missing and the like on the structured parameter representation is also avoided.
Drawings
The above and other objects, features and advantages of the present disclosure will become more apparent by describing embodiments thereof in more detail with reference to the accompanying drawings. The accompanying drawings are included to provide a further understanding of embodiments of the disclosure, and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure, without limitation to the disclosure. In the drawings, like reference numerals generally refer to like parts or steps.
FIG. 1 is a schematic diagram of a structured parametric representation acquisition system provided by an exemplary embodiment of the present disclosure;
FIG. 2 is a flow chart of a method for obtaining a structured parameter representation according to an exemplary embodiment of the present disclosure;
FIG. 3 is a flow chart of a method for obtaining a structured parameter representation according to an exemplary embodiment of the present disclosure;
FIG. 4 is a flow chart of a method for obtaining a structured parameter representation according to an exemplary embodiment of the present disclosure;
FIG. 5-1 is a schematic view of a scenario in a structured parameter representation acquisition method according to an exemplary embodiment of the present disclosure;
FIG. 5-2 is a schematic view of a scenario in a structured parameter representation acquisition method according to an exemplary embodiment of the present disclosure;
5-3 are schematic diagrams of a scenario in a structured parameter representation acquisition method according to an exemplary embodiment of the present disclosure;
FIG. 6 is a schematic structural diagram of a device for obtaining a structured parameter representation according to an exemplary embodiment of the present disclosure;
FIG. 7 is a schematic structural diagram of a device for obtaining a structured parameter representation according to an exemplary embodiment of the present disclosure;
fig. 8 is a block diagram of an electronic device according to an exemplary embodiment of the present disclosure.
Detailed Description
Hereinafter, example embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present disclosure and not all of the embodiments of the present disclosure, and that the present disclosure is not limited by the example embodiments described herein.
Summary of the application
In the above-mentioned known process, when a high-precision point cloud map is manufactured, it is generally necessary to perform parameterization on a point cloud of a target object to obtain a structured parameter representation of the target object. In general, the object may be an element in a road environment, such as various traffic signs, street lamps, signal lamps, various road signs, zebra crossings, etc. on a road surface.
In the prior art, the surrounding outline of the object is marked in the point cloud of the object in a manual marking mode, and then the geometric parameters of the marked surrounding outline are determined as the structural parameter representation of the object. However, the manual intervention degree of the method is extremely high, and the phenomena of overlarge noise, missing key points and the like may exist in the point cloud of the target object, so that the outer envelope control points of the target object are not easy to accurately mark, and the accuracy of the structural parameter representation obtained later is low.
The method and the device for obtaining the structural parameter representation are used for obtaining the corresponding structural parameter representation by fitting and further adjusting the preset model parameters of the target object and the first outer envelope point of the target object, so that manual intervention is avoided, and the accuracy of the structural parameter representation is improved.
Exemplary System
As shown in fig. 1, a structural schematic diagram of a structural parameter representation acquisition system provided in the present disclosure. Through the operation flow of the system, the whole thought of the disclosure for the acquisition of the structural parameter representation can be reflected. In the system, the corresponding target object can be determined by carrying out semantic segmentation on the point cloud to be processed. Through the target object, on one hand, the preset model parameters corresponding to the target object can be determined, and on the other hand, the first external envelope point of the target object can be determined. Then fitting according to a preset model parameter to obtain a first structural parameter representation; and adjusting the first structural parameter representation according to the first envelope point to obtain a second structural parameter representation which accurately accords with the shape of the target object in the point cloud.
Exemplary method
Fig. 2 is a flow chart illustrating a method for obtaining a structured parameter representation according to an exemplary embodiment of the present disclosure. The present embodiment may be applied to an electronic device, as shown in fig. 2, and includes the following steps:
step 201, obtaining preset model parameters of a target object corresponding to a point cloud to be processed.
After the point cloud to be processed is obtained, semantic segmentation can be performed on the point cloud to be processed, and the target object included in the point cloud to be processed is determined. The object is the object for subsequent determination of the structured parameter representation. The target object can be various elements for expressing road information in a road environment, such as various traffic signs, street lamps, signal lamps, various road marks on the road surface, zebra crossings and the like.
Since the object is generally various elements expressing road information, there is often a corresponding national standard for the shape and structure of the object. That is, a specific kind of object generally adopts a fixed system. Therefore, corresponding preset model parameters can be determined in advance for various types of targets according to the description of the target line structure in the national standard in advance.
When the object is a single shape (e.g., a common traffic sign is typically rectangular, circular, or polygonal), the preset model parameters of the object indicate the geometry of the object. When the object is a composite shape that includes a plurality of components (e.g., a common pavement marker "zebra stripes" is a composite shape that includes a plurality of rectangles, each of which can be considered a component), the predetermined model parameters of the object indicate the positional relationship between the various components of the object and the geometry of each component.
After a specific target object is determined according to the point cloud to be processed, the preset model parameters corresponding to the target object can be determined correspondingly.
Step 202, calculating a first envelope point of the target object.
After a specific target object is determined according to the point cloud to be processed, a first enveloping point of the target object can be obtained through calculation according to the actual point cloud distribution of the point cloud to be processed. The first envelope point is a series of points in the point cloud to be processed, which are determined through calculation. The series of points represent the outline of the target in the point cloud to be processed, and in the embodiment, the outline, namely the real outline of the target, can be used as the basis for the subsequent establishment of structural parameter representation. Taking a rectangular signboard as an example, the first outer envelope points may be four corner points of the signboard.
The specific manner of calculating and determining the first envelope point is not limited in this embodiment. All calculation modes capable of realizing the same or similar effects can be combined in the whole technical scheme of the embodiment.
And 203, fitting the target object in the point cloud to be processed according to the preset model parameters of the target object, and obtaining a first structural parameter representation of the target object.
The preset model parameters indicate the geometric structure and the position relation of the object or each component in the object, and also comprise standard numerical values of each parameter (such as size, pose and the like) in the object. If a structured parametric representation is to be built up in this way, the missing information includes the position of the object. In the step, a target object is fitted in a point cloud to be processed to obtain a first structural parameter representation of the target object, namely, a preset model parameter is positioned according to the position of the target object reflected in the point cloud to be processed, so that an initial structural parameter representation for the target object, namely, the first structural parameter representation is obtained.
Step 204, adjusting the first structural parameter representation according to the first envelope point to obtain a second structural parameter representation of the target object.
It will be appreciated that the various parameters in the first structured parameter representation are merely specified standard values, and may generally be in and out of true values for the object. And the determination of the first structured parameter representation position may also be inaccurate during the fitting in the point cloud to be processed. It is clear that often the accuracy of the first structured parameter representation is not satisfactory.
Whereas the previously known first envelope point represents a contour, which is considered to be the true contour of the object. The first structured parameter representation will be adjusted in this step according to the first envelope point such that the structured parameter representation is more consistent with the first envelope point. Specifically, parameters such as pose and/or size of the first structural parameter representation may be adjusted, so as to obtain a second structural parameter representation of the target object. Wherein the degree of matching between the second structural parameter representation and the first outer envelope point needs to satisfy a preset condition. That is, the second structural parameter obtained by adjustment represents the outline of the embodied object, and the outline should be sufficiently fit with the first outer envelope point, so that the adjustment is considered to be successful. The second structured parameter representation is now the exact structured parameter representation of the object.
According to the technical scheme, the beneficial effects of the embodiment are as follows: determining a first structural parameter representation through a preset model parameter with universality for a specific target object, and adjusting the first structural parameter representation according to a first outer envelope point to obtain a second structural parameter representation accurately reflecting the real form of the target object; the method has the advantages that the accurate and efficient structured parameter representation acquisition is realized, and the structured parameter representation of the target object with the accuracy meeting the requirement is obtained, so that the manual marking is replaced, the manual intervention is avoided, and the influence of the conditions of overlarge point cloud noise, key point missing and the like on the structured parameter representation is also avoided.
As shown in fig. 2, only the basic embodiment of the method disclosed in the present disclosure is shown, and certain optimization and expansion are performed on the basis of the basic embodiment, so that other preferred embodiments of the method can be obtained.
Fig. 3 is a schematic flow chart of a method for obtaining a structured parameter representation according to another exemplary embodiment of the present disclosure. The embodiment can be applied to electronic equipment. In this embodiment, the adjustment process of the first structural parameter representation will be specifically described with respect to different types of objects. As shown in fig. 3, the present embodiment includes the steps of:
step 301, obtaining preset model parameters of a target object corresponding to the point cloud to be processed.
Step 302, calculating a first envelope point of the target object.
Step 303, fitting the target object in the point cloud to be processed according to the preset model parameters of the target object, and obtaining a first structural parameter representation of the target object.
The above steps are consistent with those of the embodiment shown in fig. 2, and are not described herein.
It should be noted that, when the object is in a single shape (for example, a common traffic sign is generally rectangular, circular or polygonal), the preset model parameters of the object indicate the geometry of the object. The method in this embodiment proceeds to step 304.
When the object is a composite shape that includes a plurality of components (e.g., a common pavement marker "zebra stripes" is a composite shape that includes a plurality of rectangles, each of which can be considered a component), the predetermined model parameters of the object indicate the positional relationship between the various components of the object and the geometry of each component. The method in this embodiment proceeds to step 305.
And step 304, adjusting the pose and/or the size of the first structural parameter representation according to the first envelope point to obtain a second structural parameter representation of the target object.
In the case of a single shape of the object, the object can be considered as a whole and directly adjusted to make the structural parameter representation more consistent with the first envelope point. Specifically, parameters such as pose and/or size of the first structural parameter representation may be adjusted, so as to obtain a second structural parameter representation of the target object.
Step 305, according to the first envelope point and the position relationship between the components of the target indicated by the preset model parameters of the target, adjusting the relative positions between the component models corresponding to the components in the first structural parameter representation of the target, and adjusting the pose and/or size of each component model, to obtain the second structural parameter representation of the target.
When the object is in a composite shape, parameters such as pose, size and the like of each component of the object can be independently adjusted, and the position relation among the components is adjusted at the same time, so that the structural parameter representation is more consistent with the first envelope point. And a second structured parametric representation of the object is obtained.
In steps 304 to 305, the degree of matching between the adjusted second structural parameter representation and the first envelope point meets a preset condition. The description of the preset condition is referred to the embodiment shown in fig. 2, and will not be repeated here.
In addition, the adjustments to the first structured parameter representation in steps 304-305 include adjustments to pose and/or size. Wherein adjusting the pose may be considered adjusting the orientation of the object or a component of the object; resizing may be considered as resizing the object or a component of the object. Of course, other relevant parameters may be further adjusted according to the need in the actual situation, which is not limited in this embodiment, and any similar adjustment method may be combined in the overall scheme of this embodiment.
According to the technical scheme, the embodiment has the following beneficial effects on the basis of the embodiment shown in fig. 2: the manner of adjustment of the first structured parameter representation is disclosed in detail in connection with the different types of objects.
Fig. 4 is a flow chart illustrating a method for obtaining a structured parameter representation according to another exemplary embodiment of the present disclosure. The embodiment can be applied to electronic equipment. In this embodiment, the adjustment process of the first structural parameter representation will be specifically described with reference to a specific scenario. As shown in fig. 4, the present embodiment includes the steps of:
step 401, obtaining preset model parameters of a target object corresponding to the point cloud to be processed.
In this embodiment, a target is taken as a "zebra stripes" as an example. Since the "zebra stripes" are a composite shape, which includes a plurality of rectangles, one rectangle is considered a component. The preset model parameters of the object indicate the positional relationship between the individual rectangular components of the object and the geometry of each component. Specifically, the positional relationship between the rectangular components is the vertical distance between two adjacent rectangles; the geometry of the assembly is the value of the length and width of the rectangle.
Step 402, calculating a first envelope point of the object.
Fig. 5-1 is a schematic diagram showing the distribution of the first envelope points calculated by the point cloud to be processed of the zebra stripes, wherein solid circles in the diagram represent the first envelope points. The two solid rectangular boxes in fig. 5-1 represent two rectangular components in the "zebra stripes" in the point cloud to be processed.
And step 403, fitting the target object in the point cloud to be processed according to the preset model parameters of the target object, and obtaining a first structural parameter representation of the target object.
As shown in fig. 5-2, i.e. the target morphology embodied in the first structured parametric representation. The two dashed rectangular boxes in fig. 5-2 represent two rectangular components in the "zebra stripes" in the first structural parametric representation. It can be seen that the solid rectangular assembly at this time is of greater value, both in vertical distance and width, than the dashed rectangular assembly. That is, the first structured parameter representation is not capable of accurately representing the morphology of the target.
Step 404, adjusting the first structural parameter representation according to the first envelope point to obtain a third structural parameter representation.
In this embodiment, parameters of the first structural parameter representation are adjusted according to the first envelope point to obtain a third structural parameter representation. Reference is made to the embodiment shown in fig. 3 for a specific way of adjusting the parameters of the first structured parameter representation.
In this embodiment, the adjusted parameters specifically include a vertical distance between two adjacent rectangles in the first structural parameter representation; and rectangular length and width values.
Step 405, determining second envelope points corresponding to the first envelope points one by one from the third structured parameter representation.
After the adjusted third structural parameter representation is determined, a second outer envelope point corresponding to the first outer envelope point one to one can be determined according to the third structural parameter representation. The second envelope point then represents the contour of the object represented by the third structured parametric representation. As shown in fig. 5-3, i.e. a distribution diagram of the first envelope point and the second envelope point. In fig. 5-3, solid dots represent the first envelope points and hollow dots represent the second envelope points.
Step 406, calculating the matching degree of the third structural parameter representation according to the distance between the first envelope point and the second envelope point corresponding to the first envelope point.
If the specific proximity between the first and second envelope points is the more consistent the third structured parameter representation is with the first envelope point, i.e. the higher the accuracy of the third structured parameter representation. The degree of matching of the third structured parameter representation can be calculated from the distance between the first envelope point and its corresponding second envelope point.
Specifically, the sum of the distances between the corresponding first envelope point and the corresponding second envelope point can be calculated, and the sum of the distances is used as an index for measuring the matching degree.
Step 407, determining the matching degree satisfying the preset condition, and determining the third structural parameter representation corresponding to the determined matching degree satisfying the preset condition as the second structural parameter representation.
In this embodiment, the degree of matching satisfying the preset condition, that is, the numerical threshold value for the sum of the distances may be determined in advance. When the sum of the distances of the first envelope point and the second envelope point is smaller than the sum of the distances, the third structured parameter is considered to be indicative of meeting the preset condition. And further determining the third structural parameter representation corresponding to the determined matching degree meeting the preset condition as the second structural parameter representation. Otherwise, if the third structural parameter representation does not satisfy the preset condition, the process returns to step 404 to readjust the first structural parameter representation.
According to the technical scheme, the embodiment has the following beneficial effects on the basis of the embodiment shown in fig. 2: the adjustment mode of the first structural parameter representation is disclosed in detail in combination with a specific application scene.
Exemplary apparatus
Fig. 6 is a schematic structural diagram of a structural parameter representation acquisition device according to an exemplary embodiment of the present disclosure. The apparatus of this embodiment is a physical apparatus for performing the methods of fig. 2 to 4. The technical solution is essentially identical to the above embodiment, and the corresponding description in the above embodiment is also applicable to this embodiment. The device in this embodiment includes:
the standard value obtaining module 601 is configured to obtain a preset model parameter of a target object corresponding to a point cloud to be processed.
A calculation module 602, configured to calculate a first envelope point of the object.
The model construction module 603 is configured to fit the target object in the point cloud to be processed according to a preset model parameter of the target object, so as to obtain a first structural parameter representation of the target object.
The optimization processing module 604 is configured to adjust the first structural parameter representation according to the first envelope point to obtain a second structural parameter representation of the target object, where a matching degree between the second structural parameter representation and the first envelope point meets a preset condition.
Fig. 7 is a schematic structural diagram of an optimization processing module 604 in a structural parameter representation acquisition device according to another exemplary embodiment of the present disclosure. As shown in fig. 7, in an exemplary embodiment, the optimization processing module 604 includes:
an adjustment processing unit 711 is configured to adjust the first structural parameter representation according to the first outer envelope point, so as to obtain a third structural parameter representation.
And the control point determining unit 712 is configured to determine, from the third structural parameter representation, second envelope points that are in one-to-one correspondence with the first envelope points.
A calculating unit 713 for calculating the matching degree of the third structured parameter representation according to the distance between the first envelope point and its corresponding second envelope point.
The parameter determining unit 714 determines the degree of matching that satisfies the preset condition, and determines the third structural parameter representation corresponding to the determined degree of matching that satisfies the preset condition as the second structural parameter representation.
In addition, when the preset model parameters of the target indicate the geometric structure of the target; the optimization processing module 604 is specifically configured to adjust the pose and/or the size of the first structural parameter representation according to the first outer envelope point.
Or when the preset model parameters of the target object indicate the position relation among the components of the target object and the geometric structure of each component; the optimization processing module 604 is specifically configured to adjust the relative positions between component models corresponding to the components in the first structural parameter representation of the target object according to the first outer envelope point and the positional relationship between the components of the target object indicated by the preset model parameters of the target object, and adjust the pose and/or the size of each component model.
Exemplary electronic device
Next, an electronic device according to an embodiment of the present disclosure is described with reference to fig. 8. The electronic device may be either or both of the first device 100 and the second device 200, or a stand-alone device independent thereof, which may communicate with the first device and the second device to receive the acquired input signals therefrom.
Fig. 8 illustrates a block diagram of an electronic device according to an embodiment of the disclosure.
As shown in fig. 8, the electronic device 10 includes one or more processors 11 and a memory 12.
The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.
Memory 12 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random Access Memory (RAM) and/or cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on the computer readable storage medium that can be executed by the processor 11 to implement the structured parameter representation acquisition method and/or other desired functions of the various embodiments of the present disclosure described above. Various contents such as an input signal, a signal component, a noise component, and the like may also be stored in the computer-readable storage medium.
In one example, the electronic device 10 may further include: an input device 13 and an output device 14, which are interconnected by a bus system and/or other forms of connection mechanisms (not shown).
For example, when the electronic device is the first device 100 or the second device 200, the input means 13 may be a microphone or a microphone array as described above for capturing an input signal of a sound source. When the electronic device is a stand-alone device, the input means 13 may be a communication network connector for receiving the acquired input signals from the first device 100 and the second device 200.
In addition, the input device 13 may also include, for example, a keyboard, a mouse, and the like.
The output device 14 may output various information to the outside, including the determined distance information, direction information, and the like. The output device 14 may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, etc.
Of course, only some of the components of the electronic device 10 relevant to the present disclosure are shown in fig. 8, with components such as buses, input/output interfaces, etc. omitted for simplicity. In addition, the electronic device 10 may include any other suitable components depending on the particular application.
Exemplary computer program product and computer readable storage Medium
In addition to the methods and apparatus described above, embodiments of the present disclosure may also be a computer program product comprising computer program instructions toComputer programThe instructions, when executed by a processor, cause the processor to perform steps in a structured parameter representation acquisition method according to various embodiments of the present disclosure described in the "exemplary methods" section of this specification.
The computer program product may write program code for performing the operations of embodiments of the present disclosure in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present disclosure may also be a computer-readable storage medium, having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform the steps in a structured parameter representation acquisition method according to various embodiments of the present disclosure described in the above "exemplary methods" section of the present description.
The computer readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The basic principles of the present disclosure have been described above in connection with specific embodiments, however, it should be noted that the advantages, benefits, effects, etc. mentioned in the present disclosure are merely examples and not limiting, and these advantages, benefits, effects, etc. are not to be considered as necessarily possessed by the various embodiments of the present disclosure. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, since the disclosure is not necessarily limited to practice with the specific details described.
The block diagrams of the devices, apparatuses, devices, systems referred to in this disclosure are merely illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.
It is also noted that in the apparatus, devices and methods of the present disclosure, components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered equivalent to the present disclosure.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the disclosure to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.
Claims (10)
1. A structured parametric representation acquisition method, comprising:
obtaining preset model parameters of a target object corresponding to the point cloud to be processed; when the target object is in a single shape, the preset model parameters of the target object indicate the geometric structure of the target object; when the object is a composite shape including a plurality of components, the preset model parameters of the object indicate the position relationship among the components of the object and the geometric structure of each component;
calculating a first outer envelope point of the target object;
fitting the target object in the point cloud to be processed according to preset model parameters of the target object to obtain a first structural parameter representation of the target object;
and adjusting the first structural parameter representation according to the first outer envelope point to obtain a second structural parameter representation of the target object, wherein the matching degree between the second structural parameter representation and the first outer envelope point meets a preset condition.
2. The method of claim 1, wherein,
the preset model parameters of the target indicate the geometric structure of the target;
said adjusting said first structured parameter representation according to said first outer envelope point comprises:
and adjusting the pose and/or the size of the first structural parameter representation according to the first outer envelope point.
3. The method of claim 1, wherein,
the preset model parameters of the target object indicate the position relation among the components of the target object and the geometric structure of each component;
said adjusting said first structured parameter representation according to said first outer envelope point comprises:
according to the first envelope point and the position relation among all the components of the target object indicated by the preset model parameters of the target object, adjusting the relative positions among component models corresponding to all the components in the first structural parameter representation of the target object respectively, and adjusting the pose and/or the size of each component model.
4. A method according to any one of claim 1 to 3, wherein,
the adjusting the first structural parameter representation according to the first outer envelope point to obtain a second structural parameter representation of the target object includes:
adjusting the first structural parameter representation according to the first outer envelope point to obtain a third structural parameter representation;
determining second envelope points corresponding to the first envelope points one by one from the third structured parameter representation;
calculating the matching degree of the third structural parameter representation according to the distance between the first envelope point and the second envelope point corresponding to the first envelope point;
and determining the matching degree meeting the preset condition, and determining the third structural parameter representation corresponding to the determined matching degree meeting the preset condition as a second structural parameter representation.
5. A structured parametric representation acquisition apparatus comprising:
the standard value acquisition module is used for acquiring preset model parameters of the target object corresponding to the point cloud to be processed; when the target object is in a single shape, the preset model parameters of the target object indicate the geometric structure of the target object; when the object is a composite shape including a plurality of components, the preset model parameters of the object indicate the position relationship among the components of the object and the geometric structure of each component;
the calculating module is used for calculating a first outer envelope point of the target object;
the model construction module is used for fitting the target object in the point cloud to be processed according to preset model parameters of the target object to obtain a first structural parameter representation of the target object;
and the optimization processing module is used for adjusting the first structural parameter representation according to the first outer envelope point to obtain a second structural parameter representation of the target object, wherein the matching degree between the second structural parameter representation and the first outer envelope point meets a preset condition.
6. The apparatus of claim 5, wherein,
the preset model parameters of the target indicate the geometric structure of the target;
the optimization processing module is used for adjusting the pose and/or the size of the first structural parameter representation according to the first outer envelope point.
7. The apparatus of claim 5, wherein,
the preset model parameters of the target object indicate the position relation among the components of the target object and the geometric structure of each component;
the optimization processing module is configured to adjust relative positions between component models corresponding to each component in a first structural parameter representation of the target object according to the first outer envelope point and a position relationship between each component of the target object indicated by a preset model parameter of the target object, and adjust a pose and/or a size of each component model.
8. The device according to any one of claims 5 to 7, wherein,
the optimization processing module comprises:
the adjustment processing unit is used for adjusting the first structural parameter representation according to the first outer envelope point to obtain a third structural parameter representation;
a control point determining unit, configured to determine second envelope points corresponding to the first envelope points one to one from the third structural parameter representation;
a calculating unit, configured to calculate a matching degree of the third structural parameter representation according to a distance between the first envelope point and the second envelope point corresponding to the first envelope point;
and the parameter determining unit is used for determining the matching degree meeting the preset condition and determining the third structural parameter representation corresponding to the determined matching degree meeting the preset condition as a second structural parameter representation.
9. A computer readable storage medium storing a computer program for executing the structured parameter representation acquisition method of any of the preceding claims 1-4.
10. An electronic device, the electronic device comprising:
a processor;
a memory for storing the processor-executable instructions;
the processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the structured parameter representation acquisition method of any one of the preceding claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910786995.1A CN112489105B (en) | 2019-08-24 | 2019-08-24 | Structured parameter representation acquisition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910786995.1A CN112489105B (en) | 2019-08-24 | 2019-08-24 | Structured parameter representation acquisition method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112489105A CN112489105A (en) | 2021-03-12 |
| CN112489105B true CN112489105B (en) | 2024-03-15 |
Family
ID=74920141
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910786995.1A Active CN112489105B (en) | 2019-08-24 | 2019-08-24 | Structured parameter representation acquisition method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112489105B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105913444A (en) * | 2016-05-03 | 2016-08-31 | 华南农业大学 | Livestock body contour reconstruction method and body condition scoring method based on soft laser ranging |
| CN108595763A (en) * | 2018-03-26 | 2018-09-28 | 武汉理工大学 | Die assembly design method based on model index technology |
| CN109034214A (en) * | 2018-07-09 | 2018-12-18 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating label |
| CN109117697A (en) * | 2017-06-26 | 2019-01-01 | 韩国道路公社 | Utilize the object location information extraction system of the point cloud data of component |
| CN109949899A (en) * | 2019-02-28 | 2019-06-28 | 未艾医疗技术(深圳)有限公司 | Image three-dimensional measurement method, electronic equipment, storage medium and program product |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10049462B2 (en) * | 2016-03-23 | 2018-08-14 | Akcelita, LLC | System and method for tracking and annotating multiple objects in a 3D model |
-
2019
- 2019-08-24 CN CN201910786995.1A patent/CN112489105B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105913444A (en) * | 2016-05-03 | 2016-08-31 | 华南农业大学 | Livestock body contour reconstruction method and body condition scoring method based on soft laser ranging |
| CN109117697A (en) * | 2017-06-26 | 2019-01-01 | 韩国道路公社 | Utilize the object location information extraction system of the point cloud data of component |
| CN108595763A (en) * | 2018-03-26 | 2018-09-28 | 武汉理工大学 | Die assembly design method based on model index technology |
| CN109034214A (en) * | 2018-07-09 | 2018-12-18 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating label |
| CN109949899A (en) * | 2019-02-28 | 2019-06-28 | 未艾医疗技术(深圳)有限公司 | Image three-dimensional measurement method, electronic equipment, storage medium and program product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112489105A (en) | 2021-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11422261B2 (en) | Robot relocalization method and apparatus and robot using the same | |
| USRE49149E1 (en) | Method for detecting two dimensional sketch data from source model data for three dimensional reverse modeling | |
| EP3816663A2 (en) | Method, device, equipment, and storage medium for determining sensor solution | |
| CN109558471B (en) | Updating method, device, storage medium and system of grid map | |
| CN114663397B (en) | Method, device, equipment and storage medium for detecting drivable area | |
| EP4198901A1 (en) | Camera extrinsic parameter calibration method and apparatus | |
| US20200357156A1 (en) | Map generation system and method for generating an accurate building shadow | |
| CN113191342A (en) | Lane positioning method and electronic equipment | |
| US20220204000A1 (en) | Method for determining automatic driving feature, apparatus, device, medium and program product | |
| CN112489105B (en) | Structured parameter representation acquisition method and device | |
| CN111488977B (en) | Neural network model training method and device | |
| CN110363847B (en) | Map model construction method and device based on point cloud data | |
| CN112348874B (en) | Method and device for determining structural parameter representation of lane line | |
| CN115127565A (en) | High-precision map data generation method and device, electronic equipment and storage medium | |
| US20230090067A1 (en) | Generation device, generation method, and generation program | |
| CN115015909A (en) | Radar data and video data fusion method and system based on perspective transformation | |
| CN116934863A (en) | Camera external parameter determining method and device and electronic equipment | |
| CN112348876B (en) | Space coordinate acquisition method and device for signboards | |
| CN113191368B (en) | Method and device for matching markers | |
| CN113762397A (en) | Detection model training and high-precision map updating method, device, medium and product | |
| CN111191597A (en) | System and method for extracting road structure based on vector line | |
| JP2020042790A (en) | Actual data expansion method, apparatus and terminal | |
| CN113191279A (en) | Data annotation method, device, equipment, storage medium and computer program product | |
| CN112308905B (en) | Method and device for determining coordinates of plane marker | |
| CN115201796B (en) | External reference correction method of vehicle sensor |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |