CN111460199A - Data association method and device, computer equipment and storage medium - Google Patents
Data association method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111460199A CN111460199A CN202010133965.3A CN202010133965A CN111460199A CN 111460199 A CN111460199 A CN 111460199A CN 202010133965 A CN202010133965 A CN 202010133965A CN 111460199 A CN111460199 A CN 111460199A
- Authority
- CN
- China
- Prior art keywords
- data
- dimensional data
- pair
- corrected
- dimensional
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000002372 labelling Methods 0.000 claims abstract description 106
- 230000000875 corresponding effect Effects 0.000 claims description 91
- 230000002596 correlated effect Effects 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention relates to a data association method, a data association device, computer equipment and a storage medium. The method comprises the following steps: the computer equipment acquires two-dimensional data and three-dimensional data of at least one object, and associates the two-dimensional data and the three-dimensional data of the at least one object to obtain an associated labeling result of the at least one object; after the computer equipment receives a correction instruction input by a user, the two-dimensional data and the three-dimensional data of at least one object to be associated are associated to obtain a labeling result of the object to be associated. In the method, the computer equipment associates at least one object firstly, and then associates the associated target object and the objects which are not associated during the first association again according to the correction instruction input by the user, so that the first associated labeling result is corrected, and the accuracy of the computer equipment for obtaining the labeling result is improved.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a data association method, an apparatus, a computer device, and a storage medium.
Background
Three-dimensional data refers to data that can be described in a spatial coordinate system, and is generally used to represent our real world, for example, a certain point in space or a square box (hereinafter referred to as an object) can be represented by 8 three-dimensional data points. Two-dimensional picture data is used to describe a scene shown in a picture, for example, an object in the picture may be outlined by a simple line or rectangle.
In practical applications, in order to better show the attributes of an object to a user on a picture, the object may be labeled, and usually, in the process of labeling the object, two-dimensional picture data and three-dimensional data of the object may be associated.
However, the existing correlation method has the problem of inaccurate correlation.
Disclosure of Invention
Therefore, in order to solve the above technical problems, it is necessary to provide a data association method, an apparatus, a computer device, and a storage medium, which can effectively improve the accuracy of associating two-dimensional data with three-dimensional data, and further effectively improve the accuracy of labeling objects corresponding to the two-dimensional data and the three-dimensional data.
In a first aspect, a data association method includes:
acquiring two-dimensional data and three-dimensional data of at least one object;
associating the two-dimensional data and the three-dimensional data of at least one object to obtain an associated labeling result of the at least one object;
after a correction instruction input by a user is received, correlating two-dimensional data and three-dimensional data of at least one object to be correlated to obtain a labeling result of the object to be correlated; and the correction instruction is used for indicating that the labeling result of the target object in the associated at least one object is corrected, and the object to be associated comprises the target object and the unassociated at least one object.
In one embodiment, associating the two-dimensional data and the three-dimensional data of the at least one object to obtain an associated labeling result of the at least one object includes:
pairing the two-dimensional data and the three-dimensional data of each object to obtain a plurality of data pairs; each data pair comprises two-dimensional data and three-dimensional data;
calculating the association score of each data pair; the relevance score is used for representing the relevance degree between the two-dimensional data and the three-dimensional data in the data pair;
and determining the labeling result of at least one object according to each association score.
In one embodiment, calculating the association score for each data pair comprises:
determining characteristic parameters of objects corresponding to the two-dimensional data and characteristic parameters of objects corresponding to the three-dimensional data in each data pair; the characteristic parameters comprise at least one of a vertex and a central point of a box for labeling the object;
determining a distance parameter of each data pair; the distance parameter is used for representing the average distance between the two-dimensional data corresponding to the object and the camera in the data pair and the distance between the three-dimensional data corresponding to the object and the camera;
determining the association coefficient of each data pair according to the characteristic parameters of the object corresponding to the two-dimensional data and the three-dimensional data in each data pair and the distance parameters of each data pair;
and determining the association score of each data pair according to the association coefficient of each data pair and the preset initial comparison coefficient of each data pair.
In one embodiment, determining the labeling result of at least one object according to each association score includes:
determining the data pairs corresponding to the association scores meeting the preset conditions as associated data pairs; the preset conditions include: the relevance score is higher than a preset score threshold value and an object corresponding to the two-dimensional data and an object corresponding to the three-dimensional data in the data volume pair corresponding to the relevance score are not matched;
and labeling the object corresponding to the two-dimensional data and the object corresponding to the three-dimensional data in the associated data pair to obtain a labeling result of at least one object.
In one embodiment, associating the two-dimensional data and the three-dimensional data of at least one object to be associated to obtain a labeling result of the object to be associated, includes:
canceling the association relation between the two-dimensional data and the three-dimensional data of the target object in the object to be associated;
re-associating the two-dimensional data and the three-dimensional data of the target object and the two-dimensional data and the three-dimensional data of at least one unassociated object to obtain a labeling result of the object to be associated; re-associating comprises associating according to the two-dimensional data and the three-dimensional data of the associated at least one object;
in one embodiment, the re-associating the two-dimensional data and the three-dimensional data of the target object and the two-dimensional data and the three-dimensional data of the unassociated at least one object to obtain an annotation result of the object to be associated, includes:
pairing the two-dimensional data and the three-dimensional data of the target object and the two-dimensional data and the three-dimensional data of at least one unassociated object to obtain a plurality of data pairs to be corrected; each data pair to be corrected comprises two-dimensional data and three-dimensional data;
calculating the association score of each data pair to be corrected; the relevance score is used for representing the relevance degree between the two-dimensional data and the three-dimensional data in the data pair to be corrected;
and determining the labeling result of the object to be associated according to each association score.
In one embodiment, calculating the association score of each data pair to be corrected includes:
determining two-dimensional data and three-dimensional data in each data pair to be corrected, and determining a correlation coefficient of each data pair to be corrected;
determining a comparison coefficient of each data pair to be corrected according to the two-dimensional data and the three-dimensional data in each associated data pair; each associated data pair comprises two-dimensional data and three-dimensional data of each associated object in the at least one object;
and calculating the association score of each data pair to be corrected according to the association coefficient of each data pair to be corrected and the comparison coefficient of each data pair to be corrected.
In one embodiment, determining the association coefficient of each data pair to be corrected according to the two-dimensional data and the three-dimensional data in each data pair to be corrected includes:
determining characteristic parameters of objects corresponding to the two-dimensional data and characteristic parameters of objects corresponding to the three-dimensional data in each data pair to be corrected; the characteristic parameters comprise at least one of a vertex and a central point of a box for labeling the object;
determining a distance parameter of each data pair to be corrected; the distance parameter is used for representing the average distance between the object corresponding to the two-dimensional data and the camera in the data pair to be corrected and the distance between the object corresponding to the three-dimensional data and the camera;
and determining the association coefficient of each data pair to be corrected according to the characteristic parameters of the object corresponding to the two-dimensional data and the characteristic parameters of the object corresponding to the three-dimensional data in each data pair to be corrected and the distance parameters of each data pair to be corrected.
In one embodiment, the determining the comparison coefficient of each data pair to be corrected according to the two-dimensional data and the three-dimensional data in each associated data pair includes:
determining characteristic parameters of objects corresponding to the two-dimensional data and characteristic parameters of objects corresponding to the three-dimensional data in each associated data pair;
determining a distance parameter of each associated data pair; the distance parameter is used for representing the average distance between the two-dimensional data corresponding to the object and the camera in the associated data pair and the distance between the three-dimensional data corresponding to the object and the camera;
determining a correction association coefficient of each data pair to be corrected according to the characteristic parameters of the object corresponding to the two-dimensional data and the characteristic parameters of the object corresponding to the three-dimensional data in each associated data pair and the distance parameters of each associated data pair;
and determining the comparison coefficient of each data pair to be corrected according to the corrected correlation coefficient of each data pair to be corrected and the number of the correlated data pairs.
In one embodiment, determining the comparison coefficient of each data pair to be corrected according to the corrected correlation coefficient of each data pair to be corrected and the number of correlated data pairs includes:
summing the correction correlation coefficients of all data pairs to be corrected to obtain coefficient sums;
and carrying out division operation on the coefficient and the number of the associated data pairs to obtain a comparison coefficient of each data pair to be corrected.
In one embodiment, determining the labeling result of the object to be associated according to each association score includes:
determining the data pairs to be corrected corresponding to the association scores meeting the preset conditions as associated data pairs to be corrected; the preset conditions include: the association score is higher than a preset score threshold value and the object corresponding to the two-dimensional data and the object corresponding to the three-dimensional data in the data body to be corrected corresponding to the association score are not matched;
and labeling the object corresponding to the two-dimensional data and the object corresponding to the three-dimensional data in the associated data pair to be corrected to obtain a labeling result of the object to be associated.
In a second aspect, an apparatus for associating data, the apparatus comprising:
an acquisition module for acquiring two-dimensional data and three-dimensional data of at least one object;
the association module is used for associating the two-dimensional data and the three-dimensional data of the at least one object to obtain an associated labeling result of the at least one object;
the correction module is used for correlating the two-dimensional data and the three-dimensional data of at least one object to be correlated after receiving a correction instruction input by a user to obtain a labeling result of the object to be correlated; and the correction instruction is used for indicating that the labeling result of the target object in the associated at least one object is corrected, and the object to be associated comprises the target object and the unassociated at least one object.
In a third aspect, a computer device includes a memory and a processor, where the memory stores a computer program, and the processor implements the data association method according to any one of the embodiments of the first aspect when executing the computer program.
In a fourth aspect, a computer-readable storage medium has stored thereon a computer program which, when executed by a processor, implements the data association method of any embodiment of the first aspect.
The application provides a data association method, a data association device, computer equipment and a storage medium, which comprise the following steps: the computer equipment acquires two-dimensional data and three-dimensional data of at least one object, and associates the two-dimensional data and the three-dimensional data of the at least one object to obtain an associated labeling result of the at least one object; after the computer equipment receives a correction instruction input by a user, the two-dimensional data and the three-dimensional data of at least one object to be associated are associated to obtain a labeling result of the object to be associated. In the method, the computer equipment associates at least one object firstly, and then associates the associated target object and the objects which are not associated during the first association again according to the correction instruction input by the user, so that the first associated labeling result is corrected, and the accuracy of the computer equipment for obtaining the labeling result is improved. Moreover, since the computer device re-associates the target object indicated by the correction instruction in the second association, the target object is an object already associated for the first time, and the deviation between the two-dimensional data and the three-dimensional data of the target object is small, the success rate and the accuracy of association can be greatly improved by performing the correction association again based on the associated object. In addition, because the correction instruction is the object which is intuitively indicated by the user and has a previous association error or inaccurate association, the associated target object is re-associated through the correction instruction, so that the problem that the association is inaccurate due to hardware or software limitation of the computer equipment when only the computer equipment is associated can be solved.
Drawings
FIG. 1 is a schematic diagram illustrating an internal structure of a computer device according to an embodiment;
FIG. 2 is a flow diagram of a method for data association according to an embodiment;
FIG. 3 is a flow chart of one implementation of S102 in the embodiment of FIG. 2;
FIG. 4 is a flowchart of one implementation of S202 in the embodiment of FIG. 3;
FIG. 5 is a flowchart of one implementation of S203 in the embodiment of FIG. 3;
FIG. 6 is a flowchart of one implementation of S103 in the embodiment of FIG. 2;
FIG. 7 is a flowchart of one implementation of S502 in the embodiment of FIG. 6;
FIG. 8 is a flowchart of one implementation of S602 in the embodiment of FIG. 7;
FIG. 9 is a flowchart of one implementation of S702 in the embodiment of FIG. 8;
FIG. 10 is a flowchart of one implementation of S804 in the embodiment of FIG. 9;
fig. 11 is a schematic structural diagram of a data association apparatus according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The data association method provided by the application can be applied to computer equipment shown in FIG. 1. The computer device may be a terminal, the internal structure of which may be as shown in fig. 1. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a data association method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 1 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
The following describes in detail the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems by embodiments and with reference to the drawings. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
Fig. 2 is a flowchart of a data association method according to an embodiment, where an execution subject of the method is the computer device in fig. 1, and the method relates to a specific process of associating two-dimensional data and three-dimensional data of an object in an image by the computer device. As shown in fig. 2, the method specifically includes the following steps:
s101, acquiring two-dimensional data and three-dimensional data of at least one object.
The two-dimensional data of the at least one object may be existing picture data or picture data obtained by shooting with a camera or other shooting devices. The three-dimensional data of the object can be point cloud data obtained by scanning of a laser radar, and can also be data described in a space coordinate system. In this embodiment, the computer device may obtain the two-dimensional data of any scene by connecting the shooting device to shoot the scene. Optionally, the computer device with the shooting function may also directly shoot any scene to obtain two-dimensional data of the scene, where the scene may include at least one object, and the object may be any type of object, person, animal, or the like. The embodiment is not limited to the manner of acquiring the two-dimensional data of the object. The computer equipment can acquire the three-dimensional point cloud data of any scene by connecting the laser radar, and also can acquire the three-dimensional data of any scene in other modes. The embodiment is not limited to the manner of acquiring the three-dimensional data of the object.
S102, associating the two-dimensional data and the three-dimensional data of the at least one object to obtain an associated labeling result of the at least one object.
Note that the labeling result may be represented by a cubic outline, a square outline, or other outlines, and this embodiment is not limited thereto. Optionally, the labeling result may also be represented by characters, numbers, letters, and the like, which is not limited in this embodiment. Specifically, the labeling result may be displayed on a two-dimensional image or a three-dimensional image. In practical application, when the computer device acquires the two-dimensional data and the three-dimensional data of at least one object, the two-dimensional data and the three-dimensional data of each object may be identified, and then the two-dimensional data and the three-dimensional data of each object are associated to obtain the associated at least one object. Then, the computer device can label the associated object by using corresponding labeling boxes, characters, letters or the like, so that the user can accurately view information such as the attribute of the associated object on the display interface of the image, for example, the size, the dimension, the color, the type and the like of the associated object.
S103, after receiving a correction instruction input by a user, correlating the two-dimensional data and the three-dimensional data of at least one object to be correlated to obtain a labeling result of the object to be correlated; and the correction instruction is used for indicating that the labeling result of the target object in the associated at least one object is corrected, and the object to be associated comprises the target object and the unassociated at least one object.
When the user checks the associated labeling result of the at least one object on the computer device and checks that the labeling result has an error or is incorrectly labeled, the user can input the correction instruction on the computer device to enable the computer device to identify the labeling result having the error or the incorrectly labeled labeling result in the associated labeling result of the at least one object, so that the objects can be correlated again later to obtain an accurate labeling result. The target object represents an object with an association error or inaccurate association in the associated at least one object. In this embodiment, the method for receiving the correction instruction by the computer device is not limited, and may specifically be an interface keyboard input method, a voice input method, or the like.
In practical application, when the computer device associates the two-dimensional data and the three-dimensional data of the at least one object to obtain the labeling result associated with the at least one object, due to the limitation of hardware or software in the computer device, the previous association may be mistakenly associated or inaccurate in association, so that the mistaken or inaccurate labeling result may be generated in the labeling result associated with the at least one object. Based on the application background, the embodiment proposes that the computer device corrects the annotation result of the target object indicated by the correction instruction according to the correction instruction input by the user, so as to correct the annotation result of an object which may have a correlation error or inaccurate correlation in the previously correlated objects. Meanwhile, after the previous association, at least one associated object can be obtained, and also some unassociated objects can be obtained. Therefore, the labeling result of the object to be associated obtained by the method in S103 includes the modified labeling result of the target object and the labeling result of the object that is not associated before.
The data association method provided by the embodiment comprises the following steps: the computer equipment acquires two-dimensional data and three-dimensional data of at least one object, and associates the two-dimensional data and the three-dimensional data of the at least one object to obtain an associated labeling result of the at least one object; after the computer equipment receives a correction instruction input by a user, the two-dimensional data and the three-dimensional data of at least one object to be associated are associated to obtain a labeling result of the object to be associated. In the method, the computer equipment associates at least one object firstly, and then associates the associated target object and the objects which are not associated during the first association again according to the correction instruction input by the user, so that the first associated labeling result is corrected, and the accuracy of the computer equipment for obtaining the labeling result is improved. Moreover, because the computer device re-associates the target object indicated by the correction instruction in the second association, the target object is an object which has been associated for the first time, and the deviation between the two-dimensional data and the three-dimensional data of the target object is small, the computer device can re-associate the association based on the associated object, thereby greatly improving the success rate and the accuracy of association. In addition, because the correction instruction is the object which is intuitively indicated by the user and has a previous association error or inaccurate association, the associated target object is re-associated through the correction instruction, so that the problem that the association is inaccurate due to hardware or software limitation of the computer equipment when only the computer equipment is associated can be solved.
Optionally, as shown in fig. 3, another method of S102 "associating two-dimensional data and three-dimensional data of at least one object to obtain an associated labeling result of the at least one object" may specifically include:
s201, pairing two-dimensional data and three-dimensional data of each object to obtain a plurality of data pairs; each data pair includes a two-dimensional data and a three-dimensional data.
When the computer device acquires the two-dimensional data and the three-dimensional data of at least one object, the two-dimensional data and the three-dimensional data of each object may be further paired to match a plurality of data pairs including the two-dimensional data and the three-dimensional data, where the two-dimensional data and the three-dimensional data included in each data pair are two-dimensional data and three-dimensional data that may have an association relationship with respect to a certain object, for example, if there are two-dimensional data 21 of one object, three-dimensional data 31 of a projected object corresponding to the object, two-dimensional data 22 of another object, and three-dimensional data 32 of a projected object corresponding to the object, then after pairing, there are four data pairs that may have an association relationship: (a)21-31, (b)21-32, (a)21-31, (c)22-31, (c) 22-32.
S202, calculating the association score of each data pair; the relevance score is used to represent the degree of relevance between the two-dimensional data and the three-dimensional data in the data pair.
When the computer device obtains a plurality of data pairs, the relevance score of each data pair can be calculated by adopting a corresponding score calculation method so as to obtain the relevance degree between the two-dimensional data and the three-dimensional data in each data pair, then the relevance degree between the two-dimensional data and the three-dimensional data in each data pair is evaluated according to the relevance score of each data pair, and the data pair with high relevance score is taken as the relevant data pair. The following embodiment of fig. 4 will describe the score calculation method provided by the present scheme in detail, and will not be described repeatedly.
S203, determining the labeling result of at least one object according to each association score.
When the computer device obtains the association scores of the plurality of data pairs, a part of association scores can be further selected according to the level of each association score, then the object corresponding to the part of association scores is determined as the associated object, and then the labeling result of the object is determined according to the associated object. For example, in practical applications, after the computer device determines at least one associated object according to the association score of each data pair, the computer device may display a labeling result about the associated object on the display screen, for example, the associated object is marked out by a rectangular frame in the display picture of the picture, and the associated object is marked out by a solid frame in the display picture of the three-dimensional space. The method for selecting a part of the association scores may be determined according to actual application requirements, which is not limited in this embodiment.
Optionally, the present application provides a specific implementation manner of the foregoing S202, and as shown in fig. 4, the foregoing S202 "calculating the association score of each data pair" includes:
s301, determining characteristic parameters of objects corresponding to the two-dimensional data and characteristic parameters of objects corresponding to the three-dimensional data in each data pair.
The characteristic parameters comprise at least one of a vertex and a central point of a labeling frame for labeling the object. When the marked object is a two-dimensional object, the marking frame is a two-dimensional marking frame, for example, a rectangular frame; when the labeled object is a three-dimensional object, the labeling frame is a three-dimensional labeling frame, for example, a solid frame. For another example, the feature parameter of the object corresponding to the two-dimensional data may be 4 corner points of a rectangular frame labeling the two-dimensional object, or 1, 2, 3, etc. of the 4 corner points, or 1 central point of the rectangular frame. The feature parameter of the object corresponding to the three-dimensional data may be 8 corner points of a stereoscopic frame labeling the three-dimensional object, or 1, 2, 3, 4, 5, etc. of the 8 corner points, or 1 central point of the stereoscopic frame. In this embodiment, the characteristic parameter of the object corresponding to the two-dimensional data and the characteristic parameter of the object corresponding to the three-dimensional data in each data pair are calculation parameters for calculating the correlation coefficient of each data pair. When the computer device obtains the two-dimensional data in a certain data pair, the characteristic parameters of the corresponding object can be further determined according to the two-dimensional data, and when the computer device obtains the three-dimensional data in a certain data pair, the characteristic parameters of the corresponding object can be further determined according to the three-dimensional data, so that the association scores of the data pairs can be calculated later.
S302, determining distance parameters of each data pair.
The distance parameter is used for representing the average distance between the two-dimensional data corresponding to the object and the camera in the data pair and the distance between the three-dimensional data corresponding to the object and the camera. In this embodiment, the distance parameter of each data pair is a calculation parameter for calculating the correlation coefficient of each data pair. When the computer device acquires a plurality of matched data pairs, the distance between the object corresponding to the two-dimensional data and the camera in each data pair and the distance between the object corresponding to the three-dimensional data and the camera can be further obtained by acquiring camera parameters or evaluating the distances, then the two distances are subjected to mean value operation to obtain an average distance, and finally the average distance is determined as the distance parameter of each data pair so as to be used when calculating the association coefficient of each data pair.
S303, determining the association coefficient of each data pair according to the characteristic parameters of the object corresponding to the two-dimensional data and the three-dimensional data in each data pair and the distance parameters of each data pair.
Wherein the correlation coefficient is a calculation parameter for calculating the correlation score of each data pair. In this embodiment, when the computer device acquires the feature parameter of the two-dimensional data corresponding object and the feature parameter of the three-dimensional data corresponding object in each data pair based on the step S301, and acquires the distance parameter of each data pair based on the step S302, the computer device may calculate the association coefficient of each data pair according to the three parameters, so as to calculate the association score of each data pair according to the association coefficient.
S304, determining the association score of each data pair according to the association coefficient of each data pair and the preset initial comparison coefficient of each data pair.
The initial comparison coefficient can be predetermined according to the actual application requirement, and is another calculation parameter for calculating the association score of each data pair. Optionally, the initial alignment coefficient in this embodiment may be zero. In this embodiment, when the computer device obtains the association coefficient of each data pair and the preset initial comparison coefficient based on the step of S303, a corresponding method for calculating the association score may be further adopted to calculate the association score of each data pair according to two calculation parameters, that is, the association coefficient and the initial comparison coefficient of each data pair. It should be noted that, the association score of each data pair may be calculated by specifically calculating the distance, standard deviation, variance, or the like between the two calculation parameters, and then using the calculated value as the association score of each data pair.
The method of calculating the association score for each data pair according to the steps described above in S301-304 is discussed below by way of example. For example: assume that there are 4 well-matched data pairs: (a)21-31, (b)21-32, (c)22-31, (d)22-32, then:
firstly, the feature parameters F21 of the object corresponding to the two-dimensional data 21, F31 of the object corresponding to the three-dimensional data 31, F22 of the object corresponding to the two-dimensional data 22, and F32 of the object corresponding to the three-dimensional data 32 in the 4 data pairs obtained according to the step S301 are:
f21 ═ 70,160,50,100], where (70, 50) is the top left coordinate point of the annotation object annotation box and (160, 100) is the top right coordinate point of the annotation object annotation box.
F31 ═ 90,210,70,130], where (90, 70) is the coordinate point at the top left corner of the annotation object annotation box and (210, 130) is the coordinate point at the top right corner of the annotation object annotation box.
F22 ═ 340,440,45,140], where (340, 45) is the coordinate point at the top left corner of the annotation object annotation box, and (440, 140) is the coordinate point at the top right corner of the annotation object annotation box.
F32 ═ 320,420,30,110], where (320, 30) is the coordinate point at the top left corner of the annotation object annotation box, and (420, 110) is the coordinate point at the top right corner of the annotation object annotation box.
Secondly, the distance parameters Da, Db, Dc, Dd obtained according to the step of S302 are: da is 10, Db is 10, Dc is 10, and Dd is 10.
Thirdly, the correlation coefficient of each data pair calculated in the above step S303 ((a) the correlation coefficient Pa of the data pair, (b) the correlation coefficient Pb of the data pair, (c) the correlation coefficient Pc of the data pair, and (d) the correlation coefficient Pd of the data pair) is:
Pa＝(F21-F31)/Da＝([70,160,50,100]-[90,210,70,130])/10
＝[-2,-5,-2,-3]；
Pb＝(F21-F32)/Db＝([70,160,50,100]-[320,420,30,110])/10
＝[-25,-26,2,-1]；
Pc＝(F22-F31)/Dc＝([340,440,45,140]-[90,210,70,130])/10
＝[25,23,-2.5,1]；
Pd＝(F22-F32)/Db＝([340,440,45,140]-[320,420,30,110])/10
＝[2,2,1.5,3]；
fourth, assuming initial alignment coefficients: when P is [0,0,0,0], the association score of each data pair is calculated according to the procedure described in S304 as follows:
Si＝-distance(P,Pi) (1)；
in the above equation, Si represents the correlation score of each data pair, P represents the alignment coefficient of each data pair, and Pi represents the correlation coefficient of each data pair.
When Pi is Pa, Pb, Pc, Pd, and the initial alignment coefficient is P, the Pi can be calculated by substituting the above fraction calculation formula (1):
association score of data pair Sa: sa — 6.48, association score of data pair Sb: sb — 36.13, association score Sc of data pair: sc — 34.07, association score Sd of data pair: sd ═ 4.38.
Optionally, the present application provides a specific implementation manner of the foregoing S203, and as shown in fig. 5, the foregoing S203 "determining a labeling result of at least one object according to each association score" includes:
s401, determining the data pairs corresponding to the association scores meeting the preset conditions as the associated data pairs. The preset conditions include: and the object corresponding to the two-dimensional data and the object corresponding to the three-dimensional data in the data pair with the association score higher than the preset score threshold and the association score are not matched.
Wherein the preset score threshold value can be determined by the computer device in advance according to the actual association precision and the application requirement. When the computer device calculates the association score of each data pair based on the foregoing embodiment, it may first select a data pair corresponding to an association score higher than a preset score threshold from the obtained multiple association scores, then determine whether an object corresponding to the two-dimensional data in the selected data pair has been previously matched, i.e., associated, and whether an object corresponding to the three-dimensional data in the data pair has been previously matched, i.e., associated, and if none of the objects has been matched, finally determine the data pair as an associated data pair, and then determine the object corresponding to the data pair as an associated object.
The method for determining the associated data pairs according to the present embodiment is discussed based on the examples described in the above embodiments: for example, assuming that the preset score threshold is-10, when the computer device calculates the association score: when Sa is-6.48, Sb is-36.13, Sc is-34.07, and Sd is-4.38, the computer device may first select an association score that is greater than a preset score threshold: sd and Sa, and further determining that objects corresponding to the data in the Sd and Sa are not matched, and finally determining that the Sd and Sa are associated data pairs, so that the objects corresponding to the two-dimensional data 22 and the three-dimensional data 32 in the Sd are associated objects; the objects corresponding to the two-dimensional data 21 and the three-dimensional data 31 in Sa are associated objects.
S402, labeling the object corresponding to the two-dimensional data and the object corresponding to the three-dimensional data in the associated data pair to obtain a labeling result of at least one object.
After the computer device determines the associated data pair based on the method, the associated object is determined from at least one object, in the application scenario, the computer device may adopt a corresponding labeling method to label the object corresponding to the two-dimensional data in the associated data pair to obtain a labeling result of the object, and label the object corresponding to the three-dimensional data in the associated data pair to obtain a labeling result of the object, so that a user may clearly view information such as a labeling attribute of the object on a display interface according to the labeling result.
In practical application, when the computer device associates the two-dimensional data and the three-dimensional data of at least one object and obtains the labeling result of the associated at least one object, the user can check the labeling result of each object on the interface of the display screen of the computer device, so as to check whether each object is accurately associated by the computer device before, i.e. whether the labeling result of each object is accurate. If the wrongly labeled objects are displayed on the display interface of the computer device, the user can correspondingly input an instruction for correcting the labeling result on the computer device, and instruct the computer device to correct the wrongly labeled objects, so that the accurate labeling result of each object is obtained.
In the application environment, in an embodiment, the present application provides an implementation manner of the foregoing S103, and as shown in fig. 6, the foregoing S103 "associates two-dimensional data and three-dimensional data of at least one object to be associated to obtain a labeling result of the object to be associated", including:
s501, canceling the association relation between the two-dimensional data and the three-dimensional data of the target object in the object to be associated.
The target object represents an object with an association error or inaccurate association in at least one associated object and also represents an object needing to be corrected. In this embodiment, after receiving a correction instruction input by a user, the computer device may correct the target object to be corrected, and at this time, the computer device may cancel the association relationship between the two-dimensional data and the three-dimensional data of the target object in the associated object first, so as to associate the two-dimensional data and the three-dimensional data of the target object again later, thereby obtaining the target object with an accurate association relationship.
S502, re-associating the two-dimensional data and the three-dimensional data of the target object and the two-dimensional data and the three-dimensional data of at least one unassociated object to obtain an annotation result of the object to be associated; the re-associating includes associating based on the two-dimensional data and the three-dimensional data of the associated at least one object.
After the computer device cancels the two-dimensional data and the three-dimensional data of the target object, the computer device may further associate the two-dimensional data and the three-dimensional data of the target object and the two-dimensional data and the three-dimensional data of the unassociated at least one object by using a corresponding re-association method, so as to obtain a labeling result of the target object and the unassociated at least one object, that is, a labeling result of the object to be associated. It should be noted that the re-association method is to associate the two-dimensional data and the three-dimensional data of a part of the objects in at least one object that has been associated previously, and optionally, may also associate the two-dimensional data and the three-dimensional data of all objects that have been associated previously.
In the above embodiment, since the association relationship between the two-dimensional data and the three-dimensional data corresponding to the associated object is accurate, the accuracy of re-associating the object can be greatly improved by re-associating the two-dimensional data and the three-dimensional data based on the associated object, and the accuracy of obtaining the labeling result of the object to be associated after association is further improved.
The application provides the above re-associating method, for example, in step S502, "re-associating the two-dimensional data and the three-dimensional data of the target object, and the two-dimensional data and the three-dimensional data of the unassociated at least one object to obtain a labeling result of the object to be associated," as shown in fig. 7, specifically includes:
s601, pairing the two-dimensional data and the three-dimensional data of the target object and the two-dimensional data and the three-dimensional data of at least one unassociated object to obtain a plurality of data pairs to be corrected.
And S602, calculating the association score of each data pair to be corrected.
And S603, determining the labeling result of the object to be associated according to each association score.
The steps described in S601-S603 relate to a re-association process of data, and an association method used in the association process is substantially the same as the association method described in S201-S203, and details of the above steps are not repeated here, and please refer to the foregoing description.
It should be noted that the method for calculating the relevance score in S602 is different from the method for calculating the relevance score in S202, and as shown in fig. 8, the method specifically includes:
s701, determining the association coefficient of each data pair to be corrected according to the two-dimensional data and the three-dimensional data in each data pair to be corrected.
S702, determining a comparison coefficient of each data pair to be corrected according to the two-dimensional data and the three-dimensional data in each associated data pair.
And S703, calculating the association score of each data pair to be corrected according to the association coefficient of each data pair to be corrected and the comparison coefficient of each data pair to be corrected.
Specifically, when the computer device calculates the association score of each data pair to be corrected by using the method, unlike the calculation of the association score, it is necessary to determine the comparison coefficient of each data pair to be corrected according to the associated data pair, and then calculate the association score by using the comparison coefficient, so the application also provides a method for determining the comparison coefficient, as shown in fig. 9, where the method for determining the comparison coefficient includes:
s801, determining characteristic parameters of objects corresponding to the two-dimensional data and characteristic parameters of objects corresponding to the three-dimensional data in each associated data pair.
S802, determining the distance parameter of each associated data pair.
And S803, determining a correction association coefficient of each data pair to be corrected according to the characteristic parameters of the object corresponding to the two-dimensional data and the three-dimensional data in each associated data pair and the distance parameters of each associated data pair.
S804, determining the comparison coefficient of each data pair to be corrected according to the corrected correlation coefficient of each data pair to be corrected and the number of the correlated data pairs.
The steps described in S801 to S803 specifically relate to a process of determining each calculation parameter (characteristic parameter, distance parameter, correction correlation coefficient), and each determination method used in this process is substantially the same as the method described in S301 to S303, and the details of each step are not repeated here.
As for the step described in S804, the present application provides a specific implementation manner of the step, and as shown in fig. 10, the step S804 "determining the comparison coefficient of each data pair to be corrected according to the corrected correlation coefficient of each data pair to be corrected and the number of correlated data pairs" includes:
s901, summing the correction correlation coefficients of all the data pairs to be corrected to obtain a coefficient sum.
S902, performing division operation on the coefficient and the number of the associated data pairs to obtain a comparison coefficient of each data pair to be corrected.
In the above embodiment, when the computer device calculates the association score of each data pair to be corrected, the comparison coefficient is determined based on the associated data pair, and each associated data in the associated data pair is accurately associated, so that when the association score of the data pair to be corrected is calculated by using the comparison coefficient, the accuracy of the association score can be greatly improved.
It should be understood that although the various steps in the flow charts of fig. 2-10 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-10 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential.
In one embodiment, as shown in fig. 11, there is provided a data associating apparatus including: an obtaining module 11, an associating module 12 and a modifying module 13, wherein:
an obtaining module 11 is configured to obtain two-dimensional data and three-dimensional data of at least one object.
The association module 12 is configured to associate the two-dimensional data and the three-dimensional data of the at least one object to obtain an associated labeling result of the at least one object.
The correction module 13 is configured to, after receiving a correction instruction input by a user, associate two-dimensional data and three-dimensional data of at least one object to be associated to obtain a labeling result of the object to be associated; and the correction instruction is used for indicating that the labeling result of the target object in the associated at least one object is corrected, and the object to be associated comprises the target object and the unassociated at least one object.
For the specific definition of the data association device, reference may be made to the above definition of a data association method, which is not described herein again. The respective modules in the above data association apparatus may be wholly or partially implemented by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring two-dimensional data and three-dimensional data of at least one object;
associating the two-dimensional data and the three-dimensional data of at least one object to obtain an associated labeling result of the at least one object;
after a correction instruction input by a user is received, correlating two-dimensional data and three-dimensional data of at least one object to be correlated to obtain a labeling result of the object to be correlated; and the correction instruction is used for indicating that the labeling result of the target object in the associated at least one object is corrected, and the object to be associated comprises the target object and the unassociated at least one object.
The implementation principle and technical effect of the computer device provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, the computer program, when executed by a processor, further implementing the steps of:
acquiring two-dimensional data and three-dimensional data of at least one object;
associating the two-dimensional data and the three-dimensional data of at least one object to obtain an associated labeling result of the at least one object;
after a correction instruction input by a user is received, correlating two-dimensional data and three-dimensional data of at least one object to be correlated to obtain a labeling result of the object to be correlated; and the correction instruction is used for indicating that the labeling result of the target object in the associated at least one object is corrected, and the object to be associated comprises the target object and the unassociated at least one object.
The implementation principle and technical effect of the computer-readable storage medium provided by the above embodiments are similar to those of the above method embodiments, and are not described herein again.
It will be understood by those of ordinary skill in the art that all or a portion of the processes of the methods of the embodiments described above may be implemented by a computer program that may be stored on a non-volatile computer-readable storage medium, which when executed, may include the processes of the embodiments of the methods described above, wherein any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (13)
1. A method for associating data, the method comprising:
acquiring two-dimensional data and three-dimensional data of at least one object;
associating the two-dimensional data and the three-dimensional data of the at least one object to obtain an associated labeling result of the at least one object;
after a correction instruction input by a user is received, correlating two-dimensional data and three-dimensional data of at least one object to be correlated to obtain a labeling result of the object to be correlated; the correction instruction is used for indicating that the labeling result of a target object in the associated at least one object is corrected, and the object to be associated comprises the target object and the unassociated at least one object.
2. The method according to claim 1, wherein the associating the two-dimensional data and the three-dimensional data of the at least one object to obtain the labeling result of the associated at least one object comprises:
pairing the two-dimensional data and the three-dimensional data of each object to obtain a plurality of data pairs; each of said data pairs comprising a two-dimensional data and a three-dimensional data;
calculating an association score for each of the data pairs; the relevance score is used for representing the relevance degree between the two-dimensional data and the three-dimensional data in the data pair;
and determining the labeling result of the at least one object according to each association score.
3. The method of claim 2, wherein said calculating the relevance score for each of said data pairs comprises:
determining characteristic parameters of objects corresponding to the two-dimensional data and characteristic parameters of objects corresponding to the three-dimensional data in each data pair; the characteristic parameters comprise at least one of a vertex and a central point of a labeling frame for labeling the object;
determining a distance parameter for each of said data pairs; the distance parameter is used for representing the average distance between the two-dimensional data corresponding to the object and the camera in the data pair and the distance between the three-dimensional data corresponding to the object and the camera;
determining a correlation coefficient of each data pair according to the characteristic parameters of the objects corresponding to the two-dimensional data and the three-dimensional data in each data pair and the distance parameters of each data pair;
and determining the association score of each data pair according to the association coefficient of each data pair and a preset initial comparison coefficient of each data pair.
4. The method of claim 3, wherein the initial alignment coefficient is zero.
5. The method of claim 2, wherein said determining an annotation result for said at least one object based on each of said relevance scores comprises:
determining the data pairs corresponding to the association scores meeting the preset conditions as associated data pairs; the preset conditions include: the relevance score is higher than a preset score threshold value and objects corresponding to the two-dimensional data and the three-dimensional data in the data volume pair corresponding to the relevance score are not matched;
and labeling the object corresponding to the two-dimensional data and the object corresponding to the three-dimensional data in the associated data pair to obtain a labeling result of the at least one object.
6. The method according to claim 1, wherein the associating the two-dimensional data and the three-dimensional data of at least one object to be associated to obtain the labeling result of the object to be associated comprises:
canceling the association relation between the two-dimensional data and the three-dimensional data of the target object in the object to be associated;
re-associating the two-dimensional data and the three-dimensional data of the target object and the two-dimensional data and the three-dimensional data of the unassociated at least one object to obtain a labeling result of the object to be associated; the re-associating includes associating based on the two-dimensional data and the three-dimensional data of the associated at least one object.
7. The method according to claim 6, wherein the re-associating the two-dimensional data and the three-dimensional data of the target object and the two-dimensional data and the three-dimensional data of the unassociated at least one object to obtain the labeling result of the object to be associated comprises:
pairing the two-dimensional data and the three-dimensional data of the target object and the two-dimensional data and the three-dimensional data of the unassociated at least one object to obtain a plurality of data pairs to be corrected; each data pair to be corrected comprises two-dimensional data and three-dimensional data;
calculating the association score of each data pair to be corrected; the relevance score is used for representing the relevance degree between the two-dimensional data and the three-dimensional data in the data pair to be corrected;
and determining the labeling result of the object to be associated according to each association score.
8. The method according to claim 7, wherein the calculating the association score of each data pair to be corrected comprises:
determining a correlation coefficient of each to-be-corrected data pair according to the two-dimensional data and the three-dimensional data in each to-be-corrected data pair;
determining a comparison coefficient of each data pair to be corrected according to the two-dimensional data and the three-dimensional data in each associated data pair; each of the associated data pairs comprises two-dimensional data and three-dimensional data for each associated object of the at least one object;
and calculating the association score of each data pair to be corrected according to the association coefficient of each data pair to be corrected and the comparison coefficient of each data pair to be corrected.
9. The method according to claim 8, wherein the determining the comparison coefficient of each data pair to be corrected according to the two-dimensional data and the three-dimensional data in each associated data pair comprises:
determining characteristic parameters of objects corresponding to the two-dimensional data and characteristic parameters of objects corresponding to the three-dimensional data in each associated data pair;
determining a distance parameter for each of the associated data pairs; the distance parameter is used for representing the distance between the two-dimensional data corresponding to the object and the camera in the associated data pair and the average distance between the three-dimensional data corresponding to the object and the camera;
determining a correction association coefficient of each data pair to be corrected according to the characteristic parameters of the objects corresponding to the two-dimensional data and the three-dimensional data in each associated data pair and the distance parameters of each associated data pair;
and determining a comparison coefficient of each data pair to be corrected according to the corrected correlation coefficient of each data pair to be corrected and the number of the correlated data pairs.
10. The method according to claim 9, wherein determining the comparison coefficient for each data pair to be corrected according to the corrected correlation coefficient for each data pair to be corrected and the number of the correlated data pairs comprises:
summing the correction correlation coefficients of all the data pairs to be corrected to obtain coefficient sums;
and performing division operation on the coefficient and the number of the associated data pairs to obtain a comparison coefficient of each data pair to be corrected.
11. An apparatus for associating data, the apparatus comprising:
an acquisition module for acquiring two-dimensional data and three-dimensional data of at least one object;
the association module is used for associating the two-dimensional data and the three-dimensional data of the at least one object to obtain an associated labeling result of the at least one object;
the correction module is used for correlating two-dimensional data and three-dimensional data of at least one object to be correlated after receiving a correction instruction input by a user to obtain a labeling result of the object to be correlated; the correction instruction is used for indicating that the labeling result of a target object in the associated at least one object is corrected, and the object to be associated comprises the target object and the unassociated at least one object.
12. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method of any one of claims 1 to 10 when executing the computer program.
13. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010133965.3A CN111460199B (en) | 2020-03-02 | 2020-03-02 | Data association method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010133965.3A CN111460199B (en) | 2020-03-02 | 2020-03-02 | Data association method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111460199A true CN111460199A (en) | 2020-07-28 |
| CN111460199B CN111460199B (en) | 2024-02-23 |
Family
ID=71678164
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010133965.3A Active CN111460199B (en) | 2020-03-02 | 2020-03-02 | Data association method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111460199B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110098983A1 (en) * | 2009-10-23 | 2011-04-28 | Siemens Product Lifecycle Management Software Inc. | System and method for producing editable three-dimensional models |
| CN107784038A (en) * | 2016-08-31 | 2018-03-09 | 法乐第(北京)网络科技有限公司 | A kind of mask method of sensing data |
| JP2019018446A (en) * | 2017-07-14 | 2019-02-07 | 大日本印刷株式会社 | Data output regulating device for three-dimensional object molding |
| CN109408897A (en) * | 2018-09-26 | 2019-03-01 | 中广核工程有限公司 | The conversion method and system identified based on PDMS to AutoCAD drawing size marking |
| CN109727312A (en) * | 2018-12-10 | 2019-05-07 | 广州景骐科技有限公司 | Point cloud mask method, device, computer equipment and storage medium |
| CN110136273A (en) * | 2019-03-29 | 2019-08-16 | 初速度（苏州）科技有限公司 | A kind of sample data mask method and device in machine learning |
| CN110751149A (en) * | 2019-09-18 | 2020-02-04 | 平安科技（深圳）有限公司 | Target object labeling method and device, computer equipment and storage medium |
-
2020
- 2020-03-02 CN CN202010133965.3A patent/CN111460199B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110098983A1 (en) * | 2009-10-23 | 2011-04-28 | Siemens Product Lifecycle Management Software Inc. | System and method for producing editable three-dimensional models |
| CN107784038A (en) * | 2016-08-31 | 2018-03-09 | 法乐第(北京)网络科技有限公司 | A kind of mask method of sensing data |
| JP2019018446A (en) * | 2017-07-14 | 2019-02-07 | 大日本印刷株式会社 | Data output regulating device for three-dimensional object molding |
| CN109408897A (en) * | 2018-09-26 | 2019-03-01 | 中广核工程有限公司 | The conversion method and system identified based on PDMS to AutoCAD drawing size marking |
| CN109727312A (en) * | 2018-12-10 | 2019-05-07 | 广州景骐科技有限公司 | Point cloud mask method, device, computer equipment and storage medium |
| CN110136273A (en) * | 2019-03-29 | 2019-08-16 | 初速度（苏州）科技有限公司 | A kind of sample data mask method and device in machine learning |
| CN110751149A (en) * | 2019-09-18 | 2020-02-04 | 平安科技（深圳）有限公司 | Target object labeling method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111460199B (en) | 2024-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10872439B2 (en) | Method and device for verification | |
| US10438412B2 (en) | Techniques to facilitate accurate real and virtual object positioning in displayed scenes | |
| CN110648363A (en) | Camera posture determining method and device, storage medium and electronic equipment | |
| JP6464938B2 (en) | Image processing apparatus, image processing method, and image processing program | |
| CN113537374B (en) | Method for generating countermeasure sample | |
| JP2017097770A (en) | Camera position pose estimation device, camera position pose estimation method and camera position pose estimation program | |
| JP2022541977A (en) | Image labeling method, device, electronic device and storage medium | |
| CN109740487B (en) | Point cloud labeling method and device, computer equipment and storage medium | |
| CN108564604B (en) | Binocular vision stereo matching method and device based on plane constraint and triangulation | |
| CN113052907A (en) | Positioning method of mobile robot in dynamic environment | |
| CN114608521B (en) | Monocular ranging method and device, electronic equipment and storage medium | |
| CN114677588A (en) | Obstacle detection method, obstacle detection device, robot and storage medium | |
| CN114387347A (en) | Method and device for determining external parameter calibration, electronic equipment and medium | |
| CN113793392A (en) | Camera parameter calibration method and device | |
| CN105335959A (en) | Quick focusing method and device for imaging apparatus | |
| CN111583338B (en) | Positioning method and device for unmanned equipment, medium and unmanned equipment | |
| CN112085842B (en) | Depth value determining method and device, electronic equipment and storage medium | |
| CN111460199A (en) | Data association method and device, computer equipment and storage medium | |
| US20140348416A1 (en) | Stereo image rectification apparatus and method | |
| CN115658525A (en) | User interface checking method and device, storage medium and computer equipment | |
| US11232594B1 (en) | Iterative point indexing | |
| CN112862840B (en) | Image segmentation method, device, equipment and medium | |
| US20220130138A1 (en) | Training data generation apparatus, method and program | |
| CN111145268A (en) | Video registration method and device | |
| JP2022185872A (en) | Image processing device, image processing method and imaging apparatus |
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 |