CN109325432B - Three-dimensional object identification method and equipment and computer readable storage medium - Google Patents
Three-dimensional object identification method and equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN109325432B CN109325432B CN201811070706.XA CN201811070706A CN109325432B CN 109325432 B CN109325432 B CN 109325432B CN 201811070706 A CN201811070706 A CN 201811070706A CN 109325432 B CN109325432 B CN 109325432B
- Authority
- CN
- China
- Prior art keywords
- feature point
- feature
- characteristic
- feature points
- points
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a method for identifying a three-dimensional object, which comprises the following steps: acquiring three-dimensional feature points corresponding to a first feature point to obtain a second feature point set based on the first feature point in a preset first feature point set; the first feature point is a feature point of each image in a preset image set; acquiring parameters of the first characteristic point; wherein the parameter is used for characterizing the relevance between the first characteristic point and the preset image set; determining key feature points corresponding to the first feature points from the three-dimensional feature points of the second feature point set based on the parameters; and identifying the image to be processed based on the second feature point and the key feature point of the image to be processed. The embodiment of the invention also discloses a device for identifying the three-dimensional object and a computer readable storage medium.
Description
Technical Field
The present invention relates to the field of Augmented Reality (AR) technologies, and in particular, to a method and an apparatus for identifying a three-dimensional object, and a computer-readable storage medium.
Background
The AR technology is a technology that scans entity information in a certain time and space range of the real world by a camera, simulates and re-superimposes the entity information in a computer, and then applies virtual information to the real world, thereby achieving sensory experience beyond reality. The identification of three-dimensional objects using AR techniques generally includes: feature extraction, feature matching and pose calculation of a camera relative to a three-dimensional object; that is, when the AR technology is used to identify a three-dimensional object, the extracted feature points need to be matched with preset feature points.
However, in the related art, when the three-dimensional object is recognized, all extracted feature points need to be matched with all preset feature points, and the amount of feature point data to be matched is large, so that the matching speed of the feature points is slow, and the recognition efficiency is low.
Disclosure of Invention
In order to solve the above technical problems, embodiments of the present invention desirably provide a method, an apparatus, and a computer-readable storage medium for recognizing a three-dimensional object, so as to solve the problem that the amount of feature points to be matched is large because all extracted feature points need to be matched with all preset feature points when a three-dimensional object is recognized in the relative art, improve the matching speed of the feature points, and improve the efficiency of image recognition.
The technical scheme of the invention is realized as follows:
a method of identifying a three-dimensional object, the method comprising:
acquiring three-dimensional feature points corresponding to a first feature point to obtain a second feature point set based on the first feature point in a preset first feature point set; the first feature point is a feature point of each image in a preset image set;
acquiring parameters of the first characteristic point; wherein the parameter is used for characterizing the relevance between the first characteristic point and the preset image set;
determining key feature points corresponding to the first feature points from the three-dimensional feature points of the second feature point set based on the parameters;
and identifying the image to be processed based on the second feature point and the key feature point of the image to be processed.
Optionally, the obtaining the parameter of the first feature point includes:
calculating the proportion of the same first characteristic points in the first characteristic point set; wherein the first parameter comprises specific gravity.
Optionally, the determining, based on the parameter, a key feature point corresponding to the first feature point from the three-dimensional feature points of the second feature point set includes:
and acquiring the three-dimensional characteristic points with the specific gravity larger than a preset value from the second characteristic point set to obtain the key characteristic points.
Optionally, the determining, based on the parameter, a key feature point corresponding to the first feature point from the three-dimensional feature points of the second feature point set further includes:
sorting the three-dimensional feature points according to the specific gravity to obtain a first sequence;
determining the key feature points from the three-dimensional feature points of the second set of feature points based on the first order.
Optionally, the determining the key feature point from the three-dimensional feature points of the second feature point set based on the first order includes:
and acquiring the three-dimensional characteristic points with the specific gravity within a preset range from the second characteristic point set based on the first sequence to obtain the key characteristic points.
Optionally, the identifying the image to be processed based on the second feature point and the key feature point in the image to be processed includes:
determining a second order based on the specific gravity;
matching the characteristic value of the second characteristic point with the characteristic value of the key characteristic point according to the second sequence;
and identifying the image to be processed based on the matching result.
Optionally, the calculating a proportion of the same first feature point in the first feature point set includes:
acquiring a first number of frames of images in the preset image set;
calculating a second number of frames including the same first feature points;
and calculating the ratio of the second quantity to the first quantity to obtain the specific gravity.
An apparatus for identification of a three-dimensional object, the apparatus comprising: a processor, a memory, and a general purpose bus; wherein the content of the first and second substances,
the general bus is used for realizing communication connection between the processor and the storage;
the processor is configured to execute a three-dimensional object recognition program stored in the storage to implement the steps of:
acquiring three-dimensional feature points corresponding to a first feature point to obtain a second feature point set based on the first feature point in a preset first feature point set; the first feature point is a feature point of each image in a preset image set;
acquiring parameters of the first characteristic point; wherein the parameter is used for characterizing the number of the first characteristic points;
determining key feature points corresponding to the first feature point from the second set of feature points based on the parameters;
and identifying the image to be processed based on the second feature point and the key feature point of the image to be processed.
Optionally, the processor is configured to execute the data processing program stored in the storage, and may further implement the following steps:
calculating the proportion of the same first characteristic points in the first characteristic point set; wherein the first parameter comprises specific gravity.
A computer readable storage medium storing one or more programs, the one or more programs being executable by one or more processors to implement the steps of the method for identifying a three-dimensional object as described above.
The method, the device and the computer readable storage medium for identifying a three-dimensional object provided by the embodiments of the present invention obtain a second feature point set by obtaining three-dimensional feature points corresponding to a first feature point based on the first feature point in a preset first feature point set, where the first feature point is a feature point of each image in the preset image set, obtain a parameter of the first feature point for characterizing the relevance between the first feature point and the preset image set, and determine a key feature point corresponding to the first feature point from the three-dimensional feature points in the second feature point set based on the parameter, so that, in performing image identification, all feature points of an image to be processed are matched with a predetermined portion of key feature points, instead of matching all feature points of the image to be processed with all feature points as in a relative technique, the number of feature points to be matched is reduced compared with that in the relative technique, therefore, the problem that the quantity of the feature point data to be matched is large when all the extracted feature points are required to be matched with all the preset feature points when the three-dimensional object is identified in the relative technology is solved, the matching speed of the feature points is improved, and the image identification efficiency is improved.
Drawings
Fig. 1 is a schematic flowchart of a method for recognizing a three-dimensional object according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of another three-dimensional object recognition method according to an embodiment of the present invention;
fig. 3 is a schematic flowchart of a method for recognizing a three-dimensional object according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an apparatus for recognizing a three-dimensional object according to an embodiment of the present invention.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
An embodiment of the present invention provides a method for identifying a three-dimensional object, which is shown in fig. 1 and includes the following steps:
The first feature point is a feature point of each image in the preset image set.
It should be noted that, in step 101, based on a first feature point in a preset first feature point set, obtaining a three-dimensional feature point corresponding to the first feature point to obtain a second feature point set may be implemented by a three-dimensional object identification device; the three-dimensional object recognition device may have a camera capable of image recognition; for example, the recognition device of the three-dimensional object may be an electronic device having a camera or the like.
The first feature point set includes all feature points of all images in the preset image set, and the first feature point set is a set of all feature points of all images of the feature points. The second characteristic point set comprises three-dimensional characteristic points corresponding to each first characteristic point; of course, the second feature point set may be a set of three-dimensional feature points corresponding to all the first feature points obtained after each of the first feature points is converted into the three-dimensional feature point.
And 102, acquiring parameters of the first characteristic point.
The parameter of the first feature point is used for representing the relevance between the first feature point and the preset image set.
In other embodiments of the present invention, the obtaining 102 of the parameter of the first feature point may be implemented by a recognition device of the three-dimensional object; the parameter of the first feature point may be a parameter for characterizing a relationship between the first feature point and the first feature point set corresponding to each image in the preset image set.
And 103, determining key characteristic points corresponding to the first characteristic points from the three-dimensional characteristic points of the second characteristic point set based on the parameters of the first characteristic points.
And 104, identifying the image to be processed based on the second characteristic point and the key characteristic point of the image to be processed.
The method for identifying a three-dimensional object provided by the embodiment of the invention obtains a second feature point set by obtaining three-dimensional feature points corresponding to a first feature point based on the first feature point in a preset first feature point set, wherein the first feature point is a feature point of each image in the preset image set, obtains a parameter of the first feature point for representing the relevance between the first feature point and the preset image set, and determines a key feature point corresponding to the first feature point from the three-dimensional feature points in the second feature point set based on the parameter, so that the image identification is performed by matching all feature points of an image to be processed with the key feature points of a predetermined part instead of matching all feature points of the image to be processed with all feature points as in a relative technology, and the number of the feature points to be matched is reduced compared with that in the relative technology, therefore, the problem that the quantity of the feature point data to be matched is large when all the extracted feature points are required to be matched with all the preset feature points when the three-dimensional object is identified in the relative technology is solved, the matching speed of the feature points is improved, and the image identification efficiency is improved.
Based on the foregoing embodiments, an embodiment of the present invention provides a method for identifying a three-dimensional object, which is shown in fig. 2 and includes the following steps:
The first feature point is a feature point of each image in the preset image set.
It should be noted that, in the step 202, calculating the proportion of the same first feature point in the first feature point set may be implemented by:
a. a first number of frames of images in a preset image set is acquired.
The first number may refer to a total number of frames included in each image included in the preset image set after the number of frames is added, that is, refer to a number of all frames included in all images in the preset image set. For example, if the total number of all frames of all images included in the preset image set is M, the first number is M.
b. A second number of frames comprising the same first feature points is calculated.
The second number may refer to the number of frames in which the first feature points included in the images corresponding to the frames in all frames in the preset image set are the same. For example, if the first feature points included in the images corresponding to N frames in all frames in the preset image set are the same, the second number is N. M and N are positive integers, and N is less than or equal to M.
c. And calculating the ratio of the second quantity to the first quantity to obtain the specific gravity.
Wherein the specific gravity is a calculation result obtained by dividing the second quantity by the first quantity. The specific gravity obtained at this time is the specific gravity of the same first feature point in the first feature point set. In addition, if a plurality of groups of the same first feature points are included in the first feature point set, a plurality of specific gravities are obtained.
And step 203, the identification equipment of the three-dimensional object acquires the three-dimensional feature points with the specific gravity larger than the preset value from the second feature point set to obtain key feature points.
The preset value may be a preset value, and the preset value may be set according to actual requirements and historical usage data.
And sorting the first characteristic points in the first characteristic point set according to the proportion of the same first characteristic points in the first characteristic point set from large to small or from small to large to obtain a second sequence.
And step 205, the three-dimensional object recognition device matches the feature values of the second feature points with the feature values of the key feature points according to a second sequence.
After the second sequence is obtained, according to the sequence in the second sequence, matching the characteristic values of the second characteristic points of the first name in the second sequence with the characteristic values of the key characteristic points, then matching the characteristic values of the second characteristic points of the second name in the second sequence with the characteristic values of the key characteristic points, and so on until the characteristic values of all the second characteristic points are matched with the characteristic values of the key characteristic points.
And step 206, the identification equipment of the three-dimensional object identifies the image to be processed based on the matching result.
And after a matching result of the characteristic value of each second characteristic point and the characteristic value of the key characteristic point is obtained, identifying the key characteristic point according to successful matching to obtain the image to be processed.
The method for identifying a three-dimensional object provided by the embodiment of the invention obtains a second feature point set by obtaining three-dimensional feature points corresponding to a first feature point based on the first feature point in a preset first feature point set, wherein the first feature point is a feature point of each image in the preset image set, obtains a parameter of the first feature point for representing the relevance between the first feature point and the preset image set, and determines a key feature point corresponding to the first feature point from the three-dimensional feature points in the second feature point set based on the parameter, so that the image identification is performed by matching all feature points of an image to be processed with the key feature points of a predetermined part instead of matching all feature points of the image to be processed with all feature points as in a relative technology, and the number of the feature points to be matched is reduced compared with that in the relative technology, therefore, the problem that the quantity of the feature point data to be matched is large when all the extracted feature points are required to be matched with all the preset feature points when the three-dimensional object is identified in the relative technology is solved, the matching speed of the feature points is improved, and the image identification efficiency is improved.
Based on the foregoing embodiments, an embodiment of the present invention provides a method for identifying a three-dimensional object, which is shown in fig. 2 and includes the following steps:
The first feature point is a feature point of each image in the preset image set.
It should be noted that, the step 302 of calculating the proportion of the same first feature point in the first feature point set may be implemented by:
a. a first number of frames of images in a preset image set is acquired.
b. A second number of frames comprising the same first feature points is calculated.
c. And calculating the ratio of the second quantity to the first quantity to obtain the specific gravity.
After the proportion of the same first characteristic points in the first characteristic point set is obtained, the three-dimensional characteristic points of the second characteristic point set are sequenced according to the sequence from large to small or from small to large; that is, the first order refers to an arrangement order of the three-dimensional feature points of the second feature point set.
Wherein, the step 304 determines the key feature points from the three-dimensional feature points in the second feature point set based on the first order, and can be implemented by:
and acquiring three-dimensional feature points with the specific gravity within a preset range from the second feature point set to obtain key feature points based on the first sequence.
The preset range may be preset, and the preset range may be set according to actual requirements and historical usage data. In one possible implementation, the preset range may refer to a preset numerical range; when the key feature points are obtained, the three-dimensional feature points with the specific gravity within the preset numerical range can be sequentially obtained from the second feature point set according to the sequence of the three-dimensional feature points in the second feature point set.
And step 306, the identification device of the three-dimensional object matches the feature value of the second feature point with the feature value of the key feature point according to a second sequence.
It should be noted that, for the descriptions of the same steps and the same contents in this embodiment as those in other embodiments, reference may be made to the descriptions in other embodiments, which are not described herein again.
The method for identifying a three-dimensional object provided by the embodiment of the invention obtains a second feature point set by obtaining three-dimensional feature points corresponding to a first feature point based on the first feature point in a preset first feature point set, wherein the first feature point is a feature point of each image in the preset image set, obtains a parameter of the first feature point for representing the relevance between the first feature point and the preset image set, and determines a key feature point corresponding to the first feature point from the three-dimensional feature points in the second feature point set based on the parameter, so that the image identification is performed by matching all feature points of an image to be processed with the key feature points of a predetermined part instead of matching all feature points of the image to be processed with all feature points as in a relative technology, and the number of the feature points to be matched is reduced compared with that in the relative technology, therefore, the problem that the quantity of the feature point data to be matched is large when all the extracted feature points are required to be matched with all the preset feature points when the three-dimensional object is identified in the relative technology is solved, the matching speed of the feature points is improved, and the image identification efficiency is improved.
Based on the foregoing embodiments, an embodiment of the present invention provides an apparatus for recognizing a three-dimensional object, which may be applied to a method for recognizing a three-dimensional object provided in the embodiments corresponding to fig. 1 to 3, and as shown in fig. 4, the apparatus 4 may include: a processor 41, storage 42, and a general purpose bus 43; wherein the content of the first and second substances,
the general bus 43 is used for realizing communication connection between the processor 41 and the storage 42;
the processor 41 is configured to execute a recognition program of the three-dimensional object stored in the storage to implement the following steps:
acquiring three-dimensional feature points corresponding to the first feature points to obtain a second feature point set based on the first feature points in the preset first feature point set;
the first feature point is a feature point of each image in a preset image set;
acquiring parameters of the first characteristic point;
the parameters are used for representing the number of the first characteristic points;
determining key feature points corresponding to the first feature points from the second feature point set based on the parameters;
and identifying the image to be processed based on the second characteristic point and the key characteristic point of the image to be processed.
In other embodiments of the present invention, the processor is configured to execute the parameter stored in the storage to obtain the first feature point, and may implement the following steps:
calculating the proportion of the same first characteristic points in the first characteristic point set;
wherein the parameter of the first feature point includes a specific gravity.
In other embodiments of the present invention, the processor is configured to determine a key feature point corresponding to the first feature point from the three-dimensional feature points of the second feature point set based on the parameters stored in the storage, and may implement the following steps:
and acquiring the three-dimensional characteristic points with the specific gravity larger than a preset value from the second characteristic point set to obtain the key characteristic points corresponding to the first characteristic points.
In other embodiments of the present invention, the processor is configured to determine a key feature point corresponding to the first feature point from the three-dimensional feature points of the second feature point set based on the parameters stored in the storage, and may implement the following steps:
sorting the three-dimensional feature points according to the specific gravity to obtain a first sequence;
based on the first sequence, key feature points corresponding to the first feature points are determined from the three-dimensional feature points of the second feature point set.
In other embodiments of the present invention, the processor is configured to determine a key feature point corresponding to the first feature point from the three-dimensional feature points of the second feature point set based on the first order stored in the storage, and may implement the following steps:
and acquiring three-dimensional feature points with the specific gravity within a preset range from the second feature point set based on the first sequence to obtain key feature points corresponding to the first feature points.
In other embodiments of the present invention, the processor is configured to execute the second feature point and the key feature point stored in the storage to identify the image to be processed based on the image to be processed, and may implement the following steps:
determining a second order based on the proportion of the same first characteristic points in the first characteristic point set;
matching the characteristic value of the second characteristic point with the characteristic value of the key characteristic point according to a second sequence;
and identifying the image to be processed based on the matching result.
In other embodiments of the present invention, the processor is configured to execute the calculation stored in the storage to calculate the proportion of the same first feature point in the first feature point set, and may implement the following steps:
acquiring a first number of frames of images in a preset image set;
calculating a second number of frames including the same first feature points;
and calculating the ratio of the second quantity to the first quantity to obtain the specific gravity.
It should be noted that, in the embodiment, a specific implementation process of the step executed by the processor may refer to an implementation process in the identification method of the three-dimensional object provided in the embodiments corresponding to fig. 1 to 3, and details are not described here.
In the three-dimensional object recognition device provided by the embodiment of the invention, when the image recognition is performed, all feature points of the image to be processed are matched with the predetermined part of key feature points, instead of matching all feature points of the image to be processed with all feature points as in the relative technology, the number of the feature points needing to be matched is reduced compared with that in the relative technology, so that the problem that when the three-dimensional object is recognized in the relative technology, all extracted feature points are required to be matched with all preset feature points, and the quantity of the feature points needing to be matched is large is solved, the matching speed of the feature points is increased, and the image recognition efficiency is improved.
Based on the foregoing embodiments, embodiments of the invention provide a computer-readable storage medium storing one or more programs, the one or more programs being executable by one or more processors to perform the steps of:
acquiring three-dimensional feature points corresponding to the first feature points to obtain a second feature point set based on the first feature points in the preset first feature point set;
the first feature point is a feature point of each image in a preset image set;
acquiring parameters of the first characteristic point;
the parameters are used for representing the number of the first characteristic points;
determining key feature points corresponding to the first feature points from the second feature point set based on the parameters;
and identifying the image to be processed based on the second characteristic point and the key characteristic point of the image to be processed.
In other embodiments of the present invention, the one or more programs are executable by the one or more processors to obtain the parameter of the first feature point, and the following steps are implemented:
calculating the proportion of the same first characteristic points in the first characteristic point set;
wherein the parameter of the first feature point includes a specific gravity.
In other embodiments of the present invention, the one or more programs are executable by the one or more processors to determine key feature points corresponding to the first feature point from the three-dimensional feature points of the second feature point set based on the parameters, and may implement the steps of:
and acquiring the three-dimensional characteristic points with the specific gravity larger than a preset value from the second characteristic point set to obtain the key characteristic points corresponding to the first characteristic points.
In other embodiments of the present invention, the one or more programs are executable by the one or more processors to determine key feature points corresponding to the first feature point from the three-dimensional feature points of the second feature point set based on the parameters, and may implement the steps of:
sorting the three-dimensional feature points according to the specific gravity to obtain a first sequence;
based on the first sequence, key feature points corresponding to the first feature points are determined from the three-dimensional feature points of the second feature point set.
In other embodiments of the present invention, the one or more programs are executable by the one or more processors to determine key feature points corresponding to the first feature point from three-dimensional feature points of the second feature point set based on the first order, and may implement the steps of:
and acquiring three-dimensional feature points with the specific gravity within a preset range from the second feature point set based on the first sequence to obtain key feature points corresponding to the first feature points.
In other embodiments of the present invention, the one or more programs are executable by the one or more processors to identify the image to be processed based on the second feature point and the key feature point of the image to be processed, and may implement the following steps:
determining a second order based on the proportion of the same first characteristic points in the first characteristic point set;
matching the characteristic value of the second characteristic point with the characteristic value of the key characteristic point according to a second sequence;
and identifying the image to be processed based on the matching result.
In other embodiments of the present invention, the one or more programs are executable by the one or more processors to calculate a proportion of the same first feature point in the first feature point set, and may implement the following steps:
acquiring a first number of frames of images in a preset image set;
calculating a second number of frames including the same first feature points;
and calculating the ratio of the second quantity to the first quantity to obtain the specific gravity.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention.
Claims (7)
1. A method of identifying a three-dimensional object, the method comprising:
acquiring three-dimensional feature points corresponding to a first feature point to obtain a second feature point set based on the first feature point in a preset first feature point set; the first feature point is a feature point of each image in a preset image set;
acquiring parameters of the first characteristic point; wherein the parameter is used for characterizing the relevance between the first characteristic point and the preset image set;
determining key feature points corresponding to the first feature points from the three-dimensional feature points of the second feature point set based on the parameters;
the acquiring of the parameter of the first feature point includes:
calculating the proportion of the same first characteristic point in the first characteristic point set, wherein the parameter comprises the proportion;
determining a second sequence based on the proportion, and matching the characteristic value of a second characteristic point of the image to be processed with the characteristic value of the key characteristic point according to the second sequence;
and identifying the image to be processed based on the matching result.
2. The method according to claim 1, wherein the determining, based on the parameter, a key feature point corresponding to the first feature point from among the three-dimensional feature points of the second feature point set comprises:
and acquiring the three-dimensional characteristic points with the specific gravity larger than a preset value from the second characteristic point set to obtain the key characteristic points.
3. The method according to claim 1, wherein the determining, based on the parameter, a key feature point corresponding to the first feature point from among the three-dimensional feature points of the second feature point set further comprises:
sorting the three-dimensional feature points according to the specific gravity to obtain a first sequence;
determining the key feature points from the three-dimensional feature points of the second set of feature points based on the first order.
4. The method according to claim 3, wherein determining the key feature point from the three-dimensional feature points of the second set of feature points based on the first order comprises:
and acquiring the three-dimensional characteristic points with the specific gravity within a preset range from the second characteristic point set based on the first sequence to obtain the key characteristic points.
5. The method according to any one of claims 1 to 4, wherein the calculating of the proportion of the same first feature point in the first feature point set comprises:
acquiring a first number of frames of images in the preset image set;
calculating a second number of frames including the same first feature points;
and calculating the ratio of the second quantity to the first quantity to obtain the specific gravity.
6. An apparatus for recognizing a three-dimensional object, the apparatus comprising: a processor, a memory, and a general purpose bus; wherein the content of the first and second substances,
the general bus is used for realizing communication connection between the processor and the storage;
the processor is configured to execute a three-dimensional object recognition program stored in the storage to implement the steps of:
acquiring three-dimensional feature points corresponding to a first feature point to obtain a second feature point set based on the first feature point in a preset first feature point set; the first feature point is a feature point of each image in a preset image set;
acquiring parameters of the first characteristic point; wherein the parameter is used for characterizing the relevance between the first characteristic point and the preset image set;
determining key feature points corresponding to the first feature points from the three-dimensional feature points of the second feature point set based on the parameters;
the processor is further configured to calculate a proportion of the same first feature point in the first feature point set; wherein the parameter comprises specific gravity;
determining a second sequence based on the proportion, and matching the characteristic value of a second characteristic point of the image to be processed with the characteristic value of the key characteristic point according to the second sequence;
and identifying the image to be processed based on the matching result.
7. A computer-readable storage medium, characterized in that the computer-readable storage medium stores one or more programs which are executable by one or more processors to implement the steps of the method for identification of a three-dimensional object according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811070706.XA CN109325432B (en) | 2018-09-13 | 2018-09-13 | Three-dimensional object identification method and equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811070706.XA CN109325432B (en) | 2018-09-13 | 2018-09-13 | Three-dimensional object identification method and equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109325432A CN109325432A (en) | 2019-02-12 |
| CN109325432B true CN109325432B (en) | 2021-11-16 |
Family
ID=65265340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811070706.XA Active CN109325432B (en) | 2018-09-13 | 2018-09-13 | Three-dimensional object identification method and equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109325432B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114098536B (en) * | 2021-12-01 | 2023-04-14 | 湖南格兰博智能科技有限责任公司 | Obstacle-crossing and trapped floor-sweeping robot detection method and floor-sweeping robot |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103297811A (en) * | 2012-02-24 | 2013-09-11 | 北京明日时尚信息技术有限公司 | Method for realizing video advertisement in intelligently embedding mode |
| CN105138525A (en) * | 2014-05-30 | 2015-12-09 | 株式会社日立制作所 | Traffic video processing device and method, and retrieval device and method |
| CN105913416A (en) * | 2016-04-06 | 2016-08-31 | 中南大学 | Method for automatically segmenting three-dimensional human face model area |
| CN106022210A (en) * | 2016-05-04 | 2016-10-12 | 成都指码科技有限公司 | Vein profile three-dimensional point cloud matching identity identifying method and device |
| US9652896B1 (en) * | 2015-10-30 | 2017-05-16 | Snap Inc. | Image based tracking in augmented reality systems |
-
2018
- 2018-09-13 CN CN201811070706.XA patent/CN109325432B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103297811A (en) * | 2012-02-24 | 2013-09-11 | 北京明日时尚信息技术有限公司 | Method for realizing video advertisement in intelligently embedding mode |
| CN105138525A (en) * | 2014-05-30 | 2015-12-09 | 株式会社日立制作所 | Traffic video processing device and method, and retrieval device and method |
| US9652896B1 (en) * | 2015-10-30 | 2017-05-16 | Snap Inc. | Image based tracking in augmented reality systems |
| CN105913416A (en) * | 2016-04-06 | 2016-08-31 | 中南大学 | Method for automatically segmenting three-dimensional human face model area |
| CN106022210A (en) * | 2016-05-04 | 2016-10-12 | 成都指码科技有限公司 | Vein profile three-dimensional point cloud matching identity identifying method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109325432A (en) | 2019-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108090470B (en) | Face alignment method and device | |
| CN109035246B (en) | Face image selection method and device | |
| KR101282196B1 (en) | Apparatus and method for separating foreground and background of based codebook In a multi-view image | |
| CN109977983B (en) | Method and device for obtaining training image | |
| CN108763268B (en) | Batch processing method and device of three-dimensional model and storage medium | |
| CN109685805B (en) | Image segmentation method and device | |
| CN110648289A (en) | Image denoising processing method and device | |
| CN112016697A (en) | Method, device and equipment for federated learning and storage medium | |
| CN111783812B (en) | Forbidden image recognition method, forbidden image recognition device and computer readable storage medium | |
| CN109325432B (en) | Three-dimensional object identification method and equipment and computer readable storage medium | |
| CN105354228A (en) | Similar image searching method and apparatus | |
| CN106326920B (en) | Off-line synchronization method and device for telemetering data and video image data | |
| CN108416425B (en) | Convolution operation method and device | |
| CN110490056A (en) | The method and apparatus that image comprising formula is handled | |
| CN113297416A (en) | Video data storage method and device, electronic equipment and readable storage medium | |
| CN116844006A (en) | Target identification method and device, electronic equipment and readable storage medium | |
| CN115713669B (en) | Image classification method and device based on inter-class relationship, storage medium and terminal | |
| CN109598201B (en) | Action detection method and device, electronic equipment and readable storage medium | |
| CN115358914B (en) | Data processing method and device for visual detection, computer equipment and medium | |
| CN116661786A (en) | Design page generation method and device | |
| CN107329943B (en) | Intelligent graph adding method, storage medium and application server | |
| CN110795993A (en) | Method and device for constructing model, terminal equipment and medium | |
| CN110008940B (en) | Method and device for removing target object in image and electronic equipment | |
| CN111508045A (en) | Picture synthesis method and device | |
| CN111199189A (en) | Target object tracking method and system, electronic equipment and storage medium |
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 |