CN112949686A - Matching method based on optimal local distance - Google Patents

Matching method based on optimal local distance Download PDF

Info

Publication number
CN112949686A
CN112949686A CN202110126685.4A CN202110126685A CN112949686A CN 112949686 A CN112949686 A CN 112949686A CN 202110126685 A CN202110126685 A CN 202110126685A CN 112949686 A CN112949686 A CN 112949686A
Authority
CN
China
Prior art keywords
matching
difference
degree
optimal
local distance
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
Application number
CN202110126685.4A
Other languages
Chinese (zh)
Other versions
CN112949686B (en
Inventor
范敏
张志娟
张跃
田磊
刘子辉
粱辉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sinotruk Jinan Power Co Ltd
Original Assignee
Sinotruk Jinan Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Sinotruk Jinan Power Co Ltd filed Critical Sinotruk Jinan Power Co Ltd
Priority to CN202110126685.4A priority Critical patent/CN112949686B/en
Publication of CN112949686A publication Critical patent/CN112949686A/en
Application granted granted Critical
Publication of CN112949686B publication Critical patent/CN112949686B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to a matching method based on optimal local distance, which is used for researching the matching problem in the multi-source information fusion technology of an unmanned vehicle based on a bipartite graph model and dividing an object to be matched into a set X and a set Y. Preferentially selecting the element X with the highest element matching degree in the set X and the set Yi、YjForming an optimal matching pair; and then, forming a new bipartite graph by the remaining elements, and matching according to the optimal local distance between the elements. The invention considers the influence of the distance between elements on the matching result, and ensures the matching quality and the matching quantity.

Description

Matching method based on optimal local distance
Technical Field
The invention belongs to the technical field of unmanned driving, relates to a matching method in a multivariate information fusion technology, and particularly relates to a matching method based on an optimal local distance.
Background
The rapid development of science and technology makes the unmanned technology mature day by day. The key technologies of the unmanned automobile comprise environment perception, navigation positioning, decision planning, control and the like. Environmental sensing is usually accomplished by a combination of multiple sensors, subject to the performance of the sensors themselves. The sensors are independent in the observation process, and are particularly complex when a plurality of detection targets exist, and the system is difficult to spontaneously determine the matching relationship among the targets detected by the sensors, so that a matching method in the multi-source information fusion technology needs to be introduced.
The matching method commonly used at present is the Hungarian algorithm, which is the most common bipartite graph matching method and is based on the idea proved by sufficiency in Hall's theorem, and the core is to search an augmented path and use the augmented path to ask the bipartite graph for maximum matching. The Hungarian algorithm preferentially selects matching objects according to the ranking order and determines as many matching pairs as possible, but the difference degree between each matching pair is not fully considered, and the situation that the optimal matching is abandoned for obtaining the maximum matching number may exist, namely the final result is the maximum matching and is not the optimal matching.
In view of the above, the present invention provides a matching method based on an optimal local distance, so as to solve the defects in the prior art.
Disclosure of Invention
Aiming at the problem that the difference degree between each matching pair is not fully considered in the existing method, and the final result is probably the most matching rather than the optimal matching, the invention provides a matching method based on the optimal local distance, which ensures the matching quality and the matching quantity.
In order to achieve the purpose, the invention provides the following technical scheme:
a matching method based on optimal local distance utilizes a bipartite graph model to research the matching problem in the multi-source information fusion technology of an unmanned vehicle, and comprises the following steps:
s1: let the bipartite graph have a set X and a set Y, the number of internal elements is m and n, respectively, and any element in the set X is represented as XiAnd any element in the set Y is represented as YjWherein i is more than or equal to 1 and less than or equal to m, and j is more than or equal to 1 and less than or equal to n;
s2: by means of distance calculationCalculating the difference degree S between m elements in the set X and n elements in the set Yi_j；
S3: according to the degree of difference Si_jEstablishing XiAnd YjThe connection relation between the two;
s4: preferentially selecting the element X with the highest element matching degree in the set X and the set Yi、YjEstablishing an optimal matching pair;
s5: the rest of Xi、YjForm a new set A, B, with its internal elements denoted Ai、Bj；
S6：AiSequentially selecting one B with optimal local distancejMatching and selected BjNo longer participate in the matching;
s7: original XiAnd (4) judging whether all the matching is finished, if so, outputting all the matching results, and otherwise, sequentially continuing to carry out matching judgment.
Preferably, the set X represents a detection target of the laser radar, and the set Y represents a detection target of the camera; the set X and the set Y in the bipartite graph respectively represent a detection target of the laser radar and a detection target of the camera, and measurement-measurement data matching in multi-source information fusion of the unmanned vehicle is achieved.
Preferably, the distance calculation method in step S2 adopts the euclidean distance calculation process as follows, where the element in the set X is Xi(x1,y1) The element in the set Y is Yj(x2，y2) Calculating XiAnd YjDegree of difference therebetween
Figure BDA0002923747820000031
Preferably, the distance calculation method in step S2 adopts a manhattan distance calculation process, where the element in the set X is Xi(x1,y1) The element in the set Y is Yj(x2，y2) Calculating XiAnd YjDegree of difference S betweeni_j＝|x1-x2|+|y1-y2|；
Preferably, the difference S is calculated in step S2i_jThe degree of difference Si_jArranged in a small-to-large manner; the difference degree Si_jArranging the elements in a small-to-large manner facilitates subsequent selection of the element with the least difference for matching.
Preferably, X is established in the step S3iAnd YjThe connection relation between the two is specifically as follows:
the first step is as follows: setting a threshold value T, wherein T is greater than 0;
the second step is that: if the difference is Si_j>T, then SijIf 0 is equal to or less than-1, the degree of difference Si_jT is less than or equal to T, then Sij＝Si_j；
The third step: according to SijThe size establishes a connection relation if Sij<0, then XiAnd YjIf S has no connecting edgeijGreater than or equal to 0, then XiAnd YjWith connecting edges in between.
Establishing connection relation by comparing difference degrees, wherein X with larger difference degreeiAnd YjCannot be connected with each other, and has small difference degree of XiAnd YjAnd a connection relation is established between the two, so that the matching quality is ensured.
Preferably, the process of establishing the optimal matching pair in step S4 includes the following steps:
is XiFinding matching element and finding matching element Y from set YjMatching element YjShould satisfy the following relation with XiDegree of difference S ofi_jMinimum, Y satisfying the above requirementsjThere are 0 or more;
is YjFinding matching element and finding matching element X from set XiMatch element XiShould satisfy the relation with YjDegree of difference S ofi_jAt minimum, X satisfying the above requirementsiThere are 0 or more;
selecting the optimal matching pair, if there is some XiAnd YjWhen they match each other and both have one and only one matching element, they are both confirmedDetermining an optimal matching pair;
by preferentially selecting the element X with the highest element matching degree in the set X and the set Yi、YjThe optimal matching pair is established, so that the matching quality can be greatly improved.
Preferably, a in step S6iSequentially selecting one B with optimal local distancejIn the process of matching AiSelecting the degree of difference Si_jSmallest one BjMatching is carried out; and selecting the element with the optimal local distance and the minimum difference degree for matching, thereby effectively ensuring the matching quality.
The method has the beneficial effect that the matching problem in the multi-source information fusion technology is researched based on the bipartite graph model. In the matching process, the element with the highest element matching degree in the two sets is preferentially selected for matching, and the method has the advantages that the element can be prevented from occupying the matching elements of other elements.
Therefore, compared with the prior art, the invention has prominent substantive features and remarkable progress, and the beneficial effects of the implementation are also obvious.
Drawings
In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present invention, the drawings used in the description of the embodiments or prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
Fig. 1 is a flowchart of a matching method based on an optimal local distance according to embodiment 1 of the present invention.
FIG. 2 shows X in example 2 of the present inventioniAnd YjThe connection relationship diagram of (1).
FIG. 3 shows X in example 2 of the present inventioniAnd YjThe matching list of (2).
FIG. 4 shows X in example 2 of the present inventioniAnd YjThe optimal matching connection graph.
FIG. 5 shows A in example 2 of the present inventioniAnd BjThe matching connection graph of (1).
FIG. 6 shows X in example 3 of the present inventioniAnd YjThe connection relationship diagram of (1).
FIG. 7 shows X in example 3 of the present inventioniAnd YjThe matching list of (2).
FIG. 8 shows X in example 3 of the present inventioniAnd YjThe optimal matching connection graph.
FIG. 9 shows A in example 3 of the present inventioniAnd BjThe matching connection graph of (1).
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the drawings in the embodiment of the present invention, and it is obvious that the described embodiment is only a part of the embodiment of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1:
as shown in fig. 1, the embodiment provides a matching method based on an optimal local distance, which utilizes a bipartite graph model to research a matching problem in a multi-source information fusion technology of an unmanned vehicle, and includes the following steps:
s1: let the bipartite graph have a set X and a set Y, the number of internal elements is m and n, respectively, and any element in the set X is represented as XiAnd any element in the set Y is represented as YjWherein i is more than or equal to 1 and less than or equal to m, and j is more than or equal to 1 and less than or equal to n;
s2: calculating the difference S between m elements in the set X and n elements in the set Y by adopting a distance calculation methodi_j；
S3: according to the degree of difference Si_jEstablishing XiAnd YjThe connection relation between the two;
s4: preferentially selecting the element with the highest local matching degree in the set X and the set YElement Xi、YjEstablishing an optimal matching pair;
s5: the rest of Xi、YjForm a new set A, B, with its internal elements denoted Ai、Bj；
S6：AiSequentially selecting one B with optimal local distancejMatching and selected BjNo longer participate in the matching;
s7: original XiAnd (4) judging whether all the matching is finished, if so, outputting all the matching results, and otherwise, sequentially continuing to carry out matching judgment.
Example 2:
the embodiment provides a matching method based on an optimal local distance, which utilizes a bipartite graph model to research a matching problem, takes measurement-measurement target matching in multi-source information fusion of an unmanned vehicle as an example, and comprises the following steps:
s1: the bipartite graph comprises a set X and a set Y, wherein the number of elements in the set X is m-10, the number of elements in the set Y is n-12, and any element in the set X is represented as XiAnd any element in the set Y is represented as YjWherein i is more than or equal to 1 and less than or equal to 10, j is more than or equal to 1 and less than or equal to 12, and the element X in the set Xi＝X1、X2、X3、X4、X5、X6、X7、X8、X9、X10In the set Y, the element Y is Y1、Y2、Y3、Y4、Y5、Y6、Y7、Y8、Y9、Y10、Y11、Y12(ii) a The set X represents a detection target of the laser radar, the set Y represents a detection target of the camera, and measurement-measurement data matching in multi-source information fusion of the unmanned vehicle is achieved.
S2: calculating the difference degree S between every two 10 elements in the set X and 12 elements in the set Y by adopting a distance calculation methodi_j；
The distance calculation adopts the Euclidean distance calculation method as follows: the elements in the set X are Xi(x1,y1) The element in the set Y is Yj(x2，y2) Calculating XiAnd YjDegree of difference therebetween
Figure BDA0002923747820000071
Calculating the degree of difference Si_jThe degree of difference Si_jArranged in a small-to-large manner; the difference degree Si_jArranging the elements in a small-to-large manner facilitates subsequent selection of the element with the least difference for matching.
S3: according to the degree of difference Si_jEstablishing XiAnd YjThe connection relationship between the two is shown in fig. 2, and the specific process is as follows:
the first step is as follows: setting a threshold value T, wherein T is greater than 0, and taking T as 6;
the second step is that: if the difference is Si_j>6, then SijIf 0 is equal to or less than-1, the degree of difference Si_jIf the ratio is less than or equal to 6, then Sij＝Si_j；
The third step: according to SijThe size establishes a connection relation if Sij<0, then XiAnd YjIf S has no connecting edgeijGreater than or equal to 0, then XiAnd YjWith connecting edges in between.
Establishing connection relation by comparing difference degrees, wherein X with larger difference degreeiAnd YjCannot be connected with each other, and has small difference degree of XiAnd YjAnd a connection relation is established between the two, so that the matching quality is ensured.
S4: as shown in FIGS. 3 to 4, the element X with the highest local matching degree in the set X and the set Y is preferentially selectedi、YjEstablishing an optimal matching pair, wherein the specific process comprises the following steps:
is XiFinding matching element and finding matching element Y from set YjMatching element YjShould satisfy the following relation with XiDegree of difference S ofi_jMinimum, Y satisfying the above requirementsjThere are 0 or more; wherein, X1Match Y2，X2Match Y1、Y3，X3Match Y4，X4Match Y2，X5Match Y10，X6Match Y5，X7Match Y6，X8Match Y9，X9Match Y8、Y11，X10Match Y8、Y10；
Is YjFinding matching element and finding matching element X from set XiMatch element XiShould satisfy the relation with YjDegree of difference S ofi_jAt minimum, X satisfying the above requirementsiThere are 0 or more; wherein Y is1Match X2，Y2Match X4，Y3Match X2、X4，Y4Match X3，Y5Match X6，Y6Match X4，Y7Match X4、X10，Y8Match X5、X9、X10，Y9Match X8，Y10Match X5，Y11Match X9，Y12Match X10；
Selecting the optimal matching pair, if there is some XiAnd YjWhen the matching elements are matched with each other and only one matching element exists, the two matching elements are determined as the optimal matching pair; wherein X3Y4、X4Y2、X5Y10、X6Y5、X8Y9Is an optimal matching pair;
by preferentially selecting the element X with the highest element matching degree in the set X and the set Yi、YjThe optimal matching pair is established, so that the matching quality can be greatly improved.
S5: the rest of X1、X2、X7、X9、X10、Y1、Y3、Y6、Y7、Y8、Y11、Y12Internal elements A of set A constituting a new set A, BiIs A1、A2、A7、A9、A10Collection, collectionWith internal elements B of BjIs B1、B3、B6、B7、B8、B11、B12；
S6: as shown in FIG. 5, AiSequentially selecting one B with optimal local distancejMatching and selected BjNo longer participate in the matching; wherein A isiSequentially selecting one B with optimal local distancejIn the process of matching AiSelecting the degree of difference Si_jSmallest one BjCarrying out matching A1Match B3，A2Match B1,A7Match B6,A9Match B8，A10Match B7(ii) a And selecting the element with the optimal local distance and the minimum difference degree for matching, thereby effectively ensuring the matching quality.
S7: original XiAre all traversed and judged, and all matched pairs X are output3Y4、X4Y2、X5Y10、X6Y5、X8Y9，X1Y3，X2Y1,X7Y6,X9Y8，X10Y7。
Example 3:
the embodiment provides a matching method based on an optimal local distance, which utilizes a bipartite graph model to research a matching problem, takes measurement-measurement target matching in multi-source information fusion of an unmanned vehicle as an example, and comprises the following steps:
s1: the bipartite graph comprises a set X and a set Y, wherein the number of elements in the set X is m-10, the number of elements in the set Y is n-10, and any element in the set X is represented as XiAnd any element in the set Y is represented as YjWherein i is more than or equal to 1 and less than or equal to 10, j is more than or equal to 1 and less than or equal to 10, and the element X in the set Xi＝X1、X2、X3、X4、X5、X6、X7、X8、X9、X10In the set Y, the element Y is Y1、Y2、Y3、Y4、Y5、Y6、Y7、Y8、Y9、Y10(ii) a The set X represents a detection target of the laser radar, the set Y represents a detection target of the camera, and measurement-measurement data matching in multi-source information fusion of the unmanned vehicle is achieved.
S2: calculating the difference degree S between every two 10 elements in the set X and 12 elements in the set Y by adopting a distance calculation methodi_j；
The distance calculation adopts a Manhattan distance calculation mode process as follows, and the element in the set X is Xi(x1,y1) The element in the set Y is Yj(x2，y2) Calculating XiAnd YjDegree of difference S betweeni_j＝|x1-x2|+|y1-y2|；
Calculating the degree of difference Si_jThe degree of difference Si_jArranged in a small-to-large manner; the difference degree Si_jArranging the elements in a small-to-large manner facilitates subsequent selection of the element with the least difference for matching.
S3: according to the degree of difference Si_jEstablishing XiAnd YjThe connection relationship between the two is shown in fig. 6, and the specific process is as follows:
the first step is as follows: setting a threshold value T, wherein T is greater than 0, and taking T as 6;
the second step is that: if the difference is Si_j>6, then SijIf 0 is equal to or less than-1, the degree of difference Si_jIf the ratio is less than or equal to 6, then Sij＝Si_j；
The third step: according to SijThe size establishes a connection relation if Sij<0, then XiAnd YjIf S has no connecting edgeijGreater than or equal to 0, then XiAnd YjWith connecting edges in between.
Establishing connection relation by comparing difference degrees, wherein X with larger difference degreeiAnd YjCannot be connected with each other, and has small difference degree of XiAnd YjAnd a connection relation is established between the two, so that the matching quality is ensured.
S4：As shown in FIGS. 7 to 8, the element X with the highest local matching degree in the set X and the set Y is preferentially selectedi、YjEstablishing an optimal matching pair, wherein the specific process comprises the following steps:
is XiFinding matching element and finding matching element Y from set YjMatching element YjShould satisfy the following relation with XiDegree of difference S ofi_jMinimum, Y satisfying the above requirementsjThere are 0 or more; wherein, X1Match Y2，X2Match Y1、Y3，X3Match Y4，X4Match Y2，X5Match Y10，X6Match Y5，X7Match Y6，X8Match Y9，X9Match Y8，X10Match Y8、Y10；
Is YjFinding matching element and finding matching element X from set XiMatch element XiShould satisfy the relation with YjDegree of difference S ofi_jAt minimum, X satisfying the above requirementsiThere are 0 or more; wherein Y is1Match X2，Y2Match X4，Y3Match X2、X4，Y4Match X3，Y5Match X6，Y6Match X4，Y7Match X4、X10，Y8Match X5、X9、X10，Y9Match X8，Y10Match X5；
Selecting the optimal matching pair, if there is some XiAnd YjWhen the matching elements are matched with each other and only one matching element exists, the two matching elements are determined as the optimal matching pair; wherein X3Y4、X4Y2、X5Y10、X6Y5、X8Y9Is an optimal matching pair;
by preferentially selecting the element X with the highest element matching degree in the set X and the set Yi、YjEstablishing optimal pair of matchesThe matching quality can be greatly improved.
S5: the rest of X1、X2、X7、X9、X10、Y1、Y3、Y6、Y7、Y8Internal elements A of set A constituting a new set A, BiIs A1、A2、A7、A9、A10Internal elements B of set BjIs B1、B3、B6、B7、B8；
S6: as shown in FIG. 9, AiSequentially selecting one B with optimal local distancejMatching and selected BjNo longer participate in the matching; wherein A isiSequentially selecting one B with optimal local distancejIn the process of matching AiSelecting the degree of difference Si_jSmallest one BjCarrying out matching A1Match B3，A2Match B1,A7Match B6,A9Match B8，A10Match B7(ii) a And selecting the element with the optimal local distance and the minimum difference degree for matching, thereby effectively ensuring the matching quality.
S7: original XiAre all traversed and judged, and all matched pairs X are output3Y4、X4Y2、X5Y10、X6Y5、X8Y9，X1Y3，X2Y1,X7Y6,X9Y8，X10Y7。
Although the present invention has been described in detail by referring to the drawings in connection with the preferred embodiments, the present invention is not limited thereto. Various equivalent modifications or substitutions can be made on the embodiments of the present invention by those skilled in the art without departing from the spirit and scope of the present invention, and these modifications or substitutions are within the scope of the present invention/any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention.

Claims (8)

1. A matching method based on optimal local distance is characterized in that the method utilizes a bipartite graph model to research the matching problem in the multi-source information fusion technology of an unmanned vehicle, and comprises the following steps:
s1: let the bipartite graph have a set X and a set Y, the number of internal elements is m and n, respectively, and any element in the set X is represented as XiAnd any element in the set Y is represented as YjWherein i is more than or equal to 1 and less than or equal to m, and j is more than or equal to 1 and less than or equal to n;
s2: calculating the difference S between m elements in the set X and n elements in the set Y by adopting a distance calculation methodi_j；
S3: according to the degree of difference Si_jEstablishing XiAnd YjThe connection relation between the two;
s4: preferentially selecting the element X with the highest element matching degree in the set X and the set Yi、YjEstablishing an optimal matching pair;
s5: the rest of Xi、YjForm a new set A, B, with its internal elements denoted Ai、Bj；
S6：AiSequentially selecting one B with optimal local distancejMatching and selected BjNo longer participate in the matching;
s7: original XiAnd (4) judging whether all the matching is finished, if so, outputting all the matching results, and otherwise, sequentially continuing to carry out matching judgment.
2. The matching method based on optimal local distance as claimed in claim 1, wherein the distance calculation method in step S2 adopts euclidean distance calculation process as follows, and the element in the set X is Xi(x1,y1) The element in the set Y is Yj(x2，y2) Calculating XiAnd YjDegree of difference therebetween
Figure FDA0002923747810000011
3. The matching method based on optimal local distance as claimed in claim 1, wherein the distance calculation method in step S2 adopts a manhattan distance calculation process, where the element in the set X is Xi(x1,y1) The element in the set Y is Yj(x2，y2) Calculating XiAnd YjDegree of difference S betweeni_j＝|x1-x2|+|y1-y2|。
4. The matching method based on optimal local distance as claimed in claim 2 or 3, wherein the difference S is calculated in step S2i_jThe degree of difference Si_jArranged in a small to large manner.
5. The matching method based on optimal local distance as claimed in claim 4, wherein X is established in step S3iAnd YjThe connection relation between the two is specifically as follows:
the first step is as follows: setting a threshold value T, wherein T is greater than 0;
the second step is that: if the difference is Si_j>T, then SijIf 0 is equal to or less than-1, the degree of difference Si_jT is less than or equal to T, then Sij＝Si_j；
The third step: according to SijThe size establishes a connection relation if Sij<0, then XiAnd YjIf S has no connecting edgeijGreater than or equal to 0, then XiAnd YjWith connecting edges in between.
6. The optimal local distance-based matching method according to claim 5, wherein the step S4 of establishing the optimal matching pair comprises the following steps:
is XiFinding matching element and finding matching element Y from set YjMatch ofElement YjShould satisfy the following relation with XiDegree of difference S ofi_jMinimum, Y satisfying the above requirementsjThere are 0 or more;
is YjFinding matching element and finding matching element X from set XiMatch element XiShould satisfy the relation with YjDegree of difference S ofi_jAt minimum, X satisfying the above requirementsiThere are 0 or more;
selecting the optimal matching pair, if there is some XiAnd YjWhen the two matching elements are matched with each other and both have one matching element and only one matching element, the two matching elements are determined as the optimal matching pair.
7. The optimal local distance-based matching method according to claim 6, wherein A in step S6iSequentially selecting one B with optimal local distancejIn the process of matching AiSelecting the degree of difference Si_jSmallest one BjAnd (6) matching.
8. The optimal local distance-based matching method according to claim 7, wherein the set X represents the detection target of the laser radar, and the set Y represents the detection target of the camera, and the method is applied to the target matching of 'measurement-measurement' in the multi-source information fusion of the unmanned vehicle.
CN202110126685.4A 2021-01-29 2021-01-29 Matching method based on optimal local distance Active CN112949686B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110126685.4A CN112949686B (en) 2021-01-29 2021-01-29 Matching method based on optimal local distance

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110126685.4A CN112949686B (en) 2021-01-29 2021-01-29 Matching method based on optimal local distance

Publications (2)

Publication Number Publication Date
CN112949686A true CN112949686A (en) 2021-06-11
CN112949686B CN112949686B (en) 2022-12-09

Family

ID=76239850

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110126685.4A Active CN112949686B (en) 2021-01-29 2021-01-29 Matching method based on optimal local distance

Country Status (1)

Country Link
CN (1) CN112949686B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110866687A (en) * 2019-11-07 2020-03-06 中盈优创资讯科技有限公司 Task allocation method and device
CN111078803A (en) * 2019-11-26 2020-04-28 武汉大学 Load event multidimensional feature matching method and system based on non-invasive technology
CN111126799A (en) * 2019-12-10 2020-05-08 广东工业大学 Shared network driver and crew matching method based on bipartite graph

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110866687A (en) * 2019-11-07 2020-03-06 中盈优创资讯科技有限公司 Task allocation method and device
CN111078803A (en) * 2019-11-26 2020-04-28 武汉大学 Load event multidimensional feature matching method and system based on non-invasive technology
CN111126799A (en) * 2019-12-10 2020-05-08 广东工业大学 Shared network driver and crew matching method based on bipartite graph

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
KASPAR RIESEN ETC.: ""Approximate graph edit distance compution by means of bipartite graph matching"", 《IMAGE AND VISION COMPUTING》 *
NAN HUANG ETC.: ""Bipartite Graph Partition Based Coclustering With Joint Sparsity for Hyperspectral Images"", 《IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING》 *
王立波: ""二部图及匹配算法的描述"", 《杭州电子工业学院学报》 *
祝家烨: ""基于局部优化与二分图匹配的PPI网络比对算法"", 《计算机应用与软件》 *

Also Published As

Publication number Publication date
CN112949686B (en) 2022-12-09

Similar Documents

Publication Publication Date Title
CN109800692B (en) Visual SLAM loop detection method based on pre-training convolutional neural network
CN105205781A (en) Power transmission line aerial photographing image splicing method
CN110111375B (en) Image matching gross error elimination method and device under Delaunay triangulation network constraint
CN107609694B (en) Structure optimization method for offshore wind power cluster power transmission system and storage medium
CN112365511B (en) Point cloud segmentation method based on overlapped region retrieval and alignment
Barman et al. Shape: A novel graph theoretic algorithm for making consensus-based decisions in person re-identification systems
JP2013536960A (en) System and method for synthesizing portrait sketches from photographs
CN113239749B (en) Cross-domain point cloud semantic segmentation method based on multi-modal joint learning
CN113094558B (en) Network node influence ordering method based on local structure
Lv et al. A novel approach for detecting road based on two-stream fusion fully convolutional network
CN114064627A (en) Knowledge graph link completion method and system for multiple relations
CN108093213B (en) Target track fuzzy data fusion method based on video monitoring
CN111985566B (en) Distributed power supply time sequence joint output typical scene generation method based on Copula function
CN107133877B (en) Method for mining overlapped communities in network
CN110349176B (en) Target tracking method and system based on triple convolutional network and perceptual interference learning
CN110659680B (en) Image patch matching method based on multi-scale convolution
CN113514072B (en) Road matching method oriented to navigation data and large-scale drawing data
CN112949686B (en) Matching method based on optimal local distance
CN116952251B (en) Path planning method, device, terminal equipment and readable storage medium
CN112214684B (en) Seed-expanded overlapping community discovery method and device
CN111209839B (en) Face recognition method
CN110111353B (en) Image significance detection method based on Markov background and foreground absorption chain
CN112417579B (en) Semantic-constrained planar primitive topological relation rule detection and recovery method
CN112348042B (en) Improved YOLOv 3-based infrared target detection method
CN112348038A (en) Visual positioning method based on capsule network

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