A target similar trajectory matching method considering motion elements

Abstract

The application discloses a target similar track matching method considering motion elements, and relates to the field of geographic information processing. The application firstly constructs a candidate matching track data set with motion elements, then acquires a track to be matched, obtains an element maximum difference set according to the track to be matched and the candidate matching track data set, obtains a distance matrix according to the track to be matched, the candidate matching track data set and the element maximum difference set, then obtains a path matrix according to the distance matrix, and obtains an element similar distance between the track to be matched and any track in the candidate matching track data set according to the path matrix, and records the track corresponding to the minimum element similar distance as a matching track. The application can accurately match the similar track of the target to be matched by comprehensively considering the motion states of the target to be matched and each track in the candidate matching track data set.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of geographic information processing, in particular to a target similar trajectory matching method considering motion elements. BACKGROUND

[0002] In today's rapidly developing social and economic activities, target similar trajectory matching technology plays an increasingly important role. With the advent of the big data era, the popularity of various mobile devices and sensors makes it easy for people to obtain and record the motion trajectories of individuals or objects. These trajectory data not only have a wide range of applications in traffic management, logistics optimization, urban planning, etc., but also play a key role in security monitoring, personal health monitoring, etc. For example, in the field of transportation, by analyzing the driving trajectories of vehicles, traffic flow can be optimized and congestion can be reduced; in the field of logistics, similar trajectory matching can help enterprises optimize delivery routes and reduce costs. However, existing trajectory matching methods often ignore the diversity of motion elements and the time difference of trajectories, resulting in limited accuracy and practicality of the matching results.

[0003] Target motion elements such as speed and direction of motion are key factors affecting trajectory similarity. Traditional trajectory matching methods often rely on simple geometric distance or time series similarity, ignoring the comprehensive influence of these motion elements. This makes it difficult to achieve ideal precision and robustness when facing complex and variable actual situations. Therefore, how to combine different target motion element information to improve the matching accuracy and anti-interference of target similar trajectories has become a research focus. SUMMARY

[0004] Therefore, the present application proposes a target similar trajectory matching method considering motion elements. By comprehensively considering the motion state of each trajectory in the candidate matching trajectory dataset and the target to be matched, the present application can accurately match the similar trajectories of the target to be matched.

[0005] To achieve the above purpose, the technical solution adopted by the present application is as follows:

[0006] A target similar trajectory matching method considering motion elements, comprising the following steps:

[0007] Step 1, constructing an initial candidate matching trajectory dataset

[0008]

[0009] wherein, l i represents the i-th trajectory in the initial candidate matching trajectory dataset , i = 1, 2, 3,..., n, n is the number of initial candidate matching trajectory dataset the number of trajectories in the trajectory data set respectively represent the trajectory l i the time, longitude and latitude of the kth trajectory point in the trajectory l i , m i respectively represent the trajectory l i the number of trajectory points contained in the trajectory l

[0010] Step 2, for each trajectory in the initial candidate matching trajectory data set , calculate the motion element of each trajectory point in the trajectory, and build a candidate matching trajectory data set

[0011] Step 3, obtain the trajectory to be matched, and calculate the motion element of each trajectory point in the trajectory to be matched, and build a trajectory to be matched L re with motion elements;

[0012] Step 4, calculate the maximum difference set B max of elements between the trajectory to be matched L re and all trajectories in the candidate matching trajectory data set ;

[0013] Step 5, calculate the distance matrix D(L i , l' re ) composed of the trajectory to be matched L re and any trajectory l' i in the candidate matching trajectory data set ;

[0014] Step 6, according to the distance matrix D(L re , l' i ), calculate the path matrix W(L re , l' i ) composed of the trajectory to be matched L re and any trajectory l' i in the candidate matching trajectory data set ;

[0015] Step 7, according to the path matrix W(L re , l' i ), obtain the element similarity distance T(L re , l' i ) between the trajectory to be matched L re and any trajectory l' i in the candidate matching trajectory data set ;

[0016] Step 8, select the trajectory in the candidate matching trajectory data set corresponding to the minimum element similarity distance, and record it as the trajectory to be matched Lre The trajectory with the highest matching degree, the target similar trajectory matching considering the motion elements is completed.

[0017] Further, in step 2, the candidate matching trajectory dataset with motion elements is constructed Specifically, the candidate matching trajectory dataset with motion elements is constructed as follows:

[0018]

[0019] wherein, l' i represents the i-th trajectory in the candidate matching trajectory dataset, respectively represent the heading and the speed of the k-th trajectory point in the trajectory l' i .

[0020] When k = 1:

[0021]

[0022] When k = 2, 3,..., m i :

[0023]

[0024] wherein, arctan() represents the inverse tangent.

[0025] Further, in step 3, the to-be-matched trajectory L re with motion elements is constructed as follows:

[0026]

[0027] wherein, respectively represent the time, the longitude, the latitude, the heading and the speed corresponding to the j-th trajectory point in the to-be-matched trajectory L re , j = 1, 2, 3,..., m re , m re represents the number of trajectory points contained in the to-be-matched trajectory L re .

[0028] When j = 1:

[0029]

[0030] When j = 2, 3,..., m re :

[0031]

[0032] Further, in step 4, the element maximum difference set B max is constructed as follows:

[0033] ​B max = {x max ,y max ,d max ,s max}

[0034]

[0035] where x max ,y max ,d max ,s max denote the maximum difference of longitude, latitude, heading and speed respectively, max() denotes the maximum value operation, and |*| denotes the absolute value.

[0036] Further, the distance matrix D(L re ,l' i ) in step 5 is calculated as follows:

[0037]

[0038] where d(j, k) is the data in the jth row and kth column of the distance matrix D(L re ,l' i ), and dis(L re (j), l' i (k)) denotes the multi-dimensional distance between the jth trajectory point of the trajectory to be matched L re and the kth trajectory point of the trajectory l' i in the candidate matching trajectory data set .

[0039] Further, the path matrix W(L re ,l' i ) in step 6 is calculated as follows:

[0040]

[0041] where w(j, k) is the data in the jth row and kth column of the path matrix W(L re ,l' i ), and min{} denotes the minimum value. In order to make the above formula meaningful, the following initial conditions are set:

[0042] w(0, 0) = 0, w(j, 0) = ∞, w(0, k) = ∞.

[0043] Further, the element similarity distance T(L re ,l' i ) between the trajectory to be matched L re and any trajectory l' i in the candidate matching trajectory data set is calculated as follows:) is the path matrix W(L re ,l' i ) in which w(m re ,m i ) is the path matrix W(L

[0044] Compared with the prior art, the present application has the beneficial effects that:

[0045] 1. The present application can accurately match the similar trajectories of the target to be matched by comprehensively considering the motion state of each trajectory in the candidate matching trajectory dataset.

[0046] 2. The present application can not only significantly improve the accuracy of trajectory similarity analysis, but also effectively deal with complex noise and interference in trajectory data, and provide more reliable and efficient technical support for various data fusion. BRIEF DESCRIPTION OF DRAWINGS

[0047] Figure 1 FIG. 1 is a flowchart of a target similar trajectory matching method considering motion elements according to an embodiment of the present application. DETAILED DESCRIPTION

[0048] The present application will be further described below in combination with the drawings and specific embodiments.

[0049] A target similar trajectory matching method considering motion elements, as shown in FIG. 1, comprises the following steps: Figure 1

[0050] Step 1, constructing an initial candidate matching trajectory dataset

[0051]

[0052] wherein l i represents the i-th trajectory in the initial candidate matching trajectory dataset , i = 1, 2, 3,..., n, n is the number of trajectories in the initial candidate matching trajectory dataset , and each trajectory in the initial candidate matching trajectory dataset is a currently known historical trajectory, respectively represent the time, longitude and latitude of the k-th trajectory point in the trajectory l i , k = 1, 2, 3,..., m i , m i represents the number of trajectory points contained in the trajectory l i .

[0053] Step 2, constructing a target trajectory dataset ​For each trajectory in the dataset, calculate the motion features of each trajectory point to construct a candidate matching trajectory dataset with motion features.

[0054] Step 3: Obtain the trajectory to be matched, and calculate the motion elements of each trajectory point in the trajectory to be matched, constructing the trajectory L with motion elements. re ;

[0055] Step 4, calculate the trajectory L to be matched. re and candidate matching trajectory dataset The set of maximum differences in features of all trajectories, B max ;

[0056] Step 5, calculate the trajectory L to be matched. re and candidate matching trajectory dataset any trajectory l' i The distance matrix D(L) formed re ,l' i );

[0057] Step 6, based on the distance matrix D(L) re ,l' i Calculate the trajectory L to be matched re and candidate matching trajectory dataset any trajectory l' i The path matrix W(L) is formed re ,l' i );

[0058] Step 7, based on the path matrix W(L) re ,l' i The trajectory L to be matched is obtained. re and candidate matching trajectory dataset any trajectory l' i The similarity distance T(L) between elements re ,l' i );

[0059] Step 8: Select the candidate matching trajectory dataset corresponding to the minimum feature similarity distance. The trajectory in the image is denoted as L, which is the trajectory to be matched. re The trajectory with the highest matching degree completes the target similarity trajectory matching that takes into account motion elements.

[0060] Furthermore, in step 2, a candidate matching trajectory dataset with motion elements is constructed. Specifically:

[0061]

[0062] Among them, l'i represents the i-th trajectory in the candidate matching trajectory dataset respectively represents the heading and speed of the k-th trajectory point in the trajectory l' i

[0063] When k = 1:

[0064]

[0065] When k = 2, 3,..., m i

[0066]

[0067] wherein arctan() represents the inverse tangent.

[0068] Further, the to-be-matched trajectory L re with motion elements in step 3 is specifically:

[0069]

[0070] wherein, respectively represents the time, longitude, latitude, heading and speed corresponding to the j-th trajectory point in the to-be-matched trajectory L re , j = 1, 2, 3,..., m re , m re represents the number of trajectory points contained in the to-be-matched trajectory L re

[0071] When j = 1:

[0072]

[0073] When j = 2, 3,..., m re

[0074]

[0075] Further, the element maximum difference set B max in step 4 is specifically:

[0076] B max = {x max , y max , d max , s max}

[0077]

[0078] wherein x max , y max , d​​​​​max max respectively represent the maximum difference of longitude, latitude, heading and speed, max() represents the maximum value operation, and |*| represents the absolute value.

[0079] Further, the distance matrix D(L re ,l' i ) in step 5 is calculated as follows:

[0080]

[0081] where d(j, k) is the data in the jth row and the kth column of the distance matrix D(L re ,l' i ), and dis(L re (j), l' i (k)) represents the multi-dimensional distance between the jth trajectory point of the trajectory L re to be matched and the kth trajectory point of the trajectory l' i in the candidate matching trajectory data set .

[0082] Further, the path matrix W(L re ,l' i ) in step 6 is calculated as follows:

[0083]

[0084] where w(j, k) is the data in the jth row and the kth column of the path matrix W(L re ,l' i ), and min{} represents the minimum value. In order to make the above formula meaningful, the following initial conditions are set:

[0085] w(0, 0) = 0, w(j, 0) = ∞, and w(0, k) = ∞.

[0086] Further, the element similarity distance T(L re ,l' i ) between the trajectory L re to be matched and any trajectory l' i in the candidate matching trajectory data set in step 7 is w(m re ,m i ) in the path matrix W(L re ,l' i ).

[0087] In summary, the present application can accurately match the similar trajectories of the target to be matched by comprehensively considering the motion states of the target to be matched and each trajectory in the candidate matching trajectory data set. ​

[0088] Those skilled in the art will appreciate that the embodiments described are for purposes of illustration only and should not be construed as limiting the scope of the present application. Substantial modifications can be made by persons skilled in the art using knowledge present in the art without departing from the spirit or scope of the application. Any modifications, equivalent substitutions, improvements, combinations and / or the like which are within the spirit and principles of the application are intended to be embraced in the scope of the claims.

Claims

1. A target similar trajectory matching method considering motion elements, characterized in that, Comprising the steps of: Step 1, constructing an initial candidate matching trajectory dataset wherein, l i represents the i-th trajectory in the initial candidate matching trajectory dataset , i = 1, 2, 3,..., n, n being the number of trajectories in the initial candidate matching trajectory dataset , respectively represents the time, longitude and latitude of the k-th trajectory point in the trajectory l i , k = 1, 2, 3,..., m i , m i represents the number of trajectory points contained in the trajectory l i ; Step 2, for each trajectory in the initial candidate matching trajectory dataset compute the motion elements of each trajectory point in the trajectory, and construct the candidate matching trajectory dataset with motion elements Step 3, obtaining a to-be-matched trajectory, and calculating a motion element of each trajectory point in the to-be-matched trajectory to construct the to-be-matched trajectory L with the motion element re ; Step 4, calculating the trajectory L to be matched re and the candidate matching trajectory dataset the set B of maximum differences of elements of all trajectories in max ; Step 5, calculating the to-be-matched trajectory L re and the candidate matching trajectory dataset Any trajectory l i Distance matrix D(L re ,l i ') composed of Step 6, a path matrix W(L re ,l′ i ) is calculated according to the distance matrix D(L re ,l′ i ) between any trajectory l′ i in the to-be-matched trajectory L re and the candidate matched trajectory data set . Step 7, obtain the element similarity distance T(L re ,l′ i ) between any trajectory l′ re in the to-be-matched trajectory L i and the candidate matched trajectory data set re according to the path matrix W(L i ,l′ re ); Step 8, select the candidate matching trajectory dataset corresponding to the minimum element-wise similarity distance as the matching trajectory dataset of the target trajectory L Step 8, select the candidate matching trajectory dataset corresponding to the minimum element-wise similarity distance as the matching trajectory dataset of the target trajectory L re Step 8, select the candidate matching trajectory dataset corresponding to the minimum element-wise similarity distance as the matching trajectory dataset of the target trajectory L 2. The method of claim 1, wherein, Constructing candidate matching trajectory dataset with motion elements in step 2 Specifically: wherein, l i represents the i-th trajectory in the candidate matching trajectory dataset represents the k-th trajectory point in the trajectory l i represents the heading and speed of the k-th trajectory point in the trajectory l​ When k = 1: when k = 2, 3,..., m i when k = 2, 3,..., m where arctan() denotes the inverse tangent.

3. The method of claim 2, wherein the target similar trajectory matching method considers motion elements. The trajectory L to be matched with the motion element in step 3 re Specifically: wherein, respectively represent the trajectory L re corresponding to the jth trajectory point in the trajectory L re , m re respectively represent the trajectory L re contains; When j = 1: when j = 2, 3,..., m re when j = 2, 3,..., m 4. The method of claim 3, wherein, Element maximum difference set B in step 4 max Specifically: where x max , y max , d max , s max denote the maximum difference of longitude, latitude, heading and speed, max() denotes the maximum operation, and * denotes the absolute value.

5. The method of claim 4, wherein, The distance matrix D(L re ,l i ') is calculated as follows: where d(j, k) is the jth row and kth column data of the distance matrix D(L re , l′ i ), and dis(L re (j), l′ i (k)) represents the multi-dimensional distance between the jth trajectory point of the trajectory L re to be matched and the kth trajectory point of the trajectory l in the candidate matching trajectory data set i .

6. The method of claim 5, wherein the target similar trajectory matching method considering motion elements is characterized by, The path matrix W(L re ,l i ') is calculated as follows: where w(j, k) is the data in the jth row and kth column of the path matrix W(L re ,l′ i ) and min{} means to find the minimum value. In order for the above equation to be meaningful, the following initial conditions are set: w(0,0) = 0, w(j,0) = ∞, w(0,k) = ∞.

7. The method of claim 6, wherein the target similar trajectory matching method considers motion elements. In step 7, the trajectory L to be matched re and candidate matching trajectory dataset any trajectory l i The similarity distance T(L) between the elements re ,l′ i The path matrix W(L) is the path matrix. re ,l′ i w(m) in ) re ,m i ).

Images