Multi-source trajectory analysis method, device, equipment and readable storage medium

Abstract

The present invention provides a multi-source trajectory analysis method, apparatus, device, and readable storage medium. The method includes obtaining a first trajectory data set recorded by a raster system and a second trajectory data set recorded by a video system for the same road section within a preset time period; selecting a previously unselected trajectory data set from the first trajectory data set as the first trajectory data; dividing the same road section into i sub-segments, where adjacent sub-segments have different road surface types and / or weather conditions; segmenting the trajectory data from different data sources according to the road segmentation, calculating the similarity between each segment, and then determining the similarity between trajectory data from different data sources based on the similarity between each segment. This method fully considers the impact of road surface type and weather conditions on the similarity calculation results, thereby improving the accuracy of the multi-source trajectory analysis.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a multi-source trajectory analysis method, device, equipment, and readable storage medium. Background Art

[0002] Currently, it is necessary to search for trajectory data belonging to the same vehicle from the vehicle trajectory data recorded by the grating sensing system and the vehicle trajectory data recorded by the video surveillance system.

[0003] When faced with the technical challenge of identifying whether vehicle trajectory data from different data sources belongs to the same vehicle, the existing solution is to use a trajectory similarity algorithm to directly calculate the similarity between vehicle trajectory data from different sources. This similarity calculation result is then used to determine whether the vehicle trajectory data from different data sources belong to the same vehicle. However, field tests have shown that this approach has low accuracy. Summary of the Invention

[0004] To solve the above technical problems, the present invention provides a multi-source trajectory analysis method, apparatus, device and readable storage medium.

[0005] In a first aspect, the present invention provides a multi-source trajectory analysis method, the multi-source trajectory analysis method comprising:

[0006] Acquire a first trajectory data set recorded by the grating system and a second trajectory data set recorded by the video system for the same road section within a preset time period;

[0007] Selecting a piece of unselected trajectory data from the first trajectory data group as first trajectory data;

[0008] Divide the same road section into i sub-sections, where i is a positive integer greater than or equal to 1, and adjacent sub-sections have different road surface types and / or weather conditions;

[0009] obtaining a similarity between the first trajectory data and a piece of second trajectory data in the second trajectory data group based on a similarity between the first trajectory data and a piece of second trajectory data in the second trajectory data group on each sub-road segment;

[0010] Similarly, the similarity between the first trajectory data and each second trajectory data in the second trajectory data group is obtained;

[0011] It is determined that the first trajectory data and the second trajectory data corresponding to the maximum similarity belong to the same vehicle.

[0012] Optionally, the step of obtaining the similarity between the first trajectory data and a piece of the second trajectory data in the second trajectory data group based on the similarity between the first trajectory data and a piece of the second trajectory data in the second trajectory data group on each sub-road segment includes:

[0013] Dividing the first trajectory data into sub-first trajectory data corresponding to each sub-road segment;

[0014] Dividing a second trajectory data in the second trajectory data group into sub-second trajectory data corresponding to each sub-road segment;

[0015] Calculate the similarity between the sub-first trajectory data and the sub-second trajectory data corresponding to each sub-segment to obtain the similarity corresponding to each sub-segment;

[0016] Based on the similarity corresponding to each sub-segment and the weight corresponding to each sub-segment, a weighted sum is performed to obtain the similarity between the first trajectory data and a piece of second trajectory data in the second trajectory data group.

[0017] Optionally, the step of calculating the similarity between the sub-first trajectory data and the sub-second trajectory data corresponding to each sub-road segment includes:

[0018] Based on the longest common subsequence algorithm, the similarity between the sub-first trajectory data and the sub-second trajectory data corresponding to each sub-road segment is calculated.

[0019] Optionally, before the step of performing weighted summation based on the similarity corresponding to each sub-segment and the weight corresponding to each sub-segment to obtain the similarity between the first trajectory data and a piece of second trajectory data in the second trajectory data group, the step further includes:

[0020] The weight corresponding to each sub-segment is determined according to the road surface type and weather conditions corresponding to each sub-segment.

[0021] Optionally, the step of determining the weight corresponding to each sub-segment according to the road surface type and weather conditions corresponding to each sub-segment includes:

[0022] According to the road surface type corresponding to each sub-section, obtain the type identification value corresponding to each sub-section;

[0023] According to the weather conditions corresponding to each sub-section, the weather identification value corresponding to each sub-section is obtained;

[0024] According to the type identification value and weather identification value corresponding to each sub-road section, the weight corresponding to each sub-road section is obtained.

[0025] Optionally, the step of determining that the first trajectory data and the second trajectory data corresponding to the maximum similarity belong to the same vehicle includes:

[0026] Detect whether the difference between the maximum similarity and the second largest similarity is greater than a preset threshold;

[0027] If it is greater than a preset threshold, it is determined that the first trajectory data and the second trajectory data corresponding to the maximum similarity belong to the same vehicle.

[0028] Optionally, after the step of determining that the first trajectory data and the second trajectory data corresponding to the maximum similarity belong to the same vehicle, the method further includes:

[0029] The first trajectory data is fused with the second trajectory data corresponding to the maximum similarity to obtain trajectory record information of the same vehicle.

[0030] Optionally, after the step of determining that the first trajectory data and the second trajectory data corresponding to the maximum similarity belong to the same vehicle, the method further includes:

[0031] The second trajectory data corresponding to the maximum similarity is deleted from the second trajectory data group, and the process returns to the step of selecting a piece of trajectory data that has not been selected from the first trajectory data group as the first trajectory data.

[0032] In a second aspect, the present invention further provides a multi-source trajectory analysis device, comprising:

[0033] An acquisition module, configured to acquire a first trajectory data set recorded by the grating system and a second trajectory data set recorded by the video system for the same road section within a preset time period;

[0034] a selection module, configured to select a piece of unselected trajectory data from the first trajectory data group as first trajectory data;

[0035] a road segment division module, configured to divide the same road segment into i sub-segments, where i is a positive integer greater than or equal to 1, and adjacent sub-segments have different road surface types and / or weather conditions;

[0036] a similarity calculation module, configured to obtain a similarity between the first trajectory data and a piece of the second trajectory data in the second trajectory data group based on a similarity between the first trajectory data and a piece of the second trajectory data in the second trajectory data group on each sub-segment;

[0037] Similarly, the similarity between the first trajectory data and each second trajectory data in the second trajectory data group is obtained;

[0038] The determining module is configured to determine whether the first trajectory data and the second trajectory data corresponding to the maximum similarity belong to the same vehicle.

[0039] In a third aspect, the present invention further provides a multi-source trajectory analysis device, comprising a processor, a memory, and a multi-source trajectory analysis program stored in the memory and executable by the processor, wherein when the multi-source trajectory analysis program is executed by the processor, the steps of the multi-source trajectory analysis method described above are implemented.

[0040] In a fourth aspect, the present invention further provides a readable storage medium, on which a multi-source trajectory analysis program is stored, wherein when the multi-source trajectory analysis program is executed by a processor, the steps of the multi-source trajectory analysis method described above are implemented.

[0041] In the present invention, a first trajectory data set recorded by a grating system and a second trajectory data set recorded by a video system for the same road section within a preset time period are obtained; a piece of trajectory data that has not been selected is selected from the first trajectory data set as the first trajectory data; the same road section is divided into i sub-segments, where i is a positive integer greater than or equal to 1, and the road surface type and / or weather conditions between adjacent sub-segments are different; based on the similarity between the first trajectory data and a piece of second trajectory data in the second trajectory data set in each sub-segment, the similarity between the first trajectory data and a piece of second trajectory data in the second trajectory data set is obtained; and similarity between the first trajectory data and each piece of second trajectory data in the second trajectory data set is obtained in this manner; and it is determined that the first trajectory data and the second trajectory data corresponding to the maximum similarity belong to the same vehicle. Through the present invention, trajectory data from different data sources are segmented, and the similarity between each segment is calculated. Then, based on the similarity between each segment, the similarity between trajectory data from different data sources is determined. This fully considers the influence of road surface type and weather conditions on the similarity calculation results, thereby improving the accuracy of multi-source trajectory analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 Schematic diagram of the hardware structure of the multi-source trajectory analysis device involved in the embodiment of the present invention;

[0043] Figure 2 Schematic diagram of the process of the first embodiment of the multi-source trajectory analysis method of the present invention;

[0044] Figure 3 Schematic diagram of the flow of the second embodiment of the multi-source trajectory analysis method of the present invention;

[0045] Figure 4 FIG. 1 is a schematic diagram of functional modules of an embodiment of a multi-source trajectory analysis device according to the present invention.

[0046] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0047] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0048] In a first aspect, an embodiment of the present invention provides a multi-source trajectory analysis device, which may be a device with data processing capabilities, such as a personal computer (PC), a notebook computer, or a server.

[0049] Reference Figure 1 , Figure 1 Schematic diagram of the hardware structure of the multi-source trajectory analysis device involved in the embodiment of the present invention. In the embodiment of the present invention, the multi-source trajectory analysis device may include a processor 1001 (such as a central processing unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components; the user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard); the network interface 1004 may optionally include a standard wired interface, a wireless interface (such as wireless fidelity WIreless-FIdelity, WI-FI interface); the memory 1005 may be a high-speed random access memory (random access memory, RAM), or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may optionally be a storage device independent of the aforementioned processor 1001. Those skilled in the art will understand that Figure 1 The hardware structure shown in the figure does not constitute a limitation of the present invention, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0050] Continue to refer to Figure 1 , Figure 1 The memory 1005, which is a computer storage medium, may include an operating system, a network communication module, a user interface module, and a multi-source trajectory analysis program. The processor 1001 may call the multi-source trajectory analysis program stored in the memory 1005 and execute the multi-source trajectory analysis method provided by the embodiment of the present invention.

[0051] In a second aspect, an embodiment of the present invention provides a multi-source trajectory analysis method.

[0052] In one embodiment, referring to Figure 2 , Figure 2 FIG. 1 is a flow chart of the first embodiment of the multi-source trajectory analysis method of the present invention. Figure 2 As shown, the multi-source trajectory analysis method includes:

[0053] Step S10, obtaining a first trajectory data set recorded by the grating system and a second trajectory data set recorded by the video system for the same road section within a preset time period;

[0054] In this embodiment, the preset time period is set based on actual conditions. The first trajectory data set recorded by the grating system includes one or more trajectory data, each of which includes information such as a unique ID, time, coordinates, and vehicle model. The second trajectory data set recorded by the video system includes one or more trajectory data, each of which includes information such as a license plate, time, coordinates, and vehicle color.

[0055] In the following, it is taken as an example that the first trajectory data group includes trajectory data A1 , trajectory data A2 , and trajectory data A3 , and the second trajectory data group includes trajectory data B1 , trajectory data B2 , and trajectory data B3 .

[0056] Step S20, selecting a piece of trajectory data that has not been selected from the first trajectory data group as the first trajectory data;

[0057] In this embodiment, if the trajectory data A1 , the trajectory data A2 and the trajectory data A3 have not been selected, then one of the trajectory data A1 , the trajectory data A2 and the trajectory data A3 is selected as the first trajectory data, for example, the trajectory data A1 is selected as the first trajectory data.

[0058] Step S30, dividing the same road section into i sub-sections, where i is a positive integer greater than or equal to 1, and adjacent sub-sections have different road surface types and / or weather conditions;

[0059] In this embodiment, the same road section is divided into i sub-sections, where adjacent sub-sections have different road surface types and / or weather conditions. For example, the same road section is divided into five sub-sections, where sub-section 1 has a normal road surface type and a sunny weather condition; sub-section 2 has a normal road surface type and a light / moderate rain weather condition; sub-section 3 has a water bridge road surface type and a light / moderate rain weather condition; sub-section 4 has an overpass road surface type and a heavy rain weather condition; and sub-section 5 has a mountain road surface type and a heavy rain weather condition.

[0060] It should be noted that the above is only a schematic description of the road surface type and weather conditions, and the road surface type and weather conditions targeted by this embodiment are not limited to the above description.

[0061] Step S40, obtaining the similarity between the first trajectory data and a piece of second trajectory data in the second trajectory data group based on the similarity between the first trajectory data and a piece of second trajectory data in the second trajectory data group on each sub-road segment;

[0062] In this embodiment, the similarity between the first trajectory data and a piece of second trajectory data in the second trajectory data group on each sub-segment is first calculated, and then the similarity between the two trajectory data is obtained based on the similarity between the two trajectory data on each sub-segment.

[0063] Furthermore, in one embodiment, step S40 includes:

[0064] Step S401, dividing the first trajectory data into sub-first trajectory data corresponding to each sub-road segment;

[0065] In this embodiment, the first trajectory data can be divided into sub-first trajectory data corresponding to each sub-segment based on the starting point of each sub-segment. For example, the first trajectory data A1 can be divided into sub-first trajectory data a1 corresponding to sub-segment 1, sub-first trajectory data a2 corresponding to sub-segment 2, sub-first trajectory data a3 corresponding to sub-segment 3, sub-first trajectory data a4 corresponding to sub-segment 4, and sub-first trajectory data a5 corresponding to sub-segment 5.

[0066] Step S402: dividing a second trajectory data in the second trajectory data group into sub-second trajectory data corresponding to each sub-road segment;

[0067] In this embodiment, the second trajectory data set includes trajectory data B1, trajectory data B2, and trajectory data B3. For example, trajectory data B1 is a piece of second trajectory data. That is, in the same manner as step S40, trajectory data B1 is divided into sub-second trajectory data corresponding to each sub-segment. For example, second trajectory data B1 is divided into sub-second trajectory data b1 corresponding to sub-segment 1, sub-second trajectory data b2 corresponding to sub-segment 2, sub-second trajectory data b3 corresponding to sub-segment 3, sub-second trajectory data b4 corresponding to sub-segment 4, and sub-second trajectory data b5 corresponding to sub-segment 5.

[0068] Step S403, calculating the similarity between the sub-first trajectory data and the sub-second trajectory data corresponding to each sub-segment, and obtaining the similarity corresponding to each sub-segment;

[0069] In this embodiment, combined with the above description, the similarity between the sub-first trajectory data a1 and the sub-second trajectory data b1 corresponding to sub-segment 1 is calculated, which is recorded as similarity S11. Similarly, the similarity between the sub-first trajectory data a2 and the sub-second trajectory data b2 corresponding to sub-segment 2 is calculated, which is recorded as similarity S12. Similarly, the similarity between the sub-first trajectory data a3 and the sub-second trajectory data b3 corresponding to sub-segment 3 is calculated, which is recorded as similarity S13. Similarly, the similarity between the sub-first trajectory data a4 and the sub-second trajectory data b4 corresponding to sub-segment 4 is calculated, which is recorded as similarity S14. Similarly, the similarity between the sub-first trajectory data a5 and the sub-second trajectory data b5 corresponding to sub-segment 5 is calculated, which is recorded as similarity S15.

[0070] When calculating the similarity between the sub-first trajectory data and the sub-second trajectory data corresponding to each sub-segment, an appropriate trajectory similarity algorithm can be selected according to actual needs. For example, the similarity between the sub-first trajectory data and the sub-second trajectory data corresponding to each sub-segment can be calculated based on the longest common subsequence algorithm.

[0071] Step S404 : performing weighted summation based on the similarity corresponding to each sub-segment and the weight corresponding to each sub-segment to obtain the similarity between the first trajectory data and a second trajectory data in the second trajectory data group.

[0072] In this embodiment, the similarity corresponding to each sub-segment is obtained in step S403. Combined with the weight corresponding to each sub-segment, a weighted sum is performed to obtain the similarity between the first trajectory data A1 and a second trajectory data B1 in the second trajectory data group.

[0073] Furthermore, in one embodiment, before step S404, the process further includes:

[0074] The weight corresponding to each sub-segment is determined according to the road surface type and weather conditions corresponding to each sub-segment.

[0075] In this embodiment, the weight corresponding to each sub-segment is determined based on the road surface type and weather conditions associated with each sub-segment. This means that the calculated similarity between the first trajectory data and a second trajectory data item in the second trajectory data set takes into account the influence of the road surface type and weather conditions of the sub-segment. This makes the calculated similarity more realistic, thereby improving the accuracy of multi-source trajectory analysis.

[0076] Furthermore, in one embodiment, the step of determining the weight corresponding to each sub-segment according to the road surface type and weather conditions corresponding to each sub-segment includes:

[0077] According to the road surface type corresponding to each sub-section, obtain the type identification value corresponding to each sub-section;

[0078] According to the weather conditions corresponding to each sub-section, the weather identification value corresponding to each sub-section is obtained;

[0079] According to the type identification value and weather identification value corresponding to each sub-road section, the weight corresponding to each sub-road section is obtained.

[0080] In this embodiment, a corresponding type identification value is pre-set for each road surface type, and a corresponding weather identification value is pre-set for each weather condition. For example, the type identification value for an ordinary road section is 1, the type identification value for a water bridge section is 0.5, the type identification value for an overpass section is 0.5, and the type identification value for a mountain road section is 0.5; the weather identification value for a sunny day is 1, the weather identification value for light / moderate rain is 1, the weather identification value for heavy rain is 0.5, the weather identification value for light / moderate snow is 1, the weather identification value for heavy snow is 0.5, the weather identification value for light / moderate fog is 0.5, and the weather identification value for heavy fog is 0. It should be noted that the above is merely a schematic illustration of the correspondence between road surface types and type identification values, and the correspondence between weather conditions and weather identification values. The type identification values ​​corresponding to each road surface type and the weather identification values ​​corresponding to each weather condition can be set according to actual needs.

[0081] After determining the type and weather identification values ​​corresponding to each sub-segment, the weight corresponding to each sub-segment can be calculated based on these values. For example, the type and weather identification values ​​corresponding to each sub-segment are multiplied, and the resulting product is used as the weight corresponding to each sub-segment. For example, if sub-segment 1 has a normal road surface and sunny weather, the weight corresponding to sub-segment 1 is 1*1; if sub-segment 2 has a normal road surface and light / moderate rain, the weight corresponding to sub-segment 2 is 1*1; if sub-segment 3 has a water bridge surface and light / moderate rain, the weight corresponding to sub-segment 3 is 0.5*1; if sub-segment 4 has an overpass surface and heavy rain, the weight corresponding to sub-segment 4 is 0.5*0.5; if sub-segment 5 has a mountain road surface and heavy rain, the weight corresponding to sub-segment 5 is 0.5*0.5.

[0082] It should be noted that other methods can also be used to calculate the type identification value and weather identification value corresponding to each sub-segment to obtain the weight corresponding to each sub-segment. The specific calculation method can be selected according to actual needs and is not limited here.

[0083] On this basis, the similarity S1 between the first trajectory data A1 and the trajectory data B1 is:

[0084] S1=1*1*S11+1*1*S12+0.5*1*S13+0.5*0.5*S14+0.5*0.5*S15

[0085] Similarly, the similarity between the first trajectory data and each second trajectory data in the second trajectory data group is obtained;

[0086] Based on the above description, the similarity between the first trajectory data A1 and a second trajectory data B1 in the second trajectory data group is obtained. Then, based on the same method, the similarity between the first trajectory data A1 and each second trajectory data in the second trajectory data group can be obtained. The specific process is not repeated here.

[0087] Step S50: Determine whether the first trajectory data and the second trajectory data corresponding to the maximum similarity belong to the same vehicle.

[0088] In this embodiment, for example, according to the above steps, similarity S1 between the first trajectory data A1 and the trajectory data B1, similarity S2 between the first trajectory data A1 and the trajectory data B2, and similarity S3 between the first trajectory data A1 and the trajectory data B3 are obtained.

[0089] If the similarity S1 is the maximum value among the three similarities, it is determined that the first trajectory data A1 and the second trajectory data B1 corresponding to the similarity S1 belong to the same vehicle.

[0090] Furthermore, in one embodiment, step S50 includes:

[0091] Detect whether the difference between the maximum similarity and the second largest similarity is greater than a preset threshold;

[0092] If it is greater than a preset threshold, it is determined that the first trajectory data and the second trajectory data corresponding to the maximum similarity belong to the same vehicle.

[0093] In this embodiment, it is assumed that the relationship among similarity S1, similarity S2, and similarity S3 is as follows:

[0094] If similarity S1 > similarity S3 > similarity S2, the difference between S1 and S3 is calculated, and a test is performed to determine whether the difference is greater than a preset threshold. If so, it is determined that the first trajectory data A1 and the second trajectory data B1 corresponding to the similarity S1 belong to the same vehicle.

[0095] If it is not greater than the preset threshold, it cannot be determined whether the first trajectory data A1 and the second trajectory data B1 corresponding to the similarity S1 belong to the same vehicle, and steps S10 to S80 need to be re-executed in the next road segment.

[0096] Through this embodiment, the accuracy of the judgment result can be further improved.

[0097] Furthermore, in one embodiment, after step S50, the method further includes:

[0098] The first trajectory data is fused with the second trajectory data corresponding to the maximum similarity to obtain trajectory record information of the same vehicle.

[0099] In this embodiment, the first trajectory data is recorded by the raster system, and the second trajectory data corresponding to the maximum similarity is recorded by the video system. The first trajectory data and the second trajectory data corresponding to the maximum similarity are fused to obtain a richer trajectory record of the same vehicle.

[0100] Furthermore, in one embodiment, referring to Figure 3 , Figure 3 FIG. 1 is a flow chart of the second embodiment of the multi-source trajectory analysis method of the present invention. Figure 3 As shown, after step S50, the following steps are further included:

[0101] The second trajectory data corresponding to the maximum similarity is deleted from the second trajectory data group, and the process returns to step S20.

[0102] In this embodiment, for example, a first trajectory data set includes trajectory data A1, trajectory data A2, and trajectory data A3, and a second trajectory data set includes trajectory data B1, trajectory data B2, and trajectory data B3. If, according to steps S20 to S80, it is determined that trajectory data A1 and trajectory data B1 belong to the same vehicle, then B1 is deleted from the second trajectory data set, and the process returns to step S20. Specifically, one trajectory data is selected from trajectory data A2 and trajectory data A3 as the first trajectory data, for example, trajectory data A is selected as the first trajectory data. Subsequently, subsequent steps calculate the similarity between trajectory data A3 and trajectory data B2, and the similarity between trajectory data A3 and trajectory data B3, without calculating the similarity between trajectory data A3 and trajectory data B1, thereby reducing the computational complexity.

[0103] In this embodiment, a first trajectory data set recorded by a raster system and a second trajectory data set recorded by a video system for the same road section within a preset time period are obtained; a previously unselected trajectory data piece is selected from the first trajectory data piece as the first trajectory data piece; the same road section is divided into i sub-segments, where i is a positive integer greater than or equal to 1, and adjacent sub-segments have different road surface types and / or weather conditions; based on the similarity between the first trajectory data piece and a second trajectory data piece in the second trajectory data piece in each sub-segment, the similarity between the first trajectory data piece and a second trajectory data piece in the second trajectory data piece is determined; and similarity between the first trajectory data piece and each second trajectory data piece in the second trajectory data piece is determined similarly; and it is determined that the first trajectory data piece and the second trajectory data piece corresponding to the maximum similarity belong to the same vehicle. Through this embodiment, trajectory data from different data sources are segmented, the similarity between each segment is calculated, and the similarity between trajectory data from different data sources is determined based on the similarity between each segment. This fully considers the impact of road surface type and weather conditions on the similarity calculation results, thereby improving the accuracy of multi-source trajectory analysis.

[0104] In a third aspect, an embodiment of the present invention further provides a multi-source trajectory analysis device.

[0105] In one embodiment, referring to Figure 4 , Figure 4 FIG. 1 is a functional module diagram of an embodiment of a multi-source trajectory analysis device according to the present invention. Figure 4 As shown, the multi-source trajectory analysis device includes:

[0106] An acquisition module 10 is configured to acquire a first trajectory data set recorded by the grating system and a second trajectory data set recorded by the video system for the same road section within a preset time period;

[0107] A selection module 20 is configured to select a piece of unselected trajectory data from the first trajectory data group as first trajectory data;

[0108] a road segment division module 30 for dividing the same road segment into i sub-segments, where i is a positive integer greater than or equal to 1, and adjacent sub-segments have different road surface types and / or weather conditions;

[0109] a similarity calculation module 40 for obtaining a similarity between the first trajectory data and a piece of the second trajectory data in the second trajectory data group based on the similarity between the first trajectory data and a piece of the second trajectory data in each sub-segment;

[0110] Similarly, the similarity between the first trajectory data and each second trajectory data in the second trajectory data group is obtained;

[0111] The determination module 50 is configured to determine whether the first trajectory data and the second trajectory data corresponding to the maximum similarity belong to the same vehicle.

[0112] Furthermore, in one embodiment, the similarity calculation module 40 is configured to:

[0113] Dividing the first trajectory data into sub-first trajectory data corresponding to each sub-road segment;

[0114] Dividing a second trajectory data in the second trajectory data group into sub-second trajectory data corresponding to each sub-road segment;

[0115] Calculate the similarity between the sub-first trajectory data and the sub-second trajectory data corresponding to each sub-segment to obtain the similarity corresponding to each sub-segment;

[0116] Based on the similarity corresponding to each sub-segment and the weight corresponding to each sub-segment, a weighted sum is performed to obtain the similarity between the first trajectory data and a piece of second trajectory data in the second trajectory data group.

[0117] Furthermore, in one embodiment, the similarity calculation module 40 is configured to:

[0118] Based on the longest common subsequence algorithm, the similarity between the sub-first trajectory data and the sub-second trajectory data corresponding to each sub-road segment is calculated.

[0119] Furthermore, in one embodiment, the similarity calculation module 40 is configured to:

[0120] The weight corresponding to each sub-segment is determined according to the road surface type and weather conditions corresponding to each sub-segment.

[0121] Furthermore, in one embodiment, the similarity calculation module 40 is configured to:

[0122] According to the road surface type corresponding to each sub-section, obtain the type identification value corresponding to each sub-section;

[0123] According to the weather conditions corresponding to each sub-section, the weather identification value corresponding to each sub-section is obtained;

[0124] According to the type identification value and weather identification value corresponding to each sub-road section, the weight corresponding to each sub-road section is obtained.

[0125] Furthermore, in one embodiment, the determination module 50 is configured to:

[0126] Detect whether the difference between the maximum similarity and the second largest similarity is greater than a preset threshold;

[0127] If it is greater than a preset threshold, it is determined that the first trajectory data and the second trajectory data corresponding to the maximum similarity belong to the same vehicle.

[0128] Furthermore, in one embodiment, the multi-source trajectory analysis device further includes a fusion module for

[0129] The first trajectory data is fused with the second trajectory data corresponding to the maximum similarity to obtain trajectory record information of the same vehicle.

[0130] Furthermore, in one embodiment, the multi-source trajectory analysis apparatus further includes a loop processing module configured to:

[0131] The second trajectory data corresponding to the maximum similarity is deleted from the second trajectory data group, and the process returns to the step of selecting a piece of trajectory data that has not been selected from the first trajectory data group as the first trajectory data.

[0132] The functional implementation of each module in the multi-source trajectory analysis device corresponds to each step in the multi-source trajectory analysis method embodiment, and their functions and implementation processes are not described here one by one.

[0133] In a fourth aspect, an embodiment of the present invention further provides a readable storage medium.

[0134] The readable storage medium of the present invention stores a multi-source trajectory analysis program, wherein when the multi-source trajectory analysis program is executed by a processor, the steps of the multi-source trajectory analysis method described above are implemented.

[0135] The method implemented when the multi-source trajectory analysis program is executed may refer to the various embodiments of the multi-source trajectory analysis method of the present invention, and will not be described in detail here.

[0136] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0137] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0138] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, or of course by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for enabling a terminal device to execute the methods described in various embodiments of the present invention.

[0139] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A multi-source trajectory analysis method, characterized in that: The multi-source trajectory analysis method comprises: Acquire a first trajectory data set recorded by the grating system and a second trajectory data set recorded by the video system for the same road section within a preset time period; Selecting a piece of unselected trajectory data from the first trajectory data group as first trajectory data; Divide the same road section into i sub-sections, where i is a positive integer greater than or equal to 1, and adjacent sub-sections have different road surface types and / or weather conditions; obtaining a similarity between the first trajectory data and a piece of second trajectory data in the second trajectory data group based on a similarity between the first trajectory data and a piece of second trajectory data in the second trajectory data group on each sub-road segment; Similarly, the similarity between the first trajectory data and each second trajectory data in the second trajectory data group is obtained; It is determined that the first trajectory data and the second trajectory data corresponding to the maximum similarity belong to the same vehicle.

2. The multi-source trajectory analysis method according to claim 1, wherein: The step of obtaining the similarity between the first trajectory data and a piece of the second trajectory data in the second trajectory data group based on the similarity between the first trajectory data and a piece of the second trajectory data in the second trajectory data group on each sub-segment includes: Dividing the first trajectory data into sub-first trajectory data corresponding to each sub-road segment; Dividing a second trajectory data in the second trajectory data group into sub-second trajectory data corresponding to each sub-road segment; Calculate the similarity between the sub-first trajectory data and the sub-second trajectory data corresponding to each sub-segment to obtain the similarity corresponding to each sub-segment; Based on the similarity corresponding to each sub-segment and the weight corresponding to each sub-segment, a weighted sum is performed to obtain the similarity between the first trajectory data and a piece of second trajectory data in the second trajectory data group.

3. The multi-source trajectory analysis method according to claim 2, wherein: The step of calculating the similarity between the sub-first trajectory data and the sub-second trajectory data corresponding to each sub-road segment includes: Based on the longest common subsequence algorithm, the similarity between the sub-first trajectory data and the sub-second trajectory data corresponding to each sub-road segment is calculated.

4. The multi-source trajectory analysis method according to claim 2, wherein: Before the step of performing weighted summation based on the similarity corresponding to each sub-segment and the weight corresponding to each sub-segment to obtain the similarity between the first trajectory data and a piece of second trajectory data in the second trajectory data group, the method further includes: The weight corresponding to each sub-segment is determined according to the road surface type and weather conditions corresponding to each sub-segment.

5. The multi-source trajectory analysis method according to claim 4, characterized in that: The step of determining the weight corresponding to each sub-segment according to the road surface type and weather conditions corresponding to each sub-segment includes: According to the road surface type corresponding to each sub-section, obtain the type identification value corresponding to each sub-section; According to the weather conditions corresponding to each sub-section, the weather identification value corresponding to each sub-section is obtained; According to the type identification value and weather identification value corresponding to each sub-road section, the weight corresponding to each sub-road section is obtained.

6. The multi-source trajectory analysis method according to claim 1, wherein: The step of determining that the first trajectory data and the second trajectory data corresponding to the maximum similarity belong to the same vehicle includes: Detect whether the difference between the maximum similarity and the second largest similarity is greater than a preset threshold; If it is greater than a preset threshold, it is determined that the first trajectory data and the second trajectory data corresponding to the maximum similarity belong to the same vehicle.

7. The multi-source trajectory analysis method according to claim 1, wherein: After the step of determining that the first trajectory data and the second trajectory data corresponding to the maximum similarity belong to the same vehicle, the method further includes: The second trajectory data corresponding to the maximum similarity is deleted from the second trajectory data group, and the process returns to the step of selecting a piece of trajectory data that has not been selected from the first trajectory data group as the first trajectory data.

8. A multi-source trajectory analysis device, characterized in that: The multi-source trajectory analysis device comprises: An acquisition module, configured to acquire a first trajectory data set recorded by the grating system and a second trajectory data set recorded by the video system for the same road section within a preset time period; a selection module, configured to select a piece of unselected trajectory data from the first trajectory data group as first trajectory data; a road segment division module, configured to divide the same road segment into i sub-segments, where i is a positive integer greater than or equal to 1, and adjacent sub-segments have different road surface types and / or weather conditions; a similarity calculation module, configured to obtain a similarity between the first trajectory data and a piece of the second trajectory data in the second trajectory data group based on a similarity between the first trajectory data and a piece of the second trajectory data in the second trajectory data group on each sub-segment; Similarly, the similarity between the first trajectory data and each second trajectory data in the second trajectory data group is obtained; The determining module is configured to determine whether the first trajectory data and the second trajectory data corresponding to the maximum similarity belong to the same vehicle.

9. A multi-source trajectory analysis device, characterized in that: The multi-source trajectory analysis device includes a processor, a memory, and a multi-source trajectory analysis program stored in the memory and executable by the processor, wherein when the multi-source trajectory analysis program is executed by the processor, the steps of the multi-source trajectory analysis method according to any one of claims 1 to 7 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a multi-source trajectory analysis program, wherein when the multi-source trajectory analysis program is executed by a processor, the steps of the multi-source trajectory analysis method according to any one of claims 1 to 7 are implemented.

Images