Method, device, storage medium and electronic device for determining vehicle trajectory

Abstract

The embodiment of the present invention provides a method, device, storage medium and electronic device for determining a vehicle trajectory line, wherein the method comprises: obtaining first target information of a target vehicle, the first target information being obtained by a shooting device at each point when the target vehicle passes through multiple points within a predetermined period and stored in a target database; determining whether there is a target point between adjacent points indicated by multiple point information based on the first target information; when it is determined that there is a target point, when it is determined that the similarity between the license plate of the target to-be-confirmed vehicle in the target database and the license plate of the target vehicle is greater than a first preset threshold, determining the information corresponding to the target to-be-confirmed vehicle as the third target information obtained when the target vehicle passes through the target point; in this way, the target trajectory line of the target vehicle can be determined. Through the present invention, the problem of low integrity of vehicle trajectory data existing in the related art is solved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of big data technology, and in particular, to a method, device, storage medium and electronic device for determining a vehicle trajectory. Background Art

[0002] Trajectory data is an important analysis object in the fields of geographic information, traffic planning, intelligent transportation and traffic guidance. Relying on trajectory data, both the microscopic vehicle status and the macroscopic road status can be observed. In related technologies, vehicle trajectory data can generally be obtained through satellite positioning systems and video surveillance. However, not all vehicles are equipped with satellite positioning devices. In comparison, video surveillance information has more complete vehicle information. However, in actual applications, due to the influence of the surrounding environment, when the height and angle of the capture are different, the license plate may be misidentified, resulting in breakpoints in the trajectory of some vehicles. When analyzing large amounts of data, this part of the data is often discarded. Therefore, the analysis results will also deviate from the actual situation. If this part of the data can be repaired, the original trajectory data will be more complete, and more reliable data can be provided for subsequent traffic planning, intelligent transportation and other application fields. That is, in related technologies, there is a problem that the acquisition of vehicle trajectory data needs to rely on satellite positioning devices, or the integrity of the acquired vehicle trajectory data is low.

[0003] With regard to the problem of low integrity of vehicle trajectory data existing in related technologies, no effective solution has been proposed so far. Summary of the invention

[0004] Embodiments of the present invention provide a method, device, storage medium and electronic device for determining a vehicle trajectory line, so as to at least solve the problem of low integrity of vehicle trajectory data existing in the related art.

[0005] According to one embodiment of the present invention, a method for determining a vehicle trajectory is provided, comprising: obtaining first target information of a target vehicle, wherein the first target information is obtained by a photographing device at each of a plurality of points in a target area when the target vehicle passes through the target area within a predetermined period of time in the past and is stored in a target database, wherein the target database stores target information of vehicles passing through all points in the target area within the predetermined period of time, wherein the target information includes the license plate information of the vehicle, the point information of each of the points and the time information of the vehicle passing through each of the points; determining whether there is a target point in the target area based on the first target information, wherein the target point is the first target The point actually exists between the adjacent points indicated by the point information included in the information, and the point information of the target point is not included in the first target information; when it is determined that the target point exists, the second target information of the vehicle to be confirmed that meets the first preset condition is searched from the target database; when it is determined that there is a target vehicle to be confirmed among the vehicles to be confirmed whose license plate has a similarity with the license plate of the target vehicle greater than a first preset threshold, the information corresponding to the target vehicle to be confirmed included in the second target information is determined as the third target information obtained when the target vehicle passes the target point; the target trajectory of the target vehicle is determined based on the first target information and the third target information.

[0006] In an exemplary embodiment, determining whether a target point exists based on the first target information includes: sorting the multiple points in chronological order based on the time information of the target vehicle passing each point included in the first target information to obtain a sorting result; when it is determined that there are two points in the sorting result that are adjacent in front and behind and do not meet the adjacent point condition, determining that the target point exists, wherein the adjacent point condition is used to indicate that two points are actually adjacent points.

[0007] In an exemplary embodiment, when it is determined that there are two points in the sorting result that are adjacent to each other and do not satisfy the adjacent point condition, determining that the target point exists includes: pre-generating an adjacent point list, wherein the adjacent point list stores the correspondence between any point included in the target area and the point that satisfies the adjacent point condition with any point; when it is determined that there are two points in the sorting result that are adjacent to each other and do not satisfy the correspondence in the adjacent point list, determining that the target point exists.

[0008] In an exemplary embodiment, searching the target database for second target information of a vehicle to be confirmed that meets a first preset condition includes: determining the first vehicle as the vehicle to be confirmed when it is determined that the amount of information of the first vehicle included in the target database is less than a predetermined threshold; and obtaining the second target information of the vehicle to be confirmed.

[0009] In an exemplary embodiment, when it is determined that there is a target vehicle to be confirmed among the vehicles to be confirmed, the similarity between the license plate and the license plate of the target vehicle is greater than a first preset threshold, the information corresponding to the target vehicle to be confirmed included in the second target information is determined as the third target information obtained when the target vehicle passes the target point, including: calculating the first similarity value between the license plate of each vehicle to be confirmed and the license plate of the target vehicle based on the second target information to obtain a calculation result; determining the vehicle to be confirmed corresponding to the target similarity value included in the calculation result as the target vehicle to be confirmed, wherein the target similarity value is the largest similarity value included in the calculation result; when it is determined that the target similarity value is greater than the first preset threshold, determining the information corresponding to the target vehicle to be confirmed included in the second target information as the third target information obtained when the target vehicle passes the target point.

[0010] In an exemplary embodiment, a first similarity value between the license plate of each vehicle to be confirmed and the license plate of the target vehicle is calculated based on the second target information to obtain a calculation result, including: comparing the first character set included in the license plate of the vehicle to be confirmed with the second character set included in the license plate of the target vehicle one by one according to preset rules to obtain a comparison result, wherein the comparison result is used to indicate whether the characters at each position included in the first character set are the same as the characters at the corresponding positions included in the second character set; determining the first similarity value between the license plate of the vehicle to be confirmed and the license plate of the target vehicle based on the comparison result.

[0011] In an exemplary embodiment, determining the first similarity value between the license plate of the vehicle to be confirmed and the license plate of the target vehicle based on the comparison result includes: determining the target number of characters in which the same characters exist in corresponding positions in the first character set and the second character set based on the comparison result; calculating the second similarity value between the license plate of the vehicle to be confirmed and the license plate of the target vehicle based on the target number of characters; determining whether the first character and the second character satisfy a preset relationship when it is determined that the first character included in the first character set is different from the second character at the corresponding position in the second character set; determining the third similarity value between the first character and the second character when it is determined that the first character and the second character satisfy the preset relationship; and determining the first similarity value based on the second similarity value and the third similarity value.

[0012] In an exemplary embodiment, calculating the second similarity value between the license plate of the vehicle to be confirmed and the license plate of the target vehicle based on the target number of characters includes: determining the ratio of the target number of characters to the number of license plate characters as the second similarity value, wherein the number of license plate characters is used to indicate the number of characters included in the license plate of the target vehicle.

[0013] In an exemplary embodiment, determining whether the first character and the second character satisfy a preset relationship includes: in the case of determining that the first character and the second character are a character pair included in a target character set, determining that the first character and the second character satisfy the preset relationship, wherein the target character set stores the character pairs in which the similarity between any two characters is greater than a second preset threshold; in the case of determining that the first character and the second character do not satisfy the character pair included in the target character set, determining that the first character and the second character do not satisfy the preset relationship.

[0014] In an exemplary embodiment, the method further includes: when it is determined that the first character and the second character satisfy the preset relationship, determining a preset similarity threshold as the third similarity value; and determining the first similarity value based on the target character quantity and the third similarity value.

[0015] According to another embodiment of the present invention, a device for determining a vehicle trajectory line is also provided, including: an acquisition module, used to acquire first target information of a target vehicle, wherein the first target information is obtained by a shooting device at each of multiple points in a target area when the target vehicle passes through the target area within a predetermined period of time in the past and is stored in a target database, wherein the target database stores target information of vehicles that pass through all points in the target area within the predetermined period of time, wherein the target information includes the license plate information of the vehicle, the point information of each of the points and the time information of the vehicle passing through each of the points; a first determination module, used to determine whether there is a target point in the target area based on the first target information, wherein the target point is the target point included in the first target information a point actually existing between adjacent points indicated by the enclosed point information, and the point information of the target point is not included in the first target information; a search module, which is used to search the target database for second target information of a to-be-confirmed vehicle that meets the first preset condition when it is determined that the target point exists; a second determination module, which is used to determine the information corresponding to the target to-be-confirmed vehicle included in the second target information as the third target information obtained when the target vehicle passes through the target point when it is determined that there is a target to-be-confirmed vehicle among the to-be-confirmed vehicles whose license plate has a similarity with the license plate of the target vehicle greater than a first preset threshold; a third determination module, which is used to determine the target trajectory line of the target vehicle based on the first target information and the third target information.

[0016] According to yet another embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the steps of any one of the above method embodiments when run.

[0017] According to yet another embodiment of the present invention, there is provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0018] Through the present invention, based on the point information of each point passed by the target vehicle included in the first target information within a predetermined period, it is determined whether there is a target point between the adjacent points indicated by the point information included in the first target information. When it is determined that there is a target point, the second target information of the vehicle to be confirmed that meets the first preset condition is found from the target database. When the similarity between the license plate of the target vehicle to be confirmed included in the vehicle to be confirmed and the license plate of the target vehicle is greater than the first preset threshold, the information corresponding to the target vehicle to be confirmed included in the second target information is determined as the third target information obtained by the target vehicle when passing through the above target point, and the track passed by the target vehicle is supplemented or corrected. Then, the target track line of the target vehicle can be determined by combining the first target information and the third target information. The purpose of determining the vehicle track line without relying on a satellite positioning device is achieved. At the same time, the purpose of obtaining the complete track line of the target vehicle is achieved by determining the above target point and supplementing or correcting the target vehicle track. Therefore, the problem of low integrity of vehicle track data existing in the related art is solved, and the effect of improving the integrity of vehicle track data is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a block diagram of the hardware structure of a mobile terminal of a method for determining a vehicle trajectory line according to an embodiment of the present invention;

[0020] Figure 2 is a flow chart of a method for determining a vehicle trajectory according to an embodiment of the present invention;

[0021] Figure 3 is a flow chart of a method for determining vehicle trajectory data according to a specific embodiment of the present invention;

[0022] Figure 4 is a flow chart of a method for determining missed vehicle locations according to a specific embodiment of the present invention;

[0023] Figure 5 is a flow chart of a method for correcting missed point data according to a specific embodiment of the present invention;

[0024] Figure 6 4 is a structural block diagram of a device for determining a vehicle trajectory according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings and in combination with the embodiments.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0027] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a block diagram of the hardware structure of a mobile terminal of a method for determining a vehicle trajectory line according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0028] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for determining the vehicle trajectory line in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0029] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0030] In this embodiment, a method for determining a vehicle trajectory is provided. Figure 2 is a flow chart of a method for determining a vehicle trajectory according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0031] Step S202, obtaining first target information of the target vehicle, wherein the first target information is obtained by a photographing device at each of the multiple points in the target area when the target vehicle passes through the target area within a predetermined period of time in the past and is stored in a target database, wherein the target database stores target information of vehicles passing through all the points in the target area within the predetermined period of time, and the target information includes the license plate information of the vehicle, the point information of each of the points, and the time information when the vehicle passes through each of the points;

[0032] Step S204, determining whether there is a target point in the target area based on the first target information, wherein the target point is a point actually existing between adjacent points indicated by the point information included in the first target information, and the first target information does not include the point information of the target point;

[0033] Step S206, when it is determined that the target point exists, searching the target database for second target information of the to-be-confirmed vehicle that meets the first preset condition;

[0034] Step S208, when it is determined that there is a target vehicle to be confirmed among the vehicles to be confirmed whose license plate has a similarity with the license plate of the target vehicle greater than a first preset threshold, the information corresponding to the target vehicle to be confirmed included in the second target information is determined as the third target information obtained when the target vehicle passes through the target point;

[0035] Step S210: determining a target trajectory of the target vehicle based on the first target information and the third target information.

[0036] Through the above steps, based on the point information of each point passed by the target vehicle included in the first target information within a predetermined period, it is determined whether there is a target point between the adjacent points indicated by the point information included in the first target information. When it is determined that there is a target point, the second target information of the vehicle to be confirmed that meets the first preset condition is found from the target database. When the similarity between the license plate of the target vehicle to be confirmed included in the vehicle to be confirmed and the license plate of the target vehicle is greater than the first preset threshold, the information corresponding to the target vehicle to be confirmed included in the second target information is determined as the third target information obtained by the target vehicle when passing through the above target point, and the target vehicle passing through the track is supplemented or corrected. Then, the target track line of the target vehicle can be determined by combining the first target information and the third target information. The purpose of determining the vehicle track line without relying on the satellite positioning device is realized. At the same time, the purpose of obtaining the complete track line of the target vehicle is realized by determining the above target point and supplementing or correcting the target vehicle track. Therefore, the problem of low integrity of vehicle track data existing in the related art is solved, and the effect of improving the integrity of vehicle track data is achieved.

[0037] The execution subject of the above steps may be a terminal, or software on the terminal, for example, data analysis software, or a device or processor with data analysis and computing capabilities, or a processor with human-computer interaction capabilities configured on a storage device, or a processing device or processing unit with similar processing capabilities, but not limited thereto. The following takes the terminal executing the above operations as an example (only an exemplary description, in actual operation, other devices or modules may also be used to execute the above operations) for explanation:

[0038] In the above embodiment, the terminal obtains the first target information of the target vehicle. The first target information is obtained by the shooting device at each point when the target vehicle passes through multiple points in the target area within the past predetermined time period (such as 1 day, or 12 hours, or other time periods) and stored in the target database. In actual application, the shooting device at each point takes a photo of the passing vehicle. Optionally, the information of the passing vehicle can also be identified, including the license plate number information of the vehicle. The shooting device then uploads the obtained vehicle information, the shooting time information, and the point information to the server or the cloud, and stores them in the target database. The target database stores the information of the vehicles passing within the predetermined time period. The target information of vehicles at all points in the target area, that is, the target database also stores the target information of all other vehicles passing through all points in the target area except the target vehicle, the above target information includes the license plate information of the vehicle, the point information of each point passed by the vehicle and the time information of each point passed by the vehicle, etc.; then, according to the multiple point information included in the first target information, it is determined whether there is a target point between the adjacent points indicated in the multiple point information, that is, it is determined whether there is a target point (or called a missed point) that may be missed by the target vehicle in the above target area, that is, it is determined whether there is a point where the target vehicle cannot be photographed or cannot be correctly identified, and That is, the camera equipment at the target point may not be able to obtain the license plate information of the target vehicle. For example, the multiple points included in the first target information are sorted according to the time sequence of the target vehicle passing by, and then it is determined whether there is a point between any two points adjacent to each other in the front and rear positions that may have passed by, but the information when the target vehicle passed by the point is not obtained. If so, it is determined that the target point exists. In actual applications, when there are multiple paths between the two points adjacent to each other in the front and rear positions, the points on each path actually between the two points may be the points that the target vehicle actually passed by. In this case, the points on each path between the two points can be confirmed. The target point is determined as the target point; when it is determined that there is a target point, the second target information of the vehicle to be confirmed that meets the first preset condition is searched from the target database. For example, the second target information of the vehicle to be confirmed whose number of information is less than a predetermined value (such as 3 times, or 2 times) in the vehicle information stored in the target database in the past predetermined period of time can be found, that is, the vehicle to be confirmed is a vehicle that has been captured by the shooting equipment at each point a total of very few times. There may be one or more vehicles to be confirmed, and the target database stores the second target information of each vehicle to be confirmed. Among the second target information of these vehicles to be confirmed, there may be some that are stored in the target database because the license plate number of the target vehicle is misrecognized;Then, when it is determined that the similarity between the license plate of the target vehicle to be confirmed (such as vehicle A) and the license plate of the target vehicle is greater than a first preset threshold value (such as 85%, or 90%, or other values), the information corresponding to the target vehicle to be confirmed (such as vehicle A) included in the second target information is determined as the third target information obtained when the target vehicle passes the target point. The information includes the license plate information of the target vehicle to be confirmed, the point information and time information of the point passed by the target vehicle to be confirmed, so as to supplement or correct the track passed by the target vehicle, and then the target track line of the target vehicle can be determined by combining the first target information and the third target information. The purpose of determining the vehicle track line is achieved without relying on a satellite positioning device. At the same time, the purpose of obtaining the complete track line of the target vehicle is achieved by determining the target point and supplementing or correcting the target vehicle track. Therefore, the problem of low integrity of vehicle track data existing in the related art is solved, and the effect of improving the integrity of vehicle track data is achieved. ;

[0039] In an optional embodiment, determining whether a target point exists based on the first target information includes: sorting the multiple points in chronological order based on the time information of the target vehicle passing each point included in the first target information to obtain a sorting result; when it is determined that there are two points in the sorting result that are adjacent to each other and do not meet the adjacent point condition, determining that the target point exists, wherein the adjacent point condition is used to indicate that two points are actually adjacent points. In this embodiment, each point that the target vehicle passes through included in the first target information is sorted in chronological order to obtain a sorting result, and then, in the sorting result, it is found whether any two points adjacent to each other in the front and back positions meet the adjacent point condition, that is, it is determined whether any two points are actually adjacent points. In practical applications, a list of adjacent points for all points in the above-mentioned target area can be established in advance, that is, the corresponding relationship between any one of all points and the points actually adjacent to it is recorded in the adjacent point list, that is, all other points actually adjacent to any one point can be found through the adjacent point list. If it is found in the sorting result that two points adjacent to each other in the front and back positions (such as point A and point B) do not meet the adjacent point condition, it can be determined that there is a target point, that is, it can be determined that there are other points (or breakpoints) that must be passed between point A and point B. Through this embodiment, the purpose of determining whether there is a target point based on the point information of each point included in the first target information is achieved, that is, the purpose of determining whether there is a breakpoint in the predetermined period of time is achieved.

[0040] In an optional embodiment, when it is determined that there are two points in the sorting result that are adjacent to each other and do not satisfy the adjacent point condition, determining that the target point exists includes: pre-generating an adjacent point list, wherein the adjacent point list stores the correspondence between any point included in the target area and any point that satisfies the adjacent point condition; when it is determined that there are two points in the sorting result that are adjacent to each other and do not satisfy the correspondence in the adjacent point list, determining that the target point exists. In this embodiment, a list of adjacent points may be established in advance. For example, in actual applications, based on the trajectory data of all vehicles in the target area acquired over a period of time in the past (such as one day, two days, or other time), the order in which each vehicle passes through each point (or checkpoint) can be obtained by sorting the trajectory data of each vehicle in a day by time. Points between each other in sequence can be identified as adjacent points. Since missed shots or wrong shots are only a small amount of data in practice, the amount of data that appears to span points is relatively small. For example, two points that pass through adjacent points (such as point M and point N) more than a certain number of times in a day can be identified as actually adjacent points, that is, two points that meet the aforementioned adjacent point conditions; for example, based on According to historical data, if more than 100 times (or 200 times, or other times) vehicles (including all vehicles) pass through point M and the next point they arrive at is point N, then it can be determined that point M and point N are actually adjacent points, and a corresponding relationship between point M and point N that satisfies the adjacent point conditions can be established in the above adjacent point list. In this way, without the need to rely on road network information or traffic network information, the purpose of determining the relationship between all adjacent points in the target area can be achieved only through the captured data of each point. In this embodiment, the data of the captured point is obtained from the trajectory data, and real-time updates can be achieved. There will be no situation where the road network construction is updated, or the position of the captured camera is updated, resulting in inaccurate analysis due to the reliance on old data. Through this embodiment, the purpose of determining whether any two points meet the adjacent point conditions based on the adjacent point list is achieved, thereby achieving the purpose of determining whether there is a target point.

[0041] In an optional embodiment, searching the target database for the second target information of the to-be-confirmed vehicle that meets the first preset condition includes: determining the first vehicle as the to-be-confirmed vehicle when determining that the amount of information of the first vehicle included in the target database is less than a predetermined threshold; and obtaining the second target information of the to-be-confirmed vehicle. In this embodiment, the amount of information of all vehicles in the target database can be determined, because each piece of information in the target database records the license plate information of the vehicle obtained at each point each time any vehicle is captured, the point information passed, and the time information of the capture, which may also include the license plate information of the vehicle misidentified by the shooting device. When it is determined that the amount of information of the first vehicle included in the target database is very small, for example, less than 3 (or 2, or other number), the first vehicle is determined as the to-be-confirmed vehicle, and the to-be-confirmed vehicle may include one or more vehicles, and then the second target information of the to-be-confirmed vehicle is obtained. Through this embodiment, the purpose of obtaining the second target information of the to-be-confirmed vehicle from the target database is achieved.

[0042] In an optional embodiment, when it is determined that there is a target vehicle to be confirmed among the vehicles to be confirmed whose license plate has a similarity with the license plate of the target vehicle greater than a first preset threshold, the information corresponding to the target vehicle to be confirmed included in the second target information is determined as the third target information obtained when the target vehicle passes the target point, including: calculating the first similarity value between the license plate of each vehicle to be confirmed and the license plate of the target vehicle based on the second target information to obtain a calculation result; determining the vehicle to be confirmed corresponding to the target similarity value included in the calculation result as the target vehicle to be confirmed, wherein the target similarity value is the largest similarity value included in the calculation result; when it is determined that the target similarity value is greater than the first preset threshold, determining the information corresponding to the target vehicle to be confirmed included in the second target information as the third target information obtained when the target vehicle passes the target point. In this embodiment, the first similarity between the license plate of each to-be-confirmed vehicle and the license plate of the target vehicle is calculated to obtain a calculation result, which includes multiple first similarity values, and then the to-be-confirmed vehicle corresponding to the largest similarity value (i.e., the target similarity value, such as 96%) is determined as the target to-be-confirmed vehicle, and then it is determined whether the target similarity value is greater than a first preset threshold value (such as 85%, or 90%, or other values). When it is determined that the target similarity value is greater than the first preset threshold value, the information corresponding to the target to-be-confirmed vehicle included in the second target information is determined as the third target information obtained when the target vehicle passes through the target point, that is, the data of the target point (or breakpoint) where the target vehicle exists is supplemented or corrected. Through this embodiment, the purpose of supplementing the breakpoint data of the target vehicle is achieved.

[0043] In an optional embodiment, a first similarity value between the license plate of each vehicle to be confirmed and the license plate of the target vehicle is calculated based on the second target information to obtain a calculation result, including: comparing the first character set included in the license plate of the vehicle to be confirmed with the second character set included in the license plate of the target vehicle one by one according to preset rules to obtain a comparison result, wherein the comparison result is used to indicate whether the characters at each position included in the first character set are the same as the characters at the corresponding positions included in the second character set; determining the first similarity value between the license plate of the vehicle to be confirmed and the license plate of the target vehicle based on the comparison result. In this embodiment, when calculating the first similarity value between the license plate of the vehicle to be confirmed and the license plate of the target vehicle, the first character set included in the license plate of the vehicle to be confirmed and the second character set included in the license plate of the target vehicle can be compared for similarity to obtain a comparison result. For example, the first character set and the second character set both include 7 characters, including Chinese characters, letters, and numbers, which can be compared one by one in order. For example, the first character in the first character set is compared with the first character in the second character set, the second character in the first character set is compared with the second character in the second character set, and so on. In this way, the comparison result can be determined, that is, whether the character at each position included in the first character set is the same as the character at the corresponding position included in the second character set, and then the first similarity value is determined based on the comparison result. For example, if there are 6 characters in the corresponding positions of the first character set and the second character set that are the same, the first similarity value can be calculated as 6 / 7 (7 represents the total number of characters included in the character set). Optionally, in practical applications, when the characters in the corresponding positions of the first character set and the second character set are different but very similar, for example, 2 and Z, or C and G, etc., an optimization algorithm can be used to calculate the first similarity, which will be explained in the subsequent embodiments. Through this embodiment, the purpose of determining the first similarity between the license plate of the to-be-confirmed vehicle and the license plate of the target vehicle by performing a similarity comparison on the character set included in the license plate is achieved.

[0044] In an optional embodiment, determining the first similarity value between the license plate of the vehicle to be confirmed and the license plate of the target vehicle based on the comparison result includes: determining the target number of characters in which the same characters exist in corresponding positions in the first character set and the second character set based on the comparison result; calculating the second similarity value between the license plate of the vehicle to be confirmed and the license plate of the target vehicle based on the target number of characters; determining whether the first character and the second character satisfy a preset relationship when it is determined that the first character included in the first character set is different from the second character at the corresponding position in the second character set; determining the third similarity value between the first character and the second character when it is determined that the first character and the second character satisfy the preset relationship; and determining the first similarity value based on the second similarity value and the third similarity value. In this embodiment, the target number of characters having the same characters in the corresponding positions of the first character set and the second character set is first determined. For example, if the characters in 6 corresponding positions of the first character set and the second character set are the same, the second similarity value can be calculated to be 0.86 (i.e., 6 / 7). If the characters in one position of the first character set and the second character set are different, and if the 4th character of the first character set (corresponding to the above-mentioned first character) is different from the 4th character of the second character set (corresponding to the above-mentioned second character), it is determined whether the first character and the second character satisfy a preset relationship. For example, the preset relationship is that the two characters are similar characters. Relationship, such as 2 and Z, or C and G, etc. When it is determined that the first character and the second character satisfy the preset relationship, for example, the 4th character of the first character set is 2, and the 4th character of the second character set is Z, the third similarity value can be determined. In practical applications, the third similarity value can be taken according to the preset value, for example, the third similarity value is 0.8, or 0.9, or other values; then, the first similarity value is determined based on the second similarity value and the third similarity value, for example, the first similarity value is calculated according to the formula (6+0.8) / 7, in which 6 is the second similarity value and 0.8 is the third similarity value. Through this embodiment, the purpose of determining the first similarity between the license plate of the vehicle to be confirmed and the license plate of the target vehicle by comparing each character included in the first character set and the second character set is achieved.

[0045] In an optional embodiment, calculating the second similarity value between the license plate of the to-be-confirmed vehicle and the license plate of the target vehicle based on the target number of characters includes: determining the ratio of the target number of characters to the number of characters in the license plate as the second similarity value, wherein the number of characters in the license plate is used to indicate the number of characters included in the license plate of the target vehicle. In this embodiment, the ratio of the target number of characters to the number of characters in the license plate can be used as the second similarity value. Through this embodiment, the purpose of determining the second similarity value is achieved.

[0046] In an optional embodiment, determining whether the first character and the second character satisfy a preset relationship includes: in the case of determining that the first character and the second character are a character pair included in a target character set, determining that the first character and the second character satisfy the preset relationship, wherein the target character set stores the character pairs in which the similarity between any two characters is greater than a second preset threshold; in the case of determining that the first character and the second character do not satisfy the character pair included in the target character set, determining that the first character and the second character do not satisfy the preset relationship. In this embodiment, a target character set may be pre-established, and the target character set stores character pairs whose similarity between any two characters is greater than a second preset threshold value (such as 80%, or 85%, or other), such as 2 and Z, or C and G, or I and 1, or O and 0, etc., that is, the target character set stores character pairs with high similarity. Optionally, in actual applications, when storing similar character pairs, the similarity value of each group of character pairs may also be stored corresponding to the character pair. For example, when storing the character pair 2 and Z, the similarity value of the group of character pairs may be set to 0.8, and then the similarity value 0.8 may be stored simultaneously with the group of character pairs (i.e., 2 and Z). , and establish a corresponding relationship between the two, or, when storing character pairs D and C, the similarity value of the group of character pairs can be set to 0.7, and then the similarity value 0.7 and the group of character pairs (i.e., D and C) are stored simultaneously, and a corresponding relationship between the two is established. On the basis of establishing the target character set, it can be determined based on the target character set whether the above-mentioned first character and the above-mentioned second character meet the preset relationship. For example, if the first character and the second character are a character pair stored in the target character set, it is considered that the preset relationship is met between the two. If the target character set does not include a character pair consisting of the first character and the second character, it is considered that the preset relationship is not met between the two. Through this embodiment, the purpose of determining whether the preset relationship is met between any two characters based on the target character set is achieved.

[0047] In an optional embodiment, the method further includes: when it is determined that the first character and the second character satisfy the preset relationship, determining the preset similarity threshold as the third similarity value; determining the first similarity value based on the target character quantity and the third similarity value. In this embodiment, when it is determined that the first character and the second character satisfy the preset relationship, that is, when the first character and the second character are similar characters, the preset similarity threshold is determined as the third similarity value. For example, the preset similarity threshold can be set to 0.8, or 0.7, or other values, and then, the first similarity value can be determined based on the target character quantity and the third similarity value. Through this embodiment, the purpose of further optimizing the algorithm of the first similarity value is achieved, so as to achieve the purpose of more accurately calculating the similarity between the license plate of the vehicle to be confirmed and the license plate of the target vehicle.

[0048] Obviously, the above described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The present invention will be specifically described below in conjunction with the embodiments.

[0049] Figure 3 is a flow chart of a method for determining vehicle trajectory data according to a specific embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0050] S302, point analysis. Analyze whether there are other points (or breakpoints, or missed points, corresponding to the aforementioned target points) between the points. The main purpose is to find out whether the points are adjacent to each other. In the case of sufficient trajectory data, by sorting the trajectory data of each vehicle in a day by time, the order of passing through each checkpoint (or point) can be obtained. The points between the two points can be identified as adjacent points (corresponding to the aforementioned actual adjacent points). Since missed or wrong shots are only a small amount of data in reality, the amount of data with point crossing is small. Therefore, it can be determined that if the number of times the adjacent points are passed more than a certain number of times in a day, the two points are actually adjacent.

[0051] S304, find out the missed points of the vehicle. That is, analyze the trajectory data of each vehicle to determine the missed points (corresponding to the aforementioned target points, or breakpoints); through the above step S302, a list of adjacent points of all checkpoints can be obtained, and then the trajectory sequence of each vehicle can be analyzed to check whether the next capture point of each capture point is in the adjacent point list. If it is not in the list, it can be basically determined that there is a missed or wrong capture at the checkpoint;

[0052] The specific process of step S304 is described in detail below. Figure 4 FIG. 1 is a flow chart of a method for determining a vehicle missed shooting point according to a specific embodiment of the present invention. Figure 4 As shown, the process includes:

[0053] S30402, obtaining all trajectory data of a vehicle (or target vehicle) in one day;

[0054] S30404, sorting the trajectory data according to the capture time;

[0055] S30406, extracting the checkpoint data of the vehicle in chronological order;

[0056] S30408, determining whether the next checkpoint (such as checkpoint B) of a checkpoint (such as checkpoint A) is in the adjacent checkpoint list (corresponding to the aforementioned adjacent point list);

[0057] S30410, if the result of the determination in step S30408 ​​is yes, continue to check the next checkpoint;

[0058] S30412, when the judgment result of the above step S30408 ​​is no, it is marked that there is a mistake or omission between the bayonet, that is, it is marked that there is a mistake or omission between the bayonet A and the bayonet B;

[0059] S306, acquisition of isolated license plates, find out all isolated license plates of the day (corresponding to the license plates of the aforementioned vehicles to be confirmed), because in the city, normal vehicle travel, under the existing density of urban monitoring deployment, basically will be captured more than ten times; here we define the number of captures less than 3 times in a day as isolated license plates. Including license plates recognized as other correct formats, and license plates recognized as incorrect formats. For example, the number of digits in the license plate is wrong, and characters that cannot appear in the license plate characters appear. (For example, the letters I, O) In the actual data verification process, these license plates are basically wrong license plates;

[0060] S308, find out all isolated point captured vehicles at the missed points. Through the above step S304, we can determine at which points a certain vehicle is missed, and then through the isolated point license plate data at the points where missed photos may occur in the association step S306, we can determine all isolated point captured vehicles at the missed points;

[0061] S310, constructing a similar character set (corresponding to the aforementioned target character set). According to the captured data of existing cameras, there are often misrecognized characters, which we define as a similar character set. This character set can be updated according to the actual captured data. For example, {A, 4}, {Zhe, Xiang}, {D, C, G}, {Z, 2} are several common similar character sets;

[0062] It should be noted that the above step S310 can be executed in advance and does not necessarily have to be executed after step S308 is executed;

[0063] S312, generate the similarity of the isolated license plate based on the similar character set, and determine the license plate as a wrong license plate if the similarity (corresponding to the aforementioned target similarity value) is greater than the specified threshold (corresponding to the aforementioned first preset threshold). On the basis of executing the above step S308, combine the similar character set defined in step S310 to calculate the similarity of all isolated license plates and the target license plate (corresponding to the aforementioned first similarity value), find the isolated license plate with the highest similarity to the target license plate, that is, find the isolated license plate with the most similarity to the missed point. If the similarity exceeds the defined threshold, it can be marked as the wrong license plate number of the target license plate;

[0064] The specific process of step S312 is described in detail below. Figure 5 is a flow chart of a method for correcting missed point data according to a specific embodiment of the present invention. Figure 5 As shown, the process includes:

[0065] S31202, obtaining the missed points in the vehicle trajectory;

[0066] S31204, search out all isolated license plates that exist at these points;

[0067] S31206, calculating the similarity between each isolated license plate and the target license plate, and obtaining one or more similarity values;

[0068] Specifically, the similarity can be calculated by comparing the characters in the corresponding positions based on the number of digits in the license plate. The more consistent digits, the higher the similarity. At the same time, if the different characters are within the range of the similar character set, the similarity is higher than if they are not within the range of the similar character set. For example: the similarity can be set as the ratio of the number of identical digits to the total number of digits, and the similarity of the similar character set is set to 0.8. The similarity between the license plate numbers Zhejiang A12345 and Zhejiang A12346 is 0.86 (6 / 7), and the similarity between the license plate numbers Zhejiang A23456 and Zhejiang AZ3456 is 0.97 ((6+0.8) / 7) (2 and Z are within the similar character set);

[0069] It should be noted that only one example of similarity calculation is provided here, and all similarity calculation methods that meet the basic principles in the definition are feasible solutions;

[0070] S31208, select the license plate with the highest similarity;

[0071] S31210, determining whether the similarity selected in the above step S31208 is greater than a specified threshold;

[0072] S31212, when the judgment result of the above step S31210 is no, discard the selected license plate with the highest similarity;

[0073] S31214, when the judgment result of the above step S31210 is yes, the license plate number data is corrected to the target license plate, that is, the license plate number data with the highest similarity selected in step S31208 is corrected to the license plate number data of the target license plate at the missed point;

[0074] S314, correct the missed point data of the target license plate, that is, in the above step S312, if there is a wrong license plate number with a similarity exceeding the specified threshold, the license plate number of the captured record is corrected to the target license plate number, and it is completed in the vehicle trajectory data. In this way, a complete and continuous trajectory of the target vehicle can be obtained for subsequent applications in other aspects.

[0075] This embodiment is mainly based on offline calculation. In existing medium and large cities, a large number of vehicle driving records are generated by snapping through the checkpoint equipment every day. The default premise is that most of the snapped data are correct. It is generally divided into the following steps: Analyze all vehicle trajectory data for a day to find out whether there are other must-pass points between two points. Find out the license plate numbers that may be wrong by finding all the isolated point data in a day. Construct a similar character set based on the wrong license plates that often appeared in the past. Find out the vehicles that lack snapped records at the must-pass points and determine the missed vehicles. Based on the similar character set and the determination of the license plate similarity, find the license plate number with the highest similarity to the missed license plate from the isolated point data that may be wrong at the must-pass points where the vehicle is missed. If the similarity is greater than the specified threshold, the data is repaired.

[0076] The checkpoints or points in this embodiment refer to various types of traffic cameras and photographic devices used in public security applications built at various intersections in the city, which have the function of identifying the license plate numbers of passing vehicles and recording them.

[0077] In the above embodiment, less data is relied upon, and there is no need to rely on road network information, traffic network information, and GPS device to collect information. Only the captured data of the city monitoring checkpoints is used for analysis, which avoids the need to rely on traffic light status data, traffic flow data, vehicle trajectory data, and travel time data through intersections in related technologies. At the same time, it is also necessary to refer to the road network information of a specific city, etc. Many data in related technologies have no source and cannot be obtained, and if there is a problem with one of the data, it will have a greater impact on the result. The prerequisite requirements for the applicable scenarios are too harsh and the actual applicability is not strong. In this embodiment, the data of the capture checkpoint is obtained from the trajectory data, and real-time updates can be achieved. There will be no situation where the road network construction is updated, or the capture camera position is updated, resulting in the reliance on data that is too old and the analysis is inaccurate. The application scenarios are more extensive, and data analysis can be performed as long as there are capture records of points, and it can be applied in multiple fields such as transportation.

[0078] Through the embodiments of the present invention, the erroneous snapshot records can be supplemented and repaired only through the snapshot records taken at the checkpoint, so that the overall driving trajectory of the vehicle is more complete. Compared with the prior art, the vehicle trajectory generation method without GPS device is supplemented, and the vehicle travel trajectory is formed through the sequence of dense point snapshot records; the license plate with very few snapshots or incorrect format after recognition is defined as an isolated point snapshot record, and the license plate number is compared with it to find the most likely actual license plate of the wrongly photographed vehicle number; a maintainable similar character set is provided to calculate the similarity between license plates, which increases the accuracy of similar license plate determination based on the comparison of similar digits only.

[0079] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an 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), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0080] In this embodiment, a vehicle trajectory determination device is also provided. Figure 6 is a structural block diagram of a device for determining a vehicle trajectory according to an embodiment of the present invention. Figure 6 As shown, the device comprises:

[0081] The acquisition module 602 is used to acquire first target information of the target vehicle, wherein the first target information is obtained by a shooting device at each of the multiple points in the target area when the target vehicle passes through the target area within a predetermined period of time in the past and is stored in a target database, wherein the target database stores target information of vehicles passing through all the points in the target area within the predetermined period of time, and the target information includes the license plate information of the vehicle, the point information of each of the points and the time information when the vehicle passes through each of the points;

[0082] A first determination module 604 is used to determine whether there is a target point in the target area based on the first target information, wherein the target point is a point actually existing between adjacent points indicated by the point information included in the first target information, and the first target information does not include the point information of the target point;

[0083] A search module 606 is used to search the target database for second target information of the to-be-confirmed vehicle that meets the first preset condition when it is determined that the target point exists;

[0084] The second determination module 608 is used to determine the information corresponding to the target vehicle to be confirmed included in the second target information as the third target information obtained when the target vehicle passes the target point, if it is determined that there is a target vehicle to be confirmed among the vehicles to be confirmed whose license plate has a similarity with the license plate of the target vehicle greater than a first preset threshold.

[0085] The third determination module 610 is used to determine the target trajectory of the target vehicle based on the first target information and the third target information.

[0086] In an optional embodiment, the above-mentioned first determination module 604 includes: a sorting submodule, which is used to sort the multiple points in chronological order based on the time information of the target vehicle passing each point included in the first target information to obtain a sorting result; a first determination submodule, which is used to determine the existence of the target point when it is determined that there are two points adjacent to each other in the sorting result that do not meet the adjacent point condition, wherein the adjacent point condition is used to indicate that the two points are actually adjacent points.

[0087] In an optional embodiment, the above-mentioned first determination submodule includes: a generation unit, used to pre-generate an adjacent point list, wherein the adjacent point list stores the correspondence between any point included in the target area and the point that satisfies the adjacent point condition with any point; a first determination unit, used to determine the existence of the target point when it is determined that there are two points in the sorting result that are adjacent to each other in front and behind but do not satisfy the correspondence in the adjacent point list.

[0088] In an optional embodiment, the above-mentioned search module 606 includes: a second determination submodule, used to determine the first vehicle as the vehicle to be confirmed when it is determined that the amount of information of the first vehicle included in the target database is less than a predetermined threshold; and an acquisition submodule, used to acquire the second target information of the vehicle to be confirmed.

[0089] In an optional embodiment, the above-mentioned second determination module 608 includes: a calculation submodule, which is used to calculate the first similarity value between the license plate of each vehicle to be confirmed and the license plate of the target vehicle based on the second target information to obtain a calculation result; a third determination submodule, which is used to determine the vehicle to be confirmed corresponding to the target similarity value included in the calculation result as the target vehicle to be confirmed, wherein the target similarity value is the similarity value with the largest value included in the calculation result; a fourth determination submodule, which is used to determine the information corresponding to the target vehicle to be confirmed included in the second target information as the third target information obtained when the target vehicle passes the target point when it is determined that the target similarity value is greater than the first preset threshold.

[0090] In an optional embodiment, the above-mentioned calculation submodule includes: a comparison unit, used to compare the first character set included in the license plate of the vehicle to be confirmed with the second character set included in the license plate of the target vehicle one by one according to preset rules to obtain a comparison result, wherein the comparison result is used to indicate whether the characters at each position included in the first character set are the same as the characters at the corresponding positions included in the second character set; a second determination unit, used to determine the first similarity value between the license plate of the vehicle to be confirmed and the license plate of the target vehicle based on the comparison result.

[0091] In an optional embodiment, the above-mentioned second determination unit includes: a first determination subunit, used to determine the target number of characters in which the same characters exist in the corresponding positions of the first character set and the second character set based on the comparison result; a calculation subunit, used to calculate the second similarity value between the license plate of the vehicle to be confirmed and the license plate of the target vehicle based on the target number of characters; a second determination subunit, used to determine whether the first character and the second character satisfy a preset relationship when it is determined that the first character included in the first character set is different from the second character at the corresponding position in the second character set; a third determination subunit, used to determine the third similarity value between the first character and the second character when it is determined that the first character and the second character satisfy the preset relationship; a fourth determination subunit, used to determine the first similarity value based on the second similarity value and the third similarity value.

[0092] In an optional embodiment, the calculation subunit is used to determine the ratio of the target character quantity to the license plate character quantity as the second similarity value, wherein the license plate character quantity is used to indicate the number of characters included in the license plate of the target vehicle.

[0093] In an optional embodiment, the above-mentioned second determination subunit is used to determine that the first character and the second character satisfy the preset relationship when it is determined that the first character and the second character are a character pair included in the target character set, wherein the target character set stores the character pairs whose similarity between any two characters is greater than a second preset threshold; and, when it is determined that the first character and the second character do not satisfy the character pair included in the target character set, determine that the first character and the second character do not satisfy the preset relationship.

[0094] In an optional embodiment, the above-mentioned device also includes: a fourth determination module, used to determine the preset similarity threshold as the third similarity value when it is determined that the first character and the second character satisfy the preset relationship; a fifth determination module, used to determine the first similarity value based on the target character quantity and the third similarity value.

[0095] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0096] An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0097] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0098] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0099] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0100] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0101] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0102] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for determining a vehicle trajectory, characterized in that: include: Acquire first target information of the target vehicle, wherein the first target information is obtained by a photographing device at each of the multiple points in the target area when the target vehicle passes through the target area within a predetermined period of time in the past and is stored in a target database, wherein the target database stores target information of vehicles passing through all the points in the target area within the predetermined period of time, and the target information includes the license plate information of the vehicle, the point information of each of the points, and the time information when the vehicle passes through each of the points; Determining whether there is a target point in the target area based on the first target information, wherein the target point is a point actually existing between adjacent points indicated by the point information included in the first target information, and the first target information does not include the point information of the target point; In the case where it is determined that the target point exists, and in the case where it is determined that the amount of information of the first vehicle included in the target database is less than a predetermined threshold, the first vehicle is determined as a vehicle to be confirmed; and second target information of the vehicle to be confirmed is obtained; When it is determined that there is a target vehicle to be confirmed among the vehicles to be confirmed whose license plate has a similarity with the license plate of the target vehicle greater than a first preset threshold, the information corresponding to the target vehicle to be confirmed included in the second target information is determined as the third target information obtained when the target vehicle passes through the target point; A target trajectory of the target vehicle is determined based on the first target information and the third target information.

2. The method according to claim 1, characterized in that Determining whether a target point exists based on the first target information includes: Sorting the plurality of points in chronological order based on the time information of the target vehicle passing through each of the points included in the first target information to obtain a sorting result; When it is determined that there are two points in the sorting result that are adjacent to each other but do not meet the adjacent point condition, it is determined that the target point exists, wherein the adjacent point condition is used to indicate that the two points are actually adjacent points.

3. The method according to claim 2, characterized in that In the case where it is determined that there are two adjacent points in the sorting result that do not meet the adjacent point condition, determining that the target point exists includes: Pre-generating an adjacent point list, wherein the adjacent point list stores a correspondence between any point included in the target area and a point that satisfies the adjacent point condition with the any point; When it is determined that there are two points in the sorting result that are adjacent to each other in front and back positions but do not satisfy the corresponding relationship in the adjacent point list, it is determined that the target point exists.

4. The method according to claim 1, characterized in that: In the case where it is determined that there is a target vehicle to be confirmed among the vehicles to be confirmed whose license plate has a similarity with the license plate of the target vehicle greater than a first preset threshold, determining the information corresponding to the target vehicle to be confirmed included in the second target information as the third target information obtained when the target vehicle passes through the target point position includes: Calculating a first similarity value between the license plate of each to-be-confirmed vehicle and the license plate of the target vehicle based on the second target information to obtain a calculation result; Determining the to-be-confirmed vehicle corresponding to the target similarity value included in the calculation result as the target to-be-confirmed vehicle, wherein the target similarity value is the largest similarity value included in the calculation result; When it is determined that the target similarity value is greater than the first preset threshold, the information corresponding to the target vehicle to be confirmed and included in the second target information is determined as the third target information obtained when the target vehicle passes through the target point.

5. The method according to claim 4, characterized in that Calculating a first similarity value between the license plate of each to-be-confirmed vehicle and the license plate of the target vehicle based on the second target information to obtain a calculation result includes: Comparing the first character set included in the license plate of the to-be-confirmed vehicle with the second character set included in the license plate of the target vehicle one by one for similarity according to a preset rule to obtain a comparison result, wherein the comparison result is used to indicate whether the character at each position included in the first character set is the same as the character at the corresponding position included in the second character set; The first similarity value between the license plate of the to-be-confirmed vehicle and the license plate of the target vehicle is determined based on the comparison result.

6. The method according to claim 5, characterized in that Determining the first similarity value between the license plate of the to-be-confirmed vehicle and the license plate of the target vehicle based on the comparison result includes: Determine the number of target characters that have the same characters at corresponding positions in the first character set and the second character set based on the comparison result; Calculating a second similarity value between the license plate of the to-be-confirmed vehicle and the license plate of the target vehicle based on the target number of characters; In the case where it is determined that a first character included in the first character set is different from a second character at a corresponding position in the second character set, determining whether the first character and the second character satisfy a preset relationship; In the case where it is determined that the first character and the second character satisfy the preset relationship, determining a third similarity value between the first character and the second character; The first similarity value is determined based on the second similarity value and the third similarity value.

7. The method according to claim 6, characterized in that Calculating a second similarity value between the license plate of the to-be-confirmed vehicle and the license plate of the target vehicle based on the target number of characters includes: The ratio of the target character quantity to the license plate character quantity is determined as the second similarity value, wherein the license plate character quantity is used to indicate the number of characters included in the license plate of the target vehicle.

8. The method according to claim 6, characterized in that Determining whether the first character and the second character satisfy a preset relationship includes: In the case where it is determined that the first character and the second character are a character pair included in a target character set, determining that the first character and the second character satisfy the preset relationship, wherein the target character set stores the character pairs in which the similarity between any two characters is greater than a second preset threshold; In the case where it is determined that the first character and the second character do not satisfy the character pair included in the target character set, it is determined that the first character and the second character do not satisfy the preset relationship.

9. The method according to claim 6, characterized in that The method further comprises: In the case where it is determined that the first character and the second character satisfy the preset relationship, determining a preset similarity threshold as the third similarity value; The first similarity value is determined based on the target character quantity and the third similarity value.

10. A device for determining a vehicle trajectory, characterized in that: include: An acquisition module is used to acquire first target information of a target vehicle, wherein the first target information is obtained by a photographing device at each of the multiple points in a target area when the target vehicle passes through the target area within a predetermined period of time in the past and is stored in a target database, wherein the target database stores target information of vehicles passing through all the points in the target area within the predetermined period of time, and the target information includes the license plate information of the vehicle, the point information of each of the points, and the time information when the vehicle passes through each of the points; A first determination module is used to determine whether there is a target point in the target area based on the first target information, wherein the target point is a point actually existing between adjacent points indicated by the point information included in the first target information, and the first target information does not include the point information of the target point; A search module is used to determine the first vehicle as a to-be-confirmed vehicle when it is determined that the target point exists and when it is determined that the amount of information about the first vehicle included in the target database is less than a predetermined threshold; and obtain second target information about the to-be-confirmed vehicle; A second determination module is used to determine the information corresponding to the target vehicle to be confirmed included in the second target information as the third target information obtained when the target vehicle passes the target point, if it is determined that there is a target vehicle to be confirmed among the vehicles to be confirmed whose license plate has a similarity with the license plate of the target vehicle greater than a first preset threshold. The third determination module is used to determine the target trajectory of the target vehicle based on the first target information and the third target information.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program implements the steps of the method described in any one of claims 1 to 9 when executed by a processor.

12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method described in any one of claims 1 to 9 are implemented.

Images