CN108122415B

CN108122415B - License plate information determination method and device

Info

Publication number: CN108122415B
Application number: CN201611083291.0A
Authority: CN
Inventors: 王辉; 赵世范
Original assignee: Hangzhou Hikvision Digital Technology Co Ltd
Current assignee: Hangzhou Hikvision Digital Technology Co Ltd
Priority date: 2016-11-30
Filing date: 2016-11-30
Publication date: 2020-05-29
Anticipated expiration: 2036-11-30
Also published as: CN108122415A

Abstract

The embodiment of the invention provides a license plate information determination method and a license plate information determination device, wherein the method comprises the following steps: acquiring a target picture containing a target vehicle; acquiring a historical vehicle picture set, and grouping the historical vehicle picture set according to license plate information to obtain historical vehicle pictures of which each group contains the same license plate information; according to relevant parameters of each vehicle picture and the target picture in each group of historical vehicle pictures, determining target grouped historical vehicle pictures meeting preset conditions in a plurality of groups of historical vehicle pictures, and determining target scores of the target grouped historical vehicle pictures; and determining the license plate information of the target grouping historical vehicle picture with the highest target score as the license plate information of the target vehicle. The embodiment of the invention can determine the license plate information in the picture with failed license plate recognition.

Description

License plate information determination method and device

Technical Field

The invention relates to the technical field of image processing, in particular to a license plate information determining method and device.

Background

The license plates are two plates respectively hung at the front and the rear of the vehicle, the commonly used material is aluminum, plastic or stickers, and the license plate numbers, registration areas or other basic information of the vehicles can be displayed on the plates. The license plate information is an 'identity card' of the vehicle and is important information for distinguishing other vehicles.

In some cases, license plate recognition of a vehicle is often required. For example, in the field of traffic monitoring, an image capturing device is usually installed at a road junction, a gate, or the like to obtain a picture containing passing vehicles, and license plate information is obtained according to the picture. Alternatively, in places such as parking lots, residential gateways, or building gateways, for convenience of management, image capturing devices are also generally installed to obtain pictures including passing vehicles, and license plate information is obtained from the pictures.

When the image acquisition equipment identifies the license plate according to the acquired pictures, the license plate information can not be identified according to each picture. For example, the license plate recognition may fail due to inaccurate installation position of the image capturing device, changed shooting angle, contamination, blur, shielding, reflection of the license plate, or low visibility. Therefore, how to determine the license plate information in the picture for the picture with failed license plate recognition becomes an urgent problem to be solved.

Disclosure of Invention

The embodiment of the invention aims to provide a license plate information determining method and a license plate information determining device, so as to determine license plate information in a picture with failed license plate recognition. The specific technical scheme is as follows:

in a first aspect, an embodiment of the present invention provides a license plate information determining method, where the method includes:

acquiring a target picture containing a target vehicle;

acquiring a historical vehicle picture set, and grouping the historical vehicle picture set according to license plate information to obtain historical vehicle pictures of which each group contains the same license plate information;

according to relevant parameters of each vehicle picture and the target picture in each group of historical vehicle pictures, determining target grouped historical vehicle pictures meeting preset conditions in a plurality of groups of historical vehicle pictures, and determining target scores of the target grouped historical vehicle pictures; wherein the relevant parameters include at least one of: similarity, attribute information, and spatio-temporal relationships;

and determining the license plate information of the target grouping historical vehicle picture with the highest target score as the license plate information of the target vehicle.

Optionally, when the related parameter is a similarity, the step of determining, from among the plurality of groups of historical vehicle pictures, a target grouped historical vehicle picture that meets a preset condition according to the related parameter between each vehicle picture included in each group of historical vehicle pictures and the target picture includes:

calculating the similarity between the target picture and each vehicle picture included in each group of historical vehicle pictures aiming at each group of historical vehicle pictures;

determining a first statistical index of the group of historical vehicle pictures according to the similarity of the target picture and each vehicle picture included in the group of historical vehicle pictures; wherein the first statistical indicator comprises at least one of: the method comprises the steps of obtaining a maximum similarity, a minimum similarity, an average similarity and a first mode, wherein the first mode is the occurrence frequency of the similarity with the largest occurrence frequency;

judging whether the group of historical vehicle pictures meet preset conditions or not according to the first statistical index of the group of historical vehicle pictures;

if yes, the group of historical vehicle pictures is determined to be the target group historical vehicle pictures.

Optionally, when the first statistical indicator comprises a maximum similarity, a minimum similarity, an average similarity, and a first mode; the step of determining whether the group of historical vehicle pictures meets the preset condition according to the first statistical index of the group of historical vehicle pictures comprises at least one of the following steps:

judging whether the maximum similarity is larger than a first preset threshold value or not;

judging whether the minimum similarity is greater than a second preset threshold value or not;

judging whether the average similarity is greater than a third preset threshold value or not;

and judging whether the first mode is larger than a fourth preset threshold value.

Optionally, the step of determining the target score of each target group historical vehicle picture includes:

and determining the maximum similarity corresponding to the target grouping historical vehicle pictures as the target score of the target grouping historical vehicle pictures aiming at each target grouping historical vehicle picture.

Optionally, when the related parameter is attribute information, the step of determining, according to the related parameter between each vehicle picture included in each group of historical vehicle pictures and the target picture, a target grouped historical vehicle picture that meets a preset condition in the plurality of groups of historical vehicle pictures includes:

comparing the attribute information of the target picture with the corresponding attribute information of each vehicle picture in each group of historical vehicle pictures, and calculating the attribute score of each vehicle picture in each group of historical vehicle pictures according to the comparison result;

determining a second statistical index of the group of historical vehicle pictures according to the attribute scores of the vehicle pictures in the group of historical vehicle pictures; wherein the second statistical indicator comprises at least one of: the attribute score of each attribute is a maximum attribute score, a minimum attribute score, an average attribute score, and a second mode, wherein the second mode is the number of occurrences of the attribute score with the largest number of occurrences;

judging whether the group of historical vehicle pictures meet preset conditions or not according to a second statistical index of the group of historical vehicle pictures;

Optionally, when the second statistical indicator comprises a maximum attribute score, a minimum attribute score, an average attribute score, and a second mode; the step of determining whether the group of historical vehicle pictures meets the preset condition according to the second statistical index of the group of historical vehicle pictures comprises at least one of the following steps:

judging whether the maximum attribute score is larger than a fifth preset threshold value or not;

judging whether the minimum attribute score is larger than a sixth preset threshold value or not;

judging whether the average attribute score is larger than a seventh preset threshold value or not;

and judging whether the second mode is larger than an eighth preset threshold value.

and determining the maximum attribute score corresponding to each target grouping historical vehicle picture as the target score of the target grouping historical vehicle picture.

Optionally, when the related parameter is spatio-temporal information, the step of determining, according to the related parameter between each vehicle picture included in each group of historical vehicle pictures and the target picture, a target grouped historical vehicle picture that meets a preset condition in the plurality of groups of historical vehicle pictures includes:

determining the position information and the time information of the target picture, and the position information and the time information of each vehicle picture included in each group of historical vehicle pictures meeting a preset time condition;

calculating the difference value between the time information of the target picture and the time information of each vehicle picture included in each group of historical vehicle pictures aiming at each group of historical vehicle pictures;

acquiring time thresholds between the position information of the target picture and the position information of each vehicle picture included in the group of historical vehicle pictures according to the time thresholds between the locally stored position information;

judging whether each difference value is larger than a corresponding time threshold value;

aiming at each target grouping historical vehicle picture, determining the driving track of the vehicle corresponding to the target grouping historical vehicle picture according to the position information of each vehicle picture included in the target grouping historical vehicle picture;

determining the total times of the vehicle at each position according to the driving track of the vehicle corresponding to the target grouping historical vehicle picture, and calculating the occurrence probability of the vehicle at the position corresponding to the target picture according to the total times of the vehicle at each position and the times of the vehicle at the position corresponding to the target picture;

calculating the time probability of the vehicle appearing at the corresponding position of the target picture according to the time information of each vehicle picture, the time information of the target picture and a preset distribution function which are included in the target grouping historical vehicle picture;

and calculating the space-time score of the target grouping historical vehicle picture according to the appearance probability of the vehicle at the corresponding position of the target picture and the appearance time probability of the vehicle at the corresponding position of the target picture, and determining the space-time score as the target score of the target grouping historical vehicle picture.

Optionally, the step of calculating the spatio-temporal score of the target grouped historical vehicle picture according to the occurrence probability of the vehicle at the corresponding position of the target picture and the time probability of the vehicle occurring at the corresponding position of the target picture includes:

and calculating the product of the occurrence probability and the time probability, and determining the calculated result as the space-time score of the target grouping historical vehicle picture.

Optionally, the process of storing the time threshold between the position information includes:

for every two pieces of position information, obtaining vehicle pictures corresponding to the two pieces of position information and time information corresponding to each vehicle picture;

identifying the vehicle pictures containing the same vehicle in the vehicle pictures corresponding to the two pieces of position information;

calculating the difference value between the time information of each vehicle picture corresponding to one piece of position information and the time information of each vehicle picture corresponding to the other piece of position information aiming at the vehicle pictures containing the same vehicle;

and determining a time threshold value between the two pieces of position information according to the calculated difference value and storing the time threshold value locally.

In a second aspect, an embodiment of the present invention provides a license plate information determining apparatus, where the apparatus includes:

the first acquisition module is used for acquiring a target picture containing a target vehicle;

the execution module is used for acquiring a historical vehicle picture set, and grouping the historical vehicle picture set according to license plate information to obtain historical vehicle pictures of which each group contains the same license plate information;

the processing module is used for determining target grouped historical vehicle pictures meeting preset conditions in a plurality of groups of historical vehicle pictures according to relevant parameters of the target pictures and the vehicle pictures included in the historical vehicle pictures, and determining target scores of the target grouped historical vehicle pictures; wherein the relevant parameters include at least one of: similarity, attribute information, and spatio-temporal relationships;

and the determining module is used for determining the license plate information of the target grouping historical vehicle picture with the highest target score as the license plate information of the target vehicle.

Optionally, when the relevant parameter is similarity, the processing module includes:

the first calculation submodule is used for calculating the similarity between the target picture and each vehicle picture included in each group of historical vehicle pictures aiming at each group of historical vehicle pictures;

the first determining submodule is used for determining a first statistical index of the group of historical vehicle pictures according to the similarity between the target picture and each vehicle picture included in the group of historical vehicle pictures; wherein the first statistical indicator comprises at least one of: the method comprises the steps of obtaining a maximum similarity, a minimum similarity, an average similarity and a first mode, wherein the first mode is the occurrence frequency of the similarity with the largest occurrence frequency;

the first judgment submodule is used for judging whether the group of historical vehicle pictures meets the preset condition or not according to the first statistical index of the group of historical vehicle pictures;

and the second determining submodule is used for determining the group of historical vehicle pictures as the target grouping historical vehicle pictures when the judgment result of the first judging submodule is positive.

The embodiment of the invention provides a license plate information determination method and a license plate information determination device, when a target picture is acquired, can obtain historical vehicle picture sets, and group the historical vehicle picture sets according to the license plate information to obtain historical vehicle pictures of which each group contains the same license plate information, then according to the relevant parameters of each vehicle picture and the target picture included in each group of historical vehicle pictures, determining a target grouping historical vehicle picture meeting a preset condition from a plurality of groups of historical vehicle pictures, and determining the target score of each target group historical vehicle picture, wherein the target score of each target group historical vehicle picture can represent the correlation degree of each target group historical vehicle picture and the target picture, and finally, and determining the license plate information of the target grouping historical vehicle picture with the highest target score as the license plate information of the target vehicle, so that the license plate information in the target picture can be determined.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a flowchart of a license plate information determining method according to an embodiment of the present invention;

fig. 2 is another flowchart of a license plate information determining method according to an embodiment of the present invention;

fig. 3 is another flowchart of a license plate information determining method according to an embodiment of the present invention;

fig. 4 is another flowchart of a license plate information determining method according to an embodiment of the present invention;

fig. 5 is another flowchart of a license plate information determining method according to an embodiment of the present invention;

fig. 6 is another flowchart of a license plate information determining method according to an embodiment of the present invention;

fig. 7 is another flowchart of a license plate information determining method according to an embodiment of the present invention;

fig. 8 is another flowchart of a license plate information determining method according to an embodiment of the present invention;

fig. 9 is a schematic structural diagram of a license plate information determination device according to an embodiment of the present invention.

Detailed Description

The embodiment of the invention provides a license plate information determination method and device in order to determine license plate information in a picture with failed license plate identification.

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.

The embodiment of the invention provides a license plate information determination method, which comprises the following steps of:

s101, acquiring a target picture containing a target vehicle.

The method provided by the embodiment of the invention can be applied to electronic equipment. Specifically, the electronic device may be a desktop computer, a portable computer, an intelligent mobile terminal, a server, or the like.

In the embodiment of the invention, the image acquisition equipment can be arranged at intersections, cell gates and other places. Each image acquisition device can identify whether a vehicle passes through the acquisition area of the image acquisition device, and if so, the image acquisition device can acquire a picture containing the vehicle. The image acquisition device may be a dome camera, a video camera, a snapshot machine, and the like, which is not limited in the embodiment of the present invention.

Moreover, wired or wireless connection can be established between the image acquisition device and the electronic device, so that the image acquisition device can send the acquired picture to the electronic device. For example, a Wireless connection may be established between the image capturing device and the electronic device through a Wireless connection manner such as WIFI (Wireless Fidelity), NFC (Near Field Communication), bluetooth, and the like, which is not limited in the embodiments of the present invention.

It should be noted that, the method provided in the embodiment of the present invention may determine license plate information included in each picture acquired by each image acquisition device, and this embodiment only takes any picture as an example to illustrate the license plate information determination method provided in the embodiment of the present invention. Also, for convenience of description, a picture targeted in the embodiment of the present invention may be referred to as a target picture.

In the embodiment of the invention, the electronic equipment can acquire the target picture containing the target vehicle. For example, the electronic device may receive a target picture sent by the image capture device. The target vehicle is the vehicle with the license plate information to be confirmed included in the target picture.

S102, acquiring a historical vehicle picture set, and grouping the historical vehicle picture set according to license plate information to obtain historical vehicle pictures of which each group contains the same license plate information.

In the embodiment of the invention, after the electronic device acquires the target picture containing the target vehicle, the electronic device can acquire the historical vehicle picture set so as to determine the license plate information in the target picture through the historical vehicle picture set.

Optionally, after the electronic device acquires the target picture containing the target vehicle, it may first identify the license plate information of the target vehicle through the target picture. For example, the electronic device may use any existing image recognition method to recognize the license plate information of the target vehicle included in the target image.

In some cases, for example, the target picture has low resolution, the license plate of the target vehicle is stained and blocked, and the like, which may cause that the electronic device may not recognize the license plate information of the target vehicle according to the target picture. When the electronic device cannot recognize the license plate information of the target vehicle according to the target picture, the electronic device can acquire the historical vehicle picture so as to determine the license plate information of the target vehicle through the historical vehicle picture set.

Generally, image capturing devices are installed at a plurality of intersections, gates, and the like, and each image capturing device transmits a captured picture to an electronic device. Moreover, in the embodiment of the present invention, the electronic device stores the received picture. For example, the electronic device may save all the pictures it receives, or, to save the storage space, the electronic device may save the pictures within a preset time, which may be, for example, 2 days, 5 days, 10 days, etc.

That is, the electronic device is likely to have saved a picture containing the target vehicle for the target vehicle in the target picture. Therefore, in the embodiment of the present invention, the electronic device may determine the license plate information of the target vehicle included in the target picture according to the historical vehicle picture.

Specifically, the electronic device may obtain a historical vehicle image set, and group the historical vehicle image set according to the license plate information to obtain historical vehicle images each including the same license plate information. For example, the electronic device may obtain a set of historical vehicle pictures over a preset period of time (e.g., 1 day, 2 days, 3 days, etc.). After the historical vehicle picture set is obtained, the electronic equipment can group the historical vehicle picture set according to the license plate information. That is, the license plate information of the vehicles included in the same group of historical vehicle pictures is the same.

S103, according to the relevant parameters of the vehicle pictures and the target pictures included in the historical vehicle pictures, determining target grouped historical vehicle pictures meeting preset conditions in the multiple groups of historical vehicle pictures, and determining target scores of the target grouped historical vehicle pictures.

After each group of historical vehicle pictures is obtained, the electronic equipment can screen each group of historical license plate pictures to obtain target grouping historical vehicle pictures with relatively high correlation with the target pictures. And (4) the license plate information corresponding to the historical license plate pictures of each target group is possible license plate information of the target vehicle.

Specifically, the electronic device may determine, from among the plurality of sets of historical vehicle pictures, a target grouped historical vehicle picture that satisfies a preset condition according to a parameter related to each vehicle picture and a target picture included in each set of historical vehicle pictures. Wherein the related parameters may include at least one of: similarity, attribute information, and spatio-temporal relationships.

The images containing the same vehicle are generally higher in similarity; the attribute information (e.g., vehicle brand, sub-brand, color, etc.) should also be the same; the spatiotemporal relationship, that is, the relationship between the time when the vehicle appears at each position and the time when the vehicle appears at each position, should also satisfy the preset condition. For example, when the vehicle is present at any one location for a time a and at another location for a time b, the time difference between the time a and the time b should be greater than or equal to the time it takes for the vehicle to travel from the one location to the another location at maximum speed. When the time difference between the two positions where the vehicle included in the two pictures appears is smaller than the time taken for the vehicle to travel from one of the two positions to the other at the maximum speed, it can be indicated that different vehicles are included in the two pictures.

In the embodiment of the invention, through comparison of the related parameters, the correlation between the vehicle pictures included in each group of historical vehicle pictures and the target picture can be determined, and then each group of historical vehicle pictures with larger correlation with the target picture can be determined as the target grouping historical vehicle picture.

After determining each target group historical vehicle picture, the electronic device may further determine a target score of each target group historical vehicle picture, that is, accurately determine a degree of correlation between each target group historical vehicle picture and the target picture. For example, the electronic device may determine the target score of each target group historical vehicle picture by using a corresponding method according to different relevant parameters.

And S104, determining the license plate information of the target grouping historical vehicle picture with the highest target score as the license plate information of the target vehicle.

After the target score of each target grouping historical vehicle picture is determined, the electronic equipment can determine the license plate information of the target grouping historical vehicle picture with the highest target score as the license plate information of the target vehicle. And grouping the historical vehicle pictures of the targets with the highest target scores, namely, grouping the historical vehicle pictures of the targets with the highest relevance with the target pictures. That is, the vehicles included in the target grouping history vehicle picture should be the same as the target vehicle, and therefore, the license plate information of the target grouping history vehicle picture with the highest target score may be determined as the license plate information of the target vehicle.

The embodiment of the invention provides a license plate information determination method, which can acquire a historical vehicle picture set when acquiring a target picture, and grouping the historical vehicle picture sets according to the license plate information to obtain each group of historical vehicle pictures containing the same license plate information, then according to the relevant parameters of each vehicle picture and the target picture included in each group of historical vehicle pictures, determining a target grouping historical vehicle picture meeting a preset condition from a plurality of groups of historical vehicle pictures, and determining the target score of each target group historical vehicle picture, wherein the target score of each target group historical vehicle picture can represent the correlation degree of each target group historical vehicle picture and the target picture, and finally, and determining the license plate information of the target grouping historical vehicle picture with the highest target score as the license plate information of the target vehicle, so that the license plate information in the target picture can be determined.

As an implementation manner of the embodiment of the present invention, the electronic device may determine, in the multiple sets of historical vehicle pictures, a target group historical vehicle picture that meets a preset condition according to a similarity between the target picture and each historical vehicle picture. Specifically, as shown in fig. 2, in the embodiment of the present invention, the process of determining the target group history vehicle picture by the electronic device may include the following steps:

s201, aiming at each group of historical vehicle pictures, calculating the similarity between the target picture and each vehicle picture included in the group of historical vehicle pictures.

In the embodiment of the invention, the electronic device can sequentially analyze each group of historical vehicle pictures to determine whether the group of historical vehicle pictures meets the preset condition, and further determine whether the group of historical vehicle pictures is the target group of historical vehicle pictures. Specifically, for each group of historical vehicle pictures, the electronic device may calculate, for each vehicle picture included in the group of historical vehicle pictures, a similarity of the vehicle picture to the target picture.

The process of calculating the similarity between each vehicle picture and the target picture by the electronic device can adopt any existing method, and the process is not repeated in the embodiment of the invention.

S202, according to the similarity between the target picture and each vehicle picture included in the group of historical vehicle pictures, determining a first statistical index of the group of historical vehicle pictures.

In the embodiment of the invention, for each group of historical vehicle pictures, the electronic equipment can integrally analyze the correlation between the group of historical vehicle pictures and the target picture. Specifically, after calculating the similarity between each vehicle picture included in each group of historical vehicle pictures and the target picture for each group of historical vehicle pictures, the electronic device may further determine a first statistical indicator of the group of historical vehicle pictures.

Wherein the first statistical indicator may include at least one of: the similarity calculation method comprises the steps of maximum similarity, minimum similarity, average similarity and a first mode, wherein the first mode is the occurrence frequency of the similarity with the maximum occurrence frequency.

S203, judging whether the group of historical vehicle pictures meets preset conditions or not according to the first statistical index of the group of historical vehicle pictures; if yes, step S204 is executed, and if no, no operation is executed.

For any group of historical vehicle pictures, after the electronic device determines the first statistical indicator of the group of historical vehicle pictures, the electronic device may determine whether the group of historical vehicle pictures meets the preset condition according to the first statistical indicator of the group of historical vehicle pictures.

When the first statistical indicator includes a maximum similarity, a minimum similarity, an average similarity, and a first mode, the electronic device may perform at least one of the following when determining whether the set of historical vehicle pictures satisfies a preset condition: judging whether the maximum similarity is greater than a first preset threshold, such as 0.8, 0.85, 0.9 and the like; judging whether the minimum similarity is greater than a second preset threshold, such as 0.5, 0.55, 0.6 and the like; judging whether the average similarity is greater than a third preset threshold, such as 0.7%, 0.75%, 0.8% and the like; and judging whether the first mode is larger than a fourth preset threshold value, such as 5, 6, 7 and the like.

And S204, determining the group of historical vehicle pictures as target group historical vehicle pictures.

When the electronic device judges that the group of historical vehicle pictures meets the preset condition according to the first statistical index of the group of historical vehicle pictures, the similarity between the group of historical vehicle pictures and the target picture is high, and under the condition, the group of historical vehicle pictures can be determined to be the target grouped historical vehicle pictures.

In the embodiment of the invention, the target grouping historical vehicle pictures meeting the preset condition can be determined by analyzing the similarity between the target picture and each vehicle picture included in each group of historical vehicle pictures, and the license plate information of the target vehicle can be accurately determined according to the determined target grouping historical vehicle pictures.

Accordingly, when the electronic device determines the target grouping history vehicle picture according to the similarity between each vehicle picture included in each group of history vehicle pictures and the target picture, the electronic device may determine, for each target grouping history vehicle picture, the maximum similarity corresponding to the target grouping history vehicle picture as the target score of the target grouping history vehicle picture.

As an implementation manner of the embodiment of the present invention, the electronic device may determine, from the plurality of sets of historical vehicle pictures, a target group historical vehicle picture that meets a preset condition according to the target picture and attribute information of each historical vehicle picture. Specifically, as shown in fig. 3, in the embodiment of the present invention, the process of determining the target group history vehicle picture by the electronic device may include the following steps:

s301, aiming at each group of historical vehicle pictures, comparing the attribute information of the target picture with the corresponding attribute information of each vehicle picture in the group of historical vehicle pictures, and calculating the attribute score of each vehicle picture in the group of historical vehicle pictures according to the comparison result.

In the embodiment of the invention, the electronic device can sequentially analyze each group of historical vehicle pictures to determine whether the group of historical vehicle pictures meets the preset condition, and further determine whether the group of historical vehicle pictures is the target group of historical vehicle pictures. Specifically, for each group of historical vehicle pictures, the electronic device may compare the attribute information of the target picture with the corresponding attribute information of each vehicle picture included in the group of historical vehicle pictures, and calculate an attribute score of each vehicle picture included in the group of historical vehicle pictures according to the comparison result.

The attribute information of each picture is the attribute information of the vehicle included in the corresponding picture. The attribute information may include, for example, one or more of the following: the vehicle brand, the vehicle sub-brand, the vehicle color, the vehicle body length and other inherent information of the vehicle.

Specifically, the electronic device may set in advance the weight of each content included in the attribute information. For example, when the attribute information includes a vehicle brand, a vehicle sub-brand, a vehicle color, and a vehicle body length, the weight of the vehicle brand may be set to 0.25, the weight of the vehicle sub-brand may be set to 0.4, the weight of the vehicle color may be set to 0.15, and the weight of the vehicle body length may be set to 0.2.

When analyzing each group of historical vehicle pictures, the electronic device may compare each content included in the attribute information of the vehicle picture with each corresponding content in the attribute information of the target picture, for any vehicle picture included in the group of historical vehicle pictures. For example, the vehicle brand of the vehicle picture is compared with the vehicle brand of the target picture; comparing the vehicle sub-brand of the vehicle picture with the vehicle sub-brand of the target picture; comparing the vehicle color of the vehicle picture with the vehicle color of the target picture; and comparing the length of the vehicle body of the vehicle picture with the length of the vehicle body of the target picture.

And the electronic equipment can also calculate the attribute score of each vehicle picture included in the group of historical vehicle pictures according to the comparison result. For example, for any vehicle picture, the weights of the same contents in the attribute information of the vehicle picture and the target picture may be added as the attribute score of the vehicle picture. For example, when the vehicle brand of any vehicle picture is the same as that of the target picture, the vehicle sub-brand is the same as that of the target picture, the vehicle color is different from that of the target picture, and the vehicle body length is the same as that of the target picture, it may be determined that the attribute score of the vehicle picture is 0.25+0.4+ 0.2-0.85.

S302, determining a second statistical index of the group of historical vehicle pictures according to the attribute scores of the vehicle pictures in the group of historical vehicle pictures; wherein the second statistical indicator comprises at least one of: the attribute score of the first group is a maximum attribute score, a minimum attribute score, an average attribute score, and a second mode, wherein the second mode is a number of occurrences of the attribute score that occurs the most frequently.

In the embodiment of the invention, for each group of historical vehicle pictures, the electronic equipment can integrally analyze the correlation between the group of historical vehicle pictures and the target picture. Specifically, after calculating the attribute score of each vehicle picture included in each group of historical vehicle pictures, the electronic device may further determine a second statistical indicator of each group of historical vehicle pictures.

Wherein, the second statistical indicator may include at least one of the following: the attribute score is a maximum attribute score, a minimum attribute score, an average attribute score, and a second mode, wherein the second mode is a number of occurrences of the attribute score that occurs the most frequently.

S303, judging whether the group of historical vehicle pictures meets preset conditions according to the second statistical index of the group of historical vehicle pictures; if yes, step S304 is performed, and if no, no operation is performed.

For any group of historical vehicle pictures, after the electronic device determines the second statistical index of the group of historical vehicle pictures, the electronic device may determine whether the group of historical vehicle pictures meets the preset condition according to the second statistical index of the group of historical vehicle pictures.

When the second statistical indicator includes a maximum attribute score, a minimum attribute score, an average attribute score, and a second mode, the electronic device may perform at least one of the following when determining whether the set of historical vehicle pictures satisfies a preset condition: judging whether the maximum attribute score is larger than a fifth preset threshold value, such as 0.7, 0.75, 0.8 and the like; judging whether the minimum attribute score is larger than a sixth preset threshold value, such as 0.4, 0.5, 0.55 and the like; judging whether the average attribute score is larger than a seventh preset threshold value, such as 0.5, 0.55, 0.6 and the like; and judging whether the second mode is larger than an eighth preset threshold, such as 5, 6, 7 and the like.

S304, determining the group of historical vehicle pictures as target group historical vehicle pictures.

When the electronic device judges that the group of historical vehicle pictures meets the preset condition according to the second statistical index of the group of historical vehicle pictures, the electronic device indicates that the group of historical vehicle pictures is basically the same as the target picture in attribute information, and under the condition, the group of historical vehicle pictures can be determined to be the target grouped historical vehicle pictures.

In the embodiment of the invention, the target grouping historical vehicle pictures meeting the preset condition can be determined by comparing the attribute information of the target picture with the attribute information of each vehicle picture in each group of historical vehicle pictures, and the license plate information of the target vehicle can be accurately determined according to the determined target grouping historical vehicle pictures.

Accordingly, when the electronic device determines a target grouping history vehicle picture by comparing the attribute information of the target picture with the attribute information of each vehicle picture included in each group of history vehicle pictures, the electronic device may determine, for each target grouping history vehicle picture, a maximum attribute score corresponding to the target grouping history vehicle picture as a target score of the target grouping history vehicle picture.

As an implementation manner of the embodiment of the present invention, the electronic device may determine, from the target picture and the temporal-spatial information of each historical vehicle picture, a target grouped historical vehicle picture that meets a preset condition among the plurality of groups of historical vehicle pictures. Specifically, as shown in fig. 4, in the embodiment of the present invention, the process of determining the target group history vehicle picture by the electronic device may include the following steps:

s401, determining the position information and the time information of the target picture, and the position information and the time information of each vehicle picture included in each group of historical vehicle pictures meeting a preset time condition.

When a vehicle is present at two locations, the spatiotemporal relationship of the two locations should satisfy a certain condition. For example, when the vehicle is present at any one location for a time a and at another location for a time b, the time difference between the time a and the time b should be greater than or equal to the time it takes for the vehicle to travel from the one location to the another location at maximum speed. When the time difference between the two positions where the vehicle included in the two pictures appears is smaller than the time taken for the vehicle to travel from one of the two positions to the other at the maximum speed, it can be indicated that different vehicles are included in the two pictures.

Therefore, in the embodiment of the invention, the target grouped historical vehicle pictures can be determined according to the spatiotemporal relation between the target picture and each historical vehicle picture. That is, it is possible to determine whether or not the assumption is established based on the spatiotemporal relationship, assuming that the vehicle in the group of the historical vehicle pictures is the target vehicle, for each group of the historical vehicle pictures.

When the target grouping historical vehicle pictures are determined through the spatiotemporal relationship, under the normal condition, the vehicle usually stops at a certain place at night and does not run all the time, so if the time range corresponding to the selected historical vehicle pictures is too large, the accuracy of the determination result is influenced. Therefore, in the embodiment of the present invention, the electronic device may determine the position information and the time information of the target picture, and the position information and the time information of each vehicle picture included in each set of history vehicle pictures satisfying the preset time condition. The preset time condition may be, for example, within 1 day, within 12 hours, and the like.

For example, the electronic device may store in advance a correspondence between the identification information of each image capturing device and its installation location, and when each image capturing device captures a vehicle picture and sends it to the electronic device, it may send its identification information to the electronic device together, so that the electronic device may determine the position information of each vehicle picture according to the correspondence between the identification information of each image capturing device and its installation location. And when the image acquisition equipment sends the vehicle picture, the acquisition time of the vehicle picture can be sent to the electronic equipment together.

After receiving the vehicle pictures, the position information and the time information of the vehicle pictures, the electronic equipment can locally and correspondingly store the vehicle pictures, the position information and the time information of the vehicle pictures. Therefore, the electronic device can locally acquire the position information and the time information of the target picture, and the position information and the time information of each vehicle picture included in each group of historical vehicle pictures satisfying the preset time condition.

S402, aiming at each group of historical vehicle pictures, calculating the difference value between the time information of the target picture and the time information of each vehicle picture included in the group of historical vehicle pictures.

After the electronic device obtains the position information and the time information of the target picture and the position information and the time information of each vehicle picture included in each group of historical vehicle pictures meeting the preset time condition, the difference value between the time information of the target picture and the time information of each vehicle picture included in each group of historical vehicle pictures can be calculated for each group of historical vehicle pictures.

For example, when the position information and the time information of the target picture are P1, 2016.3.3, 3: 33: 33, the position information and the time information of each vehicle picture included in any one of the object group history vehicle pictures are shown in the following table:

location information	Time information
		P1	2016.3.3，4：00：00
P2	2016.3.3，3：00：00
		P3	2016.3.3，4：30：30

The difference value between the time information of the target picture and the time information of each vehicle picture included in the group of historical vehicle pictures calculated by the electronic equipment is respectively as follows:

wherein, | T1-T1| is the time taken by the target vehicle from the P1 position to the P1 position, | T1-T2| is the time taken by the target vehicle from the P1 position to the P2 position, and | T1-T3| is the time taken by the target vehicle from the P1 position to the P3 position.

And S403, acquiring a time threshold between the position information of the target picture and the position information of each vehicle picture included in the group of historical vehicle pictures according to the time threshold between the locally stored position information.

After obtaining the difference between the time information of the target picture and the time information of each vehicle picture included in the group of historical vehicle pictures, the electronic device may further obtain the time threshold between the position information of the target picture and the position information of each vehicle picture included in the group of historical vehicle pictures according to the time threshold between the locally stored position information.

For example, the electronic device may store the time threshold between every two locations locally in advance according to the distance between the locations and the identification information of the locations. Furthermore, the electronic device may search for a time threshold between the position information of the target picture and the position information of each vehicle picture included in the group of historical vehicle pictures from the time thresholds between the locally stored position information according to the position information of the target picture and the position information of each vehicle picture included in the group of historical vehicle pictures.

Also taking the above example as an example, the electronic device may obtain the time thresholds between P1 and P1, between P1 and P2, and between P1 and P3, which may be obtained as shown in the following table:

position information pair	Time threshold
		T1-1	0
T1-2	30 minutes
		T1-3	50 minutes

S404, judging whether each difference value is larger than a corresponding time threshold value; if yes, step S405 is performed, and if no, no operation is performed.

After obtaining the difference between the time information of the target picture and the time information of each vehicle picture included in the group of historical vehicle pictures and the time threshold between the position information of the target picture and the position information of each vehicle picture included in the group of historical vehicle pictures, the electronic device may determine whether each difference is greater than the corresponding time threshold, so as to determine whether the target vehicle and the vehicle included in the group of historical vehicle pictures are likely to be the same vehicle.

For example, in the above example, the time 26 minutes 27 seconds taken for the target vehicle to travel from the position P1 to the position P1 is greater than the corresponding time threshold 0; the time taken by the target vehicle from the P1 position to the P2 position is 33 minutes and 33 seconds greater than the corresponding time threshold of 30 minutes; the time 56 minutes 27 seconds spent by the target vehicle from the P1 position to the P3 position is greater than the corresponding time threshold of 50 minutes. That is, each time difference is greater than the corresponding time threshold.

When T1-2 is 35 minutes, the time 33 minutes 33 seconds taken by the target vehicle from the P1 position to the P2 position is less than the corresponding time threshold of 35 minutes, in which case the electronic device does not determine the set of historical vehicle pictures as the target group historical vehicle pictures.

S405, determining the group of historical vehicle pictures as target group historical vehicle pictures.

When the electronic equipment determines that each time difference is larger than the corresponding time threshold, the group of historical vehicle pictures can be determined as the target group of historical vehicle pictures.

In the embodiment of the invention, the target grouping historical vehicle pictures meeting the preset condition can be determined by analyzing the time-space relationship between the target picture and each vehicle picture included in each group of historical vehicle pictures, and the license plate information of the target vehicle can be accurately determined according to the determined target grouping historical vehicle pictures.

Accordingly, as shown in fig. 5, when the electronic device determines the target grouped historical vehicle pictures according to the spatiotemporal relationship between each vehicle picture and the target picture included in each group of historical vehicle pictures, the process of determining the target score of each target grouped historical vehicle picture may include the following steps:

s501, aiming at each target grouping historical vehicle picture, determining the driving track of the vehicle corresponding to the target grouping historical vehicle picture according to the position information of each vehicle picture included in the target grouping historical vehicle picture.

In the embodiment of the invention, for each target grouping history vehicle picture, the electronic device may determine the driving track of the vehicle corresponding to the target grouping history vehicle picture according to the position information of each vehicle picture included in the target grouping history vehicle picture.

For example, for any target group historical vehicle picture, the position information of each included vehicle picture is: p1, P2, P1, P3 and P1, the driving track of the vehicle corresponding to the target grouping history vehicle picture can be determined to be P1-P2-P1-P3-P1.

S502, determining the total number of times of the vehicle appearing at each position according to the driving track of the vehicle corresponding to the target grouping historical vehicle picture, and calculating the appearance probability of the vehicle at the position corresponding to the target picture according to the total number of times of the vehicle appearing at each position and the number of times of the vehicle appearing at the position corresponding to the target picture.

After the electronic device determines the driving track of the vehicle corresponding to the target grouping historical vehicle picture, the total number of times of occurrence of the vehicle at each position can be further determined. For example, in the above example, the total number of occurrences of the vehicle at each location is 5.

The electronic equipment can also calculate the occurrence probability of the vehicle at the corresponding position of the target picture according to the total number of times of occurrence of the vehicle at each position and the number of times of occurrence of the vehicle at the corresponding position of the target picture. For example, in the above example, when the position corresponding to the target picture is P1, it can be calculated that the probability of the vehicle appearing at the position corresponding to the target picture is 3/5 — 0.6.

S503, calculating the time probability of the vehicle appearing at the corresponding position of the target picture according to the time information of each vehicle picture included in the target grouping historical vehicle picture, the time information of the target picture and a preset distribution function.

In the embodiment of the present invention, the electronic device may further calculate a time probability that the vehicle appears at a position corresponding to the target picture according to the time information of each vehicle picture included in the target grouping history vehicle picture, the time information of the target picture, and a preset distribution function. That is, the probability that the vehicle appears at the corresponding position of the target picture is determined from the time information.

For example, the preset distribution function may be a normal distribution function, and the electronic device may determine a mean and a variance of the normal distribution function according to time information of each vehicle picture included in the target grouping history vehicle picture. Further, according to the time information of the target picture, the value of the normal distribution is calculated, and the value is determined as the time probability of the vehicle appearing at the position corresponding to the target picture.

S504, according to the appearance probability of the vehicle at the corresponding position of the target picture and the appearance time probability of the vehicle at the corresponding position of the target picture, calculating the space-time score of the target grouping historical vehicle picture, and determining the space-time score as the target score of the target grouping historical vehicle picture.

After the electronic device calculates the occurrence probability of the vehicle at the corresponding position of the target picture and the time probability, the space-time score of the target grouping historical vehicle picture can be calculated according to the occurrence probability of the vehicle at the corresponding position of the target picture and the time probability of the vehicle at the corresponding position of the target picture, and the space-time score is determined as the target score of the target grouping historical vehicle picture.

For example, the electronic device may calculate the product of the probability of occurrence and the probability of time, and determine the calculated result as the spatiotemporal score of the target group history vehicle picture.

According to the embodiment of the invention, the space-time score of each target grouping historical vehicle picture can be determined according to the space-time information, so that the license plate information of the target vehicle can be accurately determined according to the space-time score of each target grouping historical vehicle picture.

As an implementation manner of the embodiment of the present invention, the time threshold between the pieces of location information stored by the electronic device may be determined according to historical data. Namely, the position information and the time information of each vehicle picture can be determined according to the vehicle picture acquired by each image acquisition device. Specifically, as shown in fig. 6, the license plate information determining method provided in the embodiment of the present invention may further include the following steps:

s601, for every two pieces of position information, obtaining vehicle pictures corresponding to the two pieces of position information and time information corresponding to each vehicle picture.

In the embodiment of the invention, the electronic device can acquire the vehicle pictures corresponding to the two pieces of position information and the time information corresponding to each vehicle picture for every two pieces of position information.

Specifically, the electronic device may acquire, for two pieces of location information, all the vehicle pictures acquired by the image acquisition devices at the two pieces of location information, and time information of each vehicle picture. Alternatively, to improve the efficiency of determining the time threshold, the electronic device may acquire the vehicle pictures within a predetermined time acquired by the image acquisition devices at the two positions, such as the vehicle pictures acquired in the last 5 days, 10 days, or 1 month, and the time information of each vehicle picture.

For example, when the electronic device calculates the time threshold between the P1 position and the P2 position, the obtained picture information of the vehicle at the P1 position can be shown as the following table:

the picture information of the vehicle at the position P2 acquired by the electronic device can be shown as the following table:

vehicle identification	Time information
		A	15：00：00
A	16：00：00
		C	17：00：00
B	18：00：00
		D	19：00：00

And S602, identifying the vehicle pictures containing the same vehicle in the vehicle pictures corresponding to the two pieces of position information.

After the vehicle pictures at the two position information are acquired, the electronic device may identify the vehicle pictures containing the same vehicle in the acquired vehicle pictures.

For example, the electronic device may compare two vehicle pictures at two positions in any existing image recognition manner, recognize whether each two images contain the same vehicle, and further recognize the vehicle pictures containing the same vehicle.

Still taking the above example as an example, the electronic device may recognize that position 8 of P1: 00: vehicle picture of 00, position P2 15: 00: vehicle picture of 00, and 16 at position P2: 00: the vehicle picture of 00 is a vehicle picture including the same vehicle. P1 position 9: 00: vehicle picture of 00, and 18 at position P2: 00: the vehicle picture of 00 is a vehicle picture including the same vehicle. P1 position 10: 00: vehicle picture of 00, and 17 at position P2: 00: the vehicle picture of 00 is a vehicle picture including the same vehicle. P1 position 11: 00: vehicle picture of 00, position P2 15: 00: vehicle picture of 00, and 16 at position P2: 00: the vehicle picture of 00 is a vehicle picture including the same vehicle. P1 position 12: 00: vehicle picture of 00, and 19 at position P2: 00: the vehicle picture of 00 is a vehicle picture including the same vehicle.

S603, for the vehicle pictures including the same vehicle, calculating a difference between the time information of each vehicle picture corresponding to one of the position information and the time information of each vehicle picture corresponding to the other position information.

After identifying the vehicle pictures containing the same vehicle, the electronic device may calculate, for the vehicle pictures containing the same vehicle, a difference value between the time information of each vehicle picture corresponding to one of the position information and the time information of each vehicle picture corresponding to the other position information.

For example, in the above example, for position 8 at P1: 00: vehicle picture of 00, position P2 15: 00: vehicle picture of 00, and 16 at position P2: 00: 00, the electronic device may be directed to a vehicle at position 8 of P1: 00: 00, calculated to match the position 15 at P2: 00: vehicle picture of 00, and 16 at position P2: 00: the difference values of the time information of the vehicle picture of 00 are 7 hours and 8 hours, respectively.

For position 9 of P1: 00: vehicle picture of 00, and 18 at position P2: 00: 00, the electronic device may look for a vehicle picture at position 9 of P1: 00: 00, calculated to match the position 18 at P2: 00: the difference of the time information of the vehicle picture of 00 is 9 hours.

For position 10 at P1: 00: vehicle picture of 00, and 17 at position P2: 00: 00, the electronic device may be directed to 10: 00: 00, calculated to match the position 17 at P2: 00: the difference of the time information of the vehicle picture of 00 is 7 hours.

For position 11 at P1: 00: vehicle picture of 00, position P2 15: 00: vehicle picture of 00, and 16 at position P2: 00: 00, the electronic device may look for a P1 location 11: 00: 00, calculated to match the position 15 at P2: 00: vehicle picture of 00, and 16 at position P2: 00: the difference values of the time information of the vehicle picture of 00 are 4 hours and 5 hours, respectively.

For position 12 at P1: 00: vehicle picture of 00, and 19 at position P2: 00: 00, the electronic device may be directed to 12 at position P1: 00: 00, calculated to match the position 19 at position P2: 00: the difference of the time information of the vehicle picture of 00 is 7 hours.

S604, according to the calculated difference, determining a time threshold between the two pieces of position information and storing the time threshold locally.

After calculating the difference between the vehicle pictures at the two locations, each containing the same vehicle, the electronic device may further determine a time threshold between the two location information based on the calculated difference and store the time threshold locally.

In one implementation, the electronic device may determine a minimum value of the calculated difference values as a time threshold between two pieces of location information. For example, in the above example, the electronic device may determine the minimum of 4 hours of the differences as the time threshold between the P1 position and the P2 position.

It will be appreciated that the minimum of the calculated differences is the minimum time required for the vehicle to travel from one location to another. And determining the minimum value in the calculated difference value as a time threshold value between two pieces of position information, so that when determining the target grouping historical vehicle pictures according to the time threshold value, the historical vehicle pictures which accord with the space-time relationship cannot be filtered, and the integrity of the determination result is ensured.

In another implementation, when the data amount is large, such as the data amount exceeds 1000, 2000, etc., the time threshold between two pieces of location information may be determined by a quartile method according to the calculated difference, so as to improve the accuracy of the time threshold.

Specifically, the electronic device may arrange the calculated difference values from small to large, and use the first quartile, i.e., the number at the quarter position, as the time threshold between two pieces of position information.

In another implementation, the electronic device may further determine a time threshold between two pieces of location information by using a slope discrimination method according to the calculated difference. It can be understood that, in general, the difference with a large number of occurrences can best represent most of the cases and can also best represent the cases occurring in practical applications. Therefore, the time threshold between the two positions is determined by adopting a slope discrimination method, so that the difference value which is not in accordance with the actual situation and caused by special reasons can be effectively avoided being determined as the time threshold, and the accuracy of the time threshold can be improved.

Specifically, the electronic device may use time as a horizontal axis and the number as a vertical axis, draw a curve according to the calculated difference, further determine an interval with the maximum slope on the curve, that is, a time period with a large number, and use the start time of the time period as a time threshold.

Alternatively, the time taken by the vehicle to travel from one location to another may vary over time, and thus the time threshold between the two locations may also vary. Therefore, in the embodiment of the present invention, in order to improve the accuracy of the time threshold between two locations, the electronic device may periodically update the time threshold between the locally stored location information according to a set time interval, such as 1 day, 3 days, 1 week, or 1 month.

According to the scheme, the electronic equipment can accurately determine the time threshold value among the position information according to the vehicle pictures corresponding to the position information, and further determine the target grouping historical vehicle pictures according to the time threshold value among the position information, so that the accuracy of determining the target grouping historical vehicle pictures can be improved.

As an implementation manner of the embodiment of the present invention, when the related parameters include at least two of similarity, attribute information, and a spatiotemporal relationship, the electronic device may determine, from among the plurality of groups of historical vehicle pictures, a target grouped historical vehicle picture that satisfies a preset condition according to the related parameters of the target picture and each grouped historical vehicle picture. Specifically, as shown in fig. 7, in the embodiment of the present invention, the process of determining the target group history vehicle picture by the electronic device may include the following steps:

s701, determining the middle grouping historical vehicle picture corresponding to each relevant parameter according to each relevant parameter.

In the embodiment of the invention, the electronic equipment can determine the target grouping historical vehicle picture according to various related parameters. For example, the electronic device may determine the target grouping historical vehicle picture according to two or three of the similarity, the attribute information, and the spatiotemporal relationship, so as to improve the accuracy of the determination of the target grouping historical vehicle picture.

Specifically, the electronic device may determine, according to each related parameter, the intermediate group history vehicle picture corresponding to the related parameter respectively. For example, regarding the similarity, the electronic device may take the target grouping history vehicle picture determined in the embodiment shown in fig. 2 as the intermediate grouping history vehicle picture of the present embodiment according to the embodiment shown in fig. 2; regarding the attribute information, the electronic device may regard the target grouping history vehicle picture determined in the embodiment shown in fig. 3 as the intermediate grouping history vehicle picture of the present embodiment according to the embodiment shown in fig. 3; for the spatiotemporal relationship, the electronic device may use the target grouped historical vehicle picture determined in the embodiment shown in fig. 4 as the intermediate grouped historical vehicle picture of this embodiment according to the embodiment shown in fig. 4, which is not described in detail in this embodiment.

S702, counting the intermediate grouping historical vehicle pictures corresponding to all the relevant parameters in the intermediate grouping historical vehicle pictures corresponding to all the relevant parameters, and determining the counted intermediate grouping historical vehicle pictures as target grouping historical vehicle pictures.

After the intermediate group historical vehicle pictures corresponding to the relevant parameters are determined, the electronic device may count the intermediate group historical vehicle pictures corresponding to the relevant parameters in the intermediate group historical vehicle pictures corresponding to the relevant parameters, and determine the counted intermediate group historical vehicle pictures as the target group historical vehicle pictures. That is, the intersection of the intermediate grouped historical vehicle pictures corresponding to the respective related parameters may be determined, and the intersection may be determined as the target grouped historical vehicle picture.

For example, when the intermediate group history vehicle pictures corresponding to the similarity are S1, S2, S3, S4, the intermediate group history vehicle pictures corresponding to the attribute information are S1, S3, S4, S5, and the intermediate group history vehicle pictures corresponding to the spatiotemporal relationship are S2, S3, S4, S5, it may be determined that the target group history vehicle pictures are S3, S4.

According to the embodiment of the invention, the target grouping historical vehicle picture can be determined according to various related parameters, so that the accuracy of determining the target grouping historical vehicle picture can be improved.

Accordingly, as shown in fig. 8, when determining the target group history vehicle pictures through various related parameters, the process of the electronic device determining the target score of each target group history vehicle picture may include the steps of:

s801, determining initial scores of the target grouped historical vehicle pictures corresponding to the relevant parameters; wherein, corresponding to the relevant parameters, the initial score includes at least two of: similarity, attribute score, or spatio-temporal score.

In the embodiment of the invention, when the electronic device determines the target grouping historical vehicle pictures according to various related parameters, the electronic device can also determine the target score of each target grouping historical vehicle picture according to various related parameters.

Specifically, the electronic device may first determine an initial score of each target group historical vehicle picture corresponding to each relevant parameter. For example, similar to the foregoing embodiment, for the similarity, the electronic device may determine the maximum similarity corresponding to the target grouped historical vehicle picture as the initial score of the target grouped historical vehicle picture; for the attribute information, the electronic device may determine a maximum attribute score corresponding to the target grouped historical vehicle picture as an initial score of the target grouped historical vehicle picture; regarding the spatiotemporal relationship, the electronic device may determine the spatiotemporal score of the target grouped historical vehicle picture determined in the embodiment shown in fig. 5 as the initial score of the target grouped historical vehicle picture according to the embodiment shown in fig. 5.

S802, aiming at each target grouping historical vehicle picture, according to the preset weight value of each relevant parameter, carrying out weighted calculation on the initial score of the target grouping historical vehicle picture corresponding to each relevant parameter, and taking the calculation result as the target score of the target grouping historical vehicle picture.

After the initial scores of the target grouped historical vehicle pictures corresponding to the relevant parameters are determined, the electronic equipment can perform weighted calculation on the initial scores of the target grouped historical vehicle pictures corresponding to the relevant parameters according to preset weights of the relevant parameters, and the calculation result is used as the target scores of the target grouped historical vehicle pictures.

For example, the preset weight of each relevant parameter may be: the similarity is 0.25, the attribute information is 0.4, and the spatiotemporal relationship is 0.35, when the initial score corresponding to the similarity is 0.8, the initial score corresponding to the attribute information is 0.8, and the initial score corresponding to the spatiotemporal relationship is 0.7, the target score of the target grouping historical vehicle picture is 0.8 × 0.25+0.8 × 0.4+0.7 × 0.35 — 0.765.

According to the embodiment of the invention, the target score of the target group historical vehicle picture can be determined according to various related parameters, so that the accuracy of determining the license plate information of the target vehicle can be improved.

Corresponding to the above method embodiment, the embodiment of the present invention also provides a corresponding device embodiment.

Fig. 9 is a license plate information determining apparatus according to an embodiment of the present invention, where the apparatus includes:

a first obtaining module 910, configured to obtain a target picture including a target vehicle;

the execution module 920 is configured to obtain a historical vehicle image set, and group the historical vehicle image set according to license plate information to obtain historical vehicle images of each group that include the same license plate information;

a processing module 930, configured to determine, according to relevant parameters of each vehicle picture included in each group of historical vehicle pictures and the target picture, a target grouped historical vehicle picture that meets a preset condition in a plurality of groups of historical vehicle pictures, and determine a target score of each target grouped historical vehicle picture; wherein the relevant parameters include at least one of: similarity, attribute information, and spatio-temporal relationships;

the determining module 940 is configured to determine the license plate information of the target group historical vehicle picture with the highest target score as the license plate information of the target vehicle.

The embodiment of the invention provides a license plate information determining device, which can acquire a historical vehicle picture set when acquiring a target picture, and grouping the historical vehicle picture sets according to the license plate information to obtain each group of historical vehicle pictures containing the same license plate information, then according to the relevant parameters of each vehicle picture and the target picture included in each group of historical vehicle pictures, determining a target grouping historical vehicle picture meeting a preset condition from a plurality of groups of historical vehicle pictures, and determining the target score of each target group historical vehicle picture, wherein the target score of each target group historical vehicle picture can represent the correlation degree of each target group historical vehicle picture and the target picture, and finally, and determining the license plate information of the target grouping historical vehicle picture with the highest target score as the license plate information of the target vehicle, so that the license plate information in the target picture can be determined.

As an implementation manner of the embodiment of the present invention, when the relevant parameter is a similarity, the processing module includes:

a first calculating sub-module (not shown in the figure) for calculating, for each group of historical vehicle pictures, a similarity between the target picture and each vehicle picture included in the group of historical vehicle pictures;

a first determining sub-module (not shown in the figure) for determining a first statistical index of the group of historical vehicle pictures according to the similarity between the target picture and each vehicle picture included in the group of historical vehicle pictures; wherein the first statistical indicator comprises at least one of: the method comprises the steps of obtaining a maximum similarity, a minimum similarity, an average similarity and a first mode, wherein the first mode is the occurrence frequency of the similarity with the largest occurrence frequency;

a first judging sub-module (not shown in the figure) for judging whether the group of historical vehicle pictures meets a preset condition according to a first statistical index of the group of historical vehicle pictures;

and a second determining sub-module (not shown in the figure) for determining the group of historical vehicle pictures as the target grouping historical vehicle pictures when the first judging sub-module judges that the group of historical vehicle pictures is yes.

As an implementation manner of the embodiment of the present invention, when the first statistical indicator includes a maximum similarity, a minimum similarity, an average similarity, and a first mode; the first determining submodule is specifically configured to execute at least one of:

As an implementation manner of the embodiment of the present invention, the processing module is specifically configured to, for each target group history vehicle picture, determine the maximum similarity corresponding to the target group history vehicle picture as a target score of the target group history vehicle picture.

As an implementation manner of the embodiment of the present invention, when the relevant parameter is attribute information, the processing module includes:

a second calculating sub-module (not shown in the figure) for comparing the attribute information of the target picture with the corresponding attribute information of each vehicle picture included in each group of historical vehicle pictures, and calculating the attribute score of each vehicle picture included in each group of historical vehicle pictures according to the comparison result;

a third determining sub-module (not shown in the figure) for determining a second statistical index of the group of historical vehicle pictures according to the attribute scores of the vehicle pictures included in the group of historical vehicle pictures; wherein the second statistical indicator comprises at least one of: the attribute score of each attribute is a maximum attribute score, a minimum attribute score, an average attribute score, and a second mode, wherein the second mode is the number of occurrences of the attribute score with the largest number of occurrences;

a second judging sub-module (not shown in the figure) for judging whether the group of historical vehicle pictures meets the preset condition according to a second statistical index of the group of historical vehicle pictures;

a fourth determining sub-module (not shown in the figure) for determining the group of historical vehicle pictures as the target grouping historical vehicle pictures when the second judging sub-module judges that the group of historical vehicle pictures is yes.

As an implementation manner of the embodiment of the present invention, when the second statistical indicator includes a maximum attribute score, a minimum attribute score, an average attribute score, and a second mode; the second judgment sub-module is specifically configured to perform at least one of the following:

As an implementation manner of the embodiment of the present invention, the processing module is specifically configured to, for each target group history vehicle picture, determine a maximum attribute score corresponding to the target group history vehicle picture as a target score of the target group history vehicle picture.

As an implementation manner of the embodiment of the present invention, when the relevant parameter is spatio-temporal information, the processing module includes:

a fifth determining sub-module (not shown in the figure) for determining the position information and the time information of the target picture, and the position information and the time information of each vehicle picture included in each group of historical vehicle pictures satisfying a preset time condition;

a third calculation submodule (not shown in the figure) for calculating, for each group of historical vehicle pictures, a difference value between the time information of the target picture and the time information of each vehicle picture included in the group of historical vehicle pictures;

an obtaining sub-module (not shown in the figure) for obtaining a time threshold between the position information of the target picture and the position information of each vehicle picture included in the group of historical vehicle pictures according to the time threshold between the locally stored position information;

a third determining submodule (not shown in the figure) for determining whether each difference value is greater than the corresponding time threshold;

a sixth determining sub-module (not shown in the figure) for determining the group of historical vehicle pictures as the target grouping historical vehicle pictures when the determination result of the third determining sub-module is yes.

As an implementation manner of the embodiment of the present invention, the processing module further includes:

a seventh determining sub-module (not shown in the figure) for determining, for each target grouping historical vehicle picture, a driving track of the vehicle corresponding to the target grouping historical vehicle picture according to the position information of each vehicle picture included in the target grouping historical vehicle picture;

a fourth calculating submodule (not shown in the figure) for determining the total number of times of the vehicle appearing at each position according to the driving track of the vehicle corresponding to the target grouping historical vehicle picture, and calculating the probability of the vehicle appearing at the position corresponding to the target picture according to the total number of times of the vehicle appearing at each position and the number of times of the vehicle appearing at the position corresponding to the target picture;

a fifth calculating sub-module (not shown in the figure) for calculating a time probability of the vehicle appearing at a position corresponding to the target picture according to the time information of each vehicle picture included in the target grouping history vehicle picture, the time information of the target picture, and a preset distribution function;

and an eighth determining submodule (not shown in the figure) for calculating the space-time score of the target grouped historical vehicle picture according to the occurrence probability of the vehicle at the corresponding position of the target picture and the time probability of the vehicle occurring at the corresponding position of the target picture, and determining the space-time score as the target score of the target grouped historical vehicle picture.

As an implementation manner of the embodiment of the present invention, the eighth determining sub-module is specifically configured to calculate a product of the occurrence probability and the time probability, and determine a calculation result as a space-time score of the target grouped historical vehicle picture.

As an implementation manner of the embodiment of the present invention, the apparatus further includes:

a second obtaining module (not shown in the figure), configured to obtain, for every two pieces of location information, a vehicle picture corresponding to the two pieces of location information, and time information corresponding to each vehicle picture;

an identification module (not shown in the figure) for identifying the vehicle pictures containing the same vehicle in the vehicle pictures corresponding to the two pieces of position information;

a calculating module (not shown in the figure) for calculating a difference value between the time information of each vehicle picture corresponding to one of the position information and the time information of each vehicle picture corresponding to the other position information for the vehicle pictures containing the same vehicle;

and a storage module (not shown in the figure) for determining a time threshold between the two pieces of location information according to the calculated difference and storing the time threshold locally.

As an implementation manner of the embodiment of the present invention, the storage module is specifically configured to:

determining the minimum value of the difference values as a time threshold value between the two pieces of position information;

determining a time threshold value between the two pieces of position information by adopting a quartile method according to the difference value; or

And determining a time threshold between the two pieces of position information by adopting a slope discrimination method according to the difference.

and an updating module (not shown in the figure) for periodically updating the time threshold between the locally stored location information according to a set time interval.

As an implementation manner of the embodiment of the present invention, when the related parameters include at least two items of similarity, attribute information, and a spatiotemporal relationship, the processing module includes:

a ninth determining sub-module (not shown in the figure) for determining the middle grouping historical vehicle picture corresponding to each relevant parameter according to the relevant parameter;

and the counting submodule (not shown in the figure) is used for counting the intermediate grouping historical vehicle pictures corresponding to all the relevant parameters in the intermediate grouping historical vehicle pictures corresponding to all the relevant parameters, and determining the counted intermediate grouping historical vehicle pictures as target grouping historical vehicle pictures.

a tenth determining submodule (not shown in the figure) for determining an initial score of each target grouping historical vehicle picture corresponding to each relevant parameter; wherein, corresponding to the relevant parameters, the initial score includes at least two of: similarity, attribute score, or spatio-temporal score;

and a sixth calculating sub-module (not shown in the figure) for, for each target group historical vehicle picture, performing weighted calculation on the initial score of the target group historical vehicle picture corresponding to each relevant parameter according to a preset weight of each relevant parameter, and taking the calculation result as the target score of the target group historical vehicle picture.

For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

Claims

1. A license plate information determination method is characterized by comprising the following steps:

acquiring a target picture containing a target vehicle;

according to relevant parameters of each vehicle picture and the target picture in each group of historical vehicle pictures, determining target grouped historical vehicle pictures meeting preset conditions in a plurality of groups of historical vehicle pictures, and determining target scores of the target grouped historical vehicle pictures; wherein the relevant parameters include at least one of: picture similarity, vehicle attribute information and vehicle spatiotemporal relationship;

2. The method according to claim 1, wherein when the related parameter is similarity, the step of determining a target grouped historical vehicle picture satisfying a preset condition among a plurality of groups of historical vehicle pictures according to the related parameter between each vehicle picture included in each group of historical vehicle pictures and the target picture comprises:

3. The method of claim 2, wherein when the first statistical indicator comprises a maximum similarity, a minimum similarity, an average similarity, and a first mode; the step of determining whether the group of historical vehicle pictures meets the preset condition according to the first statistical index of the group of historical vehicle pictures comprises at least one of the following steps:

4. The method of claim 2, wherein the step of determining a target score for each target group historical vehicle picture comprises:

5. The method according to claim 1, wherein when the related parameter is attribute information, the step of determining a target grouped historical vehicle picture satisfying a preset condition among a plurality of groups of historical vehicle pictures according to the related parameter between each vehicle picture included in each group of historical vehicle pictures and the target picture comprises:

6. The method of claim 5, wherein when the second statistical indicator comprises a maximum attribute score, a minimum attribute score, an average attribute score, and a second mode; the step of determining whether the group of historical vehicle pictures meets the preset condition according to the second statistical index of the group of historical vehicle pictures comprises at least one of the following steps:

7. The method of claim 5, wherein the step of determining a target score for each target group historical vehicle picture comprises:

8. The method according to claim 1, wherein when the related parameter is spatio-temporal information, the step of determining a target grouped historical vehicle picture satisfying a preset condition among a plurality of groups of historical vehicle pictures according to the related parameter between each vehicle picture included in each group of historical vehicle pictures and the target picture comprises:

9. The method of claim 8, wherein the step of determining a target score for each target group historical vehicle picture comprises:

10. The method according to claim 9, wherein the step of calculating the spatiotemporal score of the target grouped historical vehicle picture according to the probability of the vehicle appearing at the corresponding position of the target picture and the probability of the vehicle appearing at the corresponding position of the target picture comprises:

11. The method of claim 8, wherein storing the time threshold between location information comprises:

12. The method of claim 11, wherein determining the time threshold between the two location information based on the calculated difference comprises:

13. The method of claim 11, further comprising:

and periodically updating the time threshold value between the locally stored position information according to a set time interval.

14. The method according to claim 1, wherein when the relevant parameters include at least two of similarity, attribute information, and spatiotemporal relationship, the step of determining a target grouped historical vehicle picture satisfying a preset condition among a plurality of groups of historical vehicle pictures according to the relevant parameters of each vehicle picture included in each group of historical vehicle pictures and the target picture comprises:

respectively determining intermediate grouping historical vehicle pictures corresponding to the relevant parameters according to the relevant parameters;

and counting the intermediate grouping historical vehicle pictures corresponding to the relevant parameters in the intermediate grouping historical vehicle pictures corresponding to the relevant parameters, and determining the counted intermediate grouping historical vehicle pictures as target grouping historical vehicle pictures.

15. The method of claim 14, wherein the step of determining a target score for each target group historical vehicle picture comprises:

determining initial scores of the target grouped historical vehicle pictures corresponding to the relevant parameters; wherein, corresponding to the relevant parameters, the initial score includes at least two of: similarity, attribute score, or spatio-temporal score;

and for each target grouping historical vehicle picture, carrying out weighted calculation on the initial score of the target grouping historical vehicle picture corresponding to each relevant parameter according to the preset weight of each relevant parameter, and taking the calculation result as the target score of the target grouping historical vehicle picture.

16. A license plate information determination apparatus, characterized in that the apparatus comprises:

the processing module is used for determining target grouped historical vehicle pictures meeting preset conditions in a plurality of groups of historical vehicle pictures according to relevant parameters of the target pictures and the vehicle pictures included in the historical vehicle pictures, and determining target scores of the target grouped historical vehicle pictures; wherein the relevant parameters include at least one of: picture similarity, vehicle attribute information and vehicle spatiotemporal relationship;

17. The apparatus of claim 16, wherein when the related parameter is similarity, the processing module comprises:

18. The apparatus of claim 17, wherein when the first statistical indicator comprises a maximum similarity, a minimum similarity, an average similarity, and a first mode; the first determining submodule is specifically configured to execute at least one of:

19. The apparatus according to claim 17, wherein the processing module is specifically configured to determine, for each target group history vehicle picture, a maximum similarity corresponding to the target group history vehicle picture as a target score of the target group history vehicle picture.

20. The apparatus of claim 16, wherein when the related parameter is attribute information, the processing module comprises:

the second calculation submodule is used for comparing the attribute information of the target picture with the corresponding attribute information of each vehicle picture in each group of historical vehicle pictures and calculating the attribute score of each vehicle picture in each group of historical vehicle pictures according to the comparison result;

the third determining submodule is used for determining a second statistical index of the group of historical vehicle pictures according to the attribute scores of the vehicle pictures in the group of historical vehicle pictures; wherein the second statistical indicator comprises at least one of: the attribute score of each attribute is a maximum attribute score, a minimum attribute score, an average attribute score, and a second mode, wherein the second mode is the number of occurrences of the attribute score with the largest number of occurrences;

the second judgment submodule is used for judging whether the group of historical vehicle pictures meets the preset condition or not according to a second statistical index of the group of historical vehicle pictures;

and the fourth determining submodule is used for determining the group of historical vehicle pictures as the target grouping historical vehicle pictures when the judgment result of the second judging submodule is yes.

21. The apparatus of claim 20, wherein when the second statistical indicator comprises a maximum attribute score, a minimum attribute score, an average attribute score, and a second mode; the second judgment sub-module is specifically configured to perform at least one of the following:

22. The apparatus according to claim 20, wherein the processing module is specifically configured to determine, for each target group history vehicle picture, a maximum attribute score corresponding to the target group history vehicle picture as a target score of the target group history vehicle picture.

23. The apparatus of claim 16, wherein when the relevant parameter is spatio-temporal information, the processing module comprises:

the fifth determining submodule is used for determining the position information and the time information of the target picture and the position information and the time information of each vehicle picture in each group of historical vehicle pictures meeting the preset time condition;

the third calculation submodule is used for calculating the difference value of the time information of the target picture and the time information of each vehicle picture included in each group of historical vehicle pictures aiming at each group of historical vehicle pictures;

the acquisition submodule is used for acquiring the time threshold between the position information of the target picture and the position information of each vehicle picture in the group of historical vehicle pictures according to the time threshold between the locally stored position information;

the third judgment submodule is used for judging whether each difference value is larger than the corresponding time threshold value;

and the sixth determining submodule is used for determining the group of historical vehicle pictures as the target grouping historical vehicle pictures when the judgment result of the third judging submodule is positive.

24. The apparatus of claim 23, wherein the processing module further comprises:

the seventh determining submodule is used for determining the driving track of the vehicle corresponding to each target grouping historical vehicle picture according to the position information of each vehicle picture included in each target grouping historical vehicle picture;

the fourth calculating submodule is used for determining the total times of the vehicles at each position according to the driving tracks of the vehicles corresponding to the target grouping historical vehicle pictures, and calculating the probability of the vehicles appearing at the positions corresponding to the target pictures according to the total times of the vehicles appearing at each position and the times of the vehicles appearing at the positions corresponding to the target pictures;

the fifth calculation submodule is used for calculating the time probability of the vehicle appearing at the corresponding position of the target picture according to the time information of each vehicle picture included in the target grouping historical vehicle picture, the time information of the target picture and a preset distribution function;

and the eighth determining submodule is used for calculating the space-time score of the target grouping historical vehicle picture according to the appearance probability of the vehicle at the corresponding position of the target picture and the appearance time probability of the vehicle at the corresponding position of the target picture, and determining the space-time score as the target score of the target grouping historical vehicle picture.

25. The apparatus according to claim 24, wherein the eighth determining sub-module is configured to calculate a product of the occurrence probability and the time probability, and determine the calculated result as a spatiotemporal score of the target grouped historical vehicle picture.

26. The apparatus of claim 23, further comprising:

the second acquisition module is used for acquiring vehicle pictures corresponding to two pieces of position information and time information corresponding to each vehicle picture aiming at every two pieces of position information;

the identification module is used for identifying the vehicle pictures containing the same vehicle in the vehicle pictures corresponding to the two pieces of position information;

the calculating module is used for calculating the difference value of the time information of each vehicle picture corresponding to one piece of position information and the time information of each vehicle picture corresponding to the other piece of position information aiming at the vehicle pictures containing the same vehicle;

and the storage module is used for determining a time threshold value between the two pieces of position information according to the calculated difference value and storing the time threshold value locally.

27. The apparatus of claim 26, wherein the storage module is specifically configured to:

28. The apparatus of claim 26, further comprising:

and the updating module is used for periodically updating the time threshold between the locally stored position information according to a set time interval.

29. The apparatus of claim 16, wherein when the related parameters include at least two of similarity, attribute information, and spatiotemporal relationship, the processing module comprises:

a ninth determining submodule, configured to determine, according to each related parameter, an intermediate group historical vehicle picture corresponding to the related parameter;

and the counting submodule is used for counting the intermediate grouping historical vehicle pictures corresponding to all the relevant parameters in the intermediate grouping historical vehicle pictures corresponding to all the relevant parameters, and determining the counted intermediate grouping historical vehicle pictures as target grouping historical vehicle pictures.

30. The apparatus of claim 29, wherein the processing module further comprises:

the tenth determining submodule is used for determining the initial scores of the target grouped historical vehicle pictures corresponding to the relevant parameters; wherein, corresponding to the relevant parameters, the initial score includes at least two of: similarity, attribute score, or spatio-temporal score;

and the sixth calculating submodule is used for carrying out weighted calculation on the initial scores of the target grouping historical vehicle pictures corresponding to the relevant parameters according to the preset weight values of the relevant parameters aiming at each target grouping historical vehicle picture, and taking the calculation result as the target score of the target grouping historical vehicle picture.