阅读说明：本技术 车辆行驶状况识别方法、装置及电子设备 (Vehicle running condition identification method and device and electronic equipment ) 是由 毛河 杨勇 石永禄 高枫 朱彬 于 2019-09-24 设计创作，主要内容包括：本申请提供了一种车辆行驶状况识别方法、装置及电子设备,其中,该车辆行驶状况识别方法包括：根据待识别现场图像集确定第一基准点组,待识别现场图像集为第一指定时间段采集目标区域得到的多张图像,第一基准点组包括待识别现场图像集中的每一张图像的车辆区域的参考中心；根据待识别现场图像集确定第二基准点,第二基准点为所述待识别现场图像集中其中一张图像的车辆区域的参考中心；根据第一基准点组及第二基准点确定待识别现场图像集中的目标车辆的移动方向；当判断移动方向与设定方向相反时,则计算目标车辆的逆向行驶距离；当判断逆向行驶距离大于第一设定值时,则输出逆行结果。(The application provides a vehicle running condition identification method, a vehicle running condition identification device and electronic equipment, wherein the vehicle running condition identification method comprises the following steps: determining a first reference point group according to a to-be-identified field image set, wherein the to-be-identified field image set is a plurality of images acquired by acquiring a target area in a first specified time period, and the first reference point group comprises a reference center of a vehicle area of each image in the to-be-identified field image set; determining a second reference point according to the field image set to be identified, wherein the second reference point is a reference center of a vehicle area of one image in the field image set to be identified; determining the moving direction of a target vehicle in the field image set to be identified according to the first reference point group and the second reference point; when the moving direction is opposite to the set direction, calculating the reverse driving distance of the target vehicle; and when the reverse driving distance is judged to be larger than the first set value, outputting a reverse driving result.)

1. A vehicle running condition recognition method characterized by comprising:

determining a first reference point group according to a to-be-identified field image set, wherein the to-be-identified field image set is a plurality of images acquired by acquiring a target area in a first specified time period, and the first reference point group comprises a reference center of a vehicle area of each image in the to-be-identified field image set;

determining a second reference point according to the field image set to be identified, wherein the second reference point is a reference center of a vehicle area of one image in the field image set to be identified;

determining the moving direction of a target vehicle in the field image set to be identified according to the first reference point group and the second reference point;

when the moving direction is opposite to the set direction, calculating the reverse driving distance of the target vehicle;

and outputting a reverse driving result when the reverse driving distance is judged to be larger than a first set value.

2. The method of claim 1, further comprising:

when the moving direction is judged to be the same as the set direction, calculating the forward moving distance of the target vehicle according to the first reference point group and the second reference point, and when the forward moving distance is judged to be larger than a second set value, taking the center of the vehicle area of the current frame image in the scene image set to be identified as an updated second reference point; or the like, or, alternatively,

and when the moving direction is opposite to the set direction, taking the center of the vehicle area of the previous frame image of the current frame image in the field image set to be identified as the updated second reference point.

3. The method of claim 1, wherein the target vehicle is matched with a first identification code, and the step of calculating the reverse driving distance of the target vehicle comprises:

judging whether the vehicle track corresponding to the first identification code is in an image collected in a second appointed time period in the to-be-identified field image set, wherein the second appointed time period is a time period after a first time node in the first appointed time period;

when the vehicle track corresponding to the first identification code is not in the images collected in the second appointed time period in the to-be-identified field image set, judging whether a second vehicle which is identified by a second identification code and only appears in the images collected in the second appointed time period in the to-be-identified field image set exists;

when the second vehicle exists, acquiring second running data of the second vehicle in the second specified time period and first running data of the target vehicle in the first time period;

determining whether the second vehicle is the target vehicle according to the second running data and first running data, wherein the first running data is the running data of the target vehicle in the first time period;

and when the second vehicle is the target vehicle, calculating the reverse driving distance of the target vehicle according to the first driving data and the second driving data.

4. The method of claim 3, wherein the step of determining whether the second vehicle is the target vehicle based on the second travel data and the first travel data comprises:

determining the disappearing position of the target vehicle in the first running data according to the field image set to be identified; determining the appearance position of a second vehicle in the second driving parameters according to the images collected by the to-be-identified field images in a second specified time period; when the position difference between the disappearing position and the appearing position is smaller than a third set value, determining whether the second vehicle is the target vehicle; alternatively, the first and second electrodes may be,

determining the disappearance time of the target vehicle in the first running data according to the disappearance position; determining the appearance time of a second vehicle in the second driving data according to the appearance position; when the time difference between the disappearance time and the appearance time is smaller than a fourth set value, determining that the second vehicle is the target vehicle; alternatively, the first and second electrodes may be,

and according to whether the pixel distance of the center of the vehicle area in the image before the target vehicle disappears and the pixel distance of the center of the vehicle area in the image when the second vehicle appears in the image is smaller than a fifth set value or not, judging that the second vehicle is the target vehicle when the pixel distance is smaller than the fifth set value or not.

5. The method of claim 3, wherein the step of determining whether the second vehicle is the target vehicle based on the second travel data and the first travel data comprises:

determining the disappearing position of the target vehicle in the first running data according to the field image set to be identified;

determining the disappearance time of the target vehicle in the first running data according to the disappearance position;

determining the appearance position of a second vehicle in the second driving parameters according to the images collected by the to-be-identified field images in the second appointed time period;

determining the appearance time of a second vehicle in the second driving data according to the appearance position;

and when the position difference between the disappearance position and the appearance position is smaller than a third set value and the time difference between the disappearance time and the appearance time is smaller than a fourth set value, determining that the second vehicle is the target vehicle.

6. The method of claim 3, wherein the step of calculating a reverse travel distance of the target vehicle from the first travel data and the second travel data comprises:

calculating a forward driving distance and a first reverse driving distance of the target vehicle according to the first driving data;

calculating a second reverse travel distance of the second vehicle according to the second travel data;

and calculating the reverse driving distance of the target vehicle according to the first reverse driving distance and the second reverse driving distance.

7. The method of claim 3, further comprising:

replacing the second identification code identifying the second vehicle with a first identification code when the second vehicle is determined to be the target vehicle.

8. A vehicle running condition recognition device characterized by comprising:

the system comprises a first determination module, a second determination module and a third determination module, wherein the first determination module is used for determining a first reference point group according to a to-be-identified field image set, the first reference point group is a reference center of a vehicle area of each image in the to-be-identified field image set, and the to-be-identified field image set is a plurality of images acquired by acquiring a target area in a first specified time period;

the second determining module is used for determining a second reference point according to the field image set to be identified, wherein the second reference point is a reference center of each image in the field image to be identified;

a third determining module, configured to determine a moving direction of a target vehicle in the to-be-identified live image set according to the first reference point group and the second reference point;

the calculation module is used for calculating the reverse driving distance of the target vehicle when the moving direction is opposite to the set direction;

and the output module is used for outputting a reverse driving result when the reverse driving distance is judged to be larger than a first set value.

9. An electronic device, comprising: a processor, a memory storing machine-readable instructions executable by the processor, the machine-readable instructions when executed by the processor performing the steps of the method of any of claims 1 to 7 when the electronic device is run.

10. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, is adapted to carry out the steps of the method according to any one of claims 1 to 7.

Technical Field

The application relates to the technical field of image processing, in particular to a vehicle driving condition identification method and device and electronic equipment.

Background

Traffic accidents are one of the more important causes of death in accidents, most of which are caused by illegal driving. On the basis, more and more monitoring cameras are arranged on each road to monitor the running condition of vehicles on the road. In the case of a vehicle driving in the wrong direction, the related staff mainly checks and identifies the monitoring camera.

Disclosure of Invention

In view of the above, an object of the embodiments of the present application is to provide a method and an apparatus for identifying a vehicle driving condition, and an electronic device. The vehicle can be identified by image identification, so that the vehicle can be identified quickly and effectively.

In a first aspect, an embodiment of the present application provides a vehicle driving condition identification method, including:

determining a first reference point group according to a to-be-identified field image set, wherein the to-be-identified field image set is a plurality of images acquired by acquiring a target area in a first specified time period, and the first reference point group comprises a reference center of a vehicle area of each image in the to-be-identified field image set;

determining a second reference point according to the field image set to be identified, wherein the second reference point is a reference center of a vehicle area of one image in the field image set to be identified;

determining the moving direction of a target vehicle in the field image set to be identified according to the first reference point group and the second reference point;

when the moving direction is opposite to the set direction, calculating the reverse driving distance of the target vehicle;

and outputting a reverse driving result when the reverse driving distance is judged to be larger than a first set value.

With reference to the first aspect, an embodiment of the present application provides a first possible implementation manner of the first aspect, where: the method further comprises the following steps:

when the moving direction is judged to be the same as the set direction, calculating the forward moving distance of the target vehicle according to the first reference point group and the second reference point, and when the forward moving distance is judged to be larger than a second set value, taking the center of the current frame image in the scene image set to be identified as the current second reference point; or the like, or, alternatively,

and when the moving direction is opposite to the set direction, taking the center of the previous frame image of the current frame image in the field image set to be identified as a current second reference point.

According to the vehicle running condition identification method provided by the embodiment of the application, different calculation modes can be adopted according to the identified condition of the target vehicle so as to better identify the running condition of the vehicle.

With reference to the first aspect, an embodiment of the present application provides a second possible implementation manner of the first aspect, where: the target vehicle is matched with a first identification code, and the step of calculating the reverse driving distance of the target vehicle comprises the following steps:

judging whether the vehicle track corresponding to the first identification code is in an image collected in a second appointed time period in the to-be-identified field image set, wherein the second appointed time period is a time period after a first time node in the first appointed time period;

when the vehicle track corresponding to the first identification code is not in the images collected in the second appointed time period in the to-be-identified field image set, judging whether a second vehicle which is identified by a second identification code and only appears in the images collected in the second appointed time period in the to-be-identified field image set exists;

when the second vehicle exists, acquiring second running data of the second vehicle in the second specified time period and first running data of the target vehicle in the first time period;

determining whether the second vehicle is the target vehicle according to the second running data and first running data, wherein the first running data is the running data of the target vehicle in the first time period;

and when the second vehicle is the target vehicle, calculating the reverse driving distance of the target vehicle according to the first driving data and the second driving data.

According to the vehicle running condition identification method provided by the embodiment of the application, the situation that the vehicles are possibly identified as other vehicles when the vehicles are shielded by the shielding object is considered, and on the basis, the identification of whether the two continuous vehicles are the same vehicle is carried out, so that wrong identification of reverse running identification caused by jumping of the identification codes is reduced.

With reference to the second possible implementation manner of the first aspect, an embodiment of the present application provides a fourth possible implementation manner of the first aspect, where the step of determining whether the second vehicle is the target vehicle according to the second travel data and the first travel data includes:

determining the disappearing position of the target vehicle in the first running data according to the field image set to be identified; determining the appearance position of a second vehicle in the second driving parameters according to the images collected by the to-be-identified field images in a second specified time period; when the position difference between the disappearing position and the appearing position is smaller than a third set value, determining whether the second vehicle is the target vehicle; alternatively, the first and second electrodes may be,

determining the disappearance time of the target vehicle in the first running data according to the disappearance position; determining the appearance time of a second vehicle in the second driving data according to the appearance position; when the time difference between the disappearance time and the appearance time is smaller than a fourth set value, determining that the second vehicle is the target vehicle; alternatively, the first and second electrodes may be,

and according to whether the pixel distance of the center of the vehicle area in the image before the target vehicle disappears and the pixel distance of the center of the vehicle area in the image when the second vehicle appears in the image is smaller than a fifth set value or not, judging that the second vehicle is the target vehicle when the pixel distance is smaller than the fifth set value or not.

According to the vehicle running state identification method provided by the embodiment of the application, two vehicles which appear continuously in a short time and the connection distance between the two vehicles are also short, the two vehicles can be the same vehicle, and through comparison of the appearance time and the appearance distance, whether the two vehicles are the same vehicle can be identified and determined, so that misjudgment of the running condition of a target vehicle caused by jumping of the identification code can be reduced.

With reference to the second possible implementation manner of the first aspect, an embodiment of the present application provides a third possible implementation manner of the first aspect, where the step of determining whether the second vehicle is the target vehicle according to the second travel data and the first travel data includes:

determining the disappearing position of the target vehicle in the first running data according to the field image set to be identified;

determining the disappearance time of the target vehicle in the first running data according to the disappearance position;

determining the appearance position of a second vehicle in the second driving parameters according to the images collected by the to-be-identified field images in the second appointed time period;

determining the appearance time of a second vehicle in the second driving data according to the appearance position;

and when the position difference between the disappearance position and the appearance position is smaller than a third set value and the time difference between the disappearance time and the appearance time is smaller than a fourth set value, determining that the second vehicle is the target vehicle.

With reference to the second possible implementation manner of the first aspect, an embodiment of the present application provides a fifth possible implementation manner of the first aspect, where the step of calculating a reverse travel distance of the target vehicle according to the first travel data and the second travel data includes:

calculating a forward driving distance and a first reverse driving distance of the target vehicle according to the first driving data;

calculating a second reverse travel distance of the second vehicle according to the second travel data;

and calculating the reverse driving distance of the target vehicle according to the first reverse driving distance and the second reverse driving distance.

According to the vehicle running condition identification method provided by the embodiment of the application, the reverse running distance of the target vehicle is determined by combining the reverse running distances before and after the jump of the identification code of the vehicle, so that the reverse running distance of the target vehicle can be obtained more accurately.

With reference to the second possible implementation manner of the first aspect, an embodiment of the present application provides a sixth possible implementation manner of the first aspect, where the method further includes:

replacing the second identification code identifying the second vehicle with a first identification code when the second vehicle is determined to be the target vehicle.

According to the vehicle running condition identification method provided by the embodiment of the application, when the second vehicle is determined to be the target vehicle, the identifier of the second vehicle can be replaced by the first identification code, so that the accuracy of the subsequent identification data of the target vehicle can be improved.

In a second aspect, an embodiment of the present application further provides a vehicle driving condition recognition apparatus, including:

the system comprises a first determination module, a second determination module and a third determination module, wherein the first determination module is used for determining a first reference point group according to a to-be-identified field image set, the first reference point group is a reference center of a vehicle area of each image in the to-be-identified field image set, and the to-be-identified field image set is a plurality of images acquired by acquiring a target area in a first specified time period;

the second determining module is used for determining a second reference point according to the field image set to be identified, wherein the second reference point is a reference center of each image in the field image to be identified;

a third determining module, configured to determine a moving direction of a target vehicle in the to-be-identified live image set according to the first reference point group and the second reference point;

the calculation module is used for calculating the reverse driving distance of the target vehicle when the moving direction is opposite to the set direction;

and the output module is used for outputting a reverse driving result when the reverse driving distance is judged to be larger than a first set value.

In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor, a memory storing machine-readable instructions executable by the processor, the machine-readable instructions, when executed by the processor, performing the steps of the method of the first aspect described above, or any possible implementation of the first aspect, when the electronic device is run.

In a fourth aspect, this embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the method in the first aspect or any one of the possible implementation manners of the first aspect.

According to the vehicle driving condition identification method, the vehicle driving condition identification device, the electronic equipment and the computer readable storage medium, the movement condition of the vehicle is identified by the collected image set, whether the vehicle is in a retrograde motion mode is determined according to the movement condition, further, the calculated retrograde motion distance is combined, and the vehicle driving condition is determined to be in the retrograde motion mode after the retrograde motion distance reaches the first set value, so that the accuracy of retrograde motion identification can be improved, and false identification is reduced.

In order to make the aforementioned objects, features and advantages of the present application more comprehensible, embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

Fig. 1 is an environment schematic diagram of a traffic monitoring system according to an embodiment of the present application.

Fig. 2 is a block diagram of an electronic device according to an embodiment of the present disclosure.

Fig. 3 is a flowchart of a vehicle driving condition identification method according to an embodiment of the present application.

Fig. 4 is a detailed flowchart of step 504 of a vehicle driving condition identification method according to an embodiment of the present application.

Fig. 5 is a functional block diagram of a vehicle driving condition recognition device according to an embodiment of the present application.

Detailed Description

The technical solution in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.