CN108022428B - Vehicle identification method and device - Google Patents
Vehicle identification method and device Download PDFInfo
- Publication number
- CN108022428B CN108022428B CN201610943479.1A CN201610943479A CN108022428B CN 108022428 B CN108022428 B CN 108022428B CN 201610943479 A CN201610943479 A CN 201610943479A CN 108022428 B CN108022428 B CN 108022428B
- Authority
- CN
- China
- Prior art keywords
- attribute information
- determining
- target
- vehicle
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention discloses a vehicle identification method and a vehicle identification device, wherein attribute information of a vehicle, and the time and the position of image acquisition of the vehicle are correspondingly stored in a database; when a traffic accident occurs, determining a first target time range and a target area according to incident time and incident place; according to the determined first target time range and the target area, determining attribute information of the matched alternative vehicle in a database; counting the occurrence times of the same attribute information in the determined attribute information of the candidate vehicles, and determining the attribute information of which the occurrence times is greater than a first preset threshold value as the candidate attribute information; and determining the target vehicle in the vehicles corresponding to the candidate attribute information. Therefore, the threshold is set according to the occurrence frequency of the attribute information, a large part of attribute information is filtered, the target vehicle is determined in the vehicles corresponding to the residual attribute information, only the target vehicle is checked subsequently, and the workload of identifying the troubling vehicle is reduced.
Description
Technical Field
The invention relates to the technical field of video monitoring, in particular to a vehicle identification method and device.
Background
In the process of handling traffic accidents, the image collected by the monitoring device is often used to identify the offending vehicle. If the incident place is provided with the monitoring equipment, the accident-related image can be directly acquired, and the incident vehicle can be identified according to the image. If the incident site is not equipped with a monitoring device, the offending vehicle is identified by images captured by the monitoring devices in the vicinity of the incident site.
The specific scheme of identifying the offending vehicle by means of images collected by monitoring devices in the vicinity of the incident site may include: determining the monitoring equipment installed at a gate near an incident place as target monitoring equipment; determining a time range associated with the incident; acquiring an image acquired by the target monitoring equipment within the time range; and manually checking the vehicles in the acquired images one by one to identify the vehicles causing the trouble.
By applying the scheme, a plurality of target monitoring devices are usually arranged, vehicles in a large number of images acquired by the plurality of target monitoring devices are manually checked one by one, and the workload is very large.
Disclosure of Invention
The embodiment of the invention aims to provide a vehicle identification method and a vehicle identification device, which can reduce the workload of identifying a troubling vehicle.
In order to achieve the above object, an embodiment of the present invention discloses a vehicle identification method, including:
determining a first target time range and a target area according to the incident time and the incident place;
determining attribute information of the alternative vehicle corresponding to the first target time range and the target area according to attribute information of the vehicle, the time and the position of image acquisition of the vehicle, which are correspondingly stored in a database;
counting the occurrence times of the same attribute information in the determined attribute information of the candidate vehicles;
determining the attribute information with the occurrence frequency larger than a first preset threshold value as candidate attribute information;
and determining a target vehicle in the vehicles corresponding to the candidate attribute information.
Optionally, before the step of determining the first target time range and the target area, the method further includes:
acquiring a vehicle image acquired by monitoring equipment and an acquisition time and an acquisition position corresponding to the image;
analyzing the image, and determining attribute information of the vehicle in the image;
and correspondingly storing the determined attribute information, the acquisition time and the acquisition position corresponding to the image into a database.
Optionally, the step of determining the first target time range and the target area according to the incident time and the incident location may include:
determining a first preset time period before the incident time as a first target time range;
and determining an area, the distance between which and the incident point is within a second preset threshold value, as a target area, or determining an area covered by a preset number of checkpoints, the distance between which and the incident point is closest, as the target area.
Optionally, the step of determining a target vehicle from the vehicles corresponding to the candidate attribute information includes:
and determining the vehicle corresponding to the candidate attribute information as a target vehicle.
Optionally, the step of determining a target vehicle from the vehicles corresponding to the candidate attribute information includes:
determining a second preset time period after the incident time as a second target time range;
searching the database for non-target attribute information of the vehicle of which the acquisition time is within the second target time range and the acquisition position is within the target area;
deleting non-target attribute information existing in the determined candidate attribute information;
and determining the vehicles corresponding to the residual candidate attribute information as target vehicles.
Optionally, the step of determining a target vehicle from the vehicles corresponding to the candidate attribute information includes:
determining a third preset time period after the incident time as a third target time range;
judging whether candidate attribute information of which the acquisition time is within the third target time range and the acquisition position is within the target area is searched in the database;
if yes, deleting the searched candidate attribute information, and determining the vehicles corresponding to the remaining candidate attribute information as target vehicles.
Optionally, the step of counting the number of occurrences of the same attribute information in the determined attribute information of the candidate vehicle may include:
determining the same attribute information as one group from among the determined attribute information of the candidate vehicles;
for each group, judging whether the difference value of the acquisition moments corresponding to every two attribute information in the group is smaller than a third preset threshold value or not;
if yes, deleting one attribute information of the two attribute information from the group;
and counting the number of the residual attribute information in the group, and determining the number as the occurrence frequency of the attribute information in the group.
Optionally, after the step of determining the vehicle corresponding to the attribute information with the occurrence frequency greater than the first preset threshold as the target vehicle, the method may further include:
sorting the attribute information corresponding to each target vehicle according to the acquisition time and/or the acquisition position and/or the occurrence frequency corresponding to the attribute information;
and sequentially outputting attribute information corresponding to each target vehicle according to the sequencing result.
In order to achieve the above object, an embodiment of the present invention discloses a vehicle identification device, including:
the first determining module is used for determining a first target time range and a target area according to the incident time and the incident place;
the second determination module is used for determining the attribute information of the alternative vehicle corresponding to the first target time range and the target area according to the attribute information of the vehicle, the time and the position of image acquisition of the vehicle, which are correspondingly stored in the database;
the statistical module is used for counting the occurrence times of the same attribute information in the determined attribute information of the alternative vehicles;
the third determining module is used for determining the attribute information of which the occurrence times is greater than the first preset threshold value as candidate attribute information;
and the fourth determining module is used for determining the target vehicle in the vehicles corresponding to the candidate attribute information.
Optionally, the apparatus may further include:
the acquisition module is used for acquiring a vehicle image acquired by monitoring equipment and an acquisition time and an acquisition position corresponding to the image;
the fifth determining module is used for analyzing and processing the image and determining the attribute information of the vehicle in the image;
and the storage module is used for correspondingly storing the determined attribute information, the acquisition time and the acquisition position corresponding to the image into a database.
Optionally, the first determining module may include:
the first determining submodule is used for determining a first preset time period before the incident time as a first target time range;
and the second determining submodule is used for determining an area, which is away from the incident point by a second preset threshold value, as a target area, or determining an area covered by a preset number of checkpoints, which are closest to the incident point, as the target area.
Optionally, the fourth determining module may be specifically configured to:
and determining the vehicle corresponding to the candidate attribute information as a target vehicle.
Optionally, the fourth determining module may be specifically configured to:
determining a second preset time period after the incident time as a second target time range;
searching the database for non-target attribute information of the vehicle of which the acquisition time is within the second target time range and the acquisition position is within the target area;
deleting non-target attribute information existing in the determined candidate attribute information;
and determining the vehicles corresponding to the residual candidate attribute information as target vehicles.
Optionally, the fourth determining module may be specifically configured to:
determining a third preset time period after the incident time as a third target time range;
judging whether candidate attribute information of which the acquisition time is within the third target time range and the acquisition position is within the target area is searched in the database;
if yes, deleting the searched candidate attribute information, and determining the vehicles corresponding to the remaining candidate attribute information as target vehicles.
Optionally, the statistical module may be specifically configured to:
determining the same attribute information as one group from among the determined attribute information of the candidate vehicles;
for each group, judging whether the difference value of the acquisition moments corresponding to every two attribute information in the group is smaller than a third preset threshold value or not;
if yes, deleting one attribute information of the two attribute information from the group;
and counting the number of the residual attribute information in the group, and determining the number as the occurrence frequency of the attribute information in the group.
Optionally, the apparatus may further include:
the sorting module is used for sorting the attribute information corresponding to each target vehicle according to the acquisition time and/or the acquisition position and/or the occurrence frequency corresponding to the attribute information;
and the output module is used for sequentially outputting the attribute information corresponding to each target vehicle according to the sequencing result.
By applying the embodiment of the invention, the attribute information of the vehicle, the time and the position of image acquisition of the vehicle are correspondingly stored in the database; when a traffic accident occurs, determining a first target time range and a target area according to incident time and incident place; according to the determined first target time range and the target area, determining attribute information of the matched alternative vehicle in a database; counting the occurrence times of the same attribute information in the determined attribute information of the candidate vehicles, and determining the attribute information of which the occurrence times is greater than a first preset threshold value as the candidate attribute information; and determining a target vehicle in the vehicles corresponding to the candidate attribute information. Therefore, the threshold is set according to the occurrence frequency of the attribute information, a large part of attribute information is filtered, the target vehicle is determined in the vehicles corresponding to the residual attribute information, only the target vehicle is checked subsequently, and the workload of identifying the troubling vehicle is reduced.
Of course, it is not necessary for any product or method of practicing the invention to achieve all of the above-described advantages at the same time.
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 schematic flow chart of a vehicle identification method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a vehicle identification device according to an embodiment of the present invention.
Detailed Description
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.
In order to solve the above technical problems, embodiments of the present invention provide a vehicle identification method and apparatus, which can be applied to various electronic devices such as a computer and a tablet computer, and are not limited specifically. First, a vehicle identification method according to an embodiment of the present invention will be described in detail.
Fig. 1 is a vehicle identification method according to an embodiment of the present invention, including:
s101: and determining a first target time range and a target area according to the incident time and the incident place.
This step may include:
determining a first preset time period before the incident time as a first target time range;
and determining an area, the distance between which and the incident point is within a second preset threshold value, as a target area, or determining an area covered by a preset number of checkpoints, the distance between which and the incident point is closest, as the target area.
The scheme needs to identify the suspicious traffic-causing vehicles, and only the suspicious traffic-causing vehicles are subsequently checked so as to reduce the workload of identifying the traffic-causing vehicles. The offending vehicle can be understood as an offending vehicle of a traffic accident, or an offending vehicle of another event, which is not limited herein. The following description will be given taking a traffic accident as an example.
Assume 2016 month 8, 30 am 11: 25, if a traffic accident occurs at site a, then 2016, 8, 30, 11 am: a first preset time period before 25 is determined as the first target time range. The first preset time period may be set according to actual conditions, such as one week, two weeks, one month, etc., and is assumed to be two weeks. That is, 16/2016/8/2016-30/8/2016 are determined as the first target time range.
The following describes the manner in which the target area is determined:
the second preset threshold is a distance threshold, and is assumed to be 1km, that is, a circle is drawn with the point a as the center and 1km as the radius, and the area covered by the circle can be determined as the target area.
The area covered by a preset number of checkpoints closest to the point a may also be determined as the target area. Assuming that the preset number is 3, the distance between the bayonet 1 and the point A is 0.5km, the distance between the bayonet 2 and the point A is 0.2km, the distance between the bayonet 3 and the point A is 1km, the distance between the bayonet 4 and the point A is 0.8km, and the distance between the bayonet 5 and the point A is 1.2 km. The checkpoints are sorted from near to far according to the distance from the point A, and the sorting result is as follows: bayonet 2, bayonet 1, bayonet 4, bayonet 3, bayonet 5. The region covered by the front 3 bayonets (bayonets 2, 1, and 4) is determined as a target region.
Of course, the levels of the bayonets in different directions may also be determined with the point a as the center of the circle, for example, the level of the bayonets closest to the point a is 1 on the east side of the point a, and the levels of the bayonets closest to the point a are 2 … … except the bayonets with the level 1, and so on; on the west side of the point A, the bayonet level closest to the point A is 1, the bayonet levels closest to the point A except the bayonet level of 1 are 2 … …, and the like; in this way, the level of each bayonet near the A site can be determined. And determining the area covered by the bayonet of the preset level as a target area. Assuming that the preset level is 2, determining the distance between the bayonet of each level 2 and the point a, determining a circle by taking the determined maximum distance as a radius and the point a as a center, and determining the area covered by the circle as the target area.
There are many ways to determine the target region, and the details are not repeated here.
S102: and determining the attribute information of the alternative vehicle corresponding to the first target time range and the target area according to the attribute information of the vehicle, the time and the position of image acquisition of the vehicle, which are correspondingly stored in the database.
The attribute information, the acquisition time and the acquisition position stored in the database are all acquired in advance. The database may be stored in the electronic device executing the present solution, or may be independently stored in another device, which is not limited herein. The following description will be given taking an example in which the database is stored in the electronic device that executes the present embodiment.
The manner of acquiring the attribute information, the acquisition time and the acquisition position may include:
acquiring a vehicle image acquired by monitoring equipment and an acquisition time and an acquisition position corresponding to the image; analyzing the image, and determining attribute information of the vehicle in the image; and correspondingly storing the determined attribute information, the acquisition time and the acquisition position corresponding to the image into a database.
The electronic equipment is in communication connection with the monitoring equipment, and each monitoring equipment sends the vehicle image acquired by the monitoring equipment and the acquisition time and the acquisition position corresponding to the image to the electronic equipment. The electronic device analyzes the received vehicle image and can determine the attribute information of the vehicle in the image. The attribute information may include information such as a license plate number, a vehicle body color, a vehicle type, and the like, or may include only a license plate number. When the attribute information contains a plurality of items of content, the plurality of items of content are taken as one piece of attribute information. For example, when the attribute information includes a body color and a vehicle type, the two items of content are taken as one piece of attribute information, that is, each piece of attribute information stored in the database includes the body color and the vehicle type.
And correspondingly storing the received acquisition time and acquisition position corresponding to the image and the analyzed attribute information of the vehicle into a database.
Continuing the above example, assuming that a circle is drawn with the point a as the center and 1km as the radius, the area covered by the circle is determined as the target area. Part of the contents stored in the database may be as shown in table 1. It should be noted that, for simplicity of description, table 1 is only a part of the contents stored in the database, and the acquisition positions are all expressed as distances from the a site, which does not constitute a limitation on the database. In fact, the collection position may be a specific geographic position, or may be identification information of the monitoring device that collects the image; determining the geographical position of the monitoring equipment according to the identification information; according to the geographical position of the monitoring equipment, the distance between the acquisition position and the A site can be determined. In addition, the column "serial number" is for easy reference, and the actual database may not contain "serial number" information.
TABLE 1
| Serial number | Attribute information of vehicle | Time of acquisition | Acquisition position |
| 1 | License plate number: jing A0001 | 2016, 8, 13, 9: 30 | The distance from the A site is 2.5km |
| 2 | License plate number: jing B0800 | Year 2016, 8, 15, 9: 30 | The distance from the A site is 1.5km |
| 3 | License plate number: jing A0102 | Year 2016, 8, 19, 9: 30 | The distance from the A site is 0.5km |
| 4 | License plate number: jing C5005 | Year 2016, 8, 20, 9: 30 | The distance from the A site is 0.4km |
| 5 | License plate number: jing C5005 | 8/2016/21/9: 30 | The distance from the A site is 0.2km |
| 6 | License plate number: jing B0800 | Year 2016, 8, 22, 17: 30 | The distance from the A site is 1.5km |
| 7 | License plate number: jing A0102 | Year 2016, 8, 22, 17: 30 | The distance from the A site is 0.1km |
| 8 | License plate number: jing A0102 | Year 2016, 8, 23, 17: 30 | The distance from the A site is 0.3km |
| 9 | License plate number: jing C5005 | Year 2016, 8, 20, 9: 40 | The distance from the A site is 0.3km |
The first target time range is from 16/2016/8/30/2016, the target area is an area less than 1km from the point a, and in table 1, the acquisition times corresponding to numbers 3, 4, 5, 7, 8, and 9 are located in the first target time range and the acquisition positions are located in the target area. Therefore, the determined attribute information of the candidate vehicle is: license plate number: jing A0102, license plate number: jing C5005, license plate number: jing C5005, license plate number: jing A0102, license plate number: jing A0102, license plate number: jing C5005.
S103: in the determined attribute information of the candidate vehicles, the number of occurrences of the same attribute information is counted.
Continuing with the above example, in the determined attribute information of the candidate vehicle, the license plate number: 3 times appeared in Jing A0102, license plate number: jing C5005 appeared 3 times.
As an embodiment of the present invention, the step may include:
determining the same attribute information as one group from among the determined attribute information of the candidate vehicles;
for each group, judging whether the difference value of the acquisition moments corresponding to every two attribute information in the group is smaller than a third preset threshold value or not;
if yes, deleting one attribute information of the two attribute information from the group;
and counting the number of the residual attribute information in the group, and determining the number as the occurrence frequency of the attribute information in the group.
The determined 3' license plate numbers: the information of Jing A0102 "is determined as X group, and the determined 3" license plate numbers: the information of Jing C5005' is determined as Y group. The third preset threshold is a time threshold, which can be set according to practical situations, such as 1 hour, 0.5 hour, etc., and is not limited herein, and is assumed to be 1 hour.
In group X, these 3 "license plate numbers: the acquisition time corresponding to Jing A0102' is respectively as follows: year 2016, 8, 19, 9: 30. year 2016, 8, 22, 17: 30. year 2016, 8, 23, 17: 30. the difference between every two of the three acquisition moments is not less than 1 hour. Attribute information "license plate number: the number of the kyo a0102 "is 3, that is, the attribute information" license plate number: the occurrence frequency of Jing A0102' is 3.
In group Y, these 3 "license plate numbers: the acquisition time corresponding to Jing C5005' is respectively as follows: year 2016, 8, 20, 9: 30. 8/2016/21/9: 30. year 2016, 8, 20, 9: 40. the difference between the last two acquisition times was less than 1 hour. And deleting one attribute information of the two attribute information corresponding to the last two acquisition moments from the Y group. The remaining attribute information "license plate number: the number of the kyo C5005 "is 2, that is, the attribute information" license plate number: the occurrence frequency of Jing C5005' is 2.
S104: and determining the attribute information with the occurrence frequency larger than a first preset threshold value as candidate attribute information.
Assuming that the first preset threshold is 1, the "license plate number: jing a0102 "and" license plate number: jing C5005 "is determined as candidate attribute information.
S105: and determining a target vehicle in the vehicles corresponding to the candidate attribute information.
Specifically, the vehicle corresponding to the candidate attribute information may be directly determined as the target vehicle.
In a traffic accident, the offending vehicle is usually a local vehicle, which may be understood as a vehicle that is often absent from an area near the incident location, such as a vehicle driven by an owner of the vehicle whose residential address or work address is near the incident location. Since the local vehicle travels much more frequently in the area near the incident point than the foreign vehicle, the local vehicle has a high probability of a traffic accident occurring at the incident point. Continuing with the above example, the offending vehicle should be present in the area near Point A often before the time of the incident. The vehicle corresponding to the attribute information having the occurrence frequency greater than the first preset threshold is determined as the target vehicle, and the vehicle frequently appearing in the area near the point a before the event time is determined based on the idea.
If the residence address of a certain owner is near the A place, the vehicle driven by the owner is a local vehicle for the A place. Generally, the vehicle goes out in the morning and goes home in the evening on a working day, the monitoring device near the place a collects images of the vehicle, and the electronic device executing the scheme stores the collection time, the collection position and the attribute information of the vehicle corresponding to the collected images into the database. If the first target time range is two weeks, the attribute information of the vehicle should appear in the database 20 times (5 weekdays each appearing 2 times a week). In this case, the first preset threshold may be set to 20 times.
It should be emphasized that the first preset threshold is set according to actual conditions, and the above-mentioned 1 time and 20 times are only two examples and are not limited.
As an embodiment, S105 may include:
determining a second preset time period after the incident time as a second target time range;
searching the database for non-target attribute information of the vehicle of which the acquisition time is within the second target time range and the acquisition position is within the target area;
deleting non-target attribute information existing in the determined candidate attribute information;
and determining the vehicles corresponding to the residual candidate attribute information as target vehicles.
Continuing with the above example, assuming that the first preset threshold is 1, the "license plate number: jing a0102 "and" license plate number: jing C5005 "is determined as candidate attribute information.
Typically, the culprit owner will not drive the culprit vehicle to appear near the incident point for a period of time after the incident time. Based on this idea, a second preset time period after the incident time is determined as a second target time range. The second preset time period may be set according to actual conditions, such as one month, half a year, and the like. Assuming a month here, 2016.8.30-2016.9.30 was determined as the second target time frame.
It is assumed that the contents of the part stored in the database are as shown in table 2. It should be noted that, for simplicity of description, table 2 is only a part of the contents stored in the database, and the acquisition positions are all expressed as distances from the a site, which does not constitute a limitation on the database. In fact, the collection position may be a specific geographic position, or may be identification information of the monitoring device that collects the image; determining the geographical position of the monitoring equipment according to the identification information; according to the geographical position of the monitoring equipment, the distance between the acquisition position and the A site can be determined.
TABLE 2
| Attribute information of vehicle | Time of acquisition | Acquisition position |
| License plate number: jing A0001 | Year 2016, 8, 29, 9: 30 | The distance from the A site is 2.5km |
| License plate number: jing B0800 | Year 2016, 9, 15, 9: 30 | The distance from the A site is 1.5km |
| License plate number: jing C5005 | Year 2016, 9, 16, 9: 30 | The distance from the A site is 0.5km |
| License plate number: jing A0001 | Year 2016, 9, 16, 9: 30 | The distance from the A site is 0.2km |
The two pieces of found information meet the conditions: the acquisition time is between 2016.8.30-2016.9.30, and the distance between the acquisition position and the A site is less than 1km, so that the number plate number: jing C5005 "and" license plate number: jing a0001 "is determined as non-target attribute information.
The determined candidate attribute information is' license plate number: jing a0102 "and" license plate number: jing C5005 ", mixing" license plate number: jing C5005 "is deleted, and the remaining candidate attribute information" license plate number: the vehicle corresponding to Jing A0102' is the target vehicle, namely the suspicious hit vehicle.
On the basis of the idea that the culprit vehicle owner will not drive the culprit vehicle within a period of time after the incident time, in the vicinity of the incident location, it is also possible to exclude non-suspicious culprit vehicles in another way:
determining a third preset time period after the incident time as a third target time range;
judging whether candidate attribute information of which the acquisition time is within the third target time range and the acquisition position is within the target area is searched in the database;
if yes, deleting the searched candidate attribute information, and determining the vehicles corresponding to the remaining candidate attribute information as target vehicles.
Continuing with the above example, assuming that the first preset threshold is 1, the "license plate number: jing a0102 "and" license plate number: jing C5005 "is determined as candidate attribute information.
The third preset time period may be set according to actual conditions, such as one month, half a year, and the like. Assuming one month here, 2016.8.30-2016.9.30 was determined as the third target time frame.
The determined candidate attribute information is' license plate number: jing a0102 "and" license plate number: jing C5005 ", determining whether the information that the acquisition time corresponding to the two candidate attribute information is between 2016.8.30 and 2016.9.30 and the distance between the acquisition position and the a location is less than 1km is found in table 2: and finding the third piece of information to meet the requirement. That is, the "license plate number: jing C5005 ", and the remaining candidate attribute information" license plate number: the vehicle corresponding to Jing A0102' is the target vehicle, namely the suspicious hit vehicle.
After the target vehicle, i.e. the suspected culprit vehicle, is determined, the attribute information of the target vehicle may be output to enable the relevant personnel to investigate the target vehicle.
As an embodiment of the present invention, after S104, the attribute information corresponding to each target vehicle may be sorted according to the collection time and/or the collection position and/or the occurrence frequency corresponding to the attribute information;
and sequentially outputting attribute information corresponding to each target vehicle according to the sequencing result.
It is understood that the attribute information corresponding to the closer the collection time to the event time, the closer the collection position to the event point, and the greater the occurrence number of the attribute information has a higher probability of the corresponding vehicle being the hit vehicle. Therefore, it is possible to preferentially output attribute information of a target vehicle having a high possibility of causing trouble. That is, the attribute information corresponding to each target vehicle is sorted according to the collection time and/or the collection position and/or the occurrence frequency corresponding to the attribute information.
The attribute information may be sorted according to only one item of content corresponding thereto: for example, the attribute information is sorted only according to the acquisition time corresponding to the attribute information, and the attribute information with the acquisition time closer to the event time is arranged in front; or sorting the attribute information according to the acquisition positions corresponding to the attribute information, and arranging the attribute information of which the acquisition position is closer to the incident place in front of the incident place; or, the attribute information is sorted according to the corresponding occurrence times of the attribute information, and the attribute information with the larger occurrence times is arranged in front.
The multiple items of content may also be sorted according to the attribute information, such as sorting according to the collection time, collection position, and occurrence frequency corresponding to the attribute information. In this case, the weight corresponding to the acquisition time, the acquisition position and the occurrence frequency can be set; determining a comprehensive weight value corresponding to the attribute information according to the acquisition time, the acquisition position, the occurrence frequency and the set weights corresponding to the attribute information; and sorting the attribute information according to the comprehensive weight value. Here, the attribute information may be ranked in front of the attribute information such that the closer the acquisition time is to the event time, the closer the acquisition position is to the event point, and the more the number of occurrences.
And sequentially outputting each attribute information according to the sequencing result. The attribute information of the vehicle with high possibility of causing the accident is preferentially output, so that the relevant personnel can preferentially check the vehicle with high possibility of causing the accident, and the efficiency of identifying the vehicle with the accident is improved.
By applying the embodiment shown in fig. 1 of the invention, the attribute information of the vehicle, the time and the position of image acquisition of the vehicle are correspondingly stored in the database; when a traffic accident occurs, determining a first target time range and a target area according to incident time and incident place; according to the determined first target time range and the target area, determining attribute information of the matched alternative vehicle in a database; counting the occurrence times of the same attribute information in the determined attribute information of the candidate vehicles, and determining the attribute information of which the occurrence times is greater than a first preset threshold value as the candidate attribute information; and determining a target vehicle in the vehicles corresponding to the candidate attribute information. Therefore, the threshold is set according to the occurrence frequency of the attribute information, a large part of attribute information is filtered, the target vehicle is determined in the vehicles corresponding to the residual attribute information, only the target vehicle is checked subsequently, and the workload of identifying the troubling vehicle is reduced.
Corresponding to the method embodiment, the embodiment of the invention also provides a vehicle identification device.
Fig. 2 is a schematic structural diagram of a vehicle identification device according to an embodiment of the present invention, including:
a first determining module 201, configured to determine a first target time range and a target area according to the incident time and the incident location;
a second determining module 202, configured to determine attribute information of the candidate vehicle corresponding to the first target time range and the target area according to attribute information of the vehicle, and a time and a position of image acquisition performed on the vehicle, which are correspondingly stored in a database;
the counting module 203 is used for counting the occurrence frequency of the same attribute information in the determined attribute information of the candidate vehicles;
a third determining module 204, configured to determine, as candidate attribute information, attribute information whose occurrence number is greater than a first preset threshold;
a fourth determining module 205, configured to determine a target vehicle from the vehicles corresponding to the candidate attribute information.
In this embodiment, the apparatus may further include: an acquisition module, a fifth determination module, and a storage module (not shown in the figures), wherein,
the acquisition module is used for acquiring a vehicle image acquired by monitoring equipment and an acquisition time and an acquisition position corresponding to the image;
the fifth determining module is used for analyzing and processing the image and determining the attribute information of the vehicle in the image;
and the storage module is used for correspondingly storing the determined attribute information, the acquisition time and the acquisition position corresponding to the image into a database.
In this embodiment, the first determining module 201 may include: a first determination submodule and a second determination submodule (not shown in the figure), wherein,
the first determining submodule is used for determining a first preset time period before the incident time as a first target time range;
and the second determining submodule is used for determining an area, which is away from the incident point by a second preset threshold value, as a target area, or determining an area covered by a preset number of checkpoints, which are closest to the incident point, as the target area.
In this embodiment, the fourth determining module 205 may specifically be configured to:
and determining the vehicle corresponding to the candidate attribute information as a target vehicle.
In this embodiment, the fourth determining module 205 may specifically be configured to:
determining a second preset time period after the incident time as a second target time range;
searching the database for non-target attribute information of the vehicle of which the acquisition time is within the second target time range and the acquisition position is within the target area;
deleting non-target attribute information existing in the determined candidate attribute information;
and determining the vehicles corresponding to the residual candidate attribute information as target vehicles.
In this embodiment, the fourth determining module 205 may specifically be configured to:
determining a third preset time period after the incident time as a third target time range;
judging whether candidate attribute information of which the acquisition time is within the third target time range and the acquisition position is within the target area is searched in the database;
if yes, deleting the searched candidate attribute information, and determining the vehicles corresponding to the remaining candidate attribute information as target vehicles.
In this embodiment, the statistical module 203 may be specifically configured to:
determining the same attribute information as one group from among the determined attribute information of the candidate vehicles;
for each group, judging whether the difference value of the acquisition moments corresponding to every two attribute information in the group is smaller than a third preset threshold value or not;
if yes, deleting one attribute information of the two attribute information from the group;
and counting the number of the residual attribute information in the group, and determining the number as the occurrence frequency of the attribute information in the group.
In this embodiment, the apparatus may further include: a sorting module and an output module, (not shown), wherein,
the sorting module is used for sorting the attribute information corresponding to each target vehicle according to the acquisition time and/or the acquisition position and/or the occurrence frequency corresponding to the attribute information;
and the output module is used for sequentially outputting the attribute information corresponding to each target vehicle according to the sequencing result.
By applying the embodiment shown in fig. 2 of the present invention, the attribute information of the vehicle, the time and the position of image acquisition of the vehicle are correspondingly stored in the database; when a traffic accident occurs, determining a first target time range and a target area according to incident time and incident place; according to the determined first target time range and the target area, determining attribute information of the matched alternative vehicle in a database; counting the occurrence times of the same attribute information in the determined attribute information of the candidate vehicles, and determining the attribute information of which the occurrence times is greater than a first preset threshold value as the candidate attribute information; and determining a target vehicle in the vehicles corresponding to the candidate attribute information. Therefore, the threshold is set according to the occurrence frequency of the attribute information, a large part of attribute information is filtered, the target vehicle is determined in the vehicles corresponding to the residual attribute information, only the target vehicle is checked subsequently, and the workload of identifying the troubling vehicle is reduced.
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, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
Those skilled in the art will appreciate that all or part of the steps in the above method embodiments may be implemented by a program to instruct relevant hardware to perform the steps, and the program may be stored in a computer-readable storage medium, which is referred to herein as a storage medium, such as: ROM/RA location M, magnetic disk, optical disk, etc.
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 (10)
1. A vehicle identification method, characterized by comprising:
determining a first target time range and a target area according to the incident time and the incident place;
determining attribute information of the alternative vehicle corresponding to the first target time range and the target area according to attribute information of the vehicle, the time and the position of image acquisition of the vehicle, which are correspondingly stored in a database;
counting the occurrence times of the same attribute information in the determined attribute information of the candidate vehicles;
determining the attribute information with the occurrence frequency larger than a first preset threshold value as candidate attribute information;
determining a target vehicle in the vehicles corresponding to the candidate attribute information;
wherein the step of determining a target vehicle among the vehicles corresponding to the candidate attribute information includes:
determining a second preset time period after the incident time as a second target time range; searching the database for non-target attribute information of the vehicle of which the acquisition time is within the second target time range and the acquisition position is within the target area; deleting non-target attribute information existing in the determined candidate attribute information; determining vehicles corresponding to the remaining candidate attribute information as target vehicles;
or determining a third preset time period after the incident time as a third target time range; judging whether candidate attribute information of which the acquisition time is within the third target time range and the acquisition position is within the target area is searched in the database; if yes, deleting the searched candidate attribute information, and determining the vehicles corresponding to the remaining candidate attribute information as target vehicles.
2. The method of claim 1, further comprising, prior to the step of determining the first target time range and the target area:
acquiring a vehicle image acquired by monitoring equipment and an acquisition time and an acquisition position corresponding to the image;
analyzing the image, and determining attribute information of the vehicle in the image;
and correspondingly storing the determined attribute information, the acquisition time and the acquisition position corresponding to the image into a database.
3. The method of claim 1, wherein the step of determining a first target time range and target area based on the time and place of the incident comprises:
determining a first preset time period before the incident time as a first target time range;
and determining an area, the distance between which and the incident point is within a second preset threshold value, as a target area, or determining an area covered by a preset number of checkpoints, the distance between which and the incident point is closest, as the target area.
4. The method according to claim 1, wherein the step of counting the number of occurrences of the same attribute information among the determined attribute information of the candidate vehicles comprises:
determining the same attribute information as one group from among the determined attribute information of the candidate vehicles;
for each group, judging whether the difference value of the acquisition moments corresponding to every two attribute information in the group is smaller than a third preset threshold value or not;
if yes, deleting one attribute information of the two attribute information from the group;
and counting the number of the residual attribute information in the group, and determining the number as the occurrence frequency of the attribute information in the group.
5. The method according to claim 1, wherein after the step of determining the vehicle corresponding to the attribute information with the occurrence frequency greater than the first preset threshold as the target vehicle, the method further comprises:
sorting the attribute information corresponding to each target vehicle according to the acquisition time and/or the acquisition position and/or the occurrence frequency corresponding to the attribute information;
and sequentially outputting attribute information corresponding to each target vehicle according to the sequencing result.
6. A vehicle identification device characterized by comprising:
the first determining module is used for determining a first target time range and a target area according to the incident time and the incident place;
the second determination module is used for determining the attribute information of the alternative vehicle corresponding to the first target time range and the target area according to the attribute information of the vehicle, the time and the position of image acquisition of the vehicle, which are correspondingly stored in the database;
the statistical module is used for counting the occurrence times of the same attribute information in the determined attribute information of the alternative vehicles;
the third determining module is used for determining the attribute information of which the occurrence times is greater than the first preset threshold value as candidate attribute information;
the fourth determining module is used for determining a target vehicle in the vehicles corresponding to the candidate attribute information;
the fourth determining module is specifically configured to:
determining a second preset time period after the incident time as a second target time range; searching the database for non-target attribute information of the vehicle of which the acquisition time is within the second target time range and the acquisition position is within the target area; deleting non-target attribute information existing in the determined candidate attribute information; determining vehicles corresponding to the remaining candidate attribute information as target vehicles;
or determining a third preset time period after the incident time as a third target time range; judging whether candidate attribute information of which the acquisition time is within the third target time range and the acquisition position is within the target area is searched in the database; if yes, deleting the searched candidate attribute information, and determining the vehicles corresponding to the remaining candidate attribute information as target vehicles.
7. The apparatus of claim 6, further comprising:
the acquisition module is used for acquiring a vehicle image acquired by monitoring equipment and an acquisition time and an acquisition position corresponding to the image;
the fifth determining module is used for analyzing and processing the image and determining the attribute information of the vehicle in the image;
and the storage module is used for correspondingly storing the determined attribute information, the acquisition time and the acquisition position corresponding to the image into a database.
8. The apparatus of claim 6, wherein the first determining module comprises:
the first determining submodule is used for determining a first preset time period before the incident time as a first target time range;
and the second determining submodule is used for determining an area, which is away from the incident point by a second preset threshold value, as a target area, or determining an area covered by a preset number of checkpoints, which are closest to the incident point, as the target area.
9. The apparatus of claim 6, wherein the statistics module is specifically configured to:
determining the same attribute information as one group from among the determined attribute information of the candidate vehicles;
for each group, judging whether the difference value of the acquisition moments corresponding to every two attribute information in the group is smaller than a third preset threshold value or not;
if yes, deleting one attribute information of the two attribute information from the group;
and counting the number of the residual attribute information in the group, and determining the number as the occurrence frequency of the attribute information in the group.
10. The apparatus of claim 6, further comprising:
the sorting module is used for sorting the attribute information corresponding to each target vehicle according to the acquisition time and/or the acquisition position and/or the occurrence frequency corresponding to the attribute information;
and the output module is used for sequentially outputting the attribute information corresponding to each target vehicle according to the sequencing result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610943479.1A CN108022428B (en) | 2016-11-02 | 2016-11-02 | Vehicle identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610943479.1A CN108022428B (en) | 2016-11-02 | 2016-11-02 | Vehicle identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108022428A CN108022428A (en) | 2018-05-11 |
| CN108022428B true CN108022428B (en) | 2021-05-25 |
Family
ID=62070740
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610943479.1A Active CN108022428B (en) | 2016-11-02 | 2016-11-02 | Vehicle identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108022428B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110874934B (en) * | 2018-08-29 | 2021-03-19 | 北京万集科技股份有限公司 | License plate recognition method, system and device |
| CN110895535B (en) * | 2018-09-12 | 2023-06-20 | 阿里巴巴集团控股有限公司 | Data processing method and device and electronic equipment |
| CN111243266B (en) * | 2018-11-29 | 2021-08-20 | 杭州海康威视数字技术股份有限公司 | Vehicle information determination method and device and electronic equipment |
| CN111259054B (en) * | 2018-11-30 | 2024-01-23 | 杭州海康威视数字技术股份有限公司 | Hidden vehicle determining method and device and electronic equipment |
| CN112148924A (en) * | 2019-06-28 | 2020-12-29 | 杭州海康威视数字技术股份有限公司 | Luggage case retrieval method and device and electronic equipment |
| CN110611886B (en) * | 2019-08-01 | 2021-10-01 | 北京北大千方科技有限公司 | Vehicle-mounted mobile phone information acquisition method and device, electronic equipment and medium |
| CN112148568B (en) * | 2020-09-25 | 2023-09-22 | 昆仑数智科技有限责任公司 | Equipment monitoring system and method |
| CN115841756A (en) * | 2021-09-06 | 2023-03-24 | 中移系统集成有限公司 | Vehicle illegal parking detection method and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101593418A (en) * | 2009-05-31 | 2009-12-02 | 上海宝康电子控制工程有限公司 | Method for associative search of suspected vehicles |
| CN102610102A (en) * | 2012-02-27 | 2012-07-25 | 安科智慧城市技术（中国）有限公司 | Suspect vehicle inspection and control method and system |
| CN102819578A (en) * | 2012-07-24 | 2012-12-12 | 武汉大千信息技术有限公司 | Suspected target analyzing system and method by video investigation |
| KR101256506B1 (en) * | 2012-11-09 | 2013-05-02 | 뉴 플러스 정보통신(주) | Overloaded vehicle controlling system and method |
| CN103914532A (en) * | 2014-03-31 | 2014-07-09 | 安徽新华博信息技术股份有限公司 | Analyzing method for automatically troubleshooting suspects |
| CN104199903A (en) * | 2014-08-27 | 2014-12-10 | 上海熙菱信息技术有限公司 | Vehicle data query system and method based on path correlation |
| CN105741598A (en) * | 2014-12-09 | 2016-07-06 | 深圳中兴力维技术有限公司 | Suspect vehicle foothold analysis and processing method and device thereof |
| CN105913656A (en) * | 2016-04-28 | 2016-08-31 | 泰华智慧产业集团股份有限公司 | Distributed statistics based method and system for frequently passing vehicles |
-
2016
- 2016-11-02 CN CN201610943479.1A patent/CN108022428B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101593418A (en) * | 2009-05-31 | 2009-12-02 | 上海宝康电子控制工程有限公司 | Method for associative search of suspected vehicles |
| CN102610102A (en) * | 2012-02-27 | 2012-07-25 | 安科智慧城市技术（中国）有限公司 | Suspect vehicle inspection and control method and system |
| CN102819578A (en) * | 2012-07-24 | 2012-12-12 | 武汉大千信息技术有限公司 | Suspected target analyzing system and method by video investigation |
| KR101256506B1 (en) * | 2012-11-09 | 2013-05-02 | 뉴 플러스 정보통신(주) | Overloaded vehicle controlling system and method |
| CN103914532A (en) * | 2014-03-31 | 2014-07-09 | 安徽新华博信息技术股份有限公司 | Analyzing method for automatically troubleshooting suspects |
| CN104199903A (en) * | 2014-08-27 | 2014-12-10 | 上海熙菱信息技术有限公司 | Vehicle data query system and method based on path correlation |
| CN105741598A (en) * | 2014-12-09 | 2016-07-06 | 深圳中兴力维技术有限公司 | Suspect vehicle foothold analysis and processing method and device thereof |
| CN105913656A (en) * | 2016-04-28 | 2016-08-31 | 泰华智慧产业集团股份有限公司 | Distributed statistics based method and system for frequently passing vehicles |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108022428A (en) | 2018-05-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108022428B (en) | Vehicle identification method and device | |
| US9542620B1 (en) | Locating persons of interest based on license plate recognition information | |
| CN106887137B (en) | Congestion event prompting method and device | |
| US9313616B2 (en) | System and method for automated identification of location types for geofences | |
| US10267643B2 (en) | System and method for automated correction of geofences | |
| CN104167095B (en) | Based on the vehicle behavior pattern checking method of smart city | |
| CN107645709B (en) | Method and device for determining personnel information | |
| CN108694216B (en) | Multi-source object association method and device | |
| CN109656973B (en) | Target object association analysis method and device | |
| CN103413440A (en) | Fake-licensed vehicle identification method based on smart city data base and identification rule base | |
| US20140188549A1 (en) | Risk assessment method and system for the security of an industrial installation | |
| CN106530685B (en) | A kind of traffic data Forecasting Approach for Short-term and device | |
| CN110895535B (en) | Data processing method and device and electronic equipment | |
| CN108389385B (en) | Method and device for intercepting overrun vehicle, electronic equipment and storage medium | |
| CN101894151B (en) | Method and device for acquiring event information | |
| CN111062562A (en) | Community grid service linkage disposal control method and system | |
| CN113470369B (en) | Method and system for judging true number plate of fake-licensed vehicle based on multi-dimensional information | |
| CN112818724A (en) | Method, device, equipment and storage medium for identifying non-programmed driving or non-programmed escort | |
| CN111798151B (en) | Enterprise fraud risk assessment method, device, equipment and readable storage medium | |
| CN112381414A (en) | Auxiliary alarm management system based on artificial intelligence | |
| CN113094388B (en) | Method and related device for detecting user workplace and residence | |
| CN114782115A (en) | Method, system and terminal device for recommending site selection of private stores | |
| CN115796584A (en) | Urban road operation risk checking method and device and electronic equipment | |
| CN113918563A (en) | Method and device for determining deployment control information, storage medium and electronic device | |
| CN112966586A (en) | Vehicle state detection method, device, system, equipment, medium and product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |