CN112419740B

CN112419740B - Vehicle state identification method and device

Info

Publication number: CN112419740B
Application number: CN201910782371.2A
Authority: CN
Inventors: 谭晶晶
Original assignee: Hangzhou Hikvision System Technology Co Ltd
Current assignee: Hangzhou Hikvision System Technology Co Ltd
Priority date: 2019-08-23
Filing date: 2019-08-23
Publication date: 2022-07-08
Anticipated expiration: 2039-08-23
Also published as: CN112419740A

Abstract

The embodiment of the invention provides a vehicle state identification method and a vehicle state identification device, wherein the method comprises the following steps: and obtaining target vehicle pictures according to a preset number of vehicle pictures at different moments, wherein the preset number of vehicle pictures are the pictures of the same target vehicle shot by the same bayonet camera, and the target vehicle pictures comprise complete target vehicles. And comparing the vehicle information corresponding to the target vehicle picture with legal vehicle information to determine a legal identifier of the target vehicle, wherein the legal identifier is used for indicating whether the target vehicle is legal or not. And determining the vehicle state of the target vehicle according to the legal identification of the target vehicle, the target vehicle picture and the vehicle identification model. The preset number of vehicle pictures shot at different moments through the bayonet camera obtain the target vehicle picture including the complete target vehicle, so that the vehicle state of the target vehicle can be recognized based on the complete target vehicle picture, and the accuracy of vehicle state recognition is improved.

Description

Vehicle state identification method and device

Technical Field

The embodiment of the invention relates to traffic technologies, in particular to a vehicle state identification method and device.

Background

With the continuous development of road traffic, the number of large vehicles running on a road is increased, and if the vehicle state of the large vehicle is abnormal, the safety and sanitation problems of the road are greatly influenced.

In the prior art, when a vehicle state of a large vehicle is recognized, a bayonet camera arranged on a road is used for shooting a picture of the vehicle, wherein the bayonet camera arranged on the road is usually arranged in a reverse direction, that is, the vehicle coming from head is shot, and a shooting range of the bayonet camera is limited, so that the vehicle picture is usually a picture of a head of the vehicle, and the state of the vehicle is analyzed based on the picture of the head of the vehicle.

However, the abnormal state of the vehicle usually occurs at the tail of the vehicle, and it is difficult to effectively identify the abnormal state of the vehicle by only taking a picture of the head of the vehicle, thereby reducing the accuracy of vehicle state identification.

Disclosure of Invention

The embodiment of the invention provides a vehicle state identification method and device, which are used for improving the accuracy of vehicle state identification.

In a first aspect, an embodiment of the present invention provides a vehicle state identification method, including:

obtaining target vehicle pictures according to a preset number of vehicle pictures at different moments, wherein the preset number of vehicle pictures are pictures of the same target vehicle shot by the same bayonet camera, and the target vehicle pictures comprise complete target vehicles;

comparing vehicle information corresponding to the target vehicle picture with legal vehicle information to determine a legal identifier of the target vehicle, wherein the legal vehicle information comprises identifier information of a vehicle of which the type is a preset vehicle type, and the legal identifier is used for indicating whether the target vehicle is legal or not;

and determining the vehicle state of the target vehicle according to the legal identification of the target vehicle, the target vehicle picture and a vehicle identification model, wherein the vehicle identification model is used for identifying the vehicle type and the tail state of the vehicle.

In one possible design, the determining the vehicle state of the target vehicle according to the legal identifier of the target vehicle, the target vehicle picture and the vehicle identification model includes:

identifying the target vehicle picture according to the vehicle identification model to obtain the vehicle type and the tail state of the target vehicle;

and determining the vehicle state of the target vehicle according to the legal identification of the target vehicle, the vehicle type and the tail state of the target vehicle.

In a possible design, if the legal identifier of the target vehicle is an identifier indicating legality, determining the vehicle state of the target vehicle according to the legal identifier of the target vehicle, the vehicle type of the target vehicle, and the vehicle tail state of the target vehicle includes:

if the vehicle type of the target vehicle is the preset vehicle type, judging whether the vehicle tail state of the target vehicle is the preset vehicle tail state or not;

if so, determining that the vehicle state of the target vehicle is an abnormal state;

if not, determining that the vehicle state of the target vehicle is a normal state.

In one possible design, if the legal identifier of the target vehicle is an identifier indicating illegal, the method further includes:

judging whether the type of the target vehicle is the preset type or not;

if so, determining that the vehicle state of the target vehicle is a black vehicle state;

In one possible design, the determining the legal identifier of the target vehicle according to the comparison between the vehicle information corresponding to the target vehicle picture and the legal vehicle information includes:

judging whether the legal vehicle information comprises vehicle information corresponding to the target vehicle picture according to the vehicle information corresponding to the target vehicle picture and the legal vehicle information, wherein the vehicle information corresponding to the target vehicle picture is the license plate number of the target vehicle;

if so, determining that the legal identification of the target vehicle is an identification for indicating legality;

and if not, determining that the legal identification of the target vehicle is an identification for indicating illegal.

In a possible design, before obtaining the target vehicle picture according to a preset number of vehicle pictures at different times, the method further includes:

acquiring a vehicle picture through a bayonet camera, and judging whether the target vehicle is a truck or not according to the vehicle picture;

if so, continuously acquiring the vehicle pictures until the number of the vehicle pictures reaches a preset number, and splicing the preset number of the vehicle pictures to obtain spliced vehicle pictures.

In a possible design, after obtaining a picture of a vehicle by a bayonet camera, the method further includes:

acquiring a license plate picture of the target vehicle according to the one vehicle picture;

the obtaining of the target vehicle picture according to the preset number of vehicle pictures at different moments comprises:

judging whether the license plate picture of the target vehicle can identify the license plate or not according to the license plate picture of the target vehicle;

if so, judging whether the license plate picture is a license plate picture of the vehicle tail;

and if not, synthesizing according to the spliced vehicle picture to obtain a target vehicle picture.

In one possible design, the method further includes:

if the license plate picture is a license plate picture of the vehicle tail, taking a first vehicle picture in the preset number of vehicle pictures as a target vehicle picture;

and if the license plate picture is not the license plate picture of the vehicle tail, synthesizing according to the spliced vehicle picture to obtain a target vehicle picture.

In one possible design, if the vehicle state of the target vehicle is a blackout state or an abnormal state, a warning is given in a preset manner, and the vehicle state of the target vehicle is displayed.

In one possible design, the preset vehicle type may be any one of the following: a residue truck, a sludge truck, an oil tank truck and a mud tank truck.

In a second aspect, an embodiment of the present invention provides a vehicle state identification device, including:

the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a target vehicle picture according to a preset number of vehicle pictures at different moments, the preset number of vehicle pictures are the pictures of the same target vehicle shot by the same bayonet camera, and the target vehicle picture comprises the complete target vehicle;

the determining module is used for comparing vehicle information corresponding to the target vehicle picture with legal vehicle information to determine a legal identifier of the target vehicle, wherein the legal vehicle information comprises identifier information of a vehicle of which the type is a preset vehicle type, and the legal identifier is used for indicating whether the target vehicle is legal or not;

the determining module is further configured to determine a vehicle state of the target vehicle according to the legal identifier of the target vehicle, the target vehicle picture and a vehicle identification model, wherein the vehicle identification model is used for identifying a vehicle type and a vehicle tail state of the vehicle.

In one possible design, the determining module is specifically configured to:

In one possible design, if the legal identifier of the target vehicle is an identifier indicating legality, the determining module is specifically configured to:

In a possible design, if the legal identifier of the target vehicle is an identifier indicating illegal, the method further includes: a judgment module;

the judging module is used for judging whether the vehicle type of the target vehicle is the preset vehicle type;

In one possible design, the determining module is specifically configured to:

judging whether the legal vehicle information comprises vehicle information corresponding to the target vehicle picture or not according to the vehicle information corresponding to the target vehicle picture and the legal vehicle information, wherein the vehicle information corresponding to the target vehicle picture is the license plate number of the target vehicle;

In one possible design, the determining module is further configured to:

before the target vehicle picture is obtained according to the preset number of vehicle pictures at different moments, obtaining a vehicle picture through a bayonet camera, and judging whether the target vehicle is a truck or not according to the vehicle picture;

In one possible design, the obtaining module is further configured to:

after a vehicle picture is obtained through the bayonet camera, a license plate picture of the target vehicle is obtained according to the vehicle picture;

the obtaining module is further specifically configured to:

In one possible design, the obtaining module is further configured to:

In a third aspect, an embodiment of the present invention provides a vehicle state recognition apparatus including:

a memory for storing a program;

a processor for executing the program stored by the memory, the processor being adapted to perform the method of the first aspect as well as any of the various possible designs of the first aspect, when the program is executed.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, including computer program instructions, which, when run on a computer, cause the computer to perform the method as described above in the first aspect and any one of various possible designs of the first aspect.

The embodiment of the invention provides a vehicle state identification method and a vehicle state identification device, wherein the method comprises the following steps: and obtaining target vehicle pictures according to a preset number of vehicle pictures at different moments, wherein the preset number of vehicle pictures are the pictures of the same target vehicle shot by the same bayonet camera, and the target vehicle pictures comprise complete target vehicles. And comparing the vehicle information corresponding to the target vehicle picture with legal vehicle information to determine the legal identification of the target vehicle, wherein the legal vehicle information comprises identification information of a vehicle of which the type is a preset vehicle type, and the legal identification is used for indicating whether the target vehicle is legal or not. And determining the vehicle state of the target vehicle according to the legal identification of the target vehicle, the target vehicle picture and the vehicle identification model, wherein the vehicle identification model is used for identifying the vehicle type and the tail state of the vehicle. The preset number of vehicle pictures shot at different moments through the bayonet camera obtain the target vehicle picture including the complete target vehicle, so that the vehicle state of the target vehicle can be recognized based on the complete target vehicle picture, and the accuracy of vehicle state recognition is improved.

Drawings

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

FIG. 1 is a system diagram of a vehicle state identification method according to an embodiment of the present invention;

fig. 2 is a schematic view of a bayonet camera of a vehicle state identification method according to an embodiment of the present invention;

FIG. 3 is a first flowchart of a vehicle state identification method according to an embodiment of the present invention;

FIG. 4 is a second flowchart of a vehicle status identification method according to an embodiment of the present invention;

fig. 5 is a flowchart of a vehicle state identification method according to an embodiment of the present invention;

fig. 6 is a scene schematic diagram of a vehicle state identification method according to an embodiment of the present invention;

fig. 7 is a first schematic structural diagram of a vehicle state identification device according to an embodiment of the present invention;

fig. 8 is a second schematic structural diagram of a vehicle state identification device according to an embodiment of the present invention;

fig. 9 is a schematic diagram of a hardware structure of a vehicle state identification device according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, 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 some, but not all, embodiments of the present invention. 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.

Fig. 1 is a schematic system diagram of a vehicle state identification method according to an embodiment of the present invention, and as shown in fig. 1, the system includes: bayonet socket camera, data center, server, terminal equipment.

At present, in a high-definition bayonet system, bayonets are arranged in important public security areas such as urban roads, highway entrances and exits and highway toll stations and are used for all-weather real-time monitoring and recording of vehicles coming and going, wherein each bayonet is at least provided with one bayonet camera and is used for shooting vehicles coming and going.

The bayonet camera sends the taken picture of the vehicle to the data center, and the data center is configured to perform preliminary analysis processing on the picture taken by the bayonet camera, where the preliminary analysis processing may be performed to obtain, for example, relevant information such as a license plate number of the vehicle, a vehicle color, a vehicle brand, a vehicle model, a face image of a user driving the vehicle, and the like, and may also be performed to analyze whether the license plate number of the vehicle is stored in the database to determine whether the vehicle is legal or not.

The data center sends the result obtained by the analysis to the server, and the server further processes the preliminary analysis result to determine the state of the vehicle, for example, the vehicle type and the vehicle tail state of the vehicle can be identified according to the vehicle picture obtained by the data center processing, so as to determine whether the current vehicle state is normal.

In alternative embodiments, the data center and the server may be the same physical entity, for example, the data center may be a unit in the server, or the data center may be provided separately from the server, which is not limited in this embodiment.

In this embodiment, if the server determines that the vehicle state is an abnormal state, the vehicle state of the vehicle is sent to the terminal device, for example, information related to the vehicle state may be sent to the terminal device, or a specific position of the abnormal state in the vehicle state may be identified in a captured vehicle picture, so as to display a specific abnormal condition to a user.

By way of example, the terminal device may be a computer device, a tablet computer, a mobile phone (or referred to as "cellular" phone), and the like, and the terminal device may also be a portable, pocket, hand-held, computer-embedded mobile device or apparatus, or a vehicle-mounted processing device or computer with mobility, and the like, which is not limited by the present invention. Those skilled in the art will appreciate that the terminal device can receive and display the data transmitted by the server 102.

On the basis of the system described above, a bayonet camera is further described in detail with reference to fig. 2, fig. 2 is a schematic view of a bayonet camera of the vehicle state identification method according to the embodiment of the present invention, as shown in fig. 2, when lenses with different focal lengths are mounted on the bayonet camera, the bayonet camera corresponds to different shooting angles and shooting distances, referring to fig. 2, when the focal length of the lens is 3.6 mm, the shooting distance is 3 m, and the shooting angle is large, which indicates that the vehicle enters the shooting range of the bayonet camera when the vehicle travels to a position 3 m away from the bayonet camera, the bayonet camera shoots the vehicle according to the shooting angle shown in the drawing, and the implementation manners of the remaining focal lengths are similar, wherein the larger the number of the lens is, the longer the corresponding shooting distance is, and the larger the shooting angle is.

It can be seen from fig. 2 that no matter what camera lens is, a shooting blind area always exists in the camera, so that in the prior art, a picture of one vehicle is shot by a bayonet camera in a reverse direction, a part of a picture of a head of the vehicle is shot, a state of the vehicle is analyzed based on the part of the picture of the head of the vehicle, and it is difficult to analyze a state of a tail of the vehicle.

Based on the above problem, the present invention provides a vehicle state identification method to improve the accuracy of vehicle state identification, which is described in detail below with reference to fig. 3, where fig. 3 is a flowchart of a vehicle state identification method according to an embodiment of the present invention, and as shown in fig. 3, the method includes:

s301, obtaining target vehicle pictures according to a preset number of vehicle pictures at different moments, wherein the preset number of vehicle pictures are pictures of the same target vehicle shot by the same bayonet camera, and the target vehicle pictures comprise complete target vehicles.

Specifically, each bayonet camera arranged on the road executes the method provided in this embodiment, taking one of the bayonet cameras as an example, after a target vehicle enters a viewing angle range of the bayonet camera, the bayonet cameras continuously shoot the target vehicle to obtain a preset number of vehicle pictures of the target vehicle, where the preset number of vehicle pictures are pictures of the same target vehicle shot by the same bayonet camera at different times, where the different times are different times when the target vehicle passes through the bayonet camera once, and the preset number may be actually set according to the viewing angle range of the bayonet camera, the road speed limit, and the like, which is not limited in this embodiment.

The vehicle image processing method comprises the steps that a plurality of vehicle images are preset, when a target vehicle passes through one bayonet, bayonet cameras shoot at different moments, and therefore the complete target vehicle (including the vehicle head and the vehicle tail) can be determined jointly according to the plurality of vehicle images, and the situation that the target vehicle can only be shot by the bayonet cameras due to the fact that shooting blind areas exist in the bayonet cameras is avoided.

For example, a preset number of vehicle pictures at different times may be synthesized to obtain a target vehicle picture including a complete target vehicle, and those skilled in the art will understand that the target vehicle picture obtained by synthesizing the preset number of vehicle pictures at different times is similar to a shot panoramic picture to obtain the complete target vehicle.

Or, a preset number of vehicle pictures at different times may be sequentially analyzed, partial information of the vehicle is obtained from each vehicle picture, and finally, information synthesis is performed according to all the partial information, so as to obtain a target vehicle picture including a complete target vehicle.

S302, according to comparison between the vehicle information corresponding to the target vehicle picture and legal vehicle information, legal identification of the target vehicle is determined, wherein the legal vehicle information comprises identification information of a vehicle of which the type is a preset vehicle type, and the legal identification is used for indicating whether the target vehicle is legal or not.

In this embodiment, the vehicle information corresponding to the target vehicle picture may include, for example: the number plate number, the number plate color, the vehicle type, the vehicle color and the like, and the vehicle information corresponding to the specific target vehicle picture can be selected according to actual requirements. The legal vehicle information comprises identification information of a vehicle of which the type is a preset vehicle type.

In an optional implementation manner, the legal vehicle information includes, for example, license plate numbers of all the slag cars registered in a legal manner, where the license plate numbers of all the slag cars registered in the legal manner are recorded in the legal vehicle information, or the legal vehicle information may further include, for example, license plate numbers of all the slag cars registered in the legal manner, vehicle types, and the like.

Those skilled in the art can understand that the vehicle information corresponding to the target vehicle picture corresponds to the legal vehicle information, for example, if the identification information included in the legal vehicle information is a license plate number, the vehicle information corresponding to the target vehicle picture is also a license plate number, and the vehicle information and the legal vehicle information can be compared correspondingly.

Specifically, if it is determined through comparison that there is a matching relationship between the vehicle information corresponding to the target vehicle and the legal vehicle information, if there is a record in the license plate number of the target vehicle and the license plate number of the legal vehicle information, or completely the same vehicle information can be matched in the legal vehicle information according to the vehicle type and the license plate number of the target vehicle, it may be determined that the current target vehicle is a registered legal vehicle, otherwise, it may be determined that the vehicle is illegal.

S303, determining the vehicle state of the target vehicle according to the legal identification of the target vehicle, the target vehicle picture and the vehicle identification model, wherein the vehicle identification model is used for identifying the vehicle type and the tail state of the vehicle.

In this embodiment, a vehicle recognition model is provided, wherein the vehicle recognition model can recognize the vehicle type and the vehicle tail state of the vehicle at the same time, and the problem of reduced processing efficiency caused by recognition by using a plurality of models can be avoided by using one model for recognition.

Specifically, the target vehicle picture is analyzed by using the vehicle identification model to determine the vehicle type and the vehicle tail state of the target vehicle, wherein the specific way of the analysis may be, for example, taking the target vehicle picture as an input of the vehicle identification model, and outputting the vehicle type and the vehicle tail state of the target vehicle after the vehicle identification model identifies the target vehicle picture.

In an alternative embodiment, the vehicle identification model may be trained according to different vehicle samples obtained from different gate systems in different regions, where the identification types included in the trained vehicle identification model may include, for example: { car, muck truck, truck head, muck truck tail, muck truck empty, mud tanker, tarpaulin truck, container truck, passenger car, minibus, muck truck cap abnormal, muck truck cap normal }, wherein muck truck cap abnormal, muck truck cap normal is the tail state.

Because the features corresponding to the vehicle type recognition and the vehicle tail state recognition are very different, and there is no conflict or mutual influence in the model training, it is feasible to perform the recognition by using the same vehicle recognition model at the same time, and performing the recognition of the vehicle type and the recognition analysis of the vehicle tail state by using one vehicle recognition model at the same time can improve the analysis operation rate and reduce the memory consumption of the graphics card, where the vehicle recognition model may be obtained by training through a convolutional neural network, for example, or may be obtained through any model training network, which is not particularly limited in this embodiment.

In this embodiment, different vehicle state determination methods need to be adopted for the legality and the unlawful state of the target vehicle, so that firstly, it is determined whether the target vehicle is legal or unlawful according to the legal identifier of the target vehicle, and secondly, when it is determined that the legal identifier of the target vehicle is an identifier for indicating legality, it is determined whether the vehicle state is a normal state or an abnormal state according to the vehicle type and the vehicle tail state of the target vehicle.

In an optional embodiment, if it is determined that the legal identifier of the target vehicle is an identifier for indicating illegal, whether the vehicle state is a normal state or a black state is determined according to the vehicle type of the target vehicle.

The vehicle state identification method provided by the embodiment of the invention comprises the following steps: and obtaining target vehicle pictures according to a preset number of vehicle pictures at different moments, wherein the preset number of vehicle pictures are the pictures of the same target vehicle shot by the same bayonet camera, and the target vehicle pictures comprise complete target vehicles. And comparing the vehicle information corresponding to the target vehicle picture with legal vehicle information to determine a legal identifier of the target vehicle, wherein the legal vehicle information comprises the identifier information of the vehicle with the type of a preset vehicle type, and the legal identifier is used for indicating whether the target vehicle is legal or not. And determining the vehicle state of the target vehicle according to the legal identification of the target vehicle, the target vehicle picture and the vehicle identification model, wherein the vehicle identification model is used for identifying the vehicle type and the tail state of the vehicle. The target vehicle pictures including complete target vehicles are obtained through the preset number of vehicle pictures shot by the bayonet cameras at different moments, so that the vehicle state of the target vehicles can be recognized based on the complete target vehicle pictures, and the accuracy of vehicle state recognition is improved.

On the basis of the foregoing embodiment, the following describes in further detail the vehicle state identification method according to the embodiment of the present invention with reference to fig. 4, and fig. 4 is a second flowchart of the vehicle state identification method according to the embodiment of the present invention.

As shown in fig. 4, the method includes:

s401, obtaining a vehicle picture through a bayonet camera, judging whether a target vehicle is a truck or not according to the vehicle picture, if so, executing S402, and if not, executing S413.

In this embodiment, the vehicle state of a large truck such as a muck truck, a sludge truck, an oil tank truck, and a sludge tank truck is mainly identified, so as to avoid a road safety problem or a road sanitation problem caused when the vehicle state of the large truck is abnormal.

Therefore, after the vehicle enters the view angle range of the bayonet camera, the bayonet camera is triggered to take a picture of the vehicle, whether the vehicle which is taken currently is a truck or not is judged according to the taken picture, if the vehicle is the truck, the goods carried by the truck are always in the rear half part of the vehicle due to the goods pulling effect of the truck, so that the vehicle state of the current truck can be determined by paying attention to the tail state of the vehicle when the vehicle state of the truck is analyzed, the vehicle needs to be taken again at different moments when the vehicle which is taken is determined to be the truck, so that a complete target vehicle picture of the target vehicle can be obtained subsequently, if the vehicle is not the truck, such as a coach, a car, a passenger car and the like, the vehicle state does not need to be paid attention to the tail state when the vehicle state is analyzed, and therefore the vehicle state is analyzed according to the picture which is taken currently, subsequent shooting is not required.

It should be noted that, in an actual application process, when vehicle state analysis is performed on vehicles of models other than trucks, if attention is wanted to be paid to the state of the tail of the truck, for example, it is wanted to detect whether a trunk of a bus is normally closed, the above determination condition may be adaptively modified as: whether the currently shot vehicle is a truck or a van is firstly judged according to the shot picture, the specific implementation mode can be selected according to actual requirements, and details of various possible implementation modes are not repeated in the embodiment.

Whether the target vehicle is the truck or not is judged in advance, so that the condition that all vehicles are shot by the bayonet camera in a preset number of vehicle pictures can be avoided, and system resources are saved.

S402, continuously obtaining the vehicle pictures until the number of the vehicle pictures reaches a preset number, and splicing the preset number of the vehicle pictures to obtain spliced vehicle pictures.

Specifically, if it is determined that the target vehicle is a truck, one picture cannot include a complete target vehicle, and here, when the target vehicle passes through the shooting range of the bayonet camera, the target vehicle needs to be continuously shot until the number of the vehicle pictures reaches a preset number.

In an alternative implementation manner, the preset number may be 4, specifically, on the premise that the network is normal, the rate of the bayonet camera performing one-time shooting and performing vehicle type recognition and license plate recognition is within milliseconds, the longest time is about 0.5 second, and the one-time shooting time is about 0.1 second. The triggering distance of a normally arranged bayonet camera is 29 meters, the running speed of the vehicle is 30 kilometers per hour according to the urban speed limit, and the converted speed is 8.3 meters per second, so that the triggering distance needs 3.5 seconds after the vehicle runs.

Secondly, the construction height of the bayonet camera on the road is generally 6 meters, the bayonet angle is generally within 45 degrees, and a vision blind area of about 6 meters exists, so that the time from the arrival of the vehicle at the triggering distance to the departure of the visual angle range of the camera is about 3 seconds. If the vehicle speed is higher than 30 km/h, it is less than 3 seconds. The shooting time of one time is about 0.1 second, so that the target vehicle is continuously shot after being determined by the bayonet camera and loaded in a truck, and 3 shooting is reasonable, the tail picture of the target vehicle can be successfully acquired, and the vehicle pictures of the target vehicle can be acquired as much as possible.

Those skilled in the art can understand that the vehicle picture of the target vehicle captured by the bayonet camera can be selected according to actual requirements, and this embodiment does not need to be particularly limited.

Then, carry out the concatenation with the vehicle picture of predetermineeing quantity and handle and obtain concatenation vehicle picture, wherein the concatenation is in the same place the picture concatenation, for example there are 4 vehicle pictures at present, then can splice these 4 pictures into the form of four palace check in order to obtain concatenation vehicle picture, perhaps can splice into a line etc. this embodiment does not restrict this, through splicing the vehicle picture of predetermineeing quantity, can carry out normalized sending and receiving to many vehicle pictures, with the processing efficiency who promotes data, avoid many pictures to take place the confusion.

S403, obtaining target vehicle pictures according to a preset number of vehicle pictures at different moments, wherein the preset number of vehicle pictures are pictures of the same target vehicle shot by the same bayonet camera, and the target vehicle pictures comprise complete target vehicles.

S404, comparing the vehicle information corresponding to the target vehicle picture with legal vehicle information, and determining the legal identification of the target vehicle. The legal vehicle information comprises identification information of a vehicle with the type of a preset vehicle type, and the legal identification is used for indicating whether a target vehicle is legal or not.

The implementation manners of S403 and S404 are similar to those of S301 and S302, and are not described herein again.

S405, identifying the target vehicle picture according to the vehicle identification model to obtain the vehicle type and the vehicle tail state of the target vehicle, wherein the vehicle identification model is used for identifying the vehicle type and the vehicle tail state of the vehicle.

Specifically, a target vehicle picture is used as an input of a vehicle recognition model, and the vehicle recognition model recognizes the target vehicle picture, wherein the vehicle recognition model includes a plurality of vehicle types and a plurality of vehicle tail states, for example, the vehicle recognition model can perform feature analysis on the target vehicle included in the target vehicle picture to obtain vehicle features, and then the vehicle recognition model matches the vehicle features included therein according to the vehicle features obtained by the analysis to obtain the vehicle type and the vehicle tail states of the target vehicle,

and S406, judging whether the legal mark of the target vehicle is a mark for indicating the legality, if so, executing S407, and if not, executing S410.

And S407, if the type of the target vehicle is the preset type, judging whether the tail state of the target vehicle is the preset tail state, if so, executing S408, and if not, executing S409.

In an optional implementation manner, if it is determined that the valid identifier of the target vehicle is the identifier indicating the validity, it may be determined that the vehicle information of the target vehicle is recorded in the system, for example, the license plate number of the target vehicle is registered and recorded in a vehicle white list (a license plate library which has been put into legal operation), and the valid vehicle information in this embodiment includes the identifier information of the vehicle of which the type is the preset vehicle type, so that it may be primarily determined that the vehicle type of the target vehicle is the preset vehicle type, and then it may be determined whether the vehicle type of the target vehicle is the preset vehicle type again, so that the accuracy of the determination may be improved.

If the type of the target vehicle is determined to be the preset type, then whether the tail state of the target vehicle is the preset tail state is judged, wherein the preset tail state is used for indicating that the tail state of the target vehicle is abnormal, for example, a muck vehicle is taken as an example, if the vehicle is overloaded (the loaded muck exceeds the highest loading line) and a cover plate is uncovered (after the carriage is loaded with muck, the cover plate is uncovered), the muck is easily thrown to the road surface to influence the appearance of the city and the like.

Those skilled in the art can understand that the specific preset vehicle tail state can be selected according to actual requirements, and any vehicle tail state inconsistent with the normal driving state can be used as the preset vehicle tail state of the embodiment.

In an optional embodiment, if it is determined that the vehicle type of the target vehicle is not the preset vehicle type, it may be determined that an error may occur in the previous determination on the legal identifier, and then the legal identifier may be determined again, or it may be directly determined that the vehicle state of the target vehicle is the normal state (because the current target vehicle is not the preset vehicle type to be identified).

And S408, determining the vehicle state of the target vehicle as an abnormal state.

And S409, determining that the vehicle state of the target vehicle is a normal state.

Specifically, if the tail state of the target vehicle is the preset tail state, it may be determined that the vehicle state of the target vehicle is an abnormal state; if the tail state of the target vehicle is not the preset tail state, the target vehicle is the preset vehicle type and the tail state is normal, and the vehicle state of the target vehicle is determined to be the normal state.

And S410, judging whether the vehicle type of the target vehicle is a preset vehicle type, if so, executing S411, and if not, executing S409.

In another alternative implementation, if it is determined that the legal identifier of the target vehicle is an identifier indicating illegal, it may be determined that the vehicle information of the target vehicle is not recorded in the system, for example, the license plate number of the target vehicle cannot be found in a vehicle white list (a license plate library which is filed for legal operation), and the target vehicle has a high possibility of being a black vehicle.

Then, it is determined whether the target vehicle is a black vehicle, specifically, the legal vehicle information in this embodiment includes identification information of a vehicle of which the type is a preset vehicle type, and therefore it is necessary to determine whether the vehicle type of the target vehicle is the preset vehicle type, and in this embodiment, identification information of a vehicle of which the type is not the preset vehicle type is not recorded in the legal vehicle information, for example, when the preset vehicle type is a muck vehicle, only a license plate of the muck vehicle that has been put on record for legal operation is recorded in the legal vehicle information, and for license plates other than the muck vehicle, no record is recorded in the legal vehicle information, and it cannot be determined that the target vehicle is a black vehicle.

And S411, determining that the vehicle state of the target vehicle is a black vehicle state.

Specifically, on the premise that the legal identifier of the target vehicle is determined to be the identifier for indicating the illegal, if the vehicle type of the target vehicle is determined to be the preset vehicle type through judgment, for example, it may be determined that the license plate number of the current target vehicle is not recorded in the white list, so that the vehicle state of the target vehicle is determined to be the black state.

Optionally, on the premise that the legal identifier of the target vehicle is determined to be the identifier for indicating the illegal, it is determined by judgment that the vehicle type of the target vehicle is not the preset vehicle type, for example, the current target vehicle is a bus, and the license plate number of the current target vehicle is not necessarily recorded in the white list.

According to the embodiment, the vehicle information corresponding to the target vehicle picture is compared with the legal vehicle information to determine whether the target vehicle is legal or not, and then whether the vehicle type of the target vehicle is the preset vehicle type or not is determined, so that management and control of a black vehicle are accurately and efficiently realized, and the applicability of the black vehicle is expanded.

And S412, if the vehicle state of the target vehicle is a black vehicle state or an abnormal state, warning according to a preset mode, and displaying the vehicle state of the target vehicle.

When the vehicle state of the target vehicle is a black vehicle state or an abnormal state, a warning needs to be given, for example, if the vehicle state of the target vehicle is determined to be the black vehicle state, a preset message can be sent to the terminal device to give a black vehicle warning, or relevant data of the target vehicle is directly sent to a management mechanism; or determining that the vehicle state of the target vehicle is an abnormal state, performing rear cover abnormality alarm, for example, sending a short message prompt to a driver of the target vehicle, or sending a prompt to a related law enforcement agency.

And the analysis server can report the identification result of the target vehicle to the WEB server, the WEB server displays the identification result of the target vehicle on the shot vehicle picture, and the vehicle picture comprising the identification result is displayed in the terminal equipment, so that the user is clearly told where the violation area is and what the violation type is, and then the violation picture which can be checked by the user is downloaded and is kept as the penalty evidence.

And S413, sending the acquired vehicle picture to a data center.

If the target vehicle is determined not to be the truck, subsequent shooting is not needed, and a currently shot vehicle picture is directly used as a basis for analysis and sent to the data center for analysis.

The vehicle state identification method provided by the embodiment of the invention comprises the following steps: and obtaining a vehicle picture through the bayonet camera, judging whether the target vehicle is a truck or not according to the vehicle picture, if so, continuously obtaining the vehicle picture until the number of the vehicle pictures reaches a preset number, and splicing the preset number of the vehicle pictures to obtain a spliced vehicle picture. And obtaining target vehicle pictures according to a preset number of vehicle pictures at different moments, wherein the preset number of vehicle pictures are the pictures of the same target vehicle shot by the same bayonet camera, and the target vehicle pictures comprise complete target vehicles. And comparing the vehicle information corresponding to the target vehicle picture with legal vehicle information to determine the legal identification of the target vehicle. The legal vehicle information comprises identification information of a vehicle with the type of a preset vehicle type, and the legal identification is used for indicating whether a target vehicle is legal or not. And identifying the target vehicle picture according to the vehicle identification model to obtain the vehicle type and the vehicle tail state of the target vehicle, wherein the vehicle identification model is used for identifying the vehicle type and the vehicle tail state of the vehicle. And judging whether the legal mark of the target vehicle is a mark for indicating the legality, if so, judging whether the vehicle tail state of the target vehicle is the preset vehicle tail state when the vehicle type of the target vehicle is the preset vehicle type, and if so, determining that the vehicle state of the target vehicle is the abnormal state. If not, determining that the vehicle state of the target vehicle is a normal state. And if the legal identification of the target vehicle is determined not to be the identification used for indicating the legal identification, judging whether the vehicle type of the target vehicle is a preset vehicle type, and if so, determining that the vehicle state of the target vehicle is a black vehicle state. If not, determining that the vehicle state of the target vehicle is a normal state. And if the vehicle state of the target vehicle is a black vehicle state or an abnormal state, warning according to a preset mode, and displaying the vehicle state of the target vehicle. And if the target vehicle is determined not to be the truck, sending the acquired vehicle picture to a data center. The vehicle information corresponding to the target vehicle picture is compared with the legal vehicle information to determine whether the target vehicle is legal or not, and then whether the vehicle type of the target vehicle is a preset vehicle type or not is judged, so that management and control on the black vehicle are accurately and efficiently realized, and the applicability of the black vehicle is expanded. And accurately recognizing the abnormal state of the vehicle by judging whether the tail state of the target vehicle is the preset tail state or not.

On the basis of the above embodiment, the vehicle state identification method provided by the present invention adopts different processing modes for the head license plate and the tail license plate, which is described below with reference to fig. 5 and 6, fig. 5 is a flowchart of the vehicle state identification method provided by the embodiment of the present invention, and fig. 6 is a scene schematic diagram of the vehicle state identification method provided by the embodiment of the present invention.

As shown in fig. 5, the method includes:

s501, obtaining a vehicle picture through a bayonet camera, and obtaining a license plate picture of a target vehicle according to the vehicle picture.

Specifically, when the bayonet camera acquires a vehicle picture to judge whether a target vehicle is a truck, and acquires a license plate picture of the vehicle according to the acquired vehicle picture, wherein when the bayonet camera starts to acquire a vehicle picture, the target vehicle is determined to just start entering a visual angle range of the bayonet camera, and the vehicle head firstly enters the visual angle range, so that the license plate picture of the target vehicle can be acquired definitely at the moment.

In an optional embodiment, if the license plate picture of the vehicle tail is obtained by forward shooting, if an initially obtained vehicle picture cannot obtain the license plate picture of the target vehicle, the license plate picture of the target vehicle can be obtained according to a preset number of subsequently obtained vehicle pictures.

S502, judging whether the license plate picture of the target vehicle can identify the license plate or not according to the license plate picture of the target vehicle, if so, executing S503, otherwise, executing S504.

Specifically, the license plate picture can be divided into a vehicle head license plate and a vehicle tail license plate, and different processing strategies are adopted for the vehicle head license plate and the vehicle tail license plate in the embodiment, so that the license plate is firstly recognized according to the license plate picture of the target vehicle, wherein the specific implementation mode of the license plate recognition can refer to the prior art, and is not repeated here.

S503, judging whether the license plate picture is the license plate picture at the tail of the vehicle, if so, executing S505, otherwise, executing S504.

Specifically, if the license plate picture of the target vehicle is determined to be capable of identifying the license plate, whether the currently identified license plate is the license plate picture at the tail of the vehicle or the license plate picture at the head of the vehicle is further judged.

In an optional implementation manner, the analysis can be performed in the gate, wherein the analysis result of the gate can inform the system of the current license plate picture of the vehicle head or the vehicle tail, so that whether the current preset number of license plate pictures are shot reversely or positively can be known, and different processing strategies are correspondingly adopted.

S504, synthesizing according to a preset number of vehicle pictures at different moments to obtain target vehicle pictures, wherein the preset number of vehicle pictures are pictures of the same target vehicle shot by the same bayonet camera, and the target vehicle pictures comprise complete target vehicles.

If it is determined that the license plate picture of the current target vehicle is the license plate picture of the vehicle head, the complete target vehicle cannot be shot due to the dead angle in the view angle shot by the bayonet camera, for example, the vehicle head picture is shot, and when the license plate number can be normally identified, the vehicle tail picture cannot be shot, so that the vehicle tail state of the target vehicle cannot be judged, and therefore, a preset number of vehicle pictures at different moments need to be synthesized, so as to include the complete target vehicle picture.

Or when the license plate picture of the target vehicle cannot identify the license plate, and whether the license plate picture is the license plate picture of the head or the license plate picture of the tail cannot be determined at the moment, synthesizing the license plate pictures according to the preset number of the vehicle pictures at different moments to obtain the target vehicle picture.

On the basis of the above embodiment, a target vehicle picture can be obtained by synthesizing spliced vehicle pictures, where a specific implementation manner of synthesizing the pictures can refer to fig. 6, and as shown in fig. 6, assuming that there are 4 vehicle pictures at different current times, the 4 vehicle pictures are firstly spliced into a format of a four-grid, and as can be seen from fig. 6, the vehicle pictures at different times correspond to vehicle pictures shot when different positions of a vehicle pass through a shooting range of a bayonet camera.

Referring to the first vehicle picture in fig. 6, at this time, the license plate picture of the vehicle head can be acquired, but the situation of the vehicle tail cannot be acquired, and referring to the third and fourth vehicle pictures, at this time, although the situation of the vehicle tail can be acquired, the license plate picture cannot be acquired, so that specific vehicle information cannot be determined, and therefore, 4 vehicle pictures are synthesized to obtain a target vehicle picture including a complete target vehicle and a target vehicle picture indicated below in fig. 6.

And S505, taking the first vehicle picture in the preset number of vehicle pictures as a target vehicle picture.

In another optional implementation manner, if it is determined that the license plate picture is the license plate picture of the car tail, the license plate picture of the car tail may include the car tail state of the vehicle and the license plate picture at the same time, at this time, the vehicle state may already be analyzed, and the synthesis of the picture is not required, and then the first vehicle picture in the spliced vehicle pictures is taken as the target vehicle picture.

In an optional embodiment, any one of the preset number of vehicle pictures at different times can be used as the target vehicle picture as long as the target vehicle picture simultaneously includes the vehicle tail state and the license plate picture of the vehicle.

S506, judging whether the legal vehicle information comprises the vehicle information corresponding to the target vehicle picture or not according to the vehicle information corresponding to the target vehicle picture and the legal vehicle information, if so, executing S507, otherwise, executing S508, wherein the vehicle information corresponding to the target vehicle picture is the license plate number of the target vehicle.

Specifically, the legal vehicle information comprises license plate numbers of vehicles of preset vehicle types, the legal identification is used for indicating whether the target vehicle is legal, and whether the target vehicle is legal is determined by judging whether the legal vehicle information comprises the license plate numbers corresponding to the target vehicle pictures.

And S507, determining the legal identification of the target vehicle as the identification for indicating the legality.

And S508, determining that the legal identification of the target vehicle is an identification for indicating illegal.

S509, determining the vehicle state of the target vehicle according to the legal identification of the target vehicle, the target vehicle picture and the vehicle identification model, wherein the vehicle identification model is used for identifying the vehicle type and the tail state of the vehicle.

The implementation manner of S509 is similar to S303, and is not described here again.

The vehicle state identification method provided by the embodiment of the invention comprises the following steps: and acquiring a vehicle picture through the bayonet camera, and acquiring a license plate picture of the target vehicle according to the vehicle picture. And judging whether the license plate picture of the target vehicle can identify the license plate according to the license plate picture of the target vehicle, if so, judging whether the license plate picture is the license plate picture of the tail of the vehicle, and if so, taking the first vehicle picture in a preset number of vehicle pictures at different moments as the target vehicle picture. And if not, synthesizing the vehicle pictures at different moments according to a preset number of the vehicle pictures to obtain target vehicle pictures, wherein the preset number of the vehicle pictures are the pictures of the same target vehicle shot by the same bayonet camera, and the target vehicle pictures comprise complete target vehicles. And judging whether the legal vehicle information comprises the vehicle information corresponding to the target vehicle picture or not according to the vehicle information corresponding to the target vehicle picture and the legal vehicle information, and if so, determining that the legal identifier of the target vehicle is an identifier for indicating legality. And if not, determining that the legal identification of the target vehicle is the identification used for indicating the illegal identification. And determining the vehicle state of the target vehicle according to the legal identification of the target vehicle, the target vehicle picture and the vehicle identification model, wherein the vehicle identification model is used for identifying the vehicle type and the tail state of the vehicle. By adopting a strategy that is not mentioned aiming at the license plate picture of the vehicle head and the license plate picture of the vehicle tail, when whether the license plate picture is the license plate picture of the vehicle tail or not is determined, the vehicle state of the target vehicle is determined only according to the first vehicle picture, so that the implementation difficulty is reduced, and the system resources are saved.

Fig. 7 is a first schematic structural diagram of a vehicle state identification device according to an embodiment of the present invention. As shown in fig. 7, the apparatus 70 includes: an obtaining module 701 and a determining module 703.

The acquisition module 701 is used for acquiring a target vehicle picture according to a preset number of vehicle pictures at different moments, wherein the preset number of vehicle pictures are pictures of the same target vehicle shot by the same bayonet camera, and the target vehicle picture comprises a complete target vehicle;

a determining module 702, configured to determine a legal identifier of the target vehicle according to comparison between vehicle information corresponding to the target vehicle picture and legal vehicle information, where the legal vehicle information includes identifier information of a vehicle of a preset vehicle type, and the legal identifier is used to indicate whether the target vehicle is legal;

the determining module 702 is further configured to determine a vehicle state of the target vehicle according to the legal identifier of the target vehicle, the target vehicle picture, and a vehicle identification model, where the vehicle identification model is used to identify a vehicle type and a vehicle tail state of the vehicle.

In one possible design, the determining module 702 is specifically configured to:

The apparatus provided in this embodiment may be used to implement the technical solutions of the above method embodiments, and the implementation principles and technical effects are similar, which are not described herein again.

Fig. 8 is a schematic structural diagram of a vehicle state identification device according to an embodiment of the present invention. As shown in fig. 8, on the basis of the embodiment in fig. 7, if the legal identifier of the target vehicle is an identifier for indicating an illegal identifier, the present embodiment further includes: a decision block 803.

In a possible design, the determining module 803 is configured to determine whether the vehicle type of the target vehicle is the preset vehicle type;

In one possible design, the determining module 802 is specifically configured to:

In one possible design, the determining module 803 is further configured to:

In one possible design, the obtaining module 801 is further configured to:

the obtaining module 801 is further specifically configured to:

In one possible design, the obtaining module 801 is further configured to:

Fig. 9 is a schematic diagram of a hardware structure of a vehicle state identification device according to an embodiment of the present invention, and as shown in fig. 9, a vehicle state identification device 90 according to the embodiment includes: a processor 901 and a memory 902; wherein

A memory 902 for storing computer-executable instructions;

the processor 901 is configured to execute computer-executable instructions stored in the memory to implement the steps performed by the vehicle state identification method in the above-described embodiment. Reference may be made in particular to the description relating to the method embodiments described above.

Alternatively, the memory 902 may be separate or integrated with the processor 901.

When the memory 902 is provided separately, the vehicle state recognition apparatus further includes a bus 903 for connecting the memory 902 and the processor 901.

An embodiment of the present invention further provides a computer-readable storage medium, in which computer-executable instructions are stored, and when a processor executes the computer-executable instructions, the vehicle state identification method performed by the above vehicle state identification device is implemented.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the modules is only one logical division, and other divisions may be realized in practice, for example, a plurality of modules may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed coupling or direct coupling or communication connection between each other may be through some interfaces, indirect coupling or communication connection between devices or modules, and may be in an electrical, mechanical or other form.

The integrated module implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present application.

It should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.

The memory may comprise a high-speed RAM memory, and may further comprise a non-volatile storage NVM, such as at least one disk memory, and may also be a usb disk, a removable hard disk, a read-only memory, a magnetic or optical disk, etc.

The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present application are not limited to only one bus or one type of bus.

The storage medium may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.

Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and these modifications or substitutions do not depart from the spirit of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. A vehicle state identification method characterized by comprising:

determining the vehicle state of the target vehicle according to the legal identification of the target vehicle, the target vehicle picture and a vehicle identification model, wherein the vehicle identification model is used for identifying the vehicle type and the vehicle tail state of the vehicle;

the determining the vehicle state of the target vehicle according to the legal identification of the target vehicle, the target vehicle picture and the vehicle identification model comprises:

determining the vehicle state of the target vehicle according to the legal identification of the target vehicle, the vehicle type and the tail state of the target vehicle;

if the legal identifier of the target vehicle is an identifier used for indicating legality, determining the vehicle state of the target vehicle according to the legal identifier of the target vehicle, the vehicle type of the target vehicle and the tail state of the vehicle, wherein the determining comprises the following steps:

if not, determining that the vehicle state of the target vehicle is a normal state;

if the legal identification of the target vehicle is an identification used for indicating illegal, the method further comprises the following steps:

judging whether the vehicle type of the target vehicle is the preset vehicle type or not;

before obtaining the target vehicle picture according to the preset number of vehicle pictures at different moments, the method further comprises:

acquiring a vehicle picture through a bayonet camera, and acquiring a license plate picture of the target vehicle according to the vehicle picture;

if so, judging whether the license plate picture is a license plate picture of the tail of the vehicle, if so, taking the first vehicle picture in the preset number of vehicle pictures as a target vehicle picture, and if not, synthesizing according to spliced vehicle pictures to obtain the target vehicle picture;

and if not, synthesizing according to the spliced vehicle pictures to obtain target vehicle pictures, wherein the spliced vehicle pictures are obtained by splicing the preset number of vehicle pictures.

2. The method according to claim 1, wherein the determining the legal identification of the target vehicle according to the comparison between the vehicle information corresponding to the target vehicle picture and the legal vehicle information comprises:

3. The method according to claim 1, wherein before obtaining the target vehicle picture according to the preset number of vehicle pictures at different time, the method further comprises:

judging whether the target vehicle is a truck or not according to the vehicle picture;

if yes, continuously obtaining the vehicle pictures until the number of the vehicle pictures reaches a preset number, and splicing the preset number of vehicle pictures to obtain the spliced vehicle pictures.

4. The method according to any one of claims 1 to 3, characterized in that if the vehicle state of the target vehicle is a blackout state or an abnormal state, a warning is given in a preset manner and the vehicle state of the target vehicle is displayed.

5. A vehicle state recognition device characterized by comprising:

determination module for

Determining the vehicle state of the target vehicle according to the legal identification of the target vehicle, the target vehicle picture and a vehicle identification model, wherein the vehicle identification model is used for identifying the vehicle type and the tail state of the vehicle;

the determination module is particularly used for

if the legal identifier of the target vehicle is an identifier for indicating legality, the determining module is specifically configured to:

if the legal identification of the target vehicle is an identification used for indicating illegal, the method further comprises the following steps: a judgment module;

the acquisition module is further configured to:

after a vehicle picture is obtained through a bayonet camera, a license plate picture of the target vehicle is obtained according to the vehicle picture;

the obtaining module is further specifically configured to:

if not, synthesizing according to the spliced vehicle pictures to obtain target vehicle pictures;

the acquisition module is further configured to:

if the license plate picture is a license plate picture of the vehicle tail, taking a first vehicle picture in the spliced vehicle pictures as a target vehicle picture;

and if the license plate picture is not the license plate picture of the vehicle tail, synthesizing according to the spliced vehicle pictures to obtain a target vehicle picture, wherein the spliced vehicle picture is obtained by splicing the preset number of vehicle pictures.

6. The apparatus of claim 5, wherein the determining module is specifically configured to:

7. The apparatus of claim 5, wherein the determining module is further configured to:

before the target vehicle picture is obtained according to the preset number of vehicle pictures at different moments, judging whether the target vehicle is a truck or not according to the one vehicle picture;

if so, continuously acquiring the vehicle pictures until the number of the vehicle pictures reaches a preset number, and splicing the preset number of the vehicle pictures to obtain the spliced vehicle pictures.

8. The apparatus according to any one of claims 5 to 7, characterized in that if the vehicle state of the target vehicle is a blackout state or an abnormal state, a warning is given in a preset manner and the vehicle state of the target vehicle is displayed.

9. A vehicle state recognition apparatus characterized by comprising:

a memory for storing a program;

a processor for executing the program stored by the memory, the processor being configured to perform the method of any of claims 1 to 4 when the program is executed.

10. A computer-readable storage medium comprising computer program instructions which, when run on a computer, cause the computer to perform the method of any one of claims 1 to 4.