CN111931545A - Number plate identification method and device - Google Patents
Number plate identification method and device Download PDFInfo
- Publication number
- CN111931545A CN111931545A CN201910395165.6A CN201910395165A CN111931545A CN 111931545 A CN111931545 A CN 111931545A CN 201910395165 A CN201910395165 A CN 201910395165A CN 111931545 A CN111931545 A CN 111931545A
- Authority
- CN
- China
- Prior art keywords
- number plate
- adr
- frame image
- current frame
- vehicle
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 231100001261 hazardous Toxicity 0.000 claims description 12
- 239000000203 mixture Substances 0.000 claims description 12
- 239000000725 suspension Substances 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 2
- 230000032258 transport Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 6
- 239000000383 hazardous chemical Substances 0.000 description 4
- 239000013056 hazardous product Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Character Discrimination (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a number plate identification method and device. According to the method and the device, the current frame image is collected, the current frame image comprises the target vehicle, the vehicle type information of the target vehicle is identified from the current frame image, whether the vehicle type information is the vehicle type information of the specified vehicle type is checked, the specified vehicle type is the vehicle type used for hanging the ADR number plate of the highway transportation of the dangerous goods, if yes, the ADR number plate hung by the target vehicle is identified, the ADR number plate hung by the vehicle for transporting the dangerous goods can be identified, the dangerous goods category is determined according to the ADR number plate, the dangerous goods classification is realized, and therefore the vehicle for transporting the dangerous goods and the dangerous goods category transported by the vehicle can be monitored.
Description
Technical Field
The invention relates to the technical field of detection, in particular to a number plate identification method and device.
Background
ADR (Automation Dangerous Road, European protocol for Road transportation of hazardous materials) was established by the European Union economic Committee (UNECE) in 9.30.1957 in Geneva, and officially implemented in 48 European countries such as Belgium, Stovack, Germany, France, etc. in 1.29.1968, aiming to improve the safety of international Road transportation of hazardous materials. All vehicles of dangerous goods (chemicals, explosives, etc.) entering the european market for road transportation need to hang an ADR number plate.
The number plate is the 'ID card' of vehicle, is an important information of distinguishing other motor vehicles, and similarly, the ADR number plate is the effective sign of transporting dangerous goods. In the related art, when a vehicle is detected, whether the vehicle is qualified for transporting dangerous goods is determined by detecting the vehicle type. However, the same vehicle model can transport various dangerous goods, and the above method cannot predict which kind of dangerous goods the vehicle transports.
Disclosure of Invention
In order to overcome the problems in the related art, the invention provides a number plate identification method and a number plate identification device.
According to a first aspect of embodiments of the present invention, there is provided a number plate recognition method, the method including:
acquiring a current frame image; the current frame image comprises a target vehicle;
identifying vehicle type information of a target vehicle from the current frame image;
checking whether the vehicle type information is vehicle type information of a specified vehicle type, wherein the specified vehicle type is a vehicle type used for hanging a hazardous article road transport European Agreement (ADR) number plate;
and if so, identifying the ADR number plate hung by the target vehicle.
According to a first aspect of embodiments of the present invention, there is provided a number plate recognition apparatus, the apparatus including:
the acquisition module is used for acquiring a current frame image; the current frame image comprises a target vehicle;
the vehicle type identification module is used for identifying vehicle type information of a target vehicle from the current frame image;
the inspection module is used for inspecting whether the vehicle type information is vehicle type information of a specified vehicle type, wherein the specified vehicle type is a vehicle type used for hanging a hazardous article road transport European Agreement (ADR) number plate;
and the number plate identification module is used for identifying the ADR number plate hung by the target vehicle if the vehicle type information is the vehicle type information of the specified vehicle type.
The technical scheme provided by the embodiment of the invention can have the following beneficial effects:
in the embodiment of the invention, the current frame image is collected, the current frame image comprises the target vehicle, the vehicle type information of the target vehicle is identified from the current frame image, whether the vehicle type information is the vehicle type information of the specified vehicle type is checked, the specified vehicle type is the vehicle type used for hanging the ADR number plate of the highway transportation of the dangerous goods, if so, the ADR number plate hung by the target vehicle is identified, the ADR number plate hung by the vehicle for transporting the dangerous goods can be identified, the dangerous goods category is determined according to the ADR number plate, and the classification of the dangerous goods is realized, so that the vehicle for transporting the dangerous goods and the dangerous goods category transported by the vehicle can be monitored.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
Fig. 1 is a flowchart illustrating a license plate identification method according to an embodiment of the present invention.
Fig. 2 is an exemplary diagram of an ADR number plate provided in an embodiment of the present invention.
Fig. 3 is a functional block diagram of a license plate recognition device according to an embodiment of the present invention.
Fig. 4 is a hardware configuration diagram of the number plate recognition apparatus according to the embodiment of the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.
The terminology used in the description is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present invention. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
The following provides a detailed description of embodiments of the present invention.
One application scenario of the license plate identification method of the embodiment of the invention can be as follows: the image acquisition equipment arranged on the road acquires the images of passing vehicles in real time, then the image acquisition equipment detects the vehicles by using the number plate identification method of the embodiment of the invention, and outputs the ADR number plate of the vehicle when the vehicle is a vehicle with the quality of transportation dangerous goods.
Another application scenario of the license plate identification method of the embodiment of the invention may be as follows: the image acquisition equipment arranged on a road is connected with the remote server through a communication network, the image acquisition equipment acquires images of passing vehicles in real time, then the image acquisition equipment sends the acquired images of the vehicles to the remote server through the communication network, and the remote server detects the vehicles by using the number plate identification method of the embodiment of the invention and outputs the ADR number plates of the vehicles when the vehicles are the vehicles with transportation dangerous goods qualification.
The image acquisition device or the remote server can further send the dangerous goods number plate of the vehicle to the designated device, so that the ADR number plate of the vehicle is displayed on the designated terminal. For example, the designated terminal may be a road monitoring display screen.
The above is an example of an application scenario of the license plate identification method according to the embodiment of the present invention, and is not intended to limit the application scenario of the license plate identification method according to the embodiment of the present invention.
Fig. 1 is a flowchart illustrating a license plate identification method according to an embodiment of the present invention. As shown in fig. 1, the method may include the steps of:
s101, acquiring a current frame image, wherein the current frame image comprises a target vehicle.
And S102, recognizing the vehicle type information of the target vehicle from the current frame image.
S103, checking whether the vehicle type information is the vehicle type information of the specified vehicle type, wherein the specified vehicle type is the vehicle type used for hanging the European Agreement ADR number plate for dangerous goods road transportation.
And S104, if so, identifying the ADR number plate hung by the target vehicle.
In step S101, the current frame image may be an image containing a license plate number area of the vehicle, such as a front image of the vehicle, or a rear image of the vehicle. When the target vehicle is a vehicle transporting a hazardous material, the current frame image may be an image including a license plate number area and an ADR number area of the vehicle.
In application, the current frame image can be acquired by an image acquisition device installed on a road. For example, a current frame image is acquired by a camera mounted on a traffic bar.
The current frame image may contain acquisition time information and/or frame number information. By collecting the time information and/or the frame number information, the position of the current frame image in the image sequence can be determined.
In step S102, the vehicle type information refers to information that can indicate what type of vehicle the vehicle is. In one example, the trained model recognition network model may be utilized to recognize the model information of the target vehicle from the current frame image. The current frame image is input into the trained vehicle type recognition network model, and the vehicle type recognition network model recognizes the vehicle type information of the target vehicle from the current frame image.
The vehicle types can be classified into trucks, cars and the like.
The designated vehicle type is a vehicle type used for hanging a dangerous goods road transport European agreement ADR number plate. For example, the designated vehicle model may be a truck.
In an application, it may be specified which vehicle models can transport the hazardous materials, thereby determining which vehicle models are used to hang the ADR number plate.
For example, if the specification states that only trucks can transport hazardous materials, the trucks may be used to hang ADR number plates.
After the model information of the target vehicle is recognized, it is determined whether the target vehicle is a vehicle transporting dangerous goods by determining what type of vehicle the target vehicle is based on the model information of the target vehicle in step S102. Further, it is determined whether to start the program for identifying the ADR number plate according to whether the target vehicle is a vehicle transporting a hazardous material. If the target vehicle is a vehicle transporting a hazardous material, the program for identifying the ADR number plate is activated, and if the target vehicle is not a vehicle transporting a hazardous material, the program for identifying the ADR number plate is not activated. Thus, the number of calls to the ADR number plate recognition program can be reduced, and resource consumption is reduced.
In step S103, in one example, when the vehicle type information is the vehicle length, the manner of checking whether the vehicle type information is the vehicle type information of the specified vehicle type may be:
determining whether the length of the vehicle is greater than a set length threshold;
if so, determining the vehicle type information as the vehicle type information of the specified vehicle type;
if not, determining that the vehicle type information is not the vehicle type information of the specified vehicle type.
In another example, when the vehicle type information is the vehicle height, the manner of checking whether the vehicle type information is the vehicle type information of the specified vehicle type may be:
determining whether the vehicle height is greater than a set height threshold;
if so, determining the vehicle type information as the vehicle type information of the specified vehicle type;
if not, determining that the vehicle type information is not the vehicle type information of the specified vehicle type.
In step S104, the ADR number plate is recognized only when the vehicle type information is checked as the vehicle type information of the designated vehicle type, and the ADR number plate is not recognized when the vehicle type information is not checked as the vehicle type information of the designated vehicle type. Thus, on the one hand, the identification of the ADR number plate of the vehicle for transporting the dangerous goods is ensured, and because the ADR number plate of the vehicle of the specified vehicle type is identified on the basis of the fact that the ADR number plates are hung on the vehicle (such as a truck) of the specified vehicle type, the identification of the ADR number plate of all the vehicles hanging the ADR number plates can be realized. On the other hand, because the ADR number plate recognition is only carried out on the vehicles of the specified vehicle type, but not all the vehicles, the calling times of the ADR number plate recognition program are reduced, and the resource consumption is reduced.
Through the ADR number plate recognition in step S104, it is possible to know not only what the transport object of the vehicle is a dangerous object, but also what kind of dangerous object the transport object is based on the ADR number plate, thereby realizing the classification of the dangerous object.
As can be seen from fig. 1, in the number plate identification method provided in the embodiment of the present invention, a current frame image is acquired, the current frame image includes a target vehicle, vehicle type information of the target vehicle is identified from the current frame image, it is checked whether the vehicle type information is vehicle type information of a designated vehicle type, the designated vehicle type is a vehicle type used for suspending an ADR number plate of a highway transportation of a hazardous article, if so, an ADR number plate suspended by the target vehicle is identified, the ADR number plate suspended by the vehicle transporting the hazardous article can be identified, and a hazardous article category is determined according to the ADR number plate, so that hazardous article classification is realized, and thus, the vehicle transporting the hazardous article and the hazardous article category transported by the vehicle can be monitored.
In addition, the number plate recognition method provided by the embodiment of the invention only performs ADR number plate recognition on the vehicle of the specified vehicle type and does not perform ADR number plate recognition on the vehicles of other vehicle types based on the fact that all the ADR number plates are hung on the vehicle of the specified vehicle type, so that the calling times of ADR number plate recognition programs are reduced, and the resource consumption is reduced.
In an exemplary implementation process, before step S104, the method may further include:
identifying first license plate information of a target vehicle from the current frame image;
step S104 includes: identifying whether the first license plate information is the same as the second license plate information, wherein the second license plate information is the license plate information identified from the previous frame image of the current frame image; if the number of the ADR number plates is the same as the number plate of the ADR number plate suspended by the target vehicle, the ADR number plate identified from the previous frame image is determined as the number plate of the ADR number plate suspended by the target vehicle; if the difference is not the same, the ADR number plate hung by the target vehicle is identified from the current frame image.
In one example, the previous frame image of the current frame image may be determined by a frame number included in the image. For example, if the frame number of the current frame image is n, where n is a natural number, the image with the frame number of n-1 is the previous frame image of the current frame image.
In another example, the previous frame image of the current frame image may be determined by acquisition time information included in the image. For example, the acquisition time of the current frame image is t1, and the image whose acquisition time t2 is before t1 and the time difference between t2 and t1 is the image of the previous frame of the current frame image.
When the vehicle is subjected to image acquisition, continuous snapshot is generally performed. In the case of such continuous snap shots, the vehicles in the two images snap back and forth are likely to be the same vehicle. Because each vehicle has a corresponding license plate number, and the license plates of different vehicles are different, the vehicles in the two images captured before and after can be determined to be the same vehicle when the license plates of the vehicles in the two images captured after are the same. When the current frame image is collected, the previous frame image has already finished the identification of the ADR number plate, and the ADR number plate of the vehicle is obtained, so that the current frame image can directly use the identification result of the ADR number plate of the previous frame image, and the ADR number plate identification program does not need to be called to identify the ADR number plate of the vehicle in the current frame image. Therefore, the ADR number plate of the vehicle in the current frame image is obtained, the calling of an ADR number plate identification program is reduced, the ADR number plate identification process is simplified, the consumed time is reduced, the identification speed is improved, and the resource consumption is further reduced.
In one exemplary implementation, identifying an ADR number plate of a target vehicle suspension from a current frame image includes:
positioning the lower layer characters of the ADR number plate from the current frame image;
positioning the upper layer characters of the ADR number plate from the current frame image;
and inputting the characters of the upper layer and the characters of the lower layer into the trained recognition model, and recognizing the ADR number plate hung by the target vehicle according to the composition mode of the ADR number plate by the recognition model.
In one example, before locating the lower-layer character of the ADR number plate from the current frame image, the method may further include:
the image area where the ADR number plate is located is determined.
Fig. 2 is an exemplary diagram of an ADR number plate provided in an embodiment of the present invention. As shown in fig. 2, the character of the ADR number plate is formed in a manner that has certain characteristics, so that the image area where the ADR number plate is located can be found from the current frame image according to the characteristics.
For example, the ADR number plate has upper and lower characters, and the number of the lower characters is a set number. Therefore, all character areas can be found from the current frame image, and then whether the character areas have two layers of characters or not is judged, if the character areas only have one layer of characters or have more than 3 layers of characters, the character areas are not the image areas where the ADR number plate is located.
If the character area has two layers of characters, further judging whether the number of the lower layer characters is the set number. For example, the number of lower characters of the ADR number plate is 4. If the number of the lower layer characters in the character area is more than 4 or less than 4, it is indicated that the character area is not the image area where the ADR number plate is located. If the number of lower characters in the character area is equal to 4, the character area is an image area where the ADR number plate is located.
In one exemplary implementation, locating the upper characters of the ADR number plate from the current frame image may include:
segmenting the lower-layer characters of the ADR number plate to obtain single lower-layer characters;
the upper layer character above each single lower layer character is positioned in the current frame image, and each single lower layer character is as high as the upper layer character.
Generally, the character area of the ADR number plate has two layers of characters, the number of lower layer characters is greater than the number of upper layer characters, and the position of the upper layer characters has a corresponding relationship with the position of a designated character in the lower layer characters. In this case, the upper character can be positioned in the manner in the present example, which enables the upper character to be positioned more quickly.
For example, the ADR number plate has 4 lower characters, 2 upper characters, and two upper characters spaced above the 2 nd lower character and the 3 rd lower character. Then, after the lower layer character is positioned, the lower layer character can be segmented to obtain a single lower layer character, then the upper layer character positioned above the character is directly positioned according to the 2 nd lower layer character, and the upper layer character positioned above the character is positioned according to the 3 rd lower layer character. Thus, the upper layer characters can be quickly and accurately positioned.
In other embodiments, the upper characters of the ADR number plate may be located from the current frame image in the same manner as the lower characters of the ADR number plate are located.
In one exemplary implementation, the identification model identifies the ADR number plate suspended by the target vehicle according to a composition manner of the ADR number plate, including:
the recognition model recognizes each input character, and checks whether the recognized character types are all designated character types, wherein the designated character types are the types of each character in the ADR number plate;
and when the type of each recognized character is a designated character type, generating an ADR number plate hung by the target vehicle by using each recognized character.
In general, for the ADR number plate, not only the composition of characters in the ADR number plate but also the character type of the characters in the ADR number plate are specified.
For example, if the character type of the ADR number plate is specified as Arabic numerals, the corresponding ADR number plate is shown in FIG. 2. At this time, when all the types of characters recognized by the recognition model are arabic numerals, an ADR number is generated and output using the recognized characters. When the type of the character recognized by the recognition model has Arabic numerals and English letters, the recognition model does not output an ADR number.
Based on the method embodiment, the embodiment of the application also provides corresponding device, equipment and storage medium embodiments.
Fig. 3 is a functional block diagram of a license plate recognition device according to an embodiment of the present invention. As shown in fig. 3, in the present embodiment, the number plate recognition apparatus may include:
an acquisition module 310, configured to acquire a current frame image; the current frame image includes a target vehicle.
And a vehicle type identification module 320, configured to identify vehicle type information of the target vehicle from the current frame image.
And the checking module 330 is used for checking whether the vehicle type information is the vehicle type information of a specified vehicle type, and the specified vehicle type is the vehicle type used for hanging the European Agreement ADR number plate for dangerous goods road transportation.
And a number plate recognition module 340, configured to recognize an ADR number plate suspended by the target vehicle if the vehicle type information is vehicle type information of a specified vehicle type.
In one exemplary implementation, the number plate recognition apparatus may further include:
the license plate recognition module is used for recognizing first license plate information of the target vehicle from the current frame image;
the number plate recognition module 340 is specifically configured to:
identifying whether the first license plate information is the same as second license plate information, wherein the second license plate information is license plate information identified from a previous frame image of a current frame image;
if the number of the ADR number plates is the same as the number plate of the ADR number plate suspended by the target vehicle, determining the number plate of the ADR number plate identified from the previous frame image as the number plate of the ADR number plate suspended by the target vehicle;
and if the difference is not the same, identifying the ADR number plate hung by the target vehicle from the current frame image.
In an exemplary implementation, the number plate recognition module 340, when configured to recognize the ADR number plate suspended by the target vehicle from the current frame image, is specifically configured to:
positioning the lower layer characters of the ADR number plate from the current frame image;
positioning upper layer characters of an ADR number plate from the current frame image;
and inputting each upper layer character and each lower layer character into a trained recognition model, and recognizing the ADR number plate hung by the target vehicle by the recognition model according to the composition mode of the ADR number plate.
In an exemplary implementation process, the license plate recognition module 340, when being configured to locate an upper character of each lower character from the current frame image, is specifically configured to:
segmenting the lower-layer characters of the ADR number plate to obtain single lower-layer characters;
and positioning an upper layer character above each single lower layer character in the current frame image, wherein each single lower layer character is as high as the upper layer character.
In an exemplary implementation, the identification model, when used to identify the ADR number plate suspended by the target vehicle according to its composition, is specifically configured to:
the recognition model recognizes each input character, and checks whether the recognized types of the characters are all specified character types, wherein the specified character types are the types of the characters in an ADR number plate;
and when the type of each recognized character is a designated character type, generating an ADR number plate hung by the target vehicle by using each recognized character.
The embodiment of the invention also provides a number plate identification device. Fig. 4 is a hardware configuration diagram of the number plate recognition apparatus according to the embodiment of the present invention. As shown in fig. 4, the number plate recognizing apparatus includes: an internal bus 401, and a memory 402, a processor 403, and an external interface 404, which are connected through the internal bus, wherein,
the processor 403 is configured to read the machine-readable instructions in the memory 402 and execute the instructions to implement the following operations:
acquiring a current frame image; the current frame image comprises a target vehicle;
identifying vehicle type information of a target vehicle from the current frame image;
checking whether the vehicle type information is vehicle type information of a specified vehicle type, wherein the specified vehicle type is a vehicle type used for hanging a hazardous article road transport European Agreement (ADR) number plate;
and if so, identifying the ADR number plate hung by the target vehicle.
In an exemplary implementation, the processor 403 further executes the instructions to implement the following operations:
identifying first license plate information of a target vehicle from the current frame image;
identifying whether the first license plate information is the same as second license plate information, wherein the second license plate information is license plate information identified from a previous frame image of a current frame image;
if the number of the ADR number plates is the same as the number plate of the ADR number plate suspended by the target vehicle, determining the number plate of the ADR number plate identified from the previous frame image as the number plate of the ADR number plate suspended by the target vehicle;
and if the difference is not the same, identifying the ADR number plate hung by the target vehicle from the current frame image.
In an exemplary implementation, the processor 403 further executes the instructions to implement the following operations:
positioning the lower layer characters of the ADR number plate from the current frame image;
positioning upper layer characters of an ADR number plate from the current frame image;
and inputting each upper layer character and each lower layer character into a trained recognition model, and recognizing the ADR number plate hung by the target vehicle by the recognition model according to the composition mode of the ADR number plate.
In an exemplary implementation, the processor 403 further executes the instructions to implement the following operations:
segmenting the lower-layer characters of the ADR number plate to obtain single lower-layer characters;
and positioning an upper layer character above each single lower layer character in the current frame image, wherein each single lower layer character is as high as the upper layer character.
In one exemplary implementation, the identification model identifies the ADR number plate suspended by the target vehicle according to a composition manner of the ADR number plate, including:
the recognition model recognizes each input character, and checks whether the recognized types of the characters are all specified character types, wherein the specified character types are the types of the characters in an ADR number plate;
and when the type of each recognized character is a designated character type, generating an ADR number plate hung by the target vehicle by using each recognized character.
An embodiment of the present invention further provides a computer-readable storage medium, where a plurality of computer instructions are stored on the computer-readable storage medium, and when executed, the computer instructions perform the following processing:
acquiring a current frame image; the current frame image comprises a target vehicle;
identifying vehicle type information of a target vehicle from the current frame image;
checking whether the vehicle type information is vehicle type information of a specified vehicle type, wherein the specified vehicle type is a vehicle type used for hanging a hazardous article road transport European Agreement (ADR) number plate;
and if so, identifying the ADR number plate hung by the target vehicle.
In one exemplary implementation, the computer instructions when executed further perform the following:
identifying first license plate information of a target vehicle from the current frame image;
identifying whether the first license plate information is the same as second license plate information, wherein the second license plate information is license plate information identified from a previous frame image of a current frame image;
if the number of the ADR number plates is the same as the number plate of the ADR number plate suspended by the target vehicle, determining the number plate of the ADR number plate identified from the previous frame image as the number plate of the ADR number plate suspended by the target vehicle;
and if the difference is not the same, identifying the ADR number plate hung by the target vehicle from the current frame image.
In one exemplary implementation, the computer instructions when executed further perform the following:
positioning the lower layer characters of the ADR number plate from the current frame image;
positioning upper layer characters of an ADR number plate from the current frame image;
and inputting each upper layer character and each lower layer character into a trained recognition model, and recognizing the ADR number plate hung by the target vehicle by the recognition model according to the composition mode of the ADR number plate.
In one exemplary implementation, the computer instructions when executed further perform the following:
segmenting the lower-layer characters of the ADR number plate to obtain single lower-layer characters;
and positioning an upper layer character above each single lower layer character in the current frame image, wherein each single lower layer character is as high as the upper layer character.
In one exemplary implementation, the identification model identifies the ADR number plate suspended by the target vehicle according to a composition manner of the ADR number plate, including:
the recognition model recognizes each input character, and checks whether the recognized types of the characters are all specified character types, wherein the specified character types are the types of the characters in an ADR number plate;
and when the type of each recognized character is a designated character type, generating an ADR number plate hung by the target vehicle by using each recognized character.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, wherein the modules described as separate parts may or may not be physically separate, and the parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the invention. One of ordinary skill in the art can understand and implement it without inventive effort.
The foregoing description of specific embodiments of the present invention has been presented. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method of identifying a number plate, the method comprising:
acquiring a current frame image; the current frame image comprises a target vehicle;
identifying vehicle type information of a target vehicle from the current frame image;
checking whether the vehicle type information is vehicle type information of a specified vehicle type, wherein the specified vehicle type is a vehicle type used for hanging a hazardous article road transport European Agreement (ADR) number plate;
and if so, identifying the ADR number plate hung by the target vehicle.
2. The method of claim 1, further comprising, prior to identifying the ADR number plate from which the target vehicle is suspended: identifying first license plate information of a target vehicle from the current frame image;
the ADR number plate for identifying the suspension of the target vehicle comprises:
identifying whether the first license plate information is the same as second license plate information, wherein the second license plate information is license plate information identified from a previous frame image of a current frame image;
if the number of the ADR number plates is the same as the number plate of the ADR number plate suspended by the target vehicle, determining the number plate of the ADR number plate identified from the previous frame image as the number plate of the ADR number plate suspended by the target vehicle;
and if the difference is not the same, identifying the ADR number plate hung by the target vehicle from the current frame image.
3. The method of claim 2, wherein said identifying the ADR plate of the target vehicle suspension from the current frame image comprises:
positioning the lower layer characters of the ADR number plate from the current frame image;
positioning upper layer characters of an ADR number plate from the current frame image;
and inputting each upper layer character and each lower layer character into a trained recognition model, and recognizing the ADR number plate hung by the target vehicle by the recognition model according to the composition mode of the ADR number plate.
4. The method of claim 3, wherein said locating the upper characters of the ADR number plate from the current frame image comprises:
segmenting the lower-layer characters of the ADR number plate to obtain single lower-layer characters;
and positioning an upper layer character above each single lower layer character in the current frame image, wherein each single lower layer character is as high as the upper layer character.
5. The method of claim 3, wherein the identification model identifies an ADR number plate suspended by the target vehicle according to a composition of the ADR number plate, comprising:
the recognition model recognizes each input character, and checks whether the recognized types of the characters are all specified character types, wherein the specified character types are the types of the characters in an ADR number plate;
and when the type of each recognized character is a designated character type, generating an ADR number plate hung by the target vehicle by using each recognized character.
6. A number plate identification device, the device comprising:
the acquisition module is used for acquiring a current frame image; the current frame image comprises a target vehicle;
the vehicle type identification module is used for identifying vehicle type information of a target vehicle from the current frame image;
the inspection module is used for inspecting whether the vehicle type information is vehicle type information of a specified vehicle type, wherein the specified vehicle type is a vehicle type used for hanging a hazardous article road transport European Agreement (ADR) number plate;
and the number plate identification module is used for identifying the ADR number plate hung by the target vehicle if the vehicle type information is the vehicle type information of the specified vehicle type.
7. The apparatus of claim 6, further comprising:
the license plate recognition module is used for recognizing first license plate information of the target vehicle from the current frame image;
the number plate identification module is specifically used for:
identifying whether the first license plate information is the same as second license plate information, wherein the second license plate information is license plate information identified from a previous frame image of a current frame image;
if the number of the ADR number plates is the same as the number plate of the ADR number plate suspended by the target vehicle, determining the number plate of the ADR number plate identified from the previous frame image as the number plate of the ADR number plate suspended by the target vehicle;
and if the difference is not the same, identifying the ADR number plate hung by the target vehicle from the current frame image.
8. The apparatus of claim 7, wherein the number plate identification module, when configured to identify the ADR number plate suspended by the target vehicle from the current frame image, is specifically configured to:
positioning the lower layer characters of the ADR number plate from the current frame image;
positioning upper layer characters of an ADR number plate from the current frame image;
and inputting each upper layer character and each lower layer character into a trained recognition model, and recognizing the ADR number plate hung by the target vehicle by the recognition model according to the composition mode of the ADR number plate.
9. The apparatus of claim 8, wherein the number plate recognition module, when configured to locate the upper characters of the ADR number plate from the current frame image, is specifically configured to:
segmenting the lower-layer characters of the ADR number plate to obtain single lower-layer characters;
and positioning an upper layer character above each single lower layer character in the current frame image, wherein each single lower layer character is as high as the upper layer character.
10. The apparatus of claim 8, wherein the recognition model, when used to identify an ADR number plate from which the target vehicle is suspended, is specifically configured to:
the recognition model recognizes each input character, and checks whether the recognized types of the characters are all specified character types, wherein the specified character types are the types of the characters in an ADR number plate;
and when the type of each recognized character is a designated character type, generating an ADR number plate hung by the target vehicle by using each recognized character.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910395165.6A CN111931545B (en) | 2019-05-13 | 2019-05-13 | License plate identification method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910395165.6A CN111931545B (en) | 2019-05-13 | 2019-05-13 | License plate identification method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111931545A true CN111931545A (en) | 2020-11-13 |
CN111931545B CN111931545B (en) | 2023-10-31 |
Family
ID=73282810
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910395165.6A Active CN111931545B (en) | 2019-05-13 | 2019-05-13 | License plate identification method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111931545B (en) |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20050068858A (en) * | 2003-12-30 | 2005-07-05 | 인천대학교 산학협력단 | Transport system of dangerous articles |
US20090058593A1 (en) * | 2002-06-11 | 2009-03-05 | Intelligent Technologies International, Inc. | Hazardous Material Transportation Monitoring Techniques |
CN103324920A (en) * | 2013-06-27 | 2013-09-25 | 华南理工大学 | Method for automatically identifying vehicle type based on vehicle frontal image and template matching |
CN103364814A (en) * | 2013-06-28 | 2013-10-23 | 青岛利发科工贸有限公司 | Road hazard cargo transportation monitoring system and method based on Beidou |
KR20140015045A (en) * | 2012-07-27 | 2014-02-06 | 한국철도기술연구원 | Management method of dangerous article transport car and management apparatus of dangerous article transport car using the method |
CN105373782A (en) * | 2015-11-16 | 2016-03-02 | 深圳市哈工大交通电子技术有限公司 | Method of automatically recognizing hazardous chemical vehicle from image or video |
CN105427614A (en) * | 2015-08-28 | 2016-03-23 | 北京动视元科技有限公司 | Model classification system and method |
CN106553655A (en) * | 2016-12-02 | 2017-04-05 | 深圳地平线机器人科技有限公司 | Hazardous vehicles detection method and system and the vehicle including the system |
CN107506803A (en) * | 2017-08-28 | 2017-12-22 | 河北交投智能交通技术有限责任公司 | Full-automatic intelligent coma card control method based on car plate vehicle |
CN108268994A (en) * | 2016-12-31 | 2018-07-10 | 山东安星危化品信息有限公司 | A kind of harmful influence managing and control system and information management platform |
CN108875600A (en) * | 2018-05-31 | 2018-11-23 | 银江股份有限公司 | A kind of information of vehicles detection and tracking method, apparatus and computer storage medium based on YOLO |
CN109001833A (en) * | 2018-06-22 | 2018-12-14 | 天和防务技术(北京)有限公司 | A kind of Terahertz hazardous material detection method based on deep learning |
CN109063544A (en) * | 2018-06-12 | 2018-12-21 | 深圳中兴网信科技有限公司 | A kind of method, system, computer equipment and the storage medium of dump truck detection |
-
2019
- 2019-05-13 CN CN201910395165.6A patent/CN111931545B/en active Active
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090058593A1 (en) * | 2002-06-11 | 2009-03-05 | Intelligent Technologies International, Inc. | Hazardous Material Transportation Monitoring Techniques |
KR20050068858A (en) * | 2003-12-30 | 2005-07-05 | 인천대학교 산학협력단 | Transport system of dangerous articles |
KR20140015045A (en) * | 2012-07-27 | 2014-02-06 | 한국철도기술연구원 | Management method of dangerous article transport car and management apparatus of dangerous article transport car using the method |
CN103324920A (en) * | 2013-06-27 | 2013-09-25 | 华南理工大学 | Method for automatically identifying vehicle type based on vehicle frontal image and template matching |
CN103364814A (en) * | 2013-06-28 | 2013-10-23 | 青岛利发科工贸有限公司 | Road hazard cargo transportation monitoring system and method based on Beidou |
CN105427614A (en) * | 2015-08-28 | 2016-03-23 | 北京动视元科技有限公司 | Model classification system and method |
CN105373782A (en) * | 2015-11-16 | 2016-03-02 | 深圳市哈工大交通电子技术有限公司 | Method of automatically recognizing hazardous chemical vehicle from image or video |
CN106553655A (en) * | 2016-12-02 | 2017-04-05 | 深圳地平线机器人科技有限公司 | Hazardous vehicles detection method and system and the vehicle including the system |
CN108268994A (en) * | 2016-12-31 | 2018-07-10 | 山东安星危化品信息有限公司 | A kind of harmful influence managing and control system and information management platform |
CN107506803A (en) * | 2017-08-28 | 2017-12-22 | 河北交投智能交通技术有限责任公司 | Full-automatic intelligent coma card control method based on car plate vehicle |
CN108875600A (en) * | 2018-05-31 | 2018-11-23 | 银江股份有限公司 | A kind of information of vehicles detection and tracking method, apparatus and computer storage medium based on YOLO |
CN109063544A (en) * | 2018-06-12 | 2018-12-21 | 深圳中兴网信科技有限公司 | A kind of method, system, computer equipment and the storage medium of dump truck detection |
CN109001833A (en) * | 2018-06-22 | 2018-12-14 | 天和防务技术(北京)有限公司 | A kind of Terahertz hazardous material detection method based on deep learning |
Also Published As
Publication number | Publication date |
---|---|
CN111931545B (en) | 2023-10-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9405988B2 (en) | License plate recognition | |
US10853936B2 (en) | Failed vehicle estimation system, failed vehicle estimation method and computer-readable non-transitory storage medium | |
CN110874934B (en) | License plate recognition method, system and device | |
CN111986174A (en) | Defect detection method, defect detection device, electronic equipment and computer storage medium | |
CN110458086A (en) | Vehicle recognition methods and device again | |
CN103778787A (en) | Automobile artificial and informal license plate identification logical judgment method | |
CN111079621A (en) | Method and device for detecting object, electronic equipment and storage medium | |
CN111177168A (en) | Vehicle detection method and device | |
CN112396023A (en) | Fire detection method based on machine learning | |
CN113743377A (en) | Cargo handling monitoring method, system, equipment and computer storage medium | |
CN109087439B (en) | Bill checking method, terminal device, storage medium and electronic device | |
CN110070566A (en) | Information detecting method, device, computer equipment and readable storage medium storing program for executing | |
CN111931545A (en) | Number plate identification method and device | |
CN105448095B (en) | Method and apparatus are surveyed in a kind of yellow mark car test | |
CN109359683B (en) | Target detection method, device, terminal and computer-readable storage medium | |
CN114743384A (en) | Alarm method and device | |
CN115880632A (en) | Timeout stay detection method, monitoring device, computer-readable storage medium, and chip | |
CN109299729B (en) | Vehicle detection method and device | |
CN111401104B (en) | Classification model training method, classification method, device, equipment and storage medium | |
CN112507757B (en) | Vehicle behavior detection method, device and computer readable medium | |
CN113095311A (en) | License plate number recognition method and device and storage medium | |
CN108932453B (en) | Vehicle spare tire detection method and device | |
CN111523544A (en) | License plate type detection method and system, computer equipment and readable storage medium | |
CN111723601A (en) | Image processing method and device | |
CN114882597B (en) | Target behavior identification method and device and electronic equipment |
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 |