CN111081027B - License plate recognition method and device, computer device and readable storage medium - Google Patents
License plate recognition method and device, computer device and readable storage medium Download PDFInfo
- Publication number
- CN111081027B CN111081027B CN201911302459.6A CN201911302459A CN111081027B CN 111081027 B CN111081027 B CN 111081027B CN 201911302459 A CN201911302459 A CN 201911302459A CN 111081027 B CN111081027 B CN 111081027B
- Authority
- CN
- China
- Prior art keywords
- vehicles
- identified
- vehicle
- target
- unidentified
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Character Discrimination (AREA)
Abstract
The invention provides a license plate recognition method and device, a computer device and a readable storage medium, wherein the method comprises the following steps: acquiring video information comprising a plurality of target vehicles, wherein the video information comprises a plurality of frames of images; determining a plurality of target vehicles in a snapshot area from any frame of image of the video information; determining vehicles to be identified, the number of which is not more than a preset number, from the plurality of target vehicles according to the coordinate positions of the target vehicles in the image coordinate system; and identifying the license plate of the vehicle to be identified to obtain the license plate information of the vehicle to be identified. The license plate recognition method is used for solving the technical problem that the existing license plate recognition efficiency is low.
Description
Technical Field
The invention relates to the technical field of intelligent transportation, in particular to a license plate recognition method and device, a computer device and a readable storage medium.
Background
Vehicle snapshot and license plate recognition are important parts in the field of security protection. The existing license plate recognition is to shoot a single image through a monitoring camera and perform license plate recognition, or to collect vehicle videos through the monitoring camera and then perform license plate recognition on all vehicles in each frame of image in the videos. However, the former has low recognition accuracy, and the latter has a slow recognition speed.
Therefore, the existing license plate recognition efficiency is low.
Disclosure of Invention
The invention provides a license plate recognition method and device, a computer device and a readable storage medium, which are used for solving the technical problem of low license plate recognition efficiency in the prior art.
In a first aspect, an embodiment of the present invention provides a license plate recognition method, including:
acquiring video information comprising a plurality of target vehicles, wherein the video information comprises a plurality of frames of images;
determining a plurality of target vehicles in a snapshot area from any frame of image of the video information;
determining vehicles to be identified, the number of which is not more than a preset number, from the plurality of target vehicles according to the coordinate positions of the target vehicles in the image coordinate system;
and identifying the license plate of the vehicle to be identified to obtain the license plate information of the vehicle to be identified.
Optionally, the determining, from the plurality of target vehicles, a number of vehicles to be recognized that is not greater than a preset number according to the coordinate position of each target vehicle in the image coordinate system includes:
determining a recognized vehicle and an unidentified vehicle from the plurality of target vehicles, wherein the number of the plurality of target vehicles is equal to the sum of the number of the recognized vehicles and the number of the unidentified vehicles;
determining a coordinate position of each target vehicle in the identified vehicles in an image coordinate system and a coordinate position of each target vehicle in the unidentified vehicles in the image coordinate system, wherein each coordinate position comprises an abscissa position and an ordinate position;
sequencing each target vehicle in the identified vehicles according to the vertical coordinate positions from large to small to obtain sequenced identified vehicles;
sequencing each target vehicle in the unidentified vehicles according to the vertical coordinate positions from large to small to obtain sequenced unidentified vehicles;
and determining vehicles to be identified which are not more than a preset number from the sequenced identified vehicles and the sequenced unidentified vehicles.
Optionally, the determining, from the ranked identified vehicles and the ranked unidentified vehicles, that the number of vehicles to be identified is not greater than a preset number includes:
determining the number T of the target vehicles, the preset number n and the number C of the identified vehicles, wherein C is an integer not less than 0, T is an integer greater than 1, and n is a positive integer;
according to the size relationship between T, n and C, determining the number of the vehicles to be identified which is not more than a preset number from the sorted identified vehicles and the sorted unidentified vehicles.
Optionally, the determining, according to the magnitude relationship between T, n and C, the vehicle to be identified from the sorted identified vehicles and the sorted unidentified vehicles includes:
and if (T-C) is less than or equal to n and less than T, taking (T-C) sorted unidentified vehicles and the top n- (T-C) target vehicles selected from the C sorted identified vehicles as the vehicles to be identified.
Optionally, the determining, according to the magnitude relationship between T, n and C, the vehicle to be identified from the sorted identified vehicles and the sorted unidentified vehicles includes:
and if n < (T-C), taking the front n target vehicles selected from the (T-C) sequenced unidentified vehicles as the vehicles to be identified. Optionally, the determining, according to the magnitude relationship between T, n and C, the vehicle to be identified from the sorted identified vehicles and the sorted unidentified vehicles includes:
and if n is larger than T, taking T target vehicles as the vehicles to be identified.
Optionally, after the license plate of the vehicle to be recognized is recognized and the license plate information of the vehicle to be recognized is obtained, the method further includes:
marking the vehicle to be identified as an identified state, wherein the identified state is used for representing that the vehicle to be identified is an identified vehicle.
In a second aspect, an embodiment of the present invention provides a license plate recognition apparatus, including:
the system comprises a collecting unit, a processing unit and a processing unit, wherein the collecting unit is used for collecting and obtaining video information comprising a plurality of target vehicles, and the video information comprises a plurality of frames of images;
a first determination unit configured to determine a plurality of target vehicles located in a snapshot area from any one frame image of the video information;
the second determining unit is used for determining vehicles to be identified, which are not more than the preset number, from the target vehicles according to the coordinate positions of the target vehicles in the image coordinate system;
and the obtaining unit is used for carrying out license plate recognition on the vehicle to be recognized and obtaining the license plate information of the vehicle to be recognized.
Optionally, the second determining unit is configured to:
determining a recognized vehicle and an unidentified vehicle from the plurality of target vehicles;
determining a coordinate position of each target vehicle in the identified vehicles in an image coordinate system and a coordinate position of each target vehicle in the unidentified vehicles in the image coordinate system, wherein each coordinate position comprises an abscissa position and an ordinate position;
sequencing each target vehicle in the identified vehicles according to the vertical coordinate positions from large to small to obtain sequenced identified vehicles;
sequencing each target vehicle in the unidentified vehicles according to the vertical coordinate positions from large to small to obtain sequenced unidentified vehicles;
and determining vehicles to be identified which are not more than a preset number from the sequenced identified vehicles and the sequenced unidentified vehicles.
Optionally, the second determining unit is configured to:
determining the number T of the target vehicles, the preset number n and the number C of the identified vehicles, wherein C is an integer not less than 0, T is an integer greater than 1, and n is a positive integer;
according to the size relationship between T, n and C, determining the number of the vehicles to be identified which is not more than a preset number from the sorted identified vehicles and the sorted unidentified vehicles.
Optionally, the second determining unit is configured to:
and if (T-C) is less than or equal to n and less than T, taking (T-C) sorted unidentified vehicles and the top n- (T-C) target vehicles selected from the C sorted identified vehicles as the vehicles to be identified.
Optionally, the second determining unit is configured to:
and if n < (T-C), taking the front n target vehicles selected from the (T-C) sequenced unidentified vehicles as the vehicles to be identified.
Optionally, the second determining unit is configured to:
and if n is larger than T, taking T target vehicles as the vehicles to be identified.
Optionally, after the obtaining unit performs license plate recognition on the vehicle to be recognized to obtain license plate information of the vehicle to be recognized, the method further includes:
marking the vehicle to be identified as an identified state, wherein the identified state is used for representing that the vehicle to be identified is an identified vehicle.
In a third aspect, an embodiment of the present invention provides a computer apparatus, including:
the computer arrangement comprises a processor for implementing the steps of the license plate recognition method as described above when executing a computer program stored in a memory.
In a fourth aspect, an embodiment of the present invention provides a readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the license plate recognition method as described above.
The invention has the following beneficial effects:
the license plate recognition method, the license plate recognition device, the license plate recognition equipment and the computer readable storage medium provided by the invention have the advantages that the video information comprising a plurality of vehicles is acquired through collection, then a plurality of target vehicles positioned in the snapshot area are determined from any frame image of a plurality of frame images of the video information, then vehicles to be recognized which are not more than the preset number are determined from the plurality of target vehicles according to the coordinate positions of the target vehicles in an image coordinate system, and then the screened vehicles to be recognized are subjected to license plate recognition, so that the corresponding license plate information is acquired. That is to say, for the target vehicles in the snapshot area in each frame of image, according to the coordinate positions of the target vehicles in the image coordinate system, the target vehicles not greater than the preset number are screened out, that is, the target vehicles and the number of the target vehicles to be subjected to license plate recognition in each frame of image of the video are controlled, so that the license plate recognition accuracy is ensured, and the license plate recognition efficiency is improved.
Drawings
Fig. 1 is a flowchart of a method for recognizing a license plate according to an embodiment of the present invention;
fig. 2 is a flowchart of a method in step S103 of a license plate recognition method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a camera imaging system according to an embodiment of the present invention;
fig. 4 is a flowchart of a method in step S205 of a license plate recognition method according to an embodiment of the present invention;
fig. 5 is a block diagram of a license plate recognition device according to an embodiment of the present invention.
Detailed Description
The terms "first," "second," and the like in the description and claims of the present invention and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "comprises" and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
In order to better understand the technical solutions of the present invention, the technical solutions of the present invention are described in detail below with reference to the drawings and the specific embodiments, and it should be understood that the specific features in the embodiments and the embodiments of the present invention are detailed descriptions of the technical solutions of the present invention, and are not limitations of the technical solutions of the present invention, and the technical features in the embodiments and the embodiments of the present invention may be combined with each other without conflict.
Referring to fig. 1, an embodiment of the present invention provides a license plate recognition method, which specifically includes:
s101: acquiring video information comprising a plurality of vehicles, wherein the video information comprises a plurality of frames of images;
for example, in the time period a, video information including a plurality of vehicles is acquired by a single monitoring camera provided at the intersection. Furthermore, the vehicle may be a motor vehicle, such as a large truck, a car. It may also be a non-motor vehicle such as an electric bicycle or a motorcycle.
S102: determining a plurality of target vehicles in a snapshot area from any frame of image of the video information;
in a specific implementation process, the snapshot area may be an area preset for a video capture device (e.g., a surveillance camera), and once a vehicle is located in the snapshot area, a snapshot function of the video capture device is triggered, and the video capture device performs snapshot to obtain a corresponding image.
S103: determining vehicles to be identified, the number of which is not more than a preset number, from the plurality of target vehicles according to the coordinate positions of the target vehicles in the image coordinate system;
in a specific implementation process, the preset number may be a number set according to a specific setting condition of the number of the lanes at the intersection, for example, when the number of the lanes at the intersection is 2, the preset number may be 2, when the number of the lanes at the intersection is 3, the preset number may be 3, and the like. Of course, in practical applications, the preset number may be set according to other situations, and is not limited herein.
S104: and identifying the license plate of the vehicle to be identified to obtain the license plate information of the vehicle to be identified.
In a specific implementation process, the license plate information may be characters, letters, numbers, and the like included in the license plate.
The license plate recognition method and device, the computer device and the readable storage medium provided by the invention acquire video information comprising a plurality of vehicles by collection, then determine a plurality of target vehicles in a snapshot area from any frame image of a plurality of frame images of the video information, then determine vehicles to be recognized which are not more than a preset number from the plurality of target vehicles according to the coordinate position of each target vehicle in an image coordinate system, and then perform license plate recognition on the screened vehicles to be recognized, thereby acquiring corresponding license plate information. That is to say, for the target vehicles in the snapshot area in each frame of image, according to the coordinate positions of the target vehicles in the image coordinate system, the target vehicles not greater than the preset number are screened out, that is, the target vehicles and the number of the target vehicles to be subjected to license plate recognition in each frame of image of the video are controlled, so that the license plate recognition accuracy is ensured, and the license plate recognition efficiency is improved.
In a specific implementation process, the technical solutions in steps S101 to S104 may be adopted to screen out a certain number of vehicles to be recognized from target vehicles in all frames in video information acquired by a single monitoring camera, and perform license plate recognition on the vehicles to be recognized, so as to realize rapid recognition of the vehicles and ensure recognition accuracy.
In the embodiment of the present invention, please refer to fig. 2, step S103: according to the coordinate position of each target vehicle in the image coordinate system, vehicles to be recognized, the number of which is not more than the preset number, are determined from the plurality of target vehicles, and the method comprises the following steps:
s201: determining a recognized vehicle and an unidentified vehicle from the plurality of target vehicles, wherein the number of the plurality of target vehicles is equal to the sum of the number of the recognized vehicles and the number of the unidentified vehicles;
s202: determining a coordinate position of each target vehicle in the identified vehicles in an image coordinate system and a coordinate position of each target vehicle in the unidentified vehicles in the image coordinate system, wherein each coordinate position comprises an abscissa position and an ordinate position;
s203: sequencing each target vehicle in the identified vehicles according to the vertical coordinate positions from large to small to obtain sequenced identified vehicles;
s204: sequencing each target vehicle in the unidentified vehicles according to the vertical coordinate positions from large to small to obtain sequenced unidentified vehicles;
s205: and determining vehicles to be identified which are not more than a preset number from the sequenced identified vehicles and the sequenced unidentified vehicles.
In the specific implementation process, the step S203 and the step S204 are not executed in sequence, and may be executed first in step S203 and then in step S204, or may be executed first in step S204 and then in step S203, or may be executed in step S203 and step S204 at the same time. Fig. 2 shows a case where step S203 is executed first and then step S204 is executed.
In the embodiment of the invention, first, a recognized vehicle and an unidentified vehicle are determined from a plurality of target vehicles; for example, the first identifier may be used to characterize the corresponding target vehicle as a vehicle whose license plate has been recognized, that is, the first identifier characterizes the corresponding target vehicle as a recognized vehicle, that is, a vehicle identified by the first identifier among the target vehicles located in the snapshot area is a recognized vehicle, and other vehicles not identified by the first identifier among the target vehicles located in the snapshot area are unidentified vehicles. Namely, the number of the target vehicles in the snapshot area is equal to the sum of the number of the recognized vehicles and the number of the unrecognized vehicles. In a specific implementation process, the corresponding target vehicle can be characterized as a vehicle without license plate recognition through the second identifier, that is, the corresponding target vehicle is characterized as an unidentified vehicle through the second identifier. For example, the first identifier may be "1" and the second identifier may be "0". That is, the vehicle identified by the identifier "1" among the plurality of target vehicles located in the snapshot area is a recognized vehicle, and the vehicle identified by the identifier "0" is an unrecognized vehicle. Of course, those skilled in the art can set the corresponding identifier according to actual needs, and the setting is not limited herein.
Then, a coordinate position of each target vehicle in the identified vehicles in the image coordinate system and a coordinate position of each target vehicle in the unidentified vehicles in the image coordinate system are determined, wherein each coordinate position comprises an abscissa position and an ordinate position. Then, sequencing each target vehicle in the identified vehicles according to the vertical coordinate positions from large to small so as to obtain the sequenced identified vehicles; and sequencing each target vehicle in the unidentified vehicles according to the vertical coordinate from large to small to obtain the sequenced unidentified vehicles. That is, the recognized vehicles and the unrecognized vehicles are sorted in descending order of their vertical coordinates, respectively. The larger the ordinate position is, the higher the rank is, and conversely, the smaller the ordinate position is, the lower the rank is.
Then, after sortingAnd determining that the number of vehicles to be identified is not more than the preset number from the identified vehicles and the sequenced unidentified vehicles. That is to say, a certain number of vehicles to be recognized are further screened out according to the sorted recognized vehicles and the sorted unidentified vehicles, so that the required number of vehicles to be recognized are further screened out according to the coordinate positions of the target vehicles in the image coordinate system, and the license plate recognition accuracy is improved, and meanwhile, the recognition speed is improved. The inventor finds that in the practical research of license plate recognition, the larger the ordinate position of the target vehicle in the image coordinate system is, the closer the target vehicle is to the monitoring camera, and correspondingly, the higher the image resolution of the target vehicle is, the higher the license plate recognition accuracy is. In conjunction with the camera imaging schematic shown in fig. 3. Wherein f denotes the focal length of the camera lens, S denotes the distance of the real object D from the optical center O of the camera lens J, S1Representing the distance of an object imaging plane M from the center point of the lens J, M representing the distance of a real object D from the focal distance, M1Representing the distance of the imaging plane M from the focal length of the camera. Wherein m, m1The relationship to f is as follows:
f2＝m×m1 (1)
when the focal length f of the lens remains unchanged, m and m can be known from the formula (1)1Negative correlation, when the value of m decreases, m1The value of (a) increases.
Wherein, S, S1The relationship between f and f is as follows:
wherein m and S are positively correlated, that is, when the lens focal length f is kept constant and the value of m is reduced, the value of S is also reduced, and as can be seen by combining the formula (1) and the formula (2), S1And m1The value of (D) increases, that is, as the real object D gets closer to the camera, the phenomenon reflected on the imaging plane M is: the ordinate of the point P 'of the real object D on the imaging plane M through the lens optical center O will become larger and larger, and accordingly the size of the image D' of the real object D on the imaging plane M will become larger and larger. I.e. P 'in the image plane M in FIG. 3'The size of the ordinate of the point in the image coordinate system (xO' y) is inversely related to the size of m. Based on this, the larger the ordinate position of the target vehicle in the image coordinate system, the closer it is to the monitoring camera.
Therefore, the recognized vehicles and the unidentified vehicles are respectively sequenced from large to small through the vertical coordinate position, and the license plate recognition precision of a single monitoring camera can be regulated and controlled. For example, a vehicle with a larger ordinate position is preferentially selected for recognition, and the recognition accuracy is higher.
In the specific implementation process, an array is taken as an example to describe a process of screening a vehicle to be identified according to a coordinate position of a target vehicle in an image coordinate system, specifically, the identified vehicle and an unidentified vehicle may be distinguished by an array, for example, the identified array is Vr, the unidentified array is Vn, and Py represents a vertical coordinate of any target vehicle P in a single monitoring camera image coordinate system, when a snapshot area is Ω, if the target vehicle P located in the snapshot area Ω is an identified vehicle, the identified vehicle P is placed in the identified array Vr, and all elements in the identified array Vr are sorted from large to small according to a Py value; if the target vehicle P in the snapshot region omega is an unidentified vehicle, putting the target vehicle P into the unidentified array Vn, and sorting all elements in the unidentified array Vn from large to small according to Py values. And then, determining objects to be recognized which are ranked in the front and not more than the preset number from the ranked recognized array Vr and the ranked unrecognized array Vn, and taking the objects to be recognized as vehicles to be recognized, thereby improving the recognition precision of the license plate of a single monitoring camera.
In the specific implementation process, as shown in fig. 4, step S205: determining vehicles to be identified which are not greater than a preset number from the sequenced identified vehicles and the sequenced unidentified vehicles, wherein the method comprises the following steps:
s301: determining the number T of the target vehicles, the preset number n and the number C of the identified vehicles, wherein C is an integer not less than 0, T is an integer greater than 1, and n is a positive integer;
s302: according to the size relationship between T, n and C, determining the number of the vehicles to be identified which is not more than a preset number from the sorted identified vehicles and the sorted unidentified vehicles.
In the specific implementation process, the specific implementation process from step S301 to step S302 is as follows:
firstly, determining the number T of a plurality of target vehicles, presetting the number n, and the number C of recognized vehicles, wherein the number of the corresponding unidentified vehicles is (T-C), C is an integer not less than 0, T is an integer greater than 1, and n is a positive integer; then, according to the size relation between T, n and the number C, vehicles to be recognized which are not more than the preset number are determined from the sorted recognized vehicles and the sorted unidentified vehicles. For example, 8 target vehicles are located in the snapshot region Ω, and it is limited that each frame of image only needs to identify license plates of 4 target vehicles, where 3 identified vehicles are located in the snapshot region Ω, and 5 unidentified vehicles are correspondingly located in the snapshot region Ω. For another example, 5 target vehicles are located in the snapshot region Ω, and it is limited that each frame of image only needs to identify license plates of 2 target vehicles, where 3 identified vehicles are located in the snapshot region Ω, and then 2 unidentified vehicles are correspondingly located in the snapshot region Ω. Then, according to the magnitude relation between the current T, n and the current C, vehicles to be recognized which are not more than the preset number are further determined from the sorted recognized vehicles and the sorted unidentified vehicles. Due to the fact that the size relation between T, n and C corresponding to each frame of image in the video information changes along with the change of time, the license plate of the target vehicle is flexibly recognized, and meanwhile the license plate recognition accuracy is improved.
In the specific implementation process, step S302: according to the magnitude relation between T, n and C, the number of the vehicles to be recognized which are determined to be not more than the preset number from the sorted recognized vehicles and the sorted unidentified vehicles can be realized in the following three ways, but is not limited to the following three ways.
The first implementation manner comprises the following steps: and if (T-C) is less than or equal to n and less than T, taking (T-C) sorted unidentified vehicles and the front n- (T-C) target vehicles selected from the C sorted identified vehicles as the vehicles to be identified, wherein T is more than or equal to C. Specifically, if (T-C) ≦ n < T has (T-C) unidentified vehicles in the snapshot area of the current frame image, the (T-C) unidentified vehicles are preferentially taken as vehicles to be identified so as to perform license plate identification on the unidentified vehicles in the snapshot area as much as possible. Meanwhile, when the number of the vehicles is (T-C) < n, the front n- (T-C) target vehicles are selected from the C sorted recognized vehicles and are used as the vehicles to be recognized, so that the front n- (T-C) target vehicles selected from the sorted recognized vehicles are closer to the monitoring camera, and the accurate recognition of the license plates of the selected front n- (T-C) target vehicles is further ensured.
In the specific implementation process, if the results of multiple identifications of the same target vehicle are different, all identification results are counted, and the condition that more identical identification results appear is taken as the criterion. For example, if 5 repeated license plate identifications are performed on the target vehicle B, wherein a license plate identification result is a for 3 times, B for 1 time, and c for 1 time, the license plate of the target vehicle is finally used as an identification result.
The second implementation manner comprises the following steps: and if n < (T-C), taking the front n target vehicles selected from the (T-C) sequenced unidentified vehicles as the vehicles to be identified. Therefore, the front n target vehicles selected from the unidentified vehicles are closer to the monitoring camera, and the accurate identification of the license plates of the selected front n target vehicles is further ensured. If n < (T-C), because the single-frame image is limited to only identify the license plates of n target vehicles at most in the embodiment of the invention, in this way, the front n target vehicles are selected from the (T-C) sequenced unidentified vehicles as the vehicles to be identified, and the identification speed is ensured, and the identification precision of the license plate of the selected target vehicle is ensured.
The third implementation manner comprises the following steps: and if n is larger than T, taking T target vehicles as the vehicles to be identified. In the specific implementation process, T target vehicles exist in the snapshot area of the current frame image, and when T is less than n, all the T target vehicles in the snapshot area are used as objects to be identified as the number n of the target vehicles needing to be identified in a single frame is greater than the number T of the target vehicles in the snapshot area, so that the identification accuracy is ensured, and the effective utilization of the identification capacity is ensured.
In addition, if the recognized vehicles do not exist in the recognition area and T is larger than n, the front n vehicles are selected from the T unidentified vehicles in the snapshot area to serve as the vehicles to be recognized, and therefore recognition accuracy is guaranteed. Of course, the corresponding object to be recognized may also be determined according to the actual application scenario, and will not be described in detail herein.
In the embodiment of the present invention, in order to improve the efficiency of license plate recognition, in step S104: after the license plate of the vehicle to be recognized is recognized, the method further comprises the following steps:
marking the vehicle to be identified as an identified state, wherein the identified state is used for representing that the vehicle to be identified is an identified vehicle. In particular implementations, the identified vehicles and/or the unidentified vehicles may be marked accordingly, for example, the vehicle to be identified may be marked as an identified state and the unidentified vehicle may be marked as an unidentified state. Accordingly, the target object is marked in each frame of video information. Therefore, the recognized vehicles and/or the unrecognized vehicles in each frame can be quickly determined, so that the license plate recognition accuracy is improved, and the license plate recognition speed is increased.
Based on the same inventive concept, as shown in fig. 5, an embodiment of the present invention provides a license plate recognition device, including:
the system comprises a collecting unit 10, a processing unit and a processing unit, wherein the collecting unit is used for collecting and obtaining video information comprising a plurality of target vehicles, and the video information comprises a plurality of frames of images;
a first determination unit 20 configured to determine a plurality of target vehicles located in a snapshot area from any one frame image of the video information;
a second determining unit 30, configured to determine, according to the coordinate position of each target vehicle in the image coordinate system, vehicles to be recognized that are not greater than a preset number from the plurality of target vehicles;
the obtaining unit 40 is configured to perform license plate recognition on the vehicle to be recognized, and obtain license plate information of the vehicle to be recognized.
In the embodiment of the present invention, the second determining unit 30 is configured to:
determining a recognized vehicle and an unidentified vehicle from the plurality of target vehicles, wherein the number of the plurality of target vehicles is equal to the sum of the number of the recognized vehicles and the number of the unidentified vehicles;
determining a coordinate position of each target vehicle in the identified vehicles in an image coordinate system and a coordinate position of each target vehicle in the unidentified vehicles in the image coordinate system, wherein each coordinate position comprises an abscissa position and an ordinate position;
sequencing each target vehicle in the identified vehicles according to the vertical coordinate positions from large to small to obtain sequenced identified vehicles;
sequencing each target vehicle in the unidentified vehicles according to the vertical coordinate positions from large to small to obtain sequenced unidentified vehicles;
and determining vehicles to be identified which are not more than a preset number from the sequenced identified vehicles and the sequenced unidentified vehicles.
In the embodiment of the present invention, since the related implementation process in the license plate recognition device has been described in detail in the corresponding license plate recognition method, the implementation process is not limited herein.
In the embodiment of the present invention, the license plate recognition device may be specifically used at a traffic intersection, may also be used in a parking lot, and may also be used in other scenes for license plate recognition, which is not limited herein.
In the embodiment of the present invention, the second determining unit 30 is configured to:
determining the number T of the target vehicles, the preset number n and the number C of the identified vehicles, wherein C is an integer not less than 0, T is an integer greater than 1, and n is a positive integer;
according to the size relationship between T, n and C, determining the number of the vehicles to be identified which is not more than a preset number from the sorted identified vehicles and the sorted unidentified vehicles.
In the embodiment of the present invention, the second determining unit 30 is configured to:
and if (T-C) is less than or equal to n and less than T, taking (T-C) sorted unidentified vehicles and the top n- (T-C) target vehicles selected from the C sorted identified vehicles as the vehicles to be identified. In the embodiment of the present invention, the second determining unit 30 is configured to:
and if n < (T-C), taking the front n target vehicles selected from the (T-C) sequenced unidentified vehicles as the vehicles to be identified. In the embodiment of the present invention, the second determining unit 30 is configured to:
and if n is larger than T, taking T target vehicles as the vehicles to be identified.
In the embodiment of the present invention, after the obtaining unit 40 performs license plate recognition on the vehicle to be recognized to obtain license plate information of the vehicle to be recognized, the method further includes:
marking the vehicle to be identified as an identified state, wherein the identified state is used for representing that the vehicle to be identified is an identified vehicle.
Based on the same inventive concept, an embodiment of the present invention further provides a computer device, where the computer device includes a processor, and the processor is configured to implement the steps of the license plate recognition method as described above when executing a computer program stored in a memory.
Based on the same inventive concept, the embodiment of the present invention further provides a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the license plate recognition method as described above is implemented.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (9)
1. A license plate recognition method is characterized by comprising the following steps:
acquiring video information comprising a plurality of vehicles, wherein the video information comprises a plurality of frames of images;
determining a plurality of target vehicles in a snapshot area from any frame of image of the video information;
determining vehicles to be identified, the number of which is not more than a preset number, from the plurality of target vehicles according to the coordinate positions of the target vehicles in the image coordinate system;
carrying out license plate recognition on the vehicle to be recognized to obtain license plate information of the vehicle to be recognized;
wherein, according to the coordinate position of each target vehicle in the image coordinate system, the vehicle to be identified which is not more than the preset number is determined from the plurality of target vehicles, and the method comprises the following steps:
determining a recognized vehicle and an unidentified vehicle from the plurality of target vehicles, wherein the number of the plurality of target vehicles is equal to the sum of the number of the recognized vehicles and the number of the unidentified vehicles;
determining a coordinate position of each target vehicle in the identified vehicles in an image coordinate system and a coordinate position of each target vehicle in the unidentified vehicles in the image coordinate system, wherein each coordinate position comprises an abscissa position and an ordinate position;
sequencing each target vehicle in the identified vehicles according to the vertical coordinate positions from large to small to obtain sequenced identified vehicles;
sequencing each target vehicle in the unidentified vehicles according to the vertical coordinate positions from large to small to obtain sequenced unidentified vehicles;
and determining vehicles to be identified which are not more than a preset number from the sequenced identified vehicles and the sequenced unidentified vehicles.
2. The method of claim 1, wherein the determining of no more than a preset number of vehicles to be identified from the ranked identified vehicles and the ranked unidentified vehicles comprises:
determining the number T of the target vehicles, the preset number n and the number C of the identified vehicles, wherein C is an integer not less than 0, T is an integer greater than 1, and n is a positive integer;
according to the size relationship between T, n and C, determining the number of the vehicles to be identified which is not more than a preset number from the sequenced identified vehicles and the sequenced unidentified vehicles.
3. The method of claim 2, wherein the determining the vehicle to be identified from the ranked identified vehicles and the ranked unidentified vehicles according to a magnitude relationship between T, n and C comprises:
and if (T-C) is less than or equal to n and less than T, taking (T-C) sorted unidentified vehicles and the top n- (T-C) target vehicles selected from the C sorted identified vehicles as the vehicles to be identified.
4. The method of claim 2, wherein the determining the vehicle to be identified from the ranked identified vehicles and the ranked unidentified vehicles according to a magnitude relationship between T, n and C comprises:
and if n < (T-C), taking the front n target vehicles selected from the (T-C) sequenced unidentified vehicles as the vehicles to be identified.
5. The method of claim 2, wherein the determining the vehicle to be identified from the ranked identified vehicles and the ranked unidentified vehicles according to a magnitude relationship between T, n and C comprises:
and if n is larger than T, taking T target vehicles as the vehicles to be identified.
6. The method of claim 1, wherein after the license plate recognition of the vehicle to be recognized is performed to obtain the license plate information of the vehicle to be recognized, the method further comprises:
marking the vehicle to be identified as an identified state, wherein the identified state is used for representing that the vehicle to be identified is an identified vehicle.
7. A license plate recognition device, comprising:
the system comprises a collecting unit, a processing unit and a processing unit, wherein the collecting unit is used for collecting and obtaining video information comprising a plurality of target vehicles, and the video information comprises a plurality of frames of images;
a first determination unit configured to determine a plurality of target vehicles located in a snapshot area from any one frame image of the video information;
the second determining unit is used for determining vehicles to be identified, which are not more than the preset number, from the target vehicles according to the coordinate positions of the target vehicles in the image coordinate system;
the obtaining unit is used for carrying out license plate recognition on the vehicle to be recognized and obtaining license plate information of the vehicle to be recognized;
wherein the second determination unit is configured to:
determining a recognized vehicle and an unidentified vehicle from the plurality of target vehicles, wherein the number of the plurality of target vehicles is equal to the sum of the number of the recognized vehicles and the number of the unidentified vehicles;
determining a coordinate position of each target vehicle in the identified vehicles in an image coordinate system and a coordinate position of each target vehicle in the unidentified vehicles in the image coordinate system, wherein each coordinate position comprises an abscissa position and an ordinate position;
sequencing each target vehicle in the identified vehicles according to the vertical coordinate positions from large to small to obtain sequenced identified vehicles;
sequencing each target vehicle in the unidentified vehicles according to the vertical coordinate positions from large to small to obtain sequenced unidentified vehicles;
and determining vehicles to be identified which are not more than a preset number from the sequenced identified vehicles and the sequenced unidentified vehicles.
8. A computer arrangement, characterized in that the computer arrangement comprises a processor for implementing the steps of the license plate recognition method according to any one of claims 1-6 when executing a computer program stored in a memory.
9. A readable storage medium on which a computer program is stored, wherein the computer program, when executed by a processor, implements the license plate recognition method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911302459.6A CN111081027B (en) | 2019-12-17 | 2019-12-17 | License plate recognition method and device, computer device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911302459.6A CN111081027B (en) | 2019-12-17 | 2019-12-17 | License plate recognition method and device, computer device and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111081027A CN111081027A (en) | 2020-04-28 |
| CN111081027B true CN111081027B (en) | 2021-06-15 |
Family
ID=70315130
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911302459.6A Active CN111081027B (en) | 2019-12-17 | 2019-12-17 | License plate recognition method and device, computer device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111081027B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111881741A (en) * | 2020-06-22 | 2020-11-03 | 浙江大华技术股份有限公司 | License plate recognition method and device, computer equipment and computer-readable storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103679214B (en) * | 2013-12-20 | 2017-10-20 | 华南理工大学 | Vehicle checking method based on online Class area estimation and multiple features Decision fusion |
| KR101596896B1 (en) * | 2015-08-21 | 2016-02-23 | 백청열 | System for regulating vehicles using image from different kind camera and control system having the same |
| CN106874954A (en) * | 2017-02-20 | 2017-06-20 | 佛山市络思讯科技有限公司 | The method and relevant apparatus of a kind of acquisition of information |
| CN110163199A (en) * | 2018-09-30 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Licence plate recognition method, license plate recognition device, car license recognition equipment and medium |
| CN109887040B (en) * | 2019-02-18 | 2020-04-14 | 北京航空航天大学 | Moving target active sensing method and system for video monitoring |
| CN110188749A (en) * | 2019-05-09 | 2019-08-30 | 青岛讯极科技有限公司 | Designated vehicle Vehicle License Plate Recognition System and method under a kind of more vehicles |
-
2019
- 2019-12-17 CN CN201911302459.6A patent/CN111081027B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111081027A (en) | 2020-04-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107305627B (en) | Vehicle video monitoring method, server and system | |
| CN105702048B (en) | Highway front truck illegal road occupation identifying system based on automobile data recorder and method | |
| CN110751012B (en) | Target detection evaluation method and device, electronic equipment and storage medium | |
| WO2020258714A1 (en) | Rider re-identification method, apparatus and device | |
| CN111860219B (en) | High-speed channel occupation judging method and device and electronic equipment | |
| KR20160109761A (en) | Method and System for Recognition/Tracking Construction Equipment and Workers Using Construction-Site-Customized Image Processing | |
| CN109685062B (en) | Target detection method, device, equipment and storage medium | |
| CN112131935A (en) | Motor vehicle carriage manned identification method and device and computer equipment | |
| KR20200069911A (en) | Method and apparatus for identifying object and object location equality between images | |
| CN111081027B (en) | License plate recognition method and device, computer device and readable storage medium | |
| CN109670366A (en) | The license plate identifying approach and automobile-used photographic device of automobile-used photographic device | |
| CN106777350B (en) | Method and device for searching pictures with pictures based on bayonet data | |
| CN114821519A (en) | Traffic sign identification method and system based on coordinate attention | |
| CN113850237A (en) | Internet vehicle target detection and evaluation method and system based on video and track data | |
| CN104077924A (en) | Reverse vehicle finding system and method | |
| CN111553339A (en) | Image unit determination method, small target detection method and computer equipment | |
| CN110633606A (en) | Parking space identification method, device and equipment and storage medium | |
| CN106778765B (en) | License plate recognition method and device | |
| CN113014876A (en) | Video monitoring method and device, electronic equipment and readable storage medium | |
| CN113095345A (en) | Data matching method and device and data processing equipment | |
| CN113392680A (en) | Road recognition device and method and electronic equipment | |
| CN113674307B (en) | Target detection tracking method, device and equipment | |
| CN114022924A (en) | Face recognition method and related device | |
| CN111741267B (en) | Method, device, equipment and medium for determining vehicle delay | |
| CN114241373A (en) | End-to-end vehicle behavior detection method, system, equipment and storage medium |
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 |