CN117152732B - Multi-feature-assisted license plate recognition method and system - Google Patents
Multi-feature-assisted license plate recognition method and system Download PDFInfo
- Publication number
- CN117152732B CN117152732B CN202311349697.9A CN202311349697A CN117152732B CN 117152732 B CN117152732 B CN 117152732B CN 202311349697 A CN202311349697 A CN 202311349697A CN 117152732 B CN117152732 B CN 117152732B
- Authority
- CN
- China
- Prior art keywords
- data
- acquisition
- contour
- license plate
- area
- 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
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000000605 extraction Methods 0.000 claims abstract description 46
- 238000005259 measurement Methods 0.000 claims abstract description 33
- 238000012360 testing method Methods 0.000 claims abstract description 26
- 230000007613 environmental effect Effects 0.000 claims description 31
- 238000010276 construction Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 abstract description 4
- 238000004458 analytical method Methods 0.000 description 4
- 230000001419 dependent effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 108010076504 Protein Sorting Signals Proteins 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013481 data capture Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/757—Matching configurations of points or features
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a multi-feature assisted license plate recognition method and a multi-feature assisted license plate recognition system, which relate to the technical field of electric digital data processing, and are characterized in that a distance measuring unit is arranged and receives a feedback signal of the unit, a target vehicle lane is determined, a feedback test instruction is generated, continuous measurement signals are transmitted to determine speed data and position data of the target vehicle, focal region data acquisition is executed in combination with acquisition time nodes, multi-contour recognition positioning and license plate region feature extraction are carried out, and a license plate recognition result is generated.
Description
Technical Field
The invention relates to the technical field of electric digital data processing, in particular to a multi-feature assisted license plate recognition method and system.
Background
License plate recognition is the basis for intelligent management of vehicles, and accurate license plate region positioning and character recognition are required for accurate and effective management of vehicles. At present, the license plate recognition of passing vehicles is carried out by a license plate recognition instrument, and when the vehicles run to a specified recognition angle range, the license plate recognition instrument is triggered to carry out license plate data detection.
In the prior art, the conventional license plate recognition technology is too limited, license plate data capture recognition can only be carried out based on a preset angle in a preset range, the license plate recognition technology cannot adapt to traffic diversity of vehicles, recognition intelligence is insufficient, and recognition results are too dependent on equipment states.
Disclosure of Invention
The application provides a multi-feature auxiliary license plate recognition method and system, which are used for solving the technical problems that in the prior art, license plate data capture recognition can only be carried out based on a preset angle in a preset range, the license plate recognition method and system cannot adapt to traffic diversity of vehicles, the recognition intelligence is insufficient, and the recognition result is too dependent on equipment state.
In view of the above problems, the present application provides a multi-feature assisted license plate recognition method and system.
In a first aspect, the present application provides a multi-feature assisted license plate recognition method, the method comprising:
setting a distance measuring unit and receiving a unit feedback signal of the distance measuring unit;
when a multipoint feedback value exists in the unit feedback signal, determining a target vehicle lane according to the multipoint feedback value, and generating a feedback test instruction;
generating a continuous measurement signal through the feedback test instruction, transmitting the continuous measurement signal through the distance measuring unit, and receiving a feedback signal;
generating speed data and position data of the target vehicle according to the signal time nodes of the continuous measurement signal and the feedback signal;
determining an acquisition time node, determining a focusing area based on the acquisition time node, the speed data and the position data, and executing focus area data acquisition of the focusing area at the acquisition time node by an image acquisition unit to obtain area identification data;
carrying out multi-outline identification positioning on the area identification data to determine a license plate area;
and executing the regional feature extraction of the license plate region, and generating a license plate recognition result according to the regional feature extraction result.
In a second aspect, the present application provides a multi-feature assisted license plate recognition system, the system comprising:
the signal receiving module is used for setting a distance measuring unit and receiving a unit feedback signal of the distance measuring unit;
the instruction generation module is used for determining a target vehicle lane according to the multipoint feedback value when the multipoint feedback value exists in the unit feedback signal and generating a feedback test instruction;
the signal testing module is used for generating a continuous measurement signal through the feedback testing instruction, transmitting the continuous measurement signal through the distance measuring unit and receiving a feedback signal;
the data generation module is used for generating speed data and position data of the target vehicle according to the signal time nodes of the continuous measurement signal and the feedback signal;
the data acquisition module is used for determining an acquisition time node, determining a focusing area based on the acquisition time node, the speed data and the position data, and executing the data acquisition of the focusing area in the acquisition time node by the image acquisition unit to obtain area identification data;
the contour positioning module is used for carrying out multi-contour identification positioning on the region identification data and determining a license plate region;
the feature extraction module is used for executing regional feature extraction of the license plate region and generating a license plate recognition result according to the regional feature extraction result.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
according to the multi-feature auxiliary license plate recognition method, a distance measuring unit is arranged, a unit feedback signal of the distance measuring unit is received, when a multi-point feedback value exists in the unit feedback signal, a target vehicle lane is determined according to the multi-point feedback value, a feedback test instruction is generated, further a continuous measurement signal is generated, signal transmission is conducted through the distance measuring unit, the feedback signal is received, speed data and position data of the target vehicle are generated according to the continuous measurement signal and a signal time node of the feedback signal, an acquisition time node is determined, a focusing area is determined according to the speed data and the position data, a focus area data acquisition of the focusing area is carried out through an image acquisition unit at the acquisition time node, area recognition data are obtained, multi-outline recognition positioning is carried out on the determined license plate area, a license plate recognition result is generated according to an area feature extraction result, the technical problems that in the prior art, the license plate recognition can only be carried out based on a preset angle in a preset range, the passing state of a vehicle cannot be adapted, recognition intelligence is insufficient, the recognition result is too dependent on a technical problem of equipment state, the target vehicle is carried out, the accurate positioning is carried out through the signal test, the target contour measurement is carried out, the intelligent recognition environment is not carried out, and the intelligent environment is matched with the intelligent environment recognition is realized, and the multi-outline environment recognition environment is optimized, and the recognition environment is realized.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
Fig. 1 is a schematic flow chart of a license plate recognition method assisted by multiple features;
fig. 2 is a schematic diagram of a determining flow of an acquisition time node in a multi-feature assisted license plate recognition method;
FIG. 3 is a schematic diagram of a multi-profile recognition positioning process in a multi-feature assisted license plate recognition method according to the present application;
fig. 4 is a schematic structural diagram of a license plate recognition system with multi-feature assistance.
Reference numerals illustrate: the device comprises a signal receiving module 11, an instruction generating module 12, a signal testing module 13, a data generating module 14, a data acquisition module 15, a contour positioning module 16 and a feature extraction module 17.
Detailed Description
According to the multi-feature assisted license plate recognition method and system, a distance measuring unit is arranged, a feedback signal of the receiving unit is set, if a multi-point feedback value exists, a target vehicle lane is determined, a feedback test instruction is generated, continuous measurement signals are transmitted through the distance measuring unit, the feedback signal is received, speed data and position data of the target vehicle are determined, focal region data acquisition of a focusing region is executed by combining acquisition time nodes, region recognition data are obtained, multi-outline recognition positioning is conducted, a license plate region is determined, region feature extraction is conducted on the determined license plate region, and a license plate recognition result is generated according to a region feature extraction result.
Example 1
As shown in fig. 1, the present application provides a multi-feature assisted license plate recognition method, which includes:
step S100: setting a distance measuring unit and receiving a unit feedback signal of the distance measuring unit;
specifically, license plate recognition is a basis for intelligent management of vehicles, and accurate license plate region positioning and character recognition are required for accurate and effective management of vehicles. According to the multi-feature auxiliary license plate recognition method, the target vehicle is positioned through signal testing, the vehicle information is determined, image data acquisition is carried out, data isolation is carried out, contour feature matching under the acquisition angle is carried out on the vehicle head data, license plate contour and character contour positioning is carried out, and the real-time environment is combined for optimization acquisition and adjustment, so that recognition influence caused by external environment factors is avoided.
Specifically, the distance measuring unit is an operation unit for positioning the vehicle, the distance measuring unit is provided with a built-in signal transmitter, the distance measuring unit transmits a measuring signal to the identification area, the measuring information contacts the vehicle to rebound, the unit feedback signal is generated, the signal transmitter in the distance measuring unit receives the unit feedback signal, and the unit feedback signal is analyzed for later analysis.
Step S200: when a multipoint feedback value exists in the unit feedback signal, determining a target vehicle lane according to the multipoint feedback value, and generating a feedback test instruction;
step S300: generating a continuous measurement signal through the feedback test instruction, transmitting the continuous measurement signal through the distance measuring unit, and receiving a feedback signal;
specifically, the unit feedback signal is identified, if a multipoint feedback value exists in the unit feedback signal, that is, a signal feedback value of a measurement signal at a plurality of different points is detected, a target vehicle position is defined, and a target vehicle can be accurately positioned and determined based on the multipoint feedback value, for example, if the target vehicle is a large vehicle or a plurality of small vehicles arranged in the vicinity, a single vehicle determination cannot be performed based on fewer feedback values. And determining the lane to which the target vehicle belongs as the lane of the target vehicle based on the target vehicle positioned by the multipoint feedback values, and synchronously generating the feedback test instruction, namely, a start instruction of continuous test.
Further, with the receiving of the feedback test instruction, a continuous measurement signal is generated based on the signal transmitter in the distance measuring unit and an equal time zone, the continuous measurement signal is sent to the target vehicle, a corresponding feedback signal is generated, the feedback signal is returned according to a signal transmitting path, the continuous measurement signal is received in the distance measuring unit, the continuous measurement signal corresponds to the feedback signal one by one and is provided with a time node identifier, and the vehicle state is conveniently determined.
Step S400: generating speed data and position data of the target vehicle according to the signal time nodes of the continuous measurement signal and the feedback signal;
specifically, mapping and correspondence are performed on the continuous measurement signal and the feedback signal, a plurality of signal sequences characterized as measurement signal-feedback signal are generated, and as time passes, data difference identification is performed on adjacent signals so as to determine a real-time position of a target vehicle in a dynamic state, and real-time positioning detection is performed on a running vehicle. Specifically, determining a real-time position of the vehicle based on the generated positions of the adjacent feedback signals; determining the driving distance of a vehicle in an adjacent measurement signal emission time interval based on the transmission distance difference value of the adjacent feedback signals, dividing the driving distance by the transmission time difference of the adjacent measurement signals, taking the calculation result as the speed data of the target vehicle, respectively analyzing and calculating the adjacent sequences in the signal sequence, determining the dynamic data of the target vehicle at different time nodes, and adding the dynamic data into the speed data and the position data of the target vehicle, wherein the speed data and the position data of the target vehicle have time node identifiers.
Step S500: determining an acquisition time node, determining a focusing area based on the acquisition time node, the speed data and the position data, and executing focus area data acquisition of the focusing area at the acquisition time node by an image acquisition unit to obtain area identification data;
further, as shown in fig. 2, step S500 of the present application further includes:
step S510: acquiring road section environment information of an acquired road section, and extracting and acquiring environment characteristics;
step S520: when the environmental characteristic is judged to be the avoidable environmental characteristic, determining an acquisition area based on the environmental characteristic;
step S530: and determining the acquisition time node according to the acquisition area.
Further, step S530 also exists in the present application, including:
step S531: when the environmental characteristics are judged to be unavoidable characteristics, acquiring light intensity data;
step S532: generating auxiliary identification matching features based on the light intensity data;
step S533: and executing regional feature extraction of the license plate region according to the auxiliary identification matching features.
Specifically, the acquisition time node is the time of image data acquisition of the target vehicle, and the acquisition time node is determined. Specifically, the target vehicle passing road section is taken as the collecting road section, environmental information collection is carried out on the collecting road section, the environment information collection comprises a plurality of dimensions such as environment light, a shielding object, an airflow state and the like, the degree of environmental characteristics of each dimension is measured, and the environment light overexposure-exposure degree is exemplified; the environmental characteristics are determined for airflow conditions, such as stormwater weather, haze weather-spatial visibility, and the like. And taking the predetermined initial acquisition time and the acquisition area as a predetermined acquisition time node and a predetermined acquisition area, and carrying out adaptive acquisition adjustment by combining the corresponding environmental characteristics.
Specifically, the evadability determination is performed on the environmental features, if the environmental features are evadability environmental features, for example, for overexposure or backlight environments, shadow shielding environments and the like, the road section area where the target vehicle is in relative preference can be determined by adjusting the acquisition time node, such as forward or backward movement of the acquisition time, as the acquisition area, the distance difference between the acquisition area and a preset acquisition area is calculated, the passing time difference is calculated in combination with the speed data of the target vehicle, the preset acquisition time node is adjusted forward or backward based on the relative positions of the acquisition area and the preset acquisition area, and the adjusted preset acquisition time is used as the acquisition time node.
Further, if the environmental feature is an unavoidable feature, it indicates that the environmental impact cannot be avoided, and the acquisition means or the processing means of the image data are required to be optimized. Specifically, under the collection angle of the image collection unit, the real-time light intensity of the area where the target vehicle is located is collected, the light intensity data is obtained, the auxiliary identification matching feature is generated based on the light intensity data, for example, the collected control information is optimized or the collected image data is processed, for example, the collected image is subjected to enhancement processing and the like. And combining the auxiliary identification matching features to perform regional feature identification and extraction on the license plate region so as to ensure the accuracy and completeness of the extracted features.
Further, a focusing area, that is, an area to be subjected to image acquisition, where the target vehicle is located is determined based on the speed data and the position data, the image acquisition unit is controlled to start to perform area image acquisition on the focusing area based on the acquisition time node, the image acquisition unit is a control unit for performing image acquisition and is in communication connection with image acquisition equipment, for example, monitoring equipment and the like arranged at different road sections are used for performing time sequence integration on acquired images, and the area identification data is used as area identification data, wherein the area identification data is source data to be subjected to license plate identification positioning.
Step S600: carrying out multi-outline identification positioning on the area identification data to determine a license plate area;
further, as shown in fig. 3, step S600 of the present application further includes:
step S610: reading control information of the image acquisition unit;
step S620: determining a matching contour feature set of a vehicle according to the control information and the focusing region, and dividing the region identification data into foreground data and background data according to color data and the focusing region;
step S630: performing data matching of the foreground data through the matching contour feature set, and completing initial contour positioning according to a data matching result;
step S640: and completing the recognition positioning of multiple contours according to the initial contour positioning.
Further, step S620 of the present application further includes:
step S621: acquiring setting position information of the image acquisition unit and generating position data;
step S622: the control information is interacted, and acquisition angle data of the image acquisition unit are acquired;
step S623: determining a contour angle of the contour feature set according to the position data and the acquisition angle data;
step S624: the control information is interacted, and acquisition rate data of the image acquisition unit are acquired;
step S625: determining the contour size of the contour feature set according to the acquisition rate data and the focusing area;
step S626: and completing the construction of the contour feature set according to the contour angle and the contour size.
Further, step S640 of the present application further includes:
step S641: after the initial contour positioning is completed, positioning contour features of the initial contour positioning are obtained;
step S642: determining a fuzzy recognition area of the area recognition data according to the license plate position of the positioning outline feature;
step S643: performing regional license plate feature traversal matching on the fuzzy recognition region, and completing accurate positioning of a license plate based on a matching result;
step S644: and completing the recognition positioning of multiple contours according to the initial contour positioning and the accurate positioning.
Specifically, information such as acquisition angle, acquisition height, acquisition multiplying power and the like of acquisition control of the image acquisition unit is read and used as the control information. And constructing the contour feature set, namely, a reference data set for analyzing the head contour of the target vehicle.
Specifically, setting position acquisition is respectively performed on image acquisition equipment communicated with the image acquisition units, and the setting position acquisition is used as the position data. And carrying out information interaction on the control information of the image acquisition units, and determining the acquisition angle of each image acquisition device, wherein the acquisition angle refers to a spatial angle covering a full-angle domain, is a comprehensive angle of a transverse angle and a vertical angle, and integrates the acquisition angle of each image acquisition device as acquisition angle data of the image acquisition units. The position data corresponds to the acquisition angle data one by one, corresponding acquisition contour angles, such as acquisition contours under different forward altitude angles, acquisition contours under different lateral space angles and the like, are determined according to the position data corresponding to the mapping and the acquisition angle data, and because vision differences exist in the acquisition images under different acquisition angles, targeted matching analysis is needed for guaranteeing the identification accuracy. Further, the control information is interacted, the size conversion multiplying power of the collected image of the image collecting unit is extracted, for example, for long-distance collection, the collected image is collected after a certain multiplying power is needed to be amplified, so that the detail integrity of the collected image is ensured, and the collection multiplying power data of the image collecting unit is determined. And determining an actual contour dimension based on the acquisition rate data and the focusing region, wherein the actual contour dimension is used as the contour dimension of the contour feature set, and the contour feature set is a contour set of a head part. Based on the contour angles, the visual state of the vehicle head contour under different acquisition angles can be determined; and determining the size parameters of the target vehicle based on the contour size, wherein the contour size comprises the steps of constructing the contour feature set based on the contour angle and the contour size before and after the transformation of the acquisition multiplying power size, and the contour feature set comprises a multi-angle and multi-size contour feature data set used for assisting in reference to perform contour analysis.
Further, traversing the contour feature set, and determining a matched contour feature set conforming to the acquisition state based on the control information and the focusing region. Dividing the region identification data according to the color region and the focusing region, determining the foreground data and the background data, wherein the foreground data is a vehicle head region, and the background region is a vehicle body and environment background region so as to divide the requirement identification region. And traversing the matched contour feature set, performing data matching with the foreground data, and determining headstock contour data based on a matching result so as to complete the initial contour positioning. And further positioning license plates, characters and the like based on the initial contour positioning, and executing multi-contour recognition positioning.
Specifically, after the initial contour positioning is completed, contour recognition is performed to determine different visual features such as contour trend, corners and the like, and the visual features are used as the positioning contour features. And carrying out license plate region position recognition based on the positioning contour features, for example, a region with a contour trend which is horizontal and vertical and has vertical corners, framing a fuzzy recognition region based on the region recognition data, and carrying out preliminary judgment on the fuzzy recognition region due to the influence of angle difference and the like of the region recognition data. Further, performing traversal matching on the fuzzy recognition area in combination with license plate features, wherein the license plate features are recognition features for license plate area identification, such as chromaticity difference of a vehicle head and a license plate area, and if the matching result has feature consistency, the fuzzy recognition area is used as the license plate area; if the matching results are different, area adjustment is performed, for example, verification images are collected for analysis and test, accurate positioning of license plates is completed, license plate areas are accurately determined based on the initial contour positioning and the accurate positioning, multi-contour recognition positioning is completed, positioning differences are weakened, and positioning accuracy is guaranteed to the greatest extent. And further identifying license plate areas to determine license plate information.
Step S700: and executing the regional feature extraction of the license plate region, and generating a license plate recognition result according to the regional feature extraction result.
Further, the executing the extracting of the regional features of the license plate region, and generating a license plate recognition result according to the regional feature extraction result, and step S700 of the present application further includes:
step S710: extracting color features of the license plate region to generate a color extraction result;
step S720: determining the matching characteristics and the matching traversal parameters of the number plate according to the color extraction result;
step S730: and carrying out license plate matching based on the license plate matching characteristics through the matching traversal parameters, and completing regional characteristic extraction according to the matching results to generate the license plate recognition results.
Specifically, the license plate region is determined by performing multi-contour recognition positioning, and region feature extraction is performed on the license plate region so as to perform license plate information recognition. Specifically, the color feature extraction is performed on the license plate region, and the character region, namely the license plate number region and the license plate background region, can be distinguished based on the different colors, so that the color extraction result is generated. And extracting characterization features, such as irregular character lines and the like, to be matched with license plate information based on the color extraction result, serving as the good matching features, and determining the matching traversal features, such as region information embedded on and different from a background color and the like. And the license plate matching characteristics and the matching traversal parameters are the basis for license plate information identification. And carrying out license plate matching on the basis of the license plate matching characteristics through the matching traversal parameters, obtaining the matching result, wherein the matching result represents the recognition result of the license plate region, carrying out region characteristic extraction on the basis of the matching result, determining license plate information as the license plate recognition result, and the license plate recognition result has accurate effectiveness.
Example two
Based on the same inventive concept as the multi-feature assisted license plate recognition method in the foregoing embodiment, as shown in fig. 4, the present application provides a multi-feature assisted license plate recognition system, which includes:
a signal receiving module 11, wherein the signal receiving module 11 is used for setting a distance measuring unit and receiving a unit feedback signal of the distance measuring unit;
the instruction generation module 12 is configured to determine a target vehicle lane according to the multi-point feedback value when the multi-point feedback value exists in the unit feedback signal, and generate a feedback test instruction;
a signal testing module 13, where the signal testing module 13 is configured to generate a continuous measurement signal according to the feedback test instruction, transmit the continuous measurement signal according to the distance measurement unit, and receive a feedback signal;
a data generation module 14, wherein the data generation module 14 is configured to generate speed data and position data of the target vehicle according to signal time nodes of the continuous measurement signal and the feedback signal;
the data acquisition module 15 is configured to determine an acquisition time node, determine a focusing area based on the acquisition time node, the speed data and the position data, and perform focal area data acquisition of the focusing area at the acquisition time node by using an image acquisition unit to obtain area identification data;
the contour positioning module 16 is used for performing multi-contour recognition positioning on the region recognition data by the contour positioning module 16 to determine a license plate region;
the feature extraction module 17, the feature extraction module 17 is configured to perform region feature extraction of the license plate region, and generate a license plate recognition result according to the region feature extraction result.
Further, the system further comprises:
the information reading module is used for reading the control information of the image acquisition unit;
the feature determining module is used for determining a matched contour feature set of the vehicle according to the control information and the focusing area and dividing the area identification data into foreground data and background data according to the color data and the focusing area;
the data matching module is used for carrying out data matching on the foreground data through the matching contour feature set and completing initial contour positioning according to a data matching result;
and the identification positioning module is used for completing the identification positioning of multiple contours according to the initial contour positioning.
Further, the system further comprises:
the position information acquisition module is used for acquiring the setting position information of the image acquisition unit and generating position data;
the acquisition angle data acquisition module is used for interacting the control information and acquiring the acquisition angle data of the image acquisition unit;
the contour angle determining module is used for determining the contour angle of the contour feature set according to the position data and the acquisition angle data;
the acquisition rate data acquisition module is used for interacting the control information and acquiring the acquisition rate data of the image acquisition unit;
the contour size determining module is used for determining the contour size of the contour feature set according to the acquisition rate data and the focusing area;
and the contour feature set construction module is used for completing the construction of the contour feature set according to the contour angle and the contour size.
Further, the system further comprises:
the contour feature acquisition module is used for acquiring positioning contour features of the initial contour positioning after the initial contour positioning is completed;
the fuzzy recognition area determining module is used for determining a fuzzy recognition area of the area recognition data according to the license plate position of the positioning outline feature;
the feature matching module is used for performing regional license plate feature traversal matching on the fuzzy recognition region and completing accurate positioning of a license plate based on a matching result;
and the multi-contour positioning module is used for completing the recognition positioning of the multiple contours according to the initial contour positioning and the accurate positioning.
Further, the system further comprises:
the color feature extraction module is used for extracting color features of the license plate area and generating a color extraction result;
the matching parameter determining module is used for determining the matching characteristics and the matching traversal parameters of the number plate according to the color extraction result;
and the license plate recognition result generation module is used for carrying out license plate matching based on the license plate matching characteristics through the matching traversal parameters, and completing regional characteristic extraction according to the matching results to generate the license plate recognition result.
Further, the system further comprises:
the environment characteristic acquisition module is used for acquiring road section environment information of the acquired road section and extracting and acquiring environment characteristics;
the acquisition region determining module is used for determining an acquisition region based on the environmental characteristics when judging that the environmental characteristics are the avoidable environmental characteristics;
and the acquisition time node determining module is used for determining the acquisition time node according to the acquisition region.
Further, the system further comprises:
the light intensity data acquisition module is used for acquiring light intensity data when the environmental characteristics are judged to be unavoidable characteristics;
the auxiliary identification matching feature generation module is used for generating auxiliary identification matching features based on the light intensity data;
and the regional characteristic extraction module is used for executing regional characteristic extraction of the license plate region according to the auxiliary identification matching characteristic.
Through the foregoing detailed description of a multi-feature assisted license plate recognition method, those skilled in the art can clearly understand that a multi-feature assisted license plate recognition method and system in this embodiment, for the device disclosed in the embodiment, the description is relatively simple because it corresponds to the method disclosed in the embodiment, and relevant places refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (3)
1. A multi-feature assisted license plate recognition method, the method comprising:
setting a distance measuring unit and receiving a unit feedback signal of the distance measuring unit;
when a multipoint feedback value exists in the unit feedback signal, determining a target vehicle lane according to the multipoint feedback value, and generating a feedback test instruction;
generating a continuous measurement signal through the feedback test instruction, transmitting the continuous measurement signal through the distance measuring unit, and receiving a feedback signal;
generating speed data and position data of the target vehicle according to the signal time nodes of the continuous measurement signal and the feedback signal;
determining an acquisition time node, determining a focusing area based on the acquisition time node, the speed data and the position data, and executing focus area data acquisition of the focusing area at the acquisition time node by an image acquisition unit to obtain area identification data;
carrying out multi-outline identification positioning on the area identification data to determine a license plate area;
performing regional feature extraction of the license plate region, and generating a license plate recognition result according to the regional feature extraction result;
wherein the method further comprises:
reading control information of the image acquisition unit;
determining a matching contour feature set of a vehicle according to the control information and the focusing region, and dividing the region identification data into foreground data and background data according to color data and the focusing region;
performing data matching of the foreground data through the matching contour feature set, and completing initial contour positioning according to a data matching result;
completing the identification positioning of multiple contours according to the initial contour positioning;
wherein the method further comprises:
acquiring setting position information of the image acquisition unit and generating position data;
the control information is interacted, and acquisition angle data of the image acquisition unit are acquired;
determining a contour angle of the contour feature set according to the position data and the acquisition angle data;
the control information is interacted, and acquisition rate data of the image acquisition unit are acquired;
determining the contour size of the contour feature set according to the acquisition rate data and the focusing area;
completing construction of the contour feature set according to the contour angle and the contour size;
wherein the method further comprises:
after the initial contour positioning is completed, positioning contour features of the initial contour positioning are obtained;
determining a fuzzy recognition area of the area recognition data according to the license plate position of the positioning outline feature;
performing regional license plate feature traversal matching on the fuzzy recognition region, and completing accurate positioning of a license plate based on a matching result;
completing the recognition positioning of multiple contours according to the initial contour positioning and the accurate positioning;
wherein the method further comprises:
acquiring road section environment information of an acquired road section, and extracting and acquiring environment characteristics;
when the environmental characteristic is judged to be the avoidable environmental characteristic, determining an acquisition area based on the environmental characteristic;
determining the acquisition time node according to the acquisition area; judging evadability of the environmental features, if the environmental features are the evadability environmental features, determining a road section area where the target vehicle is in relative preference, taking the road section area as the acquisition area, calculating the distance difference between the acquisition area and a preset acquisition area, calculating the passing time difference by combining the speed data of the target vehicle, performing forward adjustment or backward adjustment on a preset acquisition time node based on the relative positions of the acquisition area and the preset acquisition area, and taking the adjusted preset acquisition time as the acquisition time node;
when the environmental characteristics are judged to be unavoidable characteristics, acquiring light intensity data;
generating auxiliary identification matching features based on the light intensity data;
and executing regional feature extraction of the license plate region according to the auxiliary identification matching features.
2. The method of claim 1, wherein the performing the region feature extraction of the license plate region generates a license plate recognition result based on the region feature extraction result, further comprising:
extracting color features of the license plate region to generate a color extraction result;
determining the matching characteristics and the matching traversal parameters of the number plate according to the color extraction result;
and carrying out license plate matching based on the license plate matching characteristics through the matching traversal parameters, and completing regional characteristic extraction according to the matching results to generate the license plate recognition results.
3. A multi-feature assisted license plate recognition system, the system comprising:
the signal receiving module is used for setting a distance measuring unit and receiving a unit feedback signal of the distance measuring unit;
the instruction generation module is used for determining a target vehicle lane according to the multipoint feedback value when the multipoint feedback value exists in the unit feedback signal and generating a feedback test instruction;
the signal testing module is used for generating a continuous measurement signal through the feedback testing instruction, transmitting the continuous measurement signal through the distance measuring unit and receiving a feedback signal;
the data generation module is used for generating speed data and position data of the target vehicle according to the signal time nodes of the continuous measurement signal and the feedback signal;
the data acquisition module is used for determining an acquisition time node, determining a focusing area based on the acquisition time node, the speed data and the position data, and executing the data acquisition of the focusing area in the acquisition time node by the image acquisition unit to obtain area identification data;
the contour positioning module is used for carrying out multi-contour identification positioning on the region identification data and determining a license plate region;
the feature extraction module is used for executing regional feature extraction of the license plate region and generating a license plate recognition result according to the regional feature extraction result;
the system further comprises:
the information reading module is used for reading the control information of the image acquisition unit;
the feature determining module is used for determining a matched contour feature set of the vehicle according to the control information and the focusing area and dividing the area identification data into foreground data and background data according to the color data and the focusing area;
the data matching module is used for carrying out data matching on the foreground data through the matching contour feature set and completing initial contour positioning according to a data matching result;
the identification positioning module is used for completing the identification positioning of multiple contours according to the initial contour positioning;
the system further comprises:
the position information acquisition module is used for acquiring the setting position information of the image acquisition unit and generating position data;
the acquisition angle data acquisition module is used for interacting the control information and acquiring the acquisition angle data of the image acquisition unit;
the contour angle determining module is used for determining the contour angle of the contour feature set according to the position data and the acquisition angle data;
the acquisition rate data acquisition module is used for interacting the control information and acquiring the acquisition rate data of the image acquisition unit;
the contour size determining module is used for determining the contour size of the contour feature set according to the acquisition rate data and the focusing area;
the contour feature set construction module is used for completing construction of the contour feature set according to the contour angle and the contour size;
the system further comprises:
the contour feature acquisition module is used for acquiring positioning contour features of the initial contour positioning after the initial contour positioning is completed;
the fuzzy recognition area determining module is used for determining a fuzzy recognition area of the area recognition data according to the license plate position of the positioning outline feature;
the feature matching module is used for performing regional license plate feature traversal matching on the fuzzy recognition region and completing accurate positioning of a license plate based on a matching result;
the multi-contour positioning module is used for completing multi-contour identification positioning according to the initial contour positioning and the accurate positioning;
the system further comprises:
the environment characteristic acquisition module is used for acquiring road section environment information of the acquired road section and extracting and acquiring environment characteristics;
the acquisition region determining module is used for determining an acquisition region based on the environmental characteristics when judging that the environmental characteristics are the avoidable environmental characteristics;
the acquisition time node determining module is used for determining the acquisition time node according to the acquisition area, judging evadability of the environmental characteristic, determining a road section area where the target vehicle is in relative preference when the environmental characteristic is the evadability environmental characteristic, calculating the distance difference between the acquisition area and a preset acquisition area as the acquisition area, calculating the passing time difference by combining the speed data of the target vehicle, adjusting the preset acquisition time node forwards or backwards based on the relative position of the acquisition area and the preset acquisition area, and taking the adjusted preset acquisition time as the acquisition time node;
the system further comprises:
the light intensity data acquisition module is used for acquiring light intensity data when the environmental characteristics are judged to be unavoidable characteristics;
the auxiliary identification matching feature generation module is used for generating auxiliary identification matching features based on the light intensity data;
and the regional characteristic extraction module is used for executing regional characteristic extraction of the license plate region according to the auxiliary identification matching characteristic.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311349697.9A CN117152732B (en) | 2023-10-18 | 2023-10-18 | Multi-feature-assisted license plate recognition method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311349697.9A CN117152732B (en) | 2023-10-18 | 2023-10-18 | Multi-feature-assisted license plate recognition method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117152732A CN117152732A (en) | 2023-12-01 |
| CN117152732B true CN117152732B (en) | 2024-02-27 |
Family
ID=88884468
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311349697.9A Active CN117152732B (en) | 2023-10-18 | 2023-10-18 | Multi-feature-assisted license plate recognition method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117152732B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101303803A (en) * | 2008-06-11 | 2008-11-12 | 北京中星微电子有限公司 | Method and system for discriminating license plate |
| CN109447069A (en) * | 2018-10-31 | 2019-03-08 | 沈阳工业大学 | Collecting vehicle information recognition methods and system towards intelligent terminal |
| CN109543613A (en) * | 2018-11-22 | 2019-03-29 | 西安科技大学 | Vehicle Speed and Vehicle License Plate Recognition System and method based on TOF imaging |
| CN115457535A (en) * | 2022-10-10 | 2022-12-09 | 深圳市三千米光电科技有限公司 | Glare-free license plate recognition method and system |
-
2023
- 2023-10-18 CN CN202311349697.9A patent/CN117152732B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101303803A (en) * | 2008-06-11 | 2008-11-12 | 北京中星微电子有限公司 | Method and system for discriminating license plate |
| CN109447069A (en) * | 2018-10-31 | 2019-03-08 | 沈阳工业大学 | Collecting vehicle information recognition methods and system towards intelligent terminal |
| CN109543613A (en) * | 2018-11-22 | 2019-03-29 | 西安科技大学 | Vehicle Speed and Vehicle License Plate Recognition System and method based on TOF imaging |
| CN115457535A (en) * | 2022-10-10 | 2022-12-09 | 深圳市三千米光电科技有限公司 | Glare-free license plate recognition method and system |
Non-Patent Citations (4)
| Title |
|---|
| Application of Artificial Intelligence in Computer Network Technology;Ji Jingzhou and Yuexing He;《Journal of Physics: Conference Series》;全文 * |
| 基于机器学习的车牌识别技术研究;陈政;李良荣;李震;顾平;;计算机技术与发展(06);全文 * |
| 改进ＹＯＬＯｖ５的车牌检测算法在林区中的应用;朱文超等;《光电子· 激光》;第第33卷卷(第第12期期);全文 * |
| 车牌识别系统的设计与实现;李源波;宫清华;;科技创新导报(25);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117152732A (en) | 2023-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110979321B (en) | Obstacle avoidance method for unmanned vehicle | |
| CN108154084B (en) | Agricultural machinery unmanned multi-sensor fusion farmland environment sensing method | |
| CN105711597B (en) | Front locally travels context aware systems and method | |
| CN107796373B (en) | Distance measurement method based on monocular vision of front vehicle driven by lane plane geometric model | |
| DE102018108027B4 (en) | Object detection device | |
| CN102806913B (en) | Novel lane line deviation detection method and device | |
| CN107392103A (en) | The detection method and device of road surface lane line, electronic equipment | |
| US10699567B2 (en) | Method of controlling a traffic surveillance system | |
| CN111198371A (en) | Forward-looking obstacle detection system | |
| CN108089185A (en) | The unmanned air navigation aid of agricultural machinery perceived based on farm environment | |
| CN113378741B (en) | Auxiliary sensing method and system for aircraft tractor based on multi-source sensor | |
| CN209765730U (en) | vehicle type recognition system | |
| CN103176185A (en) | Method and system for detecting road barrier | |
| CN108082181B (en) | Agricultural machinery navigation control method based on farmland environment perception | |
| CN109613559B (en) | Device and method for distinguishing water-land boundary floaters based on vision and laser radar | |
| CN108169743A (en) | Agricultural machinery is unmanned to use farm environment cognitive method | |
| CN111506069B (en) | All-weather all-ground crane obstacle identification system and method | |
| CN114724104B (en) | Method, device, electronic equipment, system and medium for detecting visual recognition distance | |
| CN107832788B (en) | Vehicle distance measuring method based on monocular vision and license plate recognition | |
| CN114910891A (en) | Multi-laser radar external parameter calibration method based on non-overlapping fields of view | |
| CN117152732B (en) | Multi-feature-assisted license plate recognition method and system | |
| US20220309776A1 (en) | Method and system for determining ground level using an artificial neural network | |
| CN113532888B (en) | Pure vision automatic driving vehicle testing method and device | |
| CN115731388A (en) | Integrated rapid detection method and system for road health state | |
| CN109975794B (en) | Method for detecting and controlling intelligent manufacturing system by using hyperspectral imaging ranging model |
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 |