CN113327426A - Vehicle type code identification method and device and vehicle number identification method and device - Google Patents

Vehicle type code identification method and device and vehicle number identification method and device Download PDF

Info

Publication number
CN113327426A
CN113327426A CN202110579491.XA CN202110579491A CN113327426A CN 113327426 A CN113327426 A CN 113327426A CN 202110579491 A CN202110579491 A CN 202110579491A CN 113327426 A CN113327426 A CN 113327426A
Authority
CN
China
Prior art keywords
communicating
communication
chain
type code
vehicle type
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110579491.XA
Other languages
Chinese (zh)
Other versions
CN113327426B (en
Inventor
王保宪
唐永康
孟宪洪
王凯
杨宇飞
李义强
张广远
赵维刚
张�浩
杨勇
严世强
许宏伟
王新敏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shijiazhuang Tiedao University
Guoneng Shuohuang Railway Development Co Ltd
Original Assignee
Shijiazhuang Tiedao University
Guoneng Shuohuang Railway Development Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shijiazhuang Tiedao University, Guoneng Shuohuang Railway Development Co Ltd filed Critical Shijiazhuang Tiedao University
Priority to CN202110579491.XA priority Critical patent/CN113327426B/en
Publication of CN113327426A publication Critical patent/CN113327426A/en
Application granted granted Critical
Publication of CN113327426B publication Critical patent/CN113327426B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
    • G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Train Traffic Observation, Control, And Security (AREA)

Abstract

The application relates to a vehicle type code identification method and device and a vehicle number identification method and device. The vehicle type code recognition method comprises the following steps: acquiring a side image of a freight train; preprocessing the side image to obtain a connected body set; if the first communicating body and the second communicating body in the communicating body set meet a first condition, the first communicating body and the second communicating body form a vehicle type code main communicating chain; determining a first height section according to the height of the second communicating body; adding a communicating body meeting the second condition into the vehicle type code main communicating chain to obtain a vehicle type code communicating chain; and extracting the vehicle type code from the vehicle type code communication chain. The method has low requirement on the setting position of equipment for acquiring the side images of the freight train, and the first condition and the second condition set according to the spraying characteristics of the train type codes are applicable to different shooting distances of the image acquisition equipment, so that the method can be widely applied to the image acquisition equipment in the existing video monitoring system of a railway system, and realizes the accurate identification of the train type codes on the basis of strong applicability.

Description

Vehicle type code identification method and device and vehicle number identification method and device
Technical Field
The present application relates to the field of freight train information detection, and in particular, to a method and an apparatus for identifying a vehicle type code, a method and an apparatus for identifying a vehicle number, a computer device, and a computer-readable storage medium.
Background
Because the train model code and the train number of the freight train are the identification marks of the freight train, the train model code and the train number play an important role in the aspects of dispatching, overhauling, vehicle grouping and the like of the freight train. In the prior art, it is common to realize automatic identification of car type codes and car numbers by using an image identification technology. But the distance between the image acquisition device and the freight train will cause great influence on the identification precision of the automatic identification of the train type code and the train number in the prior art, and the applicability is poor.
Disclosure of Invention
In view of the above, it is desirable to provide a vehicle type code recognition method, a vehicle type code recognition device, a vehicle number recognition method, a vehicle number recognition device, a computer device, and a computer-readable storage medium with high applicability.
The embodiment of the invention provides a vehicle type code identification method, which comprises the following steps: acquiring a side image of a freight train; preprocessing the side images to obtain a connected body set; the communication body set comprises a plurality of communication bodies; if a first communicating body in the communicating body set and a second communicating body in the communicating body set meet a first condition, forming a vehicle type code main communicating chain by the first communicating body and the second communicating body; the first condition comprises that the height ratio of the first communicating body to the second communicating body is within a first height ratio interval, the first communicating body and the second communicating body are adjacent in a first direction, and the first direction is determined according to the setting direction of the vehicle type code; determining a first height section according to the height of the second communicating body; adding the communicating bodies meeting the second condition into the vehicle type code main communicating chain to obtain a vehicle type code communicating chain; the second condition comprises that the communicating body is adjacent to the main communicating chain of the vehicle type code in the first direction, and the height of the communicating body is within a first height interval; and extracting the vehicle type code from the vehicle type code communication chain.
The embodiment of the present invention further provides a vehicle type code recognition apparatus, including: the image acquisition module is used for acquiring a side image of the freight train; the image preprocessing module is used for preprocessing the side images to obtain a connected body set; the communication body set comprises a plurality of communication bodies; the vehicle type code communicating chain forming module is used for forming a vehicle type code main communicating chain by the first communicating body and the second communicating body if the first communicating body in the communicating body set and the second communicating body in the communicating body set meet a first condition, determining a first height interval according to the height of the second communicating body, and adding the communicating bodies meeting a second condition into the vehicle type code main communicating chain to obtain the vehicle type code communicating chain; the height of the first communicating body is greater than that of the second communicating body, the first condition comprises that the height ratio of the first communicating body to the second communicating body is within a first height ratio interval, the first communicating body and the second communicating body are adjacent in a first direction, the first direction is determined according to the setting direction of the vehicle type code, and the second condition comprises that the communicating body and a vehicle type code main communicating chain are adjacent in the first direction and the height of the communicating body is within the first height interval; and the vehicle type code extraction module is used for extracting the vehicle type code from the vehicle type code communication chain.
The embodiment of the invention also provides a vehicle number identification method, which comprises the following steps: acquiring a side image of a freight train; preprocessing the side images to obtain a connected body set; the communication body set comprises a plurality of communication bodies; determining a second height range according to the height of the first communicating body in the communicating body set; the first communication body and a second communication body in the communication body set meet a first condition, the height of the first communication body is greater than that of the second communication body, the first condition comprises that the height ratio of the first communication body to the second communication body is within a first height ratio interval, and the first communication body and the second communication body are adjacent in a first direction; wherein, the first direction is determined according to the setting direction of the vehicle type code; if the height of the connected body is within the second height range and the connected body corresponds to the numeric character, determining the connected body as a target connected body; determining a target main connecting chain according to the target connecting body; the target main communicating link comprises a plurality of target main communicating bodies, the number of the target communicating bodies in the target main communicating link is equal to the number of the vehicle number characters, the target communicating bodies are adjacent in a second direction, and the second direction can be determined according to the setting direction of the vehicle number; and extracting the vehicle number from the target main communication chain.
The embodiment of the invention also provides a car number recognition device, which comprises: the image acquisition module is used for acquiring a side image of the freight train; the image preprocessing module is used for preprocessing the side images to obtain a connected body set; the communication body set comprises a plurality of communication bodies; the target connected body determining module is used for determining a second height range according to the height of the first connected body in the connected body set, and determining the connected body as the target connected body if the height of the connected body is within the second height range and the connected body corresponds to the digital character; the first condition comprises that the height ratio of the first communicating body to the second communicating body is within a first height ratio interval, the first communicating body and the second communicating body are adjacent in a first direction, and the first direction is determined according to the setting direction of the vehicle type code; the target main connected chain determining module is used for determining a target main connected chain according to the target connected body; the target main communicating link comprises a plurality of target main communicating bodies, the number of the target communicating bodies in the target main communicating link is equal to the number of the vehicle number characters, the target communicating bodies are adjacent in a second direction, and the second direction can be determined according to the setting direction of the vehicle number; and the vehicle number extraction module is used for extracting the vehicle number from the target main communication chain.
The embodiment of the invention also provides computer equipment which comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to realize the steps of any one of the vehicle number identification method embodiment or the vehicle type code identification method embodiment.
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of any of the above-mentioned car number identification method embodiments or vehicle type code identification method embodiments.
Based on the above embodiment, a via set including a plurality of vias is obtained by preprocessing the freight train side image. Characters in the freight train side images correspond to one communicating body respectively, the communicating bodies related to the train type codes need to be found out from the communicating body set, and characters used for reflecting the train types in the train type codes are higher than other characters and have a certain proportion relation. Under different shooting distances, the height contrast and the proportional relation exist, a first condition is set according to the characteristic of the car type code, and a first communicating body and a second communicating body which meet the first condition in the communicating body set are found out and combined to form a car type code main communicating chain. The vehicle type codes are adjacent in the first direction except for the characters used for reflecting the vehicle types, a second condition is set according to the characteristic of the vehicle type codes, the communicating bodies meeting the second condition are added into the main communicating chain of the vehicle type codes, then a complete vehicle type code communicating chain corresponding to the vehicle type codes can be obtained, and finally the vehicle type codes can be extracted from the vehicle type code communicating chain. The method has low requirement on the setting position of equipment for acquiring the side images of the freight train, the first condition and the second condition set according to the spraying characteristics of the train type codes can still be suitable for the image acquisition equipment arranged at different distances, and can be widely applied to the image acquisition equipment in the existing video monitoring system of the railway system at present, and the accurate identification of the train type codes is realized on the basis of strong applicability.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments or the conventional technologies of the present application, the drawings used in the descriptions of the embodiments or the conventional technologies will be briefly introduced below, it is obvious that the drawings in the following descriptions are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a diagram illustrating an exemplary application scenario of a vehicle type code recognition method;
FIG. 2 is a flow chart illustrating a method for recognizing a vehicle type code according to an embodiment;
FIG. 3 is a schematic illustration of a car number and a car model number in one embodiment;
FIG. 4 is a schematic flow chart illustrating preprocessing of side images of a freight train in one embodiment;
FIG. 5 is a schematic flow chart of screening a set of connected bodies in another embodiment;
FIG. 6 is a schematic diagram illustrating a process for extracting a model code from a vehicle model code communication chain according to an embodiment;
FIG. 7 is a block diagram showing a structure of a vehicle type code extracting apparatus according to an embodiment;
FIG. 8 is a flowchart illustrating a vehicle number recognition method according to an embodiment;
FIG. 9 is a flowchart illustrating the step of determining a target primary connecting link according to a target connector in one embodiment;
FIG. 10 is a schematic diagram of a constituent vehicle number primary connectivity chain in one embodiment;
FIG. 11 is a schematic diagram of adding a via pair satisfying a fifth condition to a vehicle number primary connectivity chain in one embodiment;
FIG. 12 is a schematic diagram illustrating a process for extracting a model code from a vehicle model code communication chain according to an embodiment;
fig. 13 is a block diagram showing the structure of the car number recognition apparatus in one embodiment.
Detailed Description
To facilitate an understanding of the present application, the present application will now be described more fully with reference to the accompanying drawings. Embodiments of the present application are set forth in the accompanying drawings. This application may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.
It will be understood that, as used herein, the terms "first," "second," and the like may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish one element from another.
It will be understood that when an element is referred to as being "connected" to another element, it can be directly connected to the other element or be connected to the other element through intervening elements. Further, "connection" in the following embodiments is understood to mean "electrical connection", "communication connection", or the like, if there is a transfer of electrical signals or data between the connected objects.
As used herein, the singular forms "a", "an" and "the" may include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises/comprising," "includes" or "including," etc., specify the presence of stated features, integers, steps, operations, components, parts, or combinations thereof, but do not preclude the presence or addition of one or more other features, integers, steps, operations, components, parts, or combinations thereof.
Referring to fig. 1, fig. 1 is a scene diagram of an application of a vehicle type code recognition method according to an embodiment of the present application, where the application of the vehicle type code recognition method may include a vehicle type code recognition device. The vehicle type code recognition device may be specifically integrated in a server or a terminal or other computer equipment, where the server may be an independent physical server, may also be a server cluster or a distributed system formed by a plurality of physical servers, and may also be a cloud server providing basic cloud computing services such as a cloud service, a cloud database, a cloud computing, a cloud function, a cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), and a big data and artificial intelligence platform, but is not limited thereto. The terminal can be a mobile phone, a tablet computer, a notebook computer, a desktop computer and the like. The computer equipment acquires the side images of the freight train from the image acquisition equipment and identifies the train type code based on the vehicle type code identification method in the embodiment of the invention. The image acquisition equipment can be a camera in a video monitoring system in a railway system, and can also be additionally arranged, and is not limited herein.
In one embodiment, as shown in fig. 2, a vehicle type code recognition method is provided, including steps S100 to S150.
S100, acquiring a side image of the freight train.
It can be understood that the side surfaces of each carriage of the freight train are sprayed with various characters, the characters are used for reflecting the relevant information of the sprayed freight train, and relevant workers can conveniently know the relevant information of the freight train by observing the characters so as to manage and track the freight train. The train type code of the freight train is a character combination sprayed on the side surface of the freight train according to a certain coding rule, wherein the character combination comprises English characters and numeric characters. The model code is used for reflecting model information of the freight train, and the model information comprises self weight, load, vehicle type, volume and the like. The inside of the railway system is provided with a coding table corresponding to the coding rule, and the meanings of Chinese and English characters and numeric characters of the train type code can be read by looking up the coding table, so that the train type information of the freight train can be obtained.
S110, preprocessing the side image to obtain a connected body set; wherein the set of the connected bodies comprises a plurality of connected bodies.
It is understood that the minimum unit of an image is a pixel, and a connected component refers to the entirety of pixels having the same pixel value and being adjacent in position. The characters are generally in the same color and have certain intervals during spraying, so that one character corresponds to one communicating body when the preprocessing effect is good. At present, a plurality of mature algorithms preprocess an original image so as to divide the original image into a plurality of independent connected bodies.
S120, if a first communicating body in the communicating body set and a second communicating body in the communicating body set meet a first condition, forming a vehicle type code main communicating chain by the first communicating body and the second communicating body; the height of the first communicating body is larger than that of the second communicating body, the first condition comprises that the height ratio of the first communicating body to the second communicating body is within a first height ratio interval, the first communicating body is adjacent to the second communicating body in the first direction, and the first direction is determined according to the setting direction of the vehicle type code.
It is understood that the direction in which the model code is set refers to a direction selected when the model code is set on the side of the vehicle compartment for display. The connected body set also comprises a plurality of connected bodies which are not part of the vehicle type code, and the connected bodies related to the vehicle type code need to be found out from the connected body set and further identified. For convenience of description, the english characters reflecting the type of the freight train in the train type code are referred to as the type characters, and the characters other than the type characters in the train type code are referred to as code characters, for example, P in the train type code P64A is the type character, 64A is the code character, the type character P represents that the type of the freight train is boxcar, and for example, C in the train type code C60 is the type character, 60 is the code character, and the type character C represents that the type of the freight train is open car. The inventor has found that, referring to fig. 3 (the car code is exemplified by P64A, and only the car code and the car number relevant to the present application are shown in the figure, and the rest characters are not shown in the figure), the height of the model character of the freight train is higher than that of the code character when the car code of the freight train is painted, and the height of the code character is basically consistent. In addition, the height of the vehicle type characters has a certain proportional relationship with the height of the code characters. Further, even if the characters change in inclination, scaling, or the like, at different shooting distances, the characters change to the same extent, and the relationship between the vehicle type characters and the code characters is not affected. And the above-described features do not exist in the remaining character combinations other than the model code. Based on this, the characters related to the vehicle model code can be screened out from the communication body set according to the unique relationship between the vehicle type characters and the code characters.
Specifically, when a first link in the link set and a second link in the link set satisfy a first condition, that is, the first link is higher than the second link, the height ratio of the first link to the second link is in a first height ratio interval, and the first link and the second link are adjacent in the first direction, the first link can be considered as a link corresponding to the vehicle type character, and the second link is a code character adjacent to the vehicle type character in the code characters, and the first link and the second link are combined into a vehicle type code main link. Taking the vehicle model code P64A as an example, as shown in fig. 3, in the subsequent step, there is a vehicle model code main communication chain as a main body, which facilitates adding the communication bodies other than the first communication body and the second communication body in the vehicle model code to the vehicle model code main communication chain. The center of the first height ratio interval can be set according to the vehicle type code spraying rule, the width of the first height ratio interval can be adjusted in consideration of the spraying operation error, and the situation that the first communicating body and the second communicating body cannot be identified is reduced. The first direction can also be set according to the setting direction, and the reading habit from left to right is common at present, so the car codes are also arranged according to the transverse direction, so the first direction can be set to be transverse, but the method can also be applied to the setting modes of other first directions, such as from top to bottom, which is only used for illustration and is not limited herein.
And S130, determining a first height section according to the height of the second communicating body.
It can be understood that the heights of the characters of the code character part of the vehicle model code are similar, the first height section can be determined according to the height of the second connecting body, and the connecting body with the height in the first height section is similar to the height of the second connecting body. Optionally, the probability of mistakenly selecting or missing selecting a connected body except the character corresponding to the second connected body in the code character part is reduced by adjusting the width of the first height section by taking the height of the second connected body as the center of the first height section.
S140, adding the communicating bodies meeting the second condition into the vehicle type code main communicating chain to obtain a vehicle type code communicating chain; the second condition comprises that the communicating bodies are adjacent to the main communicating chain of the vehicle type code in the first direction and the height of the communicating bodies is within the first height interval.
It is understood that the via bodies of the code character portion other than the character corresponding to the second via body are all close in height to the second via body and are all adjacent in the first direction, that is, the second condition is satisfied. And adding all the communicating bodies meeting the second condition into the vehicle type code main communicating chain to obtain a complete vehicle type code communicating chain corresponding to the vehicle type code.
And S150, extracting the vehicle type code from the vehicle type code communication chain.
Specifically, the vehicle type code communication chain comprises the communication bodies which correspond to the characters of the vehicle type code one by one, all the communication bodies are extracted from the vehicle type code communication chain, and the communication bodies can be converted into the characters according to the mapping relation between the communication bodies and the characters, so that the whole vehicle type code is extracted. At present, a plurality of mature technologies can judge the mapping relation between the connected body and the character, so that the connected body can be converted into the corresponding character.
Based on the vehicle type code recognition method of the embodiment, a connected body set comprising a plurality of connected bodies is obtained by preprocessing the side images of the freight train. Characters in the freight train side images correspond to one communicating body respectively, the communicating bodies related to the train type codes need to be found out from the communicating body set, and characters used for reflecting the train types in the train type codes are higher than other characters and have a certain proportion relation. Under different shooting distances, the height contrast and the proportional relation exist, a first condition is set according to the characteristic of the car type code, and a first communicating body and a second communicating body which meet the first condition in the communicating body set are found out and combined to form a car type code main communicating chain. The vehicle type codes are adjacent in the first direction except for the characters used for reflecting the vehicle types, a second condition is set according to the characteristic of the vehicle type codes, the communicating bodies meeting the second condition are added into the main communicating chain of the vehicle type codes, then a complete vehicle type code communicating chain corresponding to the vehicle type codes can be obtained, and finally the vehicle type codes can be extracted from the vehicle type code communicating chain. The method has low requirement on the setting position of equipment for acquiring the side images of the freight train, the first condition and the second condition set according to the spraying characteristics of the train type codes can still be suitable for the image acquisition equipment arranged at different distances, and can be widely applied to the image acquisition equipment in the existing video monitoring system of the railway system at present, and the accurate identification of the train type codes is realized on the basis of strong applicability.
In one embodiment, if the first direction is a lateral direction, two vias satisfying the following condition may be determined to be adjacent in the first direction: the distance between the centroids of the minimum circumscribed rectangles corresponding to the two communicating bodies is smaller than a preset distance, and the included angle between the connecting line between the two centroids and any straight line parallel to the first direction is within a first angle range. The preset distance and the first angle range may be set according to actual conditions.
In one embodiment, as shown in fig. 4, the step S110 specifically includes steps S113 to S117.
And S113, carrying out gray level processing on the side face image to obtain a gray level side face image.
It can be understood that the image collected by the common image collecting device is generally a color, and in the RGB model, the pixel points of different colors of the color image can be obtained by superimposing the three primary colors of red, green, and blue, but each pixel point corresponds to 3 variables respectively, which increases the operation difficulty of image analysis, so that the color information with 3 variables is generally converted into the gray information with only 1 variable to simplify the analysis process. Specifically, the gray scale processing can be realized by a weighted average method, an average value method, a maximum value method, or the like. Taking the weighted average method as an example, the gray value of each pixel point can be calculated by the following formula:
R＝G＝B＝(R*Wr+G*Wg+B*Wb)/3；
wherein R is the red luminance value of each pixel, WrIs the weight of the red luminance value, G is the green luminance value of each pixel, WgIs the weight of the green luminance value, B is the blue luminance value of each pixel, WbIs the weight of the blue luminance value. In one embodiment, the inventor has found that W is a combination of different weightsr、Wg、WbThe values of (a) are respectively 0.9, 1.77 and 0.33, so that a good gray scale effect can be obtained.
And S115, carrying out binarization processing on the gray-scale side image to obtain a binarization side image.
It can be understood that the gray value of each pixel point after the graying process is in the value range of [0,255], in order to further reduce the data volume, the pixel point on the image can be set to be 0 or 255, the gray value of the pixel point is black when 0, and the gray value of the pixel point is white when 255. There are many common methods of binarization processing, which can be generally classified into a local threshold method and a global threshold method.
And S117, carrying out connected body segmentation processing on the binary side surface image to obtain a plurality of connected bodies.
It can be understood that after the binarized side image is obtained, each pixel point in the image has only two gray values of 0 or 255, adjacent pixel points with the same gray value can be found out based on an analysis method such as a 4-neighborhood region or an 8-neighborhood region, and connected bodies are formed, and each connected body corresponds to different labels or marks for distinguishing. Common methods for segmentation of the connected body include Two-pass and Seed-FillIng methods.
It should be noted that many mature image processing-related software, such as Opencv, Matlab, etc., have preset modules related to the above preprocessing steps for users to call, and the specific implementation process of the preprocessing is not limited in this embodiment.
In one embodiment, as shown in fig. 5, a step S200 is further included before the step S120.
S200, if the connected bodies in the connected body set meet a third condition, removing the connected bodies meeting the third condition from the connected body set; wherein the third condition is that the aspect ratio of the minimum circumscribed rectangle of the via is outside the set aspect ratio range.
It can be understood that under different shooting conditions, the side image of the freight train may be imaged with an interference image, for example, a shadow formed by sunlight irradiating on the side of the freight train, and the interference image may also form some connected objects, but the interference image is generally of an irregular structure, and the connected objects corresponding to the interference image are also irregular, so that the aspect ratio of the minimum circumscribed rectangle of the connected objects corresponding to the interference image does not follow a specific rule, and the ratio of the height to the width of the minimum circumscribed rectangle of the connected objects formed by characters is within a certain interval, that is, the aspect ratio range is set. In order to reduce the influence of the interference image, it is necessary to eliminate the connected objects corresponding to the interference image in the connected object set, and as can be seen from the above description, the connected objects satisfying the third condition in the connected object set can be regarded as connected objects corresponding to the interference image, and the connected objects satisfying the third condition should be eliminated.
In one embodiment, as shown in fig. 6, the step S150 includes a step S151 and a step S153.
And S151, matching each communicating body in the vehicle type code communicating chain with the template character in the first preset template character library, and determining the template character corresponding to each communicating body in the vehicle type code communicating chain according to the matching result.
It is understood that the preset template characters include a plurality of template characters, and the template characters include numeric template characters and alphabetic template characters. The matching process is to find the template character with the highest matching degree with the connected body from the preset template characters, and the template character with the highest matching degree can be determined as the template character corresponding to the connected body.
And S153, sequencing template characters corresponding to the communicating bodies in the vehicle type code communicating chain according to the center coordinates of the minimum external rectangles of the communicating bodies in the vehicle type code communicating chain to obtain the vehicle type code.
It can be understood that the central coordinates of the minimum circumscribed rectangle of the connected bodies can reflect the relative positions of the connected bodies on the carriage, and the arrangement condition of the characters corresponding to the connected bodies in the real environment can be known by comparing the central coordinates of the connected bodies. The car type code is also arranged according to a certain sequence during design to express a specific meaning, so that the template characters corresponding to the communicating bodies need to be sequenced according to the central coordinates, and the characters can be combined into the car type code. For example, if vehicle model code design and painting are performed in order from left to right, the template characters corresponding to the respective connectors may be arranged from left to right according to the center coordinates.
In a specific embodiment, matching each connected body in the vehicle type code connected chain with a template character in a first preset template character library comprises:
step 1, selecting a connected body in the connected chain of the optional vehicle type codes as a connected body to be identified.
Step 2, converting the communicating body to be identified into a standard size; wherein the standard size is the same as the size of the template character.
And 3, selecting one template character in the first preset template character library as a comparison template character.
Step 4, calculating a first result, and counting and comparing the sum of all the first results corresponding to the template characters to obtain a second result; the first result is the difference of the pixel points at the same positions of the communicating body to be identified and the comparison template character.
And 5, determining the similarity between the communication body to be identified and the comparison template character according to the second result.
The larger the second result is, the more pixel points reflecting that the communication body to be recognized is different from the comparison template character are, which means that the similarity is lower.
And (5) repeating the steps 1 to 5 for all the connected bodies in the vehicle type code connected chain, so that all the connected bodies in the vehicle type code connected chain can be matched.
The embodiment of the present invention further provides a vehicle type code recognition apparatus, as shown in fig. 7, including an image acquisition module 100, an image preprocessing module 300, a vehicle type code connecting chain composition module 500, and a vehicle type code extraction module 700. The image acquisition module 100 is used for acquiring a side image of the freight train. The image preprocessing module 300 is configured to preprocess the side image to obtain a connected body set; wherein the set of the connected bodies comprises a plurality of connected bodies. The vehicle type code communicating chain composing module 500 is used for composing a vehicle type code main communicating chain by a first communicating body and a second communicating body if the first communicating body in the communicating body set and the second communicating body in the communicating body set meet a first condition, determining a first height interval according to the height of the second communicating body, and adding the communicating bodies meeting a second condition into the vehicle type code main communicating chain to obtain the vehicle type code communicating chain; the first condition comprises that the height ratio of the first communicating body to the second communicating body is within a first height ratio interval, the first communicating body is adjacent to the second communicating body in a first direction, the first direction is determined according to the setting direction of the vehicle type code, and the second condition comprises that the communicating body is adjacent to the vehicle type code main communicating chain in the first direction and the height of the communicating body is within the first height interval. The vehicle type code extracting module 700 is configured to extract a vehicle type code from the vehicle type code communication chain.
For the specific definition of the vehicle type code recognition device, the above definition of the vehicle type code recognition method can be referred to, and is not described herein again. The modules in the car type code identification device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules. It should be noted that, in the embodiment of the present application, the division of the module is schematic, and is only one logic function division, and there may be another division manner in actual implementation.
The embodiment of the invention also provides a car number identification method, as shown in fig. 8, the car number identification method comprises steps S500 to S550.
And S500, acquiring a side image of the freight train.
S510, preprocessing the side image to obtain a connected body set; wherein the set of the connected bodies comprises a plurality of connected bodies.
S520, determining a second height range according to the height of the first communicating body in the communicating body set; the first communication body and a second communication body in the communication body set meet a first condition, the height of the first communication body is greater than that of the second communication body, the first condition comprises that the height ratio of the first communication body to the second communication body is within a first height ratio interval, and the first communication body and the second communication body are adjacent in a first direction; wherein the first direction is determined according to the setting direction of the vehicle type code.
The above steps S500 to S520 are similar to the steps S100 to S120, and reference may be made to the above description.
S530, if the height of the connected body is within the second height range and the connected body corresponds to the numeric character, the connected body is determined to be the target connected body.
It can be understood that the car number is a character combination composed of all numbers, and the heights of all number characters in the car number are similar. The inventor finds that, referring to fig. 3, the height of each numeric character in the car number is similar to the height of the second connecting body. The heights of the characters are different under different shooting distances, so that the height of directly acquiring the car number is difficult. However, based on the above findings, the second height range can be determined with reference to the height of the second via. The connected bodies with the heights within the second height range are all close to the heights of the second connected bodies, and the connected bodies with the heights within the second height range and corresponding to the numeric characters can be selected from the plurality of connected bodies as target connected bodies according to the characteristic that the vehicle numbers are all numeric characters, and the target connected bodies are more likely to be connected bodies related to the vehicle numbers. In addition, the judgment of whether the connected body corresponds to the numeric character can be realized by adopting the above matching mode based on the first preset template character library.
S540, determining a target main connected chain according to the target connected body; the target main connected chain comprises a plurality of target main connected bodies, the number of the target connected bodies in the target main connected chain is equal to the number of the vehicle number characters, the target connected bodies are adjacent to each other in the second direction, and the second direction can be determined according to the setting direction of the vehicle number.
It is understood that the direction in which the car number is set refers to a direction selected when the car number is set on the side of the vehicle compartment for display. The car number is a string of closely arranged character combinations with the number of the characters of the car number being a fixed value. Based on the feature of the car number, target links that are equal in number to the number of characters of the car number and are closely arranged (i.e., adjacent in the second direction) may be selected from the plurality of target links to constitute the target main link.
And S550, extracting the vehicle number from the target main communication chain.
Specifically, the vehicle number communication chain comprises the communication bodies corresponding to the characters of the vehicle number one by one, all the communication bodies are extracted from the vehicle number communication chain, and the communication bodies can be converted into the characters according to the mapping relation between the communication bodies and the characters, so that the whole vehicle number is extracted. At present, a plurality of mature technologies can judge the mapping relation between the connected body and the character, so that the connected body can be converted into the corresponding character.
Based on the vehicle type code recognition method of the embodiment, a connected body set comprising a plurality of connected bodies is obtained by preprocessing the side images of the freight train. Under different shooting distances, the heights of all characters are different, so that the height of directly acquiring the car number from the communicating body set is difficult, but the characters used for reflecting the car type in the car type code are higher than other characters and have a certain proportion relation. Under different shooting distances, the height contrast and the proportional relation exist, a first condition is set according to the characteristic of the vehicle type code, a first communicating body and a second communicating body meeting the first condition are screened, and the height of the second communicating body is used as a reference to determine a second height range. And the height of each communication body in the vehicle number is close to that of the second communication body, and the vehicle number is a character combination consisting of all numbers, so the communication bodies with the height within the second height range and corresponding to the number characters are more likely to be the communication bodies related to the vehicle number. And screening out parts which can be combined into a target main communication chain from the plurality of target communication bodies according to the characteristics that the characters in the car number are closely arranged and the number of the characters of the car number is a fixed value. And finally, extracting the vehicle number from the target main communication chain. The method has low requirement on the setting position of equipment for acquiring the side images of the freight train, can still be suitable for the first condition set according to the spraying characteristics of the train type codes under different distances of the image acquisition equipment, finds out the second communicating body according to the first condition, and takes the height of the second communicating body as the reference for subsequent train number identification, can be widely applied to the image acquisition equipment in the existing video monitoring system of a railway system, and realizes the accurate identification of the train number on the basis of strong applicability.
In an embodiment, as shown in fig. 9, the step S540 specifically includes steps S541 to S549.
S541, forming a connector pair by any target connectors adjacent in the first direction to obtain a connector pair set; the set of the connected body pairs comprises a plurality of connected body pairs, and each connected body pair comprises a first connected body and a last connected body.
It can be understood that the pair of the communication bodies comprises two communication bodies, wherein the communication body is the first communication body close to the head part of the vehicle number, and the communication body is the last communication body close to the tail part of the vehicle number.
S543, extracting any one connector pair from the connector pair set to serve as a reference connector pair, and if other connector pairs in the connector pair set meet a fourth condition, extracting and adding the connector pair meeting the fourth condition from the connector pair set to form a vehicle number main connecting chain corresponding to the connector pair serving as the reference connector pair; wherein the fourth condition is that the last via of the reference via pair is the same as the first via of the via pair.
Specifically, after the set of via pairs is obtained, one via pair is selected as a reference via pair, and the via pair satisfying the fourth condition and the current reference via pair constitute a main vehicle number link, because the last via of the reference via pair is the same as the first via of the via pair, as shown in fig. 10 (a rectangle is used to represent a via in the figure), the vias in the main vehicle number link are three vias arranged closely.
S545, if the remaining communication body pairs in the communication body pair set meet a fifth condition, extracting the communication body pairs meeting the fifth condition from the communication body pair set and adding the communication body pairs into the vehicle number main communication chain; and the fifth condition is that the last connecting body of the newly added connecting body pair in the main connecting chain of the vehicle number is the same as the first connecting body of the connecting body pair.
Specifically, after the vehicle number master connection chain is obtained, the search is continued for the connector pair satisfying the fifth condition, as shown in fig. 11 (a rectangle is used to represent a connector in the figure), and the last connector of the connector pair satisfying the fifth condition may be closely arranged behind the last connector of the newly added connector pair in the vehicle number master connection chain.
S547, traversing each connector pair in the connector pair set to obtain a vehicle number main connecting chain corresponding to each connector pair.
It is understood that each via pair in the set of via pairs as a reference via may form a plurality of vehicle number primary communication chains, beginning with the first via of the reference via pair, respectively.
And S549, determining a target main communication chain in the plurality of vehicle number main communication chains according to the number of the communication bodies in each vehicle number main communication chain.
It can be understood that the number of the characters in the car number is a fixed value, and only the car number main connected chain in which the number of the connected bodies is the same as the number of the characters of the car number is the target main connected chain corresponding to the car number in the plurality of car number main connected chains.
In one embodiment, the car number identification method further includes: if the number of the communicating bodies in the vehicle number main communicating chain is less than the number of the vehicle number characters and greater than the set number, adding the communicating bodies meeting the sixth condition into the vehicle number main communicating chain; the sixth condition is that the communicating body is adjacent to the vehicle number main communicating chain in the second direction;
specifically, some of the communication bodies related to the vehicle number are misjudged or misjudged as the communication bodies unrelated to the vehicle number due to improper installation of the second height range or failure to accurately judge that the communication bodies correspond to the numeric characters. Under the phenomenon, the main connected chain of the car number with the number of the connected bodies equal to the number of the characters of the car number cannot be found. And the main connected chains of the car numbers, the number of the communicating bodies of which is greater than the set number, have a part which is more likely to be the car numbers, and the main connected chains of the car numbers, the number of which is greater than the set number, are searched in the second direction, and the rest of the car numbers are supplemented into the main connected chains of the car numbers.
In one embodiment, as shown in fig. 12, the step S550 includes steps S551 and S553.
And S551, matching each communication body in the target main communication chain with the template characters in the second preset template character library, and determining the template characters corresponding to each communication body in the target main communication chain according to the matching result.
And S553, sequencing the template characters corresponding to the communicating bodies in the target main communicating chain according to the center coordinates of the minimum circumscribed rectangle of the communicating bodies in the target main communicating chain to obtain the vehicle number.
Step S551 is similar to step S151, and step S553 is similar to step S153, and reference may be made to the above description. It is worth mentioning that, since the car number only contains numeric characters, the second preset template character library can only include numeric template characters, and the car type code includes both numeric characters and numeric characters, the first preset template character library needs to include both numeric template characters and alphabetic template characters. Other template characters can be added to both the first preset template character library and the second preset template character library, and the addition is only for illustration. The first preset template character library and the second preset template character library are required to be provided with parts.
It should be understood that, although the steps in the flowcharts of fig. 2, 4-6, 8, 9, and 12 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2, 4-6, 8, 9, and 12 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least some of the other steps.
The embodiment of the invention also provides a car number recognition device, as shown in fig. 13, which includes an image acquisition module 10, an image preprocessing module 30, a target communicating body determining module 50, a target main communicating chain determining module 70 and a car number extracting module 90. The image acquisition module 10 is used for acquiring a side image of the freight train. The image preprocessing module 30 is configured to preprocess the side image to obtain a connected body set; wherein the set of the connected bodies comprises a plurality of connected bodies. The target connected body determining module 50 is configured to determine a second height range according to the height of the first connected body in the connected body set, and determine that the connected body is the target connected body if the height of the connected body is within the second height range and the connected body corresponds to the numeric character; the first communicating body and the second communicating body in the communicating body set meet a first condition, the height of the first communicating body is larger than that of the second communicating body, the first condition comprises that the height ratio of the first communicating body to the second communicating body is within a first height ratio interval, the first communicating body and the second communicating body are adjacent in a first direction, and the first direction is determined according to the setting direction of the vehicle type code. The target main connected chain determining module 70 is configured to determine a target main connected chain according to the target connected body; the target main connected chain comprises a plurality of target main connected bodies, the number of the target connected bodies in the target main connected chain is equal to the number of the vehicle number characters, the target connected bodies are adjacent to each other in the second direction, and the second direction can be determined according to the setting direction of the vehicle number. And the vehicle number extracting module 90 is used for extracting the vehicle number from the target main communication chain.
For the specific definition of the car number identification device, reference may be made to the above definition of the car number identification method, which is not described herein again. The car number identification device in the embodiment of the application can also be applied to the scene shown in fig. 1. The modules in the vehicle number identification device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules. It should be noted that, in the embodiment of the present application, the division of the module is schematic, and is only one logic function division, and there may be another division manner in actual implementation.
The embodiment of the invention also provides computer equipment which comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to realize the steps of any vehicle type code identification method embodiment or any vehicle number identification method embodiment.
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps in any of the above vehicle type code identification method embodiments or any of the above vehicle number identification method embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (12)

1. A vehicle type code recognition method is characterized by comprising the following steps:
acquiring a side image of a freight train;
preprocessing the side images to obtain a connected body set; wherein the set of vias includes a plurality of vias;
if a first communicating body in the communicating body set and a second communicating body in the communicating body set meet a first condition, the first communicating body and the second communicating body form a vehicle type code main communicating chain; the height of the first communicating body is greater than that of the second communicating body, the first condition comprises that the height ratio of the first communicating body to the second communicating body is within a first height ratio interval, the first communicating body and the second communicating body are adjacent in a first direction, and the first direction is determined according to the setting direction of the vehicle type code;
determining a first height section according to the height of the second communicating body;
adding the communicating bodies meeting a second condition into the vehicle type code main communicating chain to obtain a vehicle type code communicating chain; wherein the second condition comprises that the link is adjacent to the vehicle type code main link in the first direction and the height of the link is within the first height interval;
and extracting the vehicle type code from the vehicle type code communication chain.
2. The vehicle type code recognition method according to claim 1, wherein the step of preprocessing the side image to obtain connected bodies formed by each character in the side image comprises:
carrying out gray level processing on the side face image to obtain a gray level side face image;
carrying out binarization processing on the gray side image to obtain a binarization side image;
and carrying out connected body segmentation processing on the binarization side face image to obtain a plurality of connected bodies.
3. The vehicle type code recognition method according to claim 2, wherein before the step of forming a vehicle type code main communication chain by a first communication in the set of connections and a second communication in the plurality of connections if the first condition is satisfied, the method further comprises:
if the connected body in the connected body set meets a third condition, removing the connected body meeting the third condition from the connected body set; wherein the third condition is that an aspect ratio of a minimum circumscribed rectangle of the via is outside a set aspect ratio range.
4. The vehicle type code recognition method according to claim 1, wherein the step of extracting the vehicle type code from the vehicle type code communication chain includes:
matching each communicating body in the vehicle type code communicating chain with template characters in a first preset template character library, and determining the template characters corresponding to each communicating body in the vehicle type code communicating chain according to a matching result;
and sequencing template characters corresponding to all the communicating bodies in the vehicle type code communicating chain according to the center coordinates of the minimum external rectangles of all the communicating bodies in the vehicle type code communicating chain to obtain the vehicle type code.
5. A vehicle type code recognition device, characterized by comprising:
the image acquisition module is used for acquiring a side image of the freight train;
the image preprocessing module is used for preprocessing the side images to obtain a connected body set; wherein the set of vias includes a plurality of vias;
the vehicle type code communicating chain forming module is used for forming a vehicle type code main communicating chain by a first communicating body and a second communicating body in the communicating body set if the first communicating body in the communicating body set and the second communicating body in the communicating body set meet a first condition, determining a first height interval according to the height of the second communicating body, and adding the communicating bodies meeting a second condition into the vehicle type code main communicating chain to obtain a vehicle type code communicating chain; the height of the first communication body is greater than that of the second communication body, the first condition comprises that the height ratio of the first communication body to the second communication body is within a first height ratio interval, the first communication body is adjacent to the second communication body in a first direction, the first direction is determined according to the setting direction of the vehicle type code, and the second condition comprises that the communication body is adjacent to the main communication chain of the vehicle type code in the first direction and the height of the communication body is within the first height interval;
and the vehicle type code extraction module is used for extracting the vehicle type code from the vehicle type code communication chain.
6. A vehicle number identification method is characterized by comprising the following steps:
acquiring a side image of a freight train;
preprocessing the side images to obtain a connected body set; wherein the set of vias includes a plurality of vias;
determining a second height range according to the height of a first communicating body in the communicating body set; wherein the first communication and a second communication in the set of connections satisfy a first condition, a height of the first communication being greater than a height of the second communication, the first condition including a height ratio of the first communication to the second communication being within a first height ratio interval, the first communication being adjacent to the second communication in a first direction; wherein the first direction is determined according to the setting direction of the vehicle type code;
if the height of the connected body is within the second height range and the connected body corresponds to a digital character, determining that the connected body is a target connected body;
determining a target main connected link according to the target connected body; the target main communication chain comprises a plurality of target main communication bodies, the number of the target communication bodies in the target main communication chain is equal to the number of vehicle number characters, the target communication bodies are adjacent in a second direction, and the second direction can be determined according to the setting direction of the vehicle number;
and extracting the vehicle number from the target main communication chain.
7. The vehicle number identification method according to claim 6, wherein the step of determining a target primary connectivity chain according to the target connectivity body comprises:
forming a communication body pair by the target communication bodies which are adjacent in the first direction to obtain a communication body pair set; the set of the connected body pairs comprises a plurality of connected body pairs, and each connected body pair comprises a first connected body and a last connected body;
extracting any one of the pair of connected bodies from the set of the pair of connected bodies as a reference pair of connected bodies, and if the other pair of connected bodies in the set of the pair of connected bodies satisfies a fourth condition, extracting the pair of connected bodies satisfying the fourth condition from the set of the pair of connected bodies and adding the pair of connected bodies to form a main connected chain of the vehicle number corresponding to the pair of connected bodies as the reference pair of connected bodies; wherein the fourth condition is that a last via of the reference via pair is the same as a leading via of the via pair;
if the remaining communication body pairs in the communication body pair set meet a fifth condition, extracting the communication body pairs meeting the fifth condition from the communication body pair set and adding the communication body pairs into the vehicle number main communication chain; the fifth condition is that the last connected body of the newly added connected body pair in the vehicle number main connected chain is the same as the first connected body of the connected body pair;
traversing each communication body pair in the communication body pair set to obtain the vehicle number main communication chain corresponding to each communication body pair;
and determining the target main communication chain in the plurality of vehicle number main communication chains according to the quantity of the communication bodies in each vehicle number main communication chain.
8. The car number identification method according to claim 6, further comprising:
if the number of the communicating bodies in the vehicle number main communicating chain is less than the number of the vehicle number characters and greater than a set number, adding the communicating bodies meeting a sixth condition into the vehicle number main communicating chain; wherein the sixth condition is that the link is adjacent to the vehicle number main link in the second direction.
9. The vehicle number identification method according to claim 6, wherein the step of extracting the vehicle number from the target primary connectivity chain comprises:
matching each communicating body in the target main communicating chain with a template character in a second preset template character library, and determining the template character corresponding to each communicating body in the target main communicating chain according to a matching result;
and sequencing template characters corresponding to all the connected bodies in the target main connected chain according to the center coordinates of the minimum circumscribed rectangle of all the connected bodies in the target main connected chain to obtain the vehicle number.
10. A car number recognition device, comprising:
the image acquisition module is used for acquiring a side image of the freight train;
the image preprocessing module is used for preprocessing the side images to obtain a connected body set; wherein the set of vias includes a plurality of vias;
a target connected body determining module, configured to determine a second height range according to a height of a first connected body in the connected body set, and determine that the connected body is a target connected body if the height of the connected body is within the second height range and the connected body corresponds to a numeric character; the first communication body and a second communication body in the communication body set meet a first condition, the height of the first communication body is greater than that of the second communication body, the first condition comprises that the height ratio of the first communication body to the second communication body is within a first height ratio interval, the first communication body and the second communication body are adjacent in a first direction, and the first direction is determined according to the setting direction of the vehicle type code;
the target main connected chain determining module is used for determining a target main connected chain according to the target connected body; the target main communication chain comprises a plurality of target main communication bodies, the number of the target communication bodies in the target main communication chain is equal to the number of vehicle number characters, the target communication bodies are adjacent in a second direction, and the second direction can be determined according to the setting direction of the vehicle number;
and the vehicle number extraction module is used for extracting the vehicle number from the target main communication chain.
11. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 4 or claims 6 to 9.
12. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 4 or 6 to 9.
CN202110579491.XA 2021-05-26 2021-05-26 Vehicle type code identification method and device and vehicle number identification method and device Active CN113327426B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110579491.XA CN113327426B (en) 2021-05-26 2021-05-26 Vehicle type code identification method and device and vehicle number identification method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110579491.XA CN113327426B (en) 2021-05-26 2021-05-26 Vehicle type code identification method and device and vehicle number identification method and device

Publications (2)

Publication Number Publication Date
CN113327426A true CN113327426A (en) 2021-08-31
CN113327426B CN113327426B (en) 2022-09-09

Family

ID=77416901

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110579491.XA Active CN113327426B (en) 2021-05-26 2021-05-26 Vehicle type code identification method and device and vehicle number identification method and device

Country Status (1)

Country Link
CN (1) CN113327426B (en)

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008269101A (en) * 2007-04-17 2008-11-06 Matsushita Electric Works Ltd Stolen vehicle retrieval system, and retrieval method in the system
CN101504717A (en) * 2008-07-28 2009-08-12 上海高德威智能交通系统有限公司 Characteristic area positioning method, car body color depth and color recognition method
JP2010066997A (en) * 2008-09-10 2010-03-25 Toshiba Corp Font identification apparatus, font identification program, font determination system, and scanner
CN102915433A (en) * 2012-09-13 2013-02-06 中国科学院自动化研究所 Character combination-based license plate positioning and identifying method
CN103324920A (en) * 2013-06-27 2013-09-25 华南理工大学 Method for automatically identifying vehicle type based on vehicle frontal image and template matching
CN103699876A (en) * 2013-11-26 2014-04-02 天津商业大学 Method and device for identifying vehicle number based on linear array CCD (Charge Coupled Device) images
CN104657726A (en) * 2015-03-18 2015-05-27 哈尔滨工程大学 Identification method for truck numbers of railway tank trucks
CN105550654A (en) * 2015-12-15 2016-05-04 成都交大光芒科技股份有限公司 High-speed train image acquisition system, and real-time train number detection system and method
CN105654140A (en) * 2016-01-04 2016-06-08 哈尔滨工程大学 Complex industrial environment-oriented wagon number positioning and identifying method for railway tank wagon
CN105787524A (en) * 2014-12-26 2016-07-20 中国科学院沈阳自动化研究所 License plate identification method based on OpenCV and license plate identification system based on OpenCV
CN110020624A (en) * 2019-04-08 2019-07-16 石家庄铁道大学 image recognition method, terminal device and storage medium
CN210223049U (en) * 2019-09-23 2020-03-31 视云融聚（广州）科技有限公司 Panorama integration vehicle type recognizer
CN110991447A (en) * 2019-11-25 2020-04-10 北京交通大学 Train number accurate positioning and identification method based on deep learning
CN111369806A (en) * 2020-03-12 2020-07-03 山东泰安煤矿机械有限公司 Method and device for photographing, measuring speed and identifying license plate of freight train

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008269101A (en) * 2007-04-17 2008-11-06 Matsushita Electric Works Ltd Stolen vehicle retrieval system, and retrieval method in the system
CN101504717A (en) * 2008-07-28 2009-08-12 上海高德威智能交通系统有限公司 Characteristic area positioning method, car body color depth and color recognition method
JP2010066997A (en) * 2008-09-10 2010-03-25 Toshiba Corp Font identification apparatus, font identification program, font determination system, and scanner
CN102915433A (en) * 2012-09-13 2013-02-06 中国科学院自动化研究所 Character combination-based license plate positioning and identifying method
CN103324920A (en) * 2013-06-27 2013-09-25 华南理工大学 Method for automatically identifying vehicle type based on vehicle frontal image and template matching
CN103699876A (en) * 2013-11-26 2014-04-02 天津商业大学 Method and device for identifying vehicle number based on linear array CCD (Charge Coupled Device) images
CN105787524A (en) * 2014-12-26 2016-07-20 中国科学院沈阳自动化研究所 License plate identification method based on OpenCV and license plate identification system based on OpenCV
CN104657726A (en) * 2015-03-18 2015-05-27 哈尔滨工程大学 Identification method for truck numbers of railway tank trucks
CN105550654A (en) * 2015-12-15 2016-05-04 成都交大光芒科技股份有限公司 High-speed train image acquisition system, and real-time train number detection system and method
CN105654140A (en) * 2016-01-04 2016-06-08 哈尔滨工程大学 Complex industrial environment-oriented wagon number positioning and identifying method for railway tank wagon
CN110020624A (en) * 2019-04-08 2019-07-16 石家庄铁道大学 image recognition method, terminal device and storage medium
CN210223049U (en) * 2019-09-23 2020-03-31 视云融聚（广州）科技有限公司 Panorama integration vehicle type recognizer
CN110991447A (en) * 2019-11-25 2020-04-10 北京交通大学 Train number accurate positioning and identification method based on deep learning
CN111369806A (en) * 2020-03-12 2020-07-03 山东泰安煤矿机械有限公司 Method and device for photographing, measuring speed and identifying license plate of freight train

Also Published As

Publication number Publication date
CN113327426B (en) 2022-09-09

Similar Documents

Publication Publication Date Title
CN111488756B (en) Face recognition-based living body detection method, electronic device, and storage medium
CN108345880B (en) Invoice identification method and device, computer equipment and storage medium
CN101334836B (en) License plate positioning method incorporating color, size and texture characteristic
CN107578035A (en) Human body contour outline extracting method based on super-pixel polychrome color space
CN109447067B (en) Bill direction detection and correction method and automatic bill checking system
CN104809443A (en) Convolutional neural network-based license plate detection method and system
WO2020125057A1 (en) Livestock quantity identification method and apparatus
CN113139521A (en) Pedestrian boundary crossing monitoring method for electric power monitoring
CN106557740B (en) The recognition methods of oil depot target in a kind of remote sensing images
CN111507411B (en) Image comparison method and system
CN110334628A (en) A kind of outdoor monocular image depth estimation method based on structuring random forest
CN111310690A (en) Forest fire recognition method and device based on CN and three-channel capsule network
CN115272350A (en) Method for detecting production quality of computer PCB mainboard
CN117351499B (en) Split-combined indication state identification method, system, computer equipment and medium
CN113327426B (en) Vehicle type code identification method and device and vehicle number identification method and device
CN110348386B (en) Face image recognition method, device and equipment based on fuzzy theory
CN115147852B (en) Ancient book identification method, ancient book identification device, storage medium and equipment
CN110349119B (en) Pavement disease detection method and device based on edge detection neural network
CN112785550B (en) Image quality value determining method and device, storage medium and electronic device
CN114677428A (en) Power transmission line icing thickness detection method based on unmanned aerial vehicle image processing
CN113903018B (en) Neural network-based container number identification method
CN113643258A (en) Method for detecting loss fault of skirt board at side part of train based on deep learning
CN106295642A (en) A kind of based on serious forgiveness with the license plate locating method of textural characteristics
CN111160366A (en) Color image identification method
CN106710063B (en) A kind of RMB serial number digit recognition method based on computer vision

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