CN109344829B

CN109344829B - Train number identification method and device for high-speed railway train

Info

Publication number: CN109344829B
Application number: CN201810813119.9A
Authority: CN
Inventors: 林巍; 刘刚长
Original assignee: Guangzhou Keii Electro Optics Technology Co ltd
Current assignee: Guangzhou Keii Electro Optics Technology Co ltd
Priority date: 2018-07-23
Filing date: 2018-07-23
Publication date: 2021-05-18
Anticipated expiration: 2038-07-23
Also published as: CN109344829A

Abstract

The invention discloses a method and a device for identifying the number of a high-speed railway train, wherein the method comprises the following steps: controlling a shooting device to carry out shooting operation on the high-speed railway train to obtain a target image aiming at the high-speed railway train; identifying at least one target area in the target image, wherein character content exists in the target image, and identifying the character content in each target area; judging whether the combination of the character contents of all the target areas accords with preset character logic, wherein the preset character logic at least comprises the number of characters contained in car number identifications corresponding to different car types; and when the combination of the character contents of all the target areas accords with the preset character logic, determining the combination of the character contents of all the target areas as the train number identification of the high-speed railway train. Therefore, the embodiment of the invention can identify the target image to obtain the character content and verify the obtained character content, so that the train number identification of the high-speed railway train can be quickly and accurately identified.

Description

Train number identification method and device for high-speed railway train

Technical Field

The invention relates to the technical field of train number identification, in particular to a method and a device for identifying a train number of a high-speed railway train.

Background

The functions of parking lot charging management, traffic flow control index measurement, vehicle positioning, automobile theft prevention, highway overspeed automatic supervision, red light running electronic police, highway toll stations and the like are realized by depending on a vehicle number identification technology. However, the current car number recognition technology is for cars, trucks and other models with fixed license plate installation positions and standard characters in the car numbers, and is not suitable for high-speed railway trains. For a high-speed railway train, the main way of identifying the train number identifier of the high-speed railway train is to read an electronic tag arranged on the high-speed railway train, and practice shows that the electronic tag is easily damaged or lost in the high-speed running process of the high-speed railway train, so that the train number identifier of the high-speed railway train cannot be identified quickly and accurately.

Disclosure of Invention

The embodiment of the invention discloses a method and a device for identifying the number of a high-speed railway train, which can quickly and accurately identify the number identification of the high-speed railway train.

The embodiment of the invention discloses a train number identification method of a high-speed railway train in a first aspect, which comprises the following steps:

controlling a shooting device to carry out shooting operation on the high-speed railway train to obtain a target image of the high-speed railway train;

identifying at least one target area with character content in the target image, and identifying the character content in each target area;

judging whether the combination of the character contents of all the target areas accords with preset character logic or not, wherein the preset character logic at least comprises the number of characters contained in a train number identification corresponding to the train type of the high-speed railway train;

and when the combination of the character contents of all the target areas accords with the preset character logic, determining the combination of the character contents of all the target areas as the train number identification of the high-speed railway train.

As an alternative embodiment, in the first aspect of the embodiments of the present invention, the controlling the shooting device to perform a shooting operation on the high-speed railway train to obtain a target image of the high-speed railway train includes:

sensing environmental parameters of the environment where the shooting device is located;

adjusting the shooting parameters of the shooting device through a preset imaging quality evaluation algorithm according to the sensed environmental parameters;

and controlling the shooting device to carry out shooting operation on the high-speed railway train according to the shooting parameters to obtain a target image of the high-speed railway train.

As an alternative embodiment, in the first aspect of the embodiment of the present invention, the method further includes:

collecting an acquired image corresponding to the high-speed railway train under the train number identification of the high-speed railway train to form an image record of the high-speed railway train, wherein the image record at least comprises the train number identification, a pantograph panoramic image of the high-speed railway train and a slide plate image of the high-speed railway train;

and, before the identifying at least one target region in which character content exists in the target image, the method further comprises:

detecting whether a text region exists in the target image or not through a preset detection algorithm;

when detecting that the text area exists in the target image, performing the identification of at least one target area with character content in the target image;

wherein the text region includes the target region.

As an alternative embodiment, in the first aspect of the embodiments of the present invention, after detecting that the text region exists in the target image, the method further includes:

executing preprocessing operation on the target image and triggering and executing at least one target area for recognizing character content in the target image;

wherein the pre-processing operation comprises at least one of a smoothing filtering operation, a contrast enhancement operation, and a brightness enhancement operation;

and identifying at least one target area in the target image where character content exists, and identifying character content in each target area, including:

identifying a car number identification area in the target image, and performing character segmentation on the car number identification area to obtain at least one target area with character content;

and identifying each target area through a classifier to obtain the character content of each target area.

As an alternative embodiment, in the first aspect of the embodiment of the present invention, before the controlling the shooting device to perform the shooting operation on the high-speed railway train to obtain the target image of the high-speed railway train, the method further includes:

controlling an audio signal transmitting device to transmit an audio signal with a first preset frequency, and judging whether an audio signal receiving device receives a response signal within a preset time period after the audio signal transmitting device transmits the audio signal with the first preset frequency;

when the response signal is judged to be received, judging whether the frequency of the response signal is a second preset frequency and whether the response signal carries a signal identifier of the audio signal with the first preset frequency;

and when the frequency of the response signal is judged to be the second preset frequency and the response signal carries the signal identifier of the audio signal with the first preset frequency, triggering and executing the control shooting device to carry out shooting operation on the high-speed railway train to obtain a target image of the high-speed railway train.

The second aspect of the embodiment of the invention discloses a train number identification device of a high-speed railway train, which comprises:

the first control unit is used for controlling the shooting device to carry out shooting operation on the high-speed railway train to obtain a target image of the high-speed railway train;

the recognition unit is used for recognizing at least one target area with character content in the target image and recognizing the character content in each target area;

the judging unit is used for judging whether the combination of the character contents of all the target areas accords with preset character logic, wherein the preset character logic at least comprises the number of characters contained in a train number identification corresponding to the train type of the high-speed railway train;

and the determining unit is used for determining the combinations of the character contents of all the target areas as the train number identifications of the high-speed railway train when the judging unit judges that the combinations of the character contents of all the target areas accord with the preset character logic.

As an alternative embodiment, in the second aspect of the embodiment of the present invention, the first control unit includes:

the sensing subunit is used for sensing the environmental parameters of the environment where the shooting device is located;

the adjusting subunit is used for adjusting the shooting parameters of the shooting device through a preset imaging quality evaluation algorithm according to the environmental parameters sensed by the sensing subunit;

and the control subunit is used for controlling the shooting device to carry out shooting operation on the high-speed railway train according to the shooting parameters to obtain a target image of the high-speed railway train.

As an alternative embodiment, in the second aspect of the embodiment of the present invention, the apparatus further includes:

the collecting unit is used for collecting the collected images corresponding to the high-speed railway train under the train number identification of the high-speed railway train to form an image record of the high-speed railway train, wherein the image record at least comprises the train number identification, a pantograph panoramic image of the high-speed railway train and a sliding plate image of the high-speed railway train;

the device further comprises:

the detection unit is used for detecting whether a text region exists in the target image through a preset detection algorithm, and when the text region exists in the target image, the identification unit is triggered to execute the identification of at least one target region with character content in the target image;

wherein the text region includes the target region.

a preprocessing unit configured to perform a preprocessing operation on the target image after the detection unit detects that the text region exists in the target image; wherein the pre-processing operation comprises at least one of a smoothing filtering operation, a contrast enhancement operation, and a brightness enhancement operation;

the identification unit is specifically configured to identify at least one target area in the target image, in which character content exists, and identify character content in each target area when the detection unit detects that the text area exists in the target image and after the preprocessing unit performs a preprocessing operation on the target image;

and the identification unit identifies at least one target area with character content in the target image, and the mode of identifying the character content in each target area is specifically as follows:

the second control unit is used for controlling the audio signal transmitting device to transmit the audio signal with the first preset frequency;

the judgment unit is further configured to judge whether a response signal is received by the audio signal receiving device within a preset time period after the audio signal transmitting device transmits the audio signal with the first preset frequency, judge whether the frequency of the response signal is a second preset frequency and whether the response signal carries the signal identifier of the audio signal with the first preset frequency when the response signal is received, and trigger the first control unit to execute the shooting control operation of the shooting control device on the high-speed railway train when the frequency of the response signal is judged to be the second preset frequency and the signal identifier of the audio signal with the first preset frequency is carried by the response signal, so as to obtain a target image of the high-speed railway train.

The third aspect of the embodiment of the invention discloses a train number identification device of a high-speed railway train, which comprises:

a memory storing executable program code;

a processor coupled with the memory;

the processor calls the executable program code stored in the memory to execute the steps of the method for identifying the train number of the high-speed railway train disclosed by the first aspect of the embodiment of the invention.

The fourth aspect of the embodiments of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute the train number identification method for a high-speed railway train disclosed in the first aspect of the embodiments of the present invention.

The fifth aspect of the embodiment of the invention discloses a computer program product, which when running on a computer, causes the computer to execute the train number identification method of the high-speed railway train disclosed in the first aspect.

Compared with the prior art, the embodiment of the invention has the following beneficial effects:

in the embodiment of the invention, the shooting device is controlled to carry out shooting operation on the high-speed railway train to obtain a target image aiming at the high-speed railway train; identifying at least one target area in the target image, wherein character content exists in the target image, and identifying the character content in each target area; judging whether the combination of the character contents of all the target areas accords with preset character logic or not, wherein the preset character logic at least comprises the number of characters contained in a train number identification corresponding to the train type of the high-speed railway train; and when the combination of the character contents of all the target areas accords with the preset character logic, determining the combination of the character contents of all the target areas as the train number identification of the high-speed railway train. Therefore, by implementing the embodiment of the invention, the target image obtained by shooting the high-speed railway train by the shooting device can be recognized to obtain the character content, and the obtained character content can be verified by the preset character logic, so that the train number identification of the high-speed railway train can be rapidly and accurately recognized.

Drawings

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

FIG. 1 is a schematic flow chart of a method for identifying a train number of a high-speed railway train according to an embodiment of the invention;

FIG. 2 is a schematic flow chart of another method for identifying the train number of a high-speed railway train according to the embodiment of the invention;

FIG. 3 is a schematic structural diagram of a train number identification device of a high-speed railway train according to an embodiment of the present invention;

FIG. 4 is a schematic structural diagram of another train number identification device for a high-speed railway train according to an embodiment of the present invention;

fig. 5 is a schematic structural diagram of a train number identification device of another high-speed railway train according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the terms "comprises" and "comprising," and any variations thereof, of embodiments of the present invention are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

The embodiment of the invention discloses a train number identification method and a train number identification device for a high-speed railway train, which can be used for identifying a target image obtained by shooting the high-speed railway train by a shooting device to obtain character contents, and verifying the obtained character contents by preset character logic, so that the train number identification of the high-speed railway train can be quickly and accurately identified. The following are detailed below.

Example one

Referring to fig. 1, fig. 1 is a schematic flow chart of a train number identification method for a high-speed railway train according to an embodiment of the present invention. The method described in fig. 1 can be applied to a management system of a high-speed railway train. As shown in fig. 1, the train number identification method of a high-speed railway train may include the operations of:

101. and controlling the shooting device to carry out shooting operation on the high-speed railway train to obtain a target image of the high-speed railway train.

In the embodiment of the invention, specifically, after the shooting device is controlled to perform continuous shooting operation on the high-speed railway train, a plurality of images aiming at the high-speed railway train can be obtained, a section of video aiming at the high-speed railway train can also be obtained, and the images in the video are extracted to obtain the plurality of images. The target image may be any one of the obtained multiple images. Preferably, the target image may be an image at an intermediate position, that is, all the obtained images are sorted according to the order of the shooting time, and an image at the intermediate position at the shooting time is determined as the target image. This is advantageous in improving the reliability of recognizing the character content from the target image.

For example, if 10 images are obtained after the shooting device is controlled to continuously shoot the high-speed railway train, and the 10 images are sequenced according to the sequence of the shooting time to obtain the 1 st image to the 10 th image, wherein the shooting time of the nth image is earlier than the (N + 1) th image, and N is greater than or equal to 1 and less than or equal to 9, the 5 th image or the 6 th image can be determined as the target image of the high-speed railway train.

In an alternative embodiment, the controlling the photographing device to perform the photographing operation on the high speed railway train, and obtaining the target image of the high speed railway train may include:

adjusting the shooting parameters of the shooting device by a preset imaging quality evaluation algorithm according to the sensed environmental parameters;

In this optional embodiment, specifically, after the environmental parameters of the current environment of the shooting device are sensed, the environmental parameters of the current environment and the influence of the current shooting parameters of the shooting device on the imaging quality of the shooting device can be evaluated through a preset imaging quality evaluation algorithm, and the shooting parameters of the shooting device are adjusted according to the evaluation result, so as to ensure the quality of images shot by the shooting device under different illumination conditions at different time intervals (all weather), and further, the accuracy of vehicle number identification is improved.

102. And identifying at least one target area with character content in the target image, and identifying the character content in each target area.

In an embodiment of the present invention, as an optional implementation manner, identifying at least one target area in the target image where character content exists, and identifying character content in each target area may include:

identifying a car number identification area in a target image, and performing character segmentation on the car number identification area to obtain at least one target area with character content;

In this alternative embodiment, the identified car number identifier region is the region that may contain the car number identifier.

The identifying the car number identification area in the target image, and performing character segmentation on the car number identification area to obtain at least one target area with character content may include:

detecting an extremum region of a target image by a maximum stable extremum region algorithm (MSER) based on a common character size parameter;

screening out a character extreme value region from the detected extreme value region through the physical parameters of the character, wherein the physical parameters of the character can comprise the length, the width, the length-width ratio and the like of the character;

connecting adjacent character extreme value regions which are screened out initially into candidate character regions through morphological closing operation, and using the candidate character regions as identified regions (namely vehicle number identification regions) which possibly contain vehicle number identifications;

performing predictive recognition on characters in each candidate character region, grading a recognition result to obtain a grading value, and determining a candidate character region with the highest grading value in all the grading values with the grading values meeting a preset grading threshold value condition as a final character region;

and (3) carrying out binarization on the final character area by an Otsu (OTSU) algorithm, and detecting an extreme value area in the final character area by three types of character size (large size, common size and small size) parameters to obtain at least one target area with character content.

Further, identifying the character content in each target region may include:

segmenting the final character region by a connected region method to obtain a segmented region;

performing AND operation on the segmentation area and the target area to screen suspicious characters;

and (3) identifying and predicting the screened suspicious characters by using a car number character prediction classifier, analyzing the positions and size characteristics of the suspicious characters, sequencing the suspicious characters and supplementing missing characters by combining character prediction results to obtain the character content of each target area, wherein the missing characters are unknown characters which cannot be identified in the target area of the target image and can be replaced by special characters (such as x).

The generation process of the car number character prediction classifier may include:

determining the cut character samples, and scaling the character samples to the same resolution (such as 20 x 20);

and calculating the HOG (Histogram of Oriented Gradient) characteristics of the character samples, inputting the HOG characteristics of the character samples and the sample characters into a Support Vector Machine (SVM) classifier for training, and obtaining the vehicle number character prediction classifier.

103. And judging whether the combination of the character contents of all the target areas accords with preset character logic, wherein the preset character logic at least comprises the number of characters contained in the train number identification corresponding to the train type of the high-speed railway train.

In the embodiment of the present invention, when the determination result in step 103 is yes, step 104 is triggered to be executed; when the judgment result of step 103 is no, the following operations may be performed:

and acquiring the next image obtained by the shooting operation of the shooting device on the high-speed railway train as a target image, and re-triggering the execution step 102 and the step 103.

In this embodiment of the present invention, before performing step 103, the following operations may also be included:

and determining the preset character logic.

Optionally, determining the preset character logic may include:

determining a geographical position, a shooting direction and a time period for executing the shooting operation of a shooting device, and determining basic information of the high-speed railway train according to the geographical position, the shooting direction, the time period for executing the shooting operation and the acquired train running schedule at the geographical position, wherein the basic information at least comprises a starting place, a route station and a destination of the high-speed railway train;

and determining a preset character logic corresponding to the high-speed railway train according to the basic information. Therefore, the matching degree of the determined preset character logic and the high-speed railway train can be improved.

In the embodiment of the present invention, optionally, the preset character logic may further include a character type included in a train number identifier corresponding to a train type of the high-speed railway train, a character position corresponding to different character types, and a character number corresponding to different character types. Therefore, the accuracy of the recognized vehicle number identification can be further improved. The character types may include a chinese character type, an alphabetic type, and a numeric type, and may also include an alphabetic type and a numeric type. For example, for a train of a certain type of high-speed railway, the corresponding train number identifier should include a chinese character identifier (e.g., "zheng" of zheng state railway bureau) for indicating the railway bureau to which the train of the high-speed railway belongs, an alphabetic identifier (e.g., "D" of the train classification identifier of the bullet train) for indicating the train classification, and a four-digit code number, e.g., zheng D1314, in the order of the sequence of the character positions.

In the embodiment of the present invention, the determination manner of the combination of the character contents of all the target areas specifically is:

dividing the preliminarily recognized car number identifier into a prefix part and a coding part according to preset character logic (such as prefix ending with letter and suffix as coding number), selecting a target prefix with highest matching degree with the prefix part in a car number prefix list according to the determined character recognized by the prefix part, taking the target prefix as the prefix part of the preliminarily recognized car number identifier, and determining the combination of the target prefix and the suffix as the combination of the character contents of all target areas.

104. And when the combination of the character contents of all the target areas accords with the preset character logic, determining the combination of the character contents of all the target areas as the train number identification of the high-speed railway train.

In the embodiment of the present invention, it should be noted that, after the car number identifier is identified according to the target image, another image may be continuously selected from the multiple images as a new target image, and the step 102 and the step 104 are executed again for the new target image, so as to obtain the car number identifier corresponding to each image in the multiple images, where it should be noted that, if the car number identifier of a certain image is not determined, the car number identifier of the certain image may be set to null. The method for identifying the vehicle number identification corresponding to each image not only can be used for further verifying the accuracy of the identified vehicle number identification, but also can be used for correcting the identified vehicle number identification according to a plurality of newly identified vehicle number identifications when the identified vehicle number identification is wrong so as to finally obtain the accurate vehicle number identification. Namely: the plurality of images can be used as a car number image group, each image in the car number image group is determined as a target image, and the operations in the steps 102 to 104 are respectively executed, so that a recognized car number identifier which is not null is obtained, wherein each car number identifier can comprise a prefix part and a number part; determining the prefix part with the most occurrence times in all the identified car number identifications as a final prefix, and forming different number sets by the number parts in all the identified car number identifications according to the position sequence, wherein the position sequence of characters included in each number set in the number part is the same; determining the character with the most occurrence times in each number set as a final character at the corresponding position sequence to obtain a final number; and combining the final prefix and the final number into a final vehicle number identification. Therefore, the accuracy of the recognized vehicle number identification is improved.

In the embodiment of the invention, the algorithm can reduce the recognition period of the vehicle number (the recognition period is as low as 5 seconds) and improve the recognition accuracy rate of the vehicle number (the recognition accuracy rate is up to more than 95%).

If the special characters (such as x) exist in the final train number identifier, it indicates that the train number identification is wrong, and the high-speed railway train needs to be photographed again. Further, the train number identification method of the high-speed railway train may further include the operations of:

if the special character exists in the finally determined car number mark, determining the forming reason of the special character;

when the forming reason of the special character is that the recognized character has the defect, determining the position of the defect of the character;

when the character has the defect and is positioned at the lower side of the character, the shooting angle of the shooting device is adjusted downwards, and when the character has the defect and is positioned at the upper side of the character, the shooting angle of the shooting device is adjusted upwards. Therefore, the reliability that a plurality of images shot by the shooting device contain complete characters can be ensured.

Therefore, by implementing the train number identification method for the high-speed railway train described in fig. 1, the target image obtained by shooting the high-speed railway train by the shooting device can be identified to obtain the character content, and the obtained character content can be verified through the preset character logic, so that the train number identification of the high-speed railway train can be quickly and accurately identified.

Example two

Referring to fig. 2, fig. 2 is a schematic flow chart of another method for identifying a train number of a high-speed railway train according to an embodiment of the present invention. The method described in fig. 2 can be applied to a management system of a high-speed railway train. As shown in fig. 2, the train number identification method of a high-speed railway train may include the operations of:

201. and controlling the audio signal transmitting device to transmit the audio signal of the first preset frequency.

202. Judging whether the audio signal receiving device receives a response signal within a preset time period after the audio signal transmitting device transmits the audio signal with the first preset frequency, and triggering to execute the step 203 when the judgment result of the step 202 is yes; when the determination result of step 202 is no, step 201 may be triggered to be executed continuously.

203. Judging whether the frequency of the response signal is a second preset frequency and whether the response signal carries a signal identifier of an audio signal with a first preset frequency, and if so, determining that the high-speed railway train is approaching the shooting device and the distance between the high-speed railway train and the shooting device is short, and triggering to execute step 204; when the determination result in step 203 is negative, the present flow may be ended.

204. And controlling the shooting device to carry out shooting operation on the high-speed railway train to obtain a target image of the high-speed railway train.

205. Detecting whether a text region exists in the target image through a preset detection algorithm, and triggering to execute the step 206 when the judgment result in the step 205 is yes; when the determination result of step 205 is no, the following operations may be performed:

and acquiring the next image obtained by the shooting operation of the high-speed railway train by the shooting device as a target image, and re-triggering to execute the step 205.

In the embodiment of the present invention, the preset detection algorithm may be a maximum stable extremum region algorithm (MSER) or a gray histogram detection algorithm, which is not limited in the embodiment of the present invention.

206. When the text area exists in the target image, at least one target area with character content in the target image is identified, and the character content in each target area is identified.

207. And judging whether the combination of the character contents of all the target areas accords with preset character logic, wherein the preset character logic at least comprises the number of characters contained in the train number identification corresponding to the train type of the high-speed railway train.

In the embodiment of the present invention, when the determination result in step 207 is yes, step 208 is triggered to be executed; when the determination result of step 207 is no, the following operations may be performed:

208. And when the combination of the character contents of all the target areas accords with the preset character logic, determining the combination of the character contents of all the target areas as the train number identification of the high-speed railway train.

In the embodiment of the present invention, please refer to the detailed description of steps 102 to 104 in the first embodiment for the description of steps 206 to 208, which is not repeated herein.

Therefore, the embodiment of the invention can trigger the shooting device to execute the shooting operation under the condition that the audio signal with the specific frequency is transmitted, the response signal with the specific frequency is received and the response signal meets the condition, so that the shooting device can be controlled to shoot when the high-speed railway train approaches the shooting device, the reliability of shooting the target image aiming at the high-speed railway train by the shooting device can be improved, and the power consumption of the shooting device can be reduced.

As an alternative embodiment, after the step 208 is performed, the method for identifying the train number of the high-speed railway train may further include the following operations:

collecting the collected images corresponding to the high-speed railway train under the train number identification of the high-speed railway train to form an image record of the high-speed railway train, wherein the image record at least comprises the train number identification, a pantograph panoramic image of the high-speed railway train and a slide plate image of the high-speed railway train.

In this optional embodiment, the formed image record may be uploaded to a monitoring platform of the high-speed railway train, so that when analyzing that the high-speed railway train has a fault (such as a pantograph fault or a sliding plate fault) according to the image, a supervisor finds a corresponding train number identifier in time according to the image record, and further finds a corresponding high-speed railway train, thereby facilitating a maintenance staff to repair the fault in time or notifying corresponding train group members to take corresponding measures in time.

In another optional embodiment, when the detection result in step 205 is yes, and before step 206 is performed, the method for identifying the train number of the high-speed railway train may further include the following operations:

a pre-processing operation is performed on the target image and step 206 is triggered.

Wherein the pre-processing operation may include at least one of a smoothing filtering operation, a contrast enhancement operation, and a brightness enhancement operation.

Specifically, the performing the preprocessing operation on the target image may include:

scaling the resolution of the target image to a preset resolution, such as 512 × 256;

and analyzing the HOG characteristics of the target image after the resolution scaling, performing exposure gain processing on the target image after the resolution scaling according to the HOG characteristics obtained by analysis, and smoothing the target image through Gaussian filtering to filter noise.

Therefore, the further alternative embodiment can perform the preprocessing operation on the target image before the target area with the character content in the target image is identified, so that the image quality of the target image is further improved, and the accuracy of the identified target area is further improved.

In yet another alternative embodiment, after the step 204 is performed and before the step 205 is performed, the method for identifying the train number of the high-speed railway train may further include the following operations:

judging whether the resolution of the target image meets a preset resolution condition, when the resolution does not meet the preset resolution condition, acquiring a next image obtained by shooting the high-speed railway train by the shooting device, taking the next image as the target image, and triggering and executing the operation of judging whether the resolution of the target image meets the preset resolution condition; when the preset resolution condition is satisfied, the step 205 is triggered to be executed. Therefore, the method for directly processing the target image with high resolution is beneficial to improving the reliability of processing the target image.

Therefore, by implementing the train number identification method for the high-speed railway train described in fig. 2, the target image obtained by shooting the high-speed railway train by the shooting device can be identified to obtain the character content, and the obtained character content can be verified by the preset character logic, so that the train number identification of the high-speed railway train can be quickly and accurately identified; in addition, the reliability of the target image of the high-speed railway train shot by the shooting device can be improved, and the power consumption of the shooting device can be reduced; moreover, when the fault (such as a pantograph fault or a sliding plate fault) of the high-speed railway train is analyzed according to the image, a supervisor can find the corresponding train number identifier in time according to the image record, so as to find the corresponding high-speed railway train, thereby being beneficial to repairing the fault in time or informing corresponding train group members to take corresponding countermeasures in time by maintenance personnel; the accuracy of identifying the target area can be improved.

EXAMPLE III

Referring to fig. 3, fig. 3 is a schematic structural diagram of a train number identification device of a high-speed railway train according to an embodiment of the present invention. The device described in fig. 3 can be applied to a management system of a high-speed railway train. As shown in fig. 3, the train number recognition apparatus of the high-speed railway train may include:

and the first control unit 301 is used for controlling the shooting device to carry out shooting operation on the high-speed railway train to obtain a target image of the high-speed railway train.

A recognition unit 302, configured to recognize at least one target area in the target image where the character content exists, and recognize the character content in each target area.

The judging unit 303 is configured to judge whether a combination of the character contents of all the target areas meets a preset character logic, where the preset character logic at least includes a number of characters included in a train number identifier corresponding to a train type of the high-speed railway train.

And the determining unit 304 is configured to determine the combinations of the character contents of all the target areas as the train number identifications of the high-speed railway train when the judging unit 303 judges that the combinations of the character contents of all the target areas conform to the preset character logic.

Optionally, the determining unit 304 may be further configured to determine the preset character logic before the determining unit 303 determines whether the combination of the character contents of all the target areas conforms to the preset character logic.

The determining unit 304 may specifically determine the preset character logic in a manner that:

In the embodiment of the present invention, optionally, the preset character logic may further include a character type included in a train number identifier corresponding to a train type of the high-speed railway train, a character position corresponding to different character types, and a character number corresponding to different character types. Therefore, the accuracy of the recognized vehicle number identification can be further improved. The character types may include a chinese character type, an alphabetic type, and a numeric type, and may also include an alphabetic type and a numeric type.

In the embodiment of the present invention, after the determining unit 304 identifies the car number identifier according to the target image, it may determine one image newly selected from the multiple images as a new target image, and trigger the unit to perform the same processing as that of the target image on the new target image, so as to obtain the car number identifier corresponding to each of the multiple images, where it is to be noted that if the car number identifier of a certain image is not determined, the car number identifier of the certain image may be set to null. The method for identifying the vehicle number identification corresponding to each image not only can further verify the accuracy of the identified vehicle number identification, but also can correct the identified vehicle number identification according to a plurality of newly identified vehicle number identifications when the identified vehicle number identification is wrong so as to finally obtain the accurate vehicle number identification. That is, the determination unit 304 may also be configured to:

determining the multiple images as a car number image group, determining each image in the car number image group as a target image, and finally determining all car number identifications which are not null and correspond to the multiple images, wherein each car number identification can comprise a prefix part and a number part;

determining the prefix part with the most occurrence times in all the identified car number identifications as a final prefix, and forming different number sets by the number parts in all the identified car number identifications according to the position sequence, wherein the position sequence of characters included in each number set in the number part is the same;

determining the character with the most occurrence times in each number set as a final character at the corresponding position sequence to obtain a final number;

and combining the final prefix and the final number into a final vehicle number identification. Therefore, the accuracy of the recognized vehicle number identification is improved.

Therefore, the device described in the embodiment of fig. 3 can be used for identifying the target image obtained by shooting the high-speed railway train by the shooting device to obtain the character content, and can be used for verifying the obtained character content through the preset character logic, so that the train number identification of the high-speed railway train can be quickly and accurately identified.

In an alternative embodiment, as shown in fig. 4, the first control unit 301 may include:

and the sensing subunit 3011 is configured to sense an environmental parameter of an environment where the shooting device is located.

And the adjusting subunit 3012 is configured to adjust, according to the environmental parameter sensed by the sensing subunit 3011, a shooting parameter of the shooting device through a preset imaging quality evaluation algorithm.

And the control subunit 3013 is configured to control the shooting device to perform shooting operation on the high-speed railway train according to the shooting parameters adjusted by the adjustment subunit 3012, so as to obtain a target image of the high-speed railway train.

It can be seen that, by implementing the device described in fig. 4, after sensing the environmental parameters of the current environment of the shooting device, the environmental parameters of the current environment and the influence of the current shooting parameters of the shooting device on the imaging quality of the shooting device can be evaluated through a preset imaging quality evaluation algorithm, and the shooting parameters of the shooting device are adjusted according to the evaluation result, so as to ensure the quality of the images shot by the shooting device under different illumination conditions at different time periods (all weather), and further, the accuracy of vehicle number identification is improved.

In another alternative embodiment, as shown in fig. 4, the apparatus may further include:

the collecting unit 305 is configured to collect the collected image corresponding to the high-speed railway train under the train number identifier of the high-speed railway train to form an image record of the high-speed railway train, where the image record at least includes the train number identifier, the pantograph panoramic image of the high-speed railway train, and the slide plate image of the high-speed railway train.

In yet another alternative embodiment, as shown in fig. 4, the apparatus may further include:

a detecting unit 306, configured to detect whether a text region exists in the target image through a preset detection algorithm, and when the text region exists in the target image, trigger the identifying unit 302 to perform the above-mentioned identification of at least one target region in which character content exists in the target image.

Wherein the text area includes the target area.

In this further alternative embodiment, further optionally, as shown in fig. 4, the apparatus may further include:

a preprocessing unit 307 configured to perform a preprocessing operation on the target image after the detecting unit 306 detects that the text region exists in the target image, wherein the preprocessing operation includes at least one of a smoothing filtering operation, a contrast enhancement operation, and a brightness enhancement operation.

The preprocessing unit 307 may be specifically configured to:

The identifying unit 302 is specifically configured to identify at least one target area in the target image where character content exists and identify character content in each target area when the detecting unit 306 detects that a text area exists in the target image and after the preprocessing unit 307 performs a preprocessing operation on the target image.

It can be seen that, by implementing the apparatus described in fig. 4, it is also possible to perform a preprocessing operation on the target image before identifying the target area in which the character content exists in the target image, which further improves the image quality of the target image and thus improves the accuracy of the identified target area.

In yet another alternative embodiment, the identifying unit 302 identifies at least one target area in the target image where the character content exists, and a manner of identifying the character content in each target area may specifically be:

The way for the recognition unit 302 to recognize the car number identification area in the target image and perform character segmentation on the car number identification area to obtain at least one target area with character content may specifically be:

And, the way for identifying each target area by the identifying unit 302 through the classifier to obtain the character content of each target area may specifically be:

and a second control unit 308 for controlling the audio signal transmitting apparatus to transmit the audio signal of the first preset frequency.

The determining unit 303 is further configured to determine whether the audio signal receiving device receives a response signal within a preset time period after the audio signal transmitting device transmits the audio signal with the first preset frequency, determine whether the frequency of the response signal is the second preset frequency and whether the response signal carries the signal identifier of the audio signal with the first preset frequency when the response signal is received, and trigger the first control unit 301 to execute the shooting operation of the shooting device for the high-speed railway train when the frequency of the response signal is the second preset frequency and the response signal carries the signal identifier of the audio signal with the first preset frequency, so as to obtain the target image of the high-speed railway train.

It can be seen that the implementation of the device described in fig. 4 can also trigger the shooting device to perform shooting operation when the audio signal with the specific frequency is transmitted, the response signal with the specific frequency is received, and the response signal meets the conditions, so that the shooting device can be controlled to shoot when the high-speed railway train approaches the shooting device, and thus, not only can the reliability of shooting the target image for the high-speed railway train by the shooting device be improved, but also the power consumption of the shooting device can be reduced.

In yet another alternative embodiment, the determining unit 303 may be further configured to determine whether a special character exists in the finally determined car number identifier.

The determining unit 304 may be further configured to determine a forming reason of the special character when the special character exists in the car number identifier finally determined by the determining unit 303, and determine a position where the character exists in the defect when the forming reason of the special character is that the recognized character exists in the defect.

The second control unit 308 may be further configured to adjust a photographing angle of the photographing device downward when the character is located at a lower side of the character, and adjust a photographing angle of the photographing device upward when the character is located at an upper side of the character.

Therefore, the device described in fig. 4 can also ensure the reliability that a plurality of images obtained by the shooting device contain complete characters by adjusting the shooting angle of the shooting device.

Example four

Referring to fig. 5, fig. 5 is a schematic structural diagram of train number identification of a high-speed railway train according to an embodiment of the present invention. The device described in fig. 5 can be applied to a high-speed railway train management system. As shown in fig. 5, the apparatus may include:

a memory 501 in which executable program code is stored;

a processor 502 coupled to a memory 501;

the processor 502 calls executable program code stored in the memory 501 to perform the steps in the train number identification of the high speed railway train described in fig. 1 or fig. 2.

EXAMPLE five

The embodiment of the invention discloses a computer-readable storage medium which stores a computer program, wherein the computer program enables a computer to execute the steps in the train number identification of a high-speed railway train described in figure 1 or figure 2.

EXAMPLE six

The embodiment of the invention discloses a computer program product, which causes a computer to execute the steps in the train number identification of the high-speed railway train described in the figure 1 or the figure 2 when the computer program product runs on the computer.

In various embodiments of the present invention, it should be understood that the sequence numbers of the above-mentioned processes do not imply an inevitable order of execution, and the execution order of the processes should be determined by their functions and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

In the embodiments provided herein, it should be understood that "B corresponding to A" means that B is associated with A from which B can be determined. It should also be understood, however, that determining B from a does not mean determining B from a alone, but may also be determined from a and/or other information.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit. The integrated units, if implemented as software functional units and sold or used as a stand-alone product, may be stored in a computer accessible memory. Based on such understanding, the technical solution of the present invention, which is a part of or contributes to the prior art in essence, or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several requests for causing a computer device (which may be a personal computer, a server, a network device, or the like, and may specifically be a processor in the computer device) to execute part or all of the steps of the above-described method of each embodiment of the present invention.

It will be understood by those skilled in the art that all or part of the steps in the methods of the embodiments described above may be implemented by hardware instructions of a program, and the program may be stored in a computer-readable storage medium, where the storage medium includes Read-Only Memory (ROM), Random Access Memory (RAM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Compact Disc Read-Only Memory (CD-ROM), or other Memory, such as a magnetic disk, or a combination thereof, A tape memory, or any other medium readable by a computer that can be used to carry or store data.

The method and the device for identifying the train number of the high-speed railway train disclosed by the embodiment of the invention are described in detail, the principle and the implementation mode of the invention are explained by applying specific examples, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims

1. A train number identification method of a high-speed railway train is characterized by comprising the following steps:

when the frequency of the response signal is judged to be the second preset frequency and the response signal carries the signal identification of the audio signal with the first preset frequency, controlling a shooting device to carry out shooting operation on the high-speed railway train to obtain a target image of the high-speed railway train;

when the combination of the character contents of all the target areas accords with the preset character logic, determining the combination of the character contents of all the target areas as the train number identification of the high-speed railway train;

if the determined car number mark has the special character and the forming reason of the special character is that the recognized character content has the defect, determining the position of the character content with the defect;

when the position is located at the lower side of the character content, the shooting angle of the shooting device is adjusted downwards, and the high-speed railway train is shot again;

and when the position is positioned at the upper side of the character content, the shooting angle of the shooting device is upwards adjusted, and the high-speed railway train is shot again.

2. The train number identification method of the high-speed railway train according to claim 1, wherein the controlling the photographing device to perform a photographing operation on the high-speed railway train to obtain a target image of the high-speed railway train comprises:

3. The train number identification method of a high-speed railway train according to claim 1 or 2, characterized by further comprising:

wherein the text region includes the target region.

4. The method of claim 3, wherein after detecting the presence of the text region in the target image, the method further comprises:

5. A train number recognition apparatus for a high-speed railway train, the apparatus comprising:

the determining unit is used for determining the combinations of the character contents of all the target areas as the train number identifications of the high-speed railway train when the judging unit judges that the combinations of the character contents of all the target areas accord with the preset character logic;

the determining unit is further configured to determine a position where the character content is incomplete if the determined car number identifier has the special character and the forming reason of the special character is that the recognized character content has the incomplete;

the first control unit is further used for adjusting the shooting angle of the shooting device downwards and shooting the high-speed railway train again when the position is located at the lower side of the character content, and adjusting the shooting angle of the shooting device upwards and shooting the high-speed railway train again when the position is located at the upper side of the character content;

6. The apparatus of claim 5, wherein the first control unit comprises:

7. The apparatus of claim 5 or 6, further comprising:

the device further comprises:

wherein the text region includes the target region.

8. The apparatus of claim 7, further comprising: