CN119090876A

CN119090876A - Gas tank qualification detection method, system, equipment, medium and program product

Info

Publication number: CN119090876A
Application number: CN202411570582.7A
Authority: CN
Inventors: 李斌; 徐应林; 赵多密; 李宗颖; 龙明录
Original assignee: Shenzhen Lanyang Technology Co ltd
Current assignee: Shenzhen Lanyang Technology Co ltd
Priority date: 2024-11-06
Filing date: 2024-11-06
Publication date: 2024-12-06
Anticipated expiration: 2044-11-06
Also published as: CN119090876B

Abstract

The application provides a gas tank qualification detection method, a system, equipment, a medium and a program product, wherein the method comprises the steps of collecting images of a gas tank shield area containing a gas tank identification code on a gas tank to be filled to obtain images to be identified; the gas tank fingerprint information bound by the gas tank identification code is determined, the gas tank fingerprint information comprises standard edge distance information generated according to the identification code of the gas tank leaving the factory and the edge line of the shield, the entity edge identification is carried out on the image to be identified, the first contour edge of the gas tank identification code and the second contour edge of the gas tank shield are obtained, the identification edge distance information is generated according to the first contour edge and the second contour edge, the qualification detection is carried out on the gas tank to be filled according to the identification edge distance information and the standard edge distance information, the accuracy of the qualification detection of the gas tank is improved, the condition that the unqualified gas tank is put into use after being filled with gas is reduced, and the potential safety hazard is reduced.

Description

Method, system, apparatus, medium and program product for detecting eligibility of gas tank

Technical Field

The invention relates to the technical field of gas filling management, in particular to a gas tank qualification detection method, a gas tank qualification detection system, gas tank qualification detection equipment, a gas tank qualification detection medium and a gas tank qualification detection program product.

Background

The fuel gas is used as a high-efficiency clean energy source, and is widely applied to families and business places in the current society, and because the fuel gas has the risk of inflammability and explosiveness, if the fuel gas tank with huge number and strong fluidity is improperly managed, potential safety hazards can be caused to people and property.

In order to enhance the safety management of the gas tank and reduce the safety risk of explosion and combustion of unqualified gas tanks, related departments require that identification codes are arranged on the gas tank, and the validity period of the gas tank are detected according to the identification codes on the gas tank in the gas filling stage, so that gas filling can be carried out only when the gas tank passes the detection qualification. But at present, the detection mode of the gas tank is simpler, and gas filling personnel can use the identification code of other qualified gas tanks to detect in order to evade qualified detection, and the condition that the unqualified gas tank is put into use after filling gas easily appears, leads to the potential safety hazard higher.

Disclosure of Invention

The invention provides a method, a system, equipment, a medium and a program product for detecting the qualification of a gas tank, which are used for solving the problems that in the filling stage of the gas tank, the detection mode of the gas tank is simpler, and the unqualified gas tank is easy to put into use after filling gas, so that potential safety hazard is high.

In a first aspect, an embodiment of the present application provides a method for detecting eligibility of a gas tank, including:

image acquisition is carried out on a gas tank shield area containing a gas tank identification code on the gas tank to be filled, so as to obtain an image to be identified of the gas tank to be filled;

determining gas tank fingerprint information of a gas tank bound by a gas tank identification code, wherein the gas tank fingerprint information comprises standard edge distance information generated according to an edge line of a shield of the gas tank and an edge line of the identification code on the shield when the gas tank leaves a factory;

performing entity edge recognition on the image to be recognized to obtain a first contour edge of the gas tank identification code and a second contour edge of the gas tank shield;

generating identification edge distance information according to the first contour edge of the gas tank identification code and the second contour edge of the gas tank shield;

And detecting the qualification of the gas tank to be filled according to the identification edge distance information and the standard edge distance information.

Optionally, performing entity edge recognition on the image to be recognized to obtain a first contour edge of the gas tank identification code and a second contour edge of the gas tank shield, including:

performing entity edge detection on the image to be identified by adopting an edge detection algorithm to obtain a target identification image comprising each entity edge;

carrying out contour recognition based on each entity edge on the target recognition image by adopting a contour detection algorithm, and recognizing to obtain entity contour information in the image to be recognized;

And determining contour edge information of each named entity in the image to be identified according to the entity contour information in the image to be identified, wherein the contour edge information of each named entity comprises a first contour edge of the gas tank identification code and a second contour edge of the gas tank shield.

Optionally, the contour edge information of each named entity further includes a third contour edge of an identification code tag where the gas tank identification code is located in the image to be identified, and determining contour edge information of each named entity in the image to be identified according to the entity contour information in the image to be identified includes:

Carrying out named entity identification classification according to entity profile information in the image to be identified, and determining profile information of a gas tank identification code, profile information of a gas tank shield and profile information of an identification code label in the image to be identified;

Determining a first contour edge of the gas tank identification code according to contour information of the gas tank identification code, wherein the first contour edge is a plurality of contour edges of the gas tank identification code and a contour edge with the shortest distance from a gas tank shield;

Determining a second contour edge of the gas tank shield according to contour information of the gas tank shield, wherein the second contour edge is a contour edge with the shortest distance from the first contour edge among a plurality of contour edges of the gas tank shield;

And determining a third contour edge of the identification code label according to the contour information of the identification code label, wherein the position of the third contour edge is between the first contour edge and the second contour edge.

Optionally, performing solid edge detection on the image to be identified by using an edge detection algorithm to obtain a target identification image including each solid edge, including:

performing image gray level conversion on the image to be identified, and performing Gaussian noise filtering on the image to be identified after gray level conversion to obtain a preprocessed image to be identified;

And carrying out entity edge detection on the preprocessed image to be identified by adopting an edge detection algorithm to obtain a target identification image comprising each entity edge.

Optionally, generating the identifying edge distance information according to the first contour edge of the tank identification code and the second contour edge of the tank shield includes:

acquiring a third contour edge of an identification code tag where a gas tank identification code is located in an image to be identified, wherein the third contour edge of the identification code tag is obtained by carrying out entity edge identification on the image to be identified;

and generating identification edge distance information according to the third contour edge, the first contour edge and the second contour edge.

Optionally, generating the identifying edge distance information according to the third contour edge, the first contour edge, and the second contour edge includes:

Determining the shortest distance between the first contour edge and the third contour edge to obtain a first edge distance, and determining the shortest distance between the third contour edge and the second contour edge to obtain a second edge distance;

and generating identification edge distance information according to the first edge distance and the second edge distance.

Optionally, the gas tank fingerprint information further includes standard micro texture features of an identification code area on the gas tank to which the gas tank identification code is bound, and before the image to be identified is subjected to entity edge identification, the method further includes:

acquiring microscopic images of a gas tank shield area on a gas tank to be filled, extracting features of microscopic texture information of the microscopic images to obtain target microscopic texture features of the microscopic images, and acquiring the microscopic images of the gas tank shield area containing a gas tank identification code on the gas tank to be filled through a microscopic camera device;

and when the matching degree of the target micro-texture features and the standard micro-texture features is greater than or equal to the preset matching degree, carrying out entity edge recognition on the image to be recognized.

In a second aspect, an embodiment of the present application provides a gas tank qualification detection system, including a detection device, where the detection device is used for:

In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where when the processor executes the computer program, the processor causes the electronic device to implement the method for detecting eligibility of a gas tank.

In a fourth aspect, an embodiment of the present application provides a readable storage medium storing a computer program which, when executed by a processor, causes the above-described gas tank eligibility detection method to be performed.

In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, where the computer program is executed to cause the above-mentioned gas tank qualification detection method to be performed.

In one scheme provided by the gas tank qualification detection method, the gas tank qualification detection system, the gas tank qualification detection equipment, the gas tank qualification detection medium and the gas tank qualification detection program product, image acquisition is carried out on a gas tank shield area containing a gas tank identification code on a gas tank to be filled to obtain a to-be-identified image of the gas tank to be filled, gas tank fingerprint information of the gas tank bound by the gas tank identification code is determined, the gas tank fingerprint information comprises standard edge distance information generated according to an edge line of a shield of the gas tank and an edge line of the identification code on the shield when the gas tank leaves a factory, entity edge identification is carried out on the to-be-identified image to obtain a first contour edge of the gas tank identification code and a second contour edge of the gas tank shield, identification edge distance information is generated according to the first contour edge of the gas tank identification code and the second contour edge of the gas tank shield, and qualification detection is carried out on the gas tank to be filled according to the identification edge distance information and the standard edge distance information. In the embodiment, the gas tank fingerprint information of the gas tank is obtained by pre-generating standard edge distance information according to the edge line of the shield of the gas tank and the edge line of the identification code on the shield, the identification code and the gas tank shield are subjected to edge detection to obtain identification edge distance information in the gas tank filling stage, then the gas tank qualification is detected according to the identification edge distance information and the standard edge distance information, the gas tank qualification is detected based on the visual identification technology, the gas tank qualification detection accuracy is improved, the condition that unqualified gas tanks are put into use after being filled with gas is reduced, and the potential safety hazard is reduced.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of a fuel gas tank qualification testing system according to an embodiment of the present invention;

FIG. 2 is a flow chart of a method for detecting eligibility of a gas tank according to an embodiment of the invention;

FIG. 3 is a flowchart illustrating an implementation of step S30 in FIG. 2;

FIG. 4 is a schematic diagram of the physical locations of an image to be identified according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of a solid outline edge obtained after solid edge recognition of an image to be recognized;

FIG. 6 is a flowchart illustrating an implementation of step S40 in FIG. 2;

FIG. 7 is a schematic view of edge distance information determined from edges of physical contours in an image to be identified;

FIG. 8 is a schematic flow chart of a method for detecting eligibility of a gas tank according to an embodiment of the present invention;

FIG. 9 is a schematic diagram of the detecting device in FIG. 1;

Fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

It should be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It should also be understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.

Furthermore, the terms "first," "second," "third," and the like in the description of the present specification and in the appended claims, are used for distinguishing between descriptions and not necessarily for indicating or implying a relative importance.

Reference in the specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the invention. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," and the like in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments" unless expressly specified otherwise. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.

It should be understood that the sequence numbers of the steps in the following embodiments do not mean the order of execution, and the execution order of the processes should be determined by the functions and the internal logic, and should not be construed as limiting the implementation process of the embodiments of the present invention.

In order to illustrate the technical scheme of the invention, the following description is made by specific examples.

It is to be appreciated that gas is a highly efficient, clean energy source that is widely used and is used in a wide variety of households and businesses. However, improper management can lead to a number of safety issues due to the large number of gas tanks and their high flowability. In order to reduce potential safety hazards, related departments require that an identification code or an identification code label printed with the identification code, such as a two-dimensional code label, be installed on the gas tank, and match the scanned two-dimensional code with data in the cloud platform so as to confirm the property right state and the detection validity period of the gas tank. At present, the detection mode of the gas tank is simpler, related personnel can use the identification codes of other qualified gas tanks to detect so as to avoid qualified detection, and the potential safety hazard is higher. For example, in order to evade supervision, an inflatable person often prints two-dimension codes of some qualified gas tanks and places the two-dimension codes of the printed qualified gas tanks in pockets, the two-dimension codes of the printed qualified gas tanks are called pocket codes, and when gas filling is carried out, the inflatable person scans the pocket codes to replace the two-dimension codes of unqualified gas tanks so as to evade qualified detection, and the unqualified gas tanks are inflated by violation, so that the unqualified gas tanks can be put into use after being filled with gas, and the potential safety hazard is high. Therefore, in the gas filling stage, the authenticity of the two-dimensional code image of the gas tank needs to be verified, so that the accuracy of qualified detection of the gas steel tank is improved, the situation that the unqualified gas tank is put into use after being filled with gas is reduced, and potential safety hazards are reduced.

In view of the above problems, the method for detecting the eligibility of the gas tank provided by the embodiment of the invention can be applied to a gas tank eligibility detection system shown in fig. 1, wherein the gas tank eligibility detection system comprises a collection device and a detection device, and the detection device is communicated with the collection device through a network.

The detection device is used for acquiring images of a gas tank shield area containing a gas tank identification code on a gas tank to be filled through the acquisition device to obtain an image to be identified of the gas tank to be filled, determining gas tank fingerprint information of the gas tank bound by the gas tank identification code, wherein the gas tank fingerprint information comprises standard edge distance information generated according to an edge line of a shield (namely the gas tank shield) of the gas tank and an edge line of the identification code (namely the gas tank identification code) on the shield when the gas tank leaves a factory, carrying out entity edge identification on the image to be identified to obtain a first contour edge of the gas tank identification code and a second contour edge of the gas tank shield, generating identification edge distance information according to the first contour edge of the gas tank identification code and the second contour edge of the gas tank shield, and carrying out qualification detection on the gas tank to be filled according to the identification edge distance information and the standard edge distance information so as to carry out gas filling on the gas tank to be filled when the gas tank to be filled is detected to be the qualified gas tank.

According to the embodiment, the gas tank fingerprint information of the gas tank is obtained by the standard edge distance information generated according to the edge line of the shield of the gas tank and the edge line of the identification code on the shield when leaving the factory, the identification edge distance information is obtained by determining the edge identification of the gas tank identification code and the gas tank shield in the gas tank filling stage, then the gas tank qualification detection is carried out according to the identification edge distance information and the standard edge distance information, the qualification detection of the gas tank is realized based on the visual identification technology, the accuracy of the gas tank qualification detection is improved, the condition that the unqualified gas tank is put into use after filling gas is reduced, and the potential safety hazard is reduced.

In this embodiment, the detection device may be an electronic control unit, and in other embodiments, the detection device may also be a computer device, including but not limited to a terminal device on various personal computers, notebook computers, smart phones, tablet computers, or a server device implemented by using an independent server or a server cluster formed by multiple servers.

The gas tank qualification detecting system includes a collecting device and a detecting device, which are only exemplary, and in other embodiments, the gas tank qualification detecting system may also include other devices necessary in the gas filling process, such as a gas filling device, that is, the gas tank qualification detecting system may be a gas filling system, where the gas filling system includes not only the collecting device and the detecting device, but also devices necessary for relevant gas filling steps such as the gas filling device.

In one embodiment, as shown in fig. 2, a method for detecting the qualification rate of a gas tank is provided, and the method is applied to the detection device in fig. 1, and includes the following steps:

and S10, acquiring an image of a gas tank shield area containing a gas tank identification code on the gas tank to be filled, and obtaining an image to be identified of the gas tank to be filled.

In the filling stage of the gas tank, an image acquisition is required for an identification code (such as a two-dimensional code) of the gas tank to be filled, so that information detection is carried out on the gas tank based on the acquired image. The gas tank to be filled is a gas tank which needs to be filled with gas at present, and when an automatic gas filling system performs gas filling, the gas tank placed on a filling station of the gas filling system can be directly used as the gas tank to be filled.

The detection device controls the acquisition device of the gas tank qualification detection system (namely the gas filling system), and performs image acquisition on a gas tank shield area containing a gas tank identification code on the gas tank to be filled to obtain an image to be identified of the gas tank to be filled. The image to be identified includes at least a tank shield and an identification code printed on the tank shield, i.e., a tank identification code. The gas tank shield is a protective cap or a protective cover used for protecting the tank body and being convenient for carrying.

And S20, determining gas tank fingerprint information of the gas tank bound with the gas tank identification code, wherein the gas tank fingerprint information comprises standard edge distance information generated according to the edge line of the shield of the gas tank and the edge line of the identification code on the shield when the gas tank leaves the factory.

After obtaining an image to be identified of a gas tank to be filled, the detection device needs to identify a gas tank identification code in the image to be identified through an identification code identification device (such as a two-dimensional code identification device or a two-dimensional code identification program), then matches the gas tank identification code with a plurality of gas tank identification codes stored in a database in advance, and obtains gas tank fingerprint information of the gas tank bound by the matched gas tank identification code.

When the gas tanks leave the factory, the identification code image acquisition and the fingerprint information extraction are required to be carried out on all the gas tanks leaving the factory, and the extracted gas tank fingerprint information is bound with the gas tank identification codes of the gas tanks one by one and then stored in a database so as to facilitate the subsequent gas tank information management and monitoring.

When the gas tank leaves the factory, the standard edge distance information generated according to the edge line of the shield of the gas tank and the edge line of the identification code on the shield, namely the standard edge distance information is the edge line position distance information of the shield and the identification code. In other embodiments, the tank fingerprint information further includes a standard image (such as a light intensity image) obtained by image acquisition of a tank shield area including a tank identification code on the gas tank or a microscopic image obtained by image acquisition of a tank shield area including a tank identification code on the gas tank when the gas tank leaves the factory.

And S30, carrying out entity edge recognition on the image to be recognized to obtain a first contour edge of the gas tank identification code and a second contour edge of the gas tank shield.

After the image to be identified of the gas tank to be filled is obtained, the detection device needs to perform entity edge identification on the image to be identified by adopting an edge detection algorithm, all entity edges in the image to be identified are obtained through identification, and a first contour edge of a gas tank identification code and a second contour edge of a gas tank shield are determined from all entity edges in the image to be identified. The first contour edge of the gas tank identification code is a contour edge with the shortest distance from the gas tank shield in a plurality of contour edges of the gas tank identification code, and the second contour edge of the gas tank shield is a contour edge with the shortest distance from the first contour edge in a plurality of contour edges of the gas tank shield.

And S40, generating identification edge distance information according to the first contour edge of the gas tank identification code and the second contour edge of the gas tank shield.

After the first contour edge of the gas tank identification code and the second contour edge of the gas tank shield are obtained, the detection device needs to generate position distance information of the first contour edge and the second contour edge according to the first contour edge of the gas tank identification code and the second contour edge of the gas tank shield, and then identification edge distance information is obtained.

For example, the identified edge distance information may be the shortest perpendicular distance of the first contour edge to the second contour edge. In other embodiments, the identified edge distance information may also be a perpendicular distance from a point in the first contour edge (e.g., two corners of the tank identification code) to the second contour edge.

In other embodiments, the identification edge distance information includes a ratio of a first edge distance to a second edge distance, wherein the first edge distance is a distance (e.g., shortest distance) between the first contour edge and a third contour edge, the second edge distance is a distance (e.g., shortest distance) between the third contour edge and the second contour edge, and the third contour edge is a third contour edge of an identification code label printed with a shield identification code on a gas tank shield. Correspondingly, the standard edge distance information is generated according to an identification code, an identification code label and an edge line of the shield of the gas tank when the gas tank leaves the factory, and comprises a ratio of a first edge distance to a second edge distance determined according to a standard image when the gas tank leaves the factory. The distance ratio of the identification code, the identification code label and the contour edge of the gas tank shield is used as an information verification basis to judge the authenticity of the acquired image of the gas tank, compared with the case that the contour edge distance is directly used as the information verification basis, the distance error generated by the acquisition device for acquiring the image of the same object at different distances can be reduced, the accuracy of standard edge distance information and identification edge distance information is improved, and the accuracy of the subsequent gas tank qualification verification is improved.

And S50, detecting the qualification of the gas tank to be filled according to the identification edge distance information and the standard edge distance information in the fingerprint information of the gas tank.

After the identification edge distance information of the gas tank identification code and the gas tank shield is determined, the detection device needs to detect the qualification of the gas tank to be filled according to the identification edge distance information and the standard edge distance information in the gas tank fingerprint information, and when the gas tank to be filled is detected to be the qualified gas tank, the gas filling device is controlled to perform gas filling on the gas tank to be filled, when the gas tank to be filled is detected to be the unqualified gas tank, the gas filling on the gas tank to be filled is forbidden, and an unqualified gas tank alarm is generated to prompt related personnel.

Determining the difference between the identification edge distance information and the standard edge distance information, if the difference between the identification edge distance information and the standard edge distance information is judged, when the difference between the identification edge distance information and the standard edge distance information is smaller than a preset value, the relative positions of an identification code and a gas tank shield (and an identification code label) are basically unchanged, the identification code of the gas tank to be filled is not moved, and the identification code of the image to be identified is the real identification code of the gas tank to be filled.

The method comprises the steps of determining whether the identification edge distance information is consistent with the standard edge distance information or not if the service age of the gas tank to be filled is smaller than the preset service life according to the gas tank production date bound by the gas tank identification code and/or determining that the current date is earlier than the verification date bound by the gas tank identification code, and controlling the gas filling equipment to perform gas filling on the gas tank to be filled if the identification edge distance information is smaller than the standard edge distance information and the identification edge distance information is consistent with the standard edge distance information, wherein the identification code and the gas tank shield (and the identification code label) are basically unchanged in relative positions, the gas tank identification code is normal in position, the identification code of the gas tank to be filled is not moved, the image to be identified is a real identification code image of the gas tank to be filled, and the gas tank to be filled is determined to be the qualified gas tank.

Before the entity edge recognition is performed on the image to be recognized, whether the age of the gas tank to be filled is smaller than the preset service life or not and/or whether the current date is earlier than the date to be verified (namely, the date of gas tank verification required to be performed by a related institution) which is bound by the gas tank identification code is determined according to the gas tank production date bound by the gas tank identification code. For example, the date to be verified, to which the gas tank identification code is bound, is 2023 and 10 months, and the current date is 2024 and 10 months, which indicates that the gas tank to be filled is out of date and not checked, the date to be verified, to which the gas tank identification code is bound, is 2024 and 11 months, and the current date is 2024 and 10 months, which indicates that the gas tank to be filled is normally involved in checking. If the age algorithm of the gas tank to be filled is determined to be smaller than the preset service life, the gas tank to be filled is indicated to not exceed the service life, the current date is earlier than the date to be verified bound by the gas tank identification code, the gas tank to be filled is indicated to normally participate in the inspection, and then the gas tank to be filled can be directly determined to be a qualified gas tank when the identification edge distance information is determined to be consistent with the standard edge distance information.

When the identification edge distance information is inconsistent with the standard edge distance information, the identification edge distance information and the standard edge distance information show that the identification information and the standard edge distance information are greatly different, the position of the gas tank identification code is changed, the identification code can be counterfeited and replaced, the image to be identified can not be the true identification code image of the gas tank to be filled, and the gas tank to be filled is determined to be the unqualified gas tank. Or before entity edge recognition is carried out on the image to be recognized, if the service age of the gas tank to be filled, which is determined according to the gas tank generation date bound by the gas tank identification code, is greater than or equal to the preset service life, determining that the gas tank to be filled is an unqualified gas tank. Or before the entity edge recognition is carried out on the image to be recognized, determining that the gas tank to be filled is out of date according to the date to be verified, which is bound by the gas tank identification code, and determining that the gas tank to be filled is an unqualified gas tank.

When the error between the identification edge distance information and the standard edge distance information is smaller than a preset value (for example, the preset value may be a value smaller than 0.1 and larger than or equal to 0), the identification edge distance information is determined to be consistent with the standard edge distance information, and when the error between the identification edge distance information and the standard edge distance information is larger than or equal to the preset value, the identification edge distance information is determined to be inconsistent with the standard edge distance information.

In the embodiment, an image is acquired on a gas tank shield area containing a gas tank identification code on a gas tank to be filled to obtain an image to be identified of the gas tank to be filled, gas tank fingerprint information of the gas tank bound by the gas tank identification code is determined, the gas tank fingerprint information comprises standard edge distance information generated according to an edge line of a shield of the gas tank and an edge line of the identification code on the shield when the gas tank leaves a factory, the image to be identified is subjected to entity edge identification to obtain a first contour edge of the gas tank identification code and a second contour edge of the gas tank shield, identification edge distance information is generated according to the first contour edge of the gas tank identification code and the second contour edge of the gas tank shield, and qualification detection is performed on the gas tank to be filled according to the identification edge distance information and the standard edge distance information, so that gas filling is performed on the gas tank to be filled when the gas tank to be filled is detected to be qualified. In the embodiment, the standard edge distance information of the identification code and the shield is generated in advance according to the identification code on the gas tank shield and the edge line of the shield, so that the gas tank fingerprint information of the gas tank is obtained, the identification edge distance information of the gas tank identification code and the gas tank shield is determined in the gas tank filling stage, then the gas tank qualification detection is carried out according to the identification edge distance information and the standard edge distance information, the gas tank qualification detection is realized based on the visual identification technology, the gas tank qualification detection accuracy is improved, the condition that the unqualified gas tank is put into use after being filled with gas is reduced, and the potential safety hazard is reduced.

In an embodiment, as shown in fig. 3, in step S30, the entity edge recognition is performed on the image to be recognized to obtain a first contour edge of the tank identifier and a second contour edge of the tank shield, which specifically includes the following steps:

and S31, carrying out entity edge detection on the image to be identified by adopting an edge detection algorithm to obtain a target identification image comprising each entity edge.

After the image to be identified is obtained, the detection device carries out entity edge detection on the image to be identified by adopting an edge detection algorithm, and a target identification image comprising each entity edge is obtained. The image to be identified comprises a gas tank shield and a gas tank identification code on the gas tank shield, and the target identification image comprises all edge lines of the gas tank shield and all edge lines of the gas tank identification code. The boundary of an object in the image can be accurately acquired through an edge detection algorithm, and the gas tank identification codes on the gas tank and the outer contour edge of the gas tank shield are highlighted.

The method comprises the steps of carrying out image gray level conversion on an image to be identified, carrying out Gaussian noise filtering on the image to be identified after gray level conversion to obtain a preprocessed image to be identified, and carrying out entity edge detection on the preprocessed image to be identified by adopting an edge detection algorithm to obtain the target identification image comprising each entity edge. The method comprises the steps of converting an image to be identified into a gray image, reducing the calculated amount, only preserving contour information, using Gaussian blur to filter noise, enhancing the definition of the image edge, improving the accuracy and the robustness of entity edge identification in the image, carrying out contour detection on a target identification image, and ensuring the stability and the high efficiency of contour edge identification under complex background and illumination conditions by means of combining image preprocessing (graying, denoising), edge detection and contour detection.

The edge detection algorithm can be an image edge detection algorithm such as a Sobel operator Sobel and a first-order differential operator Prewitt. For example, a Sobel operator can be adopted to perform entity edge detection on an image to be identified to obtain a target identification image comprising each entity edge, wherein gradient calculation is performed on the image to be identified, namely gradient strength and direction of each pixel in the image are calculated, wherein the gradient strength represents the variation amplitude of a pixel value, and the gradient direction represents the variation direction; the method comprises the steps of carrying out pixel processing on an image to be identified after gradient calculation, wherein the pixel processing comprises non-maximum value inhibition and edge separation based on double thresholds, so that edges are marked only at positions with maximum variation through the non-maximum value inhibition, and strong edges, weak edges and non-edges are separated through setting high and low thresholds, wherein the strong edges are pixels with gradient intensity larger than the high threshold, the weak edges are pixels with gradient intensity between the low threshold and the high threshold, the pixels with gradient intensity lower than the low threshold are inhibited, the edges are thinned through inhibiting the non-maximum value, neighborhood pixels in the gradient direction of each pixel are checked, only local maximum values are reserved, the accuracy of the edges is ensured, unnecessary edge pixels are removed, edge connection is carried out on the image to be identified in the pixel processing, the edge connection is carried out through edge tracking to connect the weak edges and the strong edges, so that isolated weak edge pixel points are connected into complete edges, only the weak edges connected with the strong edges are reserved, and the target identification images of all the obvious edges in a display image are output, the edge continuity of broken edges is reduced.

And S32, carrying out contour recognition based on each entity edge on the target recognition image by adopting a contour detection algorithm, and recognizing to obtain entity contour information in the image to be recognized.

After the target identification image comprising each entity edge is obtained, the detection device carries out contour identification based on each entity edge on the target identification image by adopting a contour detection algorithm, and the entity contour information in the image to be identified is obtained by identification.

The method comprises the steps of carrying out contour extraction on solid edges in a target identification image by adopting a contour detection algorithm to find and obtain continuous edge lines (namely edge contours) in the target identification image, wherein the edge contours represent boundaries of objects, carrying out contour classification on all the continuous edge lines in the target identification image, dividing different edge contours into an outer contour (object boundary) and an inner contour (such as internal segmentation of an identification code), defining the shape and the boundary of each object in the image, and outputting the identified edge contours in the form of coordinate points to obtain solid contour information in the image to be identified. The edge information obtained by edge detection can be converted into more structured contour data through contour detection, accurate object shape information is provided, and the rectangular or linear contour of the identification code of the gas tank and the overall shape of the gas tank shield can be accurately identified.

For example, the method comprises the steps of performing image gray level conversion on an image to be identified to obtain a gray level image, wherein the value of all pixel points in the gray level image is 0 or 255, smoothing the gray level image by adopting a Gaussian filter to reduce the influence of noise, blurring the image by convolution operation to remove tiny noise, detecting the image edge in the binarized gray level image by using an edge detection algorithm, identifying continuous edge point sets by scanning pixels of the gray level image, wherein the sets are called contours, the contours can be closed (such as circles and rectangles) or open (such as line segments), and performing entity contour identification by analyzing the shape characteristics (such as area, perimeter and rectangular boundary and the like) of the contours to further screen out contour information of different entities, such as a positioning pattern of a two-dimensional code is formed by specific black-white squares, and the squares in the image can be used as a factor of a two-dimensional code.

Wherein a binary gray scale image is generated using a Canny or other method (e.g., thresholding) that can be an edge detection algorithm, and a function Find Contours(Input Output Array image, Output Array Of Arrays contours, Output Array hierarchy, int mode, int method, Point offset = Point()), is used to find the contours in the binary gray scale image. Each contour is a vector of points representing the boundaries of the contour, and if the hierarchy parameters are specified, the returned hierarchical information may help understand the nesting relationship between contours. In an image, a contour is typically a closed or open path made up of successive edge pixels. Examples of contours that may be considered include boundaries of objects such as the outer contours of objects in an image, internal boundaries such as holes or other features within objects, and noise that may sometimes be identified as contours that need to be filtered by shape analysis.

S33, determining contour edge information of each named entity in the image to be identified according to the entity contour information in the image to be identified, wherein the contour edge information of each named entity comprises a first contour edge of a gas tank identification code and a second contour edge of a gas tank shield.

After the entity contour information in the image to be identified is obtained, the detection device determines contour edge information of each named entity in the image to be identified according to the entity contour information in the image to be identified. Wherein the contour edge information for each named entity includes a first contour edge of the tank identification code and a second contour edge of the tank shield.

Specifically, the detection device analyzes the shape, size and position of the image contour through the entity contour information in the image to be identified, identifies and distinguishes contour edges of different entities, and obtains contour edge information of the gas tank identification code and contour edge information of the gas tank shield, for example, the gas tank identification code is usually a small and regular rectangular area, the contour of the gas tank shield is a larger area surrounding the gas tank main body, and accuracy of entity classification can be further confirmed based on preset contour shape rules (such as rectangle, circle and the like) or through a trained model. Then, a first contour edge of the tank identification code is determined in contour edge information of the tank identification code, and a second contour edge of the tank shield is determined in contour edge information of the tank shield. The process can effectively identify and distinguish different object outlines, ensure that the gas tank identification code and the gas tank shield can be accurately identified and positioned, and facilitate subsequent data processing (such as code scanning, qualification detection and the like) to provide an accurate basis.

In this embodiment, the edge detection algorithm is adopted to perform entity edge detection on the image to be identified to obtain a target identification image including each entity edge, then the contour detection algorithm is adopted to perform contour identification based on each entity edge on the target identification image to obtain entity contour information in the image to be identified, finally contour edge information of each named entity in the image to be identified is determined according to the entity contour information in the image to be identified, and the contour edge information of each named entity includes a first contour edge of a gas tank identification code and a second contour edge of a gas tank shield, so that a specific process of performing entity edge identification on the image to be identified is refined. The combination of the edge detection and the contour recognition algorithm enhances the accuracy and the robustness of recognition, can cope with the recognition requirements of gas tank images in various complex scenes, can rapidly and accurately recognize gas tank identification codes and gas tank shields in the gas tank images, and provides an accurate basis for subsequent image processing steps.

In an embodiment, the contour edge information of each named entity further includes a third contour edge of an identification code tag in which the identification code of the gas tank in the image to be identified is located. In step S33, the contour edge information of each named entity in the image to be identified is determined according to the entity contour information in the image to be identified, which specifically includes the following steps:

S331, carrying out named entity identification classification according to entity profile information in the image to be identified, and determining profile information of a gas tank identification code, profile information of a gas tank shield and profile information of an identification code label in the image to be identified.

In this embodiment, as shown in fig. 4, an identification code label is mounted on a gas tank cover of a gas tank manufactured by XX gas company, and a gas tank identification code is printed on the identification code label, and the image to be identified includes the gas tank cover, the identification code label mounted on the gas tank cover, and the gas tank identification code printed in the identification code label. Correspondingly, the contour edge information of each named entity in the image to be identified also comprises a third contour edge of the identification code label where the gas tank identification code in the image to be identified is located.

The detection device carries out named entity identification classification according to the entity profile information in the image to be identified, and determines the profile information of the gas tank identification code, the profile information of the gas tank shield and the profile information of the identification code label in the image to be identified.

The feature classification algorithm (such as shape, size, position and other features) may be utilized to perform preliminary classification on the entity profile information in the image to be identified, and generally, the shapes and positions of the gas tank identification code, the gas tank shield and the identification code label have a certain regularity, and the profile information of the gas tank identification code, the profile information of the gas tank shield and the profile information of the identification code label are classified according to a predetermined classification rule or a pre-trained entity identification model. By classifying based on the profile, key parts in the gas tank image can be accurately distinguished, and further extraction of subsequent edge information is facilitated. The classification method reduces the false recognition rate, so that the system can reliably distinguish the structures such as the gas tank identification code and the protective cover thereof.

And S332, determining a first contour edge of the gas tank identification code according to contour information of the gas tank identification code.

And determining a first contour edge of the gas tank identification code according to contour information of the gas tank identification code, wherein the first contour edge is a plurality of contour edges of the gas tank identification code and a contour edge with the shortest distance from a gas tank shield.

Specifically, by classifying the profile information of the obtained gas tank identification code, determining a plurality of profile edges of the gas tank identification code, calculating the distance between each profile edge of the gas tank identification code and the gas tank shield (such as the center point of the gas tank shield or the reference profile edge), comparing the distance between each profile edge of the gas tank identification code and each profile edge of the gas tank shield by using a distance calculation algorithm (such as Euclidean distance), and selecting the profile edge closest to the gas tank shield as the first profile edge from the plurality of profile edges of the gas tank identification code. This process may accurately determine the specific location and outer profile of the tank identification code, particularly in complex scenarios where the identification code may be adjacent to other objects. By accurately calculating the distance between the edge and the shield, the edge recognition accuracy can be improved, and the edge of other areas serving as the identification code can be prevented from being recognized by mistake.

In other embodiments, the first contour edge may also be a plurality of contour edges of the tank identification code that are the longest from the tank shield.

S333, determining a second contour edge of the gas tank shield according to contour information of the gas tank shield.

And determining a second contour edge of the gas tank shield according to contour information of the gas tank shield, wherein the second contour edge is the contour edge with the shortest distance from the first contour edge in a plurality of contour edges of the gas tank shield.

Specifically, a plurality of contour edges of the gas tank shroud are determined from contour information of the gas tank shroud, then distances between the plurality of contour edges of the gas tank shroud and a first contour edge of the gas tank identification code are calculated, and an edge that is shortest from the first contour edge of the identification code is selected from the plurality of contour edges of the shroud as a second contour edge of the gas tank shroud. By calculating the distance between the shield and the first contour edge of the gas tank identification code, the accurate position and the boundary of the gas tank shield can be determined, the relative position relation between the shield and the gas tank identification code can be recognized, and the recognition result is more stable and reliable.

S334, determining a third contour edge of the identification code label according to the contour information of the identification code label.

And determining a third contour edge of the identification code label according to the contour information of the identification code label, wherein the position of the third contour edge is between the first contour edge and the second contour edge. And obtaining the contour information of the identification code tag through the previous contour classification result.

Specifically, the relative positions of each contour edge of the identification code label and the first contour edge of the gas tank identification code and the second contour edge of the gas tank shield are determined according to the contour information of the identification code label, then the contour edge between the first contour edge and the second contour edge is determined, and the contour edge is recorded as a third contour edge of the identification code label.

For example, after entity edge recognition is performed on the image to be recognized, the contour information of each named entity in the obtained image to be recognized may be as shown in fig. 5. The edge line 1, the edge line 2 and the edge line 3 in fig. 5 are respectively the second contour edge of the tank shield, the third contour edge of the identification code label and the first contour edge of the tank identification code.

In other embodiments, it is also possible to determine only the second contour edge of the tank shield and the first contour edge of the tank identification code, and not determine the third contour edge of the identification code tag, i.e. the contour edge information of each named entity in the image to be identified comprises the first contour edge of the tank identification code and the second contour edge of the tank shield, and not the third contour edge of the identification code tag.

After determining the first contour edge of the tank identification code, the second contour edge of the tank shield, and the third contour edge of the identification code tag, identification edge distance information is generated from the third contour edge, the first contour edge, and the second contour edge.

In the embodiment, named entity identification classification is performed according to entity profile information in an image to be identified, profile information of a gas tank identification code, profile information of a gas tank shield and profile information of an identification code label in the image to be identified are determined, a first profile edge of the gas tank identification code is determined according to the profile information of the gas tank identification code, the first profile edge is a profile edge with the shortest distance from a plurality of profile edges of the gas tank identification code to the gas tank shield, a second profile edge of the gas tank shield is determined according to the profile information of the gas tank shield, the second profile edge is a profile edge with the shortest distance from the first profile edge in the plurality of profile edges of the gas tank shield, and a third profile edge of the identification code label is determined according to the profile information of the identification code label, wherein the position of the third profile edge is located between the first profile edge and the second profile edge. The method can effectively identify the edges of the gas tank identification code, the gas tank shield and the identification code label thereof through multi-round edge calculation and contour detection, ensure that the edge information is accurate, and ensure that different contours can still be accurately identified by the system through gradually determining the distance relation of the edges of different contours under a complex scene, especially when the contour edges of named entities are adjacent or overlapped, reduce the false identification condition caused by the approach between objects or image noise, reduce the identification error and improve the identification robustness, and provide a good basis for the follow-up identification task through accurately extracting and classifying various entity edge information in the gas tank image.

In an embodiment, before step S332, i.e. before determining the first contour edge of the tank identification code based on the contour information of the tank identification code, the method further comprises the steps of:

S335, after the named entity identification classification is carried out according to the entity outline information in the image to be identified, determining whether a first type entity and a second type entity exist in the image to be identified.

After the named entity identification classification is carried out according to the entity contour information in the image to be identified, all named entities included in the image to be identified are obtained, all named entities included in the image to be identified are matched with the first type entity, if the first type entity is matched, the first type entity is determined to exist in the image to be identified, if the first type entity is not matched, the first type entity is determined to not exist in the image to be identified, similarly, all named entities included in the image to be identified are matched with the second type entity, if the second type entity is matched, the second type entity is determined to exist in the image to be identified, and if the second type entity is not matched, the second type entity is determined to not exist in the image to be identified.

The first type of entity is an entity existing in a standard image in the tank fingerprint information, such as a tank shield, a tank identification code, an identification code label, a fixture (such as a bolt and a screw) on the identification code label, and the like. The second type of entity is an entity that does not exist in a standard image in the tank fingerprint information, such as a human body part (palm, finger), a tank identification code, or other entities around the identification code tag (e.g., adhesive tape, rope, etc.).

S336, if the first type entity exists in the image to be identified and the second type entity does not exist in the image to be identified, determining a first contour edge of the gas tank identification code according to contour information of the gas tank identification code.

If the first type entity exists in the image to be identified and the second type entity does not exist in the image to be identified, determining a first contour edge of the gas tank identification code according to contour information of the gas tank identification code so as to carry out contour edge-based gas tank qualification detection subsequently.

And S337, if the first type entity does not exist in the image to be identified or the second type entity exists in the image to be identified, determining that the gas tank to be filled is a disqualified gas tank.

If the first type entity does not exist in the image to be identified or the second type entity exists in the image to be identified, the identification code in the image to be identified is possibly not the true identification code of the liquefied tank to be filled, and the condition that the identification code is forged and replaced is determined, the gas tank to be filled is a disqualified gas tank. And the outline edge detection is not needed, the data processing is reduced, and the qualification detection efficiency of the gas tank is improved.

In the embodiment, after the named entity identification classification is performed according to the entity contour information in the image to be identified, whether the first type entity and the second type entity exist in the image to be identified is determined, if the first type entity exists in the image to be identified and the second type entity does not exist in the image to be identified, the first contour edge of the gas tank identification code is determined according to the contour information of the gas tank identification code, and if the first type entity does not exist in the image to be identified or the second type entity exists in the image to be identified, the gas tank to be filled is determined to be a disqualified gas tank, so that data processing can be reduced, and the qualification detection efficiency of the gas tank is improved.

In other embodiments, before entity edge recognition is performed on an image to be recognized, the detection device can perform entity detection on the image to be recognized through a target detection model obtained through pre-training to obtain all named entities in the image to be recognized, then determine whether a first type entity and a second type entity exist in the image to be recognized, if the first type entity exists in the image to be recognized and the second type entity does not exist in the image to be recognized, perform entity edge recognition on the image to be recognized, and if the first type entity does not exist in the image to be recognized or the second type entity exists in the image to be recognized, determine that the gas tank to be filled is a non-qualified gas tank, thereby reducing data processing and improving the qualification detection efficiency of the gas tank

In an embodiment, as shown in fig. 6, in step S40, that is, according to the first contour edge of the tank identification code and the second contour edge of the tank shield, identification edge distance information is generated, which specifically includes the following steps:

s41, acquiring a third contour edge of an identification code label where a gas tank identification code is located in an image to be identified.

After the first contour edge of the tank identification code and the second contour edge of the tank shield are obtained, a third contour edge of the identification code tag in which the tank identification code is located in the image to be identified needs to be obtained. The third contour edge of the identification code label is obtained by performing entity edge identification on the image to be identified, and the specific process participates in the foregoing and is not described herein.

And S42, generating identification edge distance information according to the third contour edge, the first contour edge and the second contour edge.

And then, generating identification edge distance information according to the third contour edge, the first contour edge and the second contour edge, and improving the diversity and accuracy of the identification edge distance information. For example, the distance of the third contour edge from the first contour edge, the distance of the third contour edge from the second contour edge, and the distance of the first contour edge from the second contour edge may be used together as the tank identification code and the identification edge distance information of the tank shield.

In other embodiments, the identification edge distance information of the tank identification code and the tank shield may be generated directly from the first contour edge and the second contour edge, without taking the third contour edge into account, e.g., the distance of the first contour edge from the second contour edge may be directly taken as the identification edge distance information.

In this embodiment, by acquiring the third contour edge of the identification code tag where the gas tank identification code is located in the image to be identified, the third contour edge of the identification code tag is obtained by performing entity edge identification on the image to be identified, and the identification edge distance information is generated according to the third contour edge, the first contour edge and the second contour edge, so that when the identification edge distance information is determined, the third contour edge of the identification code tag is increased, and the diversity and accuracy of the identification edge distance information are improved.

In one embodiment, in step S42, the identifying edge distance information is generated according to the third contour edge, the first contour edge, and the second contour edge, and specifically includes the following steps:

s421, determining the shortest distance between the first contour edge and the third contour edge to obtain a first edge distance, and determining the shortest distance between the third contour edge and the second contour edge to obtain a second edge distance.

The method comprises the steps of calculating the distance between a first contour edge of a gas tank identification code and each point of a third contour edge of an identification code label, and selecting a minimum distance from all possible distances from the first contour edge to the third contour edge as the shortest distance between the first contour edge and the third contour edge to obtain a first edge distance; similarly, the distance calculation is performed on each point of the second contour edge and the third contour edge, and the minimum distance is selected from all possible distances from the second contour edge to the third contour edge as the shortest distance between the two, so as to obtain the second edge distance.

In other embodiments, the first edge distance of the first contour edge from the third contour edge may be determined in other ways, and the second edge distance of the second contour edge from the third contour edge may be determined in other ways. For example, when the gas tank identifier is a rectangular identifier, a certain point (e.g., the upper left corner or the upper right corner of the rectangular identifier) of the first contour edge of the gas tank identifier is used as a reference point, the vertical distance from the reference point to the third contour edge is determined to obtain a first edge distance, and the vertical distance from the reference point (or the intersection point of the reference point and the vertical line of the third contour edge) to the second contour edge is determined to obtain a second edge distance.

For example, as shown in fig. 7, the gas tank identification code is a square two-dimensional code, a certain point (i.e. the upper left corner of the two-dimensional code) of a first contour edge of the gas tank identification code is taken as a reference point, the reference point is taken as a coordinate origin o, the first contour edge is taken as an x axis, a y axis is established in a direction perpendicular to a third contour edge, a rectangular coordinate system is established, wherein the y axis forms a first intersection point M with the third contour edge of the identification code label, the y axis forms a second intersection point N with a second contour edge of the gas tank shield, the distance from the reference point of the first contour edge to the first intersection point M is a first edge distance a, and the distance from the first intersection point M to the second intersection point N is a second edge distance b.

And S422, generating identification edge distance information according to the first edge distance and the second edge distance.

And then, generating identification edge distance information according to the first edge distance and the second edge distance, and generating the identification edge distance information by selecting the shortest distance between the two contour edges, thereby improving the accuracy of the identification edge distance information. The identifying edge distance information includes a ratio of a first edge distance to a second edge distance, the first edge distance being a distance (e.g., shortest distance) between the first contour edge and the third contour edge, and the second edge distance being a distance (e.g., shortest distance) between the third contour edge and the second contour edge.

For example, a ratio a/b of the first edge distance a and the second edge distance b may be used as the identification edge distance information. The ratio a/b of the first edge distance a and the second edge distance b, and the sum of the first edge distance a and the second edge distance b may be used together as the identification edge distance information. That is, the identification edge distance information includes a ratio of the first edge distance and the second edge distance, and a sum of the first edge distance and the second edge distance.

In an embodiment, the first edge distance a, the second edge distance b, the ratio a/b of the first edge distance a and the second edge distance b, and the sum of the first edge distance a and the second edge distance b may be used together as the identification edge distance information. That is, the identification edge distance information includes a first edge distance a, a second edge distance b, a ratio a/b of the first edge distance and the second edge distance, and a sum (a+b) of the first edge distance and the second edge distance. Correspondingly, the calculation process of the standard edge distance information and the system for identifying the edge distance information, namely the standard edge distance information has the same distance information as the number and the type of the identified edge distance information. In the embodiment, the accuracy of identifying the edge distance information and the standard edge distance information can be improved, judgment errors caused by single distance information are avoided, and the accuracy of detecting the qualification of the gas tank is improved.

In this embodiment, the shortest distance between the first contour edge and the third contour edge is determined to obtain a first edge distance, the shortest distance between the third contour edge and the second contour edge is determined to obtain a second edge distance, and the identification edge distance information is generated according to the first edge distance and the second edge distance, so that a specific process of generating the identification edge distance information is clarified, and accuracy of the identification edge distance information is improved.

In one embodiment, as shown in FIG. 8, the tank fingerprint information also includes standard micro-texture features of the identification code area on the gas tank to which the tank identification code is bound. Before step S30, i.e. before performing entity edge recognition on the image to be recognized, the method further includes the following steps:

s60, acquiring a microscopic image of a gas tank shield area on the gas tank to be filled, and extracting features of microscopic texture information of the microscopic image to obtain target microscopic texture features of the microscopic image.

Before entity edge recognition is carried out on an image to be recognized, a detection device acquires a microscopic image of a gas tank shield area on the gas tank to be filled. The microscopic image is acquired by a microscopic camera device from a gas tank shield area containing a gas tank identification code on a gas tank to be filled. A microscope image pickup device is an image pickup apparatus developed for a microscope for picking up an image of an observation object in the microscope.

In this embodiment, the collecting device may be a photographing device with a microscope photographing function, when the collecting device collects an image of a gas tank shield area containing a gas tank identification code on a gas tank to be filled, a common camera (such as a digital camera) in the collecting device collects an image of the gas tank shield area containing the gas tank identification code on the gas tank to be filled, so as to obtain an image to be identified, and the microscope photographing device in the collecting device collects a microscopic image of the gas tank shield area containing the gas tank identification code on the gas tank to be filled, so as to obtain a microscopic image of the gas tank shield area on the gas tank to be filled. Wherein, because the image acquisition distance, the acquisition angle and the equipment image parameters all can influence the imaging effect, when controlling the acquisition device to carry out image acquisition on the gas tank to be filled, the related parameters of the acquisition device are required to be ensured to be the same as the related parameters (such as the image acquisition distance, the acquisition angle and the equipment image parameters) when the gas tank is delivered to the factory and the standard microscopic image is acquired, the imaging effect is ensured to be similar, and the accuracy and the robustness of the follow-up identification are improved.

After a microscopic image of a gas tank shield area on a gas tank to be filled is acquired, the detection device performs feature extraction on microscopic texture information of the microscopic image to obtain target microscopic texture features of the microscopic image.

The acquired microscopic image is analyzed by utilizing a computer vision algorithm, microscopic texture information of a gas tank shield area is extracted, extracted texture features (target microscopic texture features and standard microscopic texture features) are feature vectors which are quantized, and each feature vector represents texture information of a specific area in the image. For example, the texture features of the microscopic image may be extracted by using a computer vision algorithm such as a Scale-invariant feature transform SIFT (Scale-INVARIANT FEATURE TRANSFORM) algorithm, an acceleration robust feature SURF (Speeded Up Robust Features) algorithm, a rapid feature point extraction ORB (Oriented Fast and Rotated Brief) algorithm, and the like, to obtain the target microscopic texture features. The extracted target micro-texture features may include surface roughness, texture directionality, microscopic shapes, etc. for describing the micro-features of the cylinder shroud, cylinder identification code (and identification code label) surface.

The microscopic imaging device is used for imaging the shield area containing the gas tank identification code on the gas tank, so that the microscopic details of the gas tank shield surface can be captured, the microscopic equipment can provide enough magnification to clearly capture microscopic texture information of the gas tank surface, the microscopic textures can reflect information such as materials, processing technology and abrasion of the shield surface, and the microscopic structures of the gas tank surface can be quantized and digitized through extracting the characteristics of the surface textures of the gas tank shield area, so that the surface features of different gas tanks can be accurately compared and evaluated. And the inflatable personnel replaces the two-dimension code image of the unqualified gas tank with the printed pocket code to carry out qualification verification, and the printed pocket code image is smooth and does not have texture information in the real gas tank image, so that the two-dimension code image of the gas tank which is not real can be intuitively and quickly screened out, and the unqualified gas tank is detected.

And S70, when the matching degree of the target micro-texture features and the standard micro-texture features is greater than or equal to the preset matching degree, carrying out entity edge recognition on the image to be recognized.

In this embodiment, the tank fingerprint information further includes standard micro-texture features of the identification code area on the gas tank to which the tank identification code is bound. When the gas tank leaves the factory, the image acquisition is needed to be carried out on a gas tank shield area containing a gas tank identification code on the gas tank through a microscope camera device, a standard microscopic image is obtained, the microscopic texture information of the standard microscopic image is extracted to obtain standard microscopic texture characteristics, then the standard microscopic texture characteristics and the standard distance information of the gas tank are taken as gas tank fingerprint information, and the gas tank fingerprint information and the gas tank representation on the gas tank are stored in a database after being bound one by one, so that the gas tank is convenient to use later.

After the target micro-texture feature of the micro-image is obtained, matching degree calculation is carried out on the target micro-texture feature of the micro-image and the standard micro-texture feature bound by the gas tank identification code in the image to be identified of the gas tank to be filled, so that the matching degree of the target micro-texture feature and the standard micro-texture feature is obtained. The matching degree of the two can be calculated by adopting feature matching algorithms such as Euclidean distance, cosine similarity and the like.

Determining whether the matching degree of the target micro-texture features and the standard micro-texture features is smaller than a preset matching degree, and when the matching degree of the target micro-texture features and the standard micro-texture features is larger than or equal to the preset matching degree, indicating that the acquired micro-image is possibly a true identification code image of the gas tank to be filled, performing entity edge identification on the image to be identified so as to further perform qualification detection on the gas tank to be filled.

Before edge recognition, standard micro texture feature recognition and feature comparison are performed, entity edge recognition is performed on the image to be recognized when the comparison is passed, qualification detection is performed on the gas tank to be filled together by combining texture feature recognition and edge distance information, and accuracy of gas tank qualification detection is improved.

When the matching degree of the target micro-texture features and the standard micro-texture features is smaller than the preset matching degree, determining that the gas tank to be filled is an unqualified gas tank, prohibiting gas filling of the gas tank to be filled, and generating an unqualified gas tank alarm to prompt related personnel.

Before edge recognition, standard micro texture feature recognition and feature comparison are performed, when the comparison is failed, the gas tank to be filled is directly determined to be an unqualified gas tank, the gas filling of the gas tank to be filled is forbidden, the unqualified gas tank can be rapidly determined, unnecessary data processing is reduced, and the efficiency of gas tank qualification detection is improved.

In the embodiment, before entity edge identification is performed on an image to be identified, a microscopic image of a gas tank shield area on a gas tank to be filled is acquired, the microscopic image is acquired through a microscopic image pick-up device, the gas tank shield area on the gas tank to be filled contains a gas tank identification code, microscopic texture information of the microscopic image is subjected to feature extraction to obtain target microscopic texture features of the microscopic image, entity edge identification is performed on the image to be identified when the matching degree of the target microscopic texture features and standard microscopic texture features is greater than or equal to a preset matching degree, and when the matching degree of the target microscopic texture features and the standard microscopic texture features is smaller than the preset matching degree, the gas tank to be filled is determined to be a disqualified gas tank, and gas filling of the gas tank to be filled is prohibited. And the qualification detection of the gas tank to be filled is carried out by combining the texture feature recognition and the edge distance information, so that the accuracy of the qualification detection of the gas tank is improved, the data processing amount can be reduced, and the efficiency of the qualification detection of the gas tank is improved.

It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.

In one embodiment, a detection device is provided, and the detection device corresponds to the gas tank qualification detection method in the embodiment. As shown in fig. 9, the detection apparatus includes an acquisition module 901, a determination module 902, an identification module 903, a generation module 904, and a detection module 905. The functional modules are described in detail as follows:

The acquisition module 901 is used for acquiring images of a gas tank shield area containing a gas tank identification code on a gas tank to be filled to obtain images to be identified of the gas tank to be filled;

a determining module 902, configured to determine tank fingerprint information of a gas tank bound by a tank identifier, where the tank fingerprint information includes standard edge distance information generated according to an edge line of a gas tank shroud and an edge line of an identifier on the shroud when the gas tank leaves the factory;

The identifying module 903 is configured to perform entity edge identification on an image to be identified, so as to obtain a first contour edge of the gas tank identifier and a second contour edge of the gas tank shield;

a generation module 904 for generating identification edge distance information from the first contour edge of the tank identification code and the second contour edge of the tank shield;

And the detection module 905 is used for detecting the qualification of the gas tank to be filled according to the identification edge distance information and the standard edge distance information.

Optionally, the identification module 903 is specifically configured to:

Optionally, the contour edge information of each named entity further includes a third contour edge of an identification code tag where the identification code of the gas tank in the image to be identified is located, and the identification module 903 is specifically further configured to:

Optionally, the identification module 903 is specifically further configured to:

Optionally, the generating module 904 is specifically configured to:

Optionally, the generating module 904 is specifically further configured to:

Optionally, the tank fingerprint information further includes standard micro texture features of an identification code area on the gas tank to which the tank identification code is bound, and the detection module 905 is further configured to, before performing entity edge recognition on the image to be recognized:

Acquiring microscopic images of a gas tank shield area on a gas tank to be filled, wherein the microscopic images are acquired by a microscopic camera device from the gas tank shield area containing a gas tank identification code on the gas tank to be filled;

Extracting features of microscopic texture information of the microscopic image to obtain target microscopic texture features of the microscopic image;

It should be noted that, because the content of information interaction and execution process between the above devices/units is based on the same concept as the method embodiment of the present application, specific functions and technical effects thereof may be referred to in the method embodiment section, and will not be described herein.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.

The embodiment of the present application further provides an electronic device, as shown in fig. 10, where the electronic device 2 includes at least one processor 20, a memory 21, and a computer program 22 stored in the memory 21 and executable on the at least one processor 20, and the steps in any of the foregoing method embodiments are implemented by the processor 20 when the processor 20 executes the computer program 22, or the functions of the modules/units in the foregoing apparatus embodiments are implemented by the processor 20 when the processor 20 executes the computer program 22.

By way of example, the computer program 22 may be divided into one or more modules/units, which are stored in the memory 21 and executed by the processor 20 to complete the present application. One or more of the modules/units may be a series of computer program instruction segments capable of performing particular functions for describing the execution of the computer program 22 in the electronic device 2.

It will be appreciated by those skilled in the art that fig. 10 is merely an example of an electronic device and is not meant to be limiting, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., an electronic device may also include an input-output device, a network access device, a bus, etc.

The processor may be a central processing unit, or may be other general purpose processors, digital signal processors, application specific integrated circuits, field programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory may be an internal storage unit of the electronic device, such as a hard disk or a memory of the electronic device. The memory may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card, a secure digital card, a flash memory card, etc. provided on the electronic device. Further, the memory may also include both internal storage units and external storage devices of the electronic device.

The embodiment of the application also provides a readable storage medium, wherein the readable storage medium stores a computer program, and when the computer program is executed by a processor, the gas tank qualification detection method is executed.

Embodiments of the present application provide a computer program product that, when run on an electronic device, causes the above-described gas tank eligibility detection method to be performed.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application may implement all or part of the flow of the method of the above-described embodiments, and may be implemented by a computer program to instruct related hardware, and the computer program may be stored in a computer readable storage medium, where the computer program may implement the steps of the method embodiments described above when executed by a processor. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable medium can include at least any entity or device capable of carrying computer program code to a camera device/terminal equipment, a recording medium, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium. Such as a U-disk, removable hard disk, magnetic or optical disk, etc. In some jurisdictions, computer readable media may not be electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus/device and method may be implemented in other manners. For example, the apparatus/device embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

The foregoing embodiments are merely illustrative of the technical solutions of the present application, and not restrictive, and although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that modifications may still be made to the technical solutions described in the foregoing embodiments or equivalent substitutions of some technical features thereof, and that such modifications or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. The method for detecting the qualification of the gas tank is characterized by comprising the following steps of:

Image acquisition is carried out on a gas tank shield area containing a gas tank identification code on a gas tank to be filled, so as to obtain an image to be identified of the gas tank to be filled;

determining gas tank fingerprint information of the gas tank bound by the gas tank identification code, wherein the gas tank fingerprint information comprises standard edge distance information generated according to an edge line of a shield of the gas tank and an edge line of the identification code on the shield when the gas tank leaves a factory;

2. The gas tank qualification detection method of claim 1, wherein the performing entity edge recognition on the image to be recognized to obtain a first contour edge of the tank identification code and a second contour edge of the tank shield comprises:

performing contour recognition based on each entity edge on the target recognition image by adopting a contour detection algorithm, and recognizing to obtain entity contour information in the image to be recognized;

3. The gas tank qualification detection method of claim 2, wherein the contour edge information of each named entity further includes a third contour edge of an identification code tag in which the gas tank identification code is located in the image to be identified, and the determining contour edge information of each named entity in the image to be identified according to the entity contour information in the image to be identified includes:

Carrying out named entity identification classification according to entity profile information in the image to be identified, and determining profile information of the gas tank identification code, profile information of the gas tank shield and profile information of the identification code label in the image to be identified;

determining a first contour edge of the gas tank identification code according to contour information of the gas tank identification code, wherein the first contour edge is a plurality of contour edges of the gas tank identification code and a contour edge with the shortest distance from the gas tank shield;

determining a second contour edge of the gas tank shield according to contour information of the gas tank shield, wherein the second contour edge is a contour edge with the shortest distance from the first contour edge in a plurality of contour edges of the gas tank shield;

4. The gas tank qualification detection method of claim 2, wherein the performing solid edge detection on the image to be identified using an edge detection algorithm to obtain a target identification image including each solid edge comprises:

Performing image gray level conversion on the image to be identified, and performing Gaussian noise filtering on the image to be identified after gray level conversion to obtain the preprocessed image to be identified;

5. The gas tank suitability detection method of any of claims 1-4, wherein the generating identifying edge distance information from the first contour edge of the tank identification code and the second contour edge of the tank shroud includes:

acquiring a third contour edge of an identification code tag where the gas tank identification code is located in the image to be identified, wherein the third contour edge of the identification code tag is obtained by carrying out entity edge identification on the image to be identified;

And generating the identification edge distance information according to the third contour edge, the first contour edge and the second contour edge.

6. The gas canister eligibility detection method of claim 5 wherein the generating of the tank identification code to the tank shroud identification edge distance information from the third contour edge, the first contour edge, and the second contour edge includes:

and generating the identification edge distance information according to the first edge distance and the second edge distance.

7. The gas tank qualification detection system is characterized by comprising a detection device, wherein the detection device is used for:

8. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, causes the electronic device to implement the gas tank qualification detection method according to any one of claims 1 to 6.

9. A readable storage medium storing a computer program, which when executed by a processor causes the gas canister eligibility detection method according to any one of claims 1 to 6 to be performed.

10. A computer program product comprising a computer program which, when run, causes the gas canister eligibility detection method of any one of claims 1-6 to be performed.