A fault identification method and device for a guardrail, a medium and an electronic device

Abstract

Embodiments of the present application disclose a guardrail fault identification method and device, a medium and an electronic device. The method comprises: acquiring image information comprising a guardrail; identifying each unit guardrail of the guardrail in the image information; identifying at least one key point of each unit guardrail, and if the key point meets a preset fault screening condition, determining that the guardrail has a fault in the current image information; wherein the key point comprises at least one of a bottom center point, an overall center point and a top center point of the unit guardrail. By implementing the present scheme, the fault condition of the guardrail of a road can be quickly and accurately identified.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of image processing, and particularly relate to a guardrail fault identification method and device, a medium and an electronic device. BACKGROUND

[0002] With the rapid development of science and technology, the order of urban road traffic has become an important factor affecting the quality of life of the general public. In order to ensure the normal operation of the road, guardrails are often erected between the oncoming lanes or between the motor vehicle road and the non-motor vehicle road. The erection of guardrails not only ensures the traffic order, but also avoids traffic hazards, and plays a significant role in orderly road traffic. If the guardrails have problems such as damage, loss, and bending, it will greatly affect the safety and orderliness of road traffic. Generally, special urban management and road management personnel are equipped to patrol and handle whether the guardrails have problems, which not only causes a large amount of human consumption, but also has problems such as untimely inspection. Therefore, how to quickly and effectively investigate the fault of the guardrail is a technical problem to be solved by those skilled in the art. SUMMARY

[0003] Embodiments of the present application provide a guardrail fault identification method, device, medium and electronic device, which can quickly and accurately identify the fault condition of the guardrail of the road.

[0004] In a first aspect, embodiments of the present application provide a guardrail fault identification method, which comprises:

[0005] Obtaining image information including a guardrail;

[0006] Identifying each unit guardrail of the guardrail in the image information;

[0007] Identifying at least one key point of each unit guardrail, and if the key point meets a preset fault screening condition, determining that the guardrail in the current image information has a fault; wherein the key point includes at least one of a bottom center point, an overall center point, and a top center point of the unit guardrail.

[0008] Further, if the key point meets the preset fault screening condition, it is determined that the guardrail in the current image information has a fault, which comprises:

[0009] Determining the key point coordinates of each unit guardrail;

[0010] If the key point coordinates cannot be applied to the Lagrange interpolation formula, it is determined that the guardrail in the current image information has a fault.

[0011] Further, after determining the key point coordinates of each unit guardrail, the method further comprises:

[0012] If the key point coordinates can be applied to Lagrange interpolation formula, a Lagrange interpolation polynomial is obtained.

[0013] If the Lagrange interpolation polynomial is not derivable at the coordinate position of at least one key point, it is determined that the guardrail has a fault according to the current image information.

[0014] Further, after determining the key point coordinates of each unit guardrail, the method further comprises:

[0015] According to the key point coordinates of each unit guardrail, an average change difference value of coordinate distance is determined.

[0016] If the difference between the distance of the key points of the adjacent two unit guardrails and the average change difference value exceeds a preset maximum distance tolerance, it is determined that the guardrail has a fault according to the current image information.

[0017] Further, the calculation formula of the average change difference value of the coordinate distance is as follows:

[0018]

[0019] Wherein, is the average change difference value, Db i is the key point position of the i-th unit guardrail, Db i-1 is the key point position of the i-1-th unit guardrail, and n is the number of unit guardrails.

[0020] Further, after the key point coordinates can be applied to the Lagrange interpolation formula to obtain the Lagrange interpolation polynomial, the method further comprises:

[0021] If the Lagrange interpolation polynomial is derivable, an average value of the derivative difference value of any unit guardrail and the previous unit guardrail is determined.

[0022] If the difference between the derivative of the key points of the adjacent two unit guardrails and the average value of the derivative difference value exceeds a preset maximum derivative difference tolerance, it is determined that the guardrail has a fault according to the current image information.

[0023] Further, the calculation formula of the average value of the derivative difference value is as follows:

[0024]

[0025] Wherein, is the average value of the derivative difference value, L b ′(Xt i ) is the derivative of the key point of the i-th unit guardrail, L b ′(Xt i-1) is the derivative of the key point of the i-1th unit guardrail, and n is the number of unit guardrails.

[0026] Further, after determining that the guardrail has a fault according to the current image information, the method further comprises:

[0027] If it is identified that the guardrail has a fault in a continuous preset number of image information, guardrail fault maintenance information is generated and sent to the client.

[0028] In a second aspect, an embodiment of the present application provides a guardrail fault identification device, and the device comprises:

[0029] An image information acquisition module is configured to acquire image information including a guardrail.

[0030] A unit guardrail identification module is configured to identify each unit guardrail of the guardrail in the image information.

[0031] A fault judgment module is configured to identify at least one key point of each unit guardrail, and if the key point meets a preset fault screening condition, it is determined that the guardrail has a fault according to the current image information; wherein the key point comprises at least one of a bottom center point, an overall center point and a top center point of the unit guardrail.

[0032] In a third aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the guardrail fault identification method according to an embodiment of the present application.

[0033] In a fourth aspect, an embodiment of the present application provides an electronic device, which comprises a memory, a processor and a computer program stored in the memory and executable by the processor, and the processor implements the guardrail fault identification method according to an embodiment of the present application when executing the computer program.

[0034] The technical scheme provided by the embodiment of the present application acquires image information including a guardrail, identifies each unit guardrail of the guardrail in the image information, identifies at least one key point of each unit guardrail, and if the key point meets a preset fault screening condition, it is determined that the guardrail has a fault according to the current image information; wherein the key point comprises at least one of a bottom center point, an overall center point and a top center point of the unit guardrail. The technical scheme provided by the present application can quickly and accurately identify the fault condition of the guardrail of a road. BRIEF DESCRIPTION OF DRAWINGS

[0035] Figure 1 FIG. 1 is a flowchart of a guardrail fault identification method according to an embodiment of the present application;

[0036] Figure 2 FIG. 2 is a schematic diagram of a key point identification result of a guardrail according to an embodiment of the present application.

[0037] Figure 3 is a schematic diagram of a geometric model of a key point of a guardrail provided by an embodiment of the present application;

[0038] Figure 4 is a schematic diagram of a missing fault of a guardrail provided by an embodiment of the present application;

[0039] Figure 5 is a schematic diagram of a geometric model of a missing guardrail provided by an embodiment of the present application;

[0040] Figure 6 is a schematic diagram of a displacement fault of a guardrail provided by an embodiment of the present application;

[0041] Figure 7 is a schematic diagram of a geometric model of a displaced guardrail provided by an embodiment of the present application;

[0042] Figure 8 is a schematic diagram of fault identification of a displaced guardrail provided by an embodiment of the present application;

[0043] Figure 9 is a schematic diagram of a structure of a fault identification device of a guardrail provided by an embodiment of the present application;

[0044] Figure 10 is a schematic diagram of a structure of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0045] The present application will be further described by examples in conjunction with the accompanying drawings. It is to be understood that the following examples are only used to explain the present application and not to limit the present application. In addition, it should be noted that only the parts related to the present application are shown in the drawings for the convenience of description.

[0046] Before some example embodiments are discussed in more detail, it should be noted that some example embodiments are described as processes or methods depicted as flow diagrams. Although the processes are described in a particular order, many of the steps can be performed concurrently, in parallel, or simultaneously. In addition, the order of the steps can be re-arranged. The processes can terminate when their operations are completed, but the processes can also have additional steps not included in the figure(s). The processes can correspond to methods, functions, procedures, subroutines, subprograms, etc.

[0047] Figure 1 is a flowchart of a fault identification method of a guardrail provided by an embodiment of the present application. The embodiment can be applicable to the case of identifying a fault of a guardrail. The method can be executed by a fault identification device of a guardrail provided by an embodiment of the present application. The device can be realized by software and / or hardware, and can be integrated in an electronic device such as a server.

[0048] As Figure 1 shown, the guardrail failure recognition method comprises:

[0049] S110, acquiring image information comprising a guardrail.

[0050] The image information can also be obtained by other image acquisition devices. Using a road traffic camera for acquisition can realize functional reuse and does not require separate deployment of a hardware device.

[0051] The road traffic camera can acquire a video of the road, and each frame of image can be obtained by frame processing the video. A plurality of adjacent frame images can be used as input data of the present scheme, and frame skipping input can also be used. In addition, input can also be performed by specifying a time. For example, there are more vehicles on the road during the day, and the guardrail in the acquired image can be blocked. Therefore, the guardrail can be acquired by setting 23:00 to 4:00 at night, so that the misjudgment problem caused by the blocking can be effectively avoided.

[0052] S120, recognizing each unit guardrail in the image information.

[0053] It can be understood that a unit guardrail is a unit structure of a guardrail, for example, the part between two support columns can be used as a unit guardrail. The shape of the unit guardrail can be rectangular, square, elliptical, etc.

[0054] In the present scheme, a model capable of recognizing a guardrail and a guardrail shape can be trained by machine learning, and the model is denoted as an HL model (guardrail model). The input of the model is a collected monitoring area image, and the output result of the model is a detection result of whether the guardrail is damaged, missing, etc. The HL model is built, the road cameras within a certain range of a city are connected to the HL model, the monitoring videos of the cameras are analyzed, and the analysis results are discriminated.

[0055] The HL model comprises a plurality of modules, including:

[0056] A guardrail recognition and extraction module is used to extract features of a monitoring area image, recognize one or more guardrails possibly existing in the image, and mark each unit guardrail in each recognized guardrail (the unit guardrail refers to a guardrail unit composed of two fixed columns and the middle part).

[0057] A guardrail key point processing module is used to process the feature map output by the unit guardrail recognition and extraction module, so as to obtain unit guardrail key point coordinates, including a guardrail bottom center point coordinate denoted as b coordinate, a guardrail overall center point coordinate denoted as c coordinate, and a guardrail top center point coordinate denoted as t coordinate.

[0058] Guardrail state calculation module: used for judging the position and state between each unit guardrail key point coordinate on the same road guardrail, judging whether the guardrail exists damage or missing phenomenon.

[0059] It can be understood that the identification mode of the unit guardrail adopted in the scheme can adopt the identification mode of the above model, and other modes such as feature point identification can also be adopted, and the unit guardrail is determined according to the identification result of the feature point.

[0060] S130, at least one key point of each unit guardrail is identified, if the key point meets the preset fault screening condition, it is determined that the guardrail in the current image information exists fault; wherein the key point includes at least one of the bottom center point, the overall center point and the top center point of the unit guardrail.

[0061] Among them, the key point can be the center position point of each unit guardrail, and there can be multiple key points in a unit guardrail, such as the points connected with the support column can be used as key points.

[0062] In the scheme, the key point can include at least one of the bottom center point, the overall center point and the top center point of the unit guardrail, that is, the bottom center point of each unit guardrail can be identified, or only the overall center point of each unit guardrail is identified, or only the top center point of each unit guardrail is identified. Figure 2 The key point identification result diagram of the guardrail provided by the embodiment of the application is shown in Figure 2 As shown, the bottom center point of each unit guardrail, the overall center point of each unit guardrail and the top center point of each unit guardrail (using dark gray points) can be identified and marked respectively. Among them, Figure 2 The part not clear in the above formula is irrelevant to the content of the scheme and can not be considered.

[0063] Among them, the preset fault screening condition can be a screening condition determined after identifying a certain type of key point, for example, taking the bottom center point of each unit guardrail as an example, if all points are on a straight line, it means that there is no bending fault, if the distance between all points is relatively fixed, for example, all 2m, it means that there is no missing fault. In the scheme, since the picture obtained by the camera is not obtained vertically, according to the principle of perspective, there will be a certain gradient change in the distance, so if the distance does not meet the change rule, it can be determined as missing.

[0064] In addition, for the bending fault, a straight line can also be fitted, and the distance of each key point to the straight line is determined, and compared with a set threshold, so as to determine whether there is one or more key points which are far away from the straight line, for example, the vertical distance of other key points to the straight line is 0-10 units, and the distance of the pixel point to the straight line is 28 units (the unit of length can be the distance of the pixel point, or the distance corresponding to the actual site, for example, each unit represents 10 pixel points, or the length of centimeter in the actual site), which indicates that there is a bending at the position of the key point.

[0065] In the scheme, optionally, if the key point meets the preset fault screening condition, it is determined that the guardrail has a fault according to the current image information, comprising:

[0066] Determine the key point coordinates of each unit guardrail;

[0067] If the key point coordinates cannot be applied to the Lagrange interpolation formula, it is determined that the guardrail has a fault according to the current image information.

[0068] The key point coordinates can be the pixel point coordinates of the key point in the image. In numerical analysis, Lagrange interpolation is a polynomial interpolation method named after the French mathematician Joseph-Louis Lagrange in the 18th century. Many practical problems use functions to represent some internal relationship or law, and many functions can only be understood through experiments and observations. For example, a physical quantity in practice is observed, and corresponding observation values are obtained at different places. The Lagrange interpolation method can find a polynomial that takes the observed values at each observation point. Such a polynomial is called a Lagrange (interpolation) polynomial. Mathematically, the Lagrange interpolation method can give a polynomial function that passes through a number of known points on a two-dimensional plane.

[0069] The scheme determines whether the guardrail has a problem by whether it can meet the Lagrange interpolation formula. If it cannot meet the Lagrange interpolation formula, it indicates that the key points of the guardrail cannot be represented by a polynomial, which indicates that there may be a bending or the like. Therefore, the problem of the guardrail can be quickly determined by such a judgment.

[0070] On the basis of the above technical scheme, optionally, after determining the key point coordinates of each unit guardrail, the method further comprises:

[0071] If the key point coordinates can be applied to the Lagrange interpolation formula, a Lagrange interpolation polynomial is obtained;

[0072] If the Lagrange interpolation polynomial is not derivable at the coordinate position of at least one key point, it is determined that the guardrail has a fault according to the current image information.

[0073] Figure 3 This is a schematic diagram of the geometric model of the key points of the guardrail provided in the embodiment of the present application, such as Figure 3 As shown in the figure, in this road guardrail, all key point coordinates are sorted from small to large according to the horizontal coordinate (X coordinate), and the number of arrangement bits is n (n>=1), so the key point coordinate of any guardrail is the coordinate of the bottom center point (Xb n ,Yb n ), the overall center point coordinates (Xc n ,Yc n ), top center coordinates (Xt n ,Yt n ),.

[0074] Then the distance between the bottom center coordinates of any guardrail and the previous guardrail is:

[0075] If the Lagrange interpolation formula cannot be applied to the coordinates of all the bottom center points on the guardrail, it means that there is an abnormality in the guardrail. If the Lagrange interpolation formula can be applied, the resulting Lagrange interpolation polynomial is: To L b (x) and take the derivative, we can get L b ′(x), if in Xb n The derivative exists at L b ′(Xb n ), if it is not differentiable, then L b (x) is not smooth here, which means L b (x) There is a sharp protrusion at this location. The slopes of the tangents on either side of the protrusion are different, so the left and right derivatives of the point are different, making it undifferentiable. This indicates that the guardrail has abnormal bending or displacement at this location, which can be determined to be a possible anomaly in the guardrail.

[0076] Similarly, the distance between any guardrail and the overall center point coordinates of the guardrail above it is:

[0077] If the Lagrange interpolation formula cannot be applied to the coordinates of all the center points on the guardrail, it means that there is an abnormality in the guardrail. If the Lagrange interpolation formula can be applied, the resulting Lagrange interpolation polynomial is: To L c (x) and take the derivative, we can get L c ′(x), if in Xc n The derivative exists at L c ′(Xc n ), if it is not differentiable, then L c(x) is not smooth here, which means L c (x) There is a sharp protrusion at this location. The slopes of the tangents on either side of the protrusion are different, so the left and right derivatives of the point are different, making it undifferentiable. This indicates that the guardrail has abnormal bending or displacement at this location, which can be determined to be a possible anomaly in the guardrail.

[0078] Similarly, the distance between the top center coordinates of any guardrail and the previous guardrail is:

[0079] If the Lagrange interpolation formula cannot be applied to the coordinates of all the top center points on the guardrail, it means that there is an abnormality in the guardrail. If the Lagrange interpolation formula can be applied, the resulting Lagrange interpolation polynomial is: To L t (x) and take the derivative, we can get L t ′(x), if in Xt n The derivative exists at L t ′(Xt n ), if it is not differentiable, then L t (x) is not smooth here, which means L t (x) There is a sharp protrusion at this point. The slopes of the tangents on both sides of the sharp protrusion are different, so the left and right derivatives of the point are different, and it is not differentiable. This indicates that the guardrail has abnormal bending or displacement at this point, and thus it can be determined that there may be an abnormality in the guardrail at this point.

[0080] In a normal state, the same guardrail should be continuous, and the actual distance between two unit guardrails is approximately equal. However, due to the high height and tilted angle of the surveillance camera, the guardrails actually photographed are roughly on a straight line, so the pixel distance between the key point coordinates of any two adjacent unit guardrails in the picture can be approximately the same.

[0081] The technical solution provided by the embodiments of the present application acquires image information including guardrails; identifies each guardrail unit in the image information; and identifies at least one key point of each guardrail unit. If the key point meets a preset fault screening condition, the guardrail in the current image information is determined to be faulty. The key point includes at least one of the bottom center point, the overall center point, and the top center point of the guardrail unit. The technical solution provided by the present application can quickly and accurately identify fault conditions in road guardrails.

[0082] Based on the above technical solutions, optionally, after determining the coordinates of the key points of each unit guardrail, the method further includes:

[0083] According to the key point coordinates of each unit guardrail, an average change difference of coordinate distance is determined;

[0084] If the distance between the key points of two adjacent unit guardrails and the difference amplitude of the average change difference exceeds a preset maximum distance tolerance, it is determined that the guardrail in the current image information has a fault.

[0085] In the above technical solution, optionally, the calculation formula of the average change difference of coordinate distance is as follows:

[0086]

[0087] Among them, is the average change difference, Db i is the key point position of the i-th unit guardrail, Db i-1 is the key point position of the i-1-th unit guardrail, and n is the number of unit guardrails.

[0088] Among them, the average change difference of the coordinate distance of the bottom center point of the unit guardrail is:

[0089] The average change difference of the coordinate distance of the overall center point of the unit guardrail is:

[0090] The average change difference of the coordinate distance of the top center point of the unit guardrail is:

[0091] If,

[0092] Or,

[0093] Or,

[0094] Then it is determined that the guardrail does not have the problem of missing or damage, otherwise it is determined that the guardrail may have the problem of missing or damage. Wherein: Hb is the maximum distance tolerance of the coordinate difference of the bottom center point of the guardrail, Hc is the maximum distance tolerance of the coordinate difference of the overall center point of the guardrail, and Ht is the maximum distance tolerance of the coordinate difference of the top center point of the guardrail.

[0095] On the contrary, if the distance between the key points of any two adjacent unit guardrails and the difference amplitude of the average change difference exceeds the preset maximum distance tolerance, it is determined that the guardrail in the current image information has a fault.

[0096] Here, the average change difference and the distance of two adjacent key points are subtracted, and if the obtained difference exceeds the maximum distance tolerance, it is determined that the guardrail is missing or severely misaligned.

[0097] On the basis of each of the above technical solutions, optionally, if the key point coordinates can be applied to the Lagrange interpolation formula to obtain a Lagrange interpolation polynomial, the method further comprises:

[0098] If the Lagrange interpolation polynomial is derivable, the average value of the derivative difference between any unit guardrail and the previous unit guardrail is determined.

[0099] If the derivative difference between the key points of the adjacent two unit guardrails and the average value of the derivative difference exceeds the preset maximum derivative difference tolerance, it is determined that the guardrail in the current image information has a fault.

[0100] In the above technical solution, optionally, the calculation formula of the average value of the derivative difference is as follows:

[0101]

[0102] Wherein, is the average value of the derivative difference, L b ′(Xt i ) is the derivative of the key point of the i-th unit guardrail, L b ′(Xt i-1 ) is the derivative of the key point of the i-1-th unit guardrail, and n is the number of unit guardrails.

[0103] The function L b (x) is the average value of the derivative difference between the bottom center point coordinates of any guardrail and the previous guardrail:

[0104]

[0105] The average value of the derivative difference between the bottom center point coordinates of any guardrail and the left and right two guardrails is:

[0106]

[0107] The average value of the derivative difference between the bottom center point coordinates of any guardrail and the left and right two guardrails is:

[0108]

[0109] If,

[0110] Or,

[0111] Or,

[0112] If the guardrail is not displaced or bent, it is determined that the guardrail may be displaced or bent. Where: Mb is the maximum tolerance for the difference between the derivatives of the center point coordinates at the bottom of the guardrail, Mc is the maximum tolerance for the difference between the derivatives of the center point coordinates of the entire guardrail, and Mt is the maximum tolerance for the difference between the derivatives of the center point coordinates at the top of the guardrail.

[0113] Through the above method, it can be determined whether the guardrail is bent or not.

[0114] Figure 4 This is a schematic diagram of a guardrail missing fault provided by an embodiment of the present application, such as Figure 4 As shown, there is a situation where the guardrail of one unit is missing. Figure 5 This is a schematic diagram of a geometric model of a missing guardrail provided in an embodiment of the present application. Figure 5 As shown, when there is a deletion, it can be determined by n-1 , Dc n , Dc n+1 to identify missing conditions. Figure 6 Schematic diagram of the displacement failure of the guardrail provided in the embodiment of the present application, such as Figure 6 As shown, there is a situation where two unit guardrails are displaced. Figure 7 is a schematic diagram of a geometric model of guardrail displacement provided in an embodiment of the present application, such as Figure 7 As shown in the figure, although the conditions of the Lagrange interpolation algorithm are met, there are two key points that have large position deviations from the original guardrail key points. Figure 8 This is a schematic diagram of fault identification of guardrail displacement provided by an embodiment of the present application, such as Figure 8 As shown, Dc n , Dc n+1 To identify the problem, and can be achieved through L c ′(Xc n ), L c ′(Xc n+1 ) and L c ′(Xc n+2 ) analysis revealed significant discrepancies, thus confirming the presence of a fault.

[0115] Based on the above technical solutions, optionally, after determining that the guardrail in the current image information has a fault, the method further includes:

[0116] If a guardrail fault is identified in a preset number of consecutive image information, guardrail fault maintenance information is generated and sent to the client.

[0117] It can be understood that by recognizing a certain amount of image information, interference caused by vehicle occlusion, light influence, etc. can be avoided, thereby improving the accuracy of the algorithm of this solution.

[0118] Because guardrails can be blocked by passing vehicles or interfered with by light, a single calculation anomaly can trigger a false alarm. Therefore, if a potential guardrail problem is identified, the camera in the image is marked. If the same camera is marked P times in a row, the guardrail in the camera's image is ultimately determined to be missing, damaged, displaced, or bent. The value of P can be configured based on actual needs.

[0119] If there is any abnormality, missing or damaged, displaced or bent problem with the guardrail, a message will be sent to the client to notify the relevant road guardrail maintenance unit to carry out repairs as soon as possible to eliminate the risk as soon as possible.

[0120] The present invention can use machine learning to perform video analysis on surveillance videos from urban road cameras to monitor the displacement and missing of urban road guardrails, and then push this information to relevant road guardrail maintenance units in a timely and rapid manner, urging them to repair them as soon as possible and reduce the risk of traffic accidents as soon as possible.

[0121] Figure 9 Schematic diagram of the structure of the fault identification device of the guardrail provided in the embodiment of the present application. Figure 9 As shown, the device includes:

[0122] An image information acquisition module 910 is used to acquire image information including guardrails;

[0123] a unit guardrail identification module 920 for identifying each unit guardrail of the guardrail in the image information;

[0124] The fault judgment module 930 is used to identify at least one key point of each unit guardrail. If the key point meets the preset fault screening conditions, it is determined that there is a fault in the guardrail described in the current image information; wherein, the key point includes at least one of the bottom center point, the overall center point and the top center point of the unit guardrail.

[0125] The above-mentioned product can execute the method provided in the embodiment of this application, and has the corresponding functional modules and beneficial effects of the execution method.

[0126] An embodiment of the present application further provides a storage medium containing computer-executable instructions. When the computer-executable instructions are executed by a computer processor, the computer-executable instructions are used to perform a guardrail fault identification method, the method comprising:

[0127] Acquire image information including guardrails;

[0128] Identifying each unit guardrail of the guardrail in the image information;

[0129] Identify at least one key point of each unit guardrail. If the key point meets the preset fault screening conditions, determine that the guardrail described in the current image information has a fault; wherein the key point includes at least one of the bottom center point, the overall center point, and the top center point of the unit guardrail.

[0130] Storage medium - any of various types of memory electronic devices or storage electronic devices. The term "storage medium" is intended to include: installation media, such as CD-ROMs, floppy disks, or tape devices; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (such as hard disks or optical storage); registers or other similar types of memory elements, etc. Storage media may also include other types of memory or combinations thereof. In addition, the storage medium may be located in the computer system in which the program is executed, or it may be located in a different second computer system that is connected to the computer system via a network (such as the Internet). The second computer system may provide program instructions to the computer for execution. The term "storage medium" may include two or more storage media that may reside in different locations (e.g., in different computer systems connected via a network). The storage medium may store program instructions (e.g., embodied as a computer program) that can be executed by one or more processors.

[0131] Of course, the storage medium containing computer-executable instructions provided in an embodiment of the present application, whose computer-executable instructions are not limited to the guardrail fault identification operation described above, can also execute related operations in the guardrail fault identification method provided in any embodiment of the present application.

[0132] An embodiment of the present application provides an electronic device, into which the guardrail fault identification device provided by the embodiment of the present application can be integrated. Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 10 As shown, this embodiment provides an electronic device 1000, which includes: one or more processors 1020; a storage device 1010 for storing one or more programs. When the one or more programs are executed by the one or more processors 1020, the one or more processors 1020 implement the guardrail fault identification method provided in the embodiment of the present application. The method includes:

[0133] Acquire image information including guardrails;

[0134] Identifying each unit guardrail of the guardrail in the image information;

[0135] Identify at least one key point of each unit guardrail, and if the key point meets a preset fault screening condition, determine that the guardrail has a fault according to the current image information; wherein the key point includes at least one of a bottom center point, an overall center point and a top center point of the unit guardrail.

[0136] Of course, those skilled in the art can understand that the processor 1020 also implements the technical solutions of the guardrail fault identification method provided by any embodiment of the present application.

[0137] Figure 10 The electronic device 1000 shown is only an example and should not limit the functions and use range of the embodiments of the present application.

[0138] As shown in Figure 10 , the electronic device 1000 includes a processor 1020, a storage device 1010, an input device 10100 and an output device 1040; the number of processors 1020 in the electronic device can be one or more, Figure 10 , taking one processor 1020 as an example; the processor 1020, the storage device 1010, the input device 10100 and the output device 1040 in the electronic device can be connected through a bus or other means, Figure 10 , taking the connection through the bus 1050 as an example.

[0139] The storage device 1010 as a kind of computer readable storage medium can be used to store software programs, computer executable programs and module units, such as the program instructions corresponding to the guardrail fault identification method in the embodiments of the present application.

[0140] The storage device 1010 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required by a function; the data storage area can store data created according to the use of the terminal and the like. In addition, the storage device 1010 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some examples, the storage device 1010 can further include a memory disposed remotely with respect to the processor 1020, and these remote memories can be connected through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0141] The input device 10100 can be used to receive input digital, character information or voice information, and generate key signal input related to user settings and function control of the electronic device. The output device 1040 can include a display screen, a speaker and other electronic devices.

[0142] The electronic device provided in the embodiments of the present application can perform video intelligent analysis on the monitoring video of the urban road traffic camera through machine learning, identify the road guardrails in the monitoring video, and then detect whether the urban road guardrails have displacement or loss. If the road guardrails have such problems, the information is pushed to the relevant road guardrail maintenance unit.

[0143] The guardrail fault identification device, medium and electronic device provided in the above embodiments can execute the guardrail fault identification method provided in any of the embodiments of the present application, and have the corresponding function modules and beneficial effects of executing the method. Technical details not described in detail in the above embodiments can be referred to the guardrail fault identification method provided in any of the embodiments of the present application.

[0144] Note that the above are only preferred embodiments of the present application and the technical principles applied. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and those skilled in the art can make various obvious changes, readjustments and substitutions without departing from the scope of the present application. Therefore, although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments, and can include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A method of failure recognition of a guardrail, characterized in that, The method comprises: acquiring image information including a guardrail; identifying each unit guardrail of the guardrail in the image information; identifying at least one key point of each unit guardrail, and determining that the guardrail in the current image information has a fault if the key point meets a preset fault screening condition; wherein the key point comprises at least one of a bottom center point, an overall center point and a top center point of the unit guardrail; the determining that the guardrail in the current image information has a fault if the key point meets the preset fault screening condition comprises: determining key point coordinates of each unit guardrail; determining that the guardrail in the current image information has a fault if the key point coordinates cannot apply a Lagrange interpolation formula.

2. The method of claim 1, wherein, After determining the key point coordinates of each unit guardrail, the method further comprises: determining an average change difference of coordinate distances according to the key point coordinates of each unit guardrail; determining that the guardrail in the current image information has a fault if a difference amplitude between the key points of adjacent two unit guardrails and the average change difference exceeds a preset maximum distance tolerance.

3. The method of claim 2, wherein, The calculation formula of the average change difference of coordinate distances is as follows: wherein, Db is the average change difference value, and i Db is the key point position of the i-th unit guardrail, and i-1 Db is the key point position of the i-1-th unit guardrail, and n is the number of unit guardrails.

4. The method of claim 1, wherein, After determining the key point coordinates of each unit guardrail, the method further comprises: if the key point coordinates can apply a Lagrange interpolation formula, obtaining a Lagrange interpolation polynomial; determining that the guardrail in the current image information has a fault if the Lagrange interpolation polynomial is not derivable at the coordinate position of at least one key point.

5. The method of claim 4, wherein, After the key point coordinates can apply the Lagrange interpolation formula to obtain the Lagrange interpolation polynomial, the method further comprises: if the Lagrange interpolation polynomial is derivable, determining an average value of a derivative difference value between any unit guardrail and a previous unit guardrail of the unit guardrail; determining that the guardrail in the current image information has a fault if a difference amplitude between the key points of adjacent two unit guardrails and the average value of the derivative difference value exceeds a preset maximum derivative difference tolerance.

6. The method of claim 5, wherein, The calculation formula of the average value of the derivative difference value is as follows: wherein, is the average of the derivative difference, L b ′(Xt i is the derivative at the key point of the i-th unit guardrail, L b ′(Xt i-1 is the derivative at the key point of the i-1-th unit guardrail, n is the number of unit guardrails.

7. The method according to any one of claims 1 to 6, characterized in that, After determining that the guardrail in the current image information has a fault, the method further comprises: if it is identified that the guardrail has a fault in a continuous preset number of image information, generating guardrail fault maintenance information and sending the guardrail fault maintenance information to a client.

8. A guardrail fault identification device, characterized in that: The method comprises: an image information acquisition module, configured to acquire image information including a guardrail; a unit guardrail identification module, configured to identify each unit guardrail of the guardrail in the image information; a fault judgment module, configured to identify at least one key point of each unit guardrail, and determine that the guardrail in the current image information has a fault if the key point meets a preset fault screening condition; wherein the key point comprises at least one of a bottom center point, an overall center point and a top center point of the unit guardrail; the fault judgment module is specifically configured to determine key point coordinates of each unit guardrail, and determine that the guardrail in the current image information has a fault if the key point coordinates cannot apply a Lagrange interpolation formula.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The program is executed by a processor to implement the guardrail fault identification method in any one of claims 1-7.

10. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the guardrail fault identification method in any one of claims 1-7.

Images