CN110533627A - Method for detecting nettle fracture - Google Patents

Abstract

The invention discloses a method for detecting the breakage of a net rope. The method comprises: extracting a target object included in an input image based on a recognition algorithm; according to the extracted target object, distinguishing it into a line segment and an end of the line segment. connection point; forming a topology network according to the connection relationship between all the connection points; determining all feasible paths in the topology network according to the topology network; determining whether there is a feasible but actually nonexistent path according to the feasible path. The method and device for detecting the broken wire rope of a railway freight car provided by this application adopts the LSD algorithm to input the wire rope skeleton in the image in advance, and determines whether there is an actual non-existent but feasible path according to the topology network structure, so as to determine whether there is a broken wire rope. The rope has a small amount of calculation, and can quickly and accurately identify the position where the net rope is broken in the image, improving the efficiency and accuracy of detecting the target object.

Description

Method for detecting breakage of net rope

technical field

The invention relates to the technical fields of rail transit, image processing and pattern recognition, in particular to a method for detecting the breakage of a railway freight car net rope.

Background technique

Rail traffic safety regulations require that the truck tarpaulin need to be reinforced with net ropes. If the net rope breaks, there is a risk of the tarpaulin floating. Therefore, it is necessary to detect whether the net rope is broken. If the net rope breaks, it is necessary to remind and alarm. The net ropes on the railway freight car are all knotted at the fixed point at the lower part of the car body and cover the whole car body. At present, the detection method for the breakage of the net rope is generally judged manually by the naked eye. The length of the freight train is long, and manual inspection is very time-consuming. In addition, a large number of repeated quadrilateral lattices are formed when the net rope is unfolded, which is difficult to identify with the naked eye, and it is difficult to find the broken part in time.

SUMMARY OF THE INVENTION

The purpose of the present application is to provide a method for detecting the breakage of a net rope, so as to solve the technical problems mentioned in the above background art section.

In a first aspect, the present application provides a method for detecting a net rope breakage, the method comprising: extracting a target object included in an input image based on a recognition algorithm; distinguishing the extracted target object into line segments and The connection point at the end of the line segment; a topology network is formed according to the connection relationship between all the connection points; according to the topology network, all feasible paths in the topology network are determined; according to the feasible path, it is determined whether there is a feasible but not actually existing path , if there is, the net rope is broken, otherwise the net rope is intact.

In some embodiments, the recognition algorithm adopts the LSD algorithm, and further includes binarizing the image after extracting the target object included in the input image, and the rope part is the foreground and the rest part is the background.

In some embodiments, the method further includes performing line segment repair on the missing part of the line segment after the above binarization.

In some embodiments, the method for repairing a line segment includes: selecting endpoints on all isolated line segments, extending a set length along the line segment with the endpoints, and judging whether the Euclidean distance between the extended line segment and endpoints on other line segments is greater than If the threshold is set, the relationship between the two line segments is not connected, otherwise they are connected.

In some embodiments, the forming a topology network includes: forming connection relationship data between connection points according to the line segment data after repairing the line segment, and establishing a tree-shaped topology relationship network, and distinguishing the connection points into root nodes and leaf nodes. The node is the fixed point at the end of the net rope, and the leaf node is the connection between the net ropes.

In some embodiments, the searching for all feasible paths in the topological network includes: searching for a feasible path extending from the root node to the upper part of the input image according to the structure of the tree-shaped topological network.

In a second aspect, the present application provides a device for detecting a broken wire rope of a railway wagon, the device comprising: an extraction unit for extracting a target object included in an input image, and the target object is divided into a line segment and an end of the line segment The topological network unit is used to establish a topological network according to the connection relationship of all the connection points; the path planning unit is used to determine all feasible paths in the topological network; the judgment unit is used to determine whether there are feasible but practical paths in the topological network nonexistent path.

In a third aspect, the present application provides a computer device, which is characterized by comprising: a memory, which stores executable instructions; one or more processors, which communicate with the memory to execute the executable instructions to complete the following operations: extracting based on an identification algorithm Input the target object included in the image; according to the extracted target object, distinguish it into line segments and connection points at the end of the line segment; form a topological network according to the connection relationship between all the connection points; determine the topological network according to the topological network All feasible paths in; according to the feasible paths, determine whether there is a feasible path that does not actually exist.

The method and device for detecting the broken wire rope of a railway freight car provided by this application adopts the LSD algorithm to input the wire rope skeleton in the image in advance, and determines whether there is a practical non-existent but feasible path according to the topology network structure, so as to judge whether there is a broken wire rope. The rope has a small amount of calculation, and can quickly and accurately identify the position where the net rope is broken in the image, improving the efficiency and accuracy of detecting the target object.

Description of drawings

Fig. 1 is the flow chart of the method for detecting the broken wire rope of railway freight car of the present application;

Fig. 2 is a schematic diagram of an application scenario of the method for detecting the broken wire rope of a railway freight car according to the present application:

3 is a schematic diagram of a target object extracted by an identification algorithm according to an embodiment of the detection method of the present application;

FIG. 4 is a schematic diagram of the target object after line segment repairing according to the detection method provided in the present application.

FIG. 5 is a schematic structural diagram of an embodiment of a device for detecting a broken wire rope of a railway freight car according to the present application;

FIG. 6 is a schematic structural diagram of an electronic device suitable for implementing a terminal device or a server according to an embodiment of the present application.

Detailed ways

The present application will be described in further detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the related invention, but not to limit the invention. It should also be noted that, for the convenience of description, only the parts related to the invention are shown in the drawings.

It should be noted that the embodiments in the present application and the features of the embodiments may be combined with each other in the case of no conflict. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

FIG. 1 illustrates a flow 100 of one embodiment of a method for detecting a rope break in a railway wagon according to the present application. The method includes the following steps:

Step 101 , extracting the target object included in the input image based on the recognition algorithm, and distinguishing the extracted target object into a line segment and a connection point at the end of the line segment, see FIG. 2 and FIG. 3 .

In the present embodiment, the described identification algorithm adopts the LSD algorithm, and the implementation steps of the LSD algorithm:

① Gaussian downsampling of the input image with a scale of S=0.8.

② Calculate the gradient value and gradient direction of each point (level-line orientation).

③ According to the gradient value, all points are pseudo-ordered (pseudo-ordered), a state list is established, and the initial state of all points is set to UNUSED.

④ Set the state of the point whose gradient value is less than ρ to USED.

⑤ Take the point with the largest gradient (the first position of the pseudo-arrangement) in the list as the seed point (seed), set it as USED in the state list, and perform the following operations in a loop:

a. Using seed as the starting point, search for points around UNUSED and the direction is within the threshold range, and the status is changed to USED.

b. Generate a rectangle R containing all satisfying points.

c. Determine whether the density of the aligned pts satisfies the threshold D, if not, truncate R into multiple rectangular boxes until it is satisfied. NFAIε

d. Calculate the NFA.

e. Change R to make the value of NFA smaller until R is added to the output list.

⑥ Output all the points of the same sex and set the gray value to 255, and set the rest points to 0.

In this embodiment, after extracting the target object included in the input image, the image is binarized, the rope part is the foreground, and the rest is the background.

Step 102: After the above binarization, line segment repair is performed on the missing part of the line segment, and the repair result is shown in FIG. 4 .

The method for repairing a line segment in this embodiment includes: selecting endpoints on all isolated line segments, extending a certain length l along the line segment direction with the endpoints, where l is 200 pixels in the present invention, and judging whether the extended line segment is different from other line segments Whether the Euclidean distance of the upper end points is greater than the set threshold ε, the value of ε in the present invention is 50 pixels, if yes, the relationship between the two line segments is not connected, otherwise they are connected. The extension line direction range is, in the present invention, the value of θ is 5'.

Step 103, forming a topology network according to the connection relationship between all the connection points;

In this embodiment, the forming a topology network includes: forming connection relationship data between connection points according to line segment data after line segment repair, and establishing a tree-shaped topology relationship network, and distinguishing connection points into root nodes and leaf nodes. The node is the fixed point at the end of the net rope, and the leaf node is the connection between the net ropes.

Step 104: Determine all feasible paths in the topological network according to the topological network.

In this embodiment, the searching for all feasible paths in the topological network includes: searching for a feasible path extending from the root node to the upper part of the input image according to the structure of the tree-shaped topological network.

Step 105, according to the feasible path, determine whether there is a feasible but non-existent path, if there is, it means that the net rope is broken, otherwise, the net rope is intact.

As shown in FIG. 5 , an embodiment of the present invention further provides a device for detecting a broken rope of a railway freight car. The device 600 includes: an extraction unit 601 for extracting a target object included in an input image. The target object Divided into line segments and connection points at the ends of the line segments; 602, a line segment repair unit, for repairing the missing part of the line segment extracted by the extraction unit; a topology network unit 603, for establishing a topology network according to the connection relationship of all the connection points; The path planning unit 604 is used for determining all feasible paths in the topological network; the judging unit 605 is used for determining whether there are feasible but non-existing paths in the topological network.

The embodiment of the present invention also provides an electronic device, which may be, for example, a mobile terminal, a personal computer (PC), a tablet computer, a server, and the like. 6 , which shows a schematic structural diagram of an electronic device 700 suitable for implementing a terminal device or a server according to an embodiment of the present application: the computer system 700 includes one or more processors, a communication part, etc., the one or more Multiple processors such as: one or more central processing units (CPUs) 701 , and/or one or more graphics processing units (GPUs) 713 , etc., the processors may Various suitable actions and processes are performed by executing instructions or executable instructions loaded from storage section 708 into random access memory (RAM) 703 . The communication part 712 may include, but is not limited to, a network card, and the network card may include, but is not limited to, an IB (Infiniband) network card,

The processor can communicate with the read-only memory 702 and/or the random access memory 630 to execute executable instructions, connect with the communication part 712 through the bus 704, and communicate with other target devices through the communication part 712, so as to complete the provision of the embodiments of the present application. The operation corresponding to any one of the methods, for example, extracting the target object included in the input image based on the recognition algorithm; according to the extracted target object, distinguish it into a line segment and a connection point at the end of the line segment; The connection relationship forms a topological network; according to the topological network, all feasible paths in the topological network are determined; according to the feasible paths, it is determined whether there is a path that is feasible but does not actually exist.

In addition, in the RAM 703, various programs and data necessary for the operation of the apparatus can also be stored. The CPU 701 , the ROM 702 and the RAM 703 are connected to each other through a bus 704 . In the case of RAM 703, ROM 702 is an optional module. The RAM 703 stores executable instructions, or writes executable instructions into the ROM 702 at runtime, and the executable instructions enable the processor 701 to perform operations corresponding to the above communication methods. An input/output (I/O) interface 705 is also connected to bus 704 . The communication part 712 may be integrated, or may be configured to have multiple sub-modules (eg, multiple IB network cards) and be connected to the bus.

The following components are connected to the I/O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc. ; and a communication section 709 including a network interface card such as a LAN card, a modem, and the like. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is mounted on the drive 710 as needed so that a computer program read therefrom is installed into the storage section 708 as needed.

It should be noted that the architecture shown in FIG. 6 is only an optional implementation. In the specific practice process, the number and type of components in the above-mentioned FIG. 6 can be selected, deleted, added or replaced according to actual needs; For the setting of different functional components, separate settings or integrated settings can also be adopted. For example, the GPU and the CPU can be set separately or the GPU can be integrated on the CPU, and the communication department can be set separately or integrated on the CPU or GPU. and many more. These alternative embodiments all fall within the protection scope of the present disclosure.

In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product including a computer program tangibly embodied on a machine-readable medium, the computer program including program code for performing the methods illustrated in the flowcharts, the program code may include corresponding Execute the instructions corresponding to the method steps provided by the embodiments of the present application, for example, extract the target object included in the input image based on the recognition algorithm; according to the extracted target object, distinguish it into a line segment and a connection point at the end of the line segment; The connection relationship between the connection points forms a topological network; according to the topological network, all feasible paths in the topological network are determined; according to the feasible paths, it is determined whether there is a feasible path that does not actually exist. In such an embodiment, the computer program may be downloaded and installed from the network via the communication portion 709 and/or installed from the removable medium 711 . When the computer program is executed by the central processing unit (CPU) 701, the above-mentioned functions defined in the method of the present application are performed.

The method and apparatus, apparatus of the present invention may be implemented in many ways. For example, the method, apparatus, and apparatus of the present invention may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of the steps of the method is for illustration only, and the steps of the method of the present invention are not limited to the order specifically described above unless specifically stated otherwise. Furthermore, in some embodiments, the present invention can also be implemented as programs recorded in a recording medium, the programs comprising machine-readable instructions for implementing the methods according to the present invention. Thus, the present invention also covers a recording medium storing a program for executing the method according to the present invention.

The description of the present invention has been presented for purposes of illustration and description, and is not intended to be exhaustive or to limit the invention to the form disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiment was chosen and described in order to better explain the principles of the invention and the practical application, and to enable others of ordinary skill in the art to understand the invention for various embodiments with various modifications as are suited to the particular use.

Claims (9)

1. A method for detecting a net rope breakage, the method comprising: Extract the target object included in the input image based on the recognition algorithm, and divide the target object into line segments and connection points at the ends of the line segments; Form a topological network according to the connection relationship between all connection points; According to the topological network, determine all feasible paths in the topological network; According to the feasible path, it is determined whether there is a path that is feasible but does not actually exist. If there is, it means that the net rope is broken, otherwise, the net rope is intact. 2. method according to claim 1, is characterized in that, described identification algorithm adopts LSD algorithm, also comprises after extracting the target object included in the input image, the image is binarized, the rope part is foreground, the rest part of the background. 3 . The method according to claim 2 , further comprising performing line segment repair on the missing part of the line segment after the binarization of the image. 4 . 4. The method according to claim 3, wherein the method for repairing the line segment comprises: Select the endpoints on all isolated line segments, extend the above endpoints along the line segment to set the length, and judge whether the Euclidean distance between the extended line segment and the endpoints on other line segments is greater than the set threshold. If yes, the relationship between the two line segments is not. connected, otherwise connected. 5. The method according to claim 4, wherein the forming a topology network comprises: forming connection relationship data between the connection points according to the line segment data after repairing the line segment, and establishing a tree-shaped topology relationship network, connecting the connection points It is divided into root node and leaf node. The root node is the fixed point at the end of the net rope, and the leaf node is the connection between the net ropes. 6 . The method according to claim 5 , wherein the searching for all feasible paths in the topological network comprises: searching for a feasible path extending from the root node to the upper part of the input image according to the structure of the tree-shaped topological network. 7 . 7. A device for detecting the breakage of a railway wagon net rope, characterized in that the device comprises: The extraction unit is used to extract the target object included in the input image, and the target object is divided into a line segment and a connection point at the end of the line segment; The topology network unit is used to establish a topology network according to the connection relationship of all the connection points; A path planning unit, used to determine all feasible paths in the topology network; The judgment unit is used to determine whether there is a feasible but non-existent path in the topology network. 8 . The device according to claim 7 , further comprising a line segment repairing unit for repairing the missing part of the line segment extracted by the extraction unit. 9 . 9. A computer equipment, characterized in that, comprising: memory, which stores executable instructions; One or more processors, in communication with the memory to execute executable instructions to: Extract the target object included in the input image based on the recognition algorithm, and divide the target object into line segments and connection points at the ends of the line segments; Form a topological network according to the connection relationship between all connection points; According to the topological network, determine all feasible paths in the topological network; According to the feasible path, it is determined whether there is a feasible path that does not actually exist.