WO2022022310A1 - Method and apparatus for identifying optical splitter ports - Google Patents

Abstract

Provided are a method and apparatus for identifying optical splitter ports. The method comprises: performing image binarization on an optical splitter picture to be subjected to identification, so as to acquire a binarized image; determining an arrangement direction of optical splitter ports according to the binarized image; and scanning the binarized image according to the arrangement direction of the optical splitter ports, so as to acquire the splitting ratio of an optical splitter in said optical splitter picture, and information of an occupied port. According to the method and apparatus for identifying optical splitter ports, which are provided in embodiments of the present application, by means of performing image binarization on an optical splitter picture to be subjected to identification, so as to acquire a binarized image, determining an arrangement direction of optical splitter ports according to the binarized image, and scanning the binarized image according to the arrangement direction of the optical splitter ports, in order to acquire the splitting ratio of an optical splitter in said optical splitter picture, and information of an occupied port, an optical splitter port can be automatically identified, the identification efficiency can be improved, and costs can be reduced.

Description

Optical splitter port identification method and device

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims the priority of the Chinese patent application with the application number 202010733053.X, filed on July 27, 2020, and the invention title is "Method and Device for Identifying Optical Splitter Ports", which is incorporated herein by reference in its entirety.

technical field

The present application relates to the field of computer technology, and in particular, to a method and device for identifying a port of an optical splitter.

Background technique

The equipment resources of communication companies include base stations, computer rooms, optical splitters and other resources. Among them, due to the fact that the optical splitter itself is not charged, its port occupancy has been judged by manual review of on-site photos, which is inefficient and expensive.

SUMMARY OF THE INVENTION

Embodiments of the present application provide a method and device for identifying a splitter port, so as to solve the defect of low efficiency in the prior art and realize efficient splitter port identification.

An embodiment of the present application provides a method for identifying a port of an optical splitter, including:

Perform image binarization on the image of the spectroscope to be identified to obtain a binarized image;

determining the arrangement direction of the ports of the optical splitter according to the binarized image;

The binarized image is scanned according to the arrangement direction of the ports of the optical splitter, and the light splitting ratio and the information of the occupied ports of the optical splitter in the to-be-identified image of the optical splitter are obtained.

According to the optical splitter port identification method according to an embodiment of the present application, the specific step of determining the arrangement direction of the optical splitter ports according to the binarized image includes:

obtaining the centroid coordinates of each port-related region in the binarized image;

According to each of the centroid coordinates, obtain the abscissa difference sequence and the ordinate difference sequence of each of the centroids;

The arrangement direction of the optical splitter ports is determined according to the abscissa interpolation sequence and the ordinate difference sequence.

According to the optical splitter port identification method according to an embodiment of the present application, the binarized image is scanned according to the arrangement direction of the optical splitter ports to obtain the splitting ratio of the optical splitter in the to-be-identified optical splitter picture And the specific steps of occupied port information include:

Scan the first reference row or column of the binarized image according to the arrangement direction of the beam splitter ports, and perform delay integration on the pixel values of the first reference row or column. The pixel threshold determines the number of ports of the optical splitter and the position coordinates of each port;

If the port number check is passed, scan the second reference row or column of the binarized image, perform delay integration on the pixel values of the second reference row or column, and perform delay integration on the pixel values of the second reference row or column. The threshold determines the position coordinates of each occupied port;

The port number of each occupied port is determined according to the position coordinates of each port and the position coordinates of each occupied port.

According to the optical splitter port identification method according to an embodiment of the present application, the first reference row or column of the binarized image is scanned according to the arrangement direction of the optical splitter ports, and the first reference row or column of the first reference row or column is scanned. Delay integration is performed on the pixel value, and after determining the number of ports of the optical splitter and the position coordinates of each port according to the result of the delay integration and the preset pixel threshold, the method further includes:

If the port number check fails, scan the new first reference row or column of the binarized image according to the arrangement direction of the ports of the optical splitter, and scan the pixels in the new first reference row or column Delay integration is performed on the value, and the number of ports of the optical splitter and the position coordinates of each port are re-determined according to the result of the delay integration and the pixel threshold.

According to the optical splitter port identification method according to an embodiment of the present application, before acquiring the centroid coordinates of each port-related region in the binarized image, the method further includes:

Each port-related region in the binarized image is acquired according to the area of each region in the binarized image.

According to the optical splitter port identification method according to an embodiment of the present application, the specific steps of performing image binarization on the image of the optical splitter to be identified, and obtaining the binarized image include:

Convert the spectroscope image into the HSV color space, perform binarization and mathematical morphological operations, and obtain the binarized image.

According to the method for identifying a port of an optical splitter according to an embodiment of the present application, before performing image binarization on the image of the optical splitter to be identified and acquiring the binarized image, the method further includes:

If it is determined according to the image features that the normalized original picture is a qualified picture, the normalized original picture is used as the to-be-identified spectroscope picture.

The embodiment of the present application also provides an optical splitter port identification device, including:

The image processing module is used to perform image binarization on the image of the spectroscope to be recognized, and obtain the binarized image;

a direction judgment module, configured to determine the arrangement direction of the ports of the optical splitter according to the binarized image;

The port analysis module is configured to scan the binarized image according to the arrangement direction of the ports of the optical splitter, and obtain the information of the splitting ratio and the occupied ports of the optical splitter in the picture of the optical splitter to be identified.

Embodiments of the present application further provide an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor implements any of the above-mentioned light splitting when executing the program Steps of the device port identification method.

Embodiments of the present application further provide a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, implements the steps of any of the foregoing methods for identifying a port of a splitter.

The optical splitter port identification method and device provided in the embodiments of the present application obtain the binarized image by performing image binarization on the image of the optical splitter to be identified, and determine the arrangement direction of the optical splitter ports according to the binarized image. According to the arrangement direction of the splitter ports, the binarized image is scanned to obtain the splitting ratio of the splitter and the information of the occupied ports in the splitter image to be identified, which can realize the automatic identification of the splitter ports, improve the identification efficiency, and reduce the cost. The operation is accurate and the operation speed meets the actual demand, which can improve the management efficiency and management ability of the optical splitter, greatly reduce the personnel input, provide an important basis for the improvement of the data quality of the resource data platform, and improve the efficiency of operation and maintenance image review.

Description of drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the accompanying drawings used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description These are some embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without any creative effort.

1 is a schematic flowchart of a method for identifying a splitter port provided by an embodiment of the present application;

2 is a schematic structural diagram of an optical splitter port identification device provided by an embodiment of the present application;

FIG. 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

detailed description

In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments It is a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

In the description of the embodiments of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer" The orientation or positional relationship indicated by ” etc. is based on the orientation or positional relationship shown in the accompanying drawings, which is only for the convenience of describing the embodiments of the present application and simplifying the description, rather than indicating or implying that the indicated device or element must have a specific orientation, It is constructed and operated in a specific orientation, and therefore should not be construed as a limitation on the embodiments of the present application. Furthermore, the terms "first", "second", and "third" are used for descriptive purposes only and should not be construed to indicate or imply relative importance.

In the description of the embodiments of the present application, it should be noted that, unless otherwise expressly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it may be a fixed connection or a Removable connection, or integral connection; can be mechanical connection, can also be electrical connection; can be directly connected, can also be indirectly connected through an intermediate medium, can be internal communication between two components. Those of ordinary skill in the art can understand the specific meanings of the above terms in the embodiments of the present application in specific situations.

In order to overcome the above-mentioned problems of the prior art, the embodiments of the present application provide a method and device for identifying a port of an optical splitter. Perform noise filtering on the contour and fit the orientation of the splitter ports. Combined with the orientation of the splitter ports, use the pseudo-TDI imaging algorithm to analyze the port occupancy, output the splitter port occupancy, and give the splitting ratio and occupied port number of the splitter. The algorithm runs fast, the port analysis is accurate, and has a high application prospect.

FIG. 1 is a schematic flowchart of a method for identifying a port of an optical splitter provided by an embodiment of the present application. The method for identifying a port of an optical splitter according to an embodiment of the present application is described below with reference to FIG. 1 . As shown in FIG. 1 , the method includes: step S101 , performing image binarization on the image of the spectroscope to be identified to obtain a binarized image.

Specifically, the image of the spectroscope to be identified is binarized, the background is removed, and the position of the spectroscope port is preliminarily determined and extracted to obtain a binarized image.

It can be understood that the binarized image includes multiple regions. The above-mentioned multiple areas include port-related areas such as the area corresponding to the port and the area corresponding to the pigtail inserted into the port.

Step S102: Determine the arrangement direction of the ports of the optical splitter according to the binarized image.

Specifically, the arrangement direction of the beam splitter ports can be determined according to the distribution of each area in the binarized image, that is, it is determined whether the beam splitter ports are arranged horizontally or vertically in the binarized image.

Usually, there is a gap between two adjacent beamsplitter ports, so each port corresponds to a region in the binarized image. For any port, if the port is not occupied, there are no other cables or devices in the direction perpendicular to the arrangement direction of the optical splitter ports, and there is no area in the binarized image; if the port is occupied, the binary value There is an area corresponding to pigtails in the image in the direction perpendicular to the arrangement direction of the splitter ports. The splitting ratio of common beamsplitters is 1:4, 1:8 or 1:16, etc. Therefore, in the binarized image, there are a large number of areas in the arrangement direction of the beamsplitter ports. A smaller number of areas exist in the direction perpendicular to the direction. Therefore, according to the distribution of each area in the binarized image, the arrangement direction of the beam splitter ports can be determined.

Step S103 , scan the binarized image according to the arrangement direction of the ports of the optical splitter, and obtain the information of the splitting ratio and the occupied ports of the optical splitter in the image of the optical splitter to be identified.

Specifically, if the ports of the beam splitter are arranged horizontally in the binarized image, the occupancy status of the ports is analyzed by scanning the lines of the binarized image, the occupancy status of the ports of the beam splitter is output, and the splitting ratio and occupied ports of the beam splitter are given. number (that is, the information about the occupied port).

If the ports of the splitter are arranged vertically in the binarized image, analyze the port occupancy by scanning the columns of the binarized image, output the port occupancy of the splitter, and give the splitting ratio and occupied port number of the splitter.

Taking the method of scanning the lines of the binarized image as an example, by scanning the lines of the binarized image, the area corresponding to each port can be determined; according to the number of areas corresponding to the ports, the light splitting ratio of the spectroscope can be obtained.

For example, if the area corresponding to 9 ports is scanned, the splitting ratio of the optical splitter can be obtained as 1:8; if the area corresponding to 5 ports is scanned, the splitting ratio of the optical splitter can be obtained as 1:4.

By scanning the lines of the binarized image, the area corresponding to the pigtail inserted into the port can also be determined; the information of the occupied port can be obtained by comparing the area corresponding to the pigtail inserted into the port with the area corresponding to the port.

It can be understood that the process of scanning the columns of the binarized image is similar to the above-mentioned process of scanning the rows of the binarized image, and details are not repeated here.

It should be noted that the method for identifying a port of an optical splitter provided by the embodiment of the present application is suitable for port identification of an optical splitter whose ports are arranged in a single row.

In this embodiment of the present application, the image of the optical splitter to be identified is binarized to obtain a binarized image, the arrangement direction of the optical splitter ports is determined according to the binarized image, and the binarized image is determined according to the arrangement direction of the optical splitter ports. Scan the image to obtain the splitting ratio of the optical splitter and the information of the occupied ports in the image of the optical splitter to be identified, which can realize the automatic identification of the optical splitter port, can improve the identification efficiency, reduce the cost, run accurately, and the running speed can meet the actual needs. Improving the management efficiency and management ability of the optical splitter can greatly reduce the personnel investment, provide an important basis for the improvement of the data quality of the resource data platform, and improve the efficiency of operation and maintenance image review.

Based on the contents of the above embodiments, and according to the binarized image, the specific steps of determining the arrangement direction of the ports of the beam splitter include: acquiring the centroid coordinates of each port-related region in the binarized image.

Specifically, a plane rectangular coordinate system is established for the binarized image, the horizontal axis along the row direction is the x axis, and the vertical axis along the column direction is the y axis.

Each region in the binarized image can be screened according to a preset standard, and each port-related region therein can be determined.

The preset criteria may be the area and/or shape of the region, and the like.

For each port-related region, the coordinates of the centroid of the region can be obtained according to the position of each pixel included in the region.

Through the above operations, the centroid coordinates (x _i , y _i ) of each port-related region can be obtained, 2≤i≤n. Among them, n represents the total number of port-related areas.

According to the coordinates of each centroid, the abscissa difference sequence and the ordinate difference sequence of each centroid are obtained.

Specifically, the abscissa sequence {x _i } and the ordinate sequence {y _i } are sorted according to the same order of size, for example, in ascending order, respectively, to obtain new abscissa sequences {x _i '} and The new ordinate sequence {y' _i }.

For the new abscissa sequence {x' _i }, the difference D _xi =x' _i -x' _i-1 of two adjacent elements in the sequence is sequentially obtained, and the abscissa difference sequence {D _xi } is obtained.

For the new ordinate sequence {y' _i }, the difference D _yi =y' _i -y' _i-1 of two adjacent elements in the sequence is sequentially obtained, and the ordinate difference sequence {D _yi } is obtained.

According to the abscissa interpolation sequence and the ordinate difference sequence, the arrangement direction of the ports of the optical splitter is determined.

Specifically, each element in the abscissa difference sequence {D _xi } is compared with a preset difference threshold T to obtain the number N of elements smaller than T in the abscissa difference sequence {D _xi }.

Each element in the ordinate difference sequence {D _yi } is compared with a preset difference threshold T, and the number M of elements smaller than T in the ordinate difference sequence {D _yi } is obtained.

If N>M, the arrangement direction of the optical splitter ports is the x-axis direction, that is, the lateral direction (or the direction along the row); if N<M, the arrangement direction of the optical splitter ports is the y-axis direction, that is, the longitudinal direction (or along the column direction). direction).

In this embodiment of the present application, the centroid coordinates of each port-related region are obtained, and according to the coordinates of each centroid, the abscissa difference sequence and the ordinate difference sequence of each centroid are obtained, and the spectrometer is determined according to the abscissa interpolation sequence and the ordinate difference sequence. According to the arrangement direction of the splitter ports, the arrangement direction of the splitter ports can be accurately analyzed, so that the binarized image can be scanned according to the arrangement direction of the splitter ports, and the splitting ratio and The information of the occupied port can realize automatic identification of the optical splitter port, which can improve the identification efficiency and reduce the cost.

Based on the contents of the above-mentioned embodiments, the binarized image is scanned according to the arrangement direction of the ports of the optical splitter, and the specific steps of obtaining the splitting ratio of the optical splitter and the information of the occupied ports in the image of the optical splitter to be identified include: Arrangement direction of the ports, scan the first reference row or column of the binarized image, perform delay integration on the pixel values of the first reference row or column, and determine the number of ports and The location coordinates of each port.

It should be noted that the binarized image is scanned according to the arrangement direction of the beamsplitter ports, and the algorithm to obtain the splitting ratio of the beamsplitter and the information of the occupied ports in the beamsplitter image to be identified is based on a CCD camera imaging method. - TDI algorithm, which can be called quasi-TDI imaging algorithm.

TDI (Time Delay Integration) is a CCD camera imaging method, and its charge transfer method is instructive for the port identification of the beam splitter. After the traditional CCD imaging is completed, an image of size N*N is directly output, and its pixel value has a one-to-one correspondence with the number of charges of the CCD pixel. However, TDI CCD is a process of continuous accumulation of charges, and it is difficult to tell the relationship between the pixel value and the number of charges at a certain pixel position.

The TDI algorithm is suitable for the imaging of high-speed moving objects. CCD devices are usually suitable for imaging some high-speed moving objects. One advantage of the TDI algorithm is that the same scene is imaged by adding multiple lines of linear array pixel signals, and the equivalent charge number of the output signal is the total number of charges in the M series, which is compared with ordinary linear array CCDs (especially area array CCDs) The non-uniformity of response between cells is reduced. Due to the influence of the non-uniformity of the camera system, under the same uniform light radiation of the remote sensing camera, the video output signal amplitudes of different pixels of the linear array TDI CCD are different, which is the so-called non-uniformity of the system response.

Taking the method of scanning the lines of the binarized image as an example, according to the distribution of the relevant areas of each port, it is possible to determine the minimum value of the ordinate in any row through which the area corresponding to each port passes or the pixels included in the relevant area of each port. line as the first reference line.

The ordinate of the first reference line is y, the coordinate of the pixel initially scanned on the first reference line is (0,y), and the pixel value of the pixel is V _(0,y) . V _(i,y) is the pixel value of the pixel traversed by scanning on the first reference line. Let Bucketj be a counter, the initial value is 0, 0≤i≤K-1, j=0,1,2,3,…. Among them, K represents the number of pixels in each row of the binarized image; L represents the number of pixels in each column.

The steps for delayed integration include:

If V _{(i, y)} = 0, and V _{(i+1, y)} > 0, then create a new Bucket _j = 0, prepare to start integration, and save the coordinate value (i, y) at this time;

If V _{(i, y)} > 0, and V _{(i+1, y)} > 0, then Bucket _j = Bucket _j +1, and the cumulative integration of pixel values is performed;

If V _{(i, y)} > 0, and V _{(i+1, y)} = 0, the integration ends, and the current Bucket _j and coordinate values (i, y) are saved.

Through the above steps of delayed integration, the result of delayed integration can be obtained as a plurality of coordinate values (i, y) and a plurality of count values (integration values) Bucket _j .

According to multiple coordinate values (i, y) and multiple count values (integral values) Bucket _j , as well as the preset pixel threshold, the number of ports k of the optical splitter and the position coordinates B _k (i, y of each port) can be obtained ).

The preset pixel threshold indicates the number of pixels occupied by one beam splitter port in general. The specific value of the pixel threshold may be determined according to the actual situation, which is not specifically limited in this embodiment of the present application.

For any Bucket _j , the number of ports included between the start and end abscissas corresponding to the Bucket _j is equal to the nearest integer of the result of dividing the Bucket _j by the pixel threshold.

According to the multiple coordinate values (i, y) recorded by the delay integration, the number of ports k, and the pixel threshold, the position coordinate B _k (i, y) of each port can be determined.

Preferably, the coordinates of the center position of each port can be determined as the position coordinates of the port.

If the port number check is passed, scan the second reference row or column of the binarized image, perform delay integration on the pixel values of the second reference row or column, and determine the position coordinates of each occupied port according to the result of the delay integration and the pixel threshold. .

Specifically, the split ratio in the resource system is used as a check code to check the port number k of the splitter.

The splitting ratio in the resource system includes 1:4, 1:8 or 1:16, etc. The splitter must include an input port, so check whether the port number k is the last term of the splitting ratio such as 4, 8 and 16 plus 1.

If so, the verification passes; if not, the verification fails.

If the verification is passed, it can be determined that any row corresponding to the area corresponding to the pigtail fiber inserted into each port passes through or the next row of the first reference row is used as the second reference row.

If the verification is passed, the light splitting ratio of the light splitter in the to-be-identified light splitter picture can be determined as 1:(k-1).

The ordinate of the second reference line is y', and the pixel coordinates of the initial scan on the second reference line are (0, y').

By performing delay integration on the pixel values of the second reference row or column, the position coordinates B' _k (i, y) of each occupied port can be obtained.

It should be noted that when the next line of the first reference line is used as the second reference line, if the obtained position coordinates B' _k (i, y) of each occupied port and the position coordinates B _k (i, y) of each port ) is the same, then take the next line of the second reference line as a new second reference line, and re-acquire the position coordinates B' _k (i, y) of each occupied port until the position coordinates B' _k (i, y) of each occupied port y) is different from the position coordinate B _k (i, y) of each port; if it reaches the row where the maximum value of the ordinate is located in the pixel points included in the relevant area of each port, the obtained position coordinate B' _k (i , y) is still the same as the position coordinate B _k (i, y) of each port, it means that the ports of the optical splitter are all occupied.

The specific steps of performing delayed integration on the pixel values of the second reference row or column are similar to the specific steps of performing delayed integration on the pixel values of the first reference row or column, and will not be repeated here.

The port number of each occupied port is determined according to the position coordinates of each port and the position coordinates of each occupied port.

Specifically, by comparing the position coordinates B _{k (i, y) of each port with the position coordinates B' k (} i, y) of each occupied port, the occupied port number can be obtained.

It can be understood that the process of scanning the columns of the binarized image is similar to the above-mentioned process of scanning the rows of the binarized image, and details are not repeated here.

In this embodiment of the present application, delay integration is performed on the pixel values of the first reference row or column and the pixel values of the second reference row or column, and the splitting ratio and occupancy of the beam splitter in the to-be-identified beam splitter picture are obtained according to the result of the delay integration. The port information can realize the automatic identification of the splitter port, can improve the identification efficiency, reduce the cost, run accurately, and the running speed can meet the actual needs, can improve the management efficiency and control ability of the splitter, can greatly reduce the personnel input, can It provides an important basis for improving the data quality of the resource data platform.

Based on the contents of the above embodiments, the first reference row or column of the binarized image is scanned according to the arrangement direction of the beam splitter ports, and the pixel values of the first reference row or column are delayed and integrated. After the set pixel threshold determines the number of ports of the beam splitter and the position coordinates of each port, it also includes: if the port number check fails, scan the new first reference line of the binarized image according to the arrangement direction of the ports of the beam splitter. Or column, delay integration is performed on the pixel values of the new first reference row or column, and the number of ports of the optical splitter and the position coordinates of each port are re-determined according to the result of the delay integration and the pixel threshold.

Specifically, taking the method of scanning the row of the binarized image as an example, if the port number check obtained by delaying the integration of the pixel values of the first reference row or column fails, it means that the row is not the area corresponding to each port If all passes, the new first reference line is determined.

Any row through which the area corresponding to each port passes or the row next to the original first reference row may be determined as a new first reference row.

Delay integration is performed on the pixel values of the new first reference row or column, and the number of ports of the optical splitter and the position coordinates of each port are re-determined according to the result of the delay integration and the pixel threshold until the port number verification is passed.

The embodiment of the present application scans the new first reference row or column of the binarized image according to the arrangement direction of the ports of the optical splitter when the port number check fails, and delays the pixel values of the new first reference row or column Integrate, re-determine the number of ports of the beam splitter and the position coordinates of each port according to the result of the delay integration and the pixel threshold, which can realize the automatic identification of the ports of the beam splitter, improve the identification efficiency, reduce the cost, run accurately, and meet the actual needs of the running speed , can improve the management efficiency and control ability of the optical splitter, can greatly reduce the personnel input, and can provide an important basis for the improvement of the data quality of the resource data platform.

Based on the contents of the above embodiments, before acquiring the centroid coordinates of each port related region in the binarized image, the method further includes: acquiring each port related region in the binarized image according to the area of each region in the binarized image.

Specifically, the information of each region in the binarized image includes connectivity attributes, area, Hu moments, convex hull analysis, and the like.

According to the area of each area in the binarized image and the preset area interval, each area can be screened, and each port-related area can be deleted.

Port-related area, with a certain area range.

The area range can be set according to the actual situation. The specific value of the area interval is not specifically limited in the embodiment of the present application.

If the area of the area is too small, it means that the area is noise and other noise points; if the area of the area is too large, it means that the area is not a port-related area.

In this embodiment of the present application, each port-related region in the binarized image can be obtained according to the area of each region in the binarized image, and each port-related region can be extracted, so that the optical splitter to be identified can be obtained by analysis according to each port-related region The splitting ratio of the optical splitter and the information of the occupied ports in the picture can realize the automatic identification of the optical splitter port, which can improve the identification efficiency and reduce the cost.

Based on the contents of the above embodiments, the image of the beam splitter to be identified is image binarized, and the specific steps of obtaining the binarized image include: converting the beam splitter image into the HSV color space, performing binarization and mathematical morphology Operation to obtain a binarized image.

Specifically, since the port color of the beam splitter has regularity, most of which are blue or green, in order to make the result of the preliminary extraction of the position of the beam splitter port through binarization more accurate, the beam splitter image can be converted to the HSV color space first. , the binarization is performed in the HSV color space, the position of the beam splitter port is preliminarily determined, and the original binarized image is obtained.

HSV (Hue, Saturation, Value) is a color space created according to the intuitive characteristics of color, also known as the Hexcone Model. The parameters of the color in this model are: Hue (H), Saturation (S), Lightness (V).

Since the original binarized image may contain irregular holes, which is not conducive to the analysis of the area in the image, we can perform mathematical morphological operations on the original binarized image to fill the holes and obtain the binarized image to ensure the port of the beam splitter. Integrity of connected domains.

Preferably, a closing operation can be used to fill the holes.

The closing operation is a mathematical morphological operation that dilates and then corrodes the image. Its role is to fill small holes in objects, connect adjacent objects, connect disconnected contour lines, and smooth its boundaries without changing the area.

Preferably, the closing operation can be performed using a 5*5 all-one structure.

In the embodiment of the present application, by converting the beam splitter image into the HSV color space, performing binarization and mathematical morphological operations, and obtaining a binarized image, a more complete area can be obtained, so that analysis based on the area in the binarized image can be achieved. Obtaining the information of the splitting ratio of the optical splitter and the information of the occupied ports in the picture of the optical splitter to be identified can realize the automatic identification of the optical splitter port, which can improve the identification efficiency and reduce the cost.

Based on the contents of the foregoing embodiments, performing image binarization on the image of the spectroscope to be identified, and before acquiring the binarized image, the method further includes: if it is determined according to the image features that the normalized original image is a qualified image, then The normalized original picture is used as the light splitter picture to be identified.

It can be understood that due to the uncertainty of the image acquisition equipment and the different acquisition personnel, the size of the original image of the spectroscope collected in the field is different, and due to factors such as the on-site environment and the photography level of the collector, the original image of the spectroscope collected on-site may exist. Too bright, too dark, single scene, blur, etc. do not meet the requirements. Therefore, you can first normalize the original image, adjust the size of the original image to the preset size, and carry out the process according to the preset gray level. convert.

The preset size can be set according to the actual situation, such as 720*1024 or 1024*720 (determined according to the shooting direction). The specific numerical value of the preset size is not limited in this embodiment of the present application.

The preset gray level can be set according to the actual situation, such as 8-bit gray level. The specific value of the preset gray level is not limited in this embodiment of the present application.

Appropriate parameters can be used as image features, for example, at least one of gray mean (Mean), standard deviation (Std), and image entropy (Entropy) can be used as image features to judge whether the normalized original image is qualified or not. .

The inter-class variance method can be used as a threshold selection method to select a feature threshold for determining whether the normalized original image is qualified.

For example, taking the gray mean value as an example, the gray mean value of the pre-acquired black image library and the qualified image library are respectively extracted, and the value with the largest variance between the two types of pictures is used as the threshold.

If the normalized original picture is a qualified picture, the normalized original picture is used as a to-be-identified beam splitter picture, and step S101 is performed to identify a beam splitter port for the to-be-identified beam splitter picture.

If the normalized original picture is an unqualified picture, the normalized original picture is not used as the optical splitter picture to be identified, and the optical splitter port is not identified for the normalized original picture.

In the embodiment of the present application, it is judged that the normalized original picture is a qualified picture according to the image features, and the normalized original picture is used as the to-be-identified beam splitter picture, so as to avoid the unqualified picture being subjected to optical splitter port identification. Identification can avoid invalid identification work and save software and hardware resources.

In order to facilitate the understanding of the above-mentioned embodiments of the present application, an example is used to describe the optical splitter port identification methods provided by the above-mentioned embodiments of the present application.

For the 17,965 pictures in the operation and maintenance picture library on a certain day, through normalization and image preprocessing, 6,660 qualified pictures were filtered out as the beam splitter pictures to be identified, and 11,305 unqualified pictures were filtered out. The ratio is reduced by more than 60%, which greatly reduces manual intervention and improves operation and maintenance efficiency.

Then, according to the optical splitter port identification method provided by the above-mentioned embodiments of the present application, the port identification is performed on the above-mentioned 6660 pictures of the optical splitter to be identified. From the 238 pictures containing the optical splitter, 216 pictures of the splitting ratio of the optical splitter are successfully identified, including 1:4 and 1:8 two kinds of ports; 205 sheets of the port number occupied by the optical splitter are correctly identified, with an accuracy rate of 94.9% and a standard deviation of 0.19.

The above examples illustrate that the embodiments of the present application have high recognition accuracy.

The laptop computer with CPU i5-6300HQ and 8G memory takes 10 pictures as the unit, the picture resolution is 1024*768, the picture format is JPG, and the optical splitter port is identified. The statistical processing time (unit: s) is shown in Table 1. Show.

Table 1 Optical splitter port identification running time statistics

picture number	1	2	3	4	5	6	7	8	9	10
operation hours	7.8	6.3	5.6	5.7	5.9	5.8	6.2	5.7	5.2	7.2

It can be seen from Table 1 that the operating speed of the optical splitter port identification method provided by the above-mentioned embodiments of the present application satisfies actual requirements.

The following describes the optical splitter port identification apparatus provided by the embodiments of the present application, and the optical splitter port identification apparatus described below and the optical splitter port identification method described above may refer to each other correspondingly.

FIG. 2 is a schematic structural diagram of an apparatus for identifying a port of an optical splitter according to an embodiment of the present application. Based on the contents of the above-mentioned embodiments, as shown in FIG. 2 , the apparatus includes an image processing module 201, a direction judgment module 202 and a port analysis module 203:

The image processing module 201 is configured to perform image binarization on the to-be-recognized spectrometer picture to obtain a binarized image;

The direction judgment module 202 is used for determining the arrangement direction of the ports of the optical splitter according to the binarized image;

The port analysis module 203 is configured to scan the binarized image according to the arrangement direction of the ports of the optical splitter to obtain the splitting ratio of the optical splitter and the information of the occupied ports in the image of the optical splitter to be identified.

Specifically, the image processing module 201 , the direction determination module 202 and the port analysis module 203 are electrically connected in sequence.

The image processing module 201 performs image binarization on the image of the spectroscope to be recognized, removes the background, and realizes preliminary determination and extraction of the position of the spectroscope port to obtain a binarized image.

The direction determination module 202 can determine the arrangement direction of the beam splitter ports according to the distribution of each area in the binarized image, that is, determine whether the beam splitter ports are arranged horizontally or vertically in the binarized image.

The port analysis module 203 can determine the area corresponding to each port by scanning the row or column of the binarized image; according to the number of areas corresponding to the port, the spectroscopic ratio of the spectroscope can be obtained; by scanning the row or column of the binarized image; You can also determine the area corresponding to the pigtail inserted into the port; by comparing the area corresponding to the pigtail inserted into the port with the area corresponding to the port, you can obtain information about the occupied port.

The optical splitter port identification device provided by the embodiment of the present application is used to execute the optical splitter port identification method provided by the above-mentioned embodiments of the present application. For the specific methods and processes of the modules included in the optical splitter port identification device to implement corresponding functions, please refer to the above-mentioned details. Embodiments of the optical splitter port identification method are not repeated here.

The optical splitter port identification device is used in the optical splitter port identification methods of the foregoing embodiments. Therefore, the descriptions and definitions in the optical splitter port identification methods in the foregoing embodiments can be used for the understanding of each execution module in the embodiments of the present application.

In this embodiment of the present application, the image of the optical splitter to be identified is binarized to obtain a binarized image, the arrangement direction of the optical splitter ports is determined according to the binarized image, and the binarized image is determined according to the arrangement direction of the optical splitter ports. Scan the image to obtain the splitting ratio of the optical splitter and the information of the occupied ports in the image of the optical splitter to be identified, which can realize the automatic identification of the optical splitter port, can improve the identification efficiency, reduce the cost, run accurately, and the running speed can meet the actual needs. Improving the management efficiency and management ability of the optical splitter can greatly reduce the personnel investment, provide an important basis for the improvement of the data quality of the resource data platform, and improve the efficiency of operation and maintenance image review.

FIG. 3 illustrates a schematic diagram of the physical structure of an electronic device. As shown in FIG. 3, the electronic device may include: a processor (processor) 301, a memory (memory) 302, and a bus 303; wherein, the processor 301 and the memory 302 pass through The bus 303 completes mutual communication; the processor 301 is configured to call computer program instructions stored in the memory 302 and run on the processor 301 to execute the optical splitter port identification method provided by the above method embodiments, the method comprising: : Binarize the image of the spectroscope to be identified to obtain a binarized image; determine the arrangement direction of the spectroscope ports according to the binarized image; scan the binarized image according to the arrangement direction of the spectroscope ports, Obtain the splitting ratio and occupied port information of the splitter in the picture of the splitter to be identified.

In addition, the above-mentioned logic instructions in the memory 302 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution, and the computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes .

On the other hand, an embodiment of the present application further provides a computer program product, the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program includes program instructions, when the program instructions When executed by a computer, the computer can execute the optical splitter port identification method provided by the above method embodiments. The method includes: performing image binarization on the image of the optical splitter to be identified, and obtaining a binarized image; according to the binarized image , determine the arrangement direction of the optical splitter ports; scan the binarized image according to the arrangement direction of the optical splitter ports to obtain the splitting ratio of the optical splitter and the information of the occupied ports in the optical splitter picture to be identified.

In yet another aspect, the embodiments of the present application further provide a non-transitory computer-readable storage medium on which a computer program is stored, and the computer program is implemented when executed by a processor to execute the optical splitter port identification method provided by the above embodiments , the method includes: performing image binarization on the image of the optical splitter to be identified to obtain a binarized image; determining the arrangement direction of the optical splitter ports according to the binarized image; The image is scanned to obtain the light splitting ratio and occupied port information of the light splitter in the picture of the light splitter to be identified.

The device embodiments described above are only illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in One place, or it can be distributed over multiple network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment. Those of ordinary skill in the art can understand and implement it without creative effort.

From the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and certainly can also be implemented by hardware. Based on this understanding, the above-mentioned technical solutions can be embodied in the form of software products in essence or the parts that make contributions to the prior art, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, magnetic A disc, an optical disc, etc., includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the methods described in various embodiments or some parts of the embodiments.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still be Modifications are made to the technical solutions recorded in the foregoing embodiments, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims (10)

1. An optical splitter port identification method, comprising:

   Perform image binarization on the image of the spectroscope to be identified to obtain a binarized image;

   determining the arrangement direction of the ports of the optical splitter according to the binarized image;

   The binarized image is scanned according to the arrangement direction of the ports of the optical splitter, and the light splitting ratio and the information of the occupied ports of the optical splitter in the to-be-identified image of the optical splitter are obtained.
2. The optical splitter port identification method according to claim 1, wherein the specific step of determining the arrangement direction of the optical splitter ports according to the binarized image comprises:

   obtaining the centroid coordinates of each port-related region in the binarized image;

   According to each of the centroid coordinates, obtain the abscissa difference sequence and the ordinate difference sequence of each of the centroids;

   The arrangement direction of the optical splitter ports is determined according to the abscissa interpolation sequence and the ordinate difference sequence.
3. The optical splitter port identification method according to claim 1, wherein the binarized image is scanned according to the arrangement direction of the optical splitter ports to obtain the light splitting of the optical splitter in the to-be-identified optical splitter picture The specific steps for comparing and occupying port information include:

   Scan the first reference row or column of the binarized image according to the arrangement direction of the beam splitter ports, and perform delay integration on the pixel values of the first reference row or column. The pixel threshold determines the number of ports of the optical splitter and the position coordinates of each port;

   If the port number check is passed, scan the second reference row or column of the binarized image, perform delay integration on the pixel values of the second reference row or column, and perform delay integration on the pixel values of the second reference row or column. The threshold determines the position coordinates of each occupied port;

   The port number of each occupied port is determined according to the position coordinates of each port and the position coordinates of each occupied port.
4. The optical splitter port identification method according to claim 3, wherein according to the arrangement direction of the optical splitter ports, the first reference row or column of the binarized image is scanned, and the first reference row or column is scanned for the first reference row or column. Delay integration is performed on the pixel value of the optical splitter, and after determining the number of ports of the optical splitter and the position coordinates of each port according to the result of the delay integration and the preset pixel threshold, it also includes:

   If the port number check fails, scan the new first reference row or column of the binarized image according to the arrangement direction of the ports of the optical splitter, and scan the pixels in the new first reference row or column Delay integration is performed on the value, and the number of ports of the optical splitter and the position coordinates of each port are re-determined according to the result of the delay integration and the pixel threshold.
5. The optical splitter port identification method according to claim 2, wherein before acquiring the centroid coordinates of each port-related region in the binarized image, the method further comprises:

   Each port-related region in the binarized image is acquired according to the area of each region in the binarized image.
6. The optical splitter port identification method according to claim 1, wherein the specific steps of performing image binarization on the image of the optical splitter to be identified, and obtaining the binarized image include:

   Convert the spectroscope image into the HSV color space, perform binarization and mathematical morphological operations, and obtain the binarized image.
7. The optical splitter port identification method according to any one of claims 1 to 6, wherein the performing image binarization on the image of the optical splitter to be identified, before acquiring the binarized image, further comprising:

   If it is determined according to the image features that the normalized original picture is a qualified picture, the normalized original picture is used as the to-be-identified spectroscope picture.
8. An optical splitter port identification device, comprising:

   The image processing module is used to perform image binarization on the image of the spectroscope to be recognized, and obtain the binarized image;

   a direction judgment module, configured to determine the arrangement direction of the ports of the optical splitter according to the binarized image;

   The port analysis module is configured to scan the binarized image according to the arrangement direction of the ports of the optical splitter, and obtain the information of the splitting ratio and the occupied ports of the optical splitter in the picture of the optical splitter to be identified.
9. An electronic device, comprising a memory, a processor and a computer program stored on the memory and running on the processor, characterized in that, when the processor executes the program, the program as claimed in any one of claims 1 to 7 is implemented. The steps of the optical splitter port identification method described above.
10. A non-transitory computer-readable storage medium on which a computer program is stored, characterized in that, when the computer program is executed by a processor, the steps of the optical splitter port identification method according to any one of claims 1 to 7 are implemented .

Images