1. A method for detecting the state of a data center server is characterized in that: the method comprises the following steps:

s1, collecting a detection image for the server;

s2, accurately positioning the image of the server in the detection image;

and S3, blocking the positioned server image, performing template matching on the image block comprising the region of interest, and judging the current state of the server according to the matching result.

2. The method of claim 1, wherein:

in step S1, the device for capturing the detection image for the server includes one or a centralized combination of a camera, a video camera, and an electronic device with a photographing or recording function.

3. The method of claim 1, wherein: the server is adhered with the two-dimensional code, the two-dimensional code is adhered to a set position of the server, the two-dimensional code serves as a unique identifier of the server and also serves as a reference object for positioning the server in an acquired detection image, the adhered two-dimensional code is set to be long in side length, and four sides of the adhered two-dimensional code are parallel to four sides of the server.

4. The method of claim 3, wherein:

in step S2, the process of accurately positioning the image of the server in the detection image includes:

s201, acquiring actual coordinates of four angles of the two-dimension code in the detection image through a two-dimension code detection recognition library;

s202, calculating theoretical coordinates of four corner points of the undeformed two-dimensional code according to the coordinates of the reference points in the obtained actual coordinates of the two-dimensional code and the height and width of the two-dimensional code;

s203, acquiring an affine transformation matrix of image deformation according to the actual coordinates and the theoretical coordinates of the two-dimensional code;

s104, acquiring the model of the server according to the content of the identified two-dimensional code, acquiring the installation position of the two-dimensional code and theoretical coordinates of four corner points of the server according to the width-height ratio of the two-dimensional code to the server, and accurately positioning the server.

5. The method of claim 3, wherein:

the two-dimensional code is pasted on one corner of the server, and two adjacent edges of the two-dimensional code are flush with the edge of the server.

6. The method of claim 3, wherein:

in step S3, the region of interest of the server is acquired according to the model of the server acquired by identifying the two-dimensional code.

7. A data center server state detection system is characterized in that: the system comprises a server image acquisition module, a server positioning module and a state discrimination module, wherein:

the server image acquisition module is used for acquiring a detection image containing a server;

the server positioning module is used for extracting an image of the server from the acquired detection image;

the state discrimination module is used for blocking the extracted image of the server, matching the template of the image block containing the interest, acquiring the matching result and obtaining the current state of the server.

8. The system of claim 7, wherein:

the server is adhered with the two-dimensional code, the two-dimensional code is adhered to a set position of the server, the two-dimensional code serves as a unique identifier of the server and also serves as a reference object for positioning the server in an acquired detection image, the adhered two-dimensional code is set to be long in side length, and four sides of the adhered two-dimensional code are parallel to four sides of the server.

9. The system of claim 8, wherein: the server image acquisition module comprises a two-dimensional code recognition library and a mapping relation calculation module, wherein:

the two-dimension code recognition library is used for acquiring actual coordinates of four angles of the two-dimension code in the detection image, and calculating theoretical coordinates of four corner points of the undeformed two-dimension code according to the coordinates of the reference points in the actual coordinates and the height and width of the two-dimension code;

and the mapping shutdown calculation module is used for acquiring an affine transformation matrix of an image phenotype according to the actual coordinates and the theoretical coordinates of the two-dimensional code, and determining the boundary of the server image according to the position relation between the server and the two-dimensional code.

10. The system of claim 9, wherein: the state discrimination module is used for determining the region of interest of the server according to the model of the server identified by the two-dimensional code identification library.

Background

A large amount of servers can be generally deposited in the data center, mostly deposit for the rack, and a plurality of servers can be deposited in a rack, spacing distance between adjacent server is generally less, consequently, in order to avoid the emergence of unexpected condition, need regularly patrol and examine data center, so that in time master the running state of server, in time discover unexpected condition, under original artifical condition of patrolling and examining, can have extravagant manpower, patrol and examine the shortcoming of inefficiency, under prior art, the intelligence is patrolled and examined the robot and can be replaced the manual work and patrol and examine, reduce artifical input, can also promote and patrol and examine efficiency, but if adopt every server of method monitoring of degree of depth learning, not only will calculate with higher speed for the special chip of degree of depth learning of robot, and the effect that detects under the computer lab environment is not ideal. However, if the server operation state detection uses the image template matching method, the more image pixels, the slower the matching speed.

Disclosure of Invention

The invention aims to provide a data center server state detection method for quickly positioning a server and a data center server state detection system for realizing the method.

The technical scheme adopted by the invention is as follows:

the invention provides a method for detecting the state of a data center server, which comprises the following steps:

s1, collecting a detection image for the server;

s2, accurately positioning the image of the server in the detection image;

and S3, blocking the positioned server image, performing template matching on the image block comprising the region of interest, and judging the current state of the server according to the matching result.

As a further optimization of the method of the present invention, in step S1 of the present invention, the device for acquiring the detection image from the server includes one or a centralized combination of a camera, a video camera and an electronic device with a photo taking or video recording function.

As a further optimization of the method, the server is pasted with the two-dimensional code, and the two-dimensional code is pasted on a set position of the server, the two-dimensional code is used as a unique identifier of the server and also used as a reference object for positioning the server in the acquired detection image, the pasted two-dimensional code has a set side length, and four sides of the pasted two-dimensional code should be parallel to four sides of the server.

As a further optimization of the method of the present invention, in step S2 of the present invention, the process of accurately positioning the image of the server in the detected image includes:

s201, acquiring actual coordinates of four angles of the two-dimension code in the detection image through a two-dimension code detection recognition library;

s202, calculating theoretical coordinates of four corner points of the undeformed two-dimensional code according to the coordinates of the reference points in the obtained actual coordinates of the two-dimensional code and the height and width of the two-dimensional code;

s203, acquiring an affine transformation matrix of image deformation according to the actual coordinates and the theoretical coordinates of the two-dimensional code;

s104, acquiring the model of the server according to the content of the identified two-dimensional code, acquiring the installation position of the two-dimensional code and theoretical coordinates of four corner points of the server according to the width-height ratio of the two-dimensional code to the server, and accurately positioning the server.

As a further optimization of the method, the two-dimensional code is pasted on one corner point of the server, and two adjacent edges of the two-dimensional code are flush with the edge of the server.

As a further optimization of the method of the present invention, in step S3 of the present invention, the region of interest of the server is obtained according to the model of the server obtained by identifying the two-dimensional code.

The invention also provides a data center server state detection system, which comprises a server image acquisition module, a server positioning module and a state discrimination module, wherein:

the server image acquisition module is used for acquiring a detection image containing a server;

the server positioning module is used for extracting an image of the server from the acquired detection image;

the state discrimination module is used for blocking the extracted image of the server, matching the template of the image block containing the interest, acquiring the matching result and obtaining the current state of the server.

As a further optimization of the system of the invention, the server is pasted with the two-dimensional code, and the two-dimensional code is pasted on a set position of the server, the two-dimensional code is used as a unique identifier of the server and also used as a reference for positioning the server in the acquired detection image, the pasted two-dimensional code has a set side length, and four sides of the pasted two-dimensional code should be parallel to four sides of the server.

As a further optimization of the system of the present invention, the server image acquisition module of the present invention includes a two-dimensional code recognition library and a mapping relation calculation module, wherein:

the two-dimension code recognition library is used for acquiring actual coordinates of four angles of the two-dimension code in the detection image, and calculating theoretical coordinates of four corner points of the undeformed two-dimension code according to the coordinates of the reference points in the actual coordinates and the height and width of the two-dimension code;

and the mapping shutdown calculation module is used for acquiring an affine transformation matrix of an image phenotype according to the actual coordinates and the theoretical coordinates of the two-dimensional code, and determining the boundary of the server image according to the position relation between the server and the two-dimensional code.

As a further optimization of the system, the state discrimination module is used for determining the region of interest of the server according to the model of the server identified by the two-dimensional code identification library.

The invention has the following advantages:

1. according to the invention, the server image is positioned from the detection image, the server image is blocked, the image block related to the interesting area of the server is extracted for template comparison, the detection effect is ensured, meanwhile, useless image area calculation is eliminated, the calculation amount is greatly reduced, and the matching speed is accelerated;

2. the two-dimensional code is used as the reference for image positioning of the server, the two-dimensional code is not only used as the unique identifier of the server to record the information of the server, but also can be used as the positioning of the server image through the definition of the size and the position, so that the positioning of the server image is more accurate.

Drawings

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

The invention is further described below with reference to the accompanying drawings:

FIG. 1 is a schematic image of a server in a detection image;

FIG. 2 is a schematic diagram of a theoretical image of a server;

fig. 3 is a schematic diagram of image blocking of a server.

Detailed Description

The present invention is further described in the following with reference to the drawings and the specific embodiments so that those skilled in the art can better understand the present invention and can implement the present invention, but the embodiments are not to be construed as limiting the present invention, and the embodiments and the technical features of the embodiments can be combined with each other without conflict.

It is to be understood that the terms first, second, and the like in the description of the embodiments of the invention are used for distinguishing between the descriptions and not necessarily for describing a sequential or chronological order. The "plurality" in the embodiment of the present invention means two or more.

The term "and/or" in the embodiment of the present invention is only an association relationship describing an associated object, and indicates that three relationships may exist, for example, a and/or B may indicate: a exists alone, B exists alone, and A and B exist at the same time. In addition, the character "/" herein generally indicates that the former and latter associated objects are in an "or" relationship.

A method for detecting the state of a server in a data center is disclosed, wherein the front view of the server is shown in FIG. 2, but in the process of inspection by an inspection robot, a shot image is shown in FIG. 1 and can be deformed to a certain extent, the detection method provided by the embodiment corrects the deviation of the deformed image of the server and then detects the state, and the method specifically comprises the following steps:

s1, collecting a detection image for the server;

the equipment for collecting the detection image for the server comprises one or the centralized combination of a camera, a video camera and electronic equipment with a photographing or video recording function;

the size of the shooting range in the acquired image can include other components except the server or more than one server, so that the image of the server needs to be positioned and extracted in subsequent processing;

s2, accurately positioning the image of the server in the detection image;

in this embodiment, an image of a server is located by a method for locating a reference object, the reference object is a two-dimensional code, the two-dimensional code is pasted on a specific position of the server, for more convenient calculation, the two-dimensional code is preferentially pasted on one corner of the server, which corner can be specifically set according to a shooting direction of the inspection robot, if the inspection robot shoots from the left side of the server, the two-dimensional code can be set at the upper left corner of the server, the two-dimensional code is flush with the adjacent edge of the server, the two-dimensional code serves as a unique identifier of the server, and also serves as a reference object for locating the server in a collected detection image, the pasted two-dimensional code is a set edge length, and four edges of the pasted two-dimensional code should be parallel to four edges of the server; the process of accurately positioning the image of the server in the detection image by adopting the two-dimensional code positioning comprises the following steps:

s101, acquiring actual coordinates of four angles of the two-dimensional code in the detection image through a two-dimensional code detection recognition library;

s102, according to the coordinates of a reference point in the obtained actual coordinates of the two-dimensional code and the height and width of the two-dimensional code, wherein the reference point is an undeformed point and is related to the shooting direction of the inspection robot, as shown in the shooting direction of FIG. 1, the reference point is a left-top point, and theoretical coordinates of four corner points of the undeformed two-dimensional code need to be calculated;

s103, acquiring an affine transformation matrix of image deformation according to the actual coordinates and the theoretical coordinates of the two-dimensional code;

s104, acquiring the model of the server according to the content of the identified two-dimensional code, acquiring the installation position of the two-dimensional code and theoretical coordinates of four corner points of the server according to the width-height ratio of the two-dimensional code to the server, and accurately positioning the server.

S3, blocking the located server image, as shown in fig. 2, and obtaining an area of interest representing the server according to the model of the server obtained by the identified two-dimensional code, performing template matching on the image block including the area of interest, and determining the current state of the server according to the matching result. As shown in fig. 2, if the region of interest of the server is distributed within the a1 tiles and the a2 tiles, the current state of the server can be determined by the comparison result by extracting the a1 and a2 tiles to compare with the template.

The embodiment further provides a data center server state detection system for implementing the method, which includes a server image acquisition module, a server positioning module and a state discrimination module, wherein:

the server image acquisition module is used for acquiring a detection image containing a server;

the server positioning module is used for extracting an image of the server from the acquired detection image;

the state discrimination module is used for blocking the extracted image of the server, matching the template of the image block containing the interest, acquiring the matching result and obtaining the current state of the server.

In this embodiment, an image of a server is located by a method for locating a reference object, the reference object is a two-dimensional code, the two-dimensional code is pasted at a specific position of the server, for more convenient calculation, the two-dimensional code is preferentially pasted at one corner of the server, which corner can be specifically set according to a shooting direction of the inspection robot, if the inspection robot shoots from the left side of the server, the two-dimensional code can be set at the upper left corner of the server, the two-dimensional code is flush with the adjacent edge of the server, the two-dimensional code serves as a unique identifier of the server, and also serves as a reference object for locating the server in a collected detection image, the pasted two-dimensional code is a set edge length, and four edges of the pasted two-dimensional code should be parallel to four edges of the server. Therefore, the server image acquisition module comprises a two-dimensional code recognition library and a mapping relation calculation module, wherein:

the two-dimension code recognition library is used for acquiring actual coordinates of four angles of the two-dimension code in the detection image, and calculating theoretical coordinates of four corner points of the undeformed two-dimension code according to the coordinates of the reference points in the actual coordinates and the height and width of the two-dimension code;

and the mapping shutdown calculation module is used for acquiring an affine transformation matrix of an image phenotype according to the actual coordinates and the theoretical coordinates of the two-dimensional code, and determining the boundary of the server image according to the position relation between the server and the two-dimensional code.

The state discrimination module is configured to determine an area of interest of the server according to the model of the server identified by the two-dimensional code identification library.

The above-mentioned embodiments are merely preferred embodiments for fully illustrating the present invention, and the scope of the present invention is not limited thereto. The equivalent substitution or change made by the technical personnel in the technical field on the basis of the invention is all within the protection scope of the invention. The protection scope of the invention is subject to the claims.