WO2019128366A1

WO2019128366A1 - Test sample notch positioning method and device

Info

Publication number: WO2019128366A1
Application number: PCT/CN2018/109073
Authority: WO
Inventors: 孙茂杰; 李福存; 苏循亮; 周鼎
Original assignee: 江苏金恒信息科技股份有限公司
Priority date: 2017-12-29
Filing date: 2018-09-30
Publication date: 2019-07-04
Also published as: CN108460798A; DE112018000224B4; DE112018000224T5

Abstract

The embodiments of the present invention propose a test sample notch positioning method and device, relating to the field of automation in the steel industry. The method and device determine a photographing parameter according to a received test sample cooling temperature, acquire a sample image to be processed acquired by an image acquisition device in the photographing parameter state, then filter said sample image to acquire key test sample image information, and finally acquire positional information concerning a test sample notch on the basis of a plurality of pre-established image recognition models and the key test sample image information. As different test sample cooling temperatures affect photographing results differently, there is always a suitable photographing parameter corresponding to each cooling temperature, so that said acquired sample image is always in a relatively clear state for facilitating subsequent operations such as background separation and test sample notch positioning, improving both the efficiency of acquiring the positional information concerning the test sample notch and the accuracy of the positional information.

Description

Sample slot positioning method and device

Technical field

The invention relates to the field of automation of the steel industry, and in particular to a method and a device for positioning a sample slot.

Background technique

With the development of economy and technology, the use of automation equipment in the steel industry is more and more extensive. When testing the material properties of steel samples, it is necessary to locate the sample notches, and then take them out to the corresponding positions for testing.

However, in the prior art, the cooling temperature range of the sample is large, ranging from -193 ° C to 20 ° C; and when the cooling temperature of the sample is less than or equal to -60 ° C, a large amount of mist may be generated to cause unclear imaging, and at the same time The brightness will be significantly lower than that at 20 °C, causing the imaging to change, causing great interference with the positioning of the sample notch, resulting in inaccurate final positioning.

Summary of the invention

In view of the above, an object of the present invention is to provide a sample notch positioning method and apparatus to solve the above problems.

In order to achieve the above object, the technical solution adopted by the embodiment of the present invention is as follows:

In a first aspect, an embodiment of the present invention provides a method for positioning a sample slot.

The sample slot positioning method includes:

The shooting parameter is determined based on the received sample cooling temperature;

Receiving an image of the sample to be processed sent by an image acquisition device in a state of the shooting parameter;

Performing filtering processing on the image of the sample to be processed to obtain image information of the key sample;

The specific position information of the sample slot is obtained based on the pre-established image recognition model and the key sample image information.

In a second aspect, the embodiment of the present invention further provides a sample slot positioning device, where the sample slot positioning device includes:

a photographing parameter determining unit, configured to determine a photographing parameter based on the received sample cooling temperature;

a receiving unit, configured to receive an image of a sample to be processed collected by an image capturing device in a state of the shooting parameter;

a filtering unit, configured to perform filtering processing on the image of the sample to be processed to obtain image information of the key sample;

The location information acquiring unit is configured to acquire specific location information of the sample slot based on the plurality of pre-established image recognition models and the key sample image information.

The sample notch positioning method and device provided by the embodiment of the invention determine a shooting parameter according to the received sample cooling temperature, and acquire an image of the sample to be processed collected by an image collecting device in the state of the shooting parameter, and then treat Processing the sample image for filtering processing to obtain the image information of the key sample, and finally obtaining the position information of the sample slot based on the plurality of pre-established image recognition models and the image information of the key sample; since the cooling temperature of the different samples has a shooting result Different degrees of influence, so there is a corresponding suitable shooting parameter corresponding to each cooling temperature, so that the image of the sample to be processed is always in a relatively clear state, which is convenient for subsequent background separation, sample slot positioning, etc. The operation not only improves the efficiency of obtaining the position information of the sample notch, but also increases the accuracy of the position information.

The above described objects, features and advantages of the present invention will become more apparent from the description of the appended claims.

DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments will be briefly described below. It should be understood that the following drawings show only certain embodiments of the present invention, and therefore It should be seen as a limitation on the scope, and those skilled in the art can obtain other related drawings according to these drawings without any creative work.

FIG. 1 is a functional block diagram of a server provided by an embodiment of the present invention.

2 is a flow chart showing a method for positioning a sample slot provided by an embodiment of the present invention;

FIG. 3 shows a specific flowchart of step S203 in FIG. 2;

Figure 4 shows a specific flow chart of sub-step S2031 in Figure 3;

FIG. 5 shows a specific flowchart of step S204 in FIG. 2;

FIG. 6 is a functional block diagram of a sample slot positioning device according to a preferred embodiment of the present invention.

Icon: 100-server; 111-memory; 112-processor; 113-communication unit; 200-sample slot positioning device; 210-shooting parameter determining unit; 220-receiving unit; 230-filtering unit; 240-position information Acquisition unit; 250-transport unit.

Detailed ways

The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of the embodiments of the invention, which are generally described and illustrated in the figures herein, may be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the invention in the claims All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

It should be noted that similar reference numerals and letters indicate similar items in the following figures, and therefore, once an item is defined in a drawing, it is not necessary to further define and explain it in the subsequent drawings. Also, in the description of the present invention, the terms "first", "second", and the like are used merely to distinguish a description, and are not to be construed as indicating or implying a relative importance.

Please refer to FIG. 1. FIG. 1 shows a functional block diagram of a server 100 that can be applied to an embodiment of the present invention. The sample slot positioning device 200, the memory 111, one or more (only one shown) processor 112, and communication unit 113 are included. These components communicate with one another via one or more communication bus/signal lines. The sample slot locating device 200 includes at least one software functional unit that can be stored in the memory 111 or in an operating system (OS) of the server 100 in the form of software or firmware.

The memory 111 can be used to store software programs and units, such as program instructions/units corresponding to the software testing apparatus and method in the embodiment of the present invention, and the processor 112 operates the software of the sample slot positioning device 200 stored in the memory 111. The program and the unit, thereby performing various function applications and data processing, such as the sample notch positioning method provided by the embodiment of the present invention. The memory 111 can be, but not limited to, a random access memory (RAM), a read only memory (ROM), and a programmable read-only memory (PROM). Erasable Programmable Read-Only Memory (EPROM), Electric Erasable Programmable Read-Only Memory (EEPROM), and the like. Access to the memory 111 by the processor 112 and other possible components can be performed under the control of the memory controller.

The communication unit 113 is configured to establish a communication connection between the server 100 and other communication terminals through the network, and is used to send and receive data through the network.

It should be understood that the structure shown in FIG. 1 is merely illustrative, and the server 100 may further include more or less components than those shown in FIG. 1, or have a different configuration than that shown in FIG. The components shown in Figure 1 can be implemented in hardware, software, or a combination thereof.

First embodiment

The invention provides a sample notch positioning method for positioning a notch position of a steel sample during an impact test on a steel sample. Please refer to FIG. 2 , which is a flowchart of a method for positioning a sample slot according to an embodiment of the present invention. The sample slot positioning method includes:

Step S201: Determine a shooting parameter based on the received sample cooling temperature.

Since when the cooling temperature of the sample is too low, for example, -80 ° C, a large amount of mist is generated around the sample, which will seriously affect the imaging result of the sample, so that the final imaging result is very unclear. This not only causes a large disturbance to the separation of the background and the sample in the imaging result, but also causes a deviation in the positioning of the notch in the sample.

Therefore, by adjusting the photographing parameters of the image pickup device according to the sample cooling temperature of the sample, the imaging result of the finally obtained sample can be prevented from being largely changed due to the change in the cooling temperature.

It can be understood that the shooting parameters include, but are not limited to, shutter, aperture, ISO, EV value, setting parameters of whether or not the flash is turned on.

Step S202: Receive an image of the sample to be processed sent by an image acquisition device in the state of the shooting parameter.

It can be understood that the image of the sample to be processed collected by an image capturing device in the state of the shooting parameter is clear, easy to identify and analyzed.

Step S203: Filtering the sample image to be processed to obtain key sample image information.

The background image and the sample portion are included in the image of the sample to be processed. It can be understood that the sample part is the image information of the sample itself, and can reflect its structure, connection relationship and the like. The background part includes the environmental information of the sample, which will cause some interference to the analysis of the sample notch; therefore, the image of the sample to be processed needs to be filtered, and the background part of the image of the sample to be processed is given. After filtering out, the image information of the key sample is obtained.

Please refer to FIG. 3, which is a specific flowchart of step S203. Step S203 includes:

Sub-step S2031: Acquire gray-scale histogram information of the sample image to be processed.

Generally, the difference between the background portion and the sample portion is large, so that the gray histogram information of the image of the sample to be processed can be first obtained, and the background portion and the sample portion are distinguished by the gray histogram information.

Please refer to FIG. 4, which is a specific flowchart of sub-step S2031. Sub-step S2031 includes:

Sub-step S20311: Obtain a line of distinction between the sample and the background in the image of the sample to be processed.

It can be understood that the sample has a certain shape and contour; therefore, the line distinguishing the sample from the background is the contour line of the sample itself, and the dividing line divides the image of the sample to be processed into the sample portion and the background portion.

Sub-step S20312: dividing the image of the sample to be processed into a plurality of regions along the dividing line.

Since there is usually alcohol adhesion at the position of the sample slot, the difference between the sample notch and the background is small, and the gray value is similar to the background, only by obtaining the gray value of a certain area as the gray of the image of the sample to be processed. The histogram information will cause a large error to the final key sample image information. Therefore, the image of the sample to be processed is first divided into multiple regions along the dividing line, and then the analysis of each region can be used to reduce the key test. The error of the image information.

Sub-step S20313: Acquire a gray histogram and a gray histogram mean for each region.

By acquiring the gray histogram and the gray histogram mean of each region, it is convenient for the server 100 to acquire the contrast of the gray value of the background portion and the sample portion of each region.

Sub-step S20314: The gray histogram having the smallest gray histogram mean is used as the gray histogram information of the sample image to be processed.

The area with the smallest mean value of the gray histogram has the smallest contrast between the sample and the background. By using the gray histogram as the gray histogram information of the sample image to be processed, the gray histogram information of the sample image to be processed can be made. Has the greatest recognition accuracy.

It can be understood that when the server 100 can recognize the sample and the background at the minimum contrast area, it is naturally also possible to identify the sample and the background at other areas, thereby distinguishing the background portion of the image to be processed from the sample portion. .

Sub-step S2032: Filtering background information contained in the image of the sample to be processed based on the grayscale histogram information to obtain key sample image information.

Step S204: Acquire specific position information of the sample slot based on the pre-established image recognition model and the key sample image information.

In a preferred embodiment, in order to avoid inaccuracies in the position information obtained during the acquisition of the position information of the sample slot, the server 100 uses a plurality of pre-established image recognition models to perform the sample slot. Positioning. It should be noted that a plurality of pre-established image recognition models are different; generally, one model corresponds to a feature of the sample slot, and a better anti-interference effect can be achieved. At this time, step S204 should be replaced with: acquiring specific position information of the sample slot based on the plurality of pre-established image recognition models and the key sample image information. Please refer to FIG. 5, which is a specific flowchart of step S204. Step S204 includes:

Sub-step S2041: Acquiring a plurality of preliminary position information of the sample slot in the key sample image information based on each of the templates.

It can be understood that, in the case of undisturbed, a plurality of preliminary position information should be within the error range.

Sub-step S2042: Integrating a plurality of preliminary location information to obtain the location information.

For example, when there is a large interference, the server 100 may reject the larger error in the plurality of preliminary position information, and determine the true position information of the sample slot from the remaining preliminary position information.

In a preferred embodiment, the specific location information is image coordinates.

Step S205: transmitting the position information to an impact robot.

By transmitting the position information to the impact robot, the impact robot can know the position of the sample in real time, and it is convenient for the impact robot to perform the impact test.

Second embodiment

Please refer to FIG. 6. FIG. 6 is a functional block diagram of a sample slot positioning device 200 according to a preferred embodiment of the present invention. It should be noted that the basic principle and the technical effects of the sample notch positioning device 200 provided in this embodiment are the same as those of the above embodiment, and are briefly described. Corresponding content in the embodiment. The sample notch positioning device 200 includes a shooting parameter determining unit 210, a receiving unit 220, a filtering unit 230, a position information acquiring unit 240, and a transmitting unit 250.

The shooting parameter determining unit 210 is configured to determine a shooting parameter based on the received sample cooling temperature.

In a preferred embodiment, it can be understood that the shooting parameter determining unit 210 can be used to perform step S201.

The receiving unit 220 is configured to receive the collected sample image to be processed sent by an image capturing device in the state of the shooting parameter.

In a preferred embodiment, it can be understood that the receiving unit 220 can be used to perform step S202.

The filtering unit 230 is configured to perform a filtering process on the sample image to be processed to obtain key sample image information.

Specifically, the filtering unit 230 is configured to acquire grayscale histogram information of a background of the image to be processed.

The filtering unit 230 is configured to acquire the distinguishing line between the sample and the background in the image acquisition of the sample to be processed; the filtering unit 230 is further configured to divide the image of the sample to be processed into multiple regions along the dividing line; The filtering unit 230 is further configured to acquire a gray histogram and a gray histogram mean of each of the regions; the filtering unit 230 is further configured to use a gray histogram having a minimum gray histogram mean as the sample to be processed Grayscale histogram information for the image.

The filtering unit 230 is further configured to filter background information included in the image to be processed based on the grayscale histogram information to obtain key sample image information.

In a preferred embodiment, it can be understood that the filtering unit 230 can be used to perform step S203, sub-step S2031, sub-step S2032, sub-step S20311, sub-step S20312, sub-step S20313, and sub-step S20314.

The location information acquisition unit 240 is configured to acquire location information of the sample slot based on the pre-established image recognition model and the focused sample image information.

In a preferred embodiment, the location information acquiring unit 240 is further configured to acquire specific location information of the sample slot based on the plurality of pre-established image recognition models and the focused sample image information.

In a preferred embodiment, it can be understood that the location information obtaining unit 240 can be used to perform step S204, sub-step S2041, and sub-step S2042.

The transmission unit 250 is for transmitting position information to an impact robot.

In a preferred embodiment, it can be understood that the transmission unit 250 can be used to perform step S205.

In summary, the method and device for positioning a sample slot provided by an embodiment of the present invention, the received sample cooling temperature determines a shooting parameter, and acquires a sample to be processed collected by an image capturing device in the state of the shooting parameter. Image, then processing the sample image to perform filtering processing to obtain key sample image information, and finally obtaining position information of the sample notch based on a plurality of pre-established image recognition models and key sample image information; due to different sample cooling temperatures The shooting results have different degrees of influence, so there is a corresponding suitable shooting parameter at each cooling temperature, so that the image of the sample to be processed is always in a relatively clear state, which is convenient for subsequent background separation and sample The operation of notch positioning and the like not only improves the efficiency of obtaining the position information of the sample notch, but also increases the accuracy of the position information.

It should be noted that, in this context, relational terms such as first and second are used merely to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply such entities or operations. There is any such actual relationship or order between them. Furthermore, the term "comprises" or "comprises" or "comprises" or any other variations thereof is intended to encompass a non-exclusive inclusion, such that a process, method, article, or device that comprises a plurality of elements includes not only those elements but also Other elements, or elements that are inherent to such a process, method, item, or device. An element that is defined by the phrase "comprising a ..." does not exclude the presence of additional equivalent elements in the process, method, item, or device that comprises the element.

The above description is only the preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes can be made to the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and scope of the invention are intended to be included within the scope of the invention. It should be noted that similar reference numerals and letters indicate similar items in the following figures, and therefore, once an item is defined in a drawing, it is not necessary to further define and explain it in the subsequent drawings.

Claims

A sample notch positioning method, wherein the sample notch positioning method comprises:

The shooting parameter is determined based on the received sample cooling temperature;

Receiving an image of the sample to be processed sent by an image acquisition device in a state of the shooting parameter;

Performing filtering processing on the image of the sample to be processed to obtain image information of the key sample;

The specific position information of the sample slot is obtained based on the pre-established image recognition model and the key sample image information.
The sample notch positioning method according to claim 1, wherein the step of filtering the image of the sample to be processed to obtain image information of the key sample comprises:

Obtaining grayscale histogram information of the image of the sample to be processed;

And extracting background information included in the image to be processed based on the grayscale histogram information to acquire the key sample image information.
The sample notch positioning method according to claim 2, wherein the step of acquiring grayscale histogram information of the image of the sample to be processed comprises:

Obtaining a distinction line between the sample and the background in the image of the sample to be processed;

Dividing the image of the sample to be processed into a plurality of regions along the distinguishing line;

Obtaining a gray histogram and a gray histogram mean value of each of the regions;

A gray histogram having the smallest gray histogram mean is used as the gray histogram information of the sample image to be processed.
The sample notch positioning method according to claim 1, wherein the step of acquiring the specific position information of the sample slot based on the pre-established image recognition model and the key sample image information further comprises:

The specific position information of the sample slot is obtained based on the plurality of pre-established image recognition models and the key sample image information.
The sample notch positioning method according to claim 4, wherein the step of acquiring position information of the sample slot based on the plurality of pre-established image recognition models and the key sample image information comprises:

Acquiring a plurality of preliminary position information of the sample slot in the image information of the key sample based on each of the image recognition models;

The plurality of the preliminary location information is integrated to obtain the specific location information.
A sample notch positioning device, wherein the sample notch positioning device comprises:

a photographing parameter determining unit, configured to determine a photographing parameter based on the received sample cooling temperature;

a receiving unit, configured to receive an image of a sample to be processed collected by an image capturing device in a state of the shooting parameter;

a filtering unit, configured to perform filtering processing on the image of the sample to be processed to obtain image information of the key sample;

The location information acquiring unit is configured to acquire specific location information of the sample slot based on the plurality of pre-established image recognition models and the key sample image information.
The sample notch positioning device according to claim 6, wherein the filtering unit is further configured to acquire grayscale histogram information of a background of the image of the sample to be processed;

The filtering unit is further configured to filter background information included in the image to be processed based on the grayscale histogram information to obtain the key sample image information.
The sample notch positioning device according to claim 7, wherein the filtering unit is further configured to acquire a distinguishing line between the sample and the background in the image acquisition of the sample to be processed;

The filtering unit is further configured to divide the image of the sample to be processed into a plurality of regions along the distinguishing line;

The filtering unit is further configured to obtain a gray histogram mean value of each of the regions;

The filtering unit is further configured to use the smallest grayscale histogram mean as the grayscale histogram information of the background.
The sample slot positioning device according to claim 6, wherein the position information acquiring unit is further configured to acquire a sample slot based on the plurality of pre-established image recognition models and the key sample image information. Specific location information.
The sample notch positioning device according to claim 9, wherein the position information acquiring unit is further configured to acquire a plurality of preliminary samples of the sample notch in the image information of the key sample based on each of the image recognition models. location information;

The location information acquiring unit is further configured to integrate the plurality of the preliminary location information to obtain the specific location information.