Method and device for positioning material area and computer readable storage medium

Abstract

The embodiment of the invention provides a method and device for positioning a material area and a computer readable storage medium. The method can comprise the following steps: acquiring a region image collected for a to-be-positioned target region of a thin film material; region feature information is extracted from the region image, and the region feature information is used for representing a group of region feature points in the region image; position information of the target area in the thin film material is determined on the basis of the area feature information and predetermined material feature information, the material feature information is used for representing a set of material feature points in a material image, and the material image is collected under the condition that the thin film material is unfolded on a two-dimensional plane.

Description

Technical Field

[0001] The present disclosure relates to the field of material detection, and in particular, to a method, an apparatus, and a computer-readable storage medium for locating a material region. Background Art

[0002] Thin film materials are usually processed through one or more processes. At present, in order to record relevant data of thin film materials during processing (for example, equipment status during processing, material quality, etc.), some positions are usually marked in the thin film materials, and these positions are associated with corresponding processing data, so that the corresponding processing data can be obtained according to the marked positions when needed.

[0003] For example, currently, laser coding is usually used to mark readable codes, such as QR codes or bar codes, at fixed intervals on the blank or non-functional parts of the film material. In this way, when the processing data of a certain position needs to be known in the subsequent process, the readable code at that position can be read by a code reader. Although this method can achieve the recording of processing data to a certain extent, this coding method is usually costly, and coding the material may affect the quality of the material. Therefore, it is desirable to improve the method of locating the area of ​​the film material. Summary of the invention

[0004] In view of the above needs, embodiments of the present disclosure provide a method, an apparatus, and a computer-readable storage medium for locating a material region.

[0005] On the one hand, an embodiment of the present disclosure provides a method for locating a material area, comprising: obtaining a regional image captured of a target area to be located of a thin film material; extracting regional feature information from the regional image, wherein the regional feature information is used to represent a set of regional feature points in the regional image; based on the regional feature information and predetermined material feature information, determining position information of the target area in the thin film material, wherein the material feature information is used to represent a set of material feature points in a material image, and the material image is captured when the thin film material is unfolded on a two-dimensional plane.

[0006] On the other hand, an embodiment of the present disclosure provides a method for determining material feature information used in the above method, the method comprising: acquiring a material image of a thin film material, wherein the material image is collected when the thin film material is unfolded on a two-dimensional plane; extracting material feature information from the material image, wherein the material feature information is used to represent a set of material feature points in the material image.

[0007] On the other hand, an embodiment of the present disclosure provides a device for locating a material area, comprising: at least one processor; a memory that communicates with the at least one processor and has executable code stored thereon, wherein the executable code, when executed by the at least one processor, causes the at least one processor to execute the above method.

[0008] On the other hand, an embodiment of the present disclosure provides a computer-readable storage medium storing executable codes, which, when executed, enable a computer to perform the above method. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The above and other objects, features and advantages of embodiments of the present disclosure will become more apparent through a more detailed description of embodiments of the present disclosure in conjunction with the accompanying drawings, wherein like reference numerals generally represent like elements throughout the various drawings.

[0010] Figure 1 is a schematic flow chart of a method for locating a material region according to some embodiments.

[0011] Figures 2A to 2C Various examples of target areas to be located are shown.

[0012] Figures 3A to 3C Various examples of candidate regions are shown.

[0013] Figure 4 is a schematic flow chart of a method for determining material characteristic information according to some embodiments.

[0014] Figure 5 is a schematic block diagram of an apparatus for locating a material region according to some embodiments.

[0015] Figure 6 is a schematic block diagram of an apparatus for determining material characteristic information according to some embodiments.

[0016] Figure 7 is a schematic block diagram of an apparatus for locating a material region according to some embodiments.

[0017] Figure 8 is a schematic block diagram of an apparatus for determining material characteristic information according to some embodiments. DETAILED DESCRIPTION

[0018] The subject matter described herein will now be discussed with reference to various embodiments. It should be understood that the discussion of these embodiments is only to enable those skilled in the art to better understand and implement the subject matter described herein, and is not intended to limit the scope of protection, applicability or examples set forth in the claims. The functions and arrangements of the elements discussed may be changed without departing from the scope of protection of the claims. Various embodiments may omit, replace or add various processes or components as needed.

[0019] As used herein, the term "including" and its variations may represent open terms, which may mean "including but not limited to". The term "based on" may mean "based at least in part on". The terms "first", "second", etc. may refer to different or the same objects.

[0020] At present, in the processing of thin film materials, in order to record processing data (for example, equipment status during processing, material quality, test indicators, etc.), readable codes are usually marked at fixed positions (for example, every 30 cm) in the blank or non-functional part of the thin film material by coding in the front process, and each position is associated with the corresponding processing data. In this way, if the processing data of a certain position of the material needs to be obtained in the back process, the readable code at the position can be read by the code reader, and the corresponding processing data can be obtained.

[0021] However, the length of the film material is usually long (e.g., 3 kilometers), so coding at fixed intervals usually has a high processing cost. In addition, although coding is usually performed in the blank or non-functional part of the film material, it may still cause some damage to the material itself and even affect the quality of the material.

[0022] In view of this, the embodiments of the present disclosure provide a technical solution for locating a material area. In addition, the embodiments of the present disclosure can be applied to a variety of thin film materials. For example, the embodiments of the present disclosure can be applied to scenarios such as the battery industry where it is impossible or difficult to code or etch thin film materials (for example, it is difficult to code or etch due to reasons such as low strength and low thickness of the thin film material). The following will be described in conjunction with specific embodiments.

[0023] Figure 1 is a schematic flow chart of a method for locating a material region according to some embodiments.

[0024] like Figure 1 As shown, in step 102, a regional image collected for a target region to be positioned of a thin film material may be acquired.

[0025] In step 104, regional feature information may be extracted from the regional image. The regional feature information may be used to represent a group of regional feature points in the regional image.

[0026] In step 106, the position information of the target area in the film material can be determined based on the region characteristic information and the predetermined material characteristic information. The material characteristic information can be used to represent a set of material characteristic points in the material image. The material image can be collected when the film material is unfolded on a two-dimensional plane.

[0027] In the embodiments of the present disclosure, the position information of the target area in the film material is determined based on the regional feature information in the regional image of the target area to be located and the material feature information in the material image of the film material. It can be seen that the technical solution provided by the embodiments of the present disclosure is essentially to locate the designated area of ​​the film material based on the image texture features of the film material, without the need to calibrate the position of the film material through physical processing, which can not only greatly reduce the processing cost, but also avoid affecting the quality of the film material.

[0028] In an embodiment of the present disclosure, the material characteristic information may be predetermined. For example, the material characteristic information may be Figure 1 The material characteristics of the thin film material can be determined before the process begins. For example, before each process of processing the thin film material, the material image of the thin film material can be collected, and then the corresponding material characteristic information can be determined and stored. In this way, when it is necessary to locate the target area, the stored material characteristic information can be obtained. For another example, suppose Figure 1 The process is in the current process, and the material image of the thin film material can be collected before the current process starts or after the previous process of the current process ends, and then the material characteristic information is determined and stored. The timing of determining the material characteristic information can be determined according to actual application requirements, etc., and this article does not limit this.

[0029] The material image can be collected in various applicable ways. For example, the material image can be collected using various applicable cameras such as a line scan camera or an array camera. For example, in some embodiments, the unfolded film material can be photographed by a line scan camera to obtain a material image. For example, two rollers can be used to roll up the film material, and a line scan camera is set between the two rollers to photograph the film material. In this case, during the imaging process of the film material, the relative positions of the camera and the film material are consistent. Regardless of which camera is used to collect the material image, it is generally required that the physical size of the film material corresponding to each pixel in the collected material image is known (such as accurately known or within a certain error range). In some implementations, after using an appropriate camera (such as a line scan camera or an array camera, etc.) to collect the material image, a camera calibration technology can be used so that the physical size of the film material corresponding to each pixel in the collected material image is known. In some implementations, the camera calibration technology may not be used. For example, the camera can be set to a known and consistent position relative to the film material, so that the physical size of the film material corresponding to each pixel is calculated based on the position of the camera. In this case, there may be a certain error (such as related to the accuracy of the position where the camera is set).

[0030] The material image mentioned in this article can be a single image or composed of several smaller images. The specific form is not limited in this article. In addition, the material image mentioned in this article can at least include the functional part of the film material.

[0031] Generally, various applicable algorithms can be used to extract material feature information from a material image. Specifically, a set of feature points and related information can be extracted from a material image. For ease of description, the feature points extracted from a material image are referred to as material feature points in this article, and the information used to describe these feature points is referred to as material feature information in this article. Generally, various applicable algorithms can be used to extract material feature information, such as Scale-Invariant Feature Transform (SIFT), Oriented FAST and Rotated BRIEF (ORB) and other algorithms.

[0032] In the embodiments of the present disclosure, the regional image may also be collected in various applicable ways. Similarly, the regional image may also be collected using various applicable cameras such as a line scan camera or an area array camera. Similar to the situation described above with respect to the material image, the correspondence between each pixel in the regional image and the physical size of the film material is known (e.g., accurate or within a certain error range). This correspondence is usually consistent for the material image and the regional image.

[0033] It can be understood that, since the correspondence between each pixel in these images and the physical size of the film material is known, in the embodiments of the present disclosure, the position of the target area in the film material can be determined based on the material image and the area image.

[0034] In addition, the target area to be located can have various shapes, such as rectangle, ellipse, circle, irregular shape, etc., which is not limited in this article. The regional image can be collected in combination with the shape and size of the target area. For example, the regional image can include part or all of the target area, or even be larger than the target area, which can be determined according to factors such as actual application requirements.

[0035] For example, in the case where the target area is rectangular, if the width of the target area is the same as the width of the film material and the length of the target area is less than the length of the film material, it can be understood that when locating the target area, the position of the target area in the length direction of the film material is actually located. In this case, the regional image can be acquired for the entire length and a part of the width of the target area, or for the entire length and the entire width of the target area.

[0036] For another example, in the case where the target area is rectangular, if the length of the target area is the same as the length of the film material and the width of the target area is smaller than the width of the film material, it can be understood that when locating the target area, the position of the target area in the width direction of the film material is actually located. In this case, the regional image can be acquired for a portion of the length and the entire width of the target area, or for the entire length and the entire width of the target area.

[0037] For another example, when the target area is a rectangle, if the length and width of the target area are respectively smaller than the length and width of the film material, then it can be understood that when positioning the target area, it is usually necessary to locate the position of the target area in the length and width directions of the film material. Therefore, the regional image can be collected for the entire length and width of the target area.

[0038] For ease of understanding, Figures 2A to 2C Various examples of target areas to be located are shown. Figures 2A to 2C In , it is assumed that 200 represents at least a portion of the thin film material. Figure 2A In the example of FIG. 2 , it is assumed that the width of the target area 202 to be located is equal to the width of the film material, but the length is less than the length of the film material. Figure 2B In the example of FIG. 2 , it is assumed that the length and width of the target area 204 to be located are both smaller than the length and width of the film material. Figure 2C In the example, it is assumed that the length of the target area 206 to be located is equal to the length of the film material, but the width is less than the width of the film material. As described above, the corresponding regional images can be collected for various target areas according to the size of the target area and factors such as actual needs.

[0039] In some embodiments, in step 102, regional feature information may be extracted from the regional image, for example, a set of feature points and related information may be extracted from the regional image. For ease of description, these feature points are referred to herein as regional feature points, and information used to describe these feature points is referred to herein as regional feature information. In addition, it is understood that the algorithm used to determine the regional feature information may be the same as the algorithm used to determine the material feature information.

[0040] In some embodiments, in step 106, at least one nearest neighbor feature point corresponding to each region feature point may be identified in a group of material feature points, so that a group of nearest neighbor feature points corresponding to a group of region feature points may be obtained. Then, the position information of the target region in the film material may be determined based on the group of nearest neighbor feature points.

[0041] In some embodiments, the regional feature information may include the position and feature vector of each regional feature point. The material feature information may include the position and feature vector of each material feature point. In this way, the distance between each regional feature point and each material feature point may be determined based on the position and feature vector of each regional feature point and the position and feature vector of each material feature point. For example, the distance between feature points may be expressed in various applicable ways, such as Euclidean distance, Hamming distance, etc.

[0042] Based on the distance between each regional feature point and each material feature point, at least one nearest neighbor feature point corresponding to each regional feature point can be identified and determined in a group of material feature points. For example, for each regional feature point, at least one material feature point in front can be selected as at least one nearest neighbor feature point corresponding to the regional feature point in the order of the distance between the regional feature point and each material feature point from small to large. The specific number of nearest neighbor feature points selected for each regional feature point can be pre-set according to actual business needs, etc., and this document does not limit this. For example, the number of nearest neighbor feature points corresponding to each regional feature point can be preset to any positive integer. For example, assuming that the number of nearest neighbor feature points corresponding to each regional feature point is 2, and assuming that there are Z regional feature points, then Z×2 nearest neighbor feature points will be obtained.

[0043] In some embodiments, the material feature information may further include grid information. The grid information may be used to represent a group of grids obtained by dividing the material image. For example, for a material image with a size of 4096×8192 pixels, assuming that the size of each grid is 64×64 pixels, the material image may be divided into 64×128 grids.

[0044] Each grid may have at least one material feature point from a set of material feature points. For example, the number of material feature points in each grid may be greater than a preset threshold, which may improve the accuracy of the location information of the target area. The preset threshold may be determined based on factors such as actual business needs.

[0045] Based on the grid information, the grids to which a group of nearest neighbor feature points belong can be determined. For example, based on the position of the nearest neighbor feature point and the position of the grid, it can be determined which grid the nearest neighbor feature point falls into. For example, assume that the x-axis corresponds to the length direction of the film material and the y-axis corresponds to the width direction of the film material. The position of each material feature point can be represented by an x-coordinate and a y-coordinate, and the nearest neighbor feature point identified from a group of material feature points has an x-coordinate and a y-coordinate accordingly. Each grid actually represents a two-dimensional interval on the x-axis and the y-axis. Therefore, based on this information, it is easy to determine which grid each nearest neighbor feature point belongs to.

[0046] In this way, by determining the grids to which a group of nearest neighbor feature points respectively belong, a group of target grids can be obtained. Based on the group of target grids, the position information of the target area in the film material can be determined.

[0047] For example, a candidate area in a material image can be determined. The candidate area can be formed by a plurality of grids in a set of target grids and have a shape that matches the target area. Specifically, a set of target grids can be projected back into the material image, and at least a portion of the grids may be gathered together to form a certain shape. If the shape matches the shape of the target area, then the grids gathered together can actually roughly represent the location of the target area. It should be understood that the shape matching of the candidate area and the target area mentioned here can refer to being exactly the same or roughly the same. In actual operation, due to factors such as calculation errors, shape matching is generally roughly the same. For example, due to factors such as calculation errors, some grids may be scattered and not gathered together with other grids. This error is usually acceptable and generally does not affect the judgment of the approximate shape. Then, based on the position information of the candidate area in the material image, the position information of the target area in the film material can be determined.

[0048] As to which target grids form the candidate regions, various appropriate methods can be used to distinguish them from a group of target grids. For example, in some embodiments, the heat of each grid in a group of target grids can be determined. The heat of each target grid can have a positive correlation with the number of nearest neighbor feature points in the target grid and / or the similarity between the nearest neighbor feature points in the target grid and the corresponding regional feature points. For example, the larger the number of nearest neighbor feature points in the target grid and / or the higher the similarity between the nearest neighbor feature points in the target grid and the corresponding regional feature points, the higher the heat of the target grid will be. Then, it can be understood that the multiple target grids forming the candidate region can be some grids with relatively high heat in a group of target grids. For example, in the group of target grids, the heat of the multiple target grids forming the candidate region is higher than that of other target grids. In some embodiments, a heat threshold can also be preset. The multiple target grids can be target grids with heat higher than the heat threshold in a group of target grids.

[0049] The heat of each target grid may be determined in various appropriate ways.

[0050] In some embodiments, the sum of the numbers of the nearest neighbor feature points in the target grid may be calculated as the heat of the target grid.

[0051] In some embodiments, the heat of the target grid can be determined based on the similarity between each nearest neighbor feature point in the target grid and the corresponding regional feature point. For example, the sum of the similarities between each nearest neighbor feature point in the target grid and the corresponding regional feature point can be calculated as the heat of the target grid. Of course, other calculation methods are also possible, which are not limited herein.

[0052] In some embodiments, the heat of the target grid can be determined based on both the number of nearest neighbor feature points in the target grid and the similarity between the nearest neighbor feature points in the target grid and the corresponding regional feature points. For example, the number of nearest neighbor feature points in the target grid can be weighted. The weight corresponding to each nearest neighbor feature point can be related to the similarity between the nearest neighbor feature point and the corresponding regional feature point, that is, the weight corresponding to each nearest neighbor feature point can be obtained based on the similarity between the nearest neighbor feature point and the corresponding regional feature point. For example, the higher the similarity, the higher the weight; the lower the similarity, the lower the weight.

[0053] Of course, here are just a few examples of ways to determine the heat of the target grid. In actual implementation, the heat of the target grid can be determined by various appropriate methods, which are not limited in this article.

[0054] In addition, the similarity between the nearest neighbor feature point in the target grid and the corresponding regional feature point may have a negative correlation with the distance between the two. For example, the smaller the distance between the nearest neighbor feature point and the corresponding regional feature point, the greater the similarity between them; the greater the distance, the smaller the similarity. For example, the similarity between the nearest neighbor feature point and the corresponding regional feature point can be expressed in the following way: exp(-1*d), where d can represent the distance between the nearest neighbor feature point and the corresponding regional feature point. Of course, other suitable ways can also be used to express similarity, which is not limited in this article.

[0055] After the candidate region is obtained, the position information of the target region in the film material can be determined based on the position information of the candidate region in the material image. It is understandable that the candidate region may correspond to the entire target region, or substantially correspond to the entire target region (for example, when considering the error), or may be larger than the entire target region (that is, the position of the target region may be within the position range of the candidate region).

[0056] Various suitable methods can be used to determine the position information of the target area in the film material using the position information of the candidate area in the material image. For example, the position of the center of the candidate area in the material image can be calculated or the candidate area can be linearly fitted, and the obtained result can be used to represent the position information of the target area in the film material, or the obtained result can be combined with the boundary range of the candidate area to represent the position information of the target area in the film material. In this case, whichever method is used to determine the position information of the target area, the shape of the target area can be taken into account.

[0057] For ease of understanding, combined FIG. 3A to FIG. 3B An example is used to illustrate the candidate regions. FIG. 3A to FIG. 3B The example corresponds to Figures 2A to 2C various target areas.

[0058] Specifically, Figure 3A Shown with Figure 2A The candidate area that matches the target area 202 in FIG. Figure 3A As shown, multiple target grids with higher heat can form a candidate region 302. The candidate region 302 can roughly correspond to Figure 2A In one implementation, the candidate region 302 may be linearly fitted along the y-axis direction to obtain an x-axis coordinate. The position information of the target region 202 may be represented by the x-axis coordinate, or further represented by combining the boundary range of the candidate region 302 on the x-axis.

[0059] Figure 3B Shown with Figure 2B The candidate area that matches the target area 204 in FIG. Figure 3B As shown, multiple target grids with higher heat can form a candidate region 304. The candidate region 304 can roughly correspond to Figure 2B In one implementation, the position of the center point of the candidate region 304 can be calculated to obtain the corresponding x-axis coordinate and y-axis coordinate. The position information of the target region 204 can be represented by the x-axis coordinate and the y-axis coordinate, or further represented by combining the boundary range of the candidate region 304 on the x-axis and the y-axis.

[0060] Figure 3C Shown with Figure 2C The candidate area that matches the target area 206 in FIG. Figure 3C As shown, multiple target grids with higher heat can form candidate region 306. Candidate region 304 can roughly correspond to Figure 2C In one implementation, linear fitting can be performed on the candidate region 306 along the x-axis direction to obtain a y-axis coordinate. The position information of the target region 206 can be represented by the y-axis coordinate, or further represented by combining the boundary range of the candidate region 306 on the y-axis.

[0061] The above are only examples. In different application scenarios, different methods may be used to determine the location information of the target area, which is not limited in this document.

[0062] In addition, as mentioned above, a line scan camera is usually used to photograph the thin film material. In this case, each pixel in the material image can have a corresponding relationship with the corresponding physical part of the thin film material, and the physical part of the thin film material can have corresponding processing data. Therefore, the pixels in the material image actually have a corresponding relationship with the processing data. Therefore, in an embodiment of the present disclosure, after determining the position information of the target area in the thin film material, the processing data corresponding to the target area can be obtained accordingly. For example, the processing data can be used for further analysis of the processing state of the thin film material at the target area.

[0063] The above describes how to locate the target area in the thin film material. The following describes the preparations before the positioning. As mentioned above, the material characteristic information is required in the positioning process, and the following describes how to determine the material characteristic information.

[0064] Figure 4 is a schematic flow chart of a method for determining material characteristic information according to some embodiments.

[0065] like Figure 4 As shown, in step 402, a material image of the thin film material may be acquired. The material image may be acquired when the thin film material is spread out on a two-dimensional plane.

[0066] In step 404, material feature information may be extracted from the material image. The material feature information may be used to represent a set of material feature points in the material image.

[0067] In some embodiments, various suitable methods may be used to obtain the material image of the thin film material. For example, as mentioned above, a line scan camera or an area array camera may be used to obtain the material image of the thin film material.

[0068] In some embodiments, various suitable methods may be used to extract material feature information, such as SIFT, ORB, etc. In some cases, a large number of material feature points may be extracted, such as N material feature points. In this case, if N is greater than a preset number threshold, M material feature points may be selected from the N material feature points as the above-mentioned set of material feature points, where M is less than N. Various suitable methods may be used to select M material feature points from the N material feature points, such as a uniform sampling method. In this way, by reducing the number of material feature points, the amount of calculation in the subsequent positioning of the target area can be reduced, for example, the amount of calculation can be reduced when determining the distance between the regional feature points and the material feature points.

[0069] In some embodiments, the material feature information may include a set of material feature point positions and feature vectors. For example, the positions of the material feature points may be represented by x-coordinates and y-coordinates, the x-axis may correspond to the length direction of the material image, and the y-axis may correspond to the width direction of the material image. The feature vector may be represented in any appropriate form, such as 64 floating point numbers. This document does not limit this.

[0070] In some embodiments, the material image may be divided into a set of grids. Each grid may include at least one material feature point from a set of material feature points. In some cases, the number of material feature points in each grid may be greater than a preset threshold.

[0071] In some implementations, the material feature points may be extracted from the material image first, and then the material image may be divided into grids. In some implementations, the material image may be divided into a group of grids, and then the material feature points may be extracted for each grid. The specific method to be adopted may depend on factors such as actual business needs, and this document does not limit this.

[0072] In this case, the material characteristic information may further include mesh information, and the mesh information may be used to represent the group of meshes.

[0073] Figure 5 is a schematic block diagram of an apparatus for locating a material region according to some embodiments.

[0074] like Figure 5 As shown, the apparatus 500 may include an acquiring unit 502 , an extracting unit 504 , and a determining unit 506 .

[0075] The acquisition unit 502 may acquire a region image collected for a target region to be located of the film material. The extraction unit 504 may extract region feature information from the region image. The region feature information may be used to represent a set of region feature points in the region image. The determination unit 506 may determine the position information of the target region in the film material based on the region feature information and predetermined material feature information. The material feature information may be used to represent a set of material feature points in the material image. The material image may be collected when the film material is unfolded on a two-dimensional plane.

[0076] Each unit of the device 500 can execute the specific process described above with respect to the method embodiment. Therefore, for the sake of brevity of description, the specific operations and functions of each unit of the device 500 are not described in detail here.

[0077] Figure 6 is a schematic block diagram of an apparatus for determining material characteristic information according to some embodiments.

[0078] like Figure 6As shown, the apparatus 600 may include an acquisition unit 602 and an extraction unit 604 .

[0079] The acquisition unit 602 may acquire a material image of the thin film material. The material image may be acquired when the thin film material is unfolded on a two-dimensional plane. The extraction unit 604 may extract material feature information from the material image. The material feature information may be used to represent a set of material feature points in the material image.

[0080] Each unit of the device 600 can execute the specific process described above with respect to the method embodiment. Therefore, for the sake of brevity of description, the specific operations and functions of each unit of the device 600 are not described in detail here.

[0081] Figure 7 is a schematic block diagram of an apparatus for locating a material region according to some embodiments.

[0082] like Figure 7 As shown, the apparatus 700 may include at least one processor 702, a memory 704, an input interface 706, and an output interface 708, and these modules may be coupled together via a bus 710. However, it should be understood that Figure 7 This is only an example and does not limit the scope of the present disclosure. For example, in different application scenarios, the device 700 may include more or fewer modules, which is not limited herein.

[0083] The memory 704 may be used to store various information related to the function or operation of the device 700 (such as the region image, region feature information, material feature information, etc. mentioned above), executable instructions or codes, etc. For example, the memory 704 may include, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a flash memory, a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a register, a hard disk, and the like.

[0084] The processor 702 may be used to implement various functions or operations of the apparatus 700, such as various operations for locating a material region described herein. For example, the processor 702 may execute executable code or instructions stored in the memory 704 to implement various processes described in connection with various embodiments of the present disclosure. The processor 702 may include various applicable processors, such as general-purpose processors (such as a central processing unit (CPU)), special-purpose processors (such as a digital signal processor, a graphics processing unit, an application-specific integrated circuit, etc.).

[0085] The input interface 706 may receive various forms of data, such as the above-mentioned regional image, etc. In some implementations, the input interface 706 may also perform corresponding communications based on various wired or wireless communication standards.

[0086] The output interface 708 may output various forms of data, etc. For example, the output interface 708 may output location information of the target area in the film material, etc. In some implementations, the output interface 708 may perform corresponding communications based on various applicable wired or wireless communication standards.

[0087] Figure 8 is a schematic block diagram of an apparatus for determining material characteristic information according to some embodiments.

[0088] like Figure 8 As shown, the apparatus 800 may include at least one processor 802, a memory 804, an input interface 806, and an output interface 808, and these modules may be coupled together via a bus 810. However, it should be understood that Figure 8 This is only an example and does not limit the scope of the present disclosure. For example, in different application scenarios, the device 800 may include more or fewer modules, which is not limited herein.

[0089] The memory 804 may be used to store various information related to the function or operation of the device 800 (such as the material image, material characteristic information, etc. mentioned above), executable instructions or codes, etc. For example, the memory 804 may include but is not limited to RAM, ROM, flash memory, PROM, EPROM, registers, hard disks, etc.

[0090] The processor 802 may be used to implement various functions or operations of the apparatus 800, such as various operations described herein for determining material characteristic information. For example, the processor 802 may execute executable codes or instructions stored in the memory 804, thereby implementing various processes described in various embodiments of the present disclosure. The processor 802 may include various applicable processors, such as general-purpose processors (such as CPUs), special-purpose processors (such as digital signal processors, graphics processing units, application-specific integrated circuits, etc.).

[0091] The input interface 806 may receive various forms of data, such as the above-mentioned material images, etc. In some implementations, the input interface 806 may also perform corresponding communications based on various wired or wireless communication standards.

[0092] The output interface 808 may output various forms of data, etc. For example, the output interface 808 may output material characteristic information, etc. In some implementations, the output interface 808 may perform corresponding communications based on various applicable wired or wireless communication standards.

[0093] The embodiments of the present disclosure further provide a computer-readable storage medium. The computer-readable storage medium may store executable codes, which, when executed by a computer, enable the computer to implement the specific processes described above with respect to each method embodiment.

[0094] For example, computer-readable storage media may include, but are not limited to, RAM, ROM, Electrically-Erasable Programmable Read-Only Memory (EEPROM), Static Random Access Memory (SRAM), hard disk, flash memory, and the like.

[0095] Specific embodiments of the present disclosure are described above. In some cases, the actions or steps described in the claims may be performed in a different order than in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In some implementations, multitasking and parallel processing are also possible or may be advantageous.

[0096] Not all steps and units in the above processes and system structure diagrams are necessary, and some steps or units may be omitted according to actual needs. The device structure described in the above embodiments may be a physical structure or a logical structure, that is, some units may be implemented by the same physical entity, some units may be implemented by multiple physical entities, or may be implemented by some components in multiple independent devices.

[0097] The optional implementation of the embodiments of the present disclosure is described in detail above in conjunction with the accompanying drawings, however, the embodiments of the present disclosure are not limited to the specific details in the above implementation. Within the technical concept of the embodiments of the present disclosure, the technical solutions of the embodiments of the present disclosure can be modified in many ways, and these modifications all belong to the protection scope of the embodiments of the present disclosure.

Claims

1. A method for locating a material region, comprising: Acquire a regional image collected from a target region to be positioned of the thin film material; Extracting regional feature information from the regional image, wherein the regional feature information is used to represent a group of regional feature points in the regional image; Based on the region characteristic information and predetermined material characteristic information, the position information of the target region in the thin film material is determined, wherein the material characteristic information is used to represent a set of material characteristic points in a material image, and the material image is collected when the thin film material is unfolded on a two-dimensional plane.

2. The method according to claim 1, wherein: Determining the position information of the target area in the material includes: Identifying at least one nearest neighbor feature point corresponding to each regional feature point in the set of material feature points to obtain a set of nearest neighbor feature points corresponding to the set of regional feature points; Based on the group of nearest neighbor feature points, position information of the target area in the film material is determined.

3. The method according to claim 2, wherein: The region feature information includes the position and feature vector of each region feature point, and the material feature information includes the position and feature vector of each material feature point; Identifying at least one nearest neighbor feature point corresponding to each region feature point in the set of material feature points includes: Based on the position and feature vector of each regional feature point and the position and feature vector of each material feature point, determining the distance between each regional feature point and each material feature point; For each region feature point, at least one material feature point is selected from the group of material feature points in ascending order of the distance between the region feature point and each material feature point as at least one nearest neighbor feature point corresponding to the region feature point.

4. The method according to claim 2, wherein: The material feature information further includes grid information, wherein the grid information is used to represent a group of grids obtained by dividing the material image, each grid having at least one material feature point in the group of material feature points; Determining the position information of the target area in the film material based on the set of nearest neighbor feature points includes: Determine the grids to which the group of nearest neighbor feature points respectively belong in the group of grids as a group of target grids; Based on the set of target grids, position information of the target area in the film material is determined.

5. The method according to claim 4, wherein: Determining the position information of the target area in the film material based on the set of target grids includes: determining a candidate region in the material image, wherein the candidate region is formed by a plurality of target grids in the set of target grids and has a shape matching the target region; Based on the position information of the candidate area in the material image, the position information of the target area in the film material is determined.

6. The method according to claim 5, further comprising: Determine the heat of each target grid in the set of target grids, wherein the heat of each target grid has a positive correlation with the number of nearest neighbor feature points in the target grid and / or the similarity between the nearest neighbor feature points in the target grid and the corresponding regional feature points; Determining a candidate region in the material image includes: A candidate region formed by the plurality of grids in the material image is determined, wherein, among the group of target grids, heats of the plurality of target grids are higher than other target grids except the plurality of target grids.

7. The method according to claim 6, wherein: Determining the heat of each target grid includes: For each target grid, the sum of the number of the nearest neighbor feature points in the target grid is calculated as the heat of the target grid; or For each target grid, calculate the sum of similarities between each nearest neighbor feature point in the target grid and the corresponding regional feature point as the heat of the target grid; or For each target grid, based on the weight corresponding to each nearest neighbor feature point in the target grid, the number of nearest neighbor feature points in the target grid is weightedly calculated to obtain the heat of the target grid, wherein the weight corresponding to each nearest neighbor feature point is determined based on the similarity between the nearest neighbor feature point and the corresponding regional feature point.

8. The method according to claim 6, wherein: The similarity between each nearest neighbor feature point and the corresponding regional feature point is negatively correlated with the distance between the nearest neighbor feature point and the corresponding regional feature point.

9. A method for determining material characteristic information, wherein: The material characteristic information is used in a method according to any one of claims 1 to 8, the method comprising: Acquire a material image of a thin film material, wherein the material image is acquired when the thin film material is spread out on a two-dimensional plane; Material feature information is extracted from the material image, wherein the material feature information is used to represent a group of material feature points in the material image.

10. The method according to claim 9, wherein: The material feature information includes the positions and feature vectors of the set of material feature points.

11. The method according to claim 9, further comprising: The material image is divided into a group of grids, wherein the material feature information further includes grid information, the grid information is used to represent the group of grids, and each grid has at least one material feature point in the group of material feature points.

12. An apparatus for locating a material region, comprising: at least one processor; A memory in communication with the at least one processor, having executable codes stored thereon, which, when executed by the at least one processor, cause the at least one processor to perform the method according to any one of claims 1 to 8.

13. A computer-readable storage medium storing executable codes, which, when executed, cause a computer to perform the method according to any one of claims 1 to 8.

Images