CN113744273A - Soft package battery cell edge folding detection method and device, electronic equipment and storage medium - Google Patents
Soft package battery cell edge folding detection method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113744273A CN113744273A CN202111310279.XA CN202111310279A CN113744273A CN 113744273 A CN113744273 A CN 113744273A CN 202111310279 A CN202111310279 A CN 202111310279A CN 113744273 A CN113744273 A CN 113744273A
- Authority
- CN
- China
- Prior art keywords
- target
- battery cell
- package battery
- target image
- soft package
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a soft-package battery cell flanging detection method and device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a target image of the target soft package battery cell after edge folding; the target image comprises a front view and a left view of the target soft package battery cell after edge folding; extracting the features of the target image to obtain the features of the target folded edge in the target image; and acquiring a folding detection result of the target soft package battery cell based on the characteristics of the target folding in the target image. According to the method and device for detecting the edge folding of the soft package battery cell, the electronic equipment and the storage medium, provided by the embodiment of the invention, the edge folding detection result of the target soft package battery cell is obtained based on the characteristics of the target edge folding in the target image by performing characteristic extraction on the target image of the target soft package battery cell subjected to edge folding, the edge folding detection of the soft package battery cell can be automatically performed based on an image processing method, the edge folding detection efficiency of the soft package battery cell can be improved, and the accuracy of the detection result is higher.
Description
Technical Field
The invention relates to the technical field of industrial control, in particular to a soft package battery cell flanging detection method and device, electronic equipment and a storage medium.
Background
In the production process of soft-packaged module, need carry out the hem through the utmost point ear of hem technology to soft-packaged electrical core to the utmost point ear to the different soft-packaged electrical cores that pile up welds.
The existing soft package battery cell edge folding detection is usually carried out through manual detection. The manual detection efficiency is low, the precision is poor, and the stability of the battery quality can not be ensured.
Disclosure of Invention
The invention provides a soft-package battery cell edge folding detection method and device, electronic equipment and a storage medium, and aims to solve the technical problem of low detection efficiency in the prior art.
The invention provides a soft-package battery cell flanging detection method, which comprises the following steps:
acquiring a target image of the target soft package battery cell after edge folding; the target image comprises a front view and a left view of the target soft package battery cell after the edge folding;
extracting the features of the target image to obtain the features of the target folded edge in the target image;
and acquiring a folding detection result of the target soft package battery cell based on the characteristics of the target folding in the target image.
According to the soft package battery cell flanging detection method provided by the invention, the feature extraction is performed on the target image to obtain the feature of the target flanging in the target image, and the method specifically comprises the following steps:
under the condition that the target image comprises a front view of the target soft package battery cell after the edge folding, acquiring a first edge folding angle and a second edge folding angle based on the target image;
the method for detecting the edge folding of the soft package battery cell based on the features of the target edge folding in the target image includes:
and determining the hem detection result of the target soft package battery cell as unqualified under the condition that the difference between the angle of the first hem or the angle of the second hem and the target angle is greater than or equal to a target threshold value.
According to the soft package battery cell flanging detection method provided by the invention, the feature extraction is performed on the target image to obtain the feature of the target flanging in the target image, and the method specifically comprises the following steps:
detecting bright spots and characteristic lines in the target image under the condition that the target image comprises the left view of the target soft package battery cell subjected to edge folding;
the method for detecting the edge folding of the soft package battery cell based on the features of the target edge folding in the target image includes:
and determining the hem detection result of the target soft package battery cell as unqualified under the condition that the bright spots exist in the target image.
According to the soft package battery cell flanging detection method provided by the invention, the feature extraction is performed on the target image to obtain the feature of the target flanging in the target image, and the method specifically comprises the following steps:
under the condition that the target image comprises a front view and a left view of the target soft package battery core subjected to edge folding, acquiring an angle of a first edge folding, an angle of a second edge folding and a distance between a first part of the first edge folding and a first part of the second edge folding based on the front view, and detecting a bright spot and a characteristic line in the left view;
the method for detecting the edge folding of the soft package battery cell based on the features of the target edge folding in the target image includes:
and acquiring a hem detection result of the target soft package battery cell based on at least one of the angle of the first hem, the angle of the second hem, the distance between the first part of the first hem and the first part of the second hem, whether the bright spot is detected and the characteristic line.
According to the soft package battery cell flanging detection method provided by the invention, the feature extraction is performed on the target image to obtain the feature of the target flanging in the target image, and the method further comprises the following steps:
acquiring a distance between a first portion of the first fold and a first portion of the second fold based on the target image when a difference between the angle of the first fold and the target angle is less than the target threshold and a difference between the angle of the second fold and the target angle is less than the target threshold;
the method for detecting the edge folding of the soft package battery cell based on the characteristics of the target edge folding in the target image further comprises the following steps:
and determining that the flanging detection result of the target soft package battery cell is qualified under the condition that the distance between the first part of the first flanging and the first part of the second flanging is smaller than or equal to the target distance.
According to the method for detecting the edge folding of the soft package battery cell, provided by the invention, the edge folding detection result of the target soft package battery cell is obtained based on the characteristics of the target edge folding in the target image, and the method further comprises the following steps:
and under the condition that the distance between the first part of the first flanging and the first part of the second flanging is larger than the target distance, determining the flanging detection result of the target soft package battery cell as unqualified.
According to the method for detecting the edge folding of the soft package battery cell, provided by the invention, the edge folding detection result of the target soft package battery cell is obtained based on the characteristics of the target edge folding in the target image, and the method further comprises the following steps:
and under the condition that the bright spots are not detected in the target image, acquiring a flanging detection result of the target soft package battery cell based on the characteristic line in the target image.
The invention also provides a soft-package battery cell flanging detection device, which comprises:
the image acquisition module is used for acquiring a target image of the target soft package battery cell after edge folding; the target image comprises a front view and a left view of the target soft package battery cell after the edge folding;
the characteristic extraction module is used for extracting the characteristics of the target image to obtain the characteristics of a target folded edge in the target image;
and the flanging detection module is used for acquiring a flanging detection result of the target soft package battery cell based on the characteristics of the target flanging in the target image.
The invention also provides electronic equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the steps of any one of the soft package cell flanging detection methods.
The invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of any one of the above-mentioned methods for detecting a soft-packing cell edge folding.
According to the soft package battery cell flanging detection method, the soft package battery cell flanging detection device, the electronic equipment and the storage medium, the target image of the target soft package battery cell subjected to flanging is subjected to feature extraction, the features of the target flanging in the target image are obtained, the flanging detection result of the target soft package battery cell is obtained based on the features of the target flanging in the target image, the flanging detection of the target soft package battery cell can be automatically performed based on an image processing method, the flanging detection efficiency of the soft package battery cell can be improved, the accuracy of the detection result is higher, and the stability of the quality of a soft package battery cell module can be further ensured.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a soft-package cell edge folding detection method provided by the invention;
fig. 2 is one of schematic diagrams of a target image in the soft-package cell edge folding detection method provided by the invention;
fig. 3 is a second schematic diagram of a target image in the soft-package cell edge folding detection method provided by the invention;
fig. 4 is a schematic structural diagram of a soft-package battery cell flanging detection device provided by the invention;
fig. 5 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the embodiments of the present invention, it should be noted that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the embodiments of the present invention and simplifying the description, but do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the embodiments of the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance, and not order.
In the description of the embodiments of the present invention, it should be noted that, unless explicitly stated or limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. Specific meanings of the above terms in the embodiments of the present invention can be understood in specific cases by those of ordinary skill in the art.
In order to overcome the problems in the prior art, the invention provides a method and a device for detecting the edge folding of a soft package cell, electronic equipment and a storage medium.
Fig. 1 is a schematic flow chart of a soft-package battery cell edge folding detection method provided by the invention. The method for detecting the edge folding of the soft package cell in the embodiment of the invention is described below with reference to fig. 1. As shown in fig. 1, the method includes: step 101, obtaining a target image of a target soft package battery cell after edge folding; the target image comprises a front view and a left view of the target soft-packed cell after crimping.
Specifically, after the target soft package battery cell is subjected to edge folding, a target image of the target soft package battery cell subjected to edge folding can be acquired based on an image of an edge folding part of the target soft package battery cell acquired by the image acquisition device. And the target image of the target soft package battery cell after the edge folding is the image of the edge folding part of the target soft package battery cell after the edge folding is performed.
And (4) folding the edge of the target soft package battery cell, namely folding the edge of the target soft package battery cell.
The image acquisition device can be a camera or a video camera and the like.
The image acquisition device can shoot the edge folding part of the target soft package battery core after the edge folding through the modes of shooting from the front and/or the left side of the target soft package battery core after the edge folding, and acquires the target image of the target soft package battery core after the edge folding.
The target image may be as shown in fig. 2. The left half part in fig. 2 is a left side view of the target soft-package battery cell after the edge folding, and the right half part in fig. 2 is a front view of the target soft-package battery cell after the edge folding.
In the actual edge folding detection, only the front view of the target soft package battery cell after edge folding is acquired as a target image, and edge folding detection is performed based on the front view of the target soft package battery cell after edge folding; or only the left view of the target soft package battery cell after the edge folding is obtained as a target image, and edge folding detection is performed based on the left view of the target soft package battery cell after the edge folding is performed; the front view and the left view of the target soft package battery cell after the edge folding can be acquired to serve as target images, and edge folding detection is carried out by combining the front view and the left view of the target soft package battery cell after the edge folding is carried out.
And 102, extracting the features of the target image to obtain the features of the target folded edge in the target image.
Specifically, as shown in fig. 2 and 3, the target hem may include a first hem 201 and a second hem 202. The first fold 201 includes two portions that intersect at a point: a first portion 2011 of first flap 201 and a second portion 2012 of first flap 201; the second flange 202 includes two portions that intersect at a point: a first portion 2021 of the second flap 202 and a second portion 2022 of the second flap 202.
The feature extraction can be carried out on the target image through a target image processing method, and the feature of the target folded edge in the target image is obtained.
Alternatively, the target image processing method may include at least one of a statistical-based image processing method, image segmentation, edge detection, brightness detection, and the like.
Alternatively, the target image processing method may be an Artificial Intelligence (AI) algorithm. Illustratively, the Artificial intelligence algorithm may be an AI algorithm based on any kind of Artificial Neural Network (ANN), or the like.
Alternatively, the features of the target folds in the target image may include a size feature of the target folds, a relative position feature between the target folds, a size feature of a gap between the target folds, and the like.
Illustratively, the dimensional characteristics of the target hem may include a length of a first portion of the first hem, a length of a second portion of the first hem, a length of a first portion of the second hem, a length of a first portion of the first hem, an angle of the first hem, and an angle of the second hem.
The angle of the first folded edge refers to an included angle between a first part of the first folded edge and a second part of the first folded edge.
The angle of the second folded edge refers to an included angle between the first part of the second folded edge and the second part of the second folded edge.
Based on the front view and the left view of the target soft package battery cell after the edge folding, the features of the target edge folding in the image can be obtained from different dimensions.
And 103, acquiring a folding detection result of the target soft package battery cell based on the characteristics of the target folding in the target image.
Specifically, the characteristic of the target edge folding in the target image may describe at least one of information such as a size of the target edge folding, a relative position between the target edge folding, and a size of a gap between the target edge folding, and therefore, the edge folding detection result of the target soft package battery cell may be obtained based on the characteristic of the target edge folding in the target image.
Optionally, under the condition that the size of the target folded edge, the relative position between the target folded edges and the size of the gap between the target folded edges all meet preset standards, determining the folded edge detection result of the target soft package battery cell to be qualified; and under the condition that the size of the target folded edges, the relative position between the target folded edges or the size of the gap between the target folded edges do not accord with the preset standard, determining the folded edge detection result of the target soft package battery core as unqualified.
Exemplarily, in the case that the dimensional characteristics of the target folded edge may include a length of the first portion of the first folded edge, a length of the second portion of the first folded edge, a length of the first portion of the second folded edge, a length of the first portion of the first folded edge, an angle of the first folded edge, and an angle of the second folded edge, and the length of the first portion of the first folded edge, the length of the second portion of the first folded edge, the length of the first portion of the first folded edge, the angle of the first folded edge, and the angle of the second folded edge all meet preset criteria, the folded edge detection result of the target soft package cell may be determined to be qualified; under the condition that any one of the length of the first part of the first folded edge, the length of the second part of the first folded edge, the length of the first part of the second folded edge, the length of the first part of the first folded edge, the angle of the first folded edge and the angle of the second folded edge does not meet a preset standard, the folded edge detection result of the target soft package battery cell can be determined to be unqualified.
Optionally, the actual values of the features of the target hems in the target image may be combined into a feature vector X, and the preset values of the features of each target hem may be combined into a reference vector Y; acquiring the similarity S between the characteristic vector X and the reference vector Y; and determining the hem detection result of the target soft package battery cell as qualified under the condition that the similarity S is greater than or equal to the similarity threshold, and determining the hem detection result of the target soft package battery cell as unqualified under the condition that the similarity S is less than the similarity threshold.
The similarity S between the feature vector X and the reference vector Y can be calculated by the following formula:
wherein n represents the dimensions of the feature vector X and the reference vector Y; x is the number ofiRepresents the ith element in the feature vector X; y isiRepresenting the ith element in the reference vector Y.
The similarity threshold may be set according to actual conditions, for example, the similarity threshold is 0.95 or 0.9. The embodiment of the present invention is not particularly limited to the specific value of the similarity threshold.
According to the embodiment of the invention, the characteristic extraction is carried out on the target image of the target soft-package battery cell after the edge folding is carried out, the characteristic of the target edge folding in the target image is obtained, the edge folding detection result of the target soft-package battery cell is obtained based on the characteristic of the target edge folding in the target image, the edge folding detection of the target soft-package battery cell can be automatically carried out based on an image processing method, the edge folding detection efficiency of the soft-package battery cell can be improved, the accuracy of the detection result is higher, and the stability of the quality of the soft-package battery cell module can be further ensured.
Based on the content of any one of the embodiments, the method for extracting the features of the target image to obtain the features of the target hem in the target image specifically includes: and in the case that the target image comprises a front view of the target soft package cell after the flanging, acquiring the angle of the first flanging and the angle of the second flanging on the basis of the target image.
In particular, the feature of the target hem in the target image may include an angle of the first hem and an angle of the second hem.
The angle of the first folded edge and the angle of the second folded edge may be obtained based on a front view of the target soft-package battery cell after the folding is performed.
Optionally, the feature extraction of the target image may include the steps of contour extraction, line detection, and edge folding recognition.
Contour extraction can be carried out on a target image based on an edge detection operator (such as a Canny operator or a Laplacian operator) and the like, and contours in the image are obtained; after the contour in the image is obtained, the straight Line Segment in the image may be obtained based on any one of straight Line Detection algorithms, such as Hough Line Detection (Hough Line Detection) or a Line Segment Detection (LSD) algorithm; after the straight line segments in the image are obtained, the body of the target soft package battery cell can be identified based on the straight line segments in the image, and a broken line segment which is connected with the body at one end and is composed of two straight line segments is determined as a target folded edge. The target folded edge comprises two straight line segments which are a first part of the target folded edge and a second part of the target folded edge respectively.
The lateral and longitudinal directions of the image may be taken as the X-axis and the Y-axis, respectively, based on which a coordinate system is established. After acquiring the first portion of the first hem and the second portion of the first hem, an angle of the first hem may be acquired based on the coordinate system; after acquiring the first portion of the second hem and the second portion of the second hem, an angle of the second hem may be acquired based on the coordinate system.
Based on the characteristics of the target edge folding in the target image, the edge folding detection result of the target soft package battery cell is obtained, and the method specifically comprises the following steps: and determining the hem detection result of the target soft package battery cell as unqualified under the condition that the difference between the angle of the first hem or the angle of the second hem and the target angle is greater than or equal to a target threshold value.
Specifically, after the angle of the first folded edge is obtained, the difference between the angle of the first folded edge and the target angle may be obtained; after the difference between the angle of the first folded edge and the target angle is obtained, the difference between the angle of the first folded edge and the target angle is compared with the target threshold value.
If the difference between the angle of the first folded edge and the target angle is greater than or equal to the target threshold value, the situation that the folded edge of the first folded edge is not in place is indicated, and the folded edge detection result of the target soft package battery cell can be determined to be unqualified.
After the angle of the second folded edge is obtained, the difference between the angle of the second folded edge and the target angle can be obtained; and after the difference between the angle of the second folded edge and the target angle is obtained, comparing the difference between the angle of the second folded edge and the target angle with the target threshold value.
If the difference between the angle of the second folded edge and the target angle is greater than or equal to the target threshold, which indicates that the folded edge of the second folded edge is not in place, the folded edge detection result of the target soft package cell may be determined to be unqualified (as shown in fig. 3).
The target angle can be set according to actual conditions. The embodiment of the present invention is not particularly limited with respect to the value of the target angle. Illustratively, the target angle may be 90 degrees.
The target threshold value may also be set according to actual conditions. The value of the target threshold is not particularly limited in the embodiments of the present invention. Illustratively, the target threshold may be 3 degrees or 1 degree.
According to the embodiment of the invention, based on the front view of the target soft-package battery cell after edge folding, the angle of the first edge folding and the angle of the second edge folding are obtained, and under the condition that the difference between the angle of the first edge folding or the angle of the second edge folding and the target angle is greater than or equal to the target threshold value, the edge folding detection result of the target soft-package battery cell is determined to be unqualified, the target soft-package battery cell with an improper edge folding can be automatically detected, the edge folding detection efficiency of the soft-package battery cell can be improved, the accuracy of the detection result is higher, and the quality stability of a soft-package battery cell module can be further ensured.
Based on the content of any of the above embodiments, the method for extracting the features of the target image to obtain the features of the target hem in the target image further includes: and acquiring the distance between the first part of the first folded edge and the first part of the second folded edge based on the target image under the condition that the difference between the angle of the first folded edge and the target angle is smaller than a target threshold value and the difference between the angle of the second folded edge and the target angle is smaller than the target threshold value.
Specifically, if the difference between the angle of the first folding edge and the target angle is smaller than the target threshold, and the difference between the angle of the second folding edge and the target angle is also smaller than the target threshold, the distance between the first portion of the first folding edge and the first portion of the second folding edge may be further acquired based on the front view of the target soft package cell after folding, and is also taken as the feature of the target folding edge in the target image. The distance between the first portion of the first hem and the first portion of the second hem is used to describe the size of the gap between the target hems.
The calculation formula for the distance between the first portion of the first flange and the first portion of the second flange may be expressed as:
wherein d represents the distance between the first portion of the first flap and the first portion of the second flap; the coordinates of a pixel point i on the first part of the first folded edge and a pixel point j on the first part of the second folded edge in the target image are respectively (X)i，Yi) And (X)j，Yj) (ii) a I is more than or equal to 1 and less than or equal to M, j is more than or equal to 1 and less than or equal to N, and M and N respectively represent the number of pixel points included in the first part of the first folded edge and the number of pixel points included in the first part of the second folded edge; k represents a conversion coefficient. A scaling factor k for converting between distances in the target image and distances in real space.
In addition, k may be k1For the conversion between the distance in the front view and the distance in real space.
Based on the characteristic of the target hem in the target image, the hem testing result of the target soft package battery cell is obtained, and the method further comprises the following steps: and determining that the folding edge detection result of the target soft package battery cell is qualified under the condition that the distance between the first part of the first folding edge and the first part of the second folding edge is smaller than or equal to the target distance.
Specifically, after the distance between the first portion of the first hem and the first portion of the second hem is acquired, the magnitude between the distance between the first portion of the first hem and the first portion of the second hem and the target distance may be compared.
If the distance between the first portion of the first folded edge and the first portion of the second folded edge is less than or equal to the target distance, it is determined that the gap between the first folded edge and the second folded edge meets the preset standard, and thus the folded edge detection result of the target soft-package battery cell can be determined to be qualified (as shown in fig. 2).
The target distance can be set according to actual conditions. The embodiment of the present invention is not particularly limited to the value of the target distance. Illustratively, the target distance may be 1 millimeter or 2 millimeters.
According to the embodiment of the invention, under the condition that the difference between the angle of the first folding edge and the target angle is smaller than the target threshold value and the difference between the angle of the second folding edge and the target angle is smaller than the target threshold value, the distance between the first part of the first folding edge and the first part of the second folding edge is obtained based on the front view of the target soft package battery cell after folding, and under the condition that the distance between the first part of the first folding edge and the first part of the second folding edge is smaller than or equal to the target distance, the folding edge detection result of the target soft package battery cell is determined to be qualified, the target soft package battery cell with qualified folding edge can be automatically detected, the folding edge detection efficiency of the soft package battery cell can be improved, the accuracy of the detection result is higher, and the stability of the quality of the soft package battery cell module can be further ensured.
Based on the content of any one of the above embodiments, based on the feature of the target edge folding in the target image, the edge folding detection result of the target soft package battery cell is obtained, which further includes: and under the condition that the distance between the first part of the first folded edge and the first part of the second folded edge is greater than the target distance, determining the folded edge detection result of the target soft package battery cell as unqualified.
Specifically, after the distance between the first portion of the first hem and the first portion of the second hem is acquired, the magnitude between the distance between the first portion of the first hem and the first portion of the second hem and the target distance may be compared.
If the distance between the first part of the first folded edge and the first part of the second folded edge is greater than the target distance, it is indicated that the gap between the first part of the first folded edge and the first part of the second folded edge is too large, and the folded edge detection result of the target soft package battery cell can be determined to be unqualified.
According to the embodiment of the invention, under the condition that the distance between the first part of the first folded edge and the first part of the second folded edge is equal to the target distance, the folded edge detection result of the target soft-package battery cell is determined to be unqualified, the target soft-package battery cell with an improper folded edge can be automatically detected, the folded edge detection efficiency of the soft-package battery cell can be improved, the accuracy of the detection result is higher, and the stability of the quality of the soft-package battery cell module can be further ensured.
Based on the content of any one of the embodiments, the method for extracting the features of the target image to obtain the features of the target hem in the target image specifically includes: and under the condition that the target image comprises the left view of the target soft package battery cell after edge folding, detecting bright spots and characteristic lines in the target image.
Specifically, the feature of the target flange in the target image may include whether or not there is a bright spot in the target image and a feature line in the target image.
Whether bright spots exist in the target image or not and characteristic lines in the target image can be obtained based on the left view of the target soft package battery cell after edge folding.
The brightness abnormality detection can be carried out on the left view of the target soft package battery cell after the edge folding based on any brightness detection algorithm, and whether bright spots exist in the image or not is detected. A bright spot refers to an area that is too bright, i.e., an area that is significantly brighter than other areas.
The contour of the target edge folding in the left view of the target soft package battery cell after edge folding can be extracted based on any edge detection algorithm, and a characteristic line is obtained. The characteristic line can be a transverse line in the left view.
Based on the characteristics of the target edge folding in the target image, the edge folding detection result of the target soft package battery cell is obtained, and the method specifically comprises the following steps: and determining the hem detection result of the target soft package battery cell as unqualified when the bright spots are detected in the target image.
Specifically, if the bright spots are detected in the target image, it is indicated that the gap between the first portion of the first flange and the first portion of the second flange is too large (as shown in fig. 3).
The target edgefold is usually made of silver metal and can reflect light, and under the condition that a gap between the first part of the first edgefold and the first part of the second edgefold is too large, bright spots exist in a left view of the target soft package battery cell after the edgefold is performed. Therefore, when the bright spots are detected in the target image, the fold detection result of the target soft package cell can be determined as unqualified.
According to the embodiment of the invention, under the condition that the bright spot exists in the left view of the target soft-package battery cell after edge folding, the edge folding detection result of the target soft-package battery cell is determined to be unqualified, the target soft-package battery cell with an improper edge folding can be automatically detected, the edge folding detection efficiency of the soft-package battery cell can be improved, the accuracy of the detection result is higher, and the stability of the quality of the soft-package battery cell module can be further ensured.
Based on the characteristic of the target hem in the target image, the hem testing result of the target soft package battery cell is obtained, and the method further comprises the following steps: and under the condition that the bright spots are not detected in the target image, acquiring a folding edge detection result of the target soft package battery cell based on the characteristic line in the target image.
Specifically, the existence of the bright spot in the target image is not detected, which indicates that it cannot be determined that the gap between the first portion of the first flange and the first portion of the second flange does not meet the preset standard, so that the flange detection result of the target soft package cell can be further obtained based on the characteristic line in the target image.
And acquiring a hem detection result of the target soft package battery cell based on the number and the positions of the characteristic lines.
Optionally, in the case that the number of the characteristic lines is not equal to 3, the fold detection result of the target soft package cell may be determined to be unqualified.
Alternatively, in the case where the number of feature lines is 3, the 3 feature lines are, in order from top to bottom in the image, the first feature line, the second feature line, and the third feature line.
A first distance between the second characteristic line and the first characteristic line and/or a second distance between the second characteristic line and the third characteristic line may be acquired.
Optionally, in a case that a difference between the first distance and the first threshold is greater than a preset first difference threshold, the fold detection result of the target soft package cell may be determined to be unqualified.
Optionally, in a case that a difference between the second distance and the second threshold is greater than a preset second difference threshold, the fold detection result of the target soft package cell may be determined to be unqualified.
Optionally, the fold detection result of the target soft package cell may be determined to be qualified when a difference between the first distance and the first threshold is less than or equal to a preset first difference threshold, and a difference between the second distance and the second threshold is less than or equal to a preset second difference threshold.
The first threshold value may be set according to actual conditions. The value of the first threshold is not particularly limited in the embodiments of the present invention. Illustratively, the first threshold may be 3 millimeters or 1 degree.
The second threshold value may be set according to actual conditions. The value of the second threshold is not particularly limited in the embodiments of the present invention. Illustratively, the second threshold may be 3 millimeters or 1 degree.
It can be understood that, under the condition that the first folding edge and the second folding edge both meet the preset standard, the number of the characteristic lines is 3, the first distance is equal to the first threshold, and the second distance is equal to the second threshold, so that the folding edge detection result of the target soft package battery cell can be obtained by the above method.
It is understood that the distance obtained in the above embodiments may be a distance in a real space obtained by mapping distances between pixel points in an image to the real space based on imaging parameters (e.g., focal length, object distance, etc.) of a target image.
According to the embodiment of the invention, under the condition that no bright spot exists in the target image, the hem detection result of the target soft-package battery cell is obtained based on the characteristic line in the target image, the hem detection of the target soft-package battery cell can be automatically carried out based on the image processing method, the hem detection efficiency of the soft-package battery cell can be improved, the accuracy of the detection result is higher, and the stability of the quality of the soft-package battery cell module can be further ensured.
Based on the content of any one of the embodiments, the method for extracting the features of the target image to obtain the features of the target hem in the target image specifically includes: and under the condition that the target image comprises a front view and a left view of the target soft package battery cell after the edge folding, acquiring the angle of the first edge folding, the angle of the second edge folding and the distance between the first part of the first edge folding and the first part of the second edge folding based on the front view, and detecting the bright spots and the characteristic lines in the left view.
In particular, the target image may include a front view and a left view of the target flexible pouch cell after crimping.
Based on the front view of the target soft-package cell after the flanging, the angle of the first flanging, the angle of the second flanging, the distance between the first portion of the first flanging and the first portion of the second flanging, and the like can be extracted as the features of the target flanging in the target image.
Based on the left view of the target soft package battery cell after the edge folding, the detection result of whether bright spots exist in the target image or not can be obtained, the characteristic line and the like in the target image can be extracted, and the characteristic line and the like can also be used as the characteristic of the target edge folding in the target image.
For the step of extracting the feature of the target hem in the target image, reference may be made to the foregoing embodiment of the present invention, and details are not described here.
Based on the characteristics of the target edge folding in the target image, the edge folding detection result of the target soft package battery cell is obtained, and the method specifically comprises the following steps: and acquiring a hem detection result of the target soft package battery cell based on at least one of the angle of the first hem, the angle of the second hem, the distance between the first part of the first hem and the first part of the second hem, and whether the bright spot and the characteristic line are detected.
Specifically, for a specific step of obtaining a hem detection result of the target soft package battery cell based on the features of the target hem in the target image obtained from the front view and the left view of the target soft package battery cell after performing the hem, reference may be made to the foregoing embodiment of the present invention, and details are not described here again.
According to the embodiment of the invention, the characteristic extraction is carried out on the front view and the left view of the target soft-package battery cell after the edge folding is carried out, the characteristic of the target edge folding in the target image is obtained, the edge folding detection result of the target soft-package battery cell is obtained based on the characteristic of the target edge folding in the target image, the edge folding detection of the target soft-package battery cell can be automatically carried out based on an image processing method, the edge folding detection efficiency of the soft-package battery cell can be improved, the accuracy of the detection result is higher, and the stability of the quality of the soft-package battery cell module can be further ensured.
The edge folding detection device for the soft-package battery cell provided by the invention is described below, and the edge folding detection device for the soft-package battery cell described below and the edge folding detection method for the soft-package battery cell described above can be referred to correspondingly.
Fig. 4 is a schematic structural diagram of a soft-package cell flanging detection device provided by an embodiment of the invention. Based on the content of any of the above embodiments, as shown in fig. 4, the apparatus includes an image acquisition module 401, a feature extraction module 402, and a hemming detection module 403, wherein:
the image acquisition module 401 is configured to acquire a target image of the target soft package battery cell after edge folding; the target image comprises a front view and a left view of the target soft package battery cell after edge folding;
a feature extraction module 402, configured to perform feature extraction on the target image, to obtain features of a target hem in the target image;
and a hem detection module 403, configured to obtain a hem detection result of the target soft package battery cell based on a feature of the target hem in the target image.
Specifically, the image acquisition module 401, the feature extraction module 402, and the hemming detection module 403 are electrically connected in sequence.
The image acquisition module 401 may acquire a target image of the target soft package battery cell after the edge folding based on the image of the edge folding portion of the target soft package battery cell acquired by the image acquisition device.
The feature extraction module 402 may perform feature extraction on the target image by using a target image processing method to obtain features of the target hem in the target image.
The folding detection module 403 may obtain a folding detection result of the target soft package battery cell based on the feature of the target folding in the target image.
Optionally, the feature extraction module 402 may be specifically configured to, when the target image includes a front view of the target soft package battery cell after being subjected to edge folding, obtain an angle of the first edge folding and an angle of the second edge folding based on the target image;
the folding edge detection module 403 may be specifically configured to determine that a folding edge detection result of the target soft package battery cell is not qualified when a difference between the angle of the first folding edge or the angle of the second folding edge and the target angle is greater than or equal to a target threshold.
Optionally, the feature extraction module 402 may be specifically configured to detect a bright spot and a feature line in the target image when the target image includes a left view of the target soft package battery cell after the edge folding;
the folding detection module 403 may be specifically configured to determine that a folding detection result of the target soft package battery cell is unqualified when a bright spot is detected in the target image.
Optionally, the feature extraction module 402 may be specifically configured to, when the target image includes a front view and a left view of the target soft package battery cell after being subjected to edge folding, obtain, based on the front view, an angle of the first edge folding, an angle of the second edge folding, and a distance between the first portion of the first edge folding and the first portion of the second edge folding, and detect a bright spot and a feature line in the left view;
the folding detection module 403 may be specifically configured to obtain a folding detection result of the target soft package battery cell based on at least one of an angle of the first folding, an angle of the second folding, a distance between the first portion of the first folding and the first portion of the second folding, whether a bright spot is detected, and a characteristic line.
Optionally, the feature extraction module 402 may be further specifically configured to, when a difference between the angle of the first hem and the target angle is smaller than a target threshold, and a difference between the angle of the second hem and the target angle is smaller than the target threshold, obtain, based on the target image, a distance between the first portion of the first hem and the first portion of the second hem;
the folded edge detection module 403 may be further specifically configured to determine that the folded edge detection result of the target soft package battery cell is qualified when a distance between the first portion of the first folded edge and the first portion of the second folded edge is less than or equal to the target distance.
Optionally, the folded edge detection module 403 may be further specifically configured to determine that the folded edge detection result of the target soft package battery cell is unqualified when a distance between the first portion of the first folded edge and the first portion of the second folded edge is greater than the target distance.
Optionally, the folding detection module 403 may be further specifically configured to, when a bright spot is not detected in the target image, obtain a folding detection result of the target soft package battery cell based on the feature line in the target image.
The edge folding detection device for the soft-package battery cell provided by the embodiment of the invention is used for executing the edge folding detection method for the soft-package battery cell provided by the invention, and the implementation mode of the edge folding detection device for the soft-package battery cell is consistent with that of the edge folding detection method for the soft-package battery cell provided by the invention, and the same beneficial effects can be achieved, and the details are not repeated here.
The soft-package battery cell flanging detection device is used for the soft-package battery cell flanging detection method in each embodiment. Therefore, the description and definition in the soft packing cell hemming detection method in the foregoing embodiments can be used for understanding the execution modules in the embodiments of the present invention.
According to the embodiment of the invention, the characteristic extraction is carried out on the target image of the target soft-package battery cell after the edge folding is carried out, the characteristic of the target edge folding in the target image is obtained, the edge folding detection result of the target soft-package battery cell is obtained based on the characteristic of the target edge folding in the target image, the edge folding detection of the target soft-package battery cell can be automatically carried out based on an image processing method, the edge folding detection efficiency of the soft-package battery cell can be improved, the accuracy of the detection result is higher, and the stability of the quality of the soft-package battery cell module can be further ensured.
Fig. 5 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 5: a processor (processor)510, a communication Interface (Communications Interface)520, a memory (memory)530 and a communication bus 540, wherein the processor 510, the communication Interface 520 and the memory 530 communicate with each other via the communication bus 540. The processor 510 may invoke logic instructions stored in the memory 530 and executable on the processor 510 to perform the pouch cell pucking detection method provided by the above-described method embodiments, the method comprising: acquiring a target image of the target soft package battery cell after edge folding; the target image comprises a front view and a left view of the target soft package battery cell after edge folding; extracting the features of the target image to obtain the features of the target folded edge in the target image; and acquiring a folding detection result of the target soft package battery cell based on the characteristics of the target folding in the target image.
Furthermore, the logic instructions in the memory 530 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The processor 510 in the electronic device provided in the embodiment of the present invention may call the logic instruction in the memory 530, and the implementation manner of the processor is consistent with the implementation manner of the soft package cell flanging detection method provided in the present invention, and the same beneficial effects may be achieved, which is not described herein again.
In another aspect, an embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, where the computer program includes program instructions, and when the program instructions are executed by a computer, the computer is capable of executing the method for detecting a soft packing cell fold provided in the above-mentioned method embodiments, where the method includes: acquiring a target image of the target soft package battery cell after edge folding; the target image comprises a front view and a left view of the target soft package battery cell after edge folding; extracting the features of the target image to obtain the features of the target folded edge in the target image; and acquiring a folding detection result of the target soft package battery cell based on the characteristics of the target folding in the target image.
When the computer program product provided by the embodiment of the present invention is executed, the above-mentioned method for detecting a folded edge of a soft package cell is implemented, and a specific implementation manner of the method is consistent with the implementation manner described in the foregoing method embodiment, and the same beneficial effects can be achieved, and details are not described here.
In another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented by a processor to execute the method for detecting a soft pack cell fold provided in the foregoing embodiments, where the method includes: acquiring a target image of the target soft package battery cell after edge folding; the target image comprises a front view and a left view of the target soft package battery cell after edge folding; extracting the features of the target image to obtain the features of the target folded edge in the target image; and acquiring a folding detection result of the target soft package battery cell based on the characteristics of the target folding in the target image.
When a computer program stored on a non-transitory computer-readable storage medium provided in an embodiment of the present invention is executed, the method for detecting a soft package cell edge fold is implemented, and a specific implementation manner of the method is consistent with that described in the foregoing method, and the same beneficial effects can be achieved, and details are not described here.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. The soft package battery cell flanging detection method is characterized by comprising the following steps:
acquiring a target image of the target soft package battery cell after edge folding; the target image comprises a front view and a left view of the target soft package battery cell after the edge folding;
extracting the features of the target image to obtain the features of the target folded edge in the target image;
and acquiring a folding detection result of the target soft package battery cell based on the characteristics of the target folding in the target image.
2. The soft package battery cell flanging detection method according to claim 1, wherein the performing feature extraction on the target image to obtain features of a target flanging in the target image specifically comprises:
under the condition that the target image comprises a front view of the target soft package battery cell after the edge folding, acquiring a first edge folding angle and a second edge folding angle based on the target image;
the method for detecting the edge folding of the soft package battery cell based on the features of the target edge folding in the target image includes:
and determining the hem detection result of the target soft package battery cell as unqualified under the condition that the difference between the angle of the first hem or the angle of the second hem and the target angle is greater than or equal to a target threshold value.
3. The soft package battery cell flanging detection method according to claim 1, wherein the performing feature extraction on the target image to obtain features of a target flanging in the target image specifically comprises:
detecting bright spots and characteristic lines in the target image under the condition that the target image comprises the left view of the target soft package battery cell subjected to edge folding;
the method for detecting the edge folding of the soft package battery cell based on the features of the target edge folding in the target image includes:
and determining the hem detection result of the target soft package battery cell as unqualified under the condition that the bright spots exist in the target image.
4. The soft package battery cell flanging detection method according to claim 1, wherein the performing feature extraction on the target image to obtain features of a target flanging in the target image specifically comprises:
under the condition that the target image comprises a front view and a left view of the target soft package battery core subjected to edge folding, acquiring an angle of a first edge folding, an angle of a second edge folding and a distance between a first part of the first edge folding and a first part of the second edge folding based on the front view, and detecting a bright spot and a characteristic line in the left view;
the method for detecting the edge folding of the soft package battery cell based on the features of the target edge folding in the target image includes:
and acquiring a hem detection result of the target soft package battery cell based on at least one of the angle of the first hem, the angle of the second hem, the distance between the first part of the first hem and the first part of the second hem, whether the bright spot is detected and the characteristic line.
5. The soft package core flanging detection method of claim 2, wherein the performing feature extraction on the target image to obtain the features of the target flanging in the target image further comprises:
acquiring a distance between a first portion of the first fold and a first portion of the second fold based on the target image when a difference between the angle of the first fold and the target angle is less than the target threshold and a difference between the angle of the second fold and the target angle is less than the target threshold;
the method for detecting the edge folding of the soft package battery cell based on the characteristics of the target edge folding in the target image further comprises the following steps:
and determining that the flanging detection result of the target soft package battery cell is qualified under the condition that the distance between the first part of the first flanging and the first part of the second flanging is smaller than or equal to the target distance.
6. The method according to claim 5, wherein the obtaining of the fold detection result of the target soft-package battery cell based on the feature of the target fold in the target image further comprises:
and under the condition that the distance between the first part of the first flanging and the first part of the second flanging is larger than the target distance, determining the flanging detection result of the target soft package battery cell as unqualified.
7. The method according to claim 3, wherein the obtaining of the fold detection result of the target soft-package battery cell based on the feature of the target fold in the target image further comprises:
and under the condition that the bright spots are not detected in the target image, acquiring a flanging detection result of the target soft package battery cell based on the characteristic line in the target image.
8. The utility model provides a soft-packaged electrical core hem detection device which characterized in that includes:
the image acquisition module is used for acquiring a target image of the target soft package battery cell after edge folding; the target image comprises a front view and a left view of the target soft package battery cell after the edge folding;
the characteristic extraction module is used for extracting the characteristics of the target image to obtain the characteristics of a target folded edge in the target image;
and the flanging detection module is used for acquiring a flanging detection result of the target soft package battery cell based on the characteristics of the target flanging in the target image.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the pouch cell hemming detection method according to any of claims 1 to 7.
10. A non-transitory computer-readable storage medium, having stored thereon a computer program, wherein the computer program, when being executed by a processor, is adapted to carry out the steps of the method of detecting a soft pack cell edge fold according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111310279.XA CN113744273B (en) | 2021-11-08 | 2021-11-08 | Soft package battery cell edge folding detection method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111310279.XA CN113744273B (en) | 2021-11-08 | 2021-11-08 | Soft package battery cell edge folding detection method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113744273A true CN113744273A (en) | 2021-12-03 |
| CN113744273B CN113744273B (en) | 2022-02-18 |
Family
ID=78727603
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111310279.XA Active CN113744273B (en) | 2021-11-08 | 2021-11-08 | Soft package battery cell edge folding detection method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113744273B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103512888A (en) * | 2013-06-05 | 2014-01-15 | 北京化工大学 | Cigarette packet seal defect detecting system based on image identification technology |
| CN203562487U (en) * | 2013-11-30 | 2014-04-23 | 东莞市金源电池科技有限公司 | Polymer thin cell with double folding edges |
| CN106355597A (en) * | 2016-08-31 | 2017-01-25 | 杭州沃朴物联科技有限公司 | Monocular vision based image processing method for automatic measuring robot for steel plate folding angle |
| US20170293802A1 (en) * | 2016-04-07 | 2017-10-12 | Fujitsu Limited | Image processing device and image processing method |
| CN113129260A (en) * | 2021-03-11 | 2021-07-16 | 广东工业大学 | Automatic detection method and device for internal defects of lithium battery cell |
| CN213856505U (en) * | 2020-09-30 | 2021-08-03 | 武汉逸飞激光股份有限公司 | Electricity core subassembly of bending |
| CN113205509A (en) * | 2021-05-24 | 2021-08-03 | 山东省人工智能研究院 | Blood vessel plaque CT image segmentation method based on position convolution attention network |
| CN113552133A (en) * | 2021-06-30 | 2021-10-26 | 广东利元亨智能装备股份有限公司 | Cell skirt edge cracking detection method and visual detection device |
-
2021
- 2021-11-08 CN CN202111310279.XA patent/CN113744273B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103512888A (en) * | 2013-06-05 | 2014-01-15 | 北京化工大学 | Cigarette packet seal defect detecting system based on image identification technology |
| CN203562487U (en) * | 2013-11-30 | 2014-04-23 | 东莞市金源电池科技有限公司 | Polymer thin cell with double folding edges |
| US20170293802A1 (en) * | 2016-04-07 | 2017-10-12 | Fujitsu Limited | Image processing device and image processing method |
| CN106355597A (en) * | 2016-08-31 | 2017-01-25 | 杭州沃朴物联科技有限公司 | Monocular vision based image processing method for automatic measuring robot for steel plate folding angle |
| CN213856505U (en) * | 2020-09-30 | 2021-08-03 | 武汉逸飞激光股份有限公司 | Electricity core subassembly of bending |
| CN113129260A (en) * | 2021-03-11 | 2021-07-16 | 广东工业大学 | Automatic detection method and device for internal defects of lithium battery cell |
| CN113205509A (en) * | 2021-05-24 | 2021-08-03 | 山东省人工智能研究院 | Blood vessel plaque CT image segmentation method based on position convolution attention network |
| CN113552133A (en) * | 2021-06-30 | 2021-10-26 | 广东利元亨智能装备股份有限公司 | Cell skirt edge cracking detection method and visual detection device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113744273B (en) | 2022-02-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3454250B1 (en) | Facial image processing method and apparatus and storage medium | |
| US11087169B2 (en) | Image processing apparatus that identifies object and method therefor | |
| JP6294615B2 (en) | System and method for detection and tracking of moving objects | |
| CN106127690A (en) | A kind of quick joining method of unmanned aerial vehicle remote sensing image | |
| CN113506957B (en) | Cutting method and device for soft-package battery cell tab, electronic equipment and storage medium | |
| WO2022082999A1 (en) | Object recognition method and apparatus, and terminal device and storage medium | |
| CN113192179A (en) | Three-dimensional reconstruction method based on binocular stereo vision | |
| CN107452028B (en) | Method and device for determining position information of target image | |
| CN115018846B (en) | AI intelligent camera-based multi-target crack defect detection method and device | |
| CN112084453A (en) | Three-dimensional virtual display system, method, computer equipment, terminal and storage medium | |
| CN111652082A (en) | Face living body detection method and device | |
| CN107610097A (en) | Instrument localization method, device and terminal device | |
| CN113985830A (en) | Feeding control method and device for sealing nail, electronic equipment and storage medium | |
| CN111553881A (en) | Method and system for detecting iron tower deformation based on three-dimensional point cloud identification | |
| CN113744273B (en) | Soft package battery cell edge folding detection method and device, electronic equipment and storage medium | |
| CN110310295A (en) | A kind of weld profile extracting method and system | |
| CN114897999B (en) | Object pose recognition method, electronic device, storage medium, and program product | |
| CN116758529A (en) | Line identification method, device and computer equipment | |
| CN110956664A (en) | Real-time camera position repositioning method for handheld three-dimensional scanning system | |
| CN114842057A (en) | Distance information complementing method, apparatus, storage medium, and computer program product | |
| CN114549825A (en) | Target detection method and device, electronic equipment and storage medium | |
| CN111630569B (en) | Binocular matching method, visual imaging device and device with storage function | |
| JP4298283B2 (en) | Pattern recognition apparatus, pattern recognition method, and program | |
| CN112949641A (en) | Image segmentation method, electronic device and computer-readable storage medium | |
| CN110796050A (en) | Target object identification method and related device in unmanned aerial vehicle inspection process |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |