CN116596932A - Method, device, equipment and storage medium for detecting appearance of battery top cover pole - Google Patents
Method, device, equipment and storage medium for detecting appearance of battery top cover pole Download PDFInfo
- Publication number
- CN116596932A CN116596932A CN202310878112.6A CN202310878112A CN116596932A CN 116596932 A CN116596932 A CN 116596932A CN 202310878112 A CN202310878112 A CN 202310878112A CN 116596932 A CN116596932 A CN 116596932A
- Authority
- CN
- China
- Prior art keywords
- appearance
- pole
- image
- top cover
- appearance image
- 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
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 238000001514 detection method Methods 0.000 claims abstract description 142
- 238000003384 imaging method Methods 0.000 claims abstract description 90
- 238000003708 edge detection Methods 0.000 claims abstract description 17
- 238000004519 manufacturing process Methods 0.000 claims description 22
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 11
- 230000009466 transformation Effects 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 9
- 230000003287 optical effect Effects 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000004806 packaging method and process Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 5
- 230000007547 defect Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000000007 visual effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005282 brightening Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000003292 glue Substances 0.000 description 1
- 238000003702 image correction Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
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
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10141—Special mode during image acquisition
- G06T2207/10152—Varying illumination
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Abstract
The invention relates to the technical field of image data processing, and discloses a method, a device, equipment and a storage medium for detecting the appearance of a battery top cover pole, wherein the method comprises the following steps: acquiring a surface appearance image of a pole on a top cover of a battery to be detected by using a prism module through a preset multi-angle imaging strategy; carrying out image registration on the surface appearance image of the pole by using an edge detection operator to obtain a current pole appearance image; channel shuffling is carried out on the current pole appearance image to obtain a target pole appearance image; identifying the target pole appearance image based on a multi-scale tag propagation identification algorithm; through the mode, the prism module is utilized to collect the surface appearance image of the pole through the preset multi-angle imaging strategy, then the surface appearance image of the pole is subjected to image registration and channel shuffling, and then the target pole appearance image is identified based on the multi-scale label propagation identification algorithm, so that the accuracy of detecting the appearance of the battery top cover pole can be effectively improved, and the detection cost is reduced.
Description
Technical Field
The present invention relates to the field of image data processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for detecting an appearance of a battery top cover post.
Background
In the production process of the new energy battery top cover, various mechanical, acoustic, optical and electric complex environments or numerous procedures possibly damage the appearance of the new energy battery top cover, especially the new energy battery top cover pole is made into a product part with defects, no matter for performance, attractive appearance or safety, very strict requirements are required for product quality, so that the surface defect detection of the new energy battery top cover pole is an indispensable important link, currently common detection modes can be divided into two modes of manual detection and automatic detection, the manual detection usually refers to naked eye visual detection or visual detection by means of a relatively simple image acquisition station, but the detection modes are very dependent on manual work and consume a great amount of labor cost by adopting one-by-one detection, the automatic detection is to acquire product surface information from 4 directions and the top surface of a side wall vertically, 5 directions are all used for judging whether the product is abnormal or not by using image detection software, and the detection modes require 5 sets of cameras for tilting or horizontally installing the side wall, the occupied space is large, the cost is high, and the defects are short, and the current common detection modes have very low cost, and the appearance detection mode is very accurate.
The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.
Disclosure of Invention
The invention mainly aims to provide a method, a device, equipment and a storage medium for detecting the appearance of a battery top cover pole, and aims to solve the technical problems of lower accuracy and higher detection cost in detecting the appearance of the battery top cover pole in the prior art.
In order to achieve the above object, the present invention provides a battery top cover post appearance detection method, comprising the steps of:
acquiring a surface appearance image of a pole on a top cover of a battery to be detected by using a prism module through a preset multi-angle imaging strategy;
carrying out image registration on the surface appearance image of the polar column through an edge detection operator to obtain a current polar column appearance image;
channel shuffling is carried out on the current pole appearance image to obtain a target pole appearance image;
and identifying the appearance image of the target pole based on a multi-scale label propagation identification algorithm so as to realize appearance detection of the pole on the battery top cover to be detected.
Optionally, the collecting, by using a prism module, the surface appearance image of the post on the top cover of the battery to be detected through a preset multi-angle imaging strategy includes:
Acquiring production line production beats of a battery top cover to be detected, and determining a photographing mode of target photographing equipment arranged right above the prism module according to the production line production beats;
acquiring the actual detection requirement of a user, and determining a light source lighting mode according to the actual detection requirement;
detecting the current distance between the lower bottom surface of the prism module arranged right above the target detection area of the battery to be detected and the upper surface of the target detection area;
when the current distance is a preset distance threshold value, acquiring the current connection state of the light source integrated on the prism module and the light source controller;
when the current connection state is a connection success state, acquiring lens focus cycles of target photographing equipment;
determining the imaging definition of the target photographing equipment according to the lens focal circle;
and when the imaging definition is greater than or equal to a preset imaging definition threshold, acquiring a surface appearance image of the pole on the battery top cover to be detected by utilizing a prism module through a preset multi-angle imaging strategy according to the photographing mode and the light source lighting mode.
Optionally, when the imaging definition is greater than or equal to a preset imaging definition threshold, acquiring, by using a prism module, a surface appearance image of a pole on a top cover of a battery to be detected according to the photographing mode and the light source lighting mode by a preset multi-angle imaging strategy, including:
When the imaging definition is greater than or equal to a preset imaging definition threshold, a light source integrated on the prism module is lightened according to the light source lightening mode;
in the lighting process of the light source, reflecting the light rays of the light source by utilizing a prism module through a preset multi-angle imaging strategy to obtain an imaging light path;
obtaining a pole top reflection imaging light path and a pole side wall reflection imaging light path according to the imaging light path;
acquiring an appearance image of the top surface of the pole on the top cover of the battery to be detected according to the photographing mode and the pole top reflection imaging optical path;
acquiring an appearance image of the side wall surface of the pole on the battery top cover to be detected according to the photographing mode and the pole side wall reflection imaging optical path;
and determining the surface appearance image of the pole on the battery top cover to be detected according to the top surface appearance image and the side wall surface appearance image.
Optionally, the performing image registration on the surface appearance image of the pole by using an edge detection operator to obtain a current pole appearance image, including:
determining a diagonal convolution template and a square window according to the edge detection operator;
performing image gradient calculation on the surface appearance image of the polar column through the diagonal convolution template and the square window to obtain a multidirectional gradient value of the appearance image;
Determining global edge data of the surface appearance image of the polar column according to the appearance image multi-direction gradient values;
determining standard surface appearance global edge data;
carrying out affine transformation on the standard surface appearance global edge data and the global edge data of the surface appearance image of the polar column to obtain a current affine transformation result;
and carrying out image registration on the surface appearance image of the polar column according to the current affine transformation result through a SIFT algorithm to obtain the current polar column appearance image.
Optionally, the performing channel shuffling on the current pole appearance image to obtain a target pole appearance image includes:
carrying out graying treatment on the current pole appearance image to obtain a pole appearance gray image;
calculating the gray value, the total number of pixel points and a central neighborhood set of the polar column appearance gray image;
performing mean value filtering on the pole appearance gray level image according to the gray level value, the total number of pixel points and the central neighborhood set;
carrying out local gray stretching on the post appearance gray image subjected to mean value filtering;
grouping the stretched pole appearance gray images, and respectively carrying out data enhancement on a plurality of groups of stretched pole appearance gray images through multi-channel multithreading;
And carrying out channel shuffling on the post appearance gray level images after the data enhancement through a plurality of groups of convolution to obtain target post appearance images.
Optionally, the identifying the appearance image of the target pole based on the multi-scale tag propagation identification algorithm to realize appearance detection of the pole on the battery top cover to be detected includes:
extracting features of the target pole appearance image to obtain pole appearance image features;
transposing the pole appearance image features to obtain global pole appearance image features and depth local appearance image features;
generating a multi-scale image feature set according to the global polar column appearance image features and the depth local features by utilizing a multi-scale feature generation strategy;
calculating the label propagation similarity between the multi-scale image feature set and the global polar post appearance image feature based on a multi-scale label propagation recognition algorithm, and calculating the cosine similarity between the multi-scale image feature set and the depth local appearance image feature;
generating a Gaussian similarity matrix according to the tag propagation similarity and the cosine similarity;
and identifying the Gaussian similarity matrix by a target appearance identification model trained by a WOA-SVM algorithm so as to realize appearance detection of the pole on the top cover of the battery to be detected.
Optionally, the identifying the appearance image of the target pole based on the multi-scale tag propagation identification algorithm to realize appearance detection of the pole on the battery top cover to be detected further includes:
obtaining appearance detection duration and appearance detection accuracy of the pole on the top cover of the battery to be detected;
when the appearance detection duration is smaller than the human detection duration and the appearance detection accuracy is larger than the human detection accuracy, acquiring the detection cost of the appearance image of the target pole;
when the detection cost of the target pole appearance image is lower than the preset detection cost, packaging the appearance detection flow of the pole on the top cover of the battery to be detected to obtain a battery appearance detection strategy;
and detecting the surfaces of the pole posts on the top covers of other batteries through the battery appearance detection strategy.
In addition, in order to achieve the above object, the present invention also provides a battery top cover post appearance detection device, including:
the acquisition module is used for acquiring the surface appearance image of the pole on the top cover of the battery to be detected through a preset multi-angle imaging strategy by utilizing the prism module;
the registration module is used for carrying out image registration on the surface appearance image of the polar column through an edge detection operator to obtain a current polar column appearance image;
The shuffling module is used for carrying out channel shuffling on the current pole appearance image to obtain a target pole appearance image;
the identification module is used for identifying the appearance image of the target pole based on a multi-scale tag propagation identification algorithm so as to realize appearance detection of the pole on the battery top cover to be detected.
In addition, in order to achieve the above object, the present invention also proposes a battery top cover pole appearance detection apparatus comprising: the battery top cap post appearance detection device comprises a memory, a processor and a battery top cap post appearance detection program stored on the memory and capable of running on the processor, wherein the battery top cap post appearance detection program is configured to realize the battery top cap post appearance detection method.
In addition, in order to achieve the above object, the present invention also proposes a storage medium having stored thereon a battery top cap post appearance detection program which, when executed by a processor, implements the battery top cap post appearance detection method as described above.
According to the battery top cover pole appearance detection method, the prism module is utilized to collect the surface appearance image of the pole on the battery top cover to be detected through a preset multi-angle imaging strategy; carrying out image registration on the surface appearance image of the polar column through an edge detection operator to obtain a current polar column appearance image; channel shuffling is carried out on the current pole appearance image to obtain a target pole appearance image; identifying the appearance image of the target pole based on a multi-scale label propagation identification algorithm so as to realize appearance detection of the pole on the battery top cover to be detected; through the mode, the prism module is utilized to collect the surface appearance image of the pole through the preset multi-angle imaging strategy, then the surface appearance image of the pole is subjected to image registration and channel shuffling, and then the target pole appearance image is identified based on the multi-scale label propagation identification algorithm, so that the accuracy of detecting the appearance of the battery top cover pole can be effectively improved, and the detection cost is reduced.
Drawings
Fig. 1 is a schematic structural diagram of a battery top cover pole appearance detection device in a hardware operation environment according to an embodiment of the present invention;
FIG. 2 is a flowchart of a first embodiment of a method for detecting the appearance of a battery top cap post according to the present invention;
FIG. 3 is a schematic diagram of a pole shape of an embodiment of a method for detecting an appearance of a pole of a battery top cover according to the present invention;
FIG. 4 is a flowchart of a second embodiment of a method for detecting the appearance of a battery top cap post according to the present invention;
FIG. 5 is a schematic view of an imaging system according to an embodiment of the present invention;
fig. 6 is a schematic functional block diagram of a first embodiment of the battery top cap post appearance detection device according to the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a battery top cover pole appearance detection device in a hardware operation environment according to an embodiment of the present invention.
As shown in fig. 1, the battery top cover post appearance detection apparatus may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) Memory or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the structure shown in fig. 1 does not constitute a limitation of the battery top cap post appearance detection device, and may include more or fewer components than shown, or certain components may be combined, or a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a battery top cover post appearance detection program may be included in a memory 1005 as one type of storage medium.
In the battery top cover post appearance detection device shown in fig. 1, the network interface 1004 is mainly used for data communication with a network integrated platform workstation; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the battery top cover pole appearance detection device of the present invention may be disposed in the battery top cover pole appearance detection device, where the battery top cover pole appearance detection device invokes a battery top cover pole appearance detection program stored in the memory 1005 through the processor 1001, and executes the battery top cover pole appearance detection method provided by the embodiment of the present invention.
Based on the hardware structure, the embodiment of the battery top cover pole appearance detection method is provided.
Referring to fig. 2, fig. 2 is a flowchart illustrating a first embodiment of a method for detecting the appearance of a battery top cap post according to the present invention.
In a first embodiment, the battery top cover post appearance detection method includes the steps of:
and S10, acquiring a surface appearance image of a pole on the top cover of the battery to be detected by using a prism module through a preset multi-angle imaging strategy.
It should be noted that, the execution body of the embodiment is a battery top cover pole appearance detection device, and may be other devices that can implement the same or similar functions, such as an appearance detection system, etc., and this embodiment is not limited thereto, and in the embodiment, the appearance detection system is taken as an example for explanation.
It should be understood that the surface appearance image refers to an appearance image of a post on a top cover of a battery to be detected, the shape of the post includes, but is not limited to, a circle, a rounded rectangle, and a rounded pentagon, and reference may be made specifically to fig. 3, fig. 3 is a schematic diagram of the post shape, specifically 3 (a) indicates a circular post, 3 (b) indicates a rounded rectangular post, 3 (c) indicates a rounded pentagon post, the battery to be detected may be a new energy battery, the surface appearance image includes a top surface appearance image and a side wall surface appearance image, the preset multi-angle imaging strategy refers to a strategy of imaging from multiple angles by using a reflection principle, that is, the surface appearance image of the top surface and multiple side walls of the post may be acquired at one time by the preset multi-angle imaging strategy by using a prism module.
And S20, carrying out image registration on the surface appearance image of the pole by an edge detection operator to obtain the current pole appearance image.
It can be understood that the current pole appearance image refers to an appearance image obtained by performing image registration on the collected surface appearance image of the pole, and the edge detection operator refers to an operator performing image registration by adopting an edge detection and enhancement mode.
Further, step S20 includes: determining a diagonal convolution template and a square window according to the edge detection operator; performing image gradient calculation on the surface appearance image of the polar column through the diagonal convolution template and the square window to obtain a multidirectional gradient value of the appearance image; determining global edge data of the surface appearance image of the polar column according to the appearance image multi-direction gradient values; determining standard surface appearance global edge data; carrying out affine transformation on the standard surface appearance global edge data and the global edge data of the surface appearance image of the polar column to obtain a current affine transformation result; and carrying out image registration on the surface appearance image of the polar column according to the current affine transformation result through a SIFT algorithm to obtain the current polar column appearance image.
It should be understood that the diagonal convolution template and the square window refer to parameters for calculating an image gradient, that is, the diagonal convolution template and the square window are used for calculating the image gradient of the surface appearance image of the pole, then the surface appearance image with the largest gradient value is selected from the multi-directional gradient values of the appearance image, in order to effectively improve the accuracy of image registration, after global edge data of the surface appearance image of the pole is obtained, affine transformation is respectively carried out on the global edge data of the standard surface appearance and the global edge data of the surface appearance image of the pole at the same time, so as to complete image correction and alignment on the global edge data of the standard surface appearance and the global edge data of the surface appearance image of the pole, and then the SIFT algorithm is used for carrying out image registration on the affine transformed standard surface appearance global edge data and the global edge data of the surface appearance image of the pole, so as to obtain the current pole appearance image.
And step S30, carrying out channel shuffling on the current pole appearance image to obtain a target pole appearance image.
Further, step S30 includes: carrying out graying treatment on the current pole appearance image to obtain a pole appearance gray image; calculating the gray value, the total number of pixel points and a central neighborhood set of the polar column appearance gray image; performing mean value filtering on the pole appearance gray level image according to the gray level value, the total number of pixel points and the central neighborhood set; carrying out local gray stretching on the post appearance gray image subjected to mean value filtering; grouping the stretched pole appearance gray images, and respectively carrying out data enhancement on a plurality of groups of stretched pole appearance gray images through multi-channel multithreading; and carrying out channel shuffling on the post appearance gray level images after the data enhancement through a plurality of groups of convolution to obtain target post appearance images.
It can be understood that the post appearance gray image refers to an image after the current post appearance gray image is subjected to gray processing, then gray values, total number of pixels and a center neighborhood set of the post appearance gray image are calculated respectively, then the post appearance gray image is subjected to mean filtering by using the gray values, the total number of pixels and the center neighborhood set to finish denoising the post appearance gray image, then the post appearance gray image subjected to mean filtering is subjected to local gray stretching, and as the number and the types of defects of the post on the top cover of the battery to be detected are less, after the post appearance gray image subjected to stretching is obtained, the post appearance gray image subjected to stretching is grouped, then a plurality of groups of post appearance gray images subjected to stretching are subjected to data enhancement by adopting multi-channel multithreading, wherein the data enhancement comprises but is not limited to rotation, translation, scaling, mirroring, color difference, noise disturbance and the like, and then the post appearance gray image subjected to data enhancement is subjected to channel shuffling by a plurality of groups of convolution, so that the target post appearance gray image is obtained.
And S40, identifying the appearance image of the target pole based on a multi-scale label propagation identification algorithm so as to realize appearance detection of the pole on the battery top cover to be detected.
It can be understood that when the appearance image of the target pole is obtained, the appearance image of the target pole is identified by utilizing a multi-scale tag propagation identification algorithm so as to obtain the appearance defect of the pole on the top cover of the battery to be detected.
Further, step S40 includes: extracting features of the target pole appearance image to obtain pole appearance image features; transposing the pole appearance image features to obtain global pole appearance image features and depth local appearance image features; generating a multi-scale image feature set according to the global polar column appearance image features and the depth local features by utilizing a multi-scale feature generation strategy; calculating the label propagation similarity between the multi-scale image feature set and the global polar post appearance image feature based on a multi-scale label propagation recognition algorithm, and calculating the cosine similarity between the multi-scale image feature set and the depth local appearance image feature; generating a Gaussian similarity matrix according to the tag propagation similarity and the cosine similarity; and identifying the Gaussian similarity matrix by a target appearance identification model trained by a WOA-SVM algorithm so as to realize appearance detection of the pole on the top cover of the battery to be detected.
It should be understood that the post appearance image features refer to features capable of identifying different target post appearance images, then the post appearance image features are set to be global post appearance image features and depth local appearance image features, then a multi-scale image feature set is generated according to the global post appearance image features and the depth local features by utilizing a multi-scale feature generation strategy, the tag propagation similarity refers to the similarity between the multi-scale image feature set and the global post appearance image features, the cosine similarity refers to the similarity between the multi-scale image feature set and the depth local appearance image features, the Gaussian similarity matrix refers to a matrix generated by the tag propagation similarity and the cosine similarity, all image features of the post on the top of the battery to be detected are represented by the Gaussian similarity matrix, and then the appearance defect of the post on the top of the battery to be detected is identified by utilizing a target appearance identification model trained by a WOA-SVM algorithm, and the appearance defect comprises but is not limited to plastic breakage, scalding, glue, side wall aluminum wires and the like.
Further, after step S40, the method further includes: obtaining appearance detection duration and appearance detection accuracy of the pole on the top cover of the battery to be detected; when the appearance detection duration is smaller than the human detection duration and the appearance detection accuracy is larger than the human detection accuracy, acquiring the detection cost of the appearance image of the target pole; when the detection cost of the target pole appearance image is lower than the preset detection cost, packaging the appearance detection flow of the pole on the top cover of the battery to be detected to obtain a battery appearance detection strategy; and detecting the surfaces of the pole posts on the top covers of other batteries through the battery appearance detection strategy.
It should be understood that after the appearance of the pole on the battery top cover to be detected is detected, the appearance detection duration and the appearance detection accuracy are obtained, then whether all conditions that the appearance detection duration is smaller than the human detection duration and the appearance detection accuracy is larger than the human detection accuracy are met is judged, if yes, the appearance detection mode of the embodiment is better than the prior art in terms of accuracy and duration, then whether the condition that the detection cost of the appearance image of the target pole is lower than the preset detection cost is continuously judged, if yes, the appearance detection mode of the embodiment is better than the prior art in terms of cost is judged, at this time, the appearance detection flow of the pole on the battery top cover to be detected can be packaged into a battery appearance detection strategy, and the surfaces of the poles on other battery top covers can be detected by utilizing the battery appearance detection strategy.
In the embodiment, the prism module is utilized to collect the surface appearance image of the pole on the top cover of the battery to be detected through a preset multi-angle imaging strategy; carrying out image registration on the surface appearance image of the polar column through an edge detection operator to obtain a current polar column appearance image; channel shuffling is carried out on the current pole appearance image to obtain a target pole appearance image; identifying the appearance image of the target pole based on a multi-scale label propagation identification algorithm so as to realize appearance detection of the pole on the battery top cover to be detected; through the mode, the prism module is utilized to collect the surface appearance image of the pole through the preset multi-angle imaging strategy, then the surface appearance image of the pole is subjected to image registration and channel shuffling, and then the target pole appearance image is identified based on the multi-scale label propagation identification algorithm, so that the accuracy of detecting the appearance of the battery top cover pole can be effectively improved, and the detection cost is reduced.
In an embodiment, as shown in fig. 4, a second embodiment of the method for detecting the appearance of a battery top cap post according to the present invention is provided based on the first embodiment, and the step S10 includes:
step S101, acquiring production line production beats of a battery top cover to be detected, and determining a photographing mode of target photographing equipment arranged right above the prism module according to the production line production beats.
It should be understood that the production line tact refers to the tact of the production line for producing the battery top cover to be detected, in order not to affect the production efficiency and the detection efficiency of the production line, the tact for detecting the battery top cover to be detected in this embodiment is kept consistent with the tact of the production line for detecting the battery top cover to be detected, the photographing mode refers to the photographing mode of photographing the pole on the battery top cover to be detected by the target photographing device arranged right above the prism module, the photographing mode includes but is not limited to normally-on static photographing by the light source, dynamic flying photographing by the stroboscopic light source with the brightness enhanced, and the like, the target photographing device may be an area array camera, and the resolution of the target photographing device may be determined according to the actual detection requirement of the user.
Step S102, obtaining the actual detection requirement of a user, and determining a light source lighting mode according to the actual detection requirement.
It will be appreciated that the actual detection requirement refers to a requirement of a user for detecting a pole on a battery top cover to be detected, and the light source lighting mode refers to a mode for lighting a light source, and the light source lighting mode includes, but is not limited to, a light source normal lighting mode and a light source brightening strobe working mode.
Step S103, detecting the current distance between the lower bottom surface of the prism module set right above the target detection area of the battery to be detected and the upper surface of the target detection area.
It should be understood that the current pitch refers to the distance between the lower bottom surface of the prism module and the upper surface of the target detection area, the prism module is disposed directly above the target detection area of the battery to be detected, and it is necessary to ensure that the center of the prism module is directly opposite to the center of the target detection area when disposed.
Step S104, when the current distance is a preset distance threshold value, the current connection state of the light source integrated on the prism module and the light source controller is obtained.
It can be understood that after the current pitch is detected, whether the current pitch is a preset pitch threshold is determined, if yes, the current connection state of the light source integrated on the prism module and the light source controller is determined, and the preset pitch threshold can be 5mm.
Step S105, when the current connection state is a connection success state, acquiring lens focal circle data of the target photographing device.
It should be understood that after the current connection state of the light source and the light source controller is obtained, whether the current connection state is a connection success state is judged, if so, whether the center of the lens arranged right above the prism module is right opposite to the center of the prism module is continuously judged, and if so, the lens focal circle data of the target photographing equipment is obtained.
And step S106, determining the imaging definition of the target photographing equipment according to the lens focal circle.
And S107, when the imaging definition is greater than or equal to a preset imaging definition threshold, acquiring surface appearance images of the pole on the top cover of the battery to be detected by utilizing a prism module through a preset multi-angle imaging strategy according to the photographing mode and the light source lighting mode.
It can be understood that after the imaging definition of the target photographing device is obtained, whether the imaging definition of the target photographing device is greater than or equal to a preset imaging definition threshold is judged, if yes, a prism module is utilized to collect the surface appearance image of the pole on the top cover of the battery to be detected according to a photographing mode and a light source lighting mode through a preset multi-angle imaging strategy, and if not, a lens focal circle is required to be adjusted until six-face images are clear.
Further, when the imaging definition is greater than or equal to a preset imaging definition threshold, acquiring a surface appearance image of a pole on a battery top cover to be detected by using a prism module through a preset multi-angle imaging strategy according to the photographing mode and the light source lighting mode, including: when the imaging definition is greater than or equal to a preset imaging definition threshold, a light source integrated on the prism module is lightened according to the light source lightening mode; in the lighting process of the light source, reflecting the light rays of the light source by utilizing a prism module through a preset multi-angle imaging strategy to obtain an imaging light path; obtaining a pole top reflection imaging light path and a pole side wall reflection imaging light path according to the imaging light path; acquiring an appearance image of the top surface of the pole on the top cover of the battery to be detected according to the photographing mode and the pole top reflection imaging optical path; acquiring an appearance image of the side wall surface of the pole on the battery top cover to be detected according to the photographing mode and the pole side wall reflection imaging optical path; and determining the surface appearance image of the pole on the battery top cover to be detected according to the top surface appearance image and the side wall surface appearance image.
It should be noted that, referring to fig. 5, fig. 5 is a schematic view of an optical path of the imaging system, and specifically includes: the device comprises an area array camera, a lens, a prism module, a light source and a pole on a battery top cover to be detected, wherein the prism module comprises an upper prism, a lower prism, a pole top reflection imaging light path and a pole side wall reflection imaging light path.
It can be understood that when it is determined that the imaging definition is greater than or equal to the preset imaging definition threshold, the light source arranged on the prism module is lightened according to the light source lighting mode, the light source emits light beams at this time, the prism module is utilized to reflect light rays of the light source through a preset multi-angle imaging strategy, the reflected imaging light path at this time comprises a pole top reflection imaging light path and a pole side wall reflection imaging light path, then the photographing mode and the pole top reflection imaging light path are utilized to collect top surface appearance images of poles on the top cover of the battery to be detected, and the photographing mode and the pole side wall reflection imaging light path are utilized to collect side wall surface appearance images of the poles on the top cover of the battery to be detected, and the top surface appearance images and the side wall surface appearance images form surface appearance images of the poles on the top cover of the battery to be detected.
According to the embodiment, the production line production beat of the battery top cover to be detected is obtained, and the photographing mode of the target photographing device arranged right above the prism module is determined according to the production line production beat; acquiring the actual detection requirement of a user, and determining a light source lighting mode according to the actual detection requirement; detecting the current distance between the lower bottom surface of the prism module arranged right above the target detection area of the battery to be detected and the upper surface of the target detection area; when the current distance is a preset distance threshold value, acquiring the current connection state of the light source integrated on the prism module and the light source controller; when the current connection state is a connection success state, acquiring lens focus cycles of target photographing equipment; determining the imaging definition of the target photographing equipment according to the lens focal circle; when the imaging definition is larger than or equal to a preset imaging definition threshold, acquiring a surface appearance image of a pole on the battery top cover to be detected by utilizing a prism module through a preset multi-angle imaging strategy according to the photographing mode and the light source lighting mode; by the method, after the photographing mode and the light source lighting mode of the target photographing equipment are determined, whether the imaging definition of the target photographing equipment is larger than or equal to the preset imaging definition threshold value is judged, if yes, the prism module is utilized to collect images of the pole on the battery top cover to be detected according to the photographing mode and the light source lighting mode through the preset multi-angle imaging strategy, so that the accuracy of obtaining the surface appearance image can be effectively improved, and the collection cost is reduced.
In addition, the embodiment of the invention also provides a storage medium, wherein the storage medium stores a battery top cover pole appearance detection program, and the battery top cover pole appearance detection program realizes the steps of the battery top cover pole appearance detection method when being executed by a processor.
Because the storage medium adopts all the technical schemes of all the embodiments, the storage medium has at least all the beneficial effects brought by the technical schemes of the embodiments, and the description is omitted here.
In addition, referring to fig. 6, an embodiment of the present invention further provides a battery top cover post appearance detection device, where the battery top cover post appearance detection device includes:
the acquisition module 10 is used for acquiring the surface appearance image of the pole on the battery top cover to be detected through a preset multi-angle imaging strategy by utilizing the prism module.
And the registration module 20 is used for carrying out image registration on the surface appearance image of the polar column through an edge detection operator to obtain the current polar column appearance image.
And the shuffling module 30 is configured to perform channel shuffling on the current pole appearance image to obtain a target pole appearance image.
The identification module 40 is configured to identify the appearance image of the target pole based on a multi-scale tag propagation identification algorithm, so as to implement appearance detection of the pole on the battery top cover to be detected.
In the embodiment, the prism module is utilized to collect the surface appearance image of the pole on the top cover of the battery to be detected through a preset multi-angle imaging strategy; carrying out image registration on the surface appearance image of the polar column through an edge detection operator to obtain a current polar column appearance image; channel shuffling is carried out on the current pole appearance image to obtain a target pole appearance image; identifying the appearance image of the target pole based on a multi-scale label propagation identification algorithm so as to realize appearance detection of the pole on the battery top cover to be detected; through the mode, the prism module is utilized to collect the surface appearance image of the pole through the preset multi-angle imaging strategy, then the surface appearance image of the pole is subjected to image registration and channel shuffling, and then the target pole appearance image is identified based on the multi-scale label propagation identification algorithm, so that the accuracy of detecting the appearance of the battery top cover pole can be effectively improved, and the detection cost is reduced.
It should be noted that the above-described working procedure is merely illustrative, and does not limit the scope of the present invention, and in practical application, a person skilled in the art may select part or all of them according to actual needs to achieve the purpose of the embodiment, which is not limited herein.
In addition, technical details not described in detail in the present embodiment can be referred to the method for detecting the appearance of the battery top cap post provided in any embodiment of the present invention, which is not described herein again.
Other embodiments of the battery top cover pole appearance detection device or the implementation method thereof can refer to the above method embodiments, and are not repeated here.
Furthermore, it should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. Read Only Memory)/RAM, magnetic disk, optical disk) and including several instructions for causing a terminal device (which may be a mobile phone, a computer, an integrated platform workstation, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. The battery top cover pole appearance detection method is characterized by comprising the following steps of:
acquiring a surface appearance image of a pole on a top cover of a battery to be detected by using a prism module through a preset multi-angle imaging strategy;
carrying out image registration on the surface appearance image of the polar column through an edge detection operator to obtain a current polar column appearance image;
channel shuffling is carried out on the current pole appearance image to obtain a target pole appearance image;
and identifying the appearance image of the target pole based on a multi-scale label propagation identification algorithm so as to realize appearance detection of the pole on the battery top cover to be detected.
2. The battery top cover post appearance detection method according to claim 1, wherein the acquiring the surface appearance image of the post on the battery top cover to be detected by using the prism module through a preset multi-angle imaging strategy comprises:
Acquiring production line production beats of a battery top cover to be detected, and determining a photographing mode of target photographing equipment arranged right above the prism module according to the production line production beats;
acquiring the actual detection requirement of a user, and determining a light source lighting mode according to the actual detection requirement;
detecting the current distance between the lower bottom surface of the prism module arranged right above the target detection area of the battery to be detected and the upper surface of the target detection area;
when the current distance is a preset distance threshold value, acquiring the current connection state of the light source integrated on the prism module and the light source controller;
when the current connection state is a connection success state, acquiring lens focus cycles of target photographing equipment;
determining the imaging definition of the target photographing equipment according to the lens focal circle;
and when the imaging definition is greater than or equal to a preset imaging definition threshold, acquiring a surface appearance image of the pole on the battery top cover to be detected by utilizing a prism module through a preset multi-angle imaging strategy according to the photographing mode and the light source lighting mode.
3. The battery top cover post appearance detection method according to claim 2, wherein when the imaging definition is greater than or equal to a preset imaging definition threshold, acquiring the surface appearance image of the post on the battery top cover to be detected according to the photographing mode and the light source lighting mode by using a prism module through a preset multi-angle imaging strategy, comprising:
When the imaging definition is greater than or equal to a preset imaging definition threshold, a light source integrated on the prism module is lightened according to the light source lightening mode;
in the lighting process of the light source, reflecting the light rays of the light source by utilizing a prism module through a preset multi-angle imaging strategy to obtain an imaging light path;
obtaining a pole top reflection imaging light path and a pole side wall reflection imaging light path according to the imaging light path;
acquiring an appearance image of the top surface of the pole on the top cover of the battery to be detected according to the photographing mode and the pole top reflection imaging optical path;
acquiring an appearance image of the side wall surface of the pole on the battery top cover to be detected according to the photographing mode and the pole side wall reflection imaging optical path;
and determining the surface appearance image of the pole on the battery top cover to be detected according to the top surface appearance image and the side wall surface appearance image.
4. The battery top cover pole appearance detection method of claim 1, wherein the performing image registration on the surface appearance image of the pole by using an edge detection operator to obtain a current pole appearance image comprises:
determining a diagonal convolution template and a square window according to the edge detection operator;
Performing image gradient calculation on the surface appearance image of the polar column through the diagonal convolution template and the square window to obtain a multidirectional gradient value of the appearance image;
determining global edge data of the surface appearance image of the polar column according to the appearance image multi-direction gradient values;
determining standard surface appearance global edge data;
carrying out affine transformation on the standard surface appearance global edge data and the global edge data of the surface appearance image of the polar column to obtain a current affine transformation result;
and carrying out image registration on the surface appearance image of the polar column according to the current affine transformation result through a SIFT algorithm to obtain the current polar column appearance image.
5. The battery top cover post appearance detection method of claim 1, wherein the performing channel shuffling on the current post appearance image to obtain a target post appearance image comprises:
carrying out graying treatment on the current pole appearance image to obtain a pole appearance gray image;
calculating the gray value, the total number of pixel points and a central neighborhood set of the polar column appearance gray image;
performing mean value filtering on the pole appearance gray level image according to the gray level value, the total number of pixel points and the central neighborhood set;
Carrying out local gray stretching on the post appearance gray image subjected to mean value filtering;
grouping the stretched pole appearance gray images, and respectively carrying out data enhancement on a plurality of groups of stretched pole appearance gray images through multi-channel multithreading;
and carrying out channel shuffling on the post appearance gray level images after the data enhancement through a plurality of groups of convolution to obtain target post appearance images.
6. The battery top cover post appearance detection method of claim 1, wherein the identifying the target post appearance image based on the multi-scale tag propagation identification algorithm to realize appearance detection of the post on the battery top cover to be detected comprises:
extracting features of the target pole appearance image to obtain pole appearance image features;
transposing the pole appearance image features to obtain global pole appearance image features and depth local appearance image features;
generating a multi-scale image feature set according to the global polar column appearance image features and the depth local features by utilizing a multi-scale feature generation strategy;
calculating the label propagation similarity between the multi-scale image feature set and the global polar post appearance image feature based on a multi-scale label propagation recognition algorithm, and calculating the cosine similarity between the multi-scale image feature set and the depth local appearance image feature;
Generating a Gaussian similarity matrix according to the tag propagation similarity and the cosine similarity;
and identifying the Gaussian similarity matrix by a target appearance identification model trained by a WOA-SVM algorithm so as to realize appearance detection of the pole on the top cover of the battery to be detected.
7. The battery top cover post appearance detection method according to any one of claims 1 to 6, wherein after the identifying the target post appearance image based on the multi-scale tag propagation identification algorithm to realize appearance detection of the post on the battery top cover to be detected, further comprises:
obtaining appearance detection duration and appearance detection accuracy of the pole on the top cover of the battery to be detected;
when the appearance detection duration is smaller than the human detection duration and the appearance detection accuracy is larger than the human detection accuracy, acquiring the detection cost of the appearance image of the target pole;
when the detection cost of the target pole appearance image is lower than the preset detection cost, packaging the appearance detection flow of the pole on the top cover of the battery to be detected to obtain a battery appearance detection strategy;
and detecting the surfaces of the pole posts on the top covers of other batteries through the battery appearance detection strategy.
8. The utility model provides a battery top cap utmost point post outward appearance detection device which characterized in that, battery top cap utmost point post outward appearance detection device includes:
the acquisition module is used for acquiring the surface appearance image of the pole on the top cover of the battery to be detected through a preset multi-angle imaging strategy by utilizing the prism module;
the registration module is used for carrying out image registration on the surface appearance image of the polar column through an edge detection operator to obtain a current polar column appearance image;
the shuffling module is used for carrying out channel shuffling on the current pole appearance image to obtain a target pole appearance image;
the identification module is used for identifying the appearance image of the target pole based on a multi-scale tag propagation identification algorithm so as to realize appearance detection of the pole on the battery top cover to be detected.
9. Battery top cap utmost point post outward appearance check out test set, its characterized in that, battery top cap utmost point post outward appearance check out test set includes: a memory, a processor, and a battery top cap post appearance detection program stored on the memory and executable on the processor, the battery top cap post appearance detection program configured to implement the battery top cap post appearance detection method of any one of claims 1 to 7.
10. A storage medium, wherein a battery top cap post appearance detection program is stored on the storage medium, and when executed by a processor, the battery top cap post appearance detection program implements the battery top cap post appearance detection method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310878112.6A CN116596932B (en) | 2023-07-18 | 2023-07-18 | Method, device, equipment and storage medium for detecting appearance of battery top cover pole |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310878112.6A CN116596932B (en) | 2023-07-18 | 2023-07-18 | Method, device, equipment and storage medium for detecting appearance of battery top cover pole |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116596932A true CN116596932A (en) | 2023-08-15 |
| CN116596932B CN116596932B (en) | 2024-02-09 |
Family
ID=87608358
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310878112.6A Active CN116596932B (en) | 2023-07-18 | 2023-07-18 | Method, device, equipment and storage medium for detecting appearance of battery top cover pole |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116596932B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108280838A (en) * | 2018-01-31 | 2018-07-13 | 桂林电子科技大学 | A kind of intermediate plate tooth form defect inspection method based on edge detection |
| CN110717896A (en) * | 2019-09-24 | 2020-01-21 | 东北大学 | Plate strip steel surface defect detection method based on saliency label information propagation model |
| CN111028213A (en) * | 2019-12-04 | 2020-04-17 | 北大方正集团有限公司 | Image defect detection method and device, electronic equipment and storage medium |
| CN111398287A (en) * | 2019-11-29 | 2020-07-10 | 合肥国轩高科动力能源有限公司 | Battery pole piece scratch detection system and detection method |
| CN112508826A (en) * | 2020-11-16 | 2021-03-16 | 哈尔滨工业大学（深圳） | Printed matter defect detection method based on feature registration and gradient shape matching fusion |
| WO2021169335A1 (en) * | 2020-02-25 | 2021-09-02 | 华南理工大学 | Visual online detection method for laser welding point of lithium battery tab |
-
2023
- 2023-07-18 CN CN202310878112.6A patent/CN116596932B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108280838A (en) * | 2018-01-31 | 2018-07-13 | 桂林电子科技大学 | A kind of intermediate plate tooth form defect inspection method based on edge detection |
| CN110717896A (en) * | 2019-09-24 | 2020-01-21 | 东北大学 | Plate strip steel surface defect detection method based on saliency label information propagation model |
| CN111398287A (en) * | 2019-11-29 | 2020-07-10 | 合肥国轩高科动力能源有限公司 | Battery pole piece scratch detection system and detection method |
| CN111028213A (en) * | 2019-12-04 | 2020-04-17 | 北大方正集团有限公司 | Image defect detection method and device, electronic equipment and storage medium |
| WO2021169335A1 (en) * | 2020-02-25 | 2021-09-02 | 华南理工大学 | Visual online detection method for laser welding point of lithium battery tab |
| CN112508826A (en) * | 2020-11-16 | 2021-03-16 | 哈尔滨工业大学（深圳） | Printed matter defect detection method based on feature registration and gradient shape matching fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116596932B (en) | 2024-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104573625B (en) | Data processing system and its generating device and type of face detection method | |
| JP4008282B2 (en) | Pupil / iris circle detector | |
| CN111080693A (en) | Robot autonomous classification grabbing method based on YOLOv3 | |
| US8805081B2 (en) | Object detection in an image | |
| CN109961399B (en) | Optimal suture line searching method based on image distance transformation | |
| KR101405410B1 (en) | Object detection device and system | |
| CN106599806A (en) | Local curved-surface geometric feature-based human body action recognition method | |
| WO2022262054A1 (en) | Image processing method, apparatus and device, and storage medium | |
| TW201317904A (en) | Tag detecting system, apparatus and method for detecting tag thereof | |
| CN114862814A (en) | Solar cell panel defect detection method and system, storage medium and terminal | |
| CN112801988A (en) | Object grabbing pose detection method based on RGBD and deep neural network | |
| CN111626241A (en) | Face detection method and device | |
| CN116596932B (en) | Method, device, equipment and storage medium for detecting appearance of battery top cover pole | |
| JP2017521011A (en) | Symbol optical detection method | |
| CN115845350B (en) | Method and system for automatic ranging of standing long jump | |
| CN111738264A (en) | Intelligent acquisition method for data of display panel of machine room equipment | |
| CN114998980A (en) | Iris detection method and device, electronic equipment and storage medium | |
| JP2008084109A (en) | Eye opening/closing determination device and eye opening/closing determination method | |
| CN113807368A (en) | Glass instrument detection method and device based on YOLO algorithm and related equipment | |
| US20040101169A1 (en) | Determination of a definition score of a digital image | |
| CN114219758A (en) | Defect detection method, system, electronic device and computer readable storage medium | |
| CN115731256A (en) | Vertex coordinate detection method, device, equipment and storage medium | |
| CN113592789A (en) | Dim light image identification method, device, equipment and storage medium | |
| CN111862098A (en) | Individual matching method, device, equipment and medium based on light field semantics | |
| CN116152685B (en) | Pedestrian detection method and system based on unmanned aerial vehicle visual field |
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 |