CN115620210A - Method and system for determining performance of electronic wire based on image processing - Google Patents
Method and system for determining performance of electronic wire based on image processing Download PDFInfo
- Publication number
- CN115620210A CN115620210A CN202211510181.3A CN202211510181A CN115620210A CN 115620210 A CN115620210 A CN 115620210A CN 202211510181 A CN202211510181 A CN 202211510181A CN 115620210 A CN115620210 A CN 115620210A
- Authority
- CN
- China
- Prior art keywords
- video
- performance test
- contrast
- test monitoring
- target
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000011056 performance test Methods 0.000 claims abstract description 528
- 238000012544 monitoring process Methods 0.000 claims abstract description 316
- 239000000463 material Substances 0.000 claims abstract description 70
- 238000004364 calculation method Methods 0.000 claims abstract description 23
- 238000012216 screening Methods 0.000 claims abstract description 17
- 238000012360 testing method Methods 0.000 claims description 23
- 238000005065 mining Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 13
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 230000004927 fusion Effects 0.000 claims description 4
- 230000006835 compression Effects 0.000 claims description 3
- 238000007906 compression Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 107
- 238000004458 analytical method Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 230000002596 correlated effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000009432 framing Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/16—Measuring arrangements characterised by the use of optical techniques for measuring the deformation in a solid, e.g. optical strain gauge
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N25/00—Investigating or analyzing materials by the use of thermal means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N3/02—Details
- G01N3/06—Special adaptations of indicating or recording means
- G01N3/068—Special adaptations of indicating or recording means with optical indicating or recording means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
- G06V10/809—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of classification results, e.g. where the classifiers operate on the same input data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C60/00—Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/0014—Type of force applied
- G01N2203/0016—Tensile or compressive
- G01N2203/0019—Compressive
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/02—Details not specific for a particular testing method
- G01N2203/06—Indicating or recording means; Sensing means
- G01N2203/0641—Indicating or recording means; Sensing means using optical, X-ray, ultraviolet, infrared or similar detectors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/02—Details not specific for a particular testing method
- G01N2203/06—Indicating or recording means; Sensing means
- G01N2203/067—Parameter measured for estimating the property
- G01N2203/0682—Spatial dimension, e.g. length, area, angle
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biochemistry (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Artificial Intelligence (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
The invention provides a method and a system for determining the performance of an electronic wire based on image processing, and relates to the technical field of image processing. In the invention, frame screening is carried out on the collected original performance test monitoring video of the target electronic wire material so as to output the corresponding target performance test monitoring video; respectively carrying out matching degree calculation on the target performance test monitoring video and each determined contrast performance test monitoring video so as to output the video matching degree between the target performance test monitoring video and each contrast performance test monitoring video; and determining the target video characteristic information of the target performance test monitoring video according to the video matching degree between the target performance test monitoring video and each contrast performance test monitoring video and by combining the contrast video characteristic information of each contrast performance test monitoring video. Based on the method, the efficiency of determining the performance of the electronic wire material can be improved to a certain extent.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a method and a system for determining the performance of an electronic wire material based on image processing.
Background
The electronic wire material has many application scenes, and the performance requirement of the electronic wire material is high in many application scenes, so that the performance of the electronic wire material needs to be determined. For example, in some applications, the performance of the electronic wire material needs to be classified into multiple grades, and for example, in other applications, the performance of the electronic wire material needs to be classified into two categories, that is, whether the target condition is satisfied, and the like. However, in the prior art, it is necessary to rely on more tools and personnel to perform observation and analysis, for example, to analyze the deformation degree of the electronic wire material in various temperature and pressure environments to obtain corresponding performance, so that the problem of low efficiency of performance analysis is likely to occur.
Disclosure of Invention
In view of the above, the present invention provides a method and a system for determining performance of an electronic wire based on image processing, so as to improve the efficiency of determining the performance of the electronic wire to a certain extent.
In order to achieve the above purpose, the embodiment of the invention adopts the following technical scheme:
a performance determination method of an electronic wire material based on image processing comprises the following steps:
performing frame screening on the collected original performance test monitoring video of the target electronic wire material to output a target performance test monitoring video corresponding to the original performance test monitoring video;
calculating the matching degree of the target performance test monitoring video and each contrast performance test monitoring video in the determined contrast performance test monitoring video sequence respectively so as to output the video matching degree between the target performance test monitoring video and each contrast performance test monitoring video respectively, wherein each contrast performance test monitoring video has contrast video characteristic information;
and determining the target video characteristic information of the target performance test monitoring video according to the video matching degree between the target performance test monitoring video and each contrast performance test monitoring video and by combining the contrast video characteristic information of each contrast performance test monitoring video, wherein the target video characteristic information is used for reflecting whether the performance of the target electronic wire meets the target condition.
In some preferred embodiments, in the method for determining the performance of the electronic wire based on image processing, the step of performing frame-wise screening on the acquired original performance test monitoring video of the target electronic wire to output the target performance test monitoring video corresponding to the original performance test monitoring video includes:
in the performance test process of a target electronic wire material, acquiring an original performance test monitoring video corresponding to the target electronic wire material, wherein the original performance test monitoring video comprises a plurality of original performance test monitoring video frames which are continuous in a frame time sequence;
for every two original performance test monitoring video frames with close frame time sequences in the original performance test monitoring video frames, carrying out similarity calculation on the two original performance test monitoring video frames relative to the outline of the electronic wire material so as to output the corresponding outline similarity of the electronic wire material;
and screening the plurality of original performance test monitoring video frames according to the electronic wire profile similarity corresponding to every two original performance test monitoring video frames with close frame time sequences in the plurality of original performance test monitoring video frames, so as to construct a target performance test monitoring video corresponding to the original performance test monitoring video based on the screened target performance test monitoring video frames.
In some preferred embodiments, in the method for determining performance of an electronic wire material based on image processing, the step of calculating a matching degree between the target performance test surveillance video and each contrast performance test surveillance video in the determined contrast performance test surveillance video sequence to output a video matching degree between the target performance test surveillance video and each contrast performance test surveillance video includes:
extracting a plurality of unknown performance test monitoring videos and a plurality of known performance test monitoring videos, wherein each unknown performance test monitoring video does not have contrast video characteristic information, each known performance test monitoring video has contrast video characteristic information, each unknown performance test monitoring video has corresponding line profile identification information of a contrast electronic line material, and each unknown performance test monitoring video and each known performance test monitoring video are obtained by performing video monitoring on the performance test process of the corresponding contrast electronic line material;
according to the line profile identification information of each unknown performance test monitoring video, respectively carrying out feature mining processing on the line profile identification information corresponding to each unknown performance test monitoring video so as to output a line profile identification information mining result corresponding to each unknown performance test monitoring video;
extracting each unknown performance test monitoring video matched with the characteristic information of the comparison video from the plurality of unknown performance test monitoring videos based on the mining result of the profile identification information of the wire material corresponding to each unknown performance test monitoring video, marking the unknown performance test monitoring video as a target unknown performance test monitoring video, and distributing the characteristic information of the comparison video to the target unknown performance test monitoring video;
constructing and forming a corresponding comparison performance test monitoring video sequence based on the marked target unknown performance test monitoring video and the plurality of known performance test monitoring videos, wherein each comparison performance test monitoring video in the comparison performance test monitoring video sequence belongs to the target unknown performance test monitoring video or the known performance test monitoring video;
and respectively calculating the matching degree of the target performance test monitoring video and each contrast performance test monitoring video in the contrast performance test monitoring video sequence so as to output the video matching degree between the target performance test monitoring video and each contrast performance test monitoring video.
In some preferred embodiments, in the method for determining performance of an electronic wire based on image processing, the step of extracting, from the plurality of unknown performance test surveillance videos, each unknown performance test surveillance video matched with the comparison video feature information based on the wire profile identification information mining result corresponding to each unknown performance test surveillance video to mark as a target unknown performance test surveillance video, and then distributing the comparison video feature information to the target unknown performance test surveillance video includes:
loading a wire profile identification information mining result corresponding to each unknown performance test monitoring video into a target video detection neural network to form a video prediction matching degree corresponding to each unknown performance test monitoring video, wherein the video prediction matching degree is used for reflecting the matching degree of the unknown performance test monitoring video and the contrast video characteristic information, the target video detection neural network is formed by performing network optimization on a plurality of typical performance test monitoring videos with wire profile identification information and typical identification information corresponding to each typical performance test monitoring video, the typical identification information comprises first typical identification information and second typical identification information, the first typical identification information is used for reflecting the matching of the typical performance test monitoring video and the contrast video characteristic information, and the second typical identification information is used for reflecting the mismatching of the typical performance test monitoring video and the contrast video characteristic information;
and extracting each unknown performance test monitoring video matched with the characteristic information of the comparison video from the plurality of unknown performance test monitoring videos based on the video prediction matching degree corresponding to each unknown performance test monitoring video, marking the unknown performance test monitoring video as a target unknown performance test monitoring video, and distributing the characteristic information of the comparison video to the target unknown performance test monitoring video.
In some preferred embodiments, in the method for determining the performance of the electronic wire based on image processing, the step of calculating the matching degree between the target performance test surveillance video and each contrast performance test surveillance video in the determined contrast performance test surveillance video sequence to output the video matching degree between the target performance test surveillance video and each contrast performance test surveillance video further includes:
performing video segmentation processing on each contrast performance test monitoring video in the contrast performance test monitoring video sequence respectively to output a contrast performance test monitoring video segment sequence corresponding to each contrast performance test monitoring video;
respectively carrying out video segment feature coding operation on each contrast performance test monitoring video segment in the contrast performance test monitoring video segment sequence to form a video segment feature coding result corresponding to each contrast performance test monitoring video segment;
respectively fusing and outputting a comparison video feature coding result corresponding to each comparison performance test monitoring video in the comparison performance test monitoring video sequence based on a video segment feature coding result corresponding to each comparison performance test monitoring video segment and the video segment importance degree corresponding to each comparison performance test monitoring video segment;
in the process of executing the step of calculating the matching degree between the target performance test surveillance video and each contrast performance test surveillance video in the contrast performance test surveillance video sequence respectively to output the video matching degree between the target performance test surveillance video and each contrast performance test surveillance video respectively, the contrast video feature coding result is used for representing the corresponding contrast performance test surveillance video to calculate the matching degree.
In some preferred embodiments, in the method for determining performance of an electronic wire based on image processing, the step of respectively fusing and outputting a contrast video feature encoding result corresponding to each contrast performance test surveillance video in the contrast performance test surveillance video sequence based on a video segment feature encoding result corresponding to each contrast performance test surveillance video segment and a video segment importance degree corresponding to each contrast performance test surveillance video segment includes:
based on the video segment importance degree corresponding to each contrast performance test monitoring video segment, respectively carrying out product calculation on the corresponding video segment feature coding results so as to output a fused video segment feature coding result corresponding to each contrast performance test monitoring video segment;
and summing the fusion video segment feature coding results corresponding to each comparison performance test monitoring video segment to output the corresponding combination video segment feature coding result, and then performing feature compression operation on the combination video segment feature coding result to form a comparison video feature coding result corresponding to each comparison performance test monitoring video in the comparison performance test monitoring video sequence.
In some preferred embodiments, in the method for determining performance of an electronic wire material based on image processing, the step of calculating a matching degree between the target performance test surveillance video and each contrast performance test surveillance video in the determined contrast performance test surveillance video sequence to output a video matching degree between the target performance test surveillance video and each contrast performance test surveillance video further includes:
performing video segmentation processing on each contrast performance test monitoring video in the contrast performance test monitoring video sequence respectively to output a contrast performance test monitoring video segment sequence corresponding to each contrast performance test monitoring video;
performing video segment feature coding operation on a key contrast performance test monitoring video segment in the contrast performance test monitoring video segment sequence to output a video segment feature coding result corresponding to the key contrast performance test monitoring video segment;
determining a comparison video feature coding result corresponding to each comparison performance test surveillance video in the comparison performance test surveillance video sequence based on the video segment feature coding result corresponding to the key comparison performance test surveillance video segment and the video segment importance degree corresponding to the key comparison performance test surveillance video segment;
in the process of executing the step of calculating the matching degree of the target performance test surveillance video and each contrast performance test surveillance video in the contrast performance test surveillance video sequence respectively to output the video matching degree between the target performance test surveillance video and each contrast performance test surveillance video respectively, the feature coding result of the contrast video is used for representing the corresponding contrast performance test surveillance video to calculate the matching degree.
In some preferred embodiments, in the method for determining performance of an electronic wire material based on image processing, the step of calculating a matching degree between the target performance test surveillance video and each contrast performance test surveillance video in the determined contrast performance test surveillance video sequence to output a video matching degree between the target performance test surveillance video and each contrast performance test surveillance video further includes:
analyzing and determining the average video correlation degree of each contrast performance test surveillance video clip in the contrast performance test surveillance video sequence, wherein the average video correlation degree is used for reflecting the average value of the video clip correlation degree between the corresponding contrast performance test surveillance video clip and each other contrast performance test surveillance video clip in the contrast performance test surveillance video sequence;
and screening out a target number of contrast performance test monitoring video clips with the maximum corresponding average video correlation degree from the contrast performance test monitoring video clip sequence to mark the target number of contrast performance test monitoring video clips as corresponding key contrast performance test monitoring video clips.
In some preferred embodiments, in the method for determining performance of an electronic wire based on image processing, the step of determining the target video feature information of the target performance test surveillance video according to the video matching degree between the target performance test surveillance video and each comparison performance test surveillance video and by combining the comparison video feature information of each comparison performance test surveillance video includes:
respectively comparing the video matching degree between the target performance test monitoring video and each contrast performance test monitoring video with a preset video matching degree reference value;
if at least one video matching degree which is greater than or equal to the reference value of the video matching degree exists in the video matching degrees between the target performance test monitoring video and each contrast performance test monitoring video, determining first target video characteristic information of the target performance test monitoring video by combining the contrast video characteristic information of each contrast performance test monitoring video;
if at least one video matching degree which is greater than or equal to the reference value of the video matching degree does not exist in the video matching degrees between the target performance test monitoring video and each contrast performance test monitoring video, determining second target video characteristic information of the target performance test monitoring video by combining the contrast video characteristic information of each contrast performance test monitoring video;
the comparison video characteristic information of each comparison performance test monitoring video is used for reflecting that the performance of the corresponding comparison electronic wire does not meet the target condition, the first target video characteristic information is used for reflecting that the performance of the target electronic wire does not meet the target condition, and the second target video characteristic information is used for reflecting that the performance of the target electronic wire meets the target condition.
The embodiment of the invention also provides a performance determining system of the electronic wire material based on image processing, which comprises a processor and a memory, wherein the memory is used for storing a computer program, and the processor is used for executing the computer program so as to realize the performance determining method of the electronic wire material.
According to the method and the system for determining the performance of the electronic wire based on the image processing, the collected original performance test monitoring video of the target electronic wire can be screened in a frame-by-frame mode to output the corresponding target performance test monitoring video; respectively carrying out matching degree calculation on the target performance test monitoring video and each determined contrast performance test monitoring video so as to output the video matching degree between the target performance test monitoring video and each contrast performance test monitoring video; and determining the target video characteristic information of the target performance test monitoring video according to the video matching degree between the target performance test monitoring video and each contrast performance test monitoring video and by combining the contrast video characteristic information of each contrast performance test monitoring video. Based on the method, the result of whether the performance of the target electronic wire meets the target condition can be obtained by sequentially performing frame screening, matching degree calculation and video characteristic information determination on the acquired original performance test monitoring video, so that manual observation and analysis in the prior art are effectively replaced, the efficiency of performance determination of the electronic wire is improved to a certain extent, and the defects in the prior art can be overcome.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
Fig. 1 is a block diagram of a system for determining performance of an electronic wire based on image processing according to an embodiment of the present invention.
Fig. 2 is a schematic flowchart of steps included in the method for determining the performance of an electronic wire based on image processing according to the embodiment of the present invention.
Fig. 3 is a schematic diagram of modules included in the apparatus for determining performance of an electronic wire based on image processing according to the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the 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.
Referring to fig. 1, an embodiment of the present invention provides a performance determination system for an electronic wire based on image processing. The performance determination system of the electronic wire based on image processing can comprise a memory and a processor.
It will be appreciated that in some implementations, the memory and processor are electrically connected, directly or indirectly, to enable transfer or interaction of data. For example, they may be electrically connected to each other via one or more communication buses or signal lines. The memory may have at least one software functional module stored therein, which may be in the form of software or firmware. The processor may be configured to execute the executable computer program stored in the memory, so as to implement the method for determining performance of an electronic wire based on image processing according to the embodiment of the present invention.
It is understood that in some implementations, the Memory may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Read Only Memory (EPROM), an electrically Erasable Read Only Memory (EEPROM), and the like. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), a System on Chip (SoC), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components.
It will be appreciated that in some implementations, the image processing-based electronic strand performance determination system may be a server with data processing capabilities.
With reference to fig. 2, an embodiment of the present invention further provides a method for determining performance of an electronic wire based on image processing, which is applicable to the system for determining performance of an electronic wire based on image processing. The method steps defined by the flow related to the method for determining the performance of the electronic wire based on the image processing can be realized by the system for determining the performance of the electronic wire based on the image processing.
The specific process shown in FIG. 2 will be described in detail below.
Step S110, frame screening is carried out on the collected original performance test monitoring video of the target electronic wire material, so as to output the target performance test monitoring video corresponding to the original performance test monitoring video.
In the embodiment of the invention, the performance determination system can perform frame screening on the acquired original performance test monitoring video of the target electronic wire material so as to output the target performance test monitoring video corresponding to the original performance test monitoring video.
Step S120, the target performance test monitoring video is respectively matched with each contrast performance test monitoring video in the determined contrast performance test monitoring video sequence, so as to output the video matching degree between the target performance test monitoring video and each contrast performance test monitoring video.
In the embodiment of the present invention, the performance determination system may perform matching calculation on the target performance test surveillance video and each contrast performance test surveillance video in the determined contrast performance test surveillance video sequence, so as to output a video matching between the target performance test surveillance video and each contrast performance test surveillance video. Each of the comparison performance test monitoring videos has comparison video characteristic information.
Step S130, determining the target video characteristic information of the target performance test monitoring video according to the video matching degree between the target performance test monitoring video and each contrast performance test monitoring video and by combining the contrast video characteristic information of each contrast performance test monitoring video.
In the embodiment of the present invention, the performance determination system may determine the target video feature information of the target performance test surveillance video according to the video matching degree between the target performance test surveillance video and each comparison performance test surveillance video and by combining the comparison video feature information of each comparison performance test surveillance video. The target video characteristic information is used for reflecting whether the performance of the target electronic wire meets a target condition.
Based on the above steps S110, S120, and S130, the result of whether the performance of the target electronic wire meets the target condition can be obtained by sequentially performing frame screening, matching degree calculation, and video characteristic information determination on the acquired original performance test monitoring video, so that manual observation and analysis in the prior art are effectively replaced, the efficiency of determining the performance of the electronic wire is improved to a certain extent, and the defects in the prior art can be overcome.
It is understood that, in some implementations, the step S110 may further include the following specific contents:
in the performance test process (such as temperature resistance test) of a target electronic wire material, acquiring an original performance test monitoring video corresponding to the target electronic wire material, wherein the original performance test monitoring video comprises a plurality of original performance test monitoring video frames which are continuous in a frame time sequence;
for every two original performance test monitoring video frames with close frame time sequences in the original performance test monitoring video frames, carrying out similarity calculation on the two original performance test monitoring video frames relative to the outline of the electronic wire material so as to output the corresponding outline similarity of the electronic wire material;
according to the electronic line material contour similarity corresponding to every two original performance test monitoring video frames with close frame time sequences in the original performance test monitoring video frames, screening processing is performed on the original performance test monitoring video frames (for example, one of the two original performance test monitoring video frames with the electronic line material contour similarity larger than the reference value of the electronic line material contour similarity can be screened out), so that a target performance test monitoring video corresponding to the original performance test monitoring video is constructed based on the screened (namely reserved) target performance test monitoring video frames.
It is to be understood that, in some implementation embodiments, the step of performing, for every two original performance test surveillance video frames in the original performance test surveillance video frames with close frame timing, a similarity calculation on the electronic wire material profile for the two original performance test surveillance video frames to output a corresponding electronic wire material profile similarity may further include the following specific contents:
performing identification and extraction operation (which may be based on any existing contour identification technology) on an electronic wire contour of a first frame of original performance test surveillance video frame to output first electronic wire contour information corresponding to the first frame of original performance test surveillance video frame, and performing identification and extraction operation on an electronic wire contour of a second frame of original performance test surveillance video frame to output second electronic wire contour information corresponding to the first frame of original performance test surveillance video frame;
performing video frame feature point identification and extraction operation (which may be based on any existing feature point identification technology) on the first frame of original performance test surveillance video frame to output a first video frame feature point set corresponding to the first frame of original performance test surveillance video frame, and then performing video frame feature point identification and extraction operation on the second frame of original performance test surveillance video frame to output a second video frame feature point set corresponding to the second frame of original performance test surveillance video frame;
for each first video frame feature point in the first video frame feature point set, determining whether the first video frame feature point belongs to the first electronic wire profile information, and when the first video frame feature point belongs to the first electronic wire profile information, marking the first video frame feature point as a target first video frame feature point;
for each second video frame feature point in the second video frame feature point set, determining whether the second video frame feature point belongs to the second electronic wire profile information, and when the second video frame feature point belongs to the second electronic wire profile information, marking the second video frame feature point as a target second video frame feature point;
according to each marked target first video frame feature point, performing segmentation processing on the first electronic wire profile information to output a first electronic wire profile segment set corresponding to the first electronic wire profile information, wherein the endpoint of each first electronic wire profile segment included in the first electronic wire profile segment set belongs to the target first video frame feature point;
according to each marked target second video frame feature point, performing segmentation processing on the second electronic wire profile information to output a second electronic wire profile segment set corresponding to the second electronic wire profile information, wherein the endpoint of each second electronic wire profile segment included in the second electronic wire profile segment set belongs to the target second video frame feature point;
for each first electronic wire material contour segment in the first electronic wire material contour segment set, respectively calculating a contour coincidence degree between each second electronic wire material contour segment included in the first electronic wire material contour segment set and the second electronic wire material contour segment set (for example, when the first electronic wire material contour segment set and the second electronic wire material contour segment set are projected to the same space, the projection position can be updated for multiple times, and a coincidence degree corresponding to each projection position is calculated, and then the coincidence degree of the maximum value therein is taken as the contour coincidence degree), and respectively calculating a pixel position deviation degree between each second electronic wire material contour segment included in the first electronic wire material contour segment set and the second electronic wire material contour segment set (exemplarily, a plurality of first pixel points can be sampled on the first electronic wire material contour segments, sampling a plurality of second pixel points on a second electronic wire profile segment, calculating an average value of pixel position distances between a plurality of first pixel points and the plurality of second pixel points to serve as the pixel position deviation degree), and performing weighted summation calculation according to the pixel position deviation degree between each second electronic wire profile segment included in the first electronic wire profile segment and the second electronic wire profile segment set so as to output the representative coincidence degree corresponding to the first electronic wire profile segment (exemplarily, the weighted value in the weighted summation calculation is in negative correlation with the pixel position deviation degree);
the representative contact ratio corresponding to each first electronic wire material contour segment in the first electronic wire material contour segment set is fused (for example, the representative contact ratio corresponding to each first electronic wire material contour segment may be subjected to mean calculation or weighted mean calculation, where a weighting coefficient of the weighted mean calculation may be determined according to the segment length and/or the segment tortuosity of the corresponding first electronic wire material contour segment, and for example, the segment length and/or the segment tortuosity is positively correlated, and the segment tortuosity may be equal to a ratio between a straight-line distance between two endpoints of the first electronic wire material contour segment and the segment length), so as to output the corresponding electronic wire material contour similarity.
It is understood that, in some implementation embodiments, the step S120 may further include the following specific contents:
extracting a plurality of unknown performance test surveillance videos and a plurality of known performance test surveillance videos, wherein each unknown performance test surveillance video does not have contrast video characteristic information (namely whether the performance of a corresponding contrast electronic wire meets a target condition is unknown), each known performance test surveillance video has contrast video characteristic information (namely whether the performance of a corresponding known contrast electronic wire meets the target condition is known, namely the comparison video characteristic information is used for determining), each unknown performance test surveillance video has wire profile identification information of a corresponding contrast electronic wire, and each unknown performance test surveillance video and each known performance test surveillance video are obtained by performing video monitoring on the performance test process of the corresponding contrast electronic wire;
according to the line profile identification information of each unknown performance test surveillance video, respectively performing feature mining on the line profile identification information corresponding to each unknown performance test surveillance video to output a line profile identification information mining result corresponding to each unknown performance test surveillance video (for example, the feature mining may be implemented by a convolutional network, and correspondingly, the line profile identification information mining result may be output by the convolutional network);
extracting each unknown performance test monitoring video matched with the characteristic information of the comparison video from the plurality of unknown performance test monitoring videos based on the mining result of the profile identification information of the wire material corresponding to each unknown performance test monitoring video, marking the unknown performance test monitoring video as a target unknown performance test monitoring video, and distributing the characteristic information of the comparison video to the target unknown performance test monitoring video;
constructing and forming a corresponding comparison performance test surveillance video sequence based on the marked target unknown performance test surveillance video and the plurality of known performance test surveillance videos, wherein each comparison performance test surveillance video in the comparison performance test surveillance video sequence belongs to the target unknown performance test surveillance video or the known performance test surveillance video (that is, the marked target unknown performance test surveillance video and the plurality of known performance test surveillance videos can be used as the comparison performance test surveillance video);
and respectively carrying out matching degree calculation on the target performance test monitoring video and each contrast performance test monitoring video in the contrast performance test monitoring video sequence so as to output the video matching degree between the target performance test monitoring video and each contrast performance test monitoring video.
It can be understood that, in some implementation embodiments, the step of extracting, based on the result of mining the profile identification information of the wire corresponding to each unknown performance test surveillance video, each unknown performance test surveillance video matched with the feature information of the comparison video from the plurality of unknown performance test surveillance videos to mark as a target unknown performance test surveillance video, and then allocating the feature information of the comparison video to the target unknown performance test surveillance video may further include the following specific contents:
loading a wire profile identification information mining result corresponding to each unknown performance test monitoring video into a target video detection neural network to form a video prediction matching degree corresponding to each unknown performance test monitoring video, wherein the video prediction matching degree is used for reflecting the matching degree of the unknown performance test monitoring video and the contrast video characteristic information, the target video detection neural network is formed by performing network optimization on a plurality of typical performance test monitoring videos with wire profile identification information and typical identification information corresponding to each typical performance test monitoring video, the typical identification information comprises first typical identification information and second typical identification information, the first typical identification information is used for reflecting the matching of the typical performance test monitoring video and the contrast video characteristic information, and the second typical identification information is used for reflecting the mismatching of the typical performance test monitoring video and the contrast video characteristic information; extracting each unknown performance test surveillance video matched with the feature information of the comparison video from the plurality of unknown performance test surveillance videos based on the video prediction matching degree corresponding to each unknown performance test surveillance video, marking the unknown performance test surveillance video as a target unknown performance test surveillance video, and then distributing the feature information of the comparison video to the target unknown performance test surveillance video (for example, the unknown performance test surveillance video with the video prediction matching degree larger than or equal to a preset video prediction matching degree reference value in the plurality of unknown performance test surveillance videos can be marked as the target unknown performance test surveillance video, and then distributing the feature information of the comparison video to the target unknown performance test surveillance video).
It is understood that, in some implementation implementations, the step S120 may further include the following specific contents:
respectively carrying out video segmentation processing on each contrast performance test surveillance video in the contrast performance test surveillance video sequence so as to output a contrast performance test surveillance video segment sequence corresponding to each contrast performance test surveillance video (the contrast performance test surveillance video segment sequence can comprise a plurality of contrast performance test surveillance video segments, and each contrast performance test surveillance video segment can comprise one or a plurality of contrast performance test surveillance video frames with continuous frame time sequence);
performing a video segment feature coding operation on each contrast performance test surveillance video segment in the contrast performance test surveillance video segment sequence to form a video segment feature coding result corresponding to each contrast performance test surveillance video segment (for example, the video segment feature coding operation may be implemented by a coding model included in the target video detection neural network, and correspondingly, the video segment feature coding result may be an output of the coding model);
based on the video segment feature coding result corresponding to each of the contrast performance test surveillance video segments and the video segment importance degree corresponding to each of the contrast performance test surveillance video segments (exemplarily, the average video correlation degree of each of the contrast performance test surveillance video segments in the contrast performance test surveillance video sequence may be determined by analyzing, where the average video correlation degree is used to reflect an average value of the video segment correlation degrees between the corresponding contrast performance test surveillance video segment and each of the other contrast performance test surveillance video segments in the contrast performance test surveillance video sequence, and then the corresponding video segment importance degree is determined according to the average video correlation degree, where the video segment importance degree may be positively correlated with the average video correlation degree), respectively outputting the contrast video feature coding result corresponding to each of the contrast performance test surveillance videos in the contrast performance test surveillance video sequence in a fusion manner;
in the process of performing the step of calculating the matching degree between the target performance testing surveillance video and each contrast performance testing surveillance video in the contrast performance testing surveillance video sequence to output the video matching degree between the target performance testing surveillance video and each contrast performance testing surveillance video, the contrast video feature coding result is used to represent the corresponding contrast performance testing surveillance video for matching degree calculation, that is, a target performance feature coding result corresponding to the target performance testing surveillance video can be determined, and then the matching degree between the target performance feature coding result and the contrast video feature coding result is calculated to obtain the corresponding video matching degree, where the matching degree between the target performance feature coding result and the contrast video feature coding result can be the vector similarity between two corresponding vectors.
It can be understood that, in some implementation embodiments, the step of respectively fusing and outputting the feature encoding result of the contrast video corresponding to each contrast performance test surveillance video in the contrast performance test surveillance video sequence based on the feature encoding result of the video segment corresponding to each contrast performance test surveillance video segment and the video segment importance degree corresponding to each contrast performance test surveillance video segment in the foregoing may further include the following specific contents:
based on the video segment importance degree corresponding to each contrast performance test monitoring video segment, respectively carrying out product calculation on the corresponding video segment feature coding results so as to output a fused video segment feature coding result corresponding to each contrast performance test monitoring video segment;
summing the feature coding results of the fused video segments corresponding to each of the comparison performance testing surveillance video segments to output corresponding feature coding results of the merged video segments, and performing feature compression on the feature coding results of the merged video segments (for example, the coding parameters in the feature coding results of the merged video segments may be mapped to an interval [0,1 ]) to form a comparison video feature coding result corresponding to each of the comparison performance testing surveillance videos in the comparison performance testing surveillance video sequence.
It is understood that, in some implementation embodiments, the step S120 may further include the following specific contents:
performing video segmentation processing on each contrast performance test surveillance video in the contrast performance test surveillance video sequence respectively to output a contrast performance test surveillance video segment sequence (as described above) corresponding to each contrast performance test surveillance video;
performing video segment feature coding operation (as described above) on the key contrast performance test surveillance video segment in the contrast performance test surveillance video segment sequence to output a video segment feature coding result corresponding to the key contrast performance test surveillance video segment;
determining a comparison video feature coding result corresponding to each comparison performance test surveillance video in the comparison performance test surveillance video sequence based on the video segment feature coding result corresponding to the key comparison performance test surveillance video segment and the video segment importance (as described above);
in the process of executing the step of calculating the matching degree between the target performance testing surveillance video and each contrast performance testing surveillance video in the contrast performance testing surveillance video sequence, so as to output the video matching degree between the target performance testing surveillance video and each contrast performance testing surveillance video, the contrast video feature coding result is used for representing the corresponding contrast performance testing surveillance video, so as to perform the matching degree calculation (as described above).
It is understood that, in some implementations, in order to determine the key contrast performance test surveillance video clip in the sequence of contrast performance test surveillance video clips, step S120 may further include the following specific contents:
analyzing and determining the average video correlation degree of each contrast performance test surveillance video clip in the contrast performance test surveillance video sequence, wherein the average video correlation degree is used for reflecting the average value of the video clip correlation degree between the corresponding contrast performance test surveillance video clip and each other contrast performance test surveillance video clip in the contrast performance test surveillance video sequence; from the contrast performance test surveillance video clip sequence, a corresponding target number of contrast performance test surveillance video clips (the target number may be preconfigured, and is not specifically limited herein, such as 20, 30, and 40, and the like) with the largest average video correlation degree are screened out to mark as corresponding key contrast performance test surveillance video clips.
It is understood that, in some implementations, the step S130 above may further include the following specific contents:
respectively comparing the video matching degree between the target performance test monitoring video and each contrast performance test monitoring video with a preset video matching degree reference value;
if at least one video matching degree which is greater than or equal to the reference value of the video matching degree exists in the video matching degrees between the target performance test monitoring video and each contrast performance test monitoring video, determining first target video characteristic information of the target performance test monitoring video by combining the contrast video characteristic information of each contrast performance test monitoring video;
if at least one video matching degree which is greater than or equal to the reference value of the video matching degree does not exist in the video matching degrees between the target performance test monitoring video and each contrast performance test monitoring video, determining second target video characteristic information of the target performance test monitoring video by combining the contrast video characteristic information of each contrast performance test monitoring video;
the comparison video characteristic information of each comparison performance test monitoring video is used for reflecting that the performance of the corresponding comparison electronic wire does not meet the target condition (namely the performance is poor), the first target video characteristic information is used for reflecting that the performance of the target electronic wire does not meet the target condition, and the second target video characteristic information is used for reflecting that the performance of the target electronic wire meets the target condition.
With reference to fig. 3, an embodiment of the present invention further provides an apparatus for determining performance of an electronic wire based on image processing, which is applicable to the system for determining performance of an electronic wire based on image processing. Wherein the performance determining apparatus of the electronic wire material based on image processing may include:
the video framing and screening module is used for framing and screening the acquired original performance testing monitoring video of the target electronic wire material so as to output a target performance testing monitoring video corresponding to the original performance testing monitoring video; the matching degree calculation module is used for calculating the matching degree of the target performance test monitoring video and each determined contrast performance test monitoring video in the contrast performance test monitoring video sequence respectively so as to output the video matching degree between the target performance test monitoring video and each contrast performance test monitoring video respectively, and each contrast performance test monitoring video has contrast video characteristic information; and the video characteristic determining module is used for determining the target video characteristic information of the target performance test monitoring video according to the video matching degree between the target performance test monitoring video and each contrast performance test monitoring video and by combining the contrast video characteristic information of each contrast performance test monitoring video, wherein the target video characteristic information is used for reflecting whether the performance of the target electronic wire material meets the target condition.
In summary, according to the method and system for determining the performance of the electronic wire based on image processing provided by the present invention, the collected original performance test monitoring video of the target electronic wire may be screened in frames to output the corresponding target performance test monitoring video; calculating the matching degree of the target performance test monitoring video and each determined contrast performance test monitoring video respectively so as to output the video matching degree between the target performance test monitoring video and each contrast performance test monitoring video respectively; and determining the target video characteristic information of the target performance test monitoring video according to the video matching degree between the target performance test monitoring video and each contrast performance test monitoring video and by combining the contrast video characteristic information of each contrast performance test monitoring video. Based on the method, the result of whether the performance of the target electronic wire meets the target condition can be obtained by sequentially performing frame screening, matching degree calculation and video characteristic information determination on the acquired original performance test monitoring video, so that manual observation and analysis in the prior art are effectively replaced, the efficiency of performance determination of the electronic wire is improved to a certain extent, and the defects in the prior art can be overcome.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for determining the performance of an electronic wire material based on image processing is characterized by comprising the following steps:
performing frame screening on the collected original performance test monitoring video of the target electronic wire material to output a target performance test monitoring video corresponding to the original performance test monitoring video;
respectively carrying out matching degree calculation on the target performance test monitoring video and each determined contrast performance test monitoring video in the contrast performance test monitoring video sequence so as to output the video matching degree between the target performance test monitoring video and each contrast performance test monitoring video, wherein each contrast performance test monitoring video has contrast video characteristic information;
and determining the target video characteristic information of the target performance test monitoring video according to the video matching degree between the target performance test monitoring video and each contrast performance test monitoring video and by combining the contrast video characteristic information of each contrast performance test monitoring video, wherein the target video characteristic information is used for reflecting whether the performance of the target electronic wire meets the target condition.
2. The method for determining performance of electronic wire based on image processing as claimed in claim 1, wherein said step of performing frame-wise screening on the collected original performance testing surveillance video of the target electronic wire to output the target performance testing surveillance video corresponding to the original performance testing surveillance video comprises:
in the performance test process of a target electronic wire material, acquiring an original performance test monitoring video corresponding to the target electronic wire material, wherein the original performance test monitoring video comprises a plurality of original performance test monitoring video frames which are continuous in a frame time sequence;
for every two original performance test monitoring video frames with close frame time sequences in the original performance test monitoring video frames, carrying out similarity calculation on the two original performance test monitoring video frames relative to the outline of the electronic wire material so as to output the corresponding outline similarity of the electronic wire material;
and screening the plurality of original performance test surveillance video frames according to the electronic wire profile similarity corresponding to every two original performance test surveillance video frames with close frame time sequences in the plurality of original performance test surveillance video frames, so as to construct a target performance test surveillance video corresponding to the original performance test surveillance video based on the screened target performance test surveillance video frames.
3. The method for determining the performance of the electronic wire material based on the image processing as claimed in claim 1, wherein the step of calculating the matching degree of the target performance test surveillance video with each contrast performance test surveillance video in the determined contrast performance test surveillance video sequence to output the video matching degree between the target performance test surveillance video and each contrast performance test surveillance video respectively comprises:
extracting a plurality of unknown performance test monitoring videos and a plurality of known performance test monitoring videos, wherein each unknown performance test monitoring video does not have contrast video characteristic information, each known performance test monitoring video has contrast video characteristic information, each unknown performance test monitoring video has corresponding line profile identification information of a contrast electronic line material, and each unknown performance test monitoring video and each known performance test monitoring video are obtained by performing video monitoring on the performance test process of the corresponding contrast electronic line material;
according to the line profile identification information of each unknown performance test monitoring video, respectively performing feature mining processing on the line profile identification information corresponding to each unknown performance test monitoring video so as to output a line profile identification information mining result corresponding to each unknown performance test monitoring video;
extracting each unknown performance test monitoring video matched with the characteristic information of the comparison video from the plurality of unknown performance test monitoring videos based on the mining result of the profile identification information of the wire material corresponding to each unknown performance test monitoring video, marking the unknown performance test monitoring video as a target unknown performance test monitoring video, and distributing the characteristic information of the comparison video to the target unknown performance test monitoring video;
constructing and forming a corresponding comparison performance test monitoring video sequence based on the marked target unknown performance test monitoring video and the plurality of known performance test monitoring videos, wherein each comparison performance test monitoring video in the comparison performance test monitoring video sequence belongs to the target unknown performance test monitoring video or the known performance test monitoring video;
and respectively calculating the matching degree of the target performance test monitoring video and each contrast performance test monitoring video in the contrast performance test monitoring video sequence so as to output the video matching degree between the target performance test monitoring video and each contrast performance test monitoring video.
4. The method for determining the performance of the electronic wire material based on the image processing as claimed in claim 3, wherein the step of extracting each unknown performance test monitoring video matched with the feature information of the comparison video from the plurality of unknown performance test monitoring videos based on the wire material profile identification information mining result corresponding to each unknown performance test monitoring video to mark the unknown performance test monitoring video as a target unknown performance test monitoring video, and then distributing the feature information of the comparison video to the unknown performance test monitoring video comprises:
loading a line profile identification information mining result corresponding to each unknown performance test monitoring video into a target video detection neural network to form a video prediction matching degree corresponding to each unknown performance test monitoring video, wherein the video prediction matching degree is used for reflecting the matching degree of the unknown performance test monitoring video and the contrast video characteristic information, the target video detection neural network is formed by performing network optimization on a plurality of typical performance test monitoring videos with line profile identification information and typical identification information corresponding to each typical performance test monitoring video, the typical identification information comprises first typical identification information and second typical identification information, the first typical identification information is used for reflecting the matching of the typical performance test monitoring video and the contrast video characteristic information, and the second typical identification information is used for reflecting the mismatching of the typical performance test monitoring video and the contrast video characteristic information;
and extracting each unknown performance test monitoring video matched with the characteristic information of the comparison video from the plurality of unknown performance test monitoring videos based on the video prediction matching degree corresponding to each unknown performance test monitoring video, marking the unknown performance test monitoring video as a target unknown performance test monitoring video, and distributing the characteristic information of the comparison video to the target unknown performance test monitoring video.
5. The method according to claim 3, wherein the step of calculating the matching degree between the target performance test surveillance video and each contrast performance test surveillance video in the determined contrast performance test surveillance video sequence to output the video matching degree between the target performance test surveillance video and each contrast performance test surveillance video further comprises:
respectively carrying out video segmentation processing on each contrast performance test monitoring video in the contrast performance test monitoring video sequence so as to output a contrast performance test monitoring video segment sequence corresponding to each contrast performance test monitoring video;
respectively carrying out video segment feature coding operation on each contrast performance test monitoring video segment in the contrast performance test monitoring video segment sequence to form a video segment feature coding result corresponding to each contrast performance test monitoring video segment;
respectively fusing and outputting a contrast video feature coding result corresponding to each contrast performance test surveillance video in the contrast performance test surveillance video sequence based on a video segment feature coding result corresponding to each contrast performance test surveillance video segment and a video segment importance corresponding to each contrast performance test surveillance video segment;
in the process of executing the step of calculating the matching degree between the target performance test surveillance video and each contrast performance test surveillance video in the contrast performance test surveillance video sequence respectively to output the video matching degree between the target performance test surveillance video and each contrast performance test surveillance video respectively, the contrast video feature coding result is used for representing the corresponding contrast performance test surveillance video to calculate the matching degree.
6. The method for determining performance of electronic wire material based on image processing according to claim 5, wherein said step of respectively merging and outputting the feature coding result of the contrast video corresponding to each of the contrast performance test surveillance videos in the contrast performance test surveillance video sequence based on the feature coding result of the video segment corresponding to each of the contrast performance test surveillance video segments and the importance of the video segment corresponding to each of the contrast performance test surveillance video segments comprises:
respectively performing product calculation on corresponding video segment feature coding results based on the video segment importance degree corresponding to each contrast performance test monitoring video segment to output a fusion video segment feature coding result corresponding to each contrast performance test monitoring video segment;
and summing the fusion video segment feature coding results corresponding to each contrast performance test monitoring video segment to output the corresponding merged video segment feature coding result, and then performing feature compression operation on the merged video segment feature coding results to form a contrast video feature coding result corresponding to each contrast performance test monitoring video in the contrast performance test monitoring video sequence.
7. The method for determining the performance of the electronic wire material based on the image processing as claimed in claim 3, wherein the step of calculating the matching degree of the target performance test surveillance video with each contrast performance test surveillance video in the determined contrast performance test surveillance video sequence to output the video matching degree between the target performance test surveillance video and each contrast performance test surveillance video further comprises:
performing video segmentation processing on each contrast performance test monitoring video in the contrast performance test monitoring video sequence respectively to output a contrast performance test monitoring video segment sequence corresponding to each contrast performance test monitoring video;
performing video segment feature coding operation on a key contrast performance test monitoring video segment in the contrast performance test monitoring video segment sequence to output a video segment feature coding result corresponding to the key contrast performance test monitoring video segment;
determining a comparison video feature coding result corresponding to each comparison performance test surveillance video in the comparison performance test surveillance video sequence based on the video segment feature coding result corresponding to the key comparison performance test surveillance video segment and the video segment importance degree corresponding to the key comparison performance test surveillance video segment;
in the process of executing the step of calculating the matching degree of the target performance test surveillance video and each contrast performance test surveillance video in the contrast performance test surveillance video sequence respectively to output the video matching degree between the target performance test surveillance video and each contrast performance test surveillance video respectively, the feature coding result of the contrast video is used for representing the corresponding contrast performance test surveillance video to calculate the matching degree.
8. The method for determining the performance of the electronic wire material based on the image processing as claimed in claim 7, wherein the step of calculating the matching degree of the target performance test surveillance video with each contrast performance test surveillance video in the determined contrast performance test surveillance video sequence to output the video matching degree between the target performance test surveillance video and each contrast performance test surveillance video further comprises:
analyzing and determining the average video correlation degree of each contrast performance test surveillance video clip in the contrast performance test surveillance video sequence, wherein the average video correlation degree is used for reflecting the average value of the video clip correlation degree between the corresponding contrast performance test surveillance video clip and each other contrast performance test surveillance video clip in the contrast performance test surveillance video sequence;
and screening out a target number of contrast performance test monitoring video clips with the maximum corresponding average video correlation degree from the contrast performance test monitoring video clip sequence to mark the target number of contrast performance test monitoring video clips as corresponding key contrast performance test monitoring video clips.
9. The method according to any one of claims 1 to 8, wherein the step of determining the target video feature information of the target performance test surveillance video according to the video matching degree between the target performance test surveillance video and each comparison performance test surveillance video and in combination with the comparison video feature information of each comparison performance test surveillance video comprises:
respectively comparing the video matching degree between the target performance test monitoring video and each contrast performance test monitoring video with a preset video matching degree reference value;
if at least one video matching degree which is greater than or equal to the reference value of the video matching degree exists in the video matching degrees between the target performance test monitoring video and each contrast performance test monitoring video, determining first target video characteristic information of the target performance test monitoring video by combining the contrast video characteristic information of each contrast performance test monitoring video;
if at least one video matching degree which is greater than or equal to the reference value of the video matching degree does not exist in the video matching degrees between the target performance test monitoring video and each contrast performance test monitoring video, determining second target video characteristic information of the target performance test monitoring video by combining the contrast video characteristic information of each contrast performance test monitoring video;
the comparison video characteristic information of each comparison performance test monitoring video is used for reflecting that the performance of the corresponding comparison electronic wire does not meet the target condition, the first target video characteristic information is used for reflecting that the performance of the target electronic wire does not meet the target condition, and the second target video characteristic information is used for reflecting that the performance of the target electronic wire meets the target condition.
10. A system for determining the performance of an electronic thread based on image processing, comprising a processor and a memory, said memory being adapted to store a computer program, said processor being adapted to execute said computer program to implement the method of any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211510181.3A CN115620210B (en) | 2022-11-29 | 2022-11-29 | Method and system for determining performance of electronic wire material based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211510181.3A CN115620210B (en) | 2022-11-29 | 2022-11-29 | Method and system for determining performance of electronic wire material based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115620210A true CN115620210A (en) | 2023-01-17 |
| CN115620210B CN115620210B (en) | 2023-03-21 |
Family
ID=84880152
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211510181.3A Active CN115620210B (en) | 2022-11-29 | 2022-11-29 | Method and system for determining performance of electronic wire material based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115620210B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008199136A (en) * | 2007-02-09 | 2008-08-28 | Sharp Corp | Similar video search apparatus and similar video search method |
| US20140366052A1 (en) * | 2013-06-05 | 2014-12-11 | David J. Ives | System for Social Media Tag Extraction |
| CN108337532A (en) * | 2018-02-13 | 2018-07-27 | 腾讯科技（深圳）有限公司 | Perform mask method, video broadcasting method, the apparatus and system of segment |
| WO2020078111A1 (en) * | 2018-10-17 | 2020-04-23 | 京东数字科技控股有限公司 | Weight measurement method and device, and computer readable storage medium |
| WO2020156361A1 (en) * | 2019-02-02 | 2020-08-06 | 杭州睿琪软件有限公司 | Training sample obtaining method and apparatus, electronic device and storage medium |
| WO2020210506A1 (en) * | 2019-04-09 | 2020-10-15 | Purdue Research Foundationj | Methods and systems for crack detection using a fully convolutional network |
| WO2021004112A1 (en) * | 2019-07-05 | 2021-01-14 | 深圳壹账通智能科技有限公司 | Anomalous face detection method, anomaly identification method, device, apparatus, and medium |
| CN114170554A (en) * | 2021-12-10 | 2022-03-11 | 上海瑾盛通信科技有限公司 | Video detection method, video detection device, storage medium and electronic equipment |
| CN114978037A (en) * | 2022-07-27 | 2022-08-30 | 一道新能源科技(衢州)有限公司 | Solar cell performance data monitoring method and system |
| CN115018840A (en) * | 2022-08-08 | 2022-09-06 | 珠海市南特金属科技股份有限公司 | Method, system and device for detecting cracks of precision casting |
| CN115091472A (en) * | 2022-08-26 | 2022-09-23 | 珠海市南特金属科技股份有限公司 | Target positioning method based on artificial intelligence and clamping manipulator control system |
-
2022
- 2022-11-29 CN CN202211510181.3A patent/CN115620210B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008199136A (en) * | 2007-02-09 | 2008-08-28 | Sharp Corp | Similar video search apparatus and similar video search method |
| US20140366052A1 (en) * | 2013-06-05 | 2014-12-11 | David J. Ives | System for Social Media Tag Extraction |
| CN108337532A (en) * | 2018-02-13 | 2018-07-27 | 腾讯科技（深圳）有限公司 | Perform mask method, video broadcasting method, the apparatus and system of segment |
| WO2020078111A1 (en) * | 2018-10-17 | 2020-04-23 | 京东数字科技控股有限公司 | Weight measurement method and device, and computer readable storage medium |
| WO2020156361A1 (en) * | 2019-02-02 | 2020-08-06 | 杭州睿琪软件有限公司 | Training sample obtaining method and apparatus, electronic device and storage medium |
| WO2020210506A1 (en) * | 2019-04-09 | 2020-10-15 | Purdue Research Foundationj | Methods and systems for crack detection using a fully convolutional network |
| WO2021004112A1 (en) * | 2019-07-05 | 2021-01-14 | 深圳壹账通智能科技有限公司 | Anomalous face detection method, anomaly identification method, device, apparatus, and medium |
| CN114170554A (en) * | 2021-12-10 | 2022-03-11 | 上海瑾盛通信科技有限公司 | Video detection method, video detection device, storage medium and electronic equipment |
| CN114978037A (en) * | 2022-07-27 | 2022-08-30 | 一道新能源科技(衢州)有限公司 | Solar cell performance data monitoring method and system |
| CN115018840A (en) * | 2022-08-08 | 2022-09-06 | 珠海市南特金属科技股份有限公司 | Method, system and device for detecting cracks of precision casting |
| CN115091472A (en) * | 2022-08-26 | 2022-09-23 | 珠海市南特金属科技股份有限公司 | Target positioning method based on artificial intelligence and clamping manipulator control system |
Non-Patent Citations (1)
| Title |
|---|
| 黄翔;段宏兵;徐胜勇;宋波涛;陈志鹏;余参参;: "基于视频流的马铃薯排种器性能检测方法" * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115620210B (en) | 2023-03-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109886282B (en) | Object detection method, device, computer-readable storage medium and computer equipment | |
| CN115018840B (en) | Method, system and device for detecting cracks of precision casting | |
| CN114978037B (en) | Solar cell performance data monitoring method and system | |
| CN113902993A (en) | Environmental state analysis method and system based on environmental monitoring | |
| CN116821777A (en) | Novel basic mapping data integration method and system | |
| CN115588157B (en) | Performance data processing method and system of cross-linked low-smoke low-halogen polyolefin material | |
| CN115620210B (en) | Method and system for determining performance of electronic wire material based on image processing | |
| CN115065842B (en) | Panoramic video streaming interaction method and system based on virtual reality | |
| CN114925348B (en) | Security verification method and system based on fingerprint identification | |
| CN115484044A (en) | Data state monitoring method and system | |
| CN115375886A (en) | Data acquisition method and system based on cloud computing service | |
| CN115147752A (en) | Video analysis method and device and computer equipment | |
| CN115620211A (en) | Performance data processing method and system of flame-retardant low-smoke halogen-free sheath | |
| CN115330140A (en) | Building risk prediction method based on data mining and prediction system thereof | |
| CN115147134A (en) | Product anti-counterfeiting tracing method and system based on industrial Internet and cloud platform | |
| CN115700821B (en) | Cell identification method and system based on image processing | |
| CN115375412B (en) | Intelligent commodity recommendation processing method and system based on image recognition | |
| CN115631448B (en) | Audio and video quality inspection processing method and system | |
| CN115272831B (en) | Transmission method and system for monitoring images of suspension state of contact network | |
| CN116437057B (en) | System optimization method and system for diborane production monitoring system | |
| CN115909215B (en) | Edge intrusion early warning method and system based on target detection | |
| CN116958838B (en) | Forest resource monitoring method and system based on unmanned aerial vehicle aerial survey technology | |
| CN114997343B (en) | Fault reason tracing method and system based on air purification detection | |
| CN114998811B (en) | Big data processing method and system based on intelligent network interconnection | |
| CN113838110B (en) | Verification method and device for target detection result, storage medium and electronic equipment |
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 | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: No. 9, Xincheng Second Road, Xincheng Industrial Park, Xincheng Town, Xinxing County, Yunfu City, Guangdong Province 527300 Patentee after: Guangdong Xiangli Technology Group Co.,Ltd. Address before: 527499 No. 9, Xincheng Second Road, Xincheng Industrial Park, Xincheng Town, Xinxing County, Yunfu City, Guangdong Province Patentee before: GUANGDONG XIANGLI TECHNOLOGY Co.,Ltd. |