CN110223267A - The recognition methods of refractory brick deep defects based on height histogram divion - Google Patents
The recognition methods of refractory brick deep defects based on height histogram divion Download PDFInfo
- Publication number
- CN110223267A CN110223267A CN201910195094.5A CN201910195094A CN110223267A CN 110223267 A CN110223267 A CN 110223267A CN 201910195094 A CN201910195094 A CN 201910195094A CN 110223267 A CN110223267 A CN 110223267A
- Authority
- CN
- China
- Prior art keywords
- image
- refractory brick
- point cloud
- height
- plane
- 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
- 239000011449 brick Substances 0.000 title claims abstract description 60
- 230000007547 defect Effects 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000012937 correction Methods 0.000 claims abstract description 18
- 230000011218 segmentation Effects 0.000 claims abstract description 8
- 238000010586 diagram Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 abstract description 4
- 230000007797 corrosion Effects 0.000 abstract description 2
- 238000005260 corrosion Methods 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 description 8
- 238000005259 measurement Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 238000003723 Smelting Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000004630 mental health Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 238000005272 metallurgy Methods 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20028—Bilateral filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30132—Masonry; Concrete
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Processing (AREA)
Abstract
The invention discloses the recognition methods of the refractory brick deep defects based on height histogram divion, the colour point clouds data of refractory brick are obtained including the use of structured light sensor, colour point clouds data are fused together by image data and three-dimensional point cloud, plane fitting is carried out to refractory brick picture point cloud using least square method and obtains zero plane, and obtain the height and width of original refractory brick image, according to the dimensional parameters and zero plane of original refractory brick image, generate corresponding datum plane image, it is poor make to original refractory brick image and datum plane image, point cloud data figure after obtaining slant correction, segmentation is filtered to the height histogram of the point cloud after slant correction, obtain the point cloud information of set depth.The present invention can be obtained the deep defects information of refractory brick, effectively avoid permeating corrosion phenomenon, extend the service life of refractory brick based on Gray Moment plane fitting to picture altitude map analysis.
Description
Technical field
The present invention relates to a kind of recognition methods of refractory brick deep defects based on height histogram divion.
Background technique
Refractory brick refers to that its chemistry is stable with physical property and energy normal use under high temperature environment according to international standard
Nonmetallic (being not precluded containing a certain proportion of metal) material and product.Refractory brick can be subjected to various mechanisms at high temperature
And physicochemical change, it is widely used in the industrial circles such as metallurgy, chemical industry, petroleum, power generation.In recent years, the refractory brick in China is raw
Rapid Development of Enterprise is produced, the market competition of refractory brick is also increasingly fierce, and numerous enterprises improve production technology and quality inspection technology one after another,
Production and detection automation are realized, to improve enterprise competitiveness.It is long before the offline vanning of product on the production line of refractory brick
It has all been by manually using tape measure manual measurement, naked eyes judge deep defects, such as the unfilled corner, truncation and fiber crops of refractory brick since phase
Face etc..Since in refractory brick production process, vibrating noise of press etc. is larger to the physical and mental health harm of worker, and much lacks
Falling into all is that worker relies on micro-judgment, larger by subjective impact, can not establish a unified judgment criteria.In addition, high-volume
The process will not only consume a large amount of labour costs in production process, but also repetition, dull measurement observation work easily cause people
Member's fatigue, is easy to appear erroneous judgement, if individual defective products are mixed into finished product by the gross, serious financial consequences can be brought to factory, even
Seriously affect the production of steel.Therefore, in the dangerous situation of some unsuitable manual works, what artificial vision was difficult to meet the requirements
Occasion and the occasion of product testing can not be continuously and stably carried out with high reproducibility, intelligence and eyes by people.It is resistance to
Firebrick is during production, in addition to shape geometric dimension, deep defects, quality and its steel of these defects for refractory brick
The behaviour in service of the smelting process of iron suffers from very important influence, therefore for the defect of refractory brick, is effectively identified
It is the vital ring of refractory brick quality testing.It there is no the measurement system that automatic measurement is carried out to the surface defect of refractory brick at present
System or method.
Summary of the invention
The purpose of the present invention is to provide a kind of recognition methods that can identify refractory brick deep defects.
The technical solution adopted by the present invention to solve the technical problems is:
The recognition methods of refractory brick deep defects based on height histogram divion, comprising the following steps:
Step 1, the colour point clouds data that refractory brick is obtained using structured light sensor, colour point clouds data are by image data
It is fused together with three-dimensional point cloud, the coordinate system of colour point clouds data is on the basis of sensor pose；
Step 2 carries out plane fitting acquisition zero plane to refractory brick picture point cloud using least square method, and obtains original
It is flat to generate corresponding benchmark according to the dimensional parameters and zero plane of original refractory brick image for the height and width of refractory brick image
Face image；
Step 3 carries out original refractory brick image and datum plane image to make poor point cloud data after obtaining slant correction
Figure；
Step 4 is filtered segmentation to the height histogram of the point cloud after slant correction, obtains the point cloud letter of set depth
The height value range of breath, setting height bandpass filter is filtered a cloud level degree histogram, the company within the scope of height value
Logical domain is accordingly to be regarded as deep defects.
Further, in step 2, the generation method of datum plane image is: according to fitting parameter α, beta, gamma, bound firebrick
Colour point clouds data Image (r, c) is generated datum plane image Image (r, c)0: for a width 2D consecutive image f (x, y)
(>=0), p+q rank square mpqIs defined as:
Wherein, p, q are non-negative integers, for discretization digital picture, above formula are as follows:
Wherein, (r0,c0) it is center-of-mass coordinate, and
Single order plane approximation method is described by following formula:
Image (r, c)=α (r-r0)+β(c-c0)+γ (4-13)
Wherein, r0For the abscissa to fitted area, c0For the ordinate to fitted area, γ is to the flat of fitted area
Equal gray scale, F are the area of entire plane, and MRow is the Gray Moment along line direction, and MCol is the Gray Moment along column direction, then
Have:
MRow=sum ((r-r0)*(Image(r,c)-γ))/F2 (4-14)
MCol=sum ((c-r0)*(Image(r,c)-γ))/F2 (4-15)
Further, to former refractory brick point cloud chart Image (r, c) and datum plane image Image (r, c)0It is poor make, and obtains
Point cloud data figure Image'(r, c after taking slant correction).
Image'(r, c)=Image (r, c)-Image (r, c)0(4-18)；
Point cloud data figure after slant correction is split along zero plane normal direction, obtains point cloud level degree histogram；If
The height value range for setting height bandpass filter is filtered a cloud level degree histogram, and the connected domain within the scope of height value is equal
It is considered as deep defects.
Further, in step 4, connected domain is obtained according to two-pass scan method, comprising the following steps:
Step 4-1: first pass is carried out to refractory brick threshold binary image, assigns each location of pixels one label, is assigned
The one or more different labels of pixel set in the same connected domain, merge and belong to the same connected domain but have different value
Label；
Step 4-2: second time scanning is carried out to refractory brick threshold binary image, the same label with relation of equality is marked
Pixel be classified as a connected domain, assign one identical label of connected domain.
Further, step 4-1 carries out connected domain acquisition using se ed filling algorithm:
(1) scan refractory brick threshold figure in pixel, until current pixel point B (x, y)==1:
A, it as seed and assigns B (x, y) to label, the adjacent all foreground pixels of the seed is all then pressed into stack
In；
B, stack top pixel is popped up, assigns with seed stack top pixel to identical label, it then again will be with the stack top pixel phase
Adjacent all foreground pixels are all pressed into stack；
C, b step is repeated, until stack is sky；
At this point, all pixel values with same label form a connected domain；
Any one pixel except connected domain is obtained as seed, (1) step is repeated, until the end of scan；Scanning knot
Shu Hou, so that it may obtain connected domain all in image B.
The present invention has the advantages that
1. picture altitude map analysis is obtained the deep defects information of refractory brick, is effectively kept away based on Gray Moment plane fitting
Exempt from permeating corrosion phenomenon, extends the service life of refractory brick.
2. using two-pass scan method, do not need to apply for a large amount of stack space, the speed for obtaining connected region is fast, and can
Multiple connected regions are obtained, RAM leakage will not occur, there is relatively good execution efficiency.
Detailed description of the invention
Fig. 1 is refractory brick scanning surface slant correction result.
Fig. 2 is segmentation anterior and posterior height histogram comparison diagram.
Fig. 3 is that deep defects extract result.
Specific embodiment
The present invention is further described with reference to the accompanying drawings and detailed description.
Refractory brick during production, in addition to because contact and caused by surface scratch, as the loss of mold
And cause some deep defects: pit pitted skin and unfilled corner truncation etc..Gocator2350 sensor acquired image data are shadows
The colour point clouds data being fused together as data and three-dimensional point cloud.In this regard, can divide from the elevation information in point cloud data
Analysis obtains deep defects.
The data of sensor acquisition are colour point clouds data, and coordinate system is on the basis of sensor pose, therefore first
It needs upper surface surveyed to refractory brick to be fitted, carries out height segmentation along its normal direction, deep defects information can be obtained.
The recognition methods of refractory brick deep defects based on height histogram divion, comprising the following steps:
Step 1, the colour point clouds data that refractory brick is obtained using structured light sensor, colour point clouds data are by image data
It is fused together with three-dimensional point cloud, the coordinate system of colour point clouds data is on the basis of sensor pose；
Step 2 carries out plane fitting acquisition zero plane to refractory brick picture point cloud using least square method, and obtains original
It is flat to generate corresponding benchmark according to the dimensional parameters and zero plane of original refractory brick image for the height and width of refractory brick image
Face image；
Step 3 carries out original refractory brick image and datum plane image to make poor point cloud data after obtaining slant correction
Figure；
Step 4 is filtered segmentation to the height histogram of the point cloud after slant correction, obtains the point cloud letter of set depth
The height value range of breath, setting height bandpass filter is filtered a cloud level degree histogram, the company within the scope of height value
Logical domain is accordingly to be regarded as deep defects.
Based on the plane fitting for calculating gray value square and single order planar approximation
Square is the operator for describing characteristics of image, and nowadays image moment technology is widely used to image retrieval and identification, image
The fields such as matching, image reconstruction, digital compression, digital watermarking and dynamic image sequence analysis.
Image can be seen as a plate object, and the value of each pixel regards the density at this as.Phase is asked to certain point
Prestige is exactly the square of the image at this point.For a width 2D consecutive image f (x, y) (>=0), p+q rank square mpqIs defined as:
Wherein, p, q are non-negative integers, for discretization digital picture, above formula are as follows:
Wherein, (r0,c0) it is center-of-mass coordinate, and
Single order plane approximation method is realized by minimizing the distance of sum of the grayscale values interplanar[61], can pass through
Following formula describes:
Image (r, c)=α (r-r0)+β(c-c0)+γ (4-13)
Wherein, r0And c0As to the transverse and longitudinal coordinate of fitted area, γ is the average gray to fitted area.
Enabling F is the area of entire plane, and MRow and MCol then have respectively along the square in row and column direction:
MRow=sum ((r-r0)*(Image(r,c)-γ))/F2 (4-14)
MCol=sum ((c-r0)*(Image(r,c)-γ))/F2 (4-15)
Deep defects are extracted in height histogram thresholding segmentation based on slant correction
The fitting parameter α acquired according to above formula, beta, gamma produce piece image as base in conjunction with the size of original image
It is quasi-.At this point, original image and benchmark image are carried out to make poor point cloud data figure after slant correction can be obtained, slant correction situation
It is illustrated in fig. 1 shown below.
At this point, being split for the height map after slant correction, it can be obtained and be split along fit Plane normal direction
Effect.Probability analysis, available histogram as shown in Figure 2 are carried out to the altitude information after slant correction.
Height bandpass filter is set, and height value range is -2.5-0mm, is filtered segmentation, available in this range
Interior all deep defects, are illustrated in fig. 3 shown below, i.e. pit pitted skin (left side) and unfilled corner truncation (right side).
To all deep defects met in altitude range being partitioned into, it is collectively labeled as 1, remaining is labeled as 0.According to connection
Domain algorithm extracts connected domain, and the area of deep defects is in 40mm2Above extracted region is as follows:
Pit pitted skin: [98,122,178,59,281,117,107,120,116,55,290,50,103,139]
Unfilled corner truncation: [92,120,97,165,63,160]
Experiment is taken multiple measurements to different types of refractory brick, in experiment is repeated several times, the defect of refractory brick is tested
Data are as shown in the table, and the defects of table value is the index according to agreement, and the pit pitted skin upper limit is 1.5mm, wherein OK is indicated
Qualification, NG indicate unqualified.By measurement result it is found that connected domain quantization defect method has obtained effective verifying, i.e. the measurement system
System can satisfy defect recognition requirement.
Table defectoscopy experimental result
Data are analysis shows the defect recognition of system meets required precision, to prove the stabilization of this set vision measuring method
Property and repeatability precision are meet demands.
Content described in this specification embodiment is only enumerating to the way of realization of inventive concept, protection of the invention
Range should not be construed as being limited to the specific forms stated in the embodiments, and protection scope of the present invention is also and in art technology
Personnel conceive according to the present invention it is conceivable that equivalent technologies mean.
Claims (5)
1. the recognition methods of the refractory brick deep defects based on height histogram divion, comprising the following steps:
Step 1, the colour point clouds data that refractory brick is obtained using structured light sensor, colour point clouds data are by image data and three
Dimension point cloud is fused together, and the coordinate system of colour point clouds data is on the basis of sensor pose；
Step 2 carries out plane fitting acquisition zero plane to refractory brick picture point cloud using least square method, and obtains original fire resisting
The height and width of brick image generate corresponding reference plane diagram according to the dimensional parameters and zero plane of original refractory brick image
Picture；
Step 3 carries out original refractory brick image and datum plane image to make poor point cloud data figure after obtaining slant correction；
Step 4 is filtered segmentation to the height histogram of the point cloud after slant correction, obtains the point cloud information of set depth,
The height value range that height bandpass filter is arranged is filtered a cloud level degree histogram, the connected domain within the scope of height value
It is accordingly to be regarded as deep defects.
2. the recognition methods of the refractory brick deep defects based on height histogram divion, feature exist as described in claim 1
In in step 2, the generation method of datum plane image is: according to fitting parameter α, beta, gamma, bound firebrick colour point clouds data
Image (r, c) is generated datum plane image Image (r, c)0: for a width 2D consecutive image f (x, y) (>=0), p+q rank square
mpqIs defined as:
Wherein, p, q are non-negative integers, for discretization digital picture, above formula are as follows:
Wherein, (r0,c0) it is center-of-mass coordinate, and
Single order plane approximation method is described by following formula:
Image (r, c)=α (r-r0)+β(c-c0)+γ (4-13)
Wherein, r0For the abscissa to fitted area, c0For the ordinate to fitted area, γ is the average ash to fitted area
Degree, F are the area of entire plane, and MRow is the Gray Moment along line direction, and MCol is the Gray Moment along column direction, then have:
MRow=sum ((r-r0)*(Image(r,c)-γ))/F2 (4-14)
MCol=sum ((c-r0)*(Image(r,c)-γ))/F2 (4-15)
3. the recognition methods of the refractory brick deep defects based on height histogram divion, feature exist as claimed in claim 2
In to former refractory brick point cloud chart Image (r, c) and datum plane image Image (r, c)0It is poor make, after obtaining slant correction
Point cloud data figure Image'(r, c).
Image'(r, c)=Image (r, c)-Image (r, c)0(4-18)；
Point cloud data figure after slant correction is split along zero plane normal direction, obtains point cloud level degree histogram；Setting is high
The height value range of degree bandpass filter is filtered a cloud level degree histogram, and the connected domain within the scope of height value is accordingly to be regarded as
Deep defects.
4. the recognition methods of the refractory brick deep defects based on height histogram divion, feature exist as claimed in claim 3
In in step 4, according to two-pass scan method acquisition connected domain, comprising the following steps:
Step 4-1: first pass is carried out to refractory brick threshold binary image, assigns each location of pixels one label, is assigned same
The one or more different labels of pixel set in a connected domain, merge and belong to the same connected domain but the mark with different value
Label；
Step 4-2: second time scanning, the picture that the same label with relation of equality is marked are carried out to refractory brick threshold binary image
Element is classified as a connected domain, assigns one identical label of connected domain.
5. the recognition methods of the refractory brick deep defects based on height histogram divion, feature exist as claimed in claim 4
In step 4-1 carries out connected domain acquisition using se ed filling algorithm:
(1) scan refractory brick threshold figure in pixel, until current pixel point B (x, y)==1:
A, it as seed and assigns B (x, y) to label, is then all pressed into the seed adjacent all foreground pixels in stack；
B, stack top pixel is popped up, assigns with seed stack top pixel to identical label, it then again will be adjacent with the stack top pixel
All foreground pixels are all pressed into stack；
C, b step is repeated, until stack is sky；
At this point, all pixel values with same label form a connected domain；
Any one pixel except connected domain is obtained as seed, (1) step is repeated, until the end of scan；After the end of scan,
It can be obtained by connected domain all in image B.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810208468 | 2018-03-14 | ||
| CN2018102084688 | 2018-03-14 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110223267A true CN110223267A (en) | 2019-09-10 |
| CN110223267B CN110223267B (en) | 2021-06-18 |
Family
ID=63626447
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810214940.9A Withdrawn CN108596873A (en) | 2018-03-14 | 2018-03-15 | The recognition methods of refractory brick deep defects based on height histogram divion |
| CN201910195094.5A Active CN110223267B (en) | 2018-03-14 | 2019-03-14 | Height histogram segmentation-based firebrick depth defect identification method |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810214940.9A Withdrawn CN108596873A (en) | 2018-03-14 | 2018-03-15 | The recognition methods of refractory brick deep defects based on height histogram divion |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN108596873A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112116576A (en) * | 2020-09-20 | 2020-12-22 | 中国人民解放军空军工程大学 | Defect detection method based on polarization structure light imaging and improved Mask R-CNN |
| CN112489025A (en) * | 2020-12-07 | 2021-03-12 | 南京钢铁股份有限公司 | Method for identifying pit defects on surface of continuous casting billet |
| CN113008895A (en) * | 2021-01-29 | 2021-06-22 | 广州信邦智能装备股份有限公司 | Block fitting defect detection method based on three-dimensional data |
| CN116481460A (en) * | 2023-05-26 | 2023-07-25 | 中国矿业大学 | Apparent pit defect size detection method based on three-dimensional reconstruction model |
| CN117073538A (en) * | 2023-07-28 | 2023-11-17 | 广州市西克传感器有限公司 | Refractory brick self-adaptive detection method based on three-dimensional vision |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109658398B (en) * | 2018-12-12 | 2021-05-18 | 华中科技大学 | Part surface defect identification and evaluation method based on three-dimensional measurement point cloud |
| CN110349195B (en) * | 2019-06-25 | 2021-09-03 | 杭州汇萃智能科技有限公司 | Depth image-based target object 3D measurement parameter acquisition method and system and storage medium |
| CN113178228B (en) * | 2021-05-25 | 2023-02-10 | 郑州中普医疗器械有限公司 | Cell analysis method based on nuclear DNA analysis, computer device, and storage medium |
| CN113793296B (en) * | 2021-08-06 | 2024-09-06 | 中国科学院国家天文台 | Point cloud data processing method and device |
| CN114663713B (en) * | 2022-05-20 | 2022-08-30 | 海门市博洋铸造有限公司 | Metal wire drawing production control method and system based on Hough transform |
| CN116165216B (en) * | 2023-03-16 | 2023-08-04 | 苏州鼎纳自动化技术有限公司 | Liquid crystal display micro scratch flaw 3D detection method, system and computing equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103500329A (en) * | 2013-10-16 | 2014-01-08 | 厦门大学 | Street lamp automatic extraction method based on vehicle-mounted moving laser scanning point cloud |
| CN106056614A (en) * | 2016-06-03 | 2016-10-26 | 武汉大学 | Building segmentation and contour line extraction method of ground laser point cloud data |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6326509A (en) * | 1986-07-19 | 1988-02-04 | Fujitsu Ltd | Inspection device for packaging component |
| CN100506401C (en) * | 2007-01-11 | 2009-07-01 | 浙江大学 | Pearl real time detection and classifying system based on mechanical vision |
| CN104020475B (en) * | 2014-06-20 | 2016-03-23 | 西安煤航信息产业有限公司 | A kind of line of electric force based on on-board LiDAR data extracts and modeling method |
| CN106354935B (en) * | 2016-08-30 | 2017-07-18 | 华中科技大学 | Complex curved surface parts matching detection method based on electron outside nucleus probability density distribution |
| WO2018043251A1 (en) * | 2016-08-31 | 2018-03-08 | 日本電気株式会社 | Defect detecting device, defect detecting method, and computer-readable recording medium |
| CN107084671B (en) * | 2017-02-24 | 2019-07-16 | 浙江大学 | A kind of recessed bulb diameter measuring system and measurement method based on three wire configuration light |
| CN107506768A (en) * | 2017-10-11 | 2017-12-22 | 电子科技大学 | A kind of stranded recognition methods of transmission line wire based on full convolutional neural networks |
-
2018
- 2018-03-15 CN CN201810214940.9A patent/CN108596873A/en not_active Withdrawn
-
2019
- 2019-03-14 CN CN201910195094.5A patent/CN110223267B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103500329A (en) * | 2013-10-16 | 2014-01-08 | 厦门大学 | Street lamp automatic extraction method based on vehicle-mounted moving laser scanning point cloud |
| CN106056614A (en) * | 2016-06-03 | 2016-10-26 | 武汉大学 | Building segmentation and contour line extraction method of ground laser point cloud data |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112116576A (en) * | 2020-09-20 | 2020-12-22 | 中国人民解放军空军工程大学 | Defect detection method based on polarization structure light imaging and improved Mask R-CNN |
| CN112116576B (en) * | 2020-09-20 | 2023-04-18 | 中国人民解放军空军工程大学 | Polarization structure light imaging and improved defect detection method |
| CN112489025A (en) * | 2020-12-07 | 2021-03-12 | 南京钢铁股份有限公司 | Method for identifying pit defects on surface of continuous casting billet |
| CN113008895A (en) * | 2021-01-29 | 2021-06-22 | 广州信邦智能装备股份有限公司 | Block fitting defect detection method based on three-dimensional data |
| CN116481460A (en) * | 2023-05-26 | 2023-07-25 | 中国矿业大学 | Apparent pit defect size detection method based on three-dimensional reconstruction model |
| CN116481460B (en) * | 2023-05-26 | 2024-05-07 | 中国矿业大学 | Apparent pit defect size detection method based on three-dimensional reconstruction model |
| CN117073538A (en) * | 2023-07-28 | 2023-11-17 | 广州市西克传感器有限公司 | Refractory brick self-adaptive detection method based on three-dimensional vision |
| CN117073538B (en) * | 2023-07-28 | 2024-06-25 | 广东西克智能科技有限公司 | Refractory brick self-adaptive detection method based on three-dimensional vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108596873A (en) | 2018-09-28 |
| CN110223267B (en) | 2021-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110223267A (en) | The recognition methods of refractory brick deep defects based on height histogram divion | |
| CN106023158B (en) | The fresh water pipless pearl pearly layer defect identification method of SD-OCT images | |
| CN109658398B (en) | Part surface defect identification and evaluation method based on three-dimensional measurement point cloud | |
| CN110288561A (en) | Refractory brick surface scratch recognition methods based on frequency filtering enhancing | |
| CN110443243B (en) | Water level monitoring method, storage medium, network device and water level monitoring system | |
| CN109472261B (en) | Computer vision-based automatic monitoring method for grain storage quantity change of granary | |
| CN106643965B (en) | Method for accurately identifying liquid level by utilizing template matching | |
| CN108416766A (en) | Bilateral incidence type light guide plate defective vision detection method | |
| CN112378349A (en) | Sagger flatness detection device based on binocular structured light and detection method thereof | |
| CN102441581A (en) | Machine vision-based device and method for online detection of structural steel section size | |
| CN102654464A (en) | Copper strip surface defect detection system based on multi-feature fuzzy recognition | |
| US20180017375A1 (en) | Shanghai university of engineering science | |
| CN113362276B (en) | Visual detection method and system for plates | |
| CN112651968A (en) | Wood board deformation and pit detection method based on depth information | |
| CN102496161A (en) | Method for extracting contour of image of printed circuit board (PCB) | |
| CN106937109B (en) | The method that low cost judges resolution ratio of camera head level | |
| CN103345632A (en) | Method for detecting surface scratch defects of battery tail end | |
| CN115597494B (en) | Precision detection method and system for prefabricated part preformed hole based on point cloud | |
| CN113554667A (en) | Three-dimensional displacement detection method and device based on image recognition | |
| CN117890389B (en) | Online detection method and equipment for surface quality of refined products and storage medium thereof | |
| CN106248634A (en) | Fruit exocuticle glossiness measurement apparatus and method | |
| CN104655642A (en) | Automatic measurement, characterization and classification method for steel cracking defects and system of method | |
| CN116818233A (en) | High-precision bridge state monitoring method and system adopting laser and machine vision | |
| CN109034172B (en) | Product appearance defect detection method based on fuzzy relaxation constraint multi-core learning | |
| CN107610101B (en) | Method for measuring visual balance quality of digital image |
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 |