CN111721216A - Steel wire rope detection device based on three-dimensional image, surface damage detection method and rope diameter calculation method - Google Patents
Steel wire rope detection device based on three-dimensional image, surface damage detection method and rope diameter calculation method Download PDFInfo
- Publication number
- CN111721216A CN111721216A CN202010609547.7A CN202010609547A CN111721216A CN 111721216 A CN111721216 A CN 111721216A CN 202010609547 A CN202010609547 A CN 202010609547A CN 111721216 A CN111721216 A CN 111721216A
- Authority
- CN
- China
- Prior art keywords
- wire rope
- steel wire
- camera
- image
- bottom plate
- 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.)
- Pending
Links
Images
Classifications
-
- 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
- G01B11/08—Measuring arrangements characterised by the use of optical techniques for measuring diameters
Abstract
The invention relates to a steel wire rope detection device based on a three-dimensional image, a surface damage detection method and a rope diameter calculation method, and belongs to the technical field of steel wire rope detection, wherein the steel wire rope detection device is sleeved on a steel wire rope and comprises a camera, two mirrors, a white bottom plate, two light sources and a communication unit; the white bottom plate is arranged above the steel wire rope, and the camera is arranged below the steel wire rope; two mirrors are respectively arranged at the left side and the right side of the steel wire rope, each mirror is gradually inclined towards the direction close to the central point of the white bottom plate from top to bottom, and the extending included angle of the two mirrors is 120 ︒; the two light sources are respectively arranged at the left side and the right side of the steel wire rope and are both arranged below the steel wire rope and above the camera; the white bottom plate, the mirror and the camera are all relatively parallel to the steel wire rope; the white bottom plate, the mirror and the center point of the camera are all located on the same plane. The detection device is a device for automatically detecting surface damage and giving an alarm, and the device can continuously and automatically calculate the diameter of the steel wire rope in real time.
Description
Technical Field
The invention belongs to the technical field of steel wire rope detection, and particularly relates to a steel wire rope detection device based on a three-dimensional image, a surface damage detection method and a rope diameter calculation method.
Background
The steel wire rope is formed by twisting a plurality of small carbon steel wires into small strands, and then combining a plurality of the strands into ropes with different diameters around a rope core. The steel wire rope is used as a traction device and widely applied to various fields of national economy, such as elevators, high-altitude ropeways, hoisting and hoisting, transportation, ship traction, mine hoisting, bridges and the like. As an important part, the steel wire rope is often subjected to surface damage phenomena such as wire breakage, corrosion, abrasion and the like in the use process, so that safety production accidents are easily caused, property loss and casualties occur, and adverse social effects are caused.
When the steel wire rope bears different loads, the rope diameter changes, once the steel wire rope bears overweight articles, fatigue damage is easy to occur, the rope diameter can not be recovered, and the steel wire rope can not bear the articles again after the rope diameter is reduced to a certain value and needs to be replaced in time. The online real-time monitoring of the surface damage condition and the diameter of the steel wire rope is very important.
At present, the surface damage detection method of the steel wire rope comprises manual inspection and machine vision. The manual detection method is mainly used for observing whether the surface of the steel wire rope is damaged or not through naked eyes, and the running steel wire rope needs to stop working in the manual detection process. The manual detection cannot ensure the detection rate of the surface damage of the steel wire rope under the influence of factors such as personnel quality, working environment and severe working conditions. The machine vision detection method mainly comprises the steps of taking a picture by using a camera, transmitting the picture to a remote server, analyzing the surface damage of the steel wire rope on the picture by using a machine vision algorithm, and giving damage information.
The diameter of the steel wire rope is measured manually by using a caliper, the steel wire rope needs to stop working during measurement, local measurement is generally carried out, if the overall measurement takes too long, and the measured value needs to be manually recorded. In addition, the diameter of the steel wire rope is measured by using a circuit system consisting of a Charge Coupled Device (CCD), so that the cost is high and the measurement is difficult to realize. In a word, the existing manual inspection has low efficiency, wastes a large amount of production time, and the surface damage detection accuracy rate cannot be ensured. Other detection methods cannot intuitively reflect the surface damage condition of the steel wire rope.
Disclosure of Invention
In order to solve the disadvantages of the prior art, the present invention is directed to a wire rope detection device based on a three-dimensional image, directed to a method for detecting surface damage of a wire rope by using the detection device, and directed to a method for calculating a rope diameter by using the detection device.
In order to achieve the purpose, the invention adopts the specific scheme that:
the steel wire rope detection device is based on a three-dimensional image, is sleeved on a steel wire rope and comprises a camera, two mirrors, a white bottom plate, two light sources and a communication unit; the white bottom plate is arranged above the steel wire rope, the camera is arranged below the steel wire rope, and the camera is connected with the communication unit through a data connecting line; the two mirrors are respectively arranged on the left side and the right side of the steel wire rope, each mirror is gradually inclined from top to bottom towards the direction close to the central point of the white bottom plate, and the extending included angle of the two mirrors is 120 degrees; the two light sources are respectively arranged at the left side and the right side of the steel wire rope and are both arranged below the steel wire rope and above the camera; the white bottom plate, the mirror and the camera are all relatively parallel to the steel wire rope; the central points of the white bottom plate, the mirror, the camera and the light source are positioned on the same plane.
As a further optimization of the above solution, the vertical distance from the camera to the white base plate is 300 mm; the white bottom plate is a square with the side length of 100 mm; the length of the mirror is 200 mm, the width of the mirror is 100 mm, the long edge of the mirror is vertical to the steel wire rope, and the wide edge of the mirror is horizontal to the steel wire rope; the vertical distances from the central point of the steel wire rope to the camera lens, the white bottom plate and the two mirrors are all 150 millimeters; the light source is 50 mm from the camera; the distance from the central point of the steel wire rope to the light source is 150 mm.
As a further optimization of the scheme, the camera adopts a black and white CCD camera; the light source adopts a white LED lamp.
The invention also provides a method for detecting surface damage by using the detection device, which comprises the following steps:
step one, three-dimensional imaging of a steel wire rope: obtaining pictures of the front side, the left rear side and the right rear side of the steel wire rope through a camera, and then obtaining a microscopic image expanded on the surface of the steel wire rope after image segmentation, image transformation, image enhancement and image splicing; calculating a normal vector of the surface of the steel wire rope by the light and shade change, namely the reflected light intensity, of each point on the microscopic image, so as to calculate the height value of each point, and recovering the three-dimensional appearance of the surface to obtain a three-dimensional image;
the cosine proportional relation between the light intensity reflected by the surface point of the object and the incidence angle of the point is as follows:
E(x，y)＝I(x，y)ρcosθ
in the formula, E (x, y) is the intensity of diffuse reflection light, I (x, y) is the intensity of incident light, rho is the reflection coefficient of the surface of an object, and theta is the included angle between the incident light and the normal vector of the surface;
the diffuse reflection light intensity E (x, y) of the surface of the steel wire rope is reflected to an image, namely the brightness of the point; solving the radiant illumination of each point to obtain a surface gradient vector of the object, further solving the surface height of the steel wire rope according to the relation between the surface gradient vector and the surface height, and recovering the three-dimensional appearance of the surface of the steel wire rope;
step two, constructing a steel wire rope surface damage data set: the data set initially comprises 100 rusty pictures, 150 broken filament pictures, 100 worn pictures and 150 fatigue pictures, and the pictures in the data set are manually marked with defect categories; expanding the data set by adopting a random cutting mode;
step three, detecting the surface damage of the steel wire rope:
adopting a deep convolutional neural network, wherein the deep convolutional neural network consists of 5 convolutional layers, 3 pooling layers, 3 full-link layers, 1 loss function and a Softmax classifier; equally partitioning each frame of image of the three-dimensional image obtained in the step one to identify the surface damage category, and storing the identification result of each block; and after the detection of the whole steel wire rope is finished, combining the identification result matrixes corresponding to each frame of image, and then counting the whole identification result matrix to realize the surface damage detection.
The invention also provides a wire rope diameter calculation method by using the detection device, which comprises the following steps:
step one, shooting a shadow area of a steel wire rope on a white bottom plate by using a camera to obtain a front image of the steel wire rope; carrying out gray scale image conversion on the front image, and then carrying out Gaussian filtering on the converted image; canny edge detection is performed on the Gaussian filtered image, and an edge (I, method, threshold) function is used, wherein I is an input image, method is a specified algorithm, the algorithm uses "Canny" for edge detection, and threshold is a threshold value, and is usually set to 0.1;
removing small objects by using a morphological algorithm to obtain an image edge characteristic image, and further obtaining the imaging width of the steel wire rope on the white bottom plate; and calculating the diameter of the steel wire rope according to the distance from the camera to the steel wire rope and the distance from the camera to the white bottom plate and the imaging width of the steel wire rope.
The working principle is as follows: the detection device disclosed by the invention continuously works when the steel wire rope runs, the camera continuously shoots the steel wire rope photos, and the obtained photos comprise three parts of information, namely a front picture of the steel wire rope and left and right rear pictures of the steel wire rope displayed in two mirrors. The data collected by the detection device are transmitted to a remote server through a communication unit, and the pictures of the steel wire rope in the mirror are processed by utilizing an image processing technology to obtain the pictures of the left back side and the right back side of the steel wire rope. A three-dimensional image of a section of steel wire rope can be obtained through a three-dimensional image modeling technology, and a three-dimensional image of the whole section of steel wire rope can be obtained through a splicing technology. And then, automatically detecting the three-dimensional image of the steel wire rope by utilizing a machine learning technology, and automatically marking the damaged part and giving alarm information when surface damage is found.
Has the advantages that:
the steel wire rope detection device is simple in structure, a three-dimensional image of the steel wire rope can be constructed by using a single camera, the device is capable of automatically detecting surface damage and giving an alarm, and the device can continuously and automatically calculate the diameter of the steel wire rope in real time.
Drawings
FIG. 1 is a schematic diagram of a top view of a steel wire rope detection device according to the present invention; in the figure, 1, camera; 2. a left side mirror; 3. a right side mirror; 4. a white base plate; 5. a wire rope; 6. a right side light source; 7. a left side light source; 8. a communication unit; 9. a data link;
FIG. 2 is a schematic view of a process for detecting surface damage of a steel wire rope and calculating a rope diameter according to the present invention;
FIG. 3 is a schematic diagram of the operation of the deep convolutional neural network of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention.
In the description of the present invention, it is to be understood that the terms "center", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description, and do not indicate or imply that the device or element referred to must have a specific orientation, and that the configuration and operation of the specific orientation, and therefore, are not to be construed as limiting the present invention.
Example 1
As shown in fig. 1, the real-time online detection device for the steel wire rope is sleeved on the steel wire rope and comprises a camera, two mirrors, a white bottom plate, two light sources and a communication unit; the steel wire rope is positioned in the center, and the white bottom plate is arranged right above the steel wire rope; the two mirrors are symmetrically arranged on the left side and the right side of the steel wire rope respectively, each mirror is gradually inclined from top to bottom to a position close to the central point of the white bottom plate, and the extending included angle of the two mirrors is 120 degrees; the two light sources are respectively arranged at the left side and the right side of the steel wire rope and are both arranged below the steel wire rope and above the camera; the white bottom plate, the mirror and the camera are all relatively parallel to the steel wire rope; the central points of the white bottom plate, the mirror, the camera and the light source are all positioned on the same horizontal plane.
The camera adopts a black and white CCD camera; the vertical distance of the camera to the white base plate is 300 mm; the length and width of the white bottom plate are 100 mm square, the length of the mirror is 200 mm, the width of the mirror is 100 mm, the long edge of the mirror is vertical to the steel wire rope, and the wide edge of the mirror is horizontal to the steel wire rope; the vertical distances from the center point of the steel wire rope to the camera lens, the white bottom plate and the mirror surfaces on the two sides are 150 mm respectively; the light source adopts white LED lamp, and LED lamp distance camera 50 millimeters, and wire rope center is to LED lamp distance 150 millimeters.
Example 2
The detection device can be used for detecting the surface damage of the steel wire rope, the detection process is shown in figure 2, and the detection method specifically comprises the following steps:
1. and (3) a steel wire rope three-dimensional imaging algorithm:
and performing image segmentation, image transformation, image enhancement and image splicing on the front side, the left rear side and the right rear side of the steel wire rope obtained by the camera to obtain an image expanded on the surface of the steel wire rope. The normal vector of the surface of the steel wire rope is calculated through the light and shade change of each point on the microscopic image of the steel wire rope, namely the intensity of reflected light, so that the height value of each point is calculated, and the three-dimensional appearance of the surface is restored. The intensity of light reflected by a point on the surface of an object is proportional to the cosine of the angle of incidence of that point, i.e.
E(x，y)＝I(x，y)ρcosθ
Wherein E (x, y) is the intensity of diffuse reflection light, I (x, y) is the intensity of incident light, rho is the reflection coefficient of the surface of the object, and theta is the included angle between the incident light and the normal vector of the surface. The diffuse reflection light intensity E (x, y) on the surface of the wire rope is reflected on the brightness of the point on the image, i.e. the brightness of the point. And solving the radiant illumination of each point to obtain a surface gradient vector of the object, further solving the surface height of the steel wire rope according to the relation between the surface gradient vector and the surface height, and finally recovering the surface appearance of the steel wire rope.
The machine learning algorithm for detecting the surface damage of the steel wire rope is as follows: and constructing a steel wire rope surface damage data set, wherein the data set initially comprises 100 rusty pictures, 150 broken wire pictures, 100 worn pictures and 150 fatigue pictures, and manually marking flaw categories on the pictures. In order to reduce the labor cost of the defective image, the original data set is expanded by adopting a random clipping mode, and random clipping is carried out near the defective image. So that each randomly cropped sample contains a portion of the flaw, resulting in 5000 images per surface damage category.
As shown in fig. 3, the deep convolutional neural network consists of 5 convolutional layers, 3 pooling layers, 3 fully-connected layers, 1 loss function, and a Softmax classifier. And equally partitioning each frame of image to identify the surface damage type, storing the identification result of each small block, combining the identification result matrixes corresponding to each frame of image after the detection of the whole steel wire rope is finished, and then counting the whole identification result matrix so as to realize the purpose of surface damage detection.
And (3) rolling layers: features are extracted using convolution operations. The convolutional layer extract sign formula is as follows:
wherein kli, j, and blj represent the convolution kernel and offset, respectively;
the operation symbol represents a convolution operation; glRepresenting a connection matrix between the convolutional layer profile and the previous layer profile, if Gl i,jIs 1, then the characteristic diagram
And feature map xl jIs associated if Gl i,jIs 0, then the characteristic diagram
And feature map xl jNo association;
the function f (x) represents the nonlinear activation function, which is formulated as follows:
a pooling layer: by pooling the local regions of the feature map
The features have some spatial invariance. Using mean pooling, the formula is as follows:
representation characteristic diagram
P (x) represents the mean of the pooled area.
Full connection layer: mapping is performed for the high-level features. The calculation method is as follows:
wherein, wl jAnd bl jRepresenting a weight vector and an offset of a jth neuron of a full connection layer; the function f (x) represents the nonlinear activation function, which is the same activation function as the convolutional layer.
SoftMax classifier: and outputting according to different damages, wherein the output result is that the damage position is drawn on the steel wire rope picture, and the damage type is given.
Wherein, wL jIs the weight vector of the Softmax regression, j 1.
Loss function: model parameter training was performed using the following loss function. The formula is as follows:
in the formula, F (x)i) Is the characteristic of the ith sample; w is akAnd bkWeight and offset for the kth class; n and K are the number of training samples in the batch and the number of classes, respectively.
Example 3
The method for calculating the rope diameter of the steel wire rope comprises the steps that a camera shoots a shadow area of the steel wire rope left on a white bottom plate to obtain a front image, the front image is processed to obtain the imaging width of the steel wire rope, and then the real-time rope diameter of the steel wire rope can be calculated according to the distance between the camera, the steel wire rope and the white bottom plate. The method specifically comprises the following steps:
and carrying out grey-scale image conversion on the front image of the steel wire rope, and carrying out Gaussian filtering on the converted image. The gaussian filtered image is subjected to Canny edge detection using an edge (I, method, threshold) function, where I is the input image, method is the specified algorithm, the algorithm uses "Canny" for edge detection, and threshold, typically set to 0.1. And removing the smaller objects by using a morphological algorithm to obtain an image edge characteristic image, and obtaining the imaging width of the steel wire rope on the white bottom plate. The distance from the camera to the steel wire rope and the distance from the camera to the white bottom plate are fixed, so that the rope diameter of the steel wire rope can be calculated according to the imaging width of the steel wire rope.
The detection device is suitable for the following rope diameters: 8 mm-20 mm; detecting the rope speed range: <5 m/s; the highest detection resolution of the system: 0.1 mm; working temperature: -40 ℃ to +70 ℃; time response: 0.1 ms; rated operating voltage of the system: AC220V +/-20%; rated power of the system: < 2W.
It should be noted that the above-mentioned embodiments illustrate rather than limit the scope of the invention, which is defined by the appended claims. It will be apparent to those skilled in the art that certain insubstantial modifications and adaptations of the present invention can be made without departing from the spirit and scope of the invention.
Claims (5)
1. The utility model provides a wire rope detection device based on three-dimensional image which characterized in that: the steel wire rope detection device is sleeved on the steel wire rope and comprises a camera, two mirrors, a white bottom plate, two light sources and a communication unit; the white bottom plate is arranged above the steel wire rope, the camera is arranged below the steel wire rope, and the camera is connected with the communication unit through a data connecting line; the two mirrors are respectively arranged at the left side and the right side of the steel wire rope, each mirror is gradually inclined towards the direction close to the central point of the white bottom plate from top to bottom, and the extending included angle of the two mirrors is 120 ︒; the two light sources are respectively arranged at the left side and the right side of the steel wire rope and are both arranged below the steel wire rope and above the camera; the white bottom plate, the mirror and the camera are all relatively parallel to the steel wire rope; the central points of the white bottom plate, the mirror, the camera and the light source are positioned on the same plane.
2. The steel wire rope detection device based on the three-dimensional image as claimed in claim 1, wherein: the vertical distance from the camera to the white bottom plate is 300 mm; the white bottom plate is a square with the side length of 100 mm; the length of the mirror is 200 mm, the width of the mirror is 100 mm, the long edge of the mirror is vertical to the steel wire rope, and the wide edge of the mirror is horizontal to the steel wire rope; the vertical distances from the central point of the steel wire rope to the camera lens, the white bottom plate and the two mirrors are all 150 millimeters; the light source is 50 mm from the camera; the distance from the central point of the steel wire rope to the light source is 150 mm.
3. The steel wire rope detection device based on the three-dimensional image as claimed in claim 1, wherein: the camera adopts a black and white CCD camera; the light source adopts a white LED lamp.
4. The method for detecting surface damage by using the steel wire rope detection device according to claim 3, characterized in that: the method comprises the following steps:
step one, three-dimensional imaging of a steel wire rope: obtaining pictures of the front side, the left rear side and the right rear side of the steel wire rope through a camera, and then obtaining a microscopic image expanded on the surface of the steel wire rope after image segmentation, image transformation, image enhancement and image splicing; calculating a normal vector of the surface of the steel wire rope by the light and shade change, namely the reflected light intensity, of each point on the microscopic image, so as to calculate the height value of each point, and recovering the three-dimensional appearance of the surface to obtain a three-dimensional image;
the cosine proportional relation between the light intensity reflected by the surface point of the object and the incidence angle of the point is as follows:
in the formula, E (x, y) is the intensity of diffuse reflection light, I (x, y) is the intensity of incident light, rho is the reflection coefficient of the surface of an object, and theta is the included angle between the incident light and the normal vector of the surface;
the diffuse reflection light intensity E (x, y) of the surface of the steel wire rope is reflected to an image, namely the brightness of the point; solving the radiant illumination of each point to obtain a surface gradient vector of the object, further solving the surface height of the steel wire rope according to the relation between the surface gradient vector and the surface height, and recovering the three-dimensional appearance of the surface of the steel wire rope;
step two, constructing a steel wire rope surface damage data set: the data set initially comprises 100 rusty pictures, 150 broken filament pictures, 100 worn pictures and 150 fatigue pictures, and the pictures in the data set are manually marked with defect categories; expanding the data set by adopting a random cutting mode;
step three, detecting the surface damage of the steel wire rope:
adopting a deep convolutional neural network, wherein the deep convolutional neural network consists of 5 convolutional layers, 3 pooling layers, 3 full-link layers, 1 loss function and a Softmax classifier; equally partitioning each frame of image of the three-dimensional image obtained in the step one to identify the surface damage category, and storing the identification result of each block; and after the detection of the whole steel wire rope is finished, combining the identification result matrixes corresponding to each frame of image, and then counting the whole identification result matrix to realize the surface damage detection.
5. A method of calculating a wire rope warp by using the wire rope detection device according to claim 3, characterized in that: the method comprises the following steps:
step one, shooting a shadow area of a steel wire rope on a white bottom plate by using a camera to obtain a front image of the steel wire rope; carrying out gray scale image conversion on the front image, and then carrying out Gaussian filtering on the converted image; canny edge detection is performed on the Gaussian filtered image, and an edge (I, method, threshold) function is used, wherein I is an input image, method is a specified algorithm, the algorithm uses "Canny" for edge detection, and threshold is a threshold value, and is usually set to 0.1;
removing small objects by using a morphological algorithm to obtain an image edge characteristic image, and further obtaining the imaging width of the steel wire rope on the white bottom plate; and calculating the rope diameter of the steel wire rope according to the distance from the camera to the steel wire rope and the distance from the camera to the white bottom plate and the imaging width of the steel wire rope.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010609547.7A CN111721216A (en) | 2020-06-29 | 2020-06-29 | Steel wire rope detection device based on three-dimensional image, surface damage detection method and rope diameter calculation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010609547.7A CN111721216A (en) | 2020-06-29 | 2020-06-29 | Steel wire rope detection device based on three-dimensional image, surface damage detection method and rope diameter calculation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111721216A true CN111721216A (en) | 2020-09-29 |
Family
ID=72571882
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010609547.7A Pending CN111721216A (en) | 2020-06-29 | 2020-06-29 | Steel wire rope detection device based on three-dimensional image, surface damage detection method and rope diameter calculation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111721216A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112945972A (en) * | 2021-01-29 | 2021-06-11 | 徐州科瑞矿业科技有限公司 | Steel wire rope state detection device and method based on machine vision |
| CN116829901A (en) * | 2021-02-17 | 2023-09-29 | 三菱电机楼宇解决方案株式会社 | Measuring device and elevator device |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080013820A1 (en) * | 2006-07-11 | 2008-01-17 | Microview Technology Ptd Ltd | Peripheral inspection system and method |
| CN101593345A (en) * | 2009-07-01 | 2009-12-02 | 电子科技大学 | Three-dimensional medical image display method based on the GPU acceleration |
| JP2011163954A (en) * | 2010-02-10 | 2011-08-25 | Fujikura Ltd | Device for detection of wire surface defect |
| CN102253043A (en) * | 2011-06-22 | 2011-11-23 | 上海工程技术大学 | Monocular CCD (Charge Coupled Device) digitalized analysis method of multi-angle yarn appearance |
| CN103163132A (en) * | 2011-12-08 | 2013-06-19 | 常州中港纺织智能科技有限公司 | System and method for real-time appearance digital analysis for yarn |
| CN103363924A (en) * | 2013-07-15 | 2013-10-23 | 中国科学院空间科学与应用研究中心 | Compressing three-dimension calculation ghost imaging system and method |
| CN103645190A (en) * | 2013-11-27 | 2014-03-19 | 上海工程技术大学 | Adjustable dual-twisting mirror box for measuring apparent parameter of yarn and device thereof |
| CN105243175A (en) * | 2015-08-28 | 2016-01-13 | 山东济宁如意毛纺织股份有限公司 | Yarn float light intensity distribution based fabric appearance simulation method |
| CN105466954A (en) * | 2016-01-18 | 2016-04-06 | 湖南远见视觉科技有限责任公司 | Column detection equipment |
| CN106803061A (en) * | 2016-12-14 | 2017-06-06 | 广州大学 | A kind of simple and fast method for detecting lane lines based on dynamic area-of-interest |
| CN109632103A (en) * | 2018-11-22 | 2019-04-16 | 西安理工大学 | High vacant building Temperature Distribution and surface crack remote supervision system and monitoring method |
| CN109738460A (en) * | 2019-01-28 | 2019-05-10 | 西京学院 | A kind of evaluation detection system for civil engineering structure visual defects |
| CN209148564U (en) * | 2018-10-25 | 2019-07-23 | 广东华中科技大学工业技术研究院 | A kind of transparent component defect detecting device |
| CN111080597A (en) * | 2019-12-12 | 2020-04-28 | 西南交通大学 | Track fastener defect identification algorithm based on deep learning |
-
2020
- 2020-06-29 CN CN202010609547.7A patent/CN111721216A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080013820A1 (en) * | 2006-07-11 | 2008-01-17 | Microview Technology Ptd Ltd | Peripheral inspection system and method |
| CN101593345A (en) * | 2009-07-01 | 2009-12-02 | 电子科技大学 | Three-dimensional medical image display method based on the GPU acceleration |
| JP2011163954A (en) * | 2010-02-10 | 2011-08-25 | Fujikura Ltd | Device for detection of wire surface defect |
| CN102253043A (en) * | 2011-06-22 | 2011-11-23 | 上海工程技术大学 | Monocular CCD (Charge Coupled Device) digitalized analysis method of multi-angle yarn appearance |
| CN103163132A (en) * | 2011-12-08 | 2013-06-19 | 常州中港纺织智能科技有限公司 | System and method for real-time appearance digital analysis for yarn |
| CN103363924A (en) * | 2013-07-15 | 2013-10-23 | 中国科学院空间科学与应用研究中心 | Compressing three-dimension calculation ghost imaging system and method |
| CN103645190A (en) * | 2013-11-27 | 2014-03-19 | 上海工程技术大学 | Adjustable dual-twisting mirror box for measuring apparent parameter of yarn and device thereof |
| CN105243175A (en) * | 2015-08-28 | 2016-01-13 | 山东济宁如意毛纺织股份有限公司 | Yarn float light intensity distribution based fabric appearance simulation method |
| CN105466954A (en) * | 2016-01-18 | 2016-04-06 | 湖南远见视觉科技有限责任公司 | Column detection equipment |
| CN106803061A (en) * | 2016-12-14 | 2017-06-06 | 广州大学 | A kind of simple and fast method for detecting lane lines based on dynamic area-of-interest |
| CN209148564U (en) * | 2018-10-25 | 2019-07-23 | 广东华中科技大学工业技术研究院 | A kind of transparent component defect detecting device |
| CN109632103A (en) * | 2018-11-22 | 2019-04-16 | 西安理工大学 | High vacant building Temperature Distribution and surface crack remote supervision system and monitoring method |
| CN109738460A (en) * | 2019-01-28 | 2019-05-10 | 西京学院 | A kind of evaluation detection system for civil engineering structure visual defects |
| CN111080597A (en) * | 2019-12-12 | 2020-04-28 | 西南交通大学 | Track fastener defect identification algorithm based on deep learning |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112945972A (en) * | 2021-01-29 | 2021-06-11 | 徐州科瑞矿业科技有限公司 | Steel wire rope state detection device and method based on machine vision |
| CN112945972B (en) * | 2021-01-29 | 2022-04-15 | 徐州科瑞矿业科技有限公司 | Steel wire rope state detection device and method based on machine vision |
| CN116829901A (en) * | 2021-02-17 | 2023-09-29 | 三菱电机楼宇解决方案株式会社 | Measuring device and elevator device |
| CN116829901B (en) * | 2021-02-17 | 2024-02-02 | 三菱电机楼宇解决方案株式会社 | Measuring device and elevator device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111696075A (en) | Intelligent fan blade defect detection method based on double-spectrum image | |
| CN101625723A (en) | Rapid image-recognizing method of power line profile | |
| CN111695514B (en) | Vehicle detection method in foggy days based on deep learning | |
| CN107782733A (en) | Image recognition the cannot-harm-detection device and method of cracks of metal surface | |
| WO2015055060A1 (en) | Online detecting method for continuous casting slab surface quality | |
| CN111721216A (en) | Steel wire rope detection device based on three-dimensional image, surface damage detection method and rope diameter calculation method | |
| CN108680833B (en) | Composite insulator defect detection system based on unmanned aerial vehicle | |
| CN113516076A (en) | Improved lightweight YOLO v4 safety protection detection method based on attention mechanism | |
| CN110378865A (en) | A kind of greasy weather visibility intelligence hierarchical identification method and system under complex background | |
| CN109506628A (en) | Object distance measuring method under a kind of truck environment based on deep learning | |
| CN113869162A (en) | Violation identification method and system based on artificial intelligence | |
| CN112560816A (en) | Equipment indicator lamp identification method and system based on YOLOv4 | |
| CN114812403B (en) | Large-span steel structure hoisting deformation monitoring method based on unmanned plane and machine vision | |
| Wu et al. | Design of online surface inspection system of hot rolled strips | |
| CN114441452B (en) | Optical fiber pigtail detection method | |
| Lin et al. | Development of a CNN-based hierarchical inspection system for detecting defects on electroluminescence images of single-crystal silicon photovoltaic modules | |
| CN117078661B (en) | Intelligent detection method for production quality of structural member of overhead working truck | |
| CN113962929A (en) | Photovoltaic cell assembly defect detection method and system and photovoltaic cell assembly production line | |
| CN109146863A (en) | A kind of pavement marker line defect detection device | |
| CN116086547B (en) | Contact net icing detection method based on infrared imaging and meteorological monitoring | |
| DE202023105341U1 (en) | Deep learning-based system for detecting corrosion in metallic objects | |
| CN112488213A (en) | Fire picture classification method based on multi-scale feature learning network | |
| CN117197412A (en) | AR-based intelligent highway disease inspection system and method | |
| CN111931577A (en) | Intelligent inspection method for specific foreign matters of power grid line | |
| CN107121063A (en) | The method for detecting workpiece |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200929 |
|
| RJ01 | Rejection of invention patent application after publication |