CN111127382A - Contact net suspension assembly U-shaped ring spare cap defect detection method - Google Patents
Contact net suspension assembly U-shaped ring spare cap defect detection method Download PDFInfo
- Publication number
- CN111127382A CN111127382A CN201811194489.5A CN201811194489A CN111127382A CN 111127382 A CN111127382 A CN 111127382A CN 201811194489 A CN201811194489 A CN 201811194489A CN 111127382 A CN111127382 A CN 111127382A
- Authority
- CN
- China
- Prior art keywords
- cap
- shaped ring
- spare
- image
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- G06T7/12—Edge-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
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of railway component detection, and discloses a method for detecting defects of a U-shaped spare cap of a suspension component of a contact network. The method specifically comprises the following steps: step 1, a camera collects images of a suspension area of a contact network; step 2, detecting the position of the U-shaped ring area by adopting a classifier; step 3, extracting the position of the cap-prepared target from the U-shaped ring area through image processing according to the shape characteristics of the cap-prepared target; step 4, judging the defects of the spare cap according to the position relation or the missing state of each component of the spare cap; and 5, outputting a detection result of the defect state of the spare cap as the state of the U-shaped ring. According to the technical scheme, the U-shaped ring area is quickly detected by adopting coarse positioning, then the strategy of accurate positioning is adopted, the cap preparation target is accurately extracted through image analysis, and the image extraction effectiveness is high; the method for detecting the defects of the spare cap by adopting the component state analysis method is rapid and effective.
Description
Technical Field
The invention relates to the technical field of railway component detection, in particular to a method for detecting defects of a U-shaped ring spare cap of a suspension component of a contact network.
Background
The overhead contact system as the main power supply network mode of electrified railway is a special power transmission line for supplying power to electric locomotive, and consists of mainly contact suspension, support unit, positioning unit, support and foundation. The contact suspension comprises components such as a contact wire, a dropper, a carrier cable, an insulator, a connecting part and the like, is erected on a support column through a supporting device and is used for transmitting electric energy obtained from a traction substation to an electric locomotive.
The U-shaped ring is used as an important component of the contact suspension, and the loosening and the falling of the U-shaped ring can bring influence to the safety of the whole contact net.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: aiming at the existing problems, the defect detection method for the catenary suspension assembly _ U-shaped ring spare cap is provided.
The technical scheme adopted by the invention is as follows: a contact net suspension assembly U-shaped ring spare cap defect detection method specifically comprises the following steps:
step 1, a camera collects images of a suspension area of a contact network;
step 2, detecting the position of the U-shaped ring area by adopting a classifier;
step 3, extracting the position of the cap-prepared target from the U-shaped ring area through image processing according to the shape characteristics of the cap-prepared target;
step 4, judging the defects of the spare cap according to the position relation or the missing state of each component of the spare cap;
and 5, outputting a detection result of the defect state of the spare cap as the state of the U-shaped ring.
Further, in step 2, the histogram of the directional gradients is used as a feature descriptor of the U-ring component, the support vector machine is used as a discrimination method, and the U-ring region position is classified and detected from the input image according to the U-ring feature extracted by the feature descriptor.
Further, the specific process of step 4 is as follows:
step 41, inputting a standby hat target position image; step 42, enhancing the edge profile of the U-shaped ring and the spare cap; 43, separating the objects with the aid of image thresholding; step 44, correcting the posture of the target with the cap; and step 45, separating the nut component and the bolt component in the target area of the spare cap, and realizing the defect judgment of the spare cap and outputting the defect state by analyzing the number of the nuts and the position posture of the nuts relative to the bolts.
Further, the specific process of step 43 is as follows: firstly, calculating an edge gradient image, and distinguishing a background from a foreground; then, processing by adopting a self-adaptive neighborhood thresholding method; and finally, communicating the foreground target through morphological processing, and separating the standby target.
Further, the specific process of step 44 is as follows: firstly, identifying and finding a cap preparation area by adopting a moment characteristic analysis method, and finishing image posture correction by taking the cap preparation area as a reference through a Blob analysis method.
Further, the specific process of step 45 is as follows: firstly, extracting an edge contour communication area from a standby hat area image; and then separating the nut and bolt images according to the geometric relationship of the outlines of the nut and the bolt, and judging different positions of the nut and the bolt.
Further, in step 45, when processing the nut and bolt images, the images of the prepared caps and bolts are perfected according to the bilateral symmetry distribution characteristics of the nuts and bolts.
Compared with the prior art, the beneficial effects of adopting the technical scheme are as follows:
(1) according to the technical scheme, the U-shaped ring area is quickly detected by adopting coarse positioning, then the strategy of accurate positioning is adopted, the cap preparation target is accurately extracted through image analysis, and the image extraction effectiveness is high.
(2) The method for detecting the defects of the spare cap by adopting the component state analysis method is rapid and effective.
Drawings
Fig. 1 is a schematic flow chart of a method for detecting defects of a U-shaped ring spare cap of a contact net suspension assembly.
FIG. 2 is a schematic flow chart of the present invention for analysis of a capped image.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
As shown in fig. 1, a method for detecting defects of a U-shaped ring spare cap of a suspension assembly of an overhead line system specifically comprises the following steps: step 1, a camera collects images of a suspension area of a contact network; step 2, detecting the position of the U-shaped ring area by adopting a classifier; step 3, extracting the position of the cap-prepared target from the U-shaped ring area through image processing according to the shape characteristics of the cap-prepared target; step 4, judging the defects of the spare cap according to the position relation or the missing state of each component of the spare cap; and 5, outputting a detection result of the defect state of the spare cap as the state of the U-shaped ring. In the contact net, the U-shaped ring spare cap is used for ensuring the correct installation of the U-shaped ring, when the spare cap is loosened or falls off, the contact suspension can generate potential safety hazards, the technical scheme adopts a non-contact detection method, and the state monitoring of the U-shaped ring spare cap assembly hung along the railway in each contact manner is realized.
The classifier detects a U-shaped ring:
preferably, in step 2, a Histogram of Oriented Gradients (HOG) is used as a feature descriptor of the U-shaped ring component, a Support Vector Machine (SVM) is used as a discrimination method, and the U-shaped ring region position is classified and detected from the input image according to the U-shaped ring feature extracted from the feature descriptor.
(1) Histogram of Oriented Gradient (HOG)
The HOG features, as a feature descriptor for object detection in computer vision and image processing, combined with an SVM classifier have been widely used in image recognition with great success.
The HOG is used as a feature descriptor, and the main reason is that the whole overhead line system is hung, particularly a U-shaped ring is in a good rigid posture and is not easy to change in form due to the change of the angle of an image acquired by a camera; for rigid target objects, the appearance and shape of the target can be well described by using the gradient or the directional density distribution of the edge, which is essentially the statistical information of the gradient, so that the characteristic is very suitable for description.
(2) Support Vector Machine (SVM)
The support vector machine, as a two-class classification model problem, defines the basic model as a linear classifier with the largest interval of the feature space, and the final purpose of learning the sample data is to maximize the interval.
Preferably, as shown in fig. 2, the specific process of step 4 is: step 41, inputting a standby hat target position image; step 42, the edge profile of the U-shaped ring and the spare cap is enhanced, so that the effect of better separating the U-shaped ring from the background is achieved; 43, separating the objects with the aid of image thresholding; step 44, correcting the posture of the target with the cap; and step 45, separating the nut component and the bolt component in the target area of the spare cap, and realizing the defect judgment of the spare cap and outputting the defect state by analyzing the number of the nuts and the position posture of the nuts relative to the bolts.
Preferably, the image thresholding object classification process: firstly, calculating an edge gradient image, and distinguishing a background from a foreground; then, processing by adopting a self-adaptive neighborhood thresholding method; and finally, communicating the foreground target through morphological processing, and separating the standby target.
Preferably, the cap-ready target posture correction: when the camera collects images of the contact suspension area, the images are limited by environmental reasons, and the possible imaging postures of the U-shaped ring area are different, so that the defect state analysis of the cap is not facilitated. In the embodiment, a moment feature analysis and Blob analysis method is adopted to uniformly correct the U-shaped ring spare cap area image to the same posture (the bolt faces upwards), specifically, the moment feature analysis is adopted for identifying and finding the spare cap area, and the reason for adopting the moment feature analysis method is that in a relatively closed image environment, the moment feature analysis method is simple and quick in identification and can meet the identification requirement; the Blob analysis method is responsible for completing the image pose correction with the capped area as a reference.
The moment is an operator for describing image characteristics, and the moment technology is widely applied to the fields of image recognition, matching and the like at present. The core of image recognition is the feature extraction of an image, that is, a simple set of data (image descriptor) is used to describe the whole image or an object, and the simpler the set of data, the more representative the data, the better the data. The invariant moment is used as a highly condensed image feature, and theoretical derivation and experimental data prove that the feature has the characteristics of translation, gray scale, rotation invariance and the like.
For an image with a gray scale distribution f (x, y), the (p + q) order moment is defined as:
the (p + q) -order central moment is defined as:
the normalized center distance of the (p + q) order is defined as:
wherein p and q are non-zero natural numbers,
the Hu moment constructs seven invariant moments using the second and third central moments, which are characterized by translational, scaling and rotational invariance, defined as:
I1＝y20+y02
I3＝(y20-3y12)2+(3y21-y03)2
I4＝(y30+y12)2+(y21+y03)2
I5＝(y30+3y12)(y30+y12)[(y30+y12)2-3(y21+y03)2]+(3y21-y03)(y21+y03)[3(y30+y12)2-(y21+y03)2]
I6＝(y20-y02)[(y30+y12)2-(y21+y03)2]+4y11(y30+y12)(y21+y03)
I7＝(3y21-y03)(y30+y12)[(y30+y12)2-3(y21+y03)2]+(3y12-y30)(y21+y03)[3(y30+y12)2-(y21+y03)2]
preferably, the cap-ready target assembly separation and defect analysis: the spare cap area of the U-shaped ring is mainly composed of spare cap nuts and bolts, and the spare cap defects are mainly divided into two cases: the nut loosens and falls off. Therefore, in the embodiment, the nut component and the bolt component in the cap preparation area are separated, and finally, the cap preparation defect judgment is realized by analyzing the number of the nuts and the position and the posture of the nuts relative to the bolts.
The separation of the spare cap components is mainly realized by an image analysis method. Firstly, extracting an edge contour communication area from a standby cap area image, and then separating and judging different positions of a nut and a bolt assembly according to the geometrical relationship of the nut and the bolt, such as the linear fitting degree of the contours of the left side and the right side of the bolt, the geometrical relationship between the height of the contour of the nut and the diameter of the contour of the bolt, and the like. In the processing process, the influence brought by imaging environment factors is considered, the thresholding separation effect of the images of the spare cap area is possibly poor, and complete images of the spare cap assembly are distinguished and compensated according to the bilateral symmetry distribution characteristic of the spare cap assembly.
The invention is not limited to the foregoing embodiments. The invention extends to any novel feature or any novel combination of features disclosed in this specification and any novel method or process steps or any novel combination of features disclosed. Those skilled in the art to which the invention pertains will appreciate that insubstantial changes or modifications can be made without departing from the spirit of the invention as defined by the appended claims.
Claims (7)
1. The method for detecting the defects of the U-shaped ring spare cap of the overhead line system suspension assembly is characterized by comprising the following steps of:
step 1, a camera collects images of a suspension area of a contact network;
step 2, detecting the position of the U-shaped ring area by adopting a classifier;
step 3, extracting the position of the cap-prepared target from the U-shaped ring area through image processing according to the shape characteristics of the cap-prepared target;
step 4, judging the defects of the spare cap according to the position relation or the missing state of each component of the spare cap;
and 5, outputting a detection result of the defect state of the spare cap as the state of the U-shaped ring.
2. The method for detecting defects of a U-shaped ring preparation cap of a catenary suspension assembly of claim 1, wherein in the step 2, a direction gradient histogram is used as a feature descriptor of the U-shaped ring assembly, a support vector machine is used as a discrimination method, and the positions of the U-shaped ring areas are classified and detected from the input image according to the U-shaped ring features extracted from the feature descriptor.
3. The method for detecting the defects of the U-shaped ring spare cap of the overhead line system suspension assembly of claim 2, wherein the specific process of the step 4 is as follows:
step 41, inputting a standby hat target position image; step 42, enhancing the edge profile of the U-shaped ring and the spare cap; 43, separating the objects with the aid of image thresholding; step 44, correcting the posture of the target with the cap; and step 45, separating the nut component and the bolt component in the target area of the spare cap, and realizing the defect judgment of the spare cap and outputting the defect state by analyzing the number of the nuts and the position posture of the nuts relative to the bolts.
4. The method for detecting defects of U-shaped ring preparation caps of contact net suspension assemblies according to claim 3, wherein the specific process of the step 43 is as follows: firstly, calculating an edge gradient image, and distinguishing a background from a foreground; then, processing by adopting a self-adaptive neighborhood thresholding method; and finally, communicating the foreground target through morphological processing, and separating the standby target.
5. The method for detecting defects of U-shaped ring preparation caps of contact net suspension assemblies according to claim 4, wherein the specific process of the step 44 is as follows: firstly, identifying and finding a cap preparation area by adopting a moment characteristic analysis method, and finishing image posture correction by taking the cap preparation area as a reference through a Blob analysis method.
6. The method for detecting defects of U-shaped ring preparation caps of contact net suspension assemblies according to claim 5, wherein the specific process of the step 45 is as follows: firstly, extracting an edge contour communication area from a standby hat area image; and then separating the nut and bolt images according to the geometric relationship of the outlines of the nut and the bolt, and judging different positions of the nut and the bolt.
7. The method for detecting defects of U-shaped spare caps of overhead line system suspension assemblies as claimed in claim 6, wherein in the step 45, when the nut and bolt images are processed, the spare caps and the bolt images are perfected according to the bilateral symmetry distribution characteristics of the nuts and the bolts.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811194489.5A CN111127382B (en) | 2018-10-15 | 2018-10-15 | Contact net suspension assembly U-shaped ring spare cap defect detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811194489.5A CN111127382B (en) | 2018-10-15 | 2018-10-15 | Contact net suspension assembly U-shaped ring spare cap defect detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111127382A true CN111127382A (en) | 2020-05-08 |
| CN111127382B CN111127382B (en) | 2022-07-22 |
Family
ID=70483998
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811194489.5A Active CN111127382B (en) | 2018-10-15 | 2018-10-15 | Contact net suspension assembly U-shaped ring spare cap defect detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111127382B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116051565A (en) * | 2023-04-03 | 2023-05-02 | 广州水木星尘信息科技有限公司 | Contact net defect target detection method and device based on structured light 3D point cloud |
| CN117197700A (en) * | 2023-11-07 | 2023-12-08 | 成都中轨轨道设备有限公司 | Intelligent unmanned inspection contact net defect identification system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1102423A2 (en) * | 1999-11-18 | 2001-05-23 | Alcatel | Method for the safe automatic restart of optical transmitters in fiber optic telecommunication systems |
| CN103310438A (en) * | 2013-04-16 | 2013-09-18 | 西南交通大学 | Overhead contact system rod insulator fault detection method based on Harris corners and image difference |
| CN104392432A (en) * | 2014-11-03 | 2015-03-04 | 深圳市华星光电技术有限公司 | Histogram of oriented gradient-based display panel defect detection method |
| CN106372667A (en) * | 2016-08-31 | 2017-02-01 | 西南交通大学 | Method for detecting adverse state of inclined sleeve part screws of high-speed train overhead line system |
| CN207576968U (en) * | 2017-11-13 | 2018-07-06 | 哈尔滨理工大学 | A kind of mechanism for steel ball surface defect detection |
| CN108508023A (en) * | 2018-03-30 | 2018-09-07 | 深圳市益鑫智能科技有限公司 | The defect detecting system of end puller bolt is contacted in a kind of railway contact line |
| CN108598992A (en) * | 2018-04-21 | 2018-09-28 | 王社兵 | A kind of cable detection attachment device |
-
2018
- 2018-10-15 CN CN201811194489.5A patent/CN111127382B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1102423A2 (en) * | 1999-11-18 | 2001-05-23 | Alcatel | Method for the safe automatic restart of optical transmitters in fiber optic telecommunication systems |
| CN103310438A (en) * | 2013-04-16 | 2013-09-18 | 西南交通大学 | Overhead contact system rod insulator fault detection method based on Harris corners and image difference |
| CN104392432A (en) * | 2014-11-03 | 2015-03-04 | 深圳市华星光电技术有限公司 | Histogram of oriented gradient-based display panel defect detection method |
| CN106372667A (en) * | 2016-08-31 | 2017-02-01 | 西南交通大学 | Method for detecting adverse state of inclined sleeve part screws of high-speed train overhead line system |
| CN207576968U (en) * | 2017-11-13 | 2018-07-06 | 哈尔滨理工大学 | A kind of mechanism for steel ball surface defect detection |
| CN108508023A (en) * | 2018-03-30 | 2018-09-07 | 深圳市益鑫智能科技有限公司 | The defect detecting system of end puller bolt is contacted in a kind of railway contact line |
| CN108598992A (en) * | 2018-04-21 | 2018-09-28 | 王社兵 | A kind of cable detection attachment device |
Non-Patent Citations (2)
| Title |
|---|
| DING SHUMIN 等: "AdaBoost learning for fabric defect detection based on HOG and SVM", 《2011 INTERNATIONAL CONFERENCE ON MULTIMEDIA TECHNOLOGY》 * |
| 徐丹 等: "基于LBP-HOG 特征的接触网旋转双耳区域识别", 《铁道科学与工程学报》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116051565A (en) * | 2023-04-03 | 2023-05-02 | 广州水木星尘信息科技有限公司 | Contact net defect target detection method and device based on structured light 3D point cloud |
| CN117197700A (en) * | 2023-11-07 | 2023-12-08 | 成都中轨轨道设备有限公司 | Intelligent unmanned inspection contact net defect identification system |
| CN117197700B (en) * | 2023-11-07 | 2024-01-26 | 成都中轨轨道设备有限公司 | Intelligent unmanned inspection contact net defect identification system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111127382B (en) | 2022-07-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109101924B (en) | Machine learning-based road traffic sign identification method | |
| CN107257161B (en) | Transformer substation disconnecting link remote control auxiliary checking method and system based on state recognition algorithm | |
| CN105069466B (en) | Pedestrian's dress ornament color identification method based on Digital Image Processing | |
| CN105719305B (en) | Component falls off defect identification method and system in contact net | |
| Wu et al. | Detection of bird nests in overhead catenary system images for high-speed rail | |
| CN111127382B (en) | Contact net suspension assembly U-shaped ring spare cap defect detection method | |
| CN111260629A (en) | Pantograph structure abnormity detection algorithm based on image processing | |
| CN105335743A (en) | Vehicle license plate recognition method | |
| CN104573713B (en) | A kind of transformer Infrared image recognition based on image texture characteristic | |
| CN107729812B (en) | Method suitable for recognizing vehicle color in monitoring scene | |
| CN104318582A (en) | Detection method for bad state of rotating double-lug component pin of high-speed rail contact network on basis of image invariance target positioning | |
| CN105354589A (en) | Method and system for intelligently identifying insulator crack in catenary image | |
| CN102980896A (en) | Method for detecting breakage of lugs of high-speed rail contact net suspension device | |
| CN107256633B (en) | Vehicle type classification method based on monocular camera three-dimensional estimation | |
| CN104281838A (en) | Lug piece breakage detection method for high-speed rail overhead line system supporting device based on HOG features and two-dimensional Gabor wavelet transformation | |
| CN103093201A (en) | Car logo locating and recognizing method and system | |
| CN107705256B (en) | Forward vehicle-mounted video image enhancement method based on contact network semantics | |
| CN112232222B (en) | Bullet train axle box end cover bolt loss fault detection method based on image processing | |
| CN105718964A (en) | Transmission line vibration damper visual detection method | |
| CN103150575A (en) | Real-time three-dimensional unmarked human body gesture recognition method and system | |
| CN110633749B (en) | Three-dimensional point cloud identification method based on improved viewpoint feature histogram | |
| CN113673614B (en) | Metro tunnel foreign matter intrusion detection device and method based on machine vision | |
| Juntanasub et al. | Car license plate recognition through Hausdorff distance technique | |
| Dong et al. | An end-to-end abnormal fastener detection method based on data synthesis | |
| CN107392127B (en) | Transmission line of electricity extracting method based on Chebyshev polynomials description |
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 |