CN114926415A - Steel rail surface detection method based on PCNN and deep learning - Google Patents
Steel rail surface detection method based on PCNN and deep learning Download PDFInfo
- Publication number
- CN114926415A CN114926415A CN202210486709.1A CN202210486709A CN114926415A CN 114926415 A CN114926415 A CN 114926415A CN 202210486709 A CN202210486709 A CN 202210486709A CN 114926415 A CN114926415 A CN 114926415A
- Authority
- CN
- China
- Prior art keywords
- image
- steel rail
- rail surface
- damage
- rail
- 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
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 89
- 239000010959 steel Substances 0.000 title claims abstract description 89
- 238000001514 detection method Methods 0.000 title claims abstract description 71
- 238000013135 deep learning Methods 0.000 title claims abstract description 11
- 230000006378 damage Effects 0.000 claims abstract description 68
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims description 31
- 210000002569 neuron Anatomy 0.000 claims description 20
- 208000027418 Wounds and injury Diseases 0.000 claims description 14
- 208000014674 injury Diseases 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000007621 cluster analysis Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000005299 abrasion Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 231100000241 scar Toxicity 0.000 claims description 3
- 208000032544 Cicatrix Diseases 0.000 claims description 2
- 230000037387 scars Effects 0.000 claims description 2
- 239000002356 single layer Substances 0.000 claims description 2
- 238000010586 diagram Methods 0.000 abstract description 8
- 238000005457 optimization Methods 0.000 abstract description 4
- 230000000007 visual effect Effects 0.000 abstract description 2
- 230000007547 defect Effects 0.000 description 3
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
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
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8883—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges involving the calculation of gauges, generating models
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/30136—Metal
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a steel rail surface detection method based on PCNN and deep learning, which comprises the steps of preprocessing a steel rail surface image; substituting the rail surface image and the rail body image into a PCNN-based steel rail surface damage detection model to obtain a damage area image; and detecting the image of the damaged area on the surface of the steel rail by using the steel rail damage type detection model to obtain a damage detection result. The rail surface detection method provided by the invention adopts a rail surface damage detection model based on PCNN to detect, a PCNN framework is compared with an original thermodynamic diagram regression framework, a positioning sub-network and a diagram structure posture optimization module are added, the original thermodynamic diagram regression framework obtains a rough positioning result, a group of suggested key points, called guidance points, are sampled, different visual features are extracted for each guidance point through the positioning sub-network, and the relationship between the guidance points is explored through the diagram structure posture optimization module to obtain a more accurate positioning result.
Description
Technical Field
The invention relates to the field of machine vision image processing, in particular to a steel rail surface detection method based on PCNN and deep learning.
Background
At present, because the intellectualization of technical equipment is low and the replacement cost is high, the domestic railway maintenance still takes manual inspection as a main part, the efficiency is low, the labor cost is high, and the false alarm rate and the missing rate of damage detection by manpower are high. Secondly, the surface of the steel rail is affected by poor working conditions such as illumination and mechanical vibration of the train, so that the image detected by the defect on the surface of the steel rail based on machine vision still can be mixed with noise, and the recognition work is interfered. Moreover, the non-contact detection device, such as a high-definition camera, may have a deviation in the position where it is fixed on the flaw detection apparatus, or the vibration of the flaw detection apparatus while moving may also cause a deviation in the angle of the image obtained by the camera, which is finally not favorable for the accuracy of detecting the surface defects of the steel rail.
In conclusion, a steel rail surface detection method is urgently needed to overcome the problems of low efficiency and low accuracy in the prior art.
Disclosure of Invention
In view of the above, the present invention has been made to provide a rail surface detection method based on PCNN and deep learning, which overcomes or at least partially solves the above problems.
According to one aspect of the invention, the invention provides a rail surface detection method based on PCNN and deep learning, which comprises the following steps:
preprocessing the surface image of the steel rail to obtain a rail surface image and a rail body image;
substituting the rail surface image and the rail body image into a PCNN-based steel rail surface damage detection model to obtain a damaged area image of the steel rail surface;
and detecting the image of the damaged area on the surface of the steel rail by using the steel rail damage type detection model to obtain a damage detection result of the detected steel rail.
Optionally, the method for preprocessing the surface image of the steel rail includes:
identifying a background part and a steel rail part in the steel rail surface image by using a background detection model for the steel rail surface image,
extracting a steel rail part in the steel rail surface image, carrying out binarization processing on the steel rail part image, obtaining pixel points of the steel rail surface part after extracting white pixels, and dividing the steel rail surface image into a rail surface image and a rail body image according to the pixel point coordinates of the steel rail surface part.
Optionally, the method for establishing the background detection model includes: firstly, acquiring different steel rail surface images, marking a background part and a steel rail part in the steel rail surface images, and then training by using standard steel rail surface images to obtain the steel rail surface image.
Optionally, the PCNN-based training method for the rail surface damage detection model includes:
marking the damage conditions of the rail surface image and the rail body image, then carrying out cluster analysis on the damage parts in the rail surface image and the rail body image, dividing the damage parts into a plurality of parts according to the cluster analysis result, and respectively marking the position information of the damage of each part;
respectively counting the number of the pixels of the injuries of each part, wherein the number of the neurons in the PCNN is equal to the number of the pixels of the injuries of each part; and the damage detection process forms each neuron, a plurality of neurons are arranged into a single-layer network with transverse connection, each neuron receives the link input of all adjacent neurons in the radius, each neuron only receives one feed input to form a neuron image, and the neuron image is trained to obtain a PCNN-based steel rail surface damage detection model.
Optionally, the rail surface detection method further includes detecting a noise-formed region on the damaged region image, performing a deletion operation when an area of the noise-formed region is smaller than a set threshold, and marking when the area of the noise-formed region is greater than or equal to the set threshold.
Optionally, the method for detecting the surface of the steel rail further includes extracting each damaged area by using a marker matrix to obtain an accurate position of the damaged area.
Optionally, the method for detecting the surface of the steel rail further includes performing feature extraction on the acquired image of the damaged area to determine the type of the damage.
Optionally, the feature extraction includes extracting geometric features, shape features, and gray-scale features of the damaged area image.
Optionally, the type of injury includes scars, abrasions.
Optionally, the method for establishing the steel rail damage type detection model includes training the steel rail damage type detection model based on a YOLO model according to damage characteristics of different damages.
In accordance with still another aspect of the present invention, there is provided an electronic apparatus including: a memory and a processor;
the memory is to store program instructions;
the processor is configured to invoke the program instructions in the memory to perform any of the above-described rail surface detection methods.
According to a further aspect of the present invention, there is provided a computer readable storage medium having computer program instructions stored therein which, when executed, implement any of the above-described rail surface inspection methods.
According to a further aspect of the present invention there is provided a computer program product comprising a computer program which when executed by a processor implements any of the rail surface detection methods described herein.
The invention has the advantages that: the invention provides a PCNN and deep learning-based steel rail surface detection method, which adopts a PCNN-based steel rail surface damage detection model for detection, a PCNN framework is compared with an original thermodynamic diagram regression framework, a positioning sub-network and a diagram structure posture optimization module are added, the original thermodynamic diagram regression network obtains a rough positioning result, a group of suggested key points, called guide points, are sampled, different visual features are extracted from each guide point through the positioning sub-network, and the relationship between the guide points is explored through the diagram structure posture optimization module, so that a more accurate positioning result is obtained, and accurate acquisition of a damage area image is realized. In addition, this application can promote detection efficiency greatly through adopting intelligent detection.
Drawings
Various additional advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 shows a schematic flow chart of a rail surface detection method based on PCNN and deep learning according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
According to one embodiment of the invention, a rail surface detection method based on PCNN and deep learning is provided, which comprises the following steps:
s1, preprocessing the surface image of the steel rail to obtain a rail surface image and a rail body image;
the method for preprocessing the surface image of the steel rail comprises the following steps:
identifying a background part and a steel rail part in the steel rail surface image by using a background detection model for the steel rail surface image, wherein the establishment method of the background detection model comprises the following steps: firstly, acquiring different steel rail surface images, marking a background part and a steel rail part in the steel rail surface images, and then training by using standard steel rail surface images to obtain the steel rail surface images;
extracting a steel rail part in the steel rail surface image, carrying out binarization processing on the steel rail part image, obtaining pixel points of the steel rail surface part after extracting white pixels, and dividing the steel rail surface image into a rail surface image and a rail body image according to the pixel point coordinates of the steel rail surface part.
S2, substituting the rail surface image and the rail body image into a PCNN-based steel rail surface damage detection model to obtain a damaged area image of the steel rail surface;
the PCNN-based training method of the steel rail surface damage detection model comprises the following steps:
marking the damage conditions of the rail surface image and the rail body image, performing cluster analysis on the damage parts in the rail surface image and the rail body image, dividing the damage parts into a plurality of parts according to the cluster analysis result, and marking the position information of the damage of each part respectively;
respectively counting the number of the pixels of the injuries of each part, wherein the number of the neurons in the PCNN is equal to the number of the pixels of the injuries of each part; and in specific implementation, each neuron receives only one feed input to form a neuron image, and the neuron image is trained to obtain a PCNN-based steel rail surface damage detection model.
In some embodiments, the rail surface detection method further includes detecting a noise-formed region on the damaged region image, performing a deletion operation when an area of the noise-formed region is smaller than a set threshold, and performing a marking when the area of the noise-formed region is greater than or equal to the set threshold. Furthermore, each damaged area is extracted by using the mark matrix so as to obtain the accurate position of the damaged area.
In some embodiments, the rail surface detection method further comprises performing feature extraction on the acquired damage region image to determine the type of damage. Specifically, the feature extraction includes extracting geometric features, shape features and gray scale features of the damaged area image. Wherein the geometrical characteristics comprise the perimeter, the area, the centroid of the defect region, the length and the width of the minimum external moment of the region; the shape characteristics comprise rectangularity, circularity, length ratio, direction and eccentricity; the gray scale features comprise a gray scale mean value, a gray scale variance, energy and entropy of the region.
The characteristics with larger difference among different types of injury images are selected as the injury characteristics of the type of injury. Wherein the type of injury comprises scar, abrasion.
And S3, detecting the damaged area image on the surface of the steel rail by using the steel rail damage type detection model, and obtaining the damage detection result of the detected steel rail. The damage detection result comprises the areas of the damage areas of different types of damages.
The method for establishing the steel rail damage type detection model comprises the step of training by using a YOLO (YOLO-based on-line analytical analysis) model according to damage characteristics of different damages.
Based on the rail surface detection method, in some embodiments, there is also provided an electronic device, including: a memory and a processor;
the memory is to store program instructions;
the processor is configured to invoke the program instructions in the memory to perform any of the above-described rail surface detection methods.
In some embodiments, there is also provided a computer readable storage medium having computer program instructions stored therein which, when executed, implement any of the above-described rail surface detection methods.
In some embodiments, there is also provided a computer program product comprising a computer program which when executed by a processor implements any one of the rail surface detection methods.
In conclusion, the rail surface detection method provided by the application can accurately acquire the image of the damaged area by adopting the rail surface damage detection model based on the PCNN for detection. In addition, this application can promote detection efficiency greatly through adopting intelligent detection.
It should be noted that:
the algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose devices may be used with the teachings herein. The required structure for constructing an arrangement of this type will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component and, in addition, may be divided into a plurality of H-bridge sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
Various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components of a PCNN and deep learning based rail surface detection method in accordance with embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website, or provided on a carrier signal, or provided in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
Claims (10)
1. A rail surface detection method based on PCNN and deep learning is characterized by comprising the following steps:
preprocessing the surface image of the steel rail to obtain a rail surface image and a rail body image;
substituting the rail surface image and the rail body image into a PCNN-based steel rail surface damage detection model to obtain a damaged area image of the steel rail surface;
and detecting the image of the damaged area on the surface of the steel rail by using the steel rail damage type detection model to obtain a damage detection result of the detected steel rail.
2. The method for detecting the surface of the steel rail according to claim 1, wherein the method for preprocessing the image of the surface of the steel rail comprises the following steps:
identifying a background part and a rail part in the rail surface image by using a background detection model for the rail surface image,
extracting a steel rail part in the steel rail surface image, carrying out binarization processing on the steel rail part image, obtaining pixel points of the steel rail surface part after extracting white pixels, and dividing the steel rail surface image into a rail surface image and a rail body image according to the pixel point coordinates of the steel rail surface part.
3. The method for detecting the surface of the steel rail according to claim 2, wherein the method for establishing the background detection model comprises the following steps: firstly, acquiring different steel rail surface images, marking a background part and a steel rail part in the steel rail surface images, and then training by using standard steel rail surface images to obtain the steel rail surface image.
4. The method for detecting the surface of the steel rail according to claim 1, wherein the PCNN-based method for training the rail surface damage detection model comprises the following steps:
marking the damage conditions of the rail surface image and the rail body image, then carrying out cluster analysis on the damage parts in the rail surface image and the rail body image, dividing the damage parts into a plurality of parts according to the cluster analysis result, and respectively marking the position information of the damage of each part;
respectively counting the number of pixels of each part of injury, wherein the number of neurons in the PCNN is equal to the number of pixels of each part of injury; and the damage detection process forms each neuron, a plurality of neurons are arranged into a single-layer network with transverse connection, each neuron receives the link input of all adjacent neurons in the radius, each neuron only receives one feed input to form a neuron image, and the neuron image is trained to obtain a PCNN-based steel rail surface damage detection model.
5. The method for detecting a steel rail surface according to claim 1, wherein: the method further comprises the steps of detecting a noise forming area on the damaged area image, carrying out deleting operation when the area of the noise forming area is smaller than a set threshold value, and marking when the area of the noise forming area is larger than or equal to the set threshold value.
6. The method for detecting a steel rail surface according to claim 1, wherein:
extracting each damaged area by using the mark matrix to obtain the accurate position of the damaged area;
and the method also comprises the step of carrying out feature extraction on the acquired image of the injury area so as to determine the type of the injury.
7. The rail surface detection method according to claim 6, characterized in that:
the characteristic extraction comprises extracting geometric characteristics, shape characteristics and gray characteristics of the damaged area image;
the types of injury include scars, abrasions.
8. The rail surface detection method according to claim 1, characterized in that: the method for establishing the steel rail damage type detection model comprises the step of training by using a YOLO (YOLO-based on-line analytical analysis) model according to damage characteristics of different damages.
9. An electronic device, comprising: a memory and a processor;
the memory is to store program instructions;
the processor is configured to invoke the program instructions in the memory to perform the rail surface detection method according to any one of claims 1 to 8.
10. A computer-readable storage medium characterized by: the computer-readable storage medium has stored therein computer program instructions which, when executed, implement the rail surface detection method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210486709.1A CN114926415A (en) | 2022-05-06 | 2022-05-06 | Steel rail surface detection method based on PCNN and deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210486709.1A CN114926415A (en) | 2022-05-06 | 2022-05-06 | Steel rail surface detection method based on PCNN and deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114926415A true CN114926415A (en) | 2022-08-19 |
Family
ID=82807526
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210486709.1A Pending CN114926415A (en) | 2022-05-06 | 2022-05-06 | Steel rail surface detection method based on PCNN and deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114926415A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116109638A (en) * | 2023-04-13 | 2023-05-12 | 中铁四局集团有限公司 | Rail break detection method and system |
| CN117253066A (en) * | 2023-11-20 | 2023-12-19 | 西南交通大学 | Rail surface state identification method, device, equipment and readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102854191A (en) * | 2012-07-18 | 2013-01-02 | 湖南大学 | Real-time visual detection and identification method for high speed rail surface defect |
| CN111626976A (en) * | 2019-11-01 | 2020-09-04 | 东莞灵虎智能科技有限公司 | Steel rail surface damage detection method based on pulse coupling neural network |
| US20210390682A1 (en) * | 2020-06-12 | 2021-12-16 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method for detecting surface defect, method for training model, apparatus, device, and media |
| CN113888488A (en) * | 2021-09-24 | 2022-01-04 | 深圳市比一比网络科技有限公司 | Steel rail defect detection method and system based on deep residual shrinkage network |
-
2022
- 2022-05-06 CN CN202210486709.1A patent/CN114926415A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102854191A (en) * | 2012-07-18 | 2013-01-02 | 湖南大学 | Real-time visual detection and identification method for high speed rail surface defect |
| CN111626976A (en) * | 2019-11-01 | 2020-09-04 | 东莞灵虎智能科技有限公司 | Steel rail surface damage detection method based on pulse coupling neural network |
| US20210390682A1 (en) * | 2020-06-12 | 2021-12-16 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method for detecting surface defect, method for training model, apparatus, device, and media |
| CN113888488A (en) * | 2021-09-24 | 2022-01-04 | 深圳市比一比网络科技有限公司 | Steel rail defect detection method and system based on deep residual shrinkage network |
Non-Patent Citations (1)
| Title |
|---|
| 段建礼: "钢轨探伤技术在铁路线路维修检测中的应用", 中小企业管理与科技, 31 December 2017 (2017-12-31) * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116109638A (en) * | 2023-04-13 | 2023-05-12 | 中铁四局集团有限公司 | Rail break detection method and system |
| CN116109638B (en) * | 2023-04-13 | 2023-07-04 | 中铁四局集团有限公司 | Rail break detection method and system |
| CN117253066A (en) * | 2023-11-20 | 2023-12-19 | 西南交通大学 | Rail surface state identification method, device, equipment and readable storage medium |
| CN117253066B (en) * | 2023-11-20 | 2024-02-27 | 西南交通大学 | Rail surface state identification method, device, equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11551341B2 (en) | Method and device for automatically drawing structural cracks and precisely measuring widths thereof | |
| CN112348787B (en) | Training method of object defect detection model, object defect detection method and device | |
| CN114926415A (en) | Steel rail surface detection method based on PCNN and deep learning | |
| CN107230203B (en) | Casting defect identification method based on human eye visual attention mechanism | |
| CN107389701A (en) | A kind of PCB visual defects automatic checkout system and method based on image | |
| CN103279765A (en) | Steel wire rope surface damage detection method based on image matching | |
| CN108416774A (en) | A kind of fabric types recognition methods based on fine granularity neural network | |
| CN111539927B (en) | Detection method of automobile plastic assembly fastening buckle missing detection device | |
| CN115937203B (en) | Visual detection method, device, equipment and medium based on template matching | |
| JP6811217B2 (en) | Crack identification method, crack identification device, crack identification system and program on concrete surface | |
| CN105891220A (en) | Pavement marker line defect detecting device and detecting method thereof | |
| CN107436304A (en) | A kind of surface of concrete structure detection means | |
| CN113947583B (en) | Weld joint nondestructive testing method based on deep learning two-dimensional time sequence image | |
| CN117214178A (en) | Intelligent identification method for appearance defects of package on packaging production line | |
| CN117593300B (en) | PE pipe crack defect detection method and system | |
| CN112967224A (en) | Electronic circuit board detection system, method and medium based on artificial intelligence | |
| CN112330633A (en) | Jumper wire adhesive tape damage fault image segmentation method based on self-adaptive band-pass filtering | |
| CN116823708A (en) | PC component side mold identification and positioning research based on machine vision | |
| CN105718929A (en) | All-weather unknown environment high precision rapid circular object positioning method and system | |
| CN112150453B (en) | Automatic detection method for breakage fault of bolster spring of railway wagon | |
| JPH0718811B2 (en) | Defect inspection method | |
| CN112730427B (en) | Product surface defect detection method and system based on machine vision | |
| JP7499210B2 (en) | Crack detection method, crack detection device, and program | |
| CN118596124B (en) | Steel bottle inner wall processing robot | |
| CN110349174B (en) | Sliding rail multi-parameter measurement method and measurement device |
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 |