CN115880243B - Rail surface damage detection method, system and medium based on 3D point cloud segmentation - Google Patents
Rail surface damage detection method, system and medium based on 3D point cloud segmentation Download PDFInfo
- Publication number
- CN115880243B CN115880243B CN202211537437.XA CN202211537437A CN115880243B CN 115880243 B CN115880243 B CN 115880243B CN 202211537437 A CN202211537437 A CN 202211537437A CN 115880243 B CN115880243 B CN 115880243B
- Authority
- CN
- China
- Prior art keywords
- point cloud
- rail
- pixel
- image
- feature
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 69
- 230000011218 segmentation Effects 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 claims abstract description 32
- 238000007781 pre-processing Methods 0.000 claims abstract description 22
- 230000008569 process Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000004587 chromatography analysis Methods 0.000 claims description 3
- 238000007499 fusion processing Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 7
- 230000009286 beneficial effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 238000001328 terahertz time-domain spectroscopy Methods 0.000 description 3
- 238000005102 attenuated total reflection Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000005457 Black-body radiation Effects 0.000 description 1
- 238000001157 Fourier transform infrared spectrum Methods 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- -1 cartons Substances 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 239000006260 foam Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000009659 non-destructive testing Methods 0.000 description 1
- 229920003023 plastic Polymers 0.000 description 1
- 239000004033 plastic Substances 0.000 description 1
- 238000004611 spectroscopical analysis Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a rail surface damage detection method, a rail surface damage detection system and a rail surface damage detection medium based on 3D point cloud segmentation, which can be applied to the technical field of workpiece damage detection. The method comprises the following steps: acquiring a first workpiece image acquired by a portal camera; preprocessing the first workpiece image to obtain a first characteristic pixel image, wherein the preprocessing comprises background removal and pixel statistics; acquiring rail point feature data of the first feature pixel image; performing point cloud segmentation on the rail point feature data to obtain rail dominant point cloud feature data and point cloud feature data to be reconstructed; and detecting rail surface damage according to the rail dominant point cloud characteristic data and the point cloud characteristic data to be reconstructed. The invention can effectively and accurately finish the detection of the rail surface damage without carrying out contact detection on the rail, and effectively improves the detection effect and the detection accuracy.
Description
Technical Field
The invention relates to the technical field of workpiece damage detection, in particular to a rail surface damage detection method, a rail surface damage detection system and a rail surface damage detection medium based on 3D point cloud segmentation.
Background
In the related art, the improvement of the train speed has higher requirements on the track smoothness of the rail line than the prior art; particularly, the high-speed railway has stricter requirements on the smoothness of the rail, if the smoothness of the rail is poor, the rail is slightly vibrated, the action force of the wheel rail is multiplied, the rail and the rolling stock parts are seriously damaged, the speed of the train is improved, and the service lives of the rail and the rolling stock are reduced; serious accidents such as derailment and overturning of the train are caused, and driving safety is endangered.
The existing feature recognition detection has low recognition efficiency, low precision and high recognition error rate, and particularly has low efficiency for recognizing the image data information of the features of some oversized and complex workpieces. However, other contact type collection and recognition devices can meet the collection requirement, but the contact type collection mode has higher field requirement and is not suitable for rail detection, so that the accuracy of rail damage detection cannot be improved.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art. Therefore, the invention provides a rail surface damage detection method, a rail surface damage detection system and a rail surface damage detection medium based on 3D point cloud segmentation, which can effectively improve the accuracy of rail damage detection.
In one aspect, an embodiment of the present invention provides a method for detecting rail surface damage based on 3D point cloud segmentation, including the following steps:
acquiring a first workpiece image acquired by a portal camera;
preprocessing the first workpiece image to obtain a first characteristic pixel image, wherein the preprocessing comprises background removal and pixel statistics;
acquiring rail point feature data of the first feature pixel image;
performing point cloud segmentation on the rail point feature data to obtain rail dominant point cloud feature data and point cloud feature data to be reconstructed;
and detecting rail surface damage according to the rail dominant point cloud characteristic data and the point cloud characteristic data to be reconstructed.
In some embodiments, the performing point cloud segmentation on the rail point feature data to obtain rail dominant point cloud feature data and point cloud feature data to be reconstructed includes:
performing first point cloud segmentation on the rail point feature data to obtain rail effective point cloud feature data and mixed point cloud feature data, wherein the rail effective point cloud feature data comprises first rail dominant point cloud feature data and point cloud feature data to be reconstructed;
and performing second point cloud segmentation on the mixed point cloud characteristic data to obtain second rail dominant point cloud characteristic data.
In some embodiments, the detecting rail surface damage according to the rail dominant point cloud feature data and the point cloud feature data to be reconstructed includes:
detecting first rail surface damage according to the first rail dominant point cloud characteristic data, and detecting a first damage result;
fitting and reconstructing the dominant point cloud characteristic data of the second rail and the point cloud characteristic data to be reconstructed to obtain target characteristic data;
detecting the damage of the surface of the second rail according to the target characteristic data to obtain a second damage detection result;
and fusing the first damage detection result and the second damage detection result to obtain a target rail surface damage detection result.
In some embodiments, the de-background the first workpiece image comprises:
removing the background of the first workpiece image by adopting the following formula:
wherein,,
representing any characteristic pixel after the background of the first workpiece image is removed, m and n represent coordinate values of any characteristic pixel point on the first workpiece image, T represents a gray value of the characteristic pixel of the corresponding 3D point cloud of the first workpiece image, and R and K represent segmentation limit values of gray levels of the characteristic pixel of the 3D point cloud
In some embodiments, the performing pixel statistics on the first workpiece image includes:
and counting the sum of characteristic pixels corresponding to the first workpiece image by adopting the following formula:
wherein,,
representing the sum of feature pixels +.>
Representing a y-th feature pixel on the first workpiece image; />
Representing the total number of feature pixels in the calculation process;
the sum of image pixels of the first workpiece image is counted by adopting the following formula:
wherein,,
representing the sum of feature pixels +.>
Representing a y-th image pixel on the first workpiece image; />
Representing the total number of image pixels in the calculation process;
and carrying out pixel statistics according to the characteristic pixel sum and the image pixel sum.
In some embodiments, after the pixel statistics, the method further comprises the steps of:
when the pixel statistical result is smaller than the pixel threshold value, acquiring a second workpiece image of the net gape camera after the vision is adjusted;
preprocessing the second workpiece image to obtain a second characteristic pixel image;
and carrying out pixel fusion processing on the feature pixel image obtained by preprocessing the second feature pixel image and the first workpiece image, and obtaining a fused feature pixel image serving as a first feature pixel image.
In some embodiments, the acquiring rail points feature data of the first feature pixel image includes:
and acquiring the rail point feature data of the first feature pixel image through a terahertz three-dimensional chromatography algorithm.
In another aspect, an embodiment of the present invention provides a rail surface damage detection system based on 3D point cloud segmentation, including:
the first acquisition module is used for acquiring a first workpiece image acquired by the internet access camera;
the preprocessing module is used for preprocessing the first workpiece image to obtain a first characteristic pixel image, wherein the preprocessing comprises background removal and pixel statistics;
the second acquisition module is used for acquiring the rail point feature data of the first feature pixel image;
the segmentation module is used for carrying out point cloud segmentation on the rail point feature data to obtain rail dominant point cloud feature data and point cloud feature data needing to be reconstructed;
and the detection module is used for detecting the rail surface damage according to the rail dominant point cloud characteristic data and the point cloud characteristic data required to be reconstructed.
In another aspect, an embodiment of the present invention provides a rail surface damage detection system based on 3D point cloud segmentation, including:
at least one memory for storing a program;
at least one processor for loading the program to perform the 3D point cloud segmentation based rail surface damage detection method.
In another aspect, an embodiment of the present invention provides a storage medium, in which a computer executable program is stored, where the computer executable program is used to implement the method for detecting rail surface damage based on 3D point cloud segmentation when executed by a processor.
The rail surface damage detection method based on 3D point cloud segmentation provided by the embodiment of the invention has the following beneficial effects:
according to the invention, the damage detection is carried out by acquiring the workpiece image acquired by the net gape camera, the point cloud segmentation is carried out on the rail point feature data corresponding to the feature pixel image after the background removal and pixel statistics pretreatment is carried out on the workpiece image, and then the rail surface damage detection is carried out according to the segmentation to obtain the rail dominant point cloud feature data and the point cloud feature data required to be reconstructed, so that the rail surface damage detection can be effectively and accurately completed without carrying out contact detection on the rail, and the detection effect and the detection accuracy are effectively improved.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The invention is further described with reference to the accompanying drawings and examples, in which:
fig. 1 is a flowchart of a rail surface damage detection method based on 3D point cloud segmentation according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention.
In the description of the present invention, it should be understood that references to orientation descriptions such as upper, lower, front, rear, left, right, etc. are based on the orientation or positional relationship shown in the drawings, are merely for convenience of description of the present invention and to simplify the description, and do not indicate or imply that the apparatus or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be construed as limiting the present invention.
In the description of the present invention, the meaning of a number is one or more, the meaning of a number is two or more, and greater than, less than, exceeding, etc. are understood to exclude the present number, and the meaning of a number is understood to include the present number. The description of the first and second is for the purpose of distinguishing between technical features only and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, unless explicitly defined otherwise, terms such as arrangement, installation, connection, etc. should be construed broadly and the specific meaning of the terms in the present invention can be reasonably determined by a person skilled in the art in combination with the specific contents of the technical scheme.
In the description of the present invention, the descriptions of the terms "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Referring to fig. 1, an embodiment of the present invention provides a method for detecting rail surface damage based on 3D point cloud segmentation, which may be applied to a background processor corresponding to a rail damage detection platform, and may also be applied to a server or cloud.
During application, the method of the present embodiment includes, but is not limited to, the following steps:
step S110, acquiring a first workpiece image acquired by a portal camera;
in this embodiment, the gateway camera may employ a GIGE camera. In the image acquisition process, the illumination intensity of the light source can be controlled by the light source controller so as to improve the acquisition precision of the internet access camera.
Step S120, preprocessing a first workpiece image to obtain a first characteristic pixel image, wherein the preprocessing comprises background removal and pixel statistics;
in this embodiment, the background of the first workpiece image may be removed by using formula (1):
Wherein,,
and (3) representing any characteristic pixel after the background of the first workpiece image is removed, m and n represent coordinate values of any characteristic pixel point on the first workpiece image, T represents a gray value of the characteristic pixel of the corresponding 3D point cloud of the first workpiece image, and R and K represent segmentation limit values of gray levels of the characteristic pixel of the 3D point cloud.
And (3) counting the sum of characteristic pixels corresponding to the first workpiece image by adopting a formula (2):
Wherein,,
representing the sum of feature pixels +.>
Representing a y-th feature pixel on the first workpiece image; />
Representing the total number of feature pixels in the calculation process;
using formula (3) to count the sum of image pixels of the first workpiece image:
Wherein,,
representing the sum of feature pixels +.>
Representing a y-th image pixel on the first workpiece image; />
Representing the total number of image pixels in the calculation process;
and carrying out pixel statistics according to the characteristic pixel sum and the image pixel sum. Specifically, the feature pixels refer to pixel statistics in the image after the feature pixel sum image pixel sum is obtained through formula (4):
Wherein,,
representing the ratio of feature pixels to image pixels.
After the proportion is obtained, whether a complete rail characteristic pixel image is obtained or not can be determined according to the proportion, and if the complete rail characteristic pixel image is obtained, the rail characteristic pixel image corresponding to the current first workpiece image is used as a first characteristic pixel image for subsequent damage detection; if the complete rail characteristic pixel image is not obtained, controlling the portal camera to adjust the acquisition view field, obtaining a workpiece image of the portal camera after the view field is adjusted as a second workpiece image, and obtaining a characteristic pixel image corresponding to the second workpiece image as a second characteristic pixel image after the same preprocessing process of the first workpiece image is carried out on the second workpiece image. And then, carrying out pixel fusion processing on the feature pixel image after the second feature pixel image is preprocessed with the first workpiece image, and obtaining a fused feature pixel image serving as a first feature pixel image. Taking the pixel threshold value as 40% as an example, when the pixel statistics result is less than 40%, it is determined that the currently acquired feature pixel image is not a complete rail feature pixel image, so that the image acquisition view of the portal camera is adjusted, and the current feature pixel image is perfected according to the workpiece image after the image acquisition view until the pixel statistics result of the current feature pixel image is greater than or equal to 40%. Therefore, the method for identifying and displaying the features of the workpiece with the super-view field by utilizing the machine vision technology can well solve the problems that the collection difficulty of the features of the workpiece with the super-view field is high, the omission, the identification error and the identification speed are easy to occur in the identification process of the feature data, and the like, so that the detection method of the embodiment can be suitable for identifying and displaying the images of the features of the workpiece under the super-view field.
Step S130, obtaining rail point feature data of a first feature pixel image;
in the embodiment of the application, the rail point feature data of the first feature pixel image can be obtained through a terahertz three-dimensional chromatography algorithm. Among other things, terahertz technology has the following advantages: the frequency bands of the first terahertz spectrum correspond to a plurality of macromolecular integral vibration modes and intermolecular vibration modes, and the vibration modes are more sensitive to the external environment, so that the terahertz spectrum has the advantage that other testing means cannot meet in the aspect of substance characteristic research; the second terahertz spectrum belongs to coherent measurement, and can simultaneously obtain the information of amplitude and phase, so that the efficiency and accuracy of measurement are improved; thirdly, the THz system is insensitive to blackbody radiation (thermal background), and the signal to noise ratio can be as high as 104, which is far higher than that of the traditional Fourier transform infrared spectrum technology; fourth, terahertz wave has transiently, the pulse width is in the picosecond or subpicosecond order, therefore have very high time resolution, can be used for ultra-fast process research in fields such as physics, biology, chemistry, etc., can also be used for the ultra-high precision thickness measurement based on the flight time; fifth, terahertz photon energy is very low, only the meV level is adopted, ionization can not be generated on biological tissues, the biological tissues are very safe to human bodies, and living tissue research can be carried out; sixth, terahertz has unique penetrability, has strong penetrability to many nonpolar materials (such as plastics, cartons, cloth, foam, etc.), and can perform nondestructive testing of the interior of the materials. Terahertz time-domain spectroscopy (THz-TDS) technology is a typical representation of the application direction of terahertz technology, and is relatively mature and wide in application field. The terahertz time-domain spectroscopy technology utilizes a femtosecond laser to pump a terahertz transmitter to generate terahertz pulses, then carries information of a test sample in transmission, reflection or Attenuated Total Reflection (ATR) and other modes to be received by a terahertz detector, and can obtain physical information of refractive index, absorption coefficient, dielectric constant and the like of the sample through the spectroscopy technology. The application fields are mainly focused on biology, medicine, chemistry, agriculture, environment, food safety and the like.
Step S140, performing point cloud segmentation on the rail point feature data to obtain rail dominant point cloud feature data and point cloud feature data to be reconstructed; and detecting the rail surface damage according to the rail dominant point cloud characteristic data and the point cloud characteristic data to be reconstructed.
In the embodiment of the application, when the point cloud segmentation is performed on the rail point feature data to obtain the rail dominant point cloud feature data and the point cloud feature data to be reconstructed, the rail effective point cloud feature data and the mixed point cloud feature data can be obtained by performing first point cloud segmentation on the rail point feature data, and the second point cloud segmentation is performed on the mixed point cloud feature data to obtain the second rail dominant point cloud feature data. The rail effective point cloud feature data comprises first rail dominant point cloud feature data and point cloud feature data to be reconstructed. And then detecting rail surface damage based on the data obtained by the two divisions. Specifically, the rail surface damage detection of the present embodiment includes, but is not limited to, the following steps:
detecting the surface damage of the first rail according to the dominant point cloud characteristic data of the first rail, and detecting a first damage result;
fitting and reconstructing the dominant point cloud characteristic data of the second rail and the point cloud characteristic data to be reconstructed to obtain target characteristic data;
detecting the second rail surface damage according to the target characteristic data to obtain a second damage detection result;
and fusing the first damage detection result and the second damage detection result to obtain a target rail surface damage detection result.
Therefore, according to the embodiment, the combination of the two damage detection results is used for comprehensively judging whether the damage exists on the surface of the rail, so that the accuracy of the damage detection result can be effectively improved.
The embodiment of the invention provides a rail surface damage detection system based on 3D point cloud segmentation, which comprises the following steps:
the first acquisition module is used for acquiring a first workpiece image acquired by the internet access camera;
the preprocessing module is used for preprocessing the first workpiece image to obtain a first characteristic pixel image, wherein the preprocessing comprises background removal and pixel statistics;
the second acquisition module is used for acquiring the rail point feature data of the first feature pixel image;
the segmentation module is used for carrying out point cloud segmentation on the rail point feature data to obtain rail dominant point cloud feature data and point cloud feature data needing to be reconstructed;
and the detection module is used for detecting the rail surface damage according to the rail dominant point cloud characteristic data and the point cloud characteristic data required to be reconstructed.
The content of the method embodiment of the invention is suitable for the system embodiment, the specific function of the system embodiment is the same as that of the method embodiment, and the achieved beneficial effects are the same as those of the method.
The embodiment of the invention provides a rail surface damage detection system based on 3D point cloud segmentation, which comprises the following steps:
at least one memory for storing a program;
at least one processor for loading the program to perform the 3D point cloud segmentation based rail surface damage detection method shown in fig. 1.
The content of the method embodiment of the invention is suitable for the system embodiment, the specific function of the system embodiment is the same as that of the method embodiment, and the achieved beneficial effects are the same as those of the method.
An embodiment of the present invention provides a storage medium in which a computer-executable program is stored, which when executed by a processor is configured to implement the rail surface damage detection method based on 3D point cloud segmentation shown in fig. 1.
The content of the method embodiment of the invention is applicable to the storage medium embodiment, the specific function of the storage medium embodiment is the same as that of the method embodiment, and the achieved beneficial effects are the same as those of the method.
Embodiments of the present invention also provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device may read the computer instructions from the computer-readable storage medium, the processor executing the computer instructions, causing the computer device to perform the rail surface damage detection method based on 3D point cloud segmentation shown in fig. 1.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of one of ordinary skill in the art without departing from the spirit of the present invention. Furthermore, embodiments of the invention and features of the embodiments may be combined with each other without conflict.
Claims (8)
1. A rail surface damage detection method based on 3D point cloud segmentation is characterized by comprising the following steps:
acquiring a first workpiece image acquired by a portal camera;
preprocessing the first workpiece image to obtain a first characteristic pixel image, wherein the preprocessing comprises background removal and pixel statistics;
acquiring rail point feature data of the first feature pixel image;
performing first point cloud segmentation on the rail point feature data to obtain rail effective point cloud feature data and mixed point cloud feature data, wherein the rail effective point cloud feature data comprises first rail dominant point cloud feature data and point cloud feature data to be reconstructed;
performing second point cloud segmentation on the mixed point cloud characteristic data to obtain second rail dominant point cloud characteristic data;
detecting first rail surface damage according to the first rail dominant point cloud characteristic data, and detecting a first damage result;
fitting and reconstructing the dominant point cloud characteristic data of the second rail and the point cloud characteristic data to be reconstructed to obtain target characteristic data;
detecting the damage of the surface of the second rail according to the target characteristic data to obtain a second damage detection result;
and fusing the first damage detection result and the second damage detection result to obtain a target rail surface damage detection result.
2. The method for detecting rail surface damage based on 3D point cloud segmentation of claim 1, wherein the removing the background from the first workpiece image comprises:
removing the background of the first workpiece image by adopting the following formula:
wherein,,
and (3) representing any characteristic pixel after the background of the first workpiece image is removed, m and n represent coordinate values of any characteristic pixel point on the first workpiece image, T represents a gray value of the characteristic pixel of the corresponding 3D point cloud of the first workpiece image, and R and K represent segmentation limit values of gray levels of the characteristic pixel of the 3D point cloud.
3. The method for detecting rail surface damage based on 3D point cloud segmentation according to claim 2, wherein the performing pixel statistics on the first workpiece image comprises:
and counting the sum of characteristic pixels corresponding to the first workpiece image by adopting the following formula:
wherein,,
representing the sum of feature pixels +.>
Representing a y-th feature pixel on the first workpiece image; />
Representing the total number of feature pixels in the calculation process;
the sum of image pixels of the first workpiece image is counted by adopting the following formula:
wherein,,
representing the sum of feature pixels +.>
Representing a y-th image pixel on the first workpiece image; />
Representing the total number of image pixels in the calculation process;
and carrying out pixel statistics according to the characteristic pixel sum and the image pixel sum.
4. A method of rail surface damage detection based on 3D point cloud segmentation as claimed in claim 3, wherein after the pixel statistics the method further comprises the steps of:
when the pixel statistical result is smaller than the pixel threshold value, acquiring a second workpiece image of the net gape camera after the vision is adjusted;
preprocessing the second workpiece image to obtain a second characteristic pixel image;
and carrying out pixel fusion processing on the feature pixel image obtained by preprocessing the second feature pixel image and the first workpiece image, and obtaining a fused feature pixel image serving as a first feature pixel image.
5. The method for detecting rail surface damage based on 3D point cloud segmentation according to claim 1, wherein the acquiring rail point feature data of the first feature pixel image comprises:
and acquiring the rail point feature data of the first feature pixel image through a terahertz three-dimensional chromatography algorithm.
6. A rail surface damage detection system based on 3D point cloud segmentation, comprising:
the first acquisition module is used for acquiring a first workpiece image acquired by the internet access camera;
the preprocessing module is used for preprocessing the first workpiece image to obtain a first characteristic pixel image, wherein the preprocessing comprises background removal and pixel statistics;
the second acquisition module is used for acquiring the rail point feature data of the first feature pixel image;
the segmentation module is used for carrying out first point cloud segmentation on the rail point feature data to obtain rail effective point cloud feature data and mixed point cloud feature data, wherein the rail effective point cloud feature data comprises first rail dominant point cloud feature data and point cloud feature data to be reconstructed; performing second point cloud segmentation on the mixed point cloud characteristic data to obtain second rail dominant point cloud characteristic data;
the detection module is used for detecting the first rail surface damage according to the first rail dominant point cloud characteristic data, and a first damage detection result is obtained; fitting and reconstructing the dominant point cloud characteristic data of the second rail and the point cloud characteristic data to be reconstructed to obtain target characteristic data; detecting the damage of the surface of the second rail according to the target characteristic data to obtain a second damage detection result; and fusing the first damage detection result and the second damage detection result to obtain a target rail surface damage detection result.
7. A rail surface damage detection system based on 3D point cloud segmentation, comprising:
at least one memory for storing a program;
at least one processor for loading the program to perform the method of 3D point cloud segmentation based rail surface damage detection as claimed in any one of claims 1-5.
8. A storage medium having stored therein a computer executable program for implementing the 3D point cloud segmentation based rail surface damage detection method of any one of claims 1-5 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211537437.XA CN115880243B (en) | 2022-12-02 | 2022-12-02 | Rail surface damage detection method, system and medium based on 3D point cloud segmentation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211537437.XA CN115880243B (en) | 2022-12-02 | 2022-12-02 | Rail surface damage detection method, system and medium based on 3D point cloud segmentation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115880243A CN115880243A (en) | 2023-03-31 |
| CN115880243B true CN115880243B (en) | 2023-07-07 |
Family
ID=85765524
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211537437.XA Active CN115880243B (en) | 2022-12-02 | 2022-12-02 | Rail surface damage detection method, system and medium based on 3D point cloud segmentation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115880243B (en) |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111340797B (en) * | 2020-03-10 | 2023-04-28 | 山东大学 | Laser radar and binocular camera data fusion detection method and system |
| US11810364B2 (en) * | 2020-08-10 | 2023-11-07 | Volvo Car Corporation | Automated road damage detection |
| CN112686877B (en) * | 2021-01-05 | 2022-11-11 | 同济大学 | Binocular camera-based three-dimensional house damage model construction and measurement method and system |
| CN113870326B (en) * | 2021-09-01 | 2023-11-28 | 浙江大学 | Structural damage mapping, quantifying and visualizing method based on image and three-dimensional point cloud registration |
| CN114255238A (en) * | 2021-11-26 | 2022-03-29 | 电子科技大学长三角研究院(湖州) | Three-dimensional point cloud scene segmentation method and system fusing image features |
| CN115100277A (en) * | 2022-03-02 | 2022-09-23 | 重庆大学 | Method for determining position and pose of complex curved surface structure part |
| CN114596313B (en) * | 2022-05-09 | 2022-10-04 | 深圳大学 | Building component damage detection method based on indoor point cloud and related equipment |
-
2022
- 2022-12-02 CN CN202211537437.XA patent/CN115880243B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115880243A (en) | 2023-03-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3349048A1 (en) | Inspection devices and methods for detecting a firearm in a luggage | |
| CN110186940B (en) | Security check identification method and device, computer equipment and storage medium | |
| EP2751547B1 (en) | Method and apparatus for the determination of a substance using thz radiation | |
| CN104764712B (en) | A kind of detection method of PCB vias inwall quality | |
| CN108956526A (en) | A kind of passive type Terahertz hazardous material detection device, detection method and its application | |
| CN111257957B (en) | Identification tracking system and method based on passive terahertz imaging | |
| EP1332334B1 (en) | Measuring device for contactless measurement of tyres | |
| CN109447071A (en) | A kind of mm-wave imaging dangerous goods detection method based on FPGA and deep learning | |
| DE202007019256U1 (en) | Device for assessing the properties of liquids | |
| US10497144B2 (en) | Vehicle inspection system, and method and system for identifying part of vehicle | |
| CN207946369U (en) | A kind of railway rail clip abnormal detector based on pointolite array linear array imaging | |
| EP3047232B1 (en) | Method and device for establishing a geometry of a container for packaging a flowable medium | |
| CN105510364A (en) | Nondestructive testing system for industrial part flaws based on X rays and detection method thereof | |
| DE102014002582A1 (en) | Method for detecting cracks in the walls of hollow glass articles | |
| CN111999742B (en) | Single-quantity estimation-based Gm-APD laser radar fog-penetrating imaging reconstruction method | |
| CN110873718A (en) | Steel plate surface defect detection system and method based on machine vision | |
| Bellens et al. | Evaluating conventional and deep learning segmentation for fast X-ray CT porosity measurements of polymer laser sintered AM parts | |
| CN107300562B (en) | X-ray nondestructive testing method for measuring contact distance of finished relay product | |
| CN115880243B (en) | Rail surface damage detection method, system and medium based on 3D point cloud segmentation | |
| CN108535138A (en) | Proportion detection device and method for green channel vehicle | |
| CN105181623B (en) | A kind of mail-detection apparatus and method | |
| CN116012297B (en) | Terahertz-based rail surface damage detection method, terahertz-based rail surface damage detection system and storage medium | |
| WO2020140982A1 (en) | Back-scattering inspection system and back-scattering inspection method | |
| JP3789696B2 (en) | Battery electrolyte leak inspection apparatus and battery electrolyte leak inspection method | |
| CN105787919A (en) | Operation method and apparatus for safety inspection CT three-dimensional images |
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 |