CN113487561A - Pantograph foreign matter detection method and device based on gray gradient abnormal voting - Google Patents
Pantograph foreign matter detection method and device based on gray gradient abnormal voting Download PDFInfo
- Publication number
- CN113487561A CN113487561A CN202110749763.6A CN202110749763A CN113487561A CN 113487561 A CN113487561 A CN 113487561A CN 202110749763 A CN202110749763 A CN 202110749763A CN 113487561 A CN113487561 A CN 113487561A
- Authority
- CN
- China
- Prior art keywords
- edge curve
- image
- gray gradient
- section
- pantograph
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/77—Determining position or orientation of objects or cameras using statistical methods
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
Abstract
The invention relates to a pantograph foreign matter detection method and device based on gray gradient abnormal voting. The method comprises the steps of obtaining a template image of the carbon sliding plate, wherein a first edge curve is drawn on the upper edge of the carbon sliding plate; calculating the gray gradient absolute value of the position of the template image where the first edge curve is located; acquiring continuous frame detection images, calculating a mapping matrix of each frame detection image and a template image, and mapping a first edge curve to the detection image to be recorded as a second edge curve; calculating the gray gradient absolute value of the position of the detection image where the second edge curve is located, performing the same segmentation on the first edge curve and the second edge curve, and comparing the gray gradient absolute value with the gray gradient of the position of the template image where the first edge curve is located; if the gray gradient change value of a certain section exceeds a threshold value, recording a ticket in the section; if the number of votes obtained for a certain section of the continuous M frames of images exceeds a threshold value, the section is judged to have foreign matters. The method can provide online identification accuracy of the foreign matters of the pantograph.
Description
Technical Field
The invention relates to the technical field of rail transit contact network detection, in particular to a pantograph foreign matter detection method and device based on gray gradient abnormal voting.
Background
The important degree of the safety of the pantograph is self-evident, and in the actual operation process, floating objects such as plastic bags, balloons and the like are hung on the pantograph, so that serious safety accidents are easily caused. In the pantograph video monitoring scheme, a pantograph slide plate monitoring device (5C) is arranged on a station, station throat area, bullet train section and locomotive service section in-out route of an electric locomotive or a high-speed railway, and adopts a high-speed, high-resolution and non-contact image analysis and measurement technology to realize dynamic automatic detection of important hidden dangers such as damage and fracture of a pantograph slide plate and indoor visual observation of states of foreign matters on a roof and key parts, so that the pantograph slide plate monitoring device is widely suitable for various domestic locomotives, motor train units and subway vehicles. But 5C devices are limited in number and do not have real-time performance. Machine learning or deep learning schemes are often used for pantograph foreign object identification in current 3C and subway bow net products. Such a scheme trains a corresponding model and recognizes a foreign object invading the pantograph, but since the type, size, position, color and the like of the foreign object are unknown, training samples of the model are difficult to obtain in advance, and the recognition rate and the false alarm rate of the model are not ideal.
Disclosure of Invention
In order to overcome the defects and shortcomings in the prior art, the invention provides a pantograph foreign matter detection method and device based on gray gradient abnormal voting.
In order to solve the problems in the prior art, the invention is realized by the following technical scheme:
a pantograph foreign matter detection method based on gray gradient abnormal voting comprises the following steps:
s1, acquiring a template image, wherein the template image is a carbon sliding plate image, and a first edge curve is drawn on the upper edge of the carbon sliding plate;
s2, calculating the gray gradient absolute value of the template image position where the first edge curve is located;
s3, acquiring continuous frame detection images, calculating a mapping matrix of each frame detection image and a template image, and mapping the first edge curve to the detection image to be recorded as a second edge curve;
s4, calculating the gray gradient absolute value of the position of the detected image where the second edge curve is located, performing the same segmentation on the first edge curve and the second edge curve, and comparing the gray gradient absolute value with the gray gradient of the position of the template image where the first edge curve is located;
s5, if the gray gradient change value of a section exceeds the preset threshold value, recording a ticket in the section;
and S6, counting the continuous M frames of images, and if the number of votes obtained in a certain section exceeds a first preset threshold value, determining that foreign matters exist in the section.
Further, in step S4, the size of each segment after segmentation is smaller than the size of the foreign object to be detected.
Further, step S6 is: counting continuous M frames of images, and if the number of votes obtained by a certain section exceeds a first preset threshold value and the number of votes obtained by the left and/or right sections of the section exceeds a second preset threshold value, determining that foreign matters exist in the section; the second preset threshold is smaller than the first preset threshold.
Further, after calculating the gray scale gradient of the template image position where the first edge curve is located in step S2 and calculating the gray scale gradient of the detected image position where the second edge curve is located in step S4, normalization processing is performed according to the maximum value.
Further, in step S4: respectively calculating the gray gradient sum of each segmented section in the template image and the detection image; step S5 is: if the gray gradient sum variation value of a section exceeds a preset threshold value, the section records a ticket.
Further, in step S6: the first preset threshold is 0.3M, and the second preset threshold is 0.2M.
Further, in step S5, if the total gray scale change value of a section exceeds 5 or 6, the section is recorded with a ticket.
Another aspect of the present invention provides a pantograph foreign object detection apparatus based on gray scale gradient anomaly voting, including:
the template acquisition module is used for acquiring a template image, wherein the template image is a carbon sliding plate image, and a first edge curve is drawn on the upper edge of the carbon sliding plate;
the template gray gradient extraction module is used for calculating the gray gradient absolute value of the template image position where the first edge curve is located;
the edge curve mapping module is used for acquiring continuous frame detection images, calculating a mapping matrix of each frame detection image and a template image, and mapping the first edge curve to the detection image to be recorded as a second edge curve;
the image gray gradient abnormity extraction module is used for calculating the gray gradient absolute value of the position of the detected image where the second edge curve is located, carrying out the same segmentation on the first edge curve and the second edge curve, and comparing the gray gradient absolute value with the gray gradient of the position of the template image where the first edge curve is located;
the abnormal voting module is used for identifying a section of which the gray gradient change value exceeds a preset threshold value, and recording a vote in the section;
and the foreign matter judging module is used for counting the continuous M frames of images, and judging that foreign matters exist in a certain section if the number of votes obtained in the section exceeds a first preset threshold value.
The invention also provides a computer device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein when the processor executes the computer program, the processor executes the steps of the pantograph foreign matter detection method based on the gray gradient abnormal voting.
The present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the above-described pantograph foreign object detection method based on gray scale gradient abnormality voting.
Compared with the prior art, the beneficial technical effects brought by the invention are as follows:
the method is different from a common pantograph foreign matter distinguishing method adopting a machine learning/deep learning mode, adopts an image processing mode, carries out suspected pantograph foreign matter primary identification based on the gray gradient abnormal characteristics of the pantograph foreign matter, and integrates the foreign matter primary identification result in a continuous frame detection image by adopting a voting method to realize online identification of the pantograph foreign matter.
The method is not interfered by external illumination change, and is only related to the gray gradient of the current detection image and the gray gradient change of the template image (because the method is only related to the gray gradient, the method is not interfered by the external illumination change). For each frame of image, the color of the size type of the foreign matter does not need to be paid attention to too much, the exposure of the image and other external information do not need to be paid attention to, and only the gray gradient of the edge curve position needs to be extracted.
In addition, because the gradient changes are severe under different road sections and different illumination conditions, the method for identifying abnormal gray gradient by calculating the normalized total gradient after dividing the sections improves the identification accuracy of the pantograph foreign matters under the complex environment condition.
Drawings
Fig. 1 is a flowchart illustrating a pantograph foreign object detection method based on abnormal gray gradient voting according to an embodiment of the present invention;
FIG. 2 is an original image of a frame of a detected image according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating mapping of an edge curve to a detected image according to an embodiment of the present invention;
FIG. 4 is a gray scale gradient projection of an embodiment of the present invention;
FIG. 5 shows the result of normalization of gray scale gradients according to an embodiment of the invention;
FIG. 6 shows the result of gray gradient summation for each segment according to an embodiment of the present invention;
FIG. 7 is a diagram illustrating the difference between the gray scale sum of each region and the template image according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of an embodiment of the present invention in which the sum of gray gradients exceeds the threshold value;
FIG. 9 shows a continuous multi-frame image no-foreign object ticketing feature of an embodiment of the present invention;
FIG. 10 shows a foreign object ticketing feature for a plurality of consecutive frame images according to an embodiment of the present invention.
Detailed Description
The technical scheme of the invention is further elaborated in the following by combining the drawings in the specification.
The present embodiment provides a pantograph foreign object detection method based on gray scale gradient abnormal voting, as shown in fig. 1, including:
s1, acquiring a template image, wherein the template image is a carbon sliding plate image, and a first edge curve is drawn on the upper edge of the carbon sliding plate;
s2, calculating the gray gradient absolute value of the template image position where the first edge curve is located;
s3, acquiring continuous frame detection images, calculating a mapping matrix of each frame detection image and a template image, and mapping the first edge curve to the detection image to be recorded as a second edge curve;
s4, calculating the gray gradient absolute value of the position of the detected image where the second edge curve is located, performing the same segmentation on the first edge curve and the second edge curve, and comparing the gray gradient absolute value with the gray gradient of the position of the template image where the first edge curve is located;
s5, if the gray gradient change value of a section exceeds the preset threshold value, recording a ticket in the section;
and S6, counting the continuous M frames of images, and if the number of votes obtained in a certain section exceeds a first preset threshold value, determining that foreign matters exist in the section.
In step S4, the size of each segment after segmentation is smaller than the size of the foreign matter to be detected.
Step S6 is: counting continuous M frames of images, and if the number of votes obtained by a certain section exceeds a first preset threshold value and the number of votes obtained by the left and/or right sections of the section exceeds a second preset threshold value, determining that foreign matters exist in the section; the second preset threshold is smaller than the first preset threshold.
Step S2 calculates the gray scale gradient of the template image position where the first edge curve is located, and step S4 calculates the gray scale gradient of the detected image position where the second edge curve is located, and then normalization processing is performed according to the maximum value.
In step S4: respectively calculating the gray gradient sum of each segmented section in the template image and the detection image; step S5 is: if the gray gradient sum variation value of a section exceeds a preset threshold value, the section records a ticket.
In step S6: the first preset threshold is 0.3M, and the second preset threshold is 0.2M.
In step S5, if the total gray scale gradient change value of a section exceeds 5 or 6, the section records a ticket.
Fig. 2 is an original image of the detection image, fig. 3 is a schematic diagram illustrating the mapping of the template image to the detection image, and the position indicated by the arrow is the position where the first edge curve in the template image is mapped to the second edge curve in the detection image. Fig. 3-10 are intermediate result graphs of the method of this embodiment, respectively, where fig. 8 is a schematic diagram of a ticket obtained when a section of a frame of detected image with abnormal gray gradient exceeds a threshold value, fig. 9 is a result graph of a ticket obtaining feature without a foreign object in a continuous M-frame image, and fig. 10 is a result graph of a ticket obtaining feature with a foreign object in a continuous M-frame image.
The gray projection of foreign matters exists in the detected image, and the gray change at the foreign matters is severe, so the gradient map processing is adopted. After the gradient is calculated, the gradient is found to change violently when different road sections are illuminated by different light, and no unified standard exists, so that the gradient is subjected to normalization processing. After normalization, the maximum gradient is always arranged at a certain fixed position, but the gradients of the left area and the right area at the maximum gradient are smaller, so that the identification accuracy is improved by adopting a method of calculating the total gradient after dividing the areas. After the total gradient of each region is calculated, the difference value of the total gradient of each region is compared with the gradient of each region of the standard image, and the gradient change value of each region when no foreign matter exists is found not to exceed 6, so that the value is used as a change threshold value. If the threshold value is exceeded, it is indicated that foreign matter may exist in the region. Continuously counting a plurality of frames of images, and accumulating the possible foreign matters in each area. When the cumulative number of the areas exceeds 30% of the statistical number and the foreign matters exist in the areas on the left and right sides of the areas is more than 20% of the statistical number, the foreign matters exist in the areas.
The present embodiment also provides a pantograph foreign object detection device based on abnormal voting of gray scale gradients, including:
the template acquisition module is used for acquiring a template image, wherein the template image is a carbon sliding plate image, and a first edge curve is drawn on the upper edge of the carbon sliding plate;
the template gray gradient extraction module is used for calculating the gray gradient absolute value of the template image position where the first edge curve is located;
the edge curve mapping module is used for acquiring continuous frame detection images, calculating a mapping matrix of each frame detection image and a template image, and mapping the first edge curve to the detection image to be recorded as a second edge curve;
the image gray gradient abnormity extraction module is used for calculating the gray gradient absolute value of the position of the detected image where the second edge curve is located, carrying out the same segmentation on the first edge curve and the second edge curve, and comparing the gray gradient absolute value with the gray gradient of the position of the template image where the first edge curve is located;
the abnormal voting module is used for identifying a section of which the gray gradient change value exceeds a preset threshold value, and recording a vote in the section;
and the foreign matter judging module is used for counting the continuous M frames of images, and judging that foreign matters exist in a certain section if the number of votes obtained in the section exceeds a first preset threshold value.
In the present embodiment, each functional module in the pantograph foreign object detection device based on the gray scale gradient abnormal voting is used to implement each step of the pantograph foreign object detection method based on the gray scale gradient abnormal voting.
The embodiment also provides a computer device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein when the processor executes the computer program, the processor executes the steps of the pantograph foreign matter detection method based on the gray gradient abnormal voting.
The present embodiment also provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the above-mentioned pantograph foreign object detection method based on gray-scale gradient abnormal voting.
The processor may be a Central Processing Unit (CPU) in this embodiment. The Processor may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, or a combination thereof.
The memory, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and units, such as the corresponding program units in the above-described method embodiments of the present invention. The processor executes various functional applications of the processor and the processing of the work data by executing the non-transitory software programs, instructions and modules stored in the memory, that is, the method in the above method embodiment is realized.
The memory may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by the processor, and the like. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory located remotely from the processor, and such remote memory may be coupled to the processor via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Claims (10)
1. A pantograph foreign matter detection method based on gray gradient abnormal voting is characterized by comprising the following steps:
s1, acquiring a template image, wherein the template image is a carbon sliding plate image, and a first edge curve is drawn on the upper edge of the carbon sliding plate;
s2, calculating the gray gradient absolute value of the template image position where the first edge curve is located;
s3, acquiring continuous frame detection images, calculating a mapping matrix of each frame detection image and a template image, and mapping the first edge curve to the detection image to be recorded as a second edge curve;
s4, calculating the gray gradient absolute value of the position of the detected image where the second edge curve is located, performing the same segmentation on the first edge curve and the second edge curve, and comparing the gray gradient absolute value with the gray gradient of the position of the template image where the first edge curve is located;
s5, if the gray gradient change value of a section exceeds the preset threshold value, recording a ticket in the section;
and S6, counting the continuous M frames of images, and if the number of votes obtained in a certain section exceeds a first preset threshold value, determining that foreign matters exist in the section.
2. The pantograph foreign substance detection method according to claim 1, wherein in step S4, the size of each segment after the segmentation is smaller than the size of the foreign substance to be detected.
3. The pantograph foreign object detection method according to claim 1, wherein step S6 is: counting continuous M frames of images, and if the number of votes obtained by a certain section exceeds a first preset threshold value and the number of votes obtained by the left and/or right sections of the section exceeds a second preset threshold value, determining that foreign matters exist in the section; the second preset threshold is smaller than the first preset threshold.
4. The method for detecting a pantograph foreign object according to claim 1, wherein the gray scale gradient of the template image position where the first edge curve is located is calculated in step S2, and the gray scale gradient of the detection image position where the second edge curve is located is calculated in step S4, and then normalization processing is performed according to a maximum value.
5. The pantograph foreign object detection method according to claim 3, wherein in step S4: respectively calculating the gray gradient sum of each segmented section in the template image and the detection image; step S5 is: if the gray gradient sum variation value of a section exceeds a preset threshold value, the section records a ticket.
6. The pantograph foreign object detection method according to claim 4, wherein in step S6: the first preset threshold is 0.3M, and the second preset threshold is 0.2M.
7. The method for detecting a pantograph foreign object according to claim 4, wherein in step S5, if the total gray scale gradient variation value of a section exceeds 5 or 6, the section is recorded with a ticket.
8. A pantograph foreign matter detection device based on gray gradient abnormal voting is characterized by comprising:
the template acquisition module is used for acquiring a template image, wherein the template image is a carbon sliding plate image, and a first edge curve is drawn on the upper edge of the carbon sliding plate;
the template gray gradient extraction module is used for calculating the gray gradient absolute value of the template image position where the first edge curve is located;
the edge curve mapping module is used for acquiring continuous frame detection images, calculating a mapping matrix of each frame detection image and a template image, and mapping the first edge curve to the detection image to be recorded as a second edge curve;
the image gray gradient abnormity extraction module is used for calculating the gray gradient absolute value of the position of the detected image where the second edge curve is located, carrying out the same segmentation on the first edge curve and the second edge curve, and comparing the gray gradient absolute value with the gray gradient of the position of the template image where the first edge curve is located;
the abnormal voting module is used for identifying a section of which the gray gradient change value exceeds a preset threshold value, and recording a vote in the section;
and the foreign matter judging module is used for counting the continuous M frames of images, and judging that foreign matters exist in a certain section if the number of votes obtained in the section exceeds a first preset threshold value.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor performing the steps of the method of any of the preceding claims 1-7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any one of the preceding claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110749763.6A CN113487561B (en) | 2021-07-02 | 2021-07-02 | Pantograph foreign matter detection method and device based on gray gradient abnormal voting |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110749763.6A CN113487561B (en) | 2021-07-02 | 2021-07-02 | Pantograph foreign matter detection method and device based on gray gradient abnormal voting |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113487561A true CN113487561A (en) | 2021-10-08 |
CN113487561B CN113487561B (en) | 2023-06-30 |
Family
ID=77940283
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110749763.6A Active CN113487561B (en) | 2021-07-02 | 2021-07-02 | Pantograph foreign matter detection method and device based on gray gradient abnormal voting |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113487561B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114067106A (en) * | 2022-01-12 | 2022-02-18 | 西南交通大学 | Inter-frame contrast-based pantograph deformation detection method and equipment and storage medium |
CN116468729A (en) * | 2023-06-20 | 2023-07-21 | 南昌江铃华翔汽车零部件有限公司 | Automobile chassis foreign matter detection method, system and computer |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101982835A (en) * | 2010-11-12 | 2011-03-02 | 西安电子科技大学 | Level set method for edge detection of SAR images of airport roads |
WO2012137511A1 (en) * | 2011-04-07 | 2012-10-11 | パナソニック株式会社 | Image processing apparatus and image processing method |
CN105158257A (en) * | 2015-05-21 | 2015-12-16 | 苏州华兴致远电子科技有限公司 | Sliding plate measurement method and device |
WO2016183225A2 (en) * | 2015-05-12 | 2016-11-17 | Lawrence Livermore National Security, Llc | Identification of uncommon objects in containers |
CN106919943A (en) * | 2015-12-25 | 2017-07-04 | 北京搜狗科技发展有限公司 | A kind of data processing method and device |
CN108694349A (en) * | 2017-04-07 | 2018-10-23 | 成都唐源电气股份有限公司 | A kind of pantograph image extraction method and device based on line-scan digital camera |
CN208745762U (en) * | 2018-07-25 | 2019-04-16 | 成都永贵东洋轨道交通装备有限公司 | A kind of segmented pantograph carbon slide |
CN110378897A (en) * | 2019-07-25 | 2019-10-25 | 中车青岛四方机车车辆股份有限公司 | A kind of pantograph running state real-time monitoring method and device based on video |
CN110781758A (en) * | 2019-09-29 | 2020-02-11 | 同济大学 | Dynamic video monitoring method and device for abnormal pantograph structure |
CN111127381A (en) * | 2018-10-15 | 2020-05-08 | 西南交通大学 | Non-parallel detection method for pantograph slide plate |
CN111260629A (en) * | 2020-01-16 | 2020-06-09 | 成都地铁运营有限公司 | Pantograph structure abnormity detection algorithm based on image processing |
CN111738342A (en) * | 2020-06-24 | 2020-10-02 | 西南交通大学 | Pantograph foreign matter detection method, storage medium and computer equipment |
CN111862023A (en) * | 2020-07-14 | 2020-10-30 | 苏州华启智能科技有限公司 | Pantograph structure abnormity detection method based on computer vision |
CN112330678A (en) * | 2021-01-07 | 2021-02-05 | 中科慧远视觉技术(北京)有限公司 | Product edge defect detection method |
-
2021
- 2021-07-02 CN CN202110749763.6A patent/CN113487561B/en active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101982835A (en) * | 2010-11-12 | 2011-03-02 | 西安电子科技大学 | Level set method for edge detection of SAR images of airport roads |
WO2012137511A1 (en) * | 2011-04-07 | 2012-10-11 | パナソニック株式会社 | Image processing apparatus and image processing method |
WO2016183225A2 (en) * | 2015-05-12 | 2016-11-17 | Lawrence Livermore National Security, Llc | Identification of uncommon objects in containers |
CN105158257A (en) * | 2015-05-21 | 2015-12-16 | 苏州华兴致远电子科技有限公司 | Sliding plate measurement method and device |
CN106919943A (en) * | 2015-12-25 | 2017-07-04 | 北京搜狗科技发展有限公司 | A kind of data processing method and device |
CN108694349A (en) * | 2017-04-07 | 2018-10-23 | 成都唐源电气股份有限公司 | A kind of pantograph image extraction method and device based on line-scan digital camera |
CN208745762U (en) * | 2018-07-25 | 2019-04-16 | 成都永贵东洋轨道交通装备有限公司 | A kind of segmented pantograph carbon slide |
CN111127381A (en) * | 2018-10-15 | 2020-05-08 | 西南交通大学 | Non-parallel detection method for pantograph slide plate |
CN110378897A (en) * | 2019-07-25 | 2019-10-25 | 中车青岛四方机车车辆股份有限公司 | A kind of pantograph running state real-time monitoring method and device based on video |
CN110781758A (en) * | 2019-09-29 | 2020-02-11 | 同济大学 | Dynamic video monitoring method and device for abnormal pantograph structure |
CN111260629A (en) * | 2020-01-16 | 2020-06-09 | 成都地铁运营有限公司 | Pantograph structure abnormity detection algorithm based on image processing |
CN111738342A (en) * | 2020-06-24 | 2020-10-02 | 西南交通大学 | Pantograph foreign matter detection method, storage medium and computer equipment |
CN111862023A (en) * | 2020-07-14 | 2020-10-30 | 苏州华启智能科技有限公司 | Pantograph structure abnormity detection method based on computer vision |
CN112330678A (en) * | 2021-01-07 | 2021-02-05 | 中科慧远视觉技术(北京)有限公司 | Product edge defect detection method |
Non-Patent Citations (4)
Title |
---|
张振琛;顾桂梅;李占斌;: "基于图像处理的弓网燃弧检测方法", 兰州交通大学学报 * |
李兵祖;宋超;武莹;薛晓利;: "基于多尺度深度学习的接触网吊弦异常检测及应用", 电气化铁道 * |
王忠立;蔡伯根;: "一种基于几何约束的轨道提取方法研究", 交通运输系统工程与信息 * |
甘玉坤;丁跃浇;罗振威;吴雪婷;李旭东;: "低对比度工况下轴安装间隙提取方法研究", 计算机技术与发展 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114067106A (en) * | 2022-01-12 | 2022-02-18 | 西南交通大学 | Inter-frame contrast-based pantograph deformation detection method and equipment and storage medium |
CN114067106B (en) * | 2022-01-12 | 2022-04-15 | 西南交通大学 | Inter-frame contrast-based pantograph deformation detection method and equipment and storage medium |
CN116468729A (en) * | 2023-06-20 | 2023-07-21 | 南昌江铃华翔汽车零部件有限公司 | Automobile chassis foreign matter detection method, system and computer |
CN116468729B (en) * | 2023-06-20 | 2023-09-12 | 南昌江铃华翔汽车零部件有限公司 | Automobile chassis foreign matter detection method, system and computer |
Also Published As
Publication number | Publication date |
---|---|
CN113487561B (en) | 2023-06-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Gibert et al. | Robust fastener detection for autonomous visual railway track inspection | |
CN202793389U (en) | On-line routing inspection device for high-speed rail overhead line system | |
CN109238756B (en) | Dynamic image detection equipment and detection method for freight car operation fault | |
CN113487561B (en) | Pantograph foreign matter detection method and device based on gray gradient abnormal voting | |
CN110298300B (en) | Method for detecting vehicle illegal line pressing | |
CN111260629A (en) | Pantograph structure abnormity detection algorithm based on image processing | |
CN111079734B (en) | Method for detecting foreign matters in triangular holes of railway wagon | |
CN112967252B (en) | Rail vehicle machine sense hanger assembly bolt loss detection method | |
CN109858456A (en) | A kind of rolling stock status fault analysis system | |
CN112330646A (en) | Motor car bottom abnormity detection method based on two-dimensional image | |
CN112381014A (en) | Illegal parking vehicle detection and management method and system based on urban road | |
CN115600124A (en) | Subway tunnel inspection system and inspection method | |
CN113903180B (en) | Method and system for detecting vehicle overspeed on expressway | |
Koh et al. | Autonomous road potholes detection on video | |
Zheng et al. | Rail detection based on LSD and the least square curve fitting | |
CN110793501A (en) | Subway tunnel clearance detection method | |
Doycheva et al. | Computer vision and deep learning for real-time pavement distress detection | |
Song et al. | Modeling and optimization of semantic segmentation for track bed foreign object based on attention mechanism | |
CN111582075A (en) | Method and system for detecting screw looseness and foreign matters of bogie at bottom of train | |
CN114882452B (en) | Track line safety monitoring method, train operation control method and control system | |
CN104504713A (en) | Automatic trouble identification method based on TEDS (trouble of moving EMU detection system) | |
CN112132088B (en) | Inspection point missing inspection identification method | |
CN107993446A (en) | A kind of traffic prohibition parking area domain parking offense monitoring device | |
CN114005097A (en) | Train operation environment real-time detection method and system based on image semantic segmentation | |
CN117437792B (en) | Real-time road traffic state monitoring method, device and system based on edge calculation |
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 |