CN112288717A - Method for detecting foreign matters on side part of motor train unit train - Google Patents
Method for detecting foreign matters on side part of motor train unit train Download PDFInfo
- Publication number
- CN112288717A CN112288717A CN202011179779.XA CN202011179779A CN112288717A CN 112288717 A CN112288717 A CN 112288717A CN 202011179779 A CN202011179779 A CN 202011179779A CN 112288717 A CN112288717 A CN 112288717A
- Authority
- CN
- China
- Prior art keywords
- image
- train
- threshold value
- skirt board
- foreign matters
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000010606 normalization Methods 0.000 claims abstract description 27
- 230000000877 morphologic effect Effects 0.000 claims abstract description 14
- 238000013507 mapping Methods 0.000 claims description 8
- 238000005260 corrosion Methods 0.000 claims description 6
- 230000007797 corrosion Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 abstract description 20
- 230000008569 process Effects 0.000 description 8
- 230000006872 improvement Effects 0.000 description 6
- 238000007781 pre-processing Methods 0.000 description 3
- 230000008961 swelling Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000007 visual effect Effects 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61K—AUXILIARY EQUIPMENT SPECIALLY ADAPTED FOR RAILWAYS, NOT OTHERWISE PROVIDED FOR
- B61K9/00—Railway vehicle profile gauges; Detecting or indicating overheating of components; Apparatus on locomotives or cars to indicate bad track sections; General design of track recording vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Mechanical Engineering (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
A method for detecting foreign matters on the side part of a motor train unit train relates to the technical field of image processing, and aims to solve the problems of low detection efficiency and accuracy when the foreign matters exist in skirt boards on the side part of the motor train unit train through manual detection in the prior art, and comprises the following steps: acquiring a two-dimensional image of the train; step two: intercepting an area image of a skirt board position on the side part of the train: step three: carrying out gray level normalization processing on the area image; step four: performing morphological processing on the image after the gray level normalization, and performing background modeling according to the fixed characteristics of the apron board; step five: carrying out differential matching on different skirt board images and background models corresponding to the skirt board images; step six: and performing morphological processing on the image after the difference matching: step seven: an area threshold value, a length threshold value, a width threshold value and an aspect ratio threshold value of the contour are set, and the morphologically processed image is compared with the threshold values to determine whether or not foreign matter is present.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to an image processing method for detecting side foreign matters based on characteristic gray scale normalization of side parts of a motor train unit train.
Background
The skirt board at the side part of the motor train unit is easy to adhere to foreign matters such as bottles and plastic bags in the running process of the motor train unit, if the foreign matters are not found and cleaned in time, the driving safety is endangered, fault detection is carried out in a mode of manually checking images, the motor train unit runs at a high density, the time for detecting the motor train unit is short, the conditions of fatigue, omission and the like are easily caused in the working process of a motor train unit detector, the detection omission and the false detection are caused, the driving safety is influenced, manual detection is adopted, and the detection efficiency and the accuracy are low.
Disclosure of Invention
The purpose of the invention is: the method for detecting the foreign matters on the side part of the motor train unit train is provided aiming at the problems of low detection efficiency and accuracy when the foreign matters exist in the skirt board on the side part of the motor train unit train through manual detection in the prior art.
The technical scheme adopted by the invention to solve the technical problems is as follows:
a method for detecting foreign matters on the side of a motor train unit train comprises the following steps:
the method comprises the following steps: acquiring a two-dimensional image of the train;
step two: intercepting an image of a skirt board area at the side part of the train:
step three: carrying out gray level normalization processing on the images of the skirt board area at the side part of the train;
step four: carrying out background modeling according to the fixed characteristics of the images of the skirt board area at the side part of the train;
step five: carrying out difference matching on the normalized train side apron board area image and a background model corresponding to the train side apron board area image;
step six: and performing morphological processing on the image after the difference matching:
step seven: and setting an area threshold value, and length, width threshold values and aspect ratio threshold values of the contour, comparing the morphologically processed image with each threshold value, and if the morphologically processed image is matched with each threshold value, determining that no foreign matter exists, otherwise, determining that the foreign matter exists.
Further, the third step comprises the following specific steps:
fixed characteristic and row according to images of skirt board area at side part of trainObtaining an image high pixel value ratio threshold R by a two-dimensional image pixel value of a vehicleH0And image low pixel value ratio threshold RL0Then, the pixel values are divided into 255 levels, the size of the currently selected side skirt board image is W multiplied by H, wherein W is the width of the image, H is the height of the image, the value of the pixel value of a certain point in the image after gray level normalization is Y, and the threshold value of the high pixel value is YH0=W×H×RH0The threshold value of the low pixel value is YL0=W×H×RL0The value of Y is obtained by the following formula:
further, the background modeling in the fourth step comprises the following steps: firstly, dividing an image of a skirt board area at the side part of a train into an upper part, a middle part and a lower part, and modeling a background image according to the image characteristics of three parts on different carriages.
Further, the background modeling in the fourth step specifically comprises the following steps:
according to the position of the grating in the image of the skirt board area at the side part of the train, the position above the grating is regarded as the upper part, the position where the grating is located is regarded as the middle part, the part below the grating is regarded as the lower part, the image after the gray normalization is divided into three parts of image areas corresponding to the upper part, the middle part and the lower part respectively according to the proportion in the height direction, and background difference matching is carried out respectively.
Further, the morphological processing in the fourth step comprises binarization, filtering, expansion and corrosion.
Further, the method also comprises a step of positioning the foreign body, and the specific steps are as follows:
and determining the position of the foreign matter in the position area image of the skirt board at the side part of the train according to the position of the foreign matter, and mapping the position of the foreign matter on the whole image of the train through position mapping to position the foreign matter.
The invention has the beneficial effects that:
1. and the automatic image identification mode is used for replacing manual detection, so that the detection efficiency and accuracy are improved.
2. Before fault detection, the train image is processed by using an improved gray level normalization algorithm, so that the gray level balance of the image is ensured, and a guarantee is provided for the fault detection of the subsequent image processing.
3. The invention improves the traditional gray normalization processing, and is more suitable for detecting the vehicle images running in different environments.
4. The method adopts a background modeling mode to model the characteristics of the skirt board at the side part of the train, and compared with the traditional interframe difference method, the method utilizes more characteristics of the skirt board at the side part of the train, and further improves the accuracy and efficiency of foreign matter detection.
Drawings
FIG. 1 is a flow chart of the fault identification of the present invention;
FIG. 2 is a flow chart of background modeling in accordance with the present invention.
Detailed Description
The first embodiment is as follows: specifically describing the embodiment with reference to fig. 1 and 2, the method for detecting foreign matter on the side of the motor train unit train in the embodiment comprises the following steps:
the method comprises the following steps: acquiring a two-dimensional image of the train;
step two: intercepting an image of a skirt board area at the side part of the train:
step three: carrying out gray level normalization processing on the images of the skirt board area at the side part of the train;
step four: carrying out background modeling according to the fixed characteristics of the images of the skirt board area at the side part of the train;
step five: carrying out difference matching on the normalized train side apron board area image and a background model corresponding to the train side apron board area image;
step six: and performing morphological processing on the image after the difference matching:
step seven: and setting an area threshold value, and length, width threshold values and aspect ratio threshold values of the contour, comparing the morphologically processed image with each threshold value, and if the morphologically processed image is matched with each threshold value, determining that no foreign matter exists, otherwise, determining that the foreign matter exists.
Linear array image acquisition
High-definition equipment is set up around the train track respectively, and the train acquires high-definition images after passing through the equipment. By adopting the line scanning mode, a two-dimensional image with wide visual field and high precision can be formed.
Intercepting area to be detected
The two-dimensional images are spliced and intercepted according to the key parts of the train according to the wheel base information and the train type information of the train, and the images of the apron board positions are obtained from the images of the whole train, so that the time occupied by image processing of the non-side apron boards can be reduced, and the identification accuracy is improved.
Implementation and improvement of algorithms
The whole image processing process is divided into an image preprocessing process and an image processing process of foreign matter detection.
In the preprocessing process, the invention selects an improved gray normalization method, each section of train has the fixed characteristic mainly according to the characteristic of high similarity of the train of the bullet train, the area ratio of the skirting board grating in the current section of train exceeds sixty percent, the pixel value of the skirting board grating in the normal image is relatively fixed in the whole section of train, and the pixel threshold value is selected according to the characteristic of the skirting board grating to perform gray normalization on the image at the side part of the train. The method enhances the quality of the image based on the characteristic gray scale normalization of the parts at the sides of the motor train unit train. The running environment of the train is complex, the image is influenced by external factors such as weather, the quality of the image can be improved through improved image gray level normalization processing, the gray level balance of the side skirt board image for foreign matter detection is guaranteed, and the generalization performance of the foreign matter detection is higher.
The method comprises the steps of carrying out background modeling according to the fixed characteristics of a side skirt board, dividing the side skirt board part of a train into an upper part, a middle part and a lower part, modeling a background image according to the characteristics of images of the three parts of different trains, and carrying out morphological processing such as binaryzation, swelling corrosion and the like on the modeled background image. And then, according to different bus sections, the image of the skirt board at the side part of the current passing bus section is subjected to differential matching with the corresponding background template, the differential image is subjected to morphological image processing such as expansion and corrosion, and the final binary image is subjected to fault judgment.
The historical passing image with better image quality is selected, the side skirt board regards the position above the grating as the upper part, the position of the grating as the middle part and the part below the grating as the lower part according to the position of the grating. When the side foreign matter detection is performed, the image with the normalized gray scale is divided into the three image areas of the upper part, the middle part and the lower part according to the proportion in the height direction, and the background difference is performed on the image areas. Different areas adopt different threshold values to carry out differential calculation, and the foreign body fault of the vehicle can be accurately detected
The second embodiment is as follows: this embodiment is a further improvement of the first embodiment, and is different from the first embodiment in that the third step includes:
obtaining an image high pixel value ratio threshold value R according to the fixed characteristics of the image of the lateral skirt board area of the train and the pixel value of the two-dimensional image of the trainH0And image low pixel value ratio threshold RL0Then, the pixel values are divided into 255 levels, the size of the currently selected side skirt board image is W multiplied by H, wherein W is the width of the image, H is the height of the image, the value of the pixel value of a certain point in the image after gray level normalization is Y, and the threshold value of the high pixel value is YH0=W×H×RH0The threshold value of the low pixel value is YL0=W×H×RL0The value of Y is obtained by the following formula:
definition of image grayscale normalization
The gray normalization is a common image preprocessing process, and because the train images acquired by the images at different time and under different illumination may have great difference in gray distribution, the gray distribution of the images is not concentrated, which directly affects subsequent feature extraction and identification, the gray normalization of the train images is required. According to the method, the improved gray level normalization processing is adopted according to the characteristics of the skirt board image at the side part of the train, compared with the traditional mean variance normalization and gray level change normalization, the gray level of the processed image is more convenient for subsequent processing, and the generalization capability of the whole identification process is improved.
Selecting an image high pixel value ratio threshold value R according to the image characteristics of the skirt board at the side of the motor train unit trainH0The low pixel value of the image is the ratio threshold of RL0。RH0,RL0And the image pixel value is obtained by conjecture according to the current station passing vehicle image pixel value. The pixel values are divided into 255 levels. Suppose the currently selected side skirt image size is W × H, where H is the image width and H is the image height.
The value of a pixel value of a certain point in the image after gray level normalization is Y, and the value of Y is obtained through the following formula:
wherein the threshold value of the high pixel value is YH0=W×H×RH0The threshold value of the low pixel value is YL0=W×H×RL0
The third concrete implementation mode: the present embodiment is a further improvement of the second embodiment, and the difference between the present embodiment and the second embodiment is that the background modeling step in the fourth step is: firstly, dividing an image of a skirt board area at the side part of a train into an upper part, a middle part and a lower part, and modeling a background image according to the image characteristics of three parts on different carriages.
Background modeling
The method has the advantages that the side images are divided into an upper area, a middle area and a lower area according to inherent part characteristics of the skirt board images at the side of the motor train unit, background modeling is carried out on the images of different motor trains, so that influences of various cover plates, bolts and grids can be effectively avoided, and accuracy and high efficiency of foreign matter detection are guaranteed. The flow is shown in detail in FIG. 2.
The fourth concrete implementation mode: the present embodiment is a further improvement of the third embodiment, and the difference between the present embodiment and the third embodiment is that the specific steps of background modeling in the fourth step are as follows:
according to the position of the grating in the image of the skirt board area at the side part of the train, the position above the grating is regarded as the upper part, the position where the grating is located is regarded as the middle part, the part below the grating is regarded as the lower part, the image after the gray normalization is divided into three parts of image areas corresponding to the upper part, the middle part and the lower part respectively according to the proportion in the height direction, and background difference matching is carried out respectively.
Differential matching
The method comprises the steps of carrying out differential matching on side skirt board images of different trains and corresponding background models, then carrying out morphological processing on the images, judging whether foreign matters exist or not according to a detected component module in the images and different from other components in the side images of the trains by setting an area threshold, a length threshold, a width threshold and an aspect ratio threshold of a contour, finally judging whether the foreign matters exist or not, determining the position in a cut small graph according to the position of the detected foreign matters, mapping the position in the cut small graph to the whole image of the train through position mapping, generating a message and positioning faults.
The fifth concrete implementation mode: the present embodiment is a further improvement of the third embodiment, and the difference between the third embodiment and the present embodiment is that the morphological processing in the fourth step includes binarization, filtering, swelling and erosion.
Basic morphological treatment
And performing morphological processing such as binarization, filtering, expansion corrosion and the like on the image after gray level equalization to remove the influence of cavities and noise.
The sixth specific implementation mode: the third embodiment is a further improvement of the third embodiment, and the difference between the third embodiment and the fourth embodiment is that the method further comprises a step of positioning the foreign matter, and the specific steps are as follows:
and determining the position of the foreign matter in the position area image of the skirt board at the side part of the train according to the position of the foreign matter, and mapping the position of the foreign matter on the whole image of the train through position mapping to position the foreign matter.
Fault detection
The flow chart is shown in FIG. 1
The method comprises the following steps: intercepting candidate area to be detected
And taking out an image of the lateral skirt board area to be detected according to the train type information and the prior knowledge of the area where the lateral skirt board is located.
Step two: carrying out gray level normalization processing on the image
Improved gray scale normalization processing for the resulting target group and image
Step three: offline background modeling
Background template creation for image according to characteristics of side skirt board through vehicle type information
Step four: fault determination
And judging the foreign matter fault through the current image information and the background template information and through morphological image processing modes such as filtering, expansion, corrosion and the like.
Step five: upload alarm
And generating a message according to the obtained fault information of the fault type and the fault position, and uploading the message to an alarm platform.
It should be noted that the detailed description is only for explaining and explaining the technical solution of the present invention, and the scope of protection of the claims is not limited thereby. It is intended that all such modifications and variations be included within the scope of the invention as defined in the following claims and the description.
Claims (6)
1. A method for detecting foreign matters on the side of a motor train unit train is characterized by comprising the following steps:
the method comprises the following steps: acquiring a two-dimensional image of the train;
step two: intercepting an image of a skirt board area at the side part of the train:
step three: carrying out gray level normalization processing on the images of the skirt board area at the side part of the train;
step four: carrying out background modeling according to the fixed characteristics of the images of the skirt board area at the side part of the train;
step five: carrying out difference matching on the normalized train side apron board area image and a background model corresponding to the train side apron board area image;
step six: and performing morphological processing on the image after the difference matching:
step seven: and setting an area threshold value, and length, width threshold values and aspect ratio threshold values of the contour, comparing the morphologically processed image with each threshold value, and if the morphologically processed image is matched with each threshold value, determining that no foreign matter exists, otherwise, determining that the foreign matter exists.
2. The method for detecting the foreign matters on the side of the motor train unit train as claimed in claim 1, wherein the third step comprises the following specific steps:
obtaining an image high pixel value ratio threshold value R according to the fixed characteristics of the image of the lateral skirt board area of the train and the pixel value of the two-dimensional image of the trainH0And image low pixel value ratio threshold RL0Then, the pixel values are divided into 255 levels, the size of the currently selected side skirt board image is W multiplied by H, wherein W is the width of the image, H is the height of the image, the value of the pixel value of a certain point in the image after gray level normalization is Y, and the threshold value of the high pixel value is YH0=W×H×RH0The threshold value of the low pixel value is YL0=W×H×RL0The value of Y is obtained by the following formula:
3. the method for detecting the foreign matters on the side of the motor train unit train as claimed in claim 2, wherein the background modeling in the fourth step comprises the following steps: firstly, dividing an image of a skirt board area at the side part of a train into an upper part, a middle part and a lower part, and modeling a background image according to the image characteristics of three parts on different carriages.
4. The method for detecting the foreign matters on the side of the motor train unit train as claimed in claim 3, wherein the background modeling in the fourth step comprises the following specific steps:
according to the position of the grating in the image of the skirt board area at the side part of the train, the position above the grating is regarded as the upper part, the position where the grating is located is regarded as the middle part, the part below the grating is regarded as the lower part, the image after the gray normalization is divided into three parts of image areas corresponding to the upper part, the middle part and the lower part respectively according to the proportion in the height direction, and background difference matching is carried out respectively.
5. The method for detecting the foreign matters on the side of the motor train unit train as claimed in claim 3, wherein the morphological processing in the fourth step includes binarization, filtering, expansion and corrosion.
6. The method for detecting the foreign matters on the side of the motor train unit train as claimed in claim 3, wherein the method further comprises the step of positioning the foreign matters, and the specific steps are as follows:
and determining the position of the foreign matter in the position area image of the skirt board at the side part of the train according to the position of the foreign matter, and mapping the position of the foreign matter on the whole image of the train through position mapping to position the foreign matter.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011179779.XA CN112288717A (en) | 2020-10-29 | 2020-10-29 | Method for detecting foreign matters on side part of motor train unit train |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011179779.XA CN112288717A (en) | 2020-10-29 | 2020-10-29 | Method for detecting foreign matters on side part of motor train unit train |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112288717A true CN112288717A (en) | 2021-01-29 |
Family
ID=74373879
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011179779.XA Pending CN112288717A (en) | 2020-10-29 | 2020-10-29 | Method for detecting foreign matters on side part of motor train unit train |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112288717A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112896231A (en) * | 2021-03-01 | 2021-06-04 | 宁夏大学 | Railway track sand burying degree monitoring device and method |
CN113298059A (en) * | 2021-07-27 | 2021-08-24 | 昆山高新轨道交通智能装备有限公司 | Pantograph foreign matter intrusion detection method, device, computer equipment, system and storage medium |
CN114549865A (en) * | 2022-02-24 | 2022-05-27 | 中铁第四勘察设计院集团有限公司 | Method and system for automatically detecting state of skirtboard of motor train unit based on computer vision |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103077526A (en) * | 2013-02-01 | 2013-05-01 | 苏州华兴致远电子科技有限公司 | Train abnormality detection method and system with deep detection function |
CN104049281A (en) * | 2014-07-02 | 2014-09-17 | 广州市地下铁道总公司 | Device and method for automatically detecting foreign matter between screen door of curve subway platform and train |
CN204044383U (en) * | 2014-07-02 | 2014-12-24 | 广州市地下铁道总公司 | Foreign matter automatic detection device between curve metro platform shield door and train |
CN105551061A (en) * | 2015-12-09 | 2016-05-04 | 天津大学 | Processing method for retaining ghosting-free moving object in high-dynamic range image fusion |
US20170069081A1 (en) * | 2015-09-07 | 2017-03-09 | RaPID Platforms, LLC | Training System for Detection and Classification of Artificial Objects in X-Ray Images |
CN106845346A (en) * | 2016-12-16 | 2017-06-13 | 北京无线电计量测试研究所 | A kind of image detecting method for airfield runway foreign bodies detection |
CN108454635A (en) * | 2018-03-31 | 2018-08-28 | 广州明森科技股份有限公司 | A kind of foreign matter detection system between the shield door and train door of subway platform |
CN209008604U (en) * | 2018-11-05 | 2019-06-21 | 常州市新创智能科技有限公司 | A kind of equipment compartment safe condition Intellisense network system |
CN110232682A (en) * | 2019-05-31 | 2019-09-13 | 宁波中车时代传感技术有限公司 | A kind of track foreign body detecting method based on image |
CN111080582A (en) * | 2019-12-02 | 2020-04-28 | 易思维(杭州)科技有限公司 | Method for detecting defects on inner surface and outer surface of workpiece |
CN111161285A (en) * | 2019-12-31 | 2020-05-15 | 佛山科学技术学院 | Pericardial region positioning method, device and system based on feature analysis |
-
2020
- 2020-10-29 CN CN202011179779.XA patent/CN112288717A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103077526A (en) * | 2013-02-01 | 2013-05-01 | 苏州华兴致远电子科技有限公司 | Train abnormality detection method and system with deep detection function |
CN104049281A (en) * | 2014-07-02 | 2014-09-17 | 广州市地下铁道总公司 | Device and method for automatically detecting foreign matter between screen door of curve subway platform and train |
CN204044383U (en) * | 2014-07-02 | 2014-12-24 | 广州市地下铁道总公司 | Foreign matter automatic detection device between curve metro platform shield door and train |
US20170069081A1 (en) * | 2015-09-07 | 2017-03-09 | RaPID Platforms, LLC | Training System for Detection and Classification of Artificial Objects in X-Ray Images |
CN105551061A (en) * | 2015-12-09 | 2016-05-04 | 天津大学 | Processing method for retaining ghosting-free moving object in high-dynamic range image fusion |
CN106845346A (en) * | 2016-12-16 | 2017-06-13 | 北京无线电计量测试研究所 | A kind of image detecting method for airfield runway foreign bodies detection |
CN108454635A (en) * | 2018-03-31 | 2018-08-28 | 广州明森科技股份有限公司 | A kind of foreign matter detection system between the shield door and train door of subway platform |
CN209008604U (en) * | 2018-11-05 | 2019-06-21 | 常州市新创智能科技有限公司 | A kind of equipment compartment safe condition Intellisense network system |
CN110232682A (en) * | 2019-05-31 | 2019-09-13 | 宁波中车时代传感技术有限公司 | A kind of track foreign body detecting method based on image |
CN111080582A (en) * | 2019-12-02 | 2020-04-28 | 易思维(杭州)科技有限公司 | Method for detecting defects on inner surface and outer surface of workpiece |
CN111161285A (en) * | 2019-12-31 | 2020-05-15 | 佛山科学技术学院 | Pericardial region positioning method, device and system based on feature analysis |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112896231A (en) * | 2021-03-01 | 2021-06-04 | 宁夏大学 | Railway track sand burying degree monitoring device and method |
CN113298059A (en) * | 2021-07-27 | 2021-08-24 | 昆山高新轨道交通智能装备有限公司 | Pantograph foreign matter intrusion detection method, device, computer equipment, system and storage medium |
CN114549865A (en) * | 2022-02-24 | 2022-05-27 | 中铁第四勘察设计院集团有限公司 | Method and system for automatically detecting state of skirtboard of motor train unit based on computer vision |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112288717A (en) | Method for detecting foreign matters on side part of motor train unit train | |
CN111652227B (en) | Method for detecting damage fault of bottom floor of railway wagon | |
CN107480646B (en) | Binocular vision-based vehicle-mounted video abnormal motion detection method | |
CN112767326B (en) | Rail surface defect detection method, device, equipment and storage medium | |
CN109785301B (en) | Rail corrugation period evaluation method based on image processing | |
CN107967681B (en) | Elevator compensation chain impact defect detection method based on machine vision | |
CN111080650B (en) | Method for detecting looseness and loss faults of small part bearing blocking key nut of railway wagon | |
CN111079734B (en) | Method for detecting foreign matters in triangular holes of railway wagon | |
CN107154034B (en) | State detection method and system for stay wire positioning hook of high-speed rail contact network | |
CN111080602B (en) | Method for detecting foreign matters in water leakage hole of railway wagon | |
CN111485475A (en) | Pavement pit recognition method and device | |
CN111462045B (en) | Method for detecting defects of catenary support assembly | |
CN112184725B (en) | Method for extracting center of structured light bar of asphalt pavement image | |
CN111080621A (en) | Method for identifying railway wagon floor damage fault image | |
CN116071692A (en) | Morphological image processing-based water gauge water level identification method and system | |
CN116883446B (en) | Real-time monitoring system for grinding degree of vehicle-mounted camera lens | |
CN112419336B (en) | Motor car gearbox oil leakage fault identification method and system based on wavelet transformation | |
CN111652228B (en) | Railway wagon sleeper beam hole foreign matter detection method | |
CN111127381A (en) | Non-parallel detection method for pantograph slide plate | |
CN117333696A (en) | Bolt detection method and device based on machine vision | |
CN116416589A (en) | Rail point cloud extraction method based on rail data and geometric properties | |
Lin et al. | Lane departure identification on Highway with searching the region of interest on Hough space | |
CN113643352B (en) | Natural icing on-line monitoring running wire image icing degree evaluation method | |
CN112699794B (en) | Method for identifying dislocation fault images of middle rubber and upper and lower floor plates of wagon axle box rubber pad | |
CN112330633A (en) | Jumper wire adhesive tape damage fault image segmentation method based on self-adaptive band-pass filtering |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210129 |
|
RJ01 | Rejection of invention patent application after publication |