CN116279650A - Switch tongue close contact detection method and system - Google Patents
Switch tongue close contact detection method and system Download PDFInfo
- Publication number
- CN116279650A CN116279650A CN202310595620.3A CN202310595620A CN116279650A CN 116279650 A CN116279650 A CN 116279650A CN 202310595620 A CN202310595620 A CN 202310595620A CN 116279650 A CN116279650 A CN 116279650A
- Authority
- CN
- China
- Prior art keywords
- rail
- point
- switch
- steel
- steel rail
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 119
- 238000003384 imaging method Methods 0.000 claims abstract description 97
- 238000005259 measurement Methods 0.000 claims abstract description 45
- 229910000831 Steel Inorganic materials 0.000 claims description 204
- 239000010959 steel Substances 0.000 claims description 204
- 238000005070 sampling Methods 0.000 claims description 32
- 238000000034 method Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 10
- 230000003287 optical effect Effects 0.000 claims description 8
- 238000013135 deep learning Methods 0.000 claims description 7
- 230000015572 biosynthetic process Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 5
- 238000012567 pattern recognition method Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 abstract description 15
- 201000010099 disease Diseases 0.000 abstract description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 2
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 238000003708 edge detection Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 210000000709 aorta Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- B61K9/08—Measuring installations for surveying permanent way
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/14—Measuring arrangements characterised by the use of optical techniques for measuring distance or clearance between spaced objects or spaced apertures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
- G01B11/2433—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures for measuring outlines by shadow casting
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
Abstract
The invention belongs to the technical field of rail transit disease detection, and provides a switch tongue close contact detection method and a switch tongue close contact detection system. The invention provides an automatic detection system and an automatic detection method based on a visual detection method, which improve an imaging unit in a visual imaging module and can automatically realize insufficient close contact detection and gap quantitative measurement of a switch rail.
Description
Technical Field
The invention relates to the technical field of rail transit disease detection, in particular to a switch tongue close contact detection method and system.
Background
The railway is an aorta of national economy, and overhauls the railway state, so that the railway is an important guarantee for ensuring the safe operation of the railway. The turnout is used for guiding the train to change the track and is an important component of the railway. The switch rail is arranged in the turnout, and the switch rail and the steel rail are required to be tightly attached under normal conditions to ensure that the train wheels are guided to change the track correctly, otherwise, the train wheels are derailed, and traffic accidents are caused.
At present, a manual inspection method is mainly adopted, steel scales with different thicknesses are inserted into gaps between a steel rail and a switch rail, and the steel scales are used for detecting the close state of the switch rail. To solve the problem, the invention provides an automatic detecting system for the close contact of the switch tongue, which is used for automatically judging whether the close contact is insufficient or not and quantitatively measuring the close contact gap.
Disclosure of Invention
In order to solve the problems in the background technology, the invention provides a switch tongue close contact detection method and a switch tongue close contact detection system, which can automatically realize the short contact detection and the gap quantitative measurement of the switch tongue.
The invention adopts a technical scheme that:
the utility model provides a switch tongue close contact detection system comprises imaging control module, vision imaging module, image processing module and delivery platform, vision imaging module is including being located 2 imaging unit directly over the rail of both sides respectively, carries out the formation of image to the rail along delivery platform direction of motion, and the formation of image region covers rail, switch tongue, switch, acquires the texture image and/or the depth image of formation of image region.
Further, the imaging unit consists of an area array camera and a surface light source, the area array camera and the surface light source are used for coaxially illuminating, and a camera optical axis is positioned right above the inner edge of the steel rail to acquire texture images of an imaging area.
Further, the imaging unit is a linear camera and a linear light source, the linear camera and the linear light source are coaxially illuminated, and an optical center of the linear camera is positioned right above the inner edge of the steel rail to acquire texture images of an imaging area;
the imaging resolution of the imaging unit along the moving direction of the carrying platform is not lower than 1mm/pixel, and the imaging resolution of the imaging unit along the direction perpendicular to the moving direction of the carrying platform is not lower than 0.05mm/pixel.
Further, the imaging unit is a line structured light 3D camera, and the 3D camera is positioned right above the steel rail to acquire texture images and depth images of the steel rail and the switch rail.
Further, the imaging unit is a line structure light 3D camera, the 3D camera is positioned above the inner side of the steel rail in an inclined manner, the line structure light plane is perpendicular to the extending direction of the steel rail, the 3D camera measuring area covers the top and the inner side surface of the steel rail, the top and the inner side surface of the point rail, the measuring precision of the 3D camera in the x direction and the y direction is not lower than 0.1mm, and the measuring precision of the 3D camera in the z direction is not lower than 0.05mm.
The invention adopts another technical scheme that:
a switch tongue close contact detection method comprises the following steps:
acquiring an image of an imaging region and detecting a first object from the image;
judging whether the point rail is not sufficiently attached or not based on the first object in the acquired imaging area image;
if the point rail is not sufficiently closely attached, calculating a point rail closely attached gap;
wherein the imaging area comprises a steel rail, a switch rail and a turnout;
the image comprises a texture image and/or a depth image.
Further, a switch tongue close contact detection method comprises the following steps:
acquiring texture images of an imaging area, and detecting steel rails and switch rails from the images;
after detecting the switch rail, setting m1 sampling windows in the texture image by taking the steel rail as an axis and being perpendicular to the extending direction of the steel rail, projecting pixels in the sampling windows along the extending direction of the steel rail, sampling a projection curve in the range of [ -u, u ] by taking the edge of the inner side of the steel rail as the center on the projection curve, and judging whether the switch rail is not close enough by adopting a classifier based on the sampling curve;
the method for judging insufficient point rail adhesion by using the classifier comprises the following steps:
two sample sets were manually set: the adhesion is insufficient; training a classifier by adopting a pattern recognition method; and classifying the sampling curve by using a trained classifier, and judging whether the point rail is not sufficiently closely attached or not according to the classification result.
If the point rail is not sufficiently stuck, measuring the width of the trough in the sampling curve, taking the average value or the maximum value of m1 point rail sticking gap measurement values as a final point rail sticking gap.
Further, a switch tongue close contact detection method comprises the following steps:
acquiring texture images of an imaging area, and detecting steel rails and switch rails from the images;
after detecting the switch rail, detecting the inner side edge of the steel rail and the first step edge of the switch rail in a texture image by adopting an edge extraction method, setting m2 sampling lines which are perpendicular to the extending direction of the steel rail by taking the steel rail as an axis, calculating the width value wi from the inner side edge of the steel rail to the bottom edge of the switch rail, and judging that the gap exists in the switch rail when wi is more than t;
when a gap exists, wi-t=wi' is used as the gap width, t is the width when the point rail is tightly attached to the steel rail, and the average value or the maximum value of m2 gap widths is taken as the point rail close-attaching gap.
Further, a switch tongue close contact detection method comprises the following steps:
acquiring a depth image of an imaging area, detecting a steel rail from the image, finding out the inner edge of the steel rail according to the position of the steel rail, and detecting a slide plate by a deep learning method;
setting a rectangular detection window in the detected slide plate area perpendicular to the extending direction of the steel rail, measuring the distance d1 from the inner edge of the steel rail to the first step edge of the point rail and the distance d2 from the inner edge of the steel rail to the second step edge of the point rail in the detection window, judging whether the distances d1 and d2 exceed the distance d10 from the inner edge of the steel rail to the first step edge of the point rail and the distance d20 from the inner edge of the second step edge of the point rail when the point rail is closely attached to the steel rail, and if any one of the distances exceeds the distance d1 and the distance d2 from the inner edge of the steel rail to the first step edge of the point rail, the point rail is not closely attached;
when there is insufficient point contact, di= (d1-d10+d2-d 20)/2 is calculated as point contact gap.
Further, a switch tongue close contact detection method comprises the following steps:
the method comprises the steps of pre-collecting switch depth images, cutting the images by taking fasteners as units, enabling each image to only contain one row of fasteners, detecting the contact position of a switch rail and a slide plate, and recording the cut pre-collected switch depth images, the contact position of the switch rail and the slide plate mark area as a background database;
collecting a current turnout depth image, cutting the current collected image by taking the turnout depth image collected in advance as a reference, and generating a foreground image corresponding to the background database one by one;
acquiring a corresponding foreground image and a switch depth image acquired in advance, judging whether a switch rail leaning place exists in a background database, and acquiring a slide plate marking area and the switch rail leaning place if the switch rail leaning place exists;
setting a measuring area according to the position of the slide plate, and respectively measuring the width from the outer edge of the steel rail to the bottom edge of the switch rail in a pre-acquired switch depth image and a pre-acquired foreground image;
judging whether a gap exists between the point rail and the steel rail in the foreground image, if so, judging whether the point rail is not in close contact, if not, judging whether the width from the outer edge of the steel rail to the bottom edge of the point rail in the foreground image is increased and overrun, and if so, judging that the point rail is in close contact.
Further, a switch tongue close contact detection method comprises the following steps:
acquiring steel rail and point rail depth images, respectively finding the steel rail and the point rail from the steel rail depth images and the point rail depth images, and detecting a slide plate;
setting rectangular detection windows in the detected slide plate area perpendicular to the extending direction of the steel rail, and setting n sampling lines in the detection windows perpendicular to the extending direction of the steel rail to obtain n steel rails and point rail profile curves;
in the profile lines of n steel rails and the point rail, performing line segment fitting on the inner edge of the steel rail to obtain L1, performing line segment fitting on the vertical edge of the first step of the point rail to obtain L2, and performing line segment fitting on the vertical edge of the second step of the point rail to obtain L3;
calculating the distance d3 between L1 and L2 and the distance d4 between L1 and L3, judging whether the distances d3 and d4 exceed the distances d30 between L1 and L2 and the distances d40 between L1 and L3 when the points cling to the steel rail, and if any of the distances exceeds the distances d30 between L1 and L3, the point cling is insufficient;
when the point rail is not close enough, di= (d 3-d30+d4-d 40)/2 is calculated as the point rail close gap measurement value, and the average value or the maximum value of the n point rail close gap measurement values Di is taken as the point rail close gap in the detection window.
Further, a switch tongue close contact detection method comprises the following steps:
acquiring steel rail and point rail depth images, respectively finding the steel rail and the point rail from the steel rail depth images and the point rail depth images, and detecting a slide plate;
in the slide plate area, a rectangular detection window is arranged perpendicular to the extending direction of the steel rail, m3 sampling lines are arranged in the detection window perpendicular to the extending direction of the steel rail, and m3 steel rails and point rail profile curves are obtained;
fitting a vertical edge line segment L4 on the inner side of the steel rail according to the position of the edge on the inner side of the steel rail; calculating a point rail waist curve fitting circle center O1 according to the point rail position, and calculating a distance f1 between the circle centers O1 and L4;
for m3 profile curves, m3 measurement results f1 are obtained, whether f1 exceeds the distance e1 when the point rail clings to the steel rail is judged, and if so, the point rail clings inadequately;
when the point rail close contact is insufficient, calculating hi=f1-e 1 as a point rail close contact gap measurement value; the point contact gap measurement hi for m3 points is averaged or maximized as the point contact gap in the detection window.
Further, a switch tongue close contact detection method comprises the following steps:
acquiring steel rail and point rail depth images, respectively finding the steel rail and the point rail from the steel rail depth images and the point rail depth images, and detecting a slide plate area;
a rectangular detection window is arranged in the slide plate area and perpendicular to the extending direction of the steel rail, and a vertical edge plane P1 on the inner side of the steel rail is fitted in the detection window according to the edge position on the inner side of the steel rail;
setting r sampling lines perpendicular to the extending direction of the steel rail in the detection window to obtain r profile curves of the steel rail and the switch rail;
calculating a point rail waist curve fitting circle center O2 according to the point rail position, and calculating the distance si from the circle center O2 to P1; judging whether si exceeds the distance e2 when the point rail clings to the steel rail, if so, judging that the point rail clings inadequately;
when the point rail is not sufficiently close, gi=si-e 2 is calculated as the point rail clearance measurement, and the average value or the maximum value of r point rail close clearance measurements gi is taken as the point rail close clearance measurement result in the detection window.
The beneficial effects of the invention are as follows:
the invention provides an automatic detection system and an automatic detection method based on a visual detection method, which improve an imaging unit in a visual imaging module and can automatically realize insufficient close contact detection and gap quantitative measurement of a switch rail. When the imaging unit is an area-array camera and a surface light source, a clear image of a gap between the high-quality steel rail and the point rail can be obtained by coaxially polishing and arranging the optical axis of the camera right above the inner edge of the steel rail. When the imaging unit is a linear array camera and a linear light source, the cost can be reduced, the measurement resolution of the gap can be increased, the resolution can reach 0.05mm/pixel, and the measurement accuracy of the gap is obviously improved.
The imaging unit is a line structured light 3D camera, texture images and depth images of the steel rail and the point rail can be obtained at the same time, and the detection and measurement of the insufficient adhesion of the steel rail can be realized from multiple dimensions based on the texture images and the depth images. Further, the imaging unit is a line structured light 3D camera, when the 3D camera is installed above the inner side of the steel rail in an inclined manner, the detection system can perform inclined imaging, when the inner side of the steel rail is measured, the inner edge of the steel rail can be clearly imaged, compared with the vertical imaging (the 3D camera is located right above the steel rail), the obtained inner edge data of the steel rail is richer, whether the steel rail is closely attached or not is judged by utilizing the distance between the first step edge plane of the point rail on the edge plane of the inner side of the steel rail, and the detection system has better robustness. The hardware architecture can also be used for measuring the profile of the steel rail, and has the effect of one machine with multiple purposes.
Aiming at the close joint gap measurement requirement, besides edge detection and distance measurement between edges through texture images, the close joint condition is judged through the statistical condition of a plurality of sampling curve measurement results, and the close joint gap measurement method has better robustness.
Furthermore, when the 3D camera is obliquely installed, the straight line/plane, the arc circle center fitting is performed by utilizing the areas such as the straight line/plane of the edge of the point rail and the arc of the point rail, and the distance between the circle center and the straight line/plane is calculated, so that the measuring precision is higher than that of directly measuring the edge distance.
Drawings
FIG. 1 is a schematic diagram of the system components;
FIG. 2 is a camera mounting schematic diagram of embodiment 1;
FIG. 3 is a schematic view of a rail and point rail;
FIG. 4 is a camera mounting schematic diagram of embodiment 5;
FIG. 5 is a schematic view of a point rail seal;
FIG. 6 is a non-stick schematic view of the point rail;
the device comprises a 1-steel rail, a 2-visual imaging module, a 3-imaging control module, a 4-image processing module, a 5-carrying platform, a 6-area camera, a 7-area light source, an 8-area camera optical axis, a 9-steel rail top surface, a 10-steel rail inner edge, a 11-point rail, a 12-sampling window, a 13-steel rail inner edge, a 14-point rail first step edge, a 15-point rail first step bottom plane, a 16-point rail second step edge, a 17-point rail waist and a 18-point rail second step bottom.
Detailed Description
The present invention will be described in detail below with reference to the drawings and examples thereof, but the scope of the present invention is not limited to the examples.
As shown in fig. 5, the rails are closely attached to the switch rails, and no gap exists; as shown in fig. 6, the rail and the tongue rail have a gap in the switch, and cannot be closely attached.
The system for realizing switch tongue close contact detection comprises an imaging control module, a visual imaging module, an image processing module and a carrying platform;
the imaging control module, the image processing module and the carrying platform adopted in the embodiment of the invention are schemes in the prior art. For example, the imaging control module comprises a carrying platform speed measuring unit and an imaging control signal generator, wherein the speed measuring unit accurately measures the speed of the carrying platform; the imaging control signal generator generates an imaging control pulse signal to the vision imaging module according to the imaging resolution requirements of the movement speed and the movement direction of the operation platform. The image processing module is connected with the visual imaging module, receives the switch texture image collected by the visual imaging module, and executes a switch close contact detection algorithm to complete switch close contact detection. The carrying platform is a train or an electric bus or a detection car or a patrol robot or a trolley and provides power supply and installation support for the detection system.
The improvement point of the invention is the improvement of the visual imaging module, the visual imaging module comprises 2 imaging units respectively positioned right above the steel rails at two sides, the steel rails are imaged along the moving direction of the carrying platform, the imaging areas cover the steel rails, the switch rails and the turnout, and the texture image and/or the depth image of the imaging areas are obtained.
The layout of the visual imaging module is different according to the acquired images, and the corresponding detection method is also different, and the following specific embodiments are referred to for specific layout and detection method.
Example 1
The switch tongue close contact detection system of the embodiment, as shown in fig. 1, consists of an imaging control module 3, a visual imaging module 2, an image processing module 4 and a carrying platform 5;
the imaging control module 3 includes: the speed measuring unit is used for accurately measuring the speed of the carrying platform; the speed measuring unit is a wheel speed measuring or radar speed measuring or LDV speed measuring module based on an encoder; the imaging control signal generator generates an imaging control pulse signal to the visual imaging module according to the imaging resolution requirements of the motion speed and the motion direction of the operation platform;
the visual imaging module 2 comprises 2 imaging units positioned right above the steel rails at two sides, images the steel rails along the moving direction of the carrying platform, and the imaging areas cover the steel rails, the switch rails and the turnout to acquire texture images and/or depth images of the imaging areas.
As shown in fig. 2, the imaging unit includes 1 mesa array camera 6 and 1 surface light source 7; the area camera 6 and the area light source 7 are coaxially illuminated, an optical axis 8 of the area camera 6 is positioned right above the inner edge 10 of the steel rail 9, and the imaging unit is arranged for obtaining a clear image of a gap between the high-quality steel rail and the point rail;
the image processing module 4 is connected with the visual imaging module 2, receives the switch texture image acquired by the visual imaging module 2, and executes a switch point close contact detection algorithm to complete switch point close contact detection;
the carrying platform 5 is a train or an electric bus or a detection vehicle or a patrol robot or a trolley and provides power supply and installation support for the detection system.
The switch blade close contact detection method of the embodiment is as follows:
s1, acquiring a steel rail texture image, and detecting a steel rail 8 by adopting an edge extraction method; detecting the switch rail 11 using the switch rail bolt or slide plate information;
s2, after detecting a point rail 11, setting m1 sampling windows 12 with a steel rail 8 as an axis and perpendicular to the extending direction of the steel rail, projecting pixels in the sampling windows along the extending direction of the steel rail, sampling a projection curve in the range of [ -u, u ] with the edge of the inner side of the steel rail as the center on the projection curve, artificially setting two sample sets with less than two close patches, training a classifier by adopting a pattern recognition method, and classifying the sampling curve by the classifier to judge whether the point rail is less than the close patch;
s3, when the point rail is not tightly attached enough, measuring the width of the trough in the sampling projection curve to be used as a point rail tightly attached gap measurement value; taking the mean of the m1 point rail tack clearance measurements (d 1,..dm) as the final tack clearance;
the imaging unit is subjected to imaging calibration, and the physical size of the steel rail plane can be obtained through image pixels.
The sampling window is set in S2 to perform projection, so as to obtain curve data of the gap between the high-quality rail and the point rail, where the curve data can reflect the close contact degree. For artificially constructing two sample set training classifiers of close-fitting and non-close-fitting, whether the two sample set training classifiers are close-fitting or not is judged through a classification method, and compared with a method for directly measuring gaps, the method is easier to realize. S3, the trough width of the projection curve is used as a measurement value of the close-fitting gap, and the method is simple and high-precision.
Example 2
The detection system of the present embodiment is different from embodiment 1 in that the imaging unit 2 is a line camera and a line light source, the line camera and the line light source are illuminated coaxially, the optical center of the line camera is located above the inner edge of the steel rail, the imaging resolution along the moving direction of the carrying platform is not less than 1mm/pixel, and the imaging resolution along the direction perpendicular to the moving direction of the carrying platform is not less than 0.05mm/pixel.
The linear array camera is adopted on the basis of the area array camera and the area array light source, so that the cost can be reduced, and the measurement resolution of the gap can be increased. The resolution of the embodiment reaches 0.05mm/pixel, and the measuring precision of the gap is remarkably improved.
The processing steps of the switch point close contact detection algorithm of this embodiment are as follows:
s1, acquiring a steel rail texture image, and detecting the steel rail by adopting an edge extraction method; detecting the switch rail by using the switch rail bolt or the slide plate information;
s2, detecting the inner side edge of the steel rail and the first step edge of the switch rail in the texture image of the steel rail by adopting an edge extraction method after detecting the switch rail, and setting m2 sampling lines which take the steel rail as an axis and are perpendicular to the extending direction of the steel rail; calculating a width value wi from the inner side edge of the steel rail to the bottom edge of the point rail, and judging that a gap exists in the point rail when wi is more than t; when a gap exists, wi-t=wi' is used as a gap width, t is the width when the point rail is tightly attached to the steel rail, and the average value or the maximum value of m2 gap widths is taken as a point rail close-contact gap measurement value.
As shown in fig. 3, imaging calibration is performed on the top surface 9 of the rail and the bottom plane 15 of the 1 st step of the point rail 11 respectively, and when the actual physical distance is calculated, the position of the edge of the rail is taken as a rail plane calibration parameter, and the position of the edge of the first step of the point rail is taken as a point rail 1 st step bottom plane calibration parameter.
Example 3
The difference of the detection system embodiment 2 of the present embodiment is that the imaging unit is a line structured light 3D camera, the 3D camera is located right above the rail, and scanning imaging is performed on the rail and the point rail region to obtain texture images of the rail and the point rail; the texture image processing method of example 2 was used for point rail contact detection and contact gap measurement by edge detection.
Example 4
The difference of the detection system embodiment 3 of the present embodiment is that the depth images of the rail and the switch rail are obtained by scanning and imaging the rail and the switch rail region; and (3) on the depth image, performing close-fitting detection, wherein the specific steps are as follows:
s1, acquiring a steel rail depth image, finding out a steel rail by adopting a threshold segmentation method according to steel rail height information, finding out the inner edge of the steel rail according to the position of the steel rail, and finding out a slide plate by adopting a deep learning method;
s2, arranging a rectangular detection window in the detected slide plate area perpendicular to the extending direction of the steel rail;
s3, measuring the distance d1 from the inner edge 13 of the steel rail to the first step edge 14 of the point rail and the distance d2 from the inner edge of the steel rail to the second step edge 16 of the point rail in a detection window through a projection and edge extraction method, judging whether the distances d1 and d2 exceed the distance d10 from the inner edge of the steel rail to the first step edge 14 of the point rail and the distance d20 from the inner edge of the steel rail to the second step edge 16 of the point rail when the point rail is closely attached to the steel rail, and if any of the distances exceeds the distance d1 and d2, the point rail is not closely attached sufficiently; s4, when the point rail close contact is insufficient, calculating di= (d 1-d10+d2-d 20)/2 as the point rail close contact gap;
and S5, carrying out the treatment on the plurality of slide plate areas to obtain the point rail close contact state and close contact gap result at each slide plate.
Example 5
The same as the imaging unit of embodiment 4, except that the point rail contact detection method is:
s1, acquiring switch depth images in advance, cutting the images by taking fasteners as units, enabling each image to only contain one row of fasteners, detecting the contact position of a switch rail and a slide plate by adopting a deep learning method, and recording the cut depth images and the contact position of the switch rail and a slide plate mark area as a background database;
s2, collecting a depth image to be detected, cutting a current collected image by taking a background image held in a background database as a reference, and generating a foreground image corresponding to the background database one by one;
s3, acquiring a corresponding prospect and a pre-acquired turnout depth image, judging whether a switch rail close-fitting mark exists in a background database, and acquiring a slide plate mark area at the marked switch rail if the switch rail close-fitting mark exists;
s4, setting a measuring area according to the position of the slide plate, and respectively measuring the width from the outer edge of the steel rail to the bottom edge of the switch rail in a pre-acquired switch depth image and a pre-acquired foreground image;
s5, judging whether a gap exists between the point rail and the steel rail in the foreground image through threshold segmentation, if so, judging whether the point rail is not in close contact, if not, judging whether the width from the outer edge of the steel rail to the bottom edge of the point rail in the foreground image is increased and exceeds the limit, and if so, judging that the point rail is not in close contact.
Example 6
The difference between the detection system of the present embodiment and embodiment 4 is that the 3D camera is installed obliquely above the inner side of the rail, as shown in fig. 4, the line structure light plane is perpendicular to the extending direction of the rail, and the 3D camera measurement area covers the top and inner side of the rail, the top and inner side of the point rail; the measurement precision of the 3D camera in the x and y directions is not lower than 0.1mm, and the measurement precision of the 3D camera in the z direction is not lower than 0.05mm; the switch tongue close contact detection algorithm comprises the following processing steps:
s1, acquiring steel rail and point rail depth images, and respectively finding out steel rail and point rail areas from the steel rail depth images and the point rail depth images; finding out a slide plate area by a deep learning method;
s2, arranging a rectangular detection window in the slide plate area perpendicular to the extending direction of the steel rail;
s3, setting n sampling lines perpendicular to the extending direction of the steel rail in a detection window to obtain n steel rails and point rail profile curves; in the profile curves of the n steel rails and the point rail, performing line segment fitting on the inner edges of the steel rails to obtain L1; performing line segment fitting on the vertical edge of the first step of the point rail to obtain L2, and performing line segment fitting on the vertical edge of the second step of the point rail to obtain L3;
s4, calculating a distance d3 between L1 and L2, a distance d4 between L1 and L3, judging whether the distances d3 and d4 exceed a distance d30 between L1 and L2 when the switch rail is in close contact and a distance d40 between L1 and L3, if any of the distances exceeds the distances, judging that the contact is insufficient, and calculating Di= (d3-d30+d4-d 40)/2 as a switch rail contact gap measurement value; the point contact gap measurements Di for n points are averaged or maximized as point contact gap measurements within the detection window.
According to the embodiment, the inclined imaging is carried out, when the measurement is carried out from the inner side, the inner edge of the steel rail can be clearly imaged, compared with the vertical imaging, the acquired data of the inner edge of the steel rail are richer, the line segment of the inner edge of the steel rail can be fitted, then the circle center is fitted according to the first step curve of the point rail, and the distance from the circle center to the line segment of the inner edge of the steel rail is calculated. Because the inner edge of the steel rail is only provided with one piece of data, noise interference is easy to exist, when the steel rail is obliquely shot, the inner edge of the steel rail is a line segment, and straight line fitting can be carried out.
Example 7
The same imaging unit as in example 6, except that the switch point contact detection algorithm is processed as follows:
s1, collecting depth images of a steel rail and a point rail, finding out the areas of the steel rail and the point rail in the depth images, and finding out a slide plate by a deep learning method;
s2, arranging a rectangular detection window in the slide plate area perpendicular to the extending direction of the steel rail;
s3, setting m3 sampling lines perpendicular to the extending direction of the steel rail in a detection window to obtain m3 steel rails and point rail profile curves; fitting a vertical edge line segment L4 on the inner side of the steel rail according to the position of the edge on the inner side of the steel rail; calculating a point rail waist curve fitting circle center O1 according to the point rail position, and calculating a distance f1 between the circle centers O1 and L4;
s4, obtaining m3 measuring results f1 for m3 profile curves, judging whether f1 exceeds the distance e1 when the point rail clings to the steel rail, judging that the point rail clings to the steel rail if the point rail clings to the steel rail and judging that the point rail clings to the steel rail and the point rail clings to the steel rail, and calculating hi=fi-e 1 as a point rail clinging gap measuring value; the point contact gap measurement hi for m3 points is averaged or maximized as the point contact gap measurement within the detection window.
In S3, the center O1 is fitted to obtain higher accuracy.
Example 8
The same imaging unit as in example 6, except that the switch point contact detection algorithm is processed as follows:
s1, acquiring depth images of a steel rail and a point rail, and finding out the areas of the steel rail and the point rail in the depth images; finding out a slide plate by a deep learning method;
s2, arranging a rectangular detection window in the slide plate area perpendicular to the extending direction of the steel rail;
s3, fitting a vertical edge plane P1 on the inner side of the steel rail according to the edge position on the inner side of the steel rail in the detection window;
s4, setting r sampling lines perpendicular to the extending direction of the steel rail in a detection window to obtain r steel rails and point rail profile curves; calculating a point rail waist curve fitting circle center O2 according to the point rail position, and calculating the distance si from the circle center O2 to P1; judging whether si exceeds the distance e2 when the point rail is tightly attached to the steel rail, if so, judging that the point rail is in insufficient adhesion, and calculating gi=si-e 2 as a point rail adhesion gap measurement value;
and S5, taking the average value or the maximum value of the n measurement results as a point rail close contact gap measurement result in the detection window.
In the embodiment, plane fitting is adopted, and compared with straight line segment fitting in the embodiments 3-5, the noise interference resistance can be further improved.
While the principles of the invention have been described in detail in connection with the preferred embodiments thereof, it should be understood by those skilled in the art that the foregoing embodiments are merely illustrative of the implementations of the invention and are not intended to limit the scope of the invention. The details of the embodiments are not to be taken as limiting the scope of the invention, and any obvious modifications based on equivalent changes, simple substitutions, etc. of the technical solution of the invention fall within the scope of the invention without departing from the spirit and scope of the invention.
Claims (13)
1. The utility model provides a switch tongue close detection system comprises imaging control module, vision imaging module, image processing module and delivery platform, its characterized in that, vision imaging module is including being located 2 imaging unit directly over the rail of both sides respectively, carries out the formation of image to the rail along delivery platform direction of motion, and the formation of image region covers rail, switch tongue, switch, acquires the texture image and/or the depth image of formation of image region.
2. The switch point contact detection system of claim 1 wherein said imaging unit is comprised of an area camera and a surface light source, said area camera and surface light source being illuminated coaxially, the camera optical axis being located directly above the rail inner edge, to obtain a texture image of the imaged area.
3. The switch tongue close contact detection system according to claim 1, wherein the imaging unit is a linear camera and a linear light source, the linear camera and the linear light source are illuminated coaxially, and the optical center of the linear camera is located right above the inner edge of the steel rail, so as to obtain a texture image of the imaging area;
the imaging resolution of the imaging unit along the moving direction of the carrying platform is not lower than 1mm/pixel, and the imaging resolution of the imaging unit along the direction perpendicular to the moving direction of the carrying platform is not lower than 0.05mm/pixel.
4. The switch point contact detection system of claim 1 wherein said imaging unit is a line structured light 3D camera, the 3D camera being positioned directly above the rail to acquire texture images and depth images of the rail and point.
5. The switch tongue close contact detection system according to claim 1, wherein the imaging unit is a line structured light 3D camera, the 3D camera is located obliquely above the inner side of the rail, the line structured light plane is perpendicular to the extending direction of the main rail, the 3D camera measuring area covers the top and inner side of the rail, the top and inner side of the tongue, the measuring precision in the x and y directions of the 3D camera is not lower than 0.1mm, and the measuring precision in the z direction is not lower than 0.05mm.
6. A switch point contact detection method, characterized in that the switch point contact detection system of claim 1 is used for detection, comprising the following steps:
acquiring an image of an imaging region and detecting a first object from the image;
judging whether the point rail is not sufficiently attached or not based on the first object in the acquired imaging area image;
if the point rail is not sufficiently closely attached, calculating a point rail closely attached gap;
wherein the imaging area comprises a steel rail, a switch rail and a turnout;
the image comprises a texture image and/or a depth image.
7. A switch point contact detection method, characterized in that the switch point contact detection system of claim 2 is used for detection, comprising the following steps:
acquiring texture images of an imaging area, and detecting steel rails and switch rails from the images;
after detecting the switch rail, setting m1 sampling windows in the texture image by taking the steel rail as an axis and being perpendicular to the extending direction of the steel rail, projecting pixels in the sampling windows along the extending direction of the steel rail, sampling a projection curve in the range of [ -u, u ] by taking the edge of the inner side of the steel rail as the center on the projection curve, and judging whether the switch rail is not close enough by adopting a classifier based on the sampling curve;
if the point rail is not sufficiently closely attached, measuring the width of a trough in the sampling curve, taking the average value or the maximum value of m1 point rail closely attached gap measurement values as a final point rail closely attached gap;
the method for judging insufficient point rail adhesion by using the classifier comprises the following steps:
two sample sets were manually set: the adhesion is insufficient; training a classifier by adopting a pattern recognition method; and classifying the sampling curve by using a trained classifier, and judging whether the point rail is not sufficiently closely attached or not according to the classification result.
8. A switch point contact detection method, characterized in that the switch point contact detection system according to claim 2 or 3 is used for detection, comprising the following steps:
acquiring texture images of an imaging area, and detecting steel rails and switch rails from the images;
after detecting the switch rail, detecting the inner side edge of the steel rail and the first step edge of the switch rail in a texture image by adopting an edge extraction method, setting m2 sampling lines which are perpendicular to the extending direction of the steel rail by taking the steel rail as an axis, calculating the width value wi from the inner side edge of the steel rail to the bottom edge of the switch rail, and judging that the gap exists in the switch rail when wi is more than t;
when a gap exists, wi-t=wi' is used as the gap width, t is the width when the point rail is tightly attached to the main rail, and the average value or the maximum value of m2 gap widths is taken as the point rail close-contact gap.
9. A switch point contact detection method, characterized in that the switch point contact detection system of claim 4 is used for detection, comprising the following steps:
acquiring a depth image of an imaging area, detecting a steel rail from the image, finding out the inner edge of the steel rail according to the position of the steel rail, and detecting a slide plate by a deep learning method;
setting a rectangular detection window in the detected slide plate area perpendicular to the extending direction of the steel rail, measuring the distance d1 from the inner edge of the steel rail to the first step edge of the point rail and the distance d2 from the inner edge of the steel rail to the second step edge of the point rail in the detection window, judging whether the distances d1 and d2 exceed the distance d10 from the inner edge of the steel rail to the first step edge of the point rail and the distance d20 from the inner edge of the steel rail to the second step edge of the point rail when the point rail is closely attached to the steel rail, and if any one of the distances exceeds the distance d1 from the inner edge of the steel rail to the first step edge of the point rail and the distance d20 from the inner edge of the steel rail to the second step edge of the point rail, the point rail is not closely attached;
when there is insufficient point contact, di= (d1-d10+d2-d 20)/2 is calculated as point contact gap.
10. A switch point contact detection method, characterized in that the switch point contact detection system of claim 4 is used for detection, comprising the following steps:
the method comprises the steps of pre-collecting switch depth images, cutting the images by taking fasteners as units, enabling each image to only contain one row of fasteners, detecting the contact position of a switch rail and a slide plate, and recording the cut pre-collected switch depth images, the contact position of the switch rail and the slide plate mark area as a background database;
collecting a current turnout depth image, cutting the current collected image by taking the turnout depth image collected in advance as a reference, and generating a foreground image corresponding to the background database one by one;
acquiring a corresponding foreground image and a switch depth image acquired in advance, judging whether a switch rail leaning place exists in a background database, and acquiring a slide plate marking area and the switch rail leaning place if the switch rail leaning place exists;
setting a measuring area according to the position of the slide plate, and respectively measuring the width from the outer edge of the steel rail to the bottom edge of the switch rail in a pre-acquired switch depth image and a pre-acquired foreground image;
judging whether a gap exists between the point rail and the steel rail in the foreground image, if so, judging whether the point rail is not in close contact, if not, judging whether the width from the outer edge of the steel rail to the bottom edge of the point rail in the foreground image is increased and overrun, and if so, judging that the point rail is in close contact.
11. A switch point contact detection method, characterized in that the switch point contact detection system of claim 5 is used for detection, comprising the following steps:
acquiring steel rail and point rail depth images, respectively finding the steel rail and the point rail from the steel rail depth images and the point rail depth images, and detecting a slide plate area;
setting rectangular detection windows in the detected slide plate area perpendicular to the extending direction of the steel rail, and setting n sampling lines in the detection windows perpendicular to the extending direction of the steel rail to obtain n steel rails and point rail profile curves;
in the profile curves of n steel rails and the point rail, performing line segment fitting on the inner edge of the steel rail to obtain L1, performing line segment fitting on the vertical edge of the first step of the point rail to obtain L2, and performing line segment fitting on the vertical edge of the second step of the point rail to obtain L3; calculating the distances d3 and d4 of the distances L1 to L2 and the distances L1 to L3, judging whether the distances d3 and d4 exceed the distances d30 and d40 of the distances L1 to L2 and the distances L1 to L3 when the points cling to the steel rail, and if any of the distances exceeds the distances d30 and d40, the point cling is insufficient;
when the point rail is not close enough, di= (d 3-d30+d4-d 40)/2 is calculated as the point rail close gap measurement value, and the average value or the maximum value of the n point rail close gap measurement values Di is taken as the point rail close gap in the detection window.
12. A switch point contact detection method, characterized in that the switch point contact detection system of claim 5 is used for detection, comprising the following steps:
acquiring steel rail and point rail depth images, respectively finding the steel rail and the point rail from the steel rail depth images and the point rail depth images, and detecting a slide plate area;
in the slide plate area, a rectangular detection window is arranged perpendicular to the extending direction of the steel rail, m3 sampling lines are arranged in the detection window perpendicular to the extending direction of the steel rail, and m3 steel rails and point rail profile curves are obtained;
fitting a vertical edge line segment L4 on the inner side of the steel rail according to the position of the edge on the inner side of the steel rail; calculating a point rail waist curve fitting circle center O1 according to the point rail position, and calculating a distance f1 between the circle centers O1 and L4;
for m3 profile curves, m3 measurement results f1 are obtained, whether f1 exceeds the distance e1 when the point rail clings to the main steel rail is judged, and if so, the point rail clings inadequately;
when the point rail close contact is insufficient, calculating hi=f1-e 1 as a point rail close contact gap measurement value; the point contact gap measurement hi for m3 points is averaged or maximized as the point contact gap in the detection window.
13. A switch point contact detection method, characterized in that the switch point contact detection system of claim 5 is used for detection, comprising the following steps:
acquiring steel rail and point rail depth images, respectively finding the steel rail and the point rail from the steel rail depth images and the point rail depth images, and detecting a slide plate area;
a rectangular detection window is arranged in the slide plate area and perpendicular to the extending direction of the steel rail, and a vertical edge plane P1 on the inner side of the steel rail is fitted in the detection window according to the edge position on the inner side of the steel rail;
setting r sampling lines perpendicular to the extending direction of the steel rail in the detection window to obtain r profile curves of the steel rail and the switch rail;
calculating a point rail waist curve fitting circle center O2 according to the point rail position, and calculating the distance si from the circle center O2 to P1; judging whether si exceeds the distance e2 when the point rail clings to the steel rail, if so, judging that the point rail clings inadequately;
when the point rail is not sufficiently close, gi=si-e 2 is calculated as the point rail close clearance measurement value, and the average value or the maximum value of r point rail close clearance measurement values gi is taken as the point rail close clearance measurement result in the detection window.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310990812.4A CN116923481A (en) | 2023-05-25 | 2023-05-25 | Switch tongue close contact detection method based on depth image and texture image |
| CN202310595620.3A CN116279650B (en) | 2023-05-25 | 2023-05-25 | Switch tongue close contact detection method and system |
| CN202310990810.5A CN116872997A (en) | 2023-05-25 | 2023-05-25 | Switch tongue close contact detection method based on texture image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310595620.3A CN116279650B (en) | 2023-05-25 | 2023-05-25 | Switch tongue close contact detection method and system |
Related Child Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310990810.5A Division CN116872997A (en) | 2023-05-25 | 2023-05-25 | Switch tongue close contact detection method based on texture image |
| CN202310990812.4A Division CN116923481A (en) | 2023-05-25 | 2023-05-25 | Switch tongue close contact detection method based on depth image and texture image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116279650A true CN116279650A (en) | 2023-06-23 |
| CN116279650B CN116279650B (en) | 2023-08-18 |
Family
ID=86819002
Family Applications (3)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310990812.4A Pending CN116923481A (en) | 2023-05-25 | 2023-05-25 | Switch tongue close contact detection method based on depth image and texture image |
| CN202310595620.3A Active CN116279650B (en) | 2023-05-25 | 2023-05-25 | Switch tongue close contact detection method and system |
| CN202310990810.5A Pending CN116872997A (en) | 2023-05-25 | 2023-05-25 | Switch tongue close contact detection method based on texture image |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310990812.4A Pending CN116923481A (en) | 2023-05-25 | 2023-05-25 | Switch tongue close contact detection method based on depth image and texture image |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310990810.5A Pending CN116872997A (en) | 2023-05-25 | 2023-05-25 | Switch tongue close contact detection method based on texture image |
Country Status (1)
| Country | Link |
|---|---|
| CN (3) | CN116923481A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014001048A2 (en) * | 2012-06-29 | 2014-01-03 | Siemens Aktiengesellschaft | Device for testing and refurbishing a switch mechanism for a railway switch |
| CN111144235A (en) * | 2019-12-10 | 2020-05-12 | 通控研究院(安徽)有限公司 | Video-based switch blade crawling monitoring method |
| CN212637504U (en) * | 2020-05-19 | 2021-03-02 | 湖南大学 | Railway switch displacement laser marking visual on-line detection device |
| CN113320447A (en) * | 2021-07-13 | 2021-08-31 | 魏运 | Track-contact net equipment health state integration comprehensive detection robot |
| CN114312905A (en) * | 2021-11-25 | 2022-04-12 | 广州智为科技发展有限公司 | Switch point rail form image real-time supervision device |
| CN114771601A (en) * | 2022-04-18 | 2022-07-22 | 西安铁路信号有限责任公司 | Method for monitoring displacement of indicating rod of close-contact checker |
-
2023
- 2023-05-25 CN CN202310990812.4A patent/CN116923481A/en active Pending
- 2023-05-25 CN CN202310595620.3A patent/CN116279650B/en active Active
- 2023-05-25 CN CN202310990810.5A patent/CN116872997A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014001048A2 (en) * | 2012-06-29 | 2014-01-03 | Siemens Aktiengesellschaft | Device for testing and refurbishing a switch mechanism for a railway switch |
| CN111144235A (en) * | 2019-12-10 | 2020-05-12 | 通控研究院(安徽)有限公司 | Video-based switch blade crawling monitoring method |
| CN212637504U (en) * | 2020-05-19 | 2021-03-02 | 湖南大学 | Railway switch displacement laser marking visual on-line detection device |
| CN113320447A (en) * | 2021-07-13 | 2021-08-31 | 魏运 | Track-contact net equipment health state integration comprehensive detection robot |
| CN114312905A (en) * | 2021-11-25 | 2022-04-12 | 广州智为科技发展有限公司 | Switch point rail form image real-time supervision device |
| CN114771601A (en) * | 2022-04-18 | 2022-07-22 | 西安铁路信号有限责任公司 | Method for monitoring displacement of indicating rod of close-contact checker |
Non-Patent Citations (1)
| Title |
|---|
| 张宇宁;谢琦;: "一种基于机器视觉的铁路道岔检测方法", 计算机应用与软件, no. 01, pages 157 - 47 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116923481A (en) | 2023-10-24 |
| CN116279650B (en) | 2023-08-18 |
| CN116872997A (en) | 2023-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107678036B (en) | Vehicle-mounted non-contact type contact net geometric parameter dynamic detection system and method | |
| CN109658397A (en) | A kind of rail polling method and system | |
| ES2910068T3 (en) | Mobile and automated device for the detection and classification of damage to the bodywork of a vehicle | |
| CN103217111B (en) | A kind of non-contact contact line geometric parameter detection method | |
| CN111666947B (en) | Pantograph head offset measuring method and system based on 3D imaging | |
| CN108778889B (en) | Method and measuring system for detecting a fixed point beside a track | |
| CN109238756B (en) | Dynamic image detection equipment and detection method for freight car operation fault | |
| CN111198371A (en) | Forward-looking obstacle detection system | |
| CN109269403A (en) | A kind of contact line conducting wire measurement of wear method and device based on machine vision | |
| CN114581437A (en) | Visual inspection system for visual track guided by visual identification | |
| CN116279650B (en) | Switch tongue close contact detection method and system | |
| CN108596968B (en) | Sleeper counting method based on track 3D depth image | |
| CN112964195B (en) | Power supply rail geometric parameter comprehensive detection method and system based on laser triangulation method | |
| CN106951820A (en) | Passenger flow statistical method based on annular template and ellipse fitting | |
| CN114279335A (en) | Trackside limit measuring method and device | |
| CN116631187B (en) | Intelligent acquisition and analysis system for case on-site investigation information | |
| CN111640155B (en) | Pantograph head inclination angle measurement method and system based on 3D imaging | |
| CN108846824B (en) | Linear array scanning image sleeper positioning and counting method based on gradient projection | |
| CN105480256B (en) | A kind of high-speed railway rail measuring device and measuring method | |
| CN112883778B (en) | Road well lid height difference identification method and equipment based on computer vision | |
| CN114659457A (en) | Track gauge dynamic measurement method based on structured light | |
| CN116109638B (en) | Rail break detection method and system | |
| CN116152237B (en) | Method and system for detecting flaking and falling blocks of steel rail | |
| Srinivasan et al. | Development of a railroad track inspection system based on visual perception using labview | |
| CN216208691U (en) | Train tread defect detection system |
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 |