CN115100519A - Method for identifying hidden danger along high-speed rail - Google Patents
Method for identifying hidden danger along high-speed rail Download PDFInfo
- Publication number
- CN115100519A CN115100519A CN202210717660.6A CN202210717660A CN115100519A CN 115100519 A CN115100519 A CN 115100519A CN 202210717660 A CN202210717660 A CN 202210717660A CN 115100519 A CN115100519 A CN 115100519A
- Authority
- CN
- China
- Prior art keywords
- area
- suspected
- line
- coordinate
- judging
- 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
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000005070 sampling Methods 0.000 claims abstract description 17
- 239000000428 dust Substances 0.000 claims description 15
- 230000001629 suppression Effects 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 9
- 230000002093 peripheral effect Effects 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 5
- 238000013459 approach Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 3
- 208000012260 Accidental injury Diseases 0.000 abstract 1
- 208000014674 injury Diseases 0.000 abstract 1
- 238000010276 construction Methods 0.000 description 3
- 229920003023 plastic Polymers 0.000 description 2
- 208000034699 Vitreous floaters Diseases 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 235000005770 birds nest Nutrition 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 125000000391 vinyl group Chemical group [H]C([*])=C([H])[H] 0.000 description 1
- 229920002554 vinyl polymer Polymers 0.000 description 1
- 235000005765 wild carrot Nutrition 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- 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
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Image Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to the field of detection methods of power supply equipment of high-speed rails, in particular to a method for identifying hidden dangers along the high-speed rails. The method aims to solve the problem that in the prior art, hidden dangers near power supply equipment along a high-speed rail are difficult to identify. The method comprises image acquisition; selecting an initial acquisition area of the overhead line system on the acquired image; analyzing the pixel points line by line in the initial acquisition area, and judging a suspected hidden danger area; statistically identifying identifiable line types in the suspected foreign area to form a key observation area; and (4) judging the type of the foreign matters according to the line type condition of the key observation area, and giving a system prompt. Has the advantages that: the method for identifying the hidden dangers along the high-speed rail samples the high-speed rail along the route, and the sampling is convenient; the characteristics of the hidden danger area are combined, the identification of the hidden danger is formed, the identification efficiency is high, the accidental injury degree is low, the identification is quick, and the cost is low.
Description
Technical Field
The invention relates to a detection method of high-speed rail power supply equipment, in particular to a method for identifying potential hazards along a high-speed rail.
Background
The power supply system is a system which is composed of a power supply system and a power transmission and distribution system and is used for generating electric energy and supplying and delivering the electric energy to electric equipment. In a long-distance power supply system, the problem that line equipment is damaged and difficult to overhaul is often faced, such as common bird nest building, line weathering hanging-up, line abrasion and the like.
The contact net foreign matter is hung on the contact net, so that the contact net is greatly damaged. Accidents caused by hanging high-speed rail contact networks on foreign matters such as kites and the like easily cause train night time. The contact net is characterized by open erection and no reserve. Farmer's (mulching) mulching films, dust screens on construction sites, vinyl houses, plastic packaging bags, kite lines and the like, which float with strong wind when the wind is strong, are called floats. At the present stage, a person generally gets on a vehicle and adds (inspects) to find foreign matters or floaters of the kind, and meanwhile, the foreign matters exist in two situations, one situation is that the foreign matters are blown up by wind and hung on a contact net and are urgently needed to be solved, and the other situation is that the foreign matters are located on the ground and do not float, in the situation, the contact net is transient and safe, but does not accord with relevant safety standards, so that great potential safety hazards are generated, a safety inspection party and a construction party are urgently needed to coordinate and correct as soon as possible, and at the present stage, equipment which can quickly react and find illegal building behaviors is lacked.
Although, we can also adopt some scientific means, such as finding the foreign object by satellite image comparison. In the prior art, the identification of the foreign matters on the contact network is relatively difficult, and the cost of satellite identification is too high. Relevant technicians propose identifying according to the unmanned aerial vehicle, but the unmanned aerial vehicle has short endurance time, high difficulty in identifying photos in the later period and complex procedure.
Disclosure of Invention
The invention aims to solve the problem of high cost in illegal construction along a high-speed rail line in the prior art.
The specific scheme of the invention is as follows:
a method for identifying potential hazards along a high-speed rail is designed, and comprises the following steps:
(1) image acquisition, namely installing a shooting and recording device outside the head of a carriage of the high-speed rail, and carrying out shooting image acquisition every 0.2 to 0.5 seconds to form an acquired image when the high-speed rail runs to more than 150KM/h, wherein the acquired image is input into an image processing system through communication or a timing hard disk to start recognition and screening;
(2) finding a catenary on the acquired image: transversely checking approach pixel points by taking a single pixel as a unit from the lower right corner to the upper left corner of an acquired image, when more than two continuous coordinate dark points with similar pixel values and different pixel values from surrounding points are found in a single-line range, judging that the coordinate dark point group is a suspected contact net line initial point group, obtaining each contact net line initial point group, combining at least 3 adjacent lines, judging that the longitudinal coordinate difference of starting and ending points between the initial point groups of all the lines is less than 5 coordinate units and the distance difference is less than 2 coordinate units, judging that the contact net type is suspected, connecting along each adjacent contact net type, when the suspected contact net type is in a continuous state and the total number of lines exceeds 1/4 of a picture, determining that a graph connected with the contact net type is a suspected contact net area, and then taking 100 or less coordinate units on both sides of each contact net area as an extension area on the suspected contact net area, the whole expanded area is divided into a contact net area;
(2) finding the vertical pole on the acquired image: in the collected image, a secondary scanning area is set below the contact network area shown in the step (1), in the secondary scanning area, the lower right corner starts to be in the upper left corner direction, path pixel points are transversely checked by taking a single pixel as a unit, when more than two continuous coordinate dark points with similar pixel values and different pixel values from peripheral points appear in a single-line range, the coordinate dark point group is judged to be a suspected upright rod initial point group, after each upright rod initial point group is obtained, at least 3 adjacent lines are combined, when the starting point and the ending point longitudinal coordinate difference between each line initial point group is judged to be less than 5 coordinate units, and when the distance difference is less than 2 coordinate units, the suspected upright rod is judged, and an area in the upright rod is divided into the suspected upright rod area;
(3) finding the rail on the acquired image: in the collected image, starting from the middle lower right corner to the upper left corner of two vertical rod areas corresponding to horizontal positions, transversely checking path pixel points by taking a single pixel as a unit, when coordinate dark points with the pixel values similar to more than two continuous pixels and different from the pixel values of peripheral points appear in a single-line range, judging that the coordinate dark point group is a suspected rail initial point group, obtaining each rail initial point group, then combining at least 3 adjacent lines, judging that when the starting point and the ending point longitudinal coordinate difference between the initial point groups of each line is less than 5 coordinate units and the distance difference is less than 2 coordinate units, judging that the rail is suspected, and when two suspected rails appear in single-line sampling, dividing areas in the two suspected rails into rail areas;
(4) analyzing pixel points in the initial acquisition area line by line, and judging a suspected foreign area: screening out the contact screen area and the upright pole area in an acquired image, setting the rest area as an acquisition area, starting from the lower right corner to the upper left corner in the acquisition area, transversely checking pixel points of a route by taking a single pixel as a unit, acquiring unit coordinate point pixel information line by line, when the edge point of the acquisition area and the adjacent point do not accord with each other in color, defining a secondary sampling range by taking the distance of 2 to 19 pixels as a radius, checking upwards along a check column in the step (2) in the secondary sampling range to form dark point distribution data line by line, then analyzing the data, and judging as a suspected boundary when the dark point area of the lower check column in the sampling area forms a straight line; then further enlarging the measuring pixel distance until the measuring pixel distance is contacted with the straight line and the vertical rod or the track or the boundary of the area, and judging as foreign matters of the mulching film and the dust suppression net;
(4) in step (3), after the pseudo-boundary is determined, the measurement pixel distance is further increased until a closed edge is formed, and it is determined that the nearby work machine is present
(5) And (5) transmitting a result, transmitting the results of the steps (4) and (5) to a master server, and guiding workers to clean.
And counting the inclined angle of the suspected boundary, and judging that the suspected boundary is suspected to further distinguish plateau earthwork or surrounding trees when the horizontal inclined angle is larger than 70 degrees.
And further counting the pixel color information of each coordinate point in the foreign matter outline, and when the color is white and the color outside the edge is blue, determining that the foreign matter outline is white cloud, and marking the foreign matter outline as suspected.
In the step (2), when the implementation and closed curve of the mulching film and the dust suppression net are staggered in the measurement result in the step (4), the mulching film and the dust suppression net are judged to be foreign matters with the weight.
When the color difference between the inside and the outside of the contour is less than 50, the foreign matter contour is judged to be a mulching film; when the contour is green, the dust suppression net is judged, and when the contour is yellow or blue, the engineering vehicle is judged.
The invention has the beneficial effects that:
a set of method for identifying hidden dangers along a high-speed rail is designed, firstly, sampling is convenient, an unmanned aerial vehicle is not needed to participate, a sampling device is directly hung outside a carriage of the high-speed rail, the line can be illuminated when the line comes down, secondly, foreign matters are identified for workers, and the workers in the district station can be immediately informed to maintain after verification;
thirdly, a set of complete image screening method is provided, and a method for reducing a sampling area can be added in the method, so that the image processing memory of an image processing background is saved, and the running speed of equipment is increased;
in the detection method, the condition and the type of the foreign matters can be analyzed in time by combining the characteristics of each foreign matter, the judgment of the type of the foreign matters is given to workers in real time by combining the reference with the database, and the safety management personnel are effectively guided to make further judgment quickly.
Drawings
FIG. 1 is an example of an image collected in step (1) of the present invention;
A. a contact screen area; 1. a machineshop truck; 2. mulching films or dust suppression nets.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
Example 1
A method for identifying potential hazards along a high-speed rail, see figures 1 to,
the method comprises the following steps:
(1) image acquisition, namely installing a shooting and recording device outside the head of a carriage of the high-speed rail, and carrying out shooting image acquisition every 0.2 to 0.5 seconds to form an acquired image when the high-speed rail runs to more than 150KM/h, wherein the acquired image is input into an image processing system through communication or a timing hard disk to start recognition and screening;
(2) finding a catenary on the acquired image: transversely checking approach pixel points by taking a single pixel as a unit from the lower right corner to the upper left corner of an acquired image, judging that a coordinate dark point group is a suspected contact net line initial point group when more than two continuous coordinate dark points with similar pixel values and different pixel values from peripheral points appear in a single-line range, combining at least 3 adjacent lines after obtaining each contact net line initial point group, judging that a suspected contact net type is judged when the longitudinal coordinate difference of starting and ending points between the initial point groups of all the lines is less than 5 coordinate units and the distance difference is less than 2 coordinate units, then connecting along each adjacent contact net type, when the suspected contact net type is in a continuous state and the total number of lines exceeds 1/4 of a picture plane, determining a graph connected with the contact net type as a suspected contact net area, and then taking the coordinate units below 100 sides of each contact net area on the suspected contact net area as an extension area, the whole expanded area is divided into a contact net area;
(2) finding the vertical pole on the acquired image: in the collected image, a secondary scanning area is set below the contact network area shown in the step (1), in the secondary scanning area, the lower right corner starts to be in the upper left corner direction, path pixel points are transversely checked by taking a single pixel as a unit, when more than two continuous coordinate dark points with similar pixel values and different pixel values from peripheral points appear in a single-line range, the coordinate dark point group is judged to be a suspected upright rod initial point group, after each upright rod initial point group is obtained, at least 3 adjacent lines are combined, when the starting point and the ending point longitudinal coordinate difference between each line initial point group is judged to be less than 5 coordinate units, and when the distance difference is less than 2 coordinate units, the suspected upright rod is judged, and an area in the upright rod is divided into the suspected upright rod area;
(3) find the rail on the captured image: in the collected image, starting from the middle lower right corner to the upper left corner of two vertical rod areas corresponding to horizontal positions, transversely checking path pixel points by taking a single pixel as a unit, when coordinate dark points with the pixel values similar to more than two continuous pixels and different from the pixel values of peripheral points appear in a single-line range, judging that the coordinate dark point group is a suspected rail initial point group, obtaining each rail initial point group, then combining at least 3 adjacent lines, judging that when the starting point and the ending point longitudinal coordinate difference between the initial point groups of each line is less than 5 coordinate units and the distance difference is less than 2 coordinate units, judging that the rail is suspected, and when two suspected rails appear in single-line sampling, dividing areas in the two suspected rails into rail areas;
(4) analyzing pixel points in the initial acquisition area line by line, and judging a suspected foreign area: screening out the contact net area and the upright pole area in an acquired image, setting the rest area as an acquisition area, starting from the lower right corner to the upper left corner in the acquisition area, transversely checking pixel points of a way by taking a single pixel as a unit, acquiring unit coordinate point pixel information line by line, when the color of an edge point of the acquisition area is not consistent with that of an adjacent point, defining a secondary sampling range by taking the distance of 2 to 19 pixels as a radius, checking upwards along a check column in the step (2) line by line in the secondary sampling range to form dark point distribution data, then analyzing the data, and judging as a suspected boundary when the dark point area of the lower check column in the sampling area forms a straight line; then further enlarging the distance of the measuring pixels until the distance is in contact with the straight line and the vertical rod or the track or the boundary of the area, and judging as foreign matters of the mulching film and the dust suppression net;
(4) in step (3), after the pseudo-boundary is determined, the measurement pixel distance is further increased until a closed edge is formed, and it is determined that the nearby work machine is present
(5) And (5) transmitting the result, namely transmitting the results of the steps (4) and (5) to a master server to guide workers to clean. In the step (2), when the implementation and the closed curve of the mulching film and the dust suppression net are staggered in the measurement result in the step (4), the mulching film and the dust suppression net with the weight are judged to be foreign matters.
In the working process, firstly, photographing and sampling are carried out, images are transmitted to a server in real time or at regular time, the photographing scene among all the photos is approximately 200 meters, the whole line can be basically covered, then, scanning is carried out one by one, contact nets, vertical rods and rails are sequentially screened out, hidden dangers along the lines such as mulching films and dust suppression nets are screened out in related areas, meanwhile, a set of screening equipment is introduced, and redundant data such as blue sky white clouds, airplane flying birds and the like are screened out.
The invention identifies the hidden danger accurately according to the position characteristics of the hidden danger objects, provides accurate guidance for workers, and can even realize the cooperative solution of remote telephone contact with related departments, thereby improving the problem processing efficiency and reducing the potential safety hazard of the high-speed rail electric network operation.
Example 2
The principle is the same as that of the embodiment 1, and the specific difference is that in the embodiment 1, when the difference between the inside and outside color of the outline is less than 50, the outline is judged to be the mulching film; the method comprises the steps of judging that a dust suppression net is a green net when the outline is inside, judging that an engineering truck has a yellow or blue outline, wherein an algorithm thought in the application is that dark points in an image are found at first, the outline is formed at the same time, further counting graphs of the outline in line-by-line scanning, and then automatically screening whether the counted graphs are plane-shaped or bird-shaped and possibly belong to misjudgment if the graphs are judged to be plane-shaped or bird-shaped in the process of contacting foreign matters hung on the net by combining the intersection condition of the graphs and the contact net.
In this embodiment, the pixel color information of each coordinate point in the foreign object outline is further counted, and when the color is white and the color outside the edge is blue, it is determined as a white cloud, and the mark is suspected.
Embodiment 3 is the same as embodiment 1 in principle, except that the inclination angle of the suspected boundary is counted, and when the horizontal inclination angle is greater than 70 degrees, it is determined that the suspected boundary is suspected to further distinguish plateau-type earthwork or surrounding trees.
By considering the color of the foreign matters, the misjudgment of the white clouds under the sunny condition and the misjudgment of the plastic bags under the cloudy condition are effectively avoided.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (5)
1. A method for identifying hidden dangers along a high-speed rail is characterized by comprising the following steps:
(1) image acquisition, namely installing a shooting and recording device outside the head of a carriage of the high-speed rail, and carrying out shooting image acquisition every 0.2 to 0.5 seconds to form an acquired image when the high-speed rail runs to more than 150KM/h, wherein the acquired image is input into an image processing system through communication or a timing hard disk to start recognition and screening;
(2) finding a catenary on the acquired image: transversely checking approach pixel points by taking a single pixel as a unit from the lower right corner to the upper left corner of an acquired image, when more than two continuous coordinate dark points with similar pixel values and different pixel values from surrounding points are found in a single-line range, judging that the coordinate dark point group is a suspected contact net line initial point group, obtaining each contact net line initial point group, combining at least 3 adjacent lines, judging that the longitudinal coordinate difference of starting and ending points between the initial point groups of all the lines is less than 5 coordinate units and the distance difference is less than 2 coordinate units, judging that the contact net type is suspected, connecting along each adjacent contact net type, when the suspected contact net type is in a continuous state and the total number of lines exceeds 1/4 of a picture, determining that a graph connected with the contact net type is a suspected contact net area, and then taking 100 or less coordinate units on both sides of each contact net area as an extension area on the suspected contact net area, the whole expanded area is divided into a contact net area;
(2) finding the vertical pole on the acquired image: in the collected image, a secondary scanning area is set below the contact network area shown in the step (1), in the secondary scanning area, the lower right corner starts to be in the upper left corner direction, path pixel points are transversely checked by taking a single pixel as a unit, when more than two continuous coordinate dark points with similar pixel values and different pixel values from peripheral points appear in a single-line range, the coordinate dark point group is judged to be a suspected upright rod initial point group, after each upright rod initial point group is obtained, at least 3 adjacent lines are combined, when the starting point and the ending point longitudinal coordinate difference between each line initial point group is judged to be less than 5 coordinate units, and when the distance difference is less than 2 coordinate units, the suspected upright rod is judged, and an area in the upright rod is divided into the suspected upright rod area;
(3) find the rail on the captured image: in the collected image, starting from the middle lower right corner to the upper left corner of two vertical rod areas corresponding to horizontal positions, transversely checking path pixel points by taking a single pixel as a unit, when coordinate dark points with the pixel values similar to more than two continuous pixels and different from the pixel values of peripheral points appear in a single-line range, judging that the coordinate dark point group is a suspected rail initial point group, obtaining each rail initial point group, then combining at least 3 adjacent lines, judging that when the starting point and the ending point longitudinal coordinate difference between the initial point groups of each line is less than 5 coordinate units and the distance difference is less than 2 coordinate units, judging that the rail is suspected, and when two suspected rails appear in single-line sampling, dividing areas in the two suspected rails into rail areas;
(4) analyzing pixel points in the initial acquisition area line by line, and judging a suspected foreign area: screening out the contact net area and the upright pole area in an acquired image, setting the rest area as an acquisition area, starting from the lower right corner to the upper left corner in the acquisition area, transversely checking pixel points of a way by taking a single pixel as a unit, acquiring unit coordinate point pixel information line by line, when the color of an edge point of the acquisition area is not consistent with that of an adjacent point, defining a secondary sampling range by taking the distance of 2 to 19 pixels as a radius, checking upwards along a check column in the step (2) line by line in the secondary sampling range to form dark point distribution data, then analyzing the data, and judging as a suspected boundary when the dark point area of the lower check column in the sampling area forms a straight line; then further enlarging the distance of the measuring pixels until the distance is in contact with the straight line and the vertical rod or the track or the boundary of the area, and judging as foreign matters of the mulching film and the dust suppression net;
(4) in the step (3), after the suspected boundary is determined, the measuring pixel distance is further expanded until a closed edge is formed, and the nearby working machine is judged;
(5) and (5) transmitting the result, namely transmitting the results of the steps (4) and (5) to a master server to guide workers to clean.
2. The method for identifying the potential hazards along the line of the high-speed rail as recited in claim 1, wherein: and counting the inclination angle of the suspected boundary, and when the horizontal inclination angle is larger than 70 degrees, judging that the suspected boundary is suspected to further distinguish the plateau earthwork or the surrounding trees.
3. The method for identifying the potential hazards along the high-speed rail as claimed in claim 1, wherein: and further counting the pixel color information of each coordinate point in the foreign matter outline, and when the color is white and the color outside the edge is blue, determining that the foreign matter outline is white cloud, and marking the foreign matter outline as suspected.
4. The method for identifying the potential hazards along the line of the high-speed rail as recited in claim 3, wherein: in the step (2), when the implementation and the closed curve of the mulching film and the dust suppression net are staggered in the measurement result in the step (4), the mulching film and the dust suppression net with the weight are judged to be foreign matters.
5. The method for identifying the potential hazards along the line of the high-speed rail as recited in claim 4, wherein: when the color difference between the inside and the outside of the contour is less than 50, the foreign matter contour is judged to be a mulching film; when the contour is green, the dust suppression net is judged, and when the contour is yellow or blue, the engineering vehicle is judged.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210717660.6A CN115100519B (en) | 2022-06-23 | 2022-06-23 | Method for identifying hidden danger objects along high-speed rail |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210717660.6A CN115100519B (en) | 2022-06-23 | 2022-06-23 | Method for identifying hidden danger objects along high-speed rail |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115100519A true CN115100519A (en) | 2022-09-23 |
| CN115100519B CN115100519B (en) | 2024-04-26 |
Family
ID=83292133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210717660.6A Active CN115100519B (en) | 2022-06-23 | 2022-06-23 | Method for identifying hidden danger objects along high-speed rail |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115100519B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112911221A (en) * | 2021-01-15 | 2021-06-04 | 欧冶云商股份有限公司 | Remote live-action storage supervision system based on 5G and VR videos |
| CN113947731A (en) * | 2021-12-21 | 2022-01-18 | 成都中轨轨道设备有限公司 | Foreign matter identification method and system based on contact net safety inspection |
| CN114266893A (en) * | 2021-12-22 | 2022-04-01 | 智洋创新科技股份有限公司 | Smoke and fire hidden danger identification method and device |
| CN114419825A (en) * | 2022-03-29 | 2022-04-29 | 中国铁路设计集团有限公司 | High-speed rail perimeter intrusion monitoring device and method based on millimeter wave radar and camera |
-
2022
- 2022-06-23 CN CN202210717660.6A patent/CN115100519B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112911221A (en) * | 2021-01-15 | 2021-06-04 | 欧冶云商股份有限公司 | Remote live-action storage supervision system based on 5G and VR videos |
| CN113947731A (en) * | 2021-12-21 | 2022-01-18 | 成都中轨轨道设备有限公司 | Foreign matter identification method and system based on contact net safety inspection |
| CN114266893A (en) * | 2021-12-22 | 2022-04-01 | 智洋创新科技股份有限公司 | Smoke and fire hidden danger identification method and device |
| CN114419825A (en) * | 2022-03-29 | 2022-04-29 | 中国铁路设计集团有限公司 | High-speed rail perimeter intrusion monitoring device and method based on millimeter wave radar and camera |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115100519B (en) | 2024-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112884931B (en) | Unmanned aerial vehicle inspection method and system for transformer substation | |
| CN109376605B (en) | Electric power inspection image bird-stab-prevention fault detection method | |
| CN106504362A (en) | Power transmission and transformation system method for inspecting based on unmanned plane | |
| CN112633535A (en) | Photovoltaic power station intelligent inspection method and system based on unmanned aerial vehicle image | |
| CN111080598B (en) | Bolt and nut missing detection method for coupler yoke key safety crane | |
| CN106657882A (en) | Real-time monitoring method for power transmission and transformation system based on unmanned aerial vehicle | |
| CN108280855A (en) | A kind of insulator breakdown detection method based on Fast R-CNN | |
| CN107392247A (en) | Atural object safe distance real-time detection method below a kind of power line | |
| CN109829908B (en) | Binocular image-based method and device for detecting safety distance of ground object below power line | |
| CN103745224A (en) | Image-based railway contact net bird-nest abnormal condition detection method | |
| CN109766746A (en) | A kind of track foreign matter detecting method of unmanned plane video | |
| CN108332927A (en) | A kind of bridge surface crack detection device | |
| CN114248819B (en) | Railway intrusion foreign matter unmanned aerial vehicle detection method, device and system based on deep learning | |
| CN112101088A (en) | Automatic unmanned aerial vehicle power inspection method, device and system | |
| CN112528979B (en) | Transformer substation inspection robot obstacle distinguishing method and system | |
| CN113947731A (en) | Foreign matter identification method and system based on contact net safety inspection | |
| CN111695506A (en) | Wind-induced foreign matter short-circuit fault early warning method and system for power transmission line | |
| Nardinocchi et al. | Fully automatic point cloud analysis for powerline corridor mapping | |
| CN113378754B (en) | Bare soil monitoring method for construction site | |
| CN109325911B (en) | Empty base rail detection method based on attention enhancement mechanism | |
| CN116740833A (en) | Line inspection and card punching method based on unmanned aerial vehicle | |
| CN112033393A (en) | Three-dimensional route planning method and device based on laser radar point cloud data | |
| CN115100519A (en) | Method for identifying hidden danger along high-speed rail | |
| CN112861737A (en) | Forest fire smoke detection method based on image dark channel and YoLov3 | |
| CN111079743A (en) | Data acquisition method based on automatic insulator identification of unmanned aerial vehicle aerial photography data |
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 |