CN106954042B - Unmanned aerial vehicle railway line inspection device, system and method - Google Patents

Abstract

An unmanned aerial vehicle railway line inspection device, system and method. The device comprises: unmanned aerial vehicle, unmanned aerial vehicle controller, camera, controller, display; the unmanned aerial vehicle controller is arranged on the unmanned aerial vehicle; the cameras comprise at least two groups, at least one group of cameras are installed on the unmanned aerial vehicle, and at least one group of cameras are installed in the railway tunnel; the camera is used for acquiring on-site image data of the railway line, and the on-site image data comprise images and coordinates of the railway line; the controller is connected with the camera and used for receiving, processing and monitoring the field image data acquired by the camera; the controller is connected with the unmanned aerial vehicle controller and is used for controlling the unmanned aerial vehicle controller to set flight parameters of the unmanned aerial vehicle; the display is used for displaying the image data output by the controller. The invention realizes the inspection of the railway lines inside and outside the tunnel, and can carry out the post-processing and monitoring on the collected image data, thereby more accurately judging and positioning the fault point of the railway line.

Description

A device, system and method for unmanned aerial vehicle inspection of railway lines

technical field

The invention relates to the field of railway line inspection, in particular to an unmanned aerial vehicle inspection device, system and method for railway lines.

Background technique

In the railway bureau system, to ensure the safety of railway traffic, railway line inspection is an indispensable daily work. At present, the existing inspection of railway lines relies entirely on the way that railway line inspection workers inspect the railway tracks along the railway line. This inspection method has huge limitations and defects. For example, inspection workers inspect a 1-kilometer railway line It takes about 1 hour, resulting in a long inspection time; inspections are still required in harsh environments such as rain, ice, snow, and high temperature, resulting in high labor intensity for inspection workers; during inspections, trains often pass by inspection sites, etc. , there are unsafe factors. Therefore, this inspection method is no longer suitable for inspection operations on existing railway lines, nor does it meet the safety requirements for high-speed railway line operations.

The UAV railway inspection system solves the problems of manual inspection, but the tunnel railway line is a special section of the railway line, and more attention should be paid to the inspection frequency of its damage and defects, but no solution has been proposed in the prior art Method. In the existing drone inspection technology for railway lines, due to the low light intensity in the tunnel and the low tunnel height, the flying height of the drone is too low and the safety is not high enough, so the drone cannot inspect the railway lines in the tunnel . And in the prior art, there is no post-processing on the photos taken by the drone, so it is impossible to judge the specific section of the railway line where the abnormal situation exists from the photos taken.

Contents of the invention

The purpose of the present invention is to provide a UAV railway line inspection device, system and method to solve the problems in the prior art that the UAV cannot inspect the railway lines in the tunnel and cannot accurately judge and locate the fault points of the railway lines And other issues.

To achieve the above object, the present invention provides the following scheme:

An unmanned aerial vehicle inspection device for railway lines, comprising: a drone, a drone controller, a camera, a controller, and a display; the drone controller is installed on the drone; the camera includes at least Two groups, at least one group of the camera is installed on the drone, at least one group of the camera is installed in the railway tunnel; the camera is used to collect on-site image data of the railway line, and the on-site image data includes the railway line image and coordinates; the controller is connected with the camera for receiving, processing and monitoring the on-site image data collected by the camera; the controller is connected with the UAV controller for Controlling the UAV controller to set the flight parameters of the UAV; the display is used to display the image data output by the controller.

Optionally, there are multiple groups of cameras installed in the railway tunnel, and multiple groups of cameras are installed on the top of the railway tunnel at preset distances.

Optionally, the device also includes a storage module and a transmission module; the storage module is installed on the wall outside the entrance of the railway tunnel, and is used to store the on-site image data in the railway tunnel collected by the camera; the transmission The module is installed on the wall outside the entrance of the railway tunnel, and is used for sending the on-site image data stored in the storage module to the controller.

Optionally, the controller includes a receiving module, an image processing module, and a monitoring module; the receiving module is used to receive the on-site image data sent by the transmission module; the image processing module is used to process the on-site image data; the monitoring module is used to monitor the processed on-site image data.

Optionally, the device further includes a mobile phone detection system, which is installed on a mobile smart device and used to view the monitoring results of the monitoring module.

An unmanned aerial vehicle railway line inspection method, the method specifically includes:

Obtaining on-site image data of the railway line, the on-site image data including the image and coordinates of the railway line;

Processing the on-site image data of the railway line to obtain a processed image;

Judging whether there is a fault point in the railway line in the processed image;

If there is a fault point, locate the railway line where the fault point exists;

If there is no fault point, return to the step of processing the image of the railway line.

Optionally, the step of processing the on-site image data of the railway line specifically includes:

stitching images of said railway lines;

performing grayscale processing on the images of the spliced railway lines to obtain grayscale images;

Denoising the grayscale image by using a median filter method;

Using a Gaussian filter method to sharpen the image after noise reduction;

Using an edge detection algorithm to perform feature extraction on the sharpened image, extract the image of the rail assembly in the image, and obtain the image of the rail assembly, the rail assembly includes rails, rail foundations, track slabs, track beds and tracks fasteners;

Gray scale compensation is performed on the rail component image to obtain a processed image.

Optionally, the judging whether there is a fault point in the railway line in the processed image specifically includes:

Acquiring the gray value of the processed image;

comparing the grayscale value with a preset threshold;

If the gray value is greater than the preset threshold, it is determined that there is a fault point in the railway line in the image;

If the gray value is less than or equal to the preset threshold, it is determined that there is no fault point on the railway line in the image.

Optionally, the locating the railway line with the fault point specifically includes:

reading the coordinates of the processed image;

determining the coordinates of the fault point according to the coordinates of the processed image and the fault point;

The actual geographic location of the fault point is determined according to the correspondence between the coordinates of the fault point and the latitude and longitude of the earth.

An unmanned aerial vehicle inspection system for railway lines, comprising:

An image acquisition unit, configured to acquire on-site image data of the railway line, the on-site image data including images and coordinates of the railway line;

An image processing unit, configured to process on-site image data of the railway line to obtain a processed image;

A judging unit, configured to judge whether there is a fault point in the railway line in the processed image;

The positioning unit is configured to locate the railway line with the fault point when the judging unit determines that there is a fault point in the railway line in the processed image.

Compared with the prior art, the beneficial effects of the present invention are: the present invention provides a UAV railway line inspection device, system and method, in the present invention, the UAV controller is installed on the UAV, and can be set without The flight parameters of the man-machine control the flight attitude of the drone to ensure the safe flight of the drone; the camera is installed on the drone and in the railway tunnel, which can not only collect on-site image data on the railway line outside the tunnel, but also collect On-site image data on the railway line in the tunnel; and the controller is connected to the camera, the controller can perform post-processing and monitoring on the on-site image data on the railway line collected by the camera, through preprocessing of image data, threshold comparison And the reading of the coordinates can determine whether there is a fault point on the railway line, and can accurately locate the fault point, and then display the monitoring results through the display screen, which is convenient for the staff to check and carry out timely maintenance. To sum up, the present invention realizes the patrol inspection of the railway lines inside and outside the tunnel, and can perform post-processing and monitoring on the collected image data, thereby more accurately judging and locating the fault points of the railway lines.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required in the embodiments. Obviously, the accompanying drawings in the following description are only some of the present invention. Embodiments, for those of ordinary skill in the art, other drawings can also be obtained according to these drawings without paying creative labor.

Fig. 1 is the structural diagram of the unmanned aerial vehicle railway line inspection device of the embodiment of the present invention;

Fig. 2 is the structural diagram of the controller of the embodiment of the present invention;

Fig. 3 is the flowchart of the inspection method of the embodiment of the present invention;

4 is a flowchart of a method for processing images of railway lines according to an embodiment of the present invention;

Fig. 5 is a flow chart of a method for judging whether there is a fault point in the railway line in the processed image according to an embodiment of the present invention;

6 is a flowchart of a method for locating a railway line with a fault point according to an embodiment of the present invention;

FIG. 7 is a structural diagram of a patrol inspection system according to an embodiment of the present invention.

Among them, 1-UAV, 2-UAV controller, 3-camera, 4-controller, 5-display, 41-receiving module, 42-image processing module, 43-monitoring module, 6-image acquisition unit , 7-image processing unit, 8-image processing unit, 9-positioning unit.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

The purpose of the present invention is to provide a UAV railway line inspection device, system and method to solve the problems in the prior art that the UAV cannot inspect the railway lines in the tunnel and cannot accurately judge and locate the fault points of the railway lines And other issues.

In order to make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

Fig. 1 is a structural diagram of a UAV railway line inspection device according to an embodiment of the present invention; Fig. 2 is a structural diagram of a controller according to an embodiment of the present invention.

Embodiment 1, as shown in FIG. 1 , the UAV railway line inspection system includes a UAV 1 , a UAV controller 2 , a camera 3 , a controller 4 , and a display 5 .

The UAV 1 is used to patrol the railway lines outside the tunnel, and the UAV controller 2 is installed on the UAV 1 to control the flight route, flight trajectory, and flight attitude of the UAV 1 in real time. During the inspection process, UAV 1 encounters a passing train, and can keep the original position and wait according to the parameters set by UAV controller 2. After the train runs, it will continue to patrol according to the flight attitude set by UAV controller 2. This can ensure the safety of the UAV 1 in the inspection process.

There are at least two groups of cameras 3, at least one group is installed on the UAV 1, at least one group is installed in the railway tunnel, the camera 3 is mainly used to collect on-site image data of the railway line, and the on-site image data includes the image and coordinates of the railway line . The camera 3 installed on the unmanned aerial vehicle 1 is mainly used to collect the on-site image data of the railway line outside the tunnel, and the camera 3 installed in the railway tunnel is a plurality of groups, and the multi-group camera 3 is installed in the railway tunnel by a preset distance The top is mainly used to collect field data of the railway line in the tunnel. In addition, the device also includes a storage module and a transmission module, the storage module is installed on the wall outside the railway tunnel mouth, and is used to store the on-site image data in the railway tunnel collected by the camera 3; the transmission module is installed on the wall outside the railway tunnel mouth, It is used to send the on-site image data stored in the storage module to the controller 4. When there is a problem with the transmission module, the on-site image data can also be imported into the controller 4 by manual extraction. Since the camera 3 includes at least two groups, not only installed on the UAV 1, but at least one group is installed in the tunnel, which ensures the integrity and comprehensiveness of the on-site image data of the railway line collected by the device.

The controller 4 is connected with the camera 3 for receiving, processing and monitoring the on-site image data collected by the camera 3; and the controller is also connected with the UAV controller 2 for controlling the UAV controller 2 to the UAV 1 to set the flight parameters. As shown in FIG. 2 , the controller 4 includes a receiving module 41 , an image processing module 42 and a monitoring module 43 . The receiving module 41 is used for receiving the on-site image data sent by the transmission module; the image processing module 42 is used for processing the on-site image data; the monitoring module 43 is used for monitoring the processed on-site image data. The on-site image data collected by the camera 3 on the railway line can be post-processed and monitored through the controller 4, so as to determine whether there is a fault point on the railway line and accurately locate the fault point.

The display 5 is connected with the controller 4, and is used for displaying the image data output by the controller 4, and the output image data is played in the form of video, which is convenient for staff to check and carry out timely maintenance.

Embodiment 2, different from above-mentioned embodiment 1, this device also comprises mobile phone detection system, and mobile phone detection system is installed on the movable smart device, is used for viewing the monitoring result of monitoring module 43, facilitates monitoring personnel to check at any time, makes monitoring The personnel can organize personnel to repair or deal with the abnormal situation of the railway line in time. Abnormal conditions include catenary and its accessories, rails, rail foundations, track slabs, track beds, and track fasteners, such as cracks, breaks, falling off, loosening, off-line, and protrusions that affect train driving safety.

Fig. 3 is a flow chart of the inspection method of the present invention, Fig. 4 is a flow chart of a method for processing images of railway lines in an embodiment of the present invention, and Fig. 5 is a flow chart of an embodiment of the present invention judging whether the railway line in the processed image exists A flow chart of a method for a fault point, FIG. 6 is a flow chart of a method for locating a railway line with a fault point according to an embodiment of the present invention.

As shown in Figure 3, the method for carrying out railway inspection using the UAV railway line inspection device described in the above-mentioned embodiments 1 and 2 includes the following steps:

S301. Obtain on-site image data of the railway line, where the on-site image data includes the image and coordinates of the railway line;

Specifically, the on-site data on the railway lines inside and outside the tunnel are collected by the camera 3 installed on the unmanned aerial vehicle 1 and the railway tunnel;

S302, processing the on-site image data of the railway line to obtain the processed image;

As shown in Figure 4, the steps of processing the image of the railway line specifically include the following steps:

S3021, splicing the images of the railway lines;

S3022, performing grayscale processing on the spliced images of the railway line to obtain a grayscale image;

S3023, using a median filter method to denoise the grayscale image;

S4024, using a Gaussian filtering method to sharpen the image after noise reduction;

S3025, using the edge detection algorithm to perform feature extraction on the sharpened image, extracting the image of the rail component in the image, and obtaining the rail component image, the rail component including the rail, the rail foundation, the track slab, the track bed and the track fastener ;

S3026. Perform grayscale compensation on the rail component image to obtain a processed image.

S303, judging whether there is a fault point in the railway line in the processed image;

As shown in Figure 5, judging whether there is a fault point in the railway line in the processed image specifically includes the following steps:

S3031, acquiring the gray value of the processed image;

S3032, comparing the gray value with a preset threshold;

S3033, if the gray value is greater than the preset threshold, determine that there is a fault point in the railway line in the image;

S3034. If the gray value is less than or equal to the preset threshold, determine that there is no fault point in the railway line in the image.

S304, if there is a fault point, locate the railway line with the fault point;

As shown in Figure 6, locating the railway line with the fault point specifically includes the following steps:

S3041, read the coordinates of the processed image;

S3042. Determine the coordinates of the fault point according to the coordinates of the processed image and the fault point;

S3043. Determine the actual geographic location of the fault point according to the coordinates of the fault point and the corresponding relationship between the latitude and longitude of the earth.

S305, if there is no fault point, return to the step of processing the image of the railway line.

Through the above method, the railway line in the tunnel can be inspected, and the collected image data can be processed and monitored in the later stage, so as to judge and locate the fault point of the railway line more accurately.

Fig. 7 is a structural diagram of the UAV railway line inspection system of the present invention. As shown in FIG. 7 , the UAV railway line inspection system includes an image acquisition unit 6 , an image processing unit 7 , a judging unit 8 , and a positioning unit 9 . The image acquisition unit 6 is used to obtain the on-site image data of the railway line, and the on-site image data includes images and coordinates of the railway line; the image processing unit 7 is used to process the on-site image data of the railway line to obtain the processed image ; judging unit 8, for judging whether there is a fault point in the railway line in the image after processing; positioning unit 9, for when the judgment unit 8 judges that there is a fault point in the railway line in the image after processing , and locate the railway line where the fault point exists.

Through the inspection system of the present invention, the collected image data can be processed and monitored in the later stage, and then the fault point of the railway line can be judged and located more accurately.

Each embodiment in this specification is described in a progressive manner, each embodiment focuses on the difference from other embodiments, and the same and similar parts of each embodiment can be referred to each other.

In this paper, specific examples have been used to illustrate the principle and implementation of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; meanwhile, for those of ordinary skill in the art, according to the present invention Thoughts, there will be changes in specific implementation methods and application ranges. In summary, the contents of this specification should not be construed as limiting the present invention.

Claims (5)

1. An unmanned aerial vehicle railway line inspection device is characterized in that, comprising: an unmanned aerial vehicle, an unmanned aerial vehicle controller, a camera, a controller, a display, a storage module and a transmission module; On the unmanned aerial vehicle; The camera includes at least two groups, at least one group of the camera is installed on the unmanned aerial vehicle, at least one group of the camera is installed in the railway tunnel; the camera is used to collect the information of the railway line On-site image data, the on-site image data includes images and coordinates of railway lines; the controller is connected to the camera for receiving, processing and monitoring the on-site image data collected by the camera; the controller Connected with the UAV controller, used to control the UAV controller to set the flight parameters of the UAV; the display is used to display the image data output by the controller; the The storage module is installed on the wall outside the railway tunnel mouth, and is used to store the on-site image data in the railway tunnel collected by the camera; the transmission module is installed on the wall outside the railway tunnel mouth, and is used to transfer the storage module The on-site image data stored in is sent to the controller; the controller includes a receiving module, an image processing module and a monitoring module; the receiving module is used to receive the on-site image data sent by the transmission module; the The image processing module is used to process the on-site image data; the monitoring module is used to monitor the processed on-site image data; The method of using the unmanned aerial vehicle railway line inspection device to carry out inspections includes: Obtain on-site image data of railway lines; Processing the on-site image data of the railway line to obtain a processed image; Judging whether there is a fault point in the railway line in the processed image; If there is a fault point, locate the railway line where the fault point exists; If there is no fault point, return to the step of processing the image of the railway line; The step of processing the on-site image data of the railway line specifically includes: stitching images of said railway lines; performing grayscale processing on the images of the spliced railway lines to obtain grayscale images; Denoising the grayscale image by using a median filter method; Using a Gaussian filter method to sharpen the image after noise reduction; Using an edge detection algorithm to perform feature extraction on the sharpened image, extract the image of the rail assembly in the image, and obtain the image of the rail assembly, the rail assembly includes rails, rail foundations, track slabs, track beds and tracks fasteners; Gray scale compensation is performed on the rail component image to obtain a processed image. 2. A kind of unmanned aerial vehicle railway line inspection device according to claim 1, characterized in that, the cameras installed in the railway tunnel are multiple groups, and the multiple groups of cameras are installed in the railway tunnel according to a preset distance inside the top. 3. A kind of unmanned aerial vehicle railway line inspection device according to claim 1, characterized in that, the device also includes a mobile phone detection system, the mobile phone detection system is installed on a mobile smart device for viewing all Describe the monitoring results of the monitoring module. 4. A kind of unmanned aerial vehicle railway circuit inspection device according to claim 1, is characterized in that, described whether there is fault point in the railway circuit in the image after described judging described processing, specifically comprises: Acquiring the gray value of the processed image; comparing the grayscale value with a preset threshold; If the gray value is greater than the preset threshold, it is determined that there is a fault point in the railway line in the image; If the gray value is less than or equal to the preset threshold, it is determined that there is no fault point on the railway line in the image. 5. A kind of UAV railway line inspection device according to claim 4, characterized in that, the positioning of the railway line with the fault point specifically includes: reading the coordinates of the processed image; determining the coordinates of the fault point according to the coordinates of the processed image and the fault point; The actual geographic location of the fault point is determined according to the correspondence between the coordinates of the fault point and the latitude and longitude of the earth.

Images