Tunnel crack detection method and system based on unmanned aerial vehicle cluster

The tunnel lining image is acquired in real time by drone clusters and using image recognition algorithms to detect cracks, solving the problems of low tunnel detection efficiency and low accuracy in the prior art, and achieving efficient and accurate crack detection and warning generation.

CN119086595APending Publication Date: 2024-12-06PRODRONE TECH (SHENZHEN) CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411382587.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-30
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

In the prior art, the detection of railway tunnel lining disease mainly relies on manual inspection, which is low in efficiency, high in risk and low in accuracy.

Method used

The drone cluster is used to obtain tunnel lining images in real time, and cracks are identified through automatic identification and detection. If the standard exceeds the standard, warning information will be generated to improve detection efficiency and accuracy.

Benefits of technology

Through the real-time image acquisition and image recognition algorithm of the drone cluster, efficient and accurate detection of tunnel cracks is achieved, detection efficiency and accuracy are improved, and warning information is generated.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119086595A_ABST
    Figure CN119086595A_ABST
Patent Text Reader

Abstract

The invention discloses a tunnel crack detection method and system based on an unmanned aerial vehicle cluster, and the method comprises the following steps: controlling an unmanned aerial vehicle to fly, and enabling the unmanned aerial vehicle to inspect a designated area according to a set cruise height and route in a tunnel; in the unmanned aerial vehicle inspection process, tunnel lining images are obtained in real time through imaging equipment carried on an unmanned aerial vehicle holder; a crack in the tunnel lining image is identified, if the crack is identified, the unmanned aerial vehicle hovers at the crack generation position, the focal length of the imaging equipment is adjusted, and different crack images are acquired under different focal lengths; different crack images are detected through an image recognition module and the like to obtain crack information; and judging whether the crack exceeds the standard or not according to the crack information, and if yes, automatically generating warning information. The tunnel lining image is obtained in real time through the unmanned aerial vehicle, whether the tunnel lining has cracks or not is automatically recognized and detected, and the tunnel crack detection efficiency and accuracy can be greatly improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of machine vision, and in particular to a tunnel crack detection method and system based on drone clusters. Background Art

[0002] At present, most of the inspection work on tunnel lining defects in domestic railways is completed through manual inspection. This inspection method has the disadvantages of low detection efficiency, high risk, and low accuracy of detection results. Summary of the invention

[0003] In view of the shortcomings of the prior art, the present invention provides a tunnel crack detection method and system based on drone clusters, which obtains tunnel lining images in real time through drones, automatically identifies and detects whether there are cracks in the tunnel lining, and can greatly improve the efficiency and accuracy of tunnel crack detection.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] On the one hand, a method for detecting tunnel cracks based on drone clusters is provided, which comprises the following steps:

[0006] Control the flight of the drone cluster so that each drone in the drone cluster is in the tunnel and inspects the designated area according to the set corresponding cruising altitude and route;

[0007] During each drone inspection, the tunnel lining images are acquired in real time through the imaging equipment carried on the drone gimbal;

[0008] Identify cracks in each tunnel lining image. If a crack is identified, the corresponding drone hovers at the location where the crack occurs, adjusts the focal length of the imaging device, and obtains different crack images at different focal lengths.

[0009] Detect different crack images through image recognition modules, etc., to obtain crack information;

[0010] It is determined whether the cracks exceed the standard according to the crack information, and if so, a warning message is automatically generated.

[0011] Preferably, the crack information includes one or more of the length, width and location of the crack.

[0012] Preferably, the location of the crack can be represented by the position coordinates of the drone when it is hovering.

[0013] Preferably, judging whether the crack exceeds the standard according to the crack information includes the following steps: judging whether the length and / or width of the crack exceeds a set threshold.

[0014] On the other hand, a tunnel crack detection system is also provided, which is used to implement the above tunnel crack detection method, and includes:

[0015] Several drones;

[0016] A plurality of imaging devices, which are carried on the UAVs and are used to obtain images of the tunnel lining, and each UAV is equipped with an imaging device;

[0017] A crack identification unit, which is used to identify cracks in the tunnel lining image;

[0018] A crack detection unit, which is used to detect different crack images to obtain crack information;

[0019] The monitoring alarm unit is used to automatically generate a warning message when the crack is considered to be excessive.

[0020] Preferably, the imaging device comprises a high-resolution visible light camera.

[0021] The present invention uses a drone cluster to acquire tunnel lining images in real time, combines image recognition algorithms to automatically identify and detect whether there are cracks in the tunnel lining, and uploads the detected crack information to the background management system, which can greatly improve the efficiency and accuracy of tunnel crack detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flowchart of the steps of the tunnel crack detection method based on drone cluster in the present invention;

[0023] Figure 2 It is a structural schematic diagram of the tunnel crack detection system based on drone cluster in the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] Embodiment 1:

[0026] like Figure 1 As shown, this embodiment provides a tunnel crack detection method based on drone clusters, which includes the following steps:

[0027] S1. Control the flight of the drone cluster so that each drone in the drone cluster is in the tunnel and inspects the designated area according to the set corresponding cruising altitude and route;

[0028] S2. During each drone inspection, the tunnel lining image is acquired in real time by an imaging device (including a high-resolution visible light camera) mounted on the drone gimbal; in this embodiment, each drone is equipped with an imaging device, and each tunnel lining image corresponds to the drone on which the imaging device that acquired the image is located;

[0029] S3, identifying cracks in each tunnel lining image. If cracks are identified, the corresponding drone hovers at the location where the cracks occur, and adjusts the focal length of the imaging device to obtain different crack images at different focal lengths;

[0030] S4. Detect different crack images using the yolov8 target detection algorithm to obtain crack information. In this embodiment, the crack information includes one or more of the length, width, and location of the crack, and the location of the crack can be represented by the position coordinates of the drone when it is hovering;

[0031] S5. Determine whether the cracks exceed the standard according to the crack information. If so, automatically generate a warning message and upload the crack information to the background management system for reference by relevant departments.

[0032] In this embodiment, judging whether the cracks exceed the standard according to the crack information includes the following steps:

[0033] Determine whether the length and / or width of the crack exceeds a set threshold. If so, a warning message is automatically generated.

[0034] S6. Repeat steps S1-S5 until multiple inspections are completed.

[0035] Therefore, this embodiment uses a drone to obtain tunnel lining images in real time, combines image recognition algorithms, automatically identifies and detects whether there are cracks in the tunnel lining, and uploads the detected crack information to the background management system, which can greatly improve the efficiency and accuracy of tunnel crack detection.

[0036] Embodiment 2:

[0037] This embodiment provides a tunnel crack detection system, which can implement the tunnel crack detection method described in Embodiment 1, such as Figure 2 As shown, it includes:

[0038] A plurality of drones 1, which form a drone cluster;

[0039] A plurality of imaging devices 2, which are carried on the drone 1 and are used to obtain tunnel lining images; and each drone 1 is equipped with an imaging device 2;

[0040] A crack identification unit 3 is used to identify cracks in the tunnel lining image, and its process is the same as step S3;

[0041] A crack detection unit 4 is used to detect different crack images to obtain crack information, and its process is the same as step S4;

[0042] The monitoring alarm unit 5 is used to automatically generate warning information when it is considered that the cracks exceed the standard, and upload the crack information to the background management system. The process is the same as step S5.

[0043] In summary, the present invention uses drones to acquire tunnel lining images in real time, combines image recognition algorithms, automatically identifies and detects whether there are cracks in the tunnel lining, and uploads the detected crack information to the background management system, which can greatly improve the efficiency and accuracy of tunnel crack detection.

[0044] It should be noted that the technical features in the above-mentioned embodiments 1-2 can be combined arbitrarily, and the combined technical solutions all belong to the protection scope of the present application. In this article, terms such as "including", "comprising" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or equipment. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the presence of other identical elements in the process, method, article or equipment including the elements.

[0045] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A tunnel crack detection method based on drone clusters, characterized in that: The steps include: Control the flight of the drone cluster so that each drone in the drone cluster is in the tunnel and inspects the designated area according to the set corresponding cruising altitude and route; During each drone inspection, the tunnel lining images are acquired in real time through the imaging equipment carried on the drone gimbal; Identify cracks in each tunnel lining image. If a crack is identified, the corresponding drone hovers at the location where the crack occurs, adjusts the focal length of the imaging device, and obtains different crack images at different focal lengths. Detect different crack images through image recognition modules, etc., to obtain crack information; It is determined whether the cracks exceed the standard according to the crack information, and if so, a warning message is automatically generated.

2. The tunnel crack detection method according to claim 1, characterized in that: The crack information includes one or more of the length, width, and location of the crack.

3. The tunnel crack detection method according to claim 1, characterized in that: The location of the crack can be indicated by the coordinates of the drone's hovering position.

4. The tunnel crack detection method according to claim 1, characterized in that: Judging whether the crack exceeds the standard according to the crack information includes the following steps: judging whether the length and / or width of the crack exceeds a set threshold.

5. A tunnel crack detection system, used to implement the tunnel crack detection method according to any one of claims 1 to 4, characterized in that: include: Several drones; A plurality of imaging devices, which are carried on the UAVs and are used to obtain images of the tunnel lining, and each UAV is equipped with an imaging device; A crack identification unit, which is used to identify cracks in the tunnel lining image; A crack detection unit, which is used to detect different crack images to obtain crack information; The monitoring alarm unit is used to automatically generate a warning message when the crack is considered to be excessive.

6. The tunnel crack detection system according to claim 5, characterized in that: The imaging device includes a high-resolution visible light camera.

Citation Information

Cited By

  • Railway tunnel construction crack detection method based on machine vision

    CN119413812A