Unmanned aerial vehicle bridge bottom detection system

文档序号：240609 发布日期：2021-11-12 浏览：40次中文

阅读说明：本技术 一种无人机桥底检测系统 (Unmanned aerial vehicle bridge bottom detection system ) 是由钟盛蒋盛川张晓明于 2021-08-18 设计创作，主要内容包括：本发明公开了一种无人机桥底检测系统,包括,无人机采集模块,用于在多角度采集桥底图像；定位模块,用于实时获取无人机的位置信息；传输模块,用于将采集到的图像和所述无人机的位置信息传输到处理器；处理器,用于对采集的图像进行处理,获得桥底检测信息。与传统检测相比,本项目开发设备仪器简便,安装操作简单,经济合理,对测量环境要求低。仅需要定期进行简单的标定工作,测量结果精度较高。另外,在该系统中,采用了多种无线传感器网络技术,使得数据的采集传输更为可靠,利用GPS设备可以采集配套的地理信息,并可以与电子地图结合,对桥梁健康进行实时的数据采集与显示。(The invention discloses an unmanned aerial vehicle bridge bottom detection system, which comprises an unmanned aerial vehicle acquisition module, a bridge bottom detection module and a control module, wherein the unmanned aerial vehicle acquisition module is used for acquiring bridge bottom images at multiple angles; the positioning module is used for acquiring the position information of the unmanned aerial vehicle in real time; the transmission module is used for transmitting the acquired image and the position information of the unmanned aerial vehicle to the processor; and the processor is used for processing the acquired image to obtain bridge bottom detection information. Compared with the traditional detection, the project development equipment has the advantages of simple instrument, simple installation and operation, economy and reasonability and low requirement on the measurement environment. Only simple calibration work is required to be carried out regularly, and the precision of the measurement result is high. In addition, in the system, various wireless sensor network technologies are adopted, so that data acquisition and transmission are more reliable, matched geographic information can be acquired by utilizing GPS equipment, and real-time data acquisition and display can be carried out on bridge health by combining with an electronic map.)

1. An unmanned aerial vehicle bridge bottom detection system, its characterized in that includes:

the unmanned aerial vehicle acquisition module is used for acquiring the bridge bottom image at multiple angles;

the positioning module is used for acquiring the position information of the unmanned aerial vehicle in real time;

the transmission module is used for transmitting the acquired bridge bottom image and the position information of the unmanned aerial vehicle to the processor;

and the processor is used for processing the bridge bottom image to obtain bridge bottom detection information.

2. The system of claim 1, wherein the drone acquisition module comprises:

the industrial camera is carried above the unmanned aerial vehicle and used for acquiring an under-bridge image right above the unmanned aerial vehicle, and the under-bridge image right above the unmanned aerial vehicle has color information;

the wide-angle camera is carried below the unmanned aerial vehicle in a forward facing mode and used for acquiring an under-bridge image in front of the unmanned aerial vehicle, and the under-bridge image in front of the unmanned aerial vehicle has no color information;

the cloud platform carries on respectively the industry camera wide angle camera with between the unmanned aerial vehicle for guarantee image acquisition's angle or scope.

3. The system of claim 2, wherein the process of collecting the bridge bottom image at multiple angles by the unmanned aerial vehicle collecting module comprises:

the unmanned aerial vehicle takes off in situ to the height of the inspection operation altitude, is close to the end, connected with the beam bottom to be detected, of the bridge pier and keeps a safe distance with the beam bottom, wherein the safe distance is preset by a worker;

respectively adjusting the attitude angle, the shooting angle and the focal length value of the industrial camera and the wide-angle camera through the cloud deck to ensure that a shooting picture completely covers the bottom surface of the bridge;

the unmanned aerial vehicle flies along the direction of the bridge line, collects images and numbers the bridge bottom.

4. The system of claim 3, wherein the process of the unmanned aerial vehicle flying along the direction of the bridge line and performing image acquisition comprises:

the distance between the unmanned aerial vehicle and surrounding obstacles or the distance between the unmanned aerial vehicle and the upper beam bottom are detected through a distance judging module respectively, when any distance is smaller than a threshold value, a warning is sent out, the speed is reduced to prepare for hovering, turning or descending, and the distance judging module is located on the unmanned aerial vehicle.

5. The system of claim 1, wherein the positioning module acquires the real-time location of the drone in real-time via GPS.

6. The system of claim 3 or 5, wherein the unmanned aerial vehicle flies along the direction of the bridge line and performs image acquisition, and further comprises:

setting a flight track and performing cruise acquisition based on the image acquired by the wide-angle camera;

judging whether the unmanned aerial vehicle drifts during cruising based on the real-time position of the unmanned aerial vehicle acquired by the positioning module;

if the yaw occurs, deviation rectification is carried out based on the flight track and the real-time position of the unmanned aerial vehicle.

7. The system of claim 1, wherein the transmitting module transmits the acquired underbridge image and the position information of the drone to the processor comprises:

the data transmission module comprises a communication module, and data transmission is completed through the communication module;

the communication module adopts a wireless connection mode to transmit data, and comprises: WIFI, 4G, 5G and GPRS.

8. The system of claim 1, wherein the processor processes the captured image to obtain the bridge floor detection information comprises:

detecting the bridge bottom image based on a stacked hourglass network, wherein the stacked hourglass network comprises a plurality of hourglass network structures;

detecting the received bridge bottom image through each hourglass network structure to obtain spatial position characteristics of key points at the bridge bottom and probability information of the key points of the beam bottom plate in each pixel neighborhood;

the spatial position characteristics of different key points at the bottom of the bridge are referred or predicted by stacking a plurality of hourglass network structures, so that the condition of the key points at the bottom of the bridge is judged, and the detection information of the key points at the bottom of the bridge is obtained;

and acquiring corresponding bridge bottom information, and finishing final key point positioning based on the positions of the key points.

9. The system of claim 2 or 8, wherein the detecting the bridge floor image based on the stacked hourglass network comprises:

and detecting the bridge bottom image without color information collected by the wide-angle lens based on the stacked hourglass network.

10. The system of claim 3 or 8, wherein obtaining corresponding bridge floor information, and based on the locations of the key points, completing the final key point location comprises:

sampling color values of the bottom plate based on the bridge bottom image with the color information acquired by the industrial camera;

calculating a normalized color value to obtain a bottom plate color value variance;

and judging based on the color value variance of the bottom plate and the number of the bridge bottom, determining the number of the bridge bottom plate to which the key point belongs, and positioning the key point corresponding to the bridge bottom.

Technical Field

The invention relates to the field of bridge rapid inspection, in particular to an unmanned aerial vehicle bridge bottom detection system.

Background

At present, conventional bridge safety detection equipment is single, and main detection equipment comprises an artificial telescope, remote photographing, a bridge inspection vehicle, preset track video detection and the like. The traditional detection means almost have the problems of low efficiency, high cost, certain potential safety hazard to detection personnel and the like. Therefore, the unmanned aerial vehicle is developed to carry out bridge safety inspection, so that the efficiency is greatly improved, and the personal safety is guaranteed.

The unmanned aerial vehicle obstacle avoidance technology is that when an unmanned aerial vehicle meets an obstacle in the automatic flight process, the obstacle is automatically identified in advance and effectively avoided, so that the effect of flight safety is achieved, and the unmanned aerial vehicle obstacle avoidance technology is one of important contents of unmanned aerial vehicle research.

The monitoring and analysis of the bridge bottom condition is a basic task of bridge health monitoring. Currently, the bridge bottom detection technology mainly has two modes of manual detection and unmanned aerial vehicle detection. Unmanned aerial vehicle detection generally relies on a Global Positioning System (GPS) Positioning device to perform coarse Positioning of detection data (e.g., detection data frames). However, this positioning method has a disadvantage that, due to the influence of the GPS positioning accuracy, the positioning error is large, and is generally in the order of meter or ten meter accuracy, when the positioning accuracy is enhanced without using the RTK (Real-Time Kinematic) carrier phase difference technique. There is a need in the art for a solution to the problems of the prior art.

Disclosure of Invention

The invention aims to provide an unmanned aerial vehicle bridge bottom detection system to solve the problems in the prior art.

In order to achieve the purpose, the invention provides the following scheme:

the invention provides an unmanned aerial vehicle bridge bottom detection system, which comprises:

the unmanned aerial vehicle acquisition module is used for acquiring the bridge bottom image at multiple angles;

the positioning module is used for acquiring the position information of the unmanned aerial vehicle in real time;

the transmission module is used for transmitting the acquired bridge bottom image and the position information of the unmanned aerial vehicle to the processor;

and the processor is used for processing the bridge bottom image to obtain bridge bottom detection information.

Optionally, unmanned aerial vehicle collection module includes:

the cloud platform carries on respectively the industry camera wide angle camera with between the unmanned aerial vehicle for guarantee image acquisition's angle or scope.

Optionally, the unmanned aerial vehicle acquisition module includes in the process of acquiring the bridge bottom image at multiple angles:

the unmanned aerial vehicle flies along the direction of the bridge line, collects images and numbers the bridge bottom.

Optionally, the process that unmanned aerial vehicle flies along the bridge route direction and carries out image acquisition includes:

Optionally, the positioning module acquires the real-time position of the unmanned aerial vehicle in real time through a GPS.

Optionally, unmanned aerial vehicle flies and carries out image acquisition's in-process along bridge line direction, still includes:

setting a flight track and performing cruise acquisition based on the image acquired by the wide-angle camera;

judging whether the unmanned aerial vehicle drifts during cruising based on the real-time position of the unmanned aerial vehicle acquired by the positioning module;

if the yaw occurs, deviation rectification is carried out based on the flight track and the real-time position of the unmanned aerial vehicle.

Optionally, the process of transmitting the acquired bridge bottom image and the position information of the unmanned aerial vehicle to the processor by the transmission module includes:

the data transmission module comprises a communication module, and data transmission is completed through the communication module;

the communication module adopts a wireless connection mode to transmit data, and comprises: WIFI, 4G, 5G and GPRS.

Optionally, the processing the acquired image by the processor to obtain the bridge bottom detection information includes:

detecting the bridge bottom image based on a stacked hourglass network, wherein the stacked hourglass network comprises a plurality of hourglass network structures;

and acquiring corresponding bridge bottom information, and finishing final key point positioning based on the positions of the key points.

Optionally, the detecting the bridge bottom image based on the stacked hourglass network includes:

and detecting the bridge bottom image without color information collected by the wide-angle lens based on the stacked hourglass network.

Optionally, the step of obtaining corresponding bridge bottom information, and based on the positions of the key points, completing final key point positioning includes:

sampling color values of the bottom plate based on the bridge bottom image with the color information acquired by the industrial camera;

calculating a normalized color value to obtain a bottom plate color value variance;

The invention discloses the following technical effects:

compared with the traditional detection, the device and the instrument for developing the application are simple and convenient, simple to install and operate, economical and reasonable, and low in requirement on measurement environment. Only simple calibration work is required to be carried out regularly, and the precision of the measurement result is high. In addition, in the system, various wireless sensor network technologies are adopted, so that data acquisition and transmission are more reliable, matched geographic information can be acquired by utilizing GPS equipment, and real-time data acquisition and display can be carried out on bridge health by combining with an electronic map.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.

Fig. 1 is a schematic structural diagram of a system in an embodiment of the present application.

Detailed Description

Reference will now be made in detail to various exemplary embodiments of the invention, the detailed description should not be construed as limiting the invention but as a more detailed description of certain aspects, features and embodiments of the invention.

It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. Further, for numerical ranges in this disclosure, it is understood that each intervening value, between the upper and lower limit of that range, is also specifically disclosed. Every smaller range between any stated value or intervening value in a stated range and any other stated or intervening value in a stated range is encompassed within the invention. The upper and lower limits of these smaller ranges may independently be included or excluded in the range.

It will be apparent to those skilled in the art that various modifications and variations can be made in the specific embodiments of the present disclosure without departing from the scope or spirit of the disclosure. Other embodiments will be apparent to those skilled in the art from consideration of the specification. The specification and examples are exemplary only.

As used herein, the terms "comprising," "including," "having," "containing," and the like are open-ended terms that mean including, but not limited to.

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.

The invention provides a method for realizing the level refined positioning of a bridge bottom plate by a high-speed industrial camera shot upwards and a wide-angle camera shot forwards, wherein the refined positioning process comprises two steps of bridge bottom plate detection and bridge bottom plate labeling:

the former method is a method for selecting characteristic points through a specific Stacked Hourglass network (Stack Hourglass Networks) structure to realize detection of characteristic points at the bottom of a beam and complete detection of a bottom plate area of a bridge;

the latter refers to further processing according to the detection result of the bridge bottom plate area to obtain the beam bottom plate number above the unmanned aerial vehicle, namely, the serial number counted from the leftmost side (or the rightmost side) of the current flight direction area.

An unmanned aerial vehicle bridge bottom detection system, includes the following equipment: unmanned aerial vehicle carries on the industry camera of shooting, the unmanned aerial vehicle below hangs wide angle camera, the image transmission module of shooting forward.

By processing foreground image information through stacking hourglass networks, the fact that each hourglass network structure is subjected to a process of reducing the number of channels and then increasing the number of channels can be found, the process is used for excavating space position characteristics of key points of a beam bottom plate and providing probability information of the key points of the beam bottom plate in each pixel neighborhood of the image; on the other hand, reference prediction of different key points can be realized by stacking a plurality of hourglass structures, so that the overall prediction precision of the key points of the lane is improved.

Meanwhile, fixed-track cruising can be completed through the foreground camera.

In the stage of detecting the beam bottom plate, because the used image information is a foreground image and colors and the like are not particularly distinguished, the accurate positioning of the lane cannot be realized in the wide bottom plate.

Therefore, further mining of the bottom plate information is completed through a bottom plate labeling post-processing task on the basis of beam bottom plate detection, and finally positioning is achieved.

Since the key points of different bottom plates have been obtained in the bottom plate detection stage, color value sampling can be further performed on the bottom plates by shooting upward the industrial camera. And (3) carrying out pixel-by-pixel RGB color value sampling on the cross section of the bottom plate, calculating the pixel-by-pixel normalized color value of the cross section, and determining whether the cross section is the same bottom plate or not according to the color value variance of the bottom plate.

The invention provides an unmanned aerial vehicle bridge bottom detection system, which comprises: