Unmanned aerial vehicle positioning system for high concrete dam surface crack detection under weak GNSS

Abstract

The utility model discloses an unmanned aerial vehicle positioning system for high concrete dam surface crack detection under a weak GNSS. The system comprises a high-precision inertial navigation device, a binocular vision camera, an infrared sensing module, an obstacle avoidance radar and an airborne processor which are installed on an unmanned aerial vehicle platform, and the output ends of the high-precision inertial navigation device, the binocular vision camera, the infrared sensing module and the obstacle avoidance radar are all connected with the input end of the airborne processor. According to the utility model, under a weak GNSS condition, a binocular vision camera, an infrared sensing module, an obstacle avoidance radar, a high-precision inertial navigation sensor and other sensors are adopted, and a high-performance airborne processor is combined to realize accurate positioning of the unmanned aerial vehicle, so that the problems of autonomous positioning and navigation of the unmanned aerial vehicle under a weak GNSS environment of a high concrete dam are solved; and the phenomena of route deviation and inaccurate positioning of the unmanned aerial vehicle in a weak GNSS environment are avoided.

Description

Technical Field

[0001] The utility model belongs to the technical field of building surface detection, and specifically relates to an unmanned aerial vehicle positioning system for detecting surface cracks of high concrete dams under weak GNSS. Background Art

[0002] Concrete dams are a predominant type of reservoir dam. China boasts numerous concrete dams exceeding 100 and 200 meters in height, with many located in the deep mountainous canyons of the southwest. Cracks in concrete dams are a common problem, with virtually every dam experiencing them. This is a major hazard associated with high concrete dams, requiring regular inspections to monitor their safety status over the long term. Currently, drone-based image acquisition and crack detection methods are gaining traction, but they are primarily used in areas with strong GNSS capabilities, such as bridges, embankments, road pavements, and building exteriors. Their application to high concrete dams is limited.

[0003] High concrete dams are often located in the deep mountains and canyons of the southwest, where global navigation satellite (GNSS) signals are weak and sometimes even absent in some areas. Furthermore, when drones fly over reservoirs, water surface signal reflections and interference with positioning barometers can lead to inaccurate or even impossible positioning. Current drone crack detection systems cannot accurately locate targets in weak GNSS conditions, making tracking navigation difficult. Surface crack detection in high concrete dams typically covers a large area and size, making precise drone positioning crucial for automated and efficient surface crack detection in these dams. Utility Model Content

[0004] The purpose of the present invention is to address the deficiencies in the above-mentioned background technology and to provide a UAV positioning system for detecting surface cracks in high concrete dams under weak GNSS conditions.

[0005] The technical solution adopted by the utility model is: a UAV positioning system for detecting surface cracks in high concrete dams under weak GNSS, including a high-precision inertial navigation, a binocular vision camera, an infrared perception module, an obstacle avoidance radar and an airborne processor installed on a UAV platform, wherein the output ends of the high-precision inertial navigation, binocular vision camera, infrared perception module and obstacle avoidance radar are all connected to the input end of the airborne processor.

[0006] Furthermore, the high-precision inertial navigation is installed inside the UAV platform, and the high-precision inertial navigation includes an accelerometer, a gyroscope, and a barometer. The output ends of the accelerometer, gyroscope, and barometer are all connected to the input end of the onboard processor.

[0007] Furthermore, there are four binocular vision cameras, which are evenly spaced and arranged on the outer side wall of the UAV platform. The binocular vision cameras are 90-degree viewing angle width lenses.

[0008] Further, the infrared sensing module and the obstacle avoidance radar are both mounted on the outer side wall of the unmanned aerial vehicle platform.

[0009] Still further, the on-board processor is a Nvidia TX2 on-board processor.

[0010] The present application has the following advantages:

[0011] The present application sets up a binocular vision camera, a high-precision inertial navigation system, an infrared sensing module, an omnidirectional obstacle avoidance radar, and a high-performance on-board processor on the unmanned aerial vehicle platform. BRIEF DESCRIPTION OF DRAWINGS

[0012] Figure 1 It is a schematic diagram of the principle of the present application.

[0013] Figure 2 It is a schematic diagram of the arrangement of the binocular vision camera on the unmanned aerial vehicle platform. DETAILED DESCRIPTION

[0014] The specific embodiments of the present application will be further described below in conjunction with the accompanying drawings. It should be noted that the description of these embodiments is used to help understand the present application, but does not constitute a limitation on the present application. In addition, the technical features involved in each embodiment of the present application described below can be combined with each other as long as there is no conflict.

[0015] As shown in Figure 1 The present application provides an unmanned aerial vehicle positioning system for detecting surface cracks of high concrete dams under weak GNSS, which comprises a high-precision inertial navigation system 1, a binocular vision camera 2, an infrared sensing module 3, an obstacle avoidance radar 4, and an on-board processor 5 mounted on an unmanned aerial vehicle platform 6. The output ends of the high-precision inertial navigation system 1, the binocular vision camera 2, the infrared sensing module 3, and the obstacle avoidance radar 4 are all connected to the input end of the on-board processor 5.

[0016] The utility model sets binocular vision cameras, high-precision inertial navigation, infrared perception module, omnidirectional obstacle avoidance radar, and high-performance airborne processor hardware on the UAV platform. Under GNSS conditions, the UAV's built-in positioning and obstacle avoidance system is used for flight control. Under weak GNSS conditions, binocular vision cameras, infrared perception module, high-precision inertial navigation and other multiple sensors are used, combined with high-performance airborne processors to achieve precise positioning of the UAV. This positioning system overcomes the problem of autonomous positioning and navigation of UAVs in the weak GNSS environment of high concrete dams, avoids the phenomenon of UAVs deviating from their route and inaccurate positioning in weak GNSS environments, and meets the positioning needs of UAVs in weak GNSS environments in deep mountain canyons.

[0017] In the above scheme, the high-precision inertial navigation system 1 measures the drone's dynamic flight parameters and sends them to the onboard processor. The high-precision inertial navigation system is an inertial measurement component that includes an accelerometer 1.1, a gyroscope 1.2, and a barometer 1.3. The accelerometer measures the drone's translational acceleration in three directions, the gyroscope measures the drone's angular acceleration in three directions of rotation, and the barometer measures relative elevation. This total includes six degrees of freedom (DOF) information plus one elevation value.

[0018] In the above scheme, the binocular vision camera 2 collects images and locates the static coordinate position of the drone in three-dimensional space by generating three-dimensional point cloud data. There are four binocular vision cameras, which are arranged on the four side walls of the drone platform. The binocular vision camera lens is a 90-degree viewing angle lens with a maximum detection range of 40 to 50 meters. The four binocular vision cameras can form a 360-degree full field of view measurement, such as Figure 2 In the above scheme, the infrared sensing module 3 and the obstacle avoidance radar 4 are both installed on the external side wall of the UAV platform 6. The infrared sensing module 3 collects infrared signals from the external environment of the UAV platform, and the obstacle avoidance radar 4 collects radar signals and sends them to the onboard processor. The number of infrared sensing modules 3 and obstacle avoidance radar 4 can be set to one or more according to actual needs.

[0019] In the above scheme, a high-performance airborne processor 5 is installed inside the drone platform 6 to receive data collected by various sensors to achieve drone positioning. The airborne processor and high-precision inertial navigation are integrated on the same circuit board fixed inside the drone platform. The circuit board is covered by an anti-interference shield, which is a spherical crown made of glass, metal, or composite materials. In this embodiment, the airborne processor is the NVIDIA TX2 microprocessor, which has super computing power and low power consumption. The NVIDIA TX2 micro airborne processor is a highly efficient embedded AI computing device that is independent of the network environment. It has a built-in ROS system under Linux, 6 CPUs and 1 GPU, and 6 binocular vision cameras are connected to the airborne processor TX2 interface.

[0020] It should be understood that the above is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited to this. Any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this utility model should be included in the scope of protection of the present utility model. Matters not described in detail in this specification belong to the prior art known to those skilled in the art.

Claims

1. A UAV positioning system for detecting surface cracks in high concrete dams under weak GNSS conditions, characterized by: It includes a high-precision inertial navigation, a binocular vision camera, an infrared perception module, an obstacle avoidance radar and an airborne processor installed on a UAV platform. The output ends of the high-precision inertial navigation, binocular vision camera, infrared perception module and obstacle avoidance radar are all connected to the input end of the airborne processor.

2. The UAV positioning system for detecting surface cracks in high concrete dams under weak GNSS according to claim 1 is characterized by: The high-precision inertial navigation system is installed inside the UAV platform and includes an accelerometer, a gyroscope, and a barometer. The output ends of the accelerometer, gyroscope, and barometer are all connected to the input end of the onboard processor.

3. The UAV positioning system for detecting surface cracks in high concrete dams under weak GNSS according to claim 1 is characterized by: There are four binocular vision cameras, which are respectively arranged on the four side walls outside the UAV platform. The binocular vision cameras are 90-degree viewing angle width lenses.

4. The UAV positioning system for detecting surface cracks in high concrete dams under weak GNSS according to claim 1 is characterized by: The infrared sensing module and obstacle avoidance radar are both installed on the external side wall of the UAV platform.

5. The UAV positioning system for detecting surface cracks in high concrete dams under weak GNSS according to claim 1 is characterized by: The onboard processor is the NVIDIA TX2 onboard processor.

Images