Unmanned aerial vehicle road intelligent cruise system based on internal signals

Abstract

The invention discloses an unmanned aerial vehicle road intelligent cruise system based on internal signals, and relates to the field of unmanned aerial vehicle cruise. When an unmanned aerial vehicle performs road inspection, data information around an inspection road is obtained by using a laser radar sensor and a camera, and the obtained two different data are fused; more comprehensive and more accurate perception of the environment is realized so as to improve the environment perception precision of a subsequent built-in map chip, the current position of the unmanned aerial vehicle on the inspection road is acquired by using a scene matching mode, and during path planning, an unmanned aerial vehicle autonomous flight system masters regional map information, so that the path planning efficiency is improved. In this way, inspection can be intelligently completed without external signals, the problem that the unmanned aerial vehicle is difficult to complete road inspection work due to the fact that the unmanned aerial vehicle gets lost in a district with weak satellite signals and dark light can be avoided, the unmanned aerial vehicle inspection can achieve a better effect, and the practicability of the unmanned aerial vehicle is further improved.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle cruising, and in particular to an unmanned aerial vehicle road intelligent cruising system based on internal signals. Background Art

[0002] Road inspection refers to the regular inspection and testing of road facilities to ensure road safety and good operating conditions. The use of drones for road inspection can cover a wider area in a shorter period of time, achieving monitoring and reconnaissance of a large area. At the same time, it can reduce personnel operations and reduce human risks in complex or dangerous environments.

[0003] In the prior art, such as the Chinese publication number: CN108198417B, the invention provides a road inspection system based on drones, a road inspection system based on drones, including: a ground control center and a drone; the drone includes a control module, a camera module, a wireless transmission module and a GPS positioning module, wherein: the camera module is used to capture road images; the GPS module is used to accurately locate the drone and obtain real-time positioning information of the drone; the wireless transmission module is used to send the road image and positioning information to the ground control center, and receive the inspection plan sent from the ground control center; the control module is used to control the flight path of the drone according to the inspection plan; the ground control center is used to receive the image and positioning information sent from the drone, and send the inspection plan to the drone. The invention obtains road images through drones and monitors road conditions in real time, with strong intelligence and high accuracy.

[0004] In the prior art, such as the Chinese publication number: CN113467519B, the application provides a method and system for automatic cruising of unmanned aerial vehicles, the method is applied to the automatic cruising system of unmanned aerial vehicles, the system includes unmanned aerial vehicles and unmanned aerial vehicle hangars, the method includes: the unmanned aerial vehicle hangar responds to the command of the user terminal to open the door, and moves the helipad carrying the unmanned aerial vehicle in the closed state from the first preset position in the unmanned aerial vehicle hangar to the second preset position at the door opening of the unmanned aerial vehicle hangar; the starting current is transmitted to the unmanned aerial vehicle through the internal mechanical arm to turn it into the open state; the unmanned aerial vehicle responds to the command of the user terminal to start cruising and collect remote sensing images during the cruising; the unmanned aerial vehicle returns to the helipad after reaching the end of the cruising route; after arriving at the helipad, the remote sensing image is uploaded to the server; after the remote sensing image is uploaded, if no control command is received within the preset time, the unmanned aerial vehicle becomes closed. This application can realize the full automation of unmanned aerial vehicle flight, greatly reducing the application threshold of unmanned aerial vehicle remote sensing.

[0005] To sum up, when drones are conducting inspections, the use of an autonomous flight system allows the drones to conduct road inspections along a set route. However, during the road inspection process, it is inevitable that large obstacles will block the inspection road, such as tunnels, underpasses, etc. In this case, the satellite signal is weak and the light is dim. At this time, the drone's perception system and autonomous navigation technology can easily lose the signal, and the drone is very likely to get lost during inspections, making it difficult to complete road inspections. Summary of the invention

[0006] The purpose of the present invention is to solve the problem that the UAV road intelligent cruise system based on internal signals loses the signal and becomes lost in places with weak satellite signals and dim light, making it difficult to complete road inspection work.

[0007] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0008] The UAV road intelligent cruise system based on internal signals includes the following steps:

[0009] S1. During the inspection process, the drone obtains data about the inspection environment through the sensors it carries;

[0010] S2, the processing module fuses the acquired data and transmits the fused data to the built-in map chip of the drone;

[0011] S3, the built-in map chip matches the acquired environmental data;

[0012] S4, the planning module plans the inspection path of the UAV according to the matching results;

[0013] S5. The autonomous flight system controls the drone to intelligently complete the inspection according to the path planning content.

[0014] Preferably, in step S1, the sensor includes a laser radar sensor and a camera, the laser radar sensor is used to sense the information of the surrounding environment during inspection to obtain point cloud data, and the camera is used to obtain image data of the surrounding environment during inspection in real time.

[0015] Preferably, in step S2, the processing module uses Gaussian filtering to denoise the acquired image data to avoid the presence of noise in the image data affecting subsequent feature extraction, thereby further improving the accuracy of image recognition. Thereafter, feature points of the denoised image data and point cloud data are extracted respectively, and the extracted feature points are fused. The fusion of the two types of data can achieve a more comprehensive and accurate perception of the environment, thereby improving the environmental perception accuracy of the subsequent built-in map chip.

[0016] Preferably, in step S2, the Gaussian filtering formula is: Where: G(x, y) represents Gaussian distribution, x and y are the coordinates of the filter kernel, δ is the standard deviation, π is pi, and e is the base of the natural logarithm.

[0017] Preferably, in step S3, the built-in map chip is used to store and process map data, provide information about the environment to be inspected, and simultaneously achieve matching between the map and data around the inspection road environment. The map data may be a static map input in advance or a dynamic map updated in real time.

[0018] Preferably, in step S3, the built-in map chip uses scene matching to obtain the current position of the drone by matching the map data frame stored in advance with the surrounding data frame of the currently perceived inspection environment.

[0019] Preferably, in step S3, the scene matching to obtain the current position of the drone includes the following sub-steps:

[0020] S31, extracting feature points from the built-in map chip and environmental data respectively;

[0021] S32, for the feature points and their descriptors extracted from the two images, find the corresponding relationship between them based on similarity matching;

[0022] S33, matching points are determined, and then the corresponding relationship between the two images is obtained to obtain the current position of the UAV.

[0023] Preferably, in step S31, the extracted feature points include edge points and corner points of the inspection environment, and the grayscale value of each pixel in the image of the map chip and the environmental data differs from the grayscale values ​​of its surrounding pixels to find pixels having the features of the edge points and the corner points.

[0024] Preferably, in step S31, the pixel point determines whether the image structure at the pixel point is the edge point or the corner point by calculating the response function of the pixel point, and the calculation formula of the response function is: R = Det (N) - K × Trace (N) 2 , where: R is the response function, Det(N) is the determinant of the autocorrelation matrix within the image, K is a constant, and Trace(N) is the trace of the autocorrelation matrix within the image.

[0025] Preferably, in step S4, the planning module determines the position information of each target point of the inspection road on the built-in map chip according to the matching result, so that the drone can grasp the inspection road map information internally, so that the inspection can be completed intelligently without external signals.

[0026] The beneficial effects of the present invention are:

[0027] When inspecting roads, the drone of the present invention uses a laser radar sensor and a camera to obtain data information around the inspection road, and performs denoising processing on the image data obtained by the camera to prevent the presence of noise in the image data from affecting subsequent feature extraction, further improving the accuracy of image recognition, and fusing the two different data obtained to achieve a more comprehensive and accurate perception of the environment, so as to improve the environmental perception accuracy of the subsequent built-in map chip, and use scene matching to obtain the current position of the drone on the inspection road. When performing path planning, the drone's autonomous flight system grasps the regional map information, so that the inspection can be completed intelligently without the need for external signals, and the problem of the drone being lost in areas with weak satellite signals and dim light and having difficulty completing road inspections can be avoided, so that the drone inspection achieves better results and further improves the practicality of the drone. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 The present invention is a flowchart of the steps of an embodiment of the UAV road intelligent cruise system based on internal signals.

[0029] Figure 2 The present invention is a flowchart of the steps of obtaining the current position of the drone by scene matching in the drone road intelligent cruise system based on internal signals. DETAILED DESCRIPTION

[0030] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further described below in conjunction with specific embodiments, but the following embodiments are only preferred embodiments of the present invention, not all. Based on the embodiments in the implementation mode, other embodiments obtained by those skilled in the art without creative work all belong to the protection scope of the present invention. The experimental methods in the following embodiments, unless otherwise specified, are conventional methods, and the materials, reagents, etc. used in the following embodiments, unless otherwise specified, can all be obtained from commercial channels.

[0031] Combine the following Figure 1 and Figure 2 The present invention is further described.

[0032] The UAV road intelligent cruise system based on internal signals includes the following steps:

[0033] S1. During the inspection process, the drone obtains data about the inspection environment through the sensors it carries.

[0034] The present invention is further configured as follows: the sensor includes a laser radar sensor and a camera, the laser radar sensor is used to sense the information of the surrounding environment during inspection and obtain point cloud data, and the camera is used to obtain image data of the surrounding environment during inspection in real time.

[0035] S2. The processing module fuses the acquired data and transmits the fused data to the built-in map chip of the drone.

[0036] The present invention is further configured as follows: in step S2, the processing module uses Gaussian filtering to perform denoising on the acquired image data, so as to avoid the presence of noise in the image data affecting subsequent feature extraction, thereby further improving the accuracy of image recognition, and then extracting feature points of the denoised image data and point cloud data respectively, and fusing the extracted feature points. The fusion of the two types of data can achieve a more comprehensive and accurate perception of the environment, thereby improving the environmental perception accuracy of the subsequent built-in map chip.

[0037] The present invention is further configured as follows: in step S2, the Gaussian filtering formula is: Where: G(x, y) represents Gaussian distribution, x and y are the coordinates of the filter kernel, δ is the standard deviation, π is pi, and e is the base of the natural logarithm.

[0038] S3, the built-in map chip matches the acquired environmental data.

[0039] The present invention is further configured as follows: the built-in map chip is used to store and process map data, provide information on the environment to be inspected, and simultaneously achieve matching of the map with data around the inspection road environment. The map data can be a static map input in advance or a dynamic map updated in real time.

[0040] The present invention is further configured as follows: the built-in map chip obtains the current position of the drone by matching the map data frame stored in advance with the surrounding data frame of the currently perceived inspection environment using scene matching.

[0041] The present invention is further configured as follows: the scene matching to obtain the current position of the drone comprises the following sub-steps:

[0042] S31, extracting feature points from the built-in map chip and environmental data respectively.

[0043] S32, for the feature points and their descriptors extracted from the two images, find the corresponding relationship between them based on similarity matching;

[0044] S33, matching points are determined, and then the corresponding relationship between the two images is obtained to obtain the current position of the UAV.

[0045] The present invention is further configured as follows: the extracted feature points include edge points and corner points of the inspection environment, the grayscale value of each pixel point in the image of the map chip and the environmental data differs from the grayscale value of its surrounding pixels, and the pixel points having the features of the edge points and the corner points are found.

[0046] The present invention is further configured as follows: the pixel point determines whether the image structure at the pixel point is the edge point and the corner point by calculating the response function of the pixel point, and the calculation formula of the response function is: R = Det (N) - K × Trace (N) 2 , where: R is the response function, Det(N) is the determinant of the autocorrelation matrix within the image, K is a constant, and Trace(N) is the trace of the autocorrelation matrix within the image.

[0047] S5. The planning module plans the inspection path of the UAV according to the matching results.

[0048] The present invention is further configured as follows: the planning module determines the position information of each target point on the inspection road on the built-in map chip according to the matching result, so that the drone can grasp the inspection road map information internally, so that the inspection can be completed intelligently without the need for external signals, and the problem of the drone being unable to complete the road inspection work due to being lost in areas with weak satellite signals and dim light can be avoided.

[0049] S6. The autonomous flight system controls the drone to intelligently complete the inspection according to the path planning content.

[0050] To sum up, when the drone of the present invention inspects the road, it uses a lidar sensor and a camera to obtain data information around the inspection road, and performs denoising on the image data obtained by the camera to avoid the presence of noise in the image data affecting subsequent feature extraction, further improving the accuracy of image recognition, and fusing the two different data obtained to achieve a more comprehensive and accurate perception of the environment, so as to improve the environmental perception accuracy of the subsequent built-in map chip, and use scene matching to obtain the current position of the drone on the inspection road. When performing path planning, the drone's autonomous flight system masters the regional map information, so that the inspection can be completed intelligently without the need for external signals, which can avoid the problem that the drone is lost in areas with weak satellite signals and dim light, and it is difficult to complete the road inspection work, so that the drone inspection can achieve better results and further improve the practicality of the drone.

[0051] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. The UAV road intelligent cruise system based on internal signals is characterized by: The following steps are involved: S1. During the inspection process, the drone obtains data about the inspection environment through the sensors it carries; S2, the processing module fuses the acquired data and transmits the fused data to the built-in map chip of the drone; S3, the built-in map chip matches the acquired environmental data; S4, the planning module plans the inspection path of the UAV according to the matching results; S5. The autonomous flight system controls the drone to intelligently complete the inspection according to the path planning content.

2. The UAV road intelligent cruise system based on internal signals according to claim 1 is characterized in that: In step S1, the sensor includes a laser radar sensor and a camera, wherein the laser radar sensor is used to sense the surrounding environment information to obtain point cloud data, and the camera is used to obtain image data of the surrounding environment in real time.

3. The UAV road intelligent cruising system based on internal signals according to claim 1 is characterized in that: In step S2, the processing module uses Gaussian filtering to perform denoising on the acquired image data, then extracts feature points of the denoised image data and point cloud data respectively, and fuses the extracted feature points.

4. The UAV road intelligent cruising system based on internal signals according to claim 3 is characterized in that: In step S2, the Gaussian filtering formula is: Where: G(x, y) represents Gaussian distribution, x and y are the coordinates of the filter kernel, δ is the standard deviation, π is pi, and e is the base of the natural logarithm.

5. The UAV road intelligent cruising system based on internal signals according to claim 1 is characterized in that: In step S3, the built-in map chip is used to store and process map data, provide information about the environment to be inspected, and match the map with data around the inspection road environment. The map data can be a static map input in advance or a dynamic map updated in real time.

6. The UAV road intelligent cruise system based on internal signals according to claim 5 is characterized in that: In step S3, the built-in map chip uses scene matching to obtain the current position of the drone by matching the map data frame stored in advance with the surrounding data frame of the currently perceived inspection environment.

7. The UAV road intelligent cruising system based on internal signals according to claim 6 is characterized in that: In step S3, the scene matching to obtain the current position of the drone includes the following sub-steps: S31, extracting feature points from the built-in map chip and environmental data respectively; S32, for the feature points extracted from the two images, finding the corresponding relationship between them based on similarity matching; S33, matching points are determined, and then the corresponding relationship between the two images is obtained to obtain the current position of the UAV.

8. The UAV road intelligent cruising system based on internal signals according to claim 7 is characterized in that: In step S31, the extracted feature points include edge points and corner points of the inspection environment, the grayscale value of each pixel in the image of the map chip and the environmental data is different from the grayscale value of its surrounding pixels, and the pixel points with the edge point and corner point features are found.

9. The UAV road intelligent cruising system based on internal signals according to claim 8 is characterized in that: In step S31, the pixel point determines whether the image structure at the pixel point is the edge point or the corner point by calculating the response function of the pixel point. The calculation formula of the response function is: R = Det (N) - K × Trace (N) 2 , where: R is the response function, Det(N) is the determinant of the autocorrelation matrix within the image, K is a constant, and Trace(N) is the trace of the autocorrelation matrix within the image.

10. The UAV road intelligent cruising system based on internal signals according to claim 1 is characterized in that: In step S4, the planning module determines the location information of each target point on the inspection road on the built-in map chip according to the matching result.

Images