Unmanned aerial vehicle inspection method and device, unmanned aerial vehicle, electronic device, and storage medium

Abstract

The application relates to the technical field of unmanned aerial vehicles, and provides an unmanned aerial vehicle inspection method and device, an unmanned aerial vehicle, electronic equipment and a storage medium. The method comprises the following steps: firstly, after receiving an abnormality detection signal sent by an acoustic imaging component carried on the unmanned aerial vehicle, autonomous cruising is paused, and an abnormality detection position is calculated based on the abnormality detection signal; then, flight is performed around the abnormality detection position, the acoustic imaging component is controlled to shoot multi-angle detection images of the abnormality detection position; finally, the position where the autonomous cruising is paused is returned to, and the autonomous cruising is continued. The unmanned aerial vehicle inspection method can realize intelligent switching of the cruising state according to whether the unmanned aerial vehicle receives the abnormality detection signal, and can shoot multi-angle detection images of the abnormality detection position after the intelligent switching, so that sufficient image information of the abnormality detection position can be provided for professional inspection personnel, the professional inspection personnel can obtain sufficient information without re-inspection, and the workload of the professional inspection personnel can be greatly reduced.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) technology, and in particular to a UAV inspection method, apparatus, UAV, electronic device, and storage medium. Background Technology

[0002] Currently, drones are widely used for the inspection of power lines, large equipment, and other objects.

[0003] The existing inspection method typically involves assigning power line patrol personnel to the site with a drone according to a work plan, manually operating the drone to conduct aerial inspections of the target objects. When anomalies are found, the relevant information about the anomalies is recorded, and the inspection continues.

[0004] However, the recorded information is limited, and power line patrol personnel still need to conduct follow-up inspections, which increases labor costs. Summary of the Invention

[0005] This invention provides a method, apparatus, drone, electronic device, and storage medium for drone inspection, in order to overcome the deficiencies in the prior art.

[0006] This invention provides a method for unmanned aerial vehicle (UAV) inspection, comprising:

[0007] If an anomaly detection signal is received from the acoustic imaging component mounted on the drone, the autonomous cruise is paused, and the anomaly detection location is determined based on the anomaly detection signal.

[0008] The system flies around the anomaly detection location and controls the acoustic imaging component to capture multi-angle detection images of the anomaly detection location.

[0009] Return to the position where the autonomous cruise was paused, and then resume the autonomous cruise.

[0010] According to the present invention, a drone inspection method is provided, which involves flying around the anomaly detection location and controlling the acoustic imaging component to capture multi-angle detection images of the anomaly detection location, including:

[0011] Determine multiple shooting points of the acoustic imaging component at different angles relative to the anomaly detection location, and plan a flight path that flies sequentially from the anomaly detection location to each shooting point.

[0012] The system flies along the flight path and, upon reaching each shooting point, controls the acoustic imaging component to face the anomaly detection location and captures a detection image at the corresponding angle.

[0013] According to the present invention, a drone inspection method is provided, which involves flying along the flight path, including:

[0014] If there is an obstacle within the preset range of any shooting point, then skip that shooting point and continue flying to the next shooting point;

[0015] If there is an obstacle outside the preset range of any shooting point, a new sub-flight path is planned to the shooting point, and the aircraft flies along the sub-flight path to the shooting point.

[0016] According to a UAV inspection method provided by the present invention, determining the shooting points of the acoustic imaging component at multiple different angles relative to the anomaly detection location includes:

[0017] A preset spherical surface centered on the anomaly detection location is determined, and the shooting points are evenly distributed on the preset spherical surface;

[0018] Wherein, the radius of the preset sphere is a preset multiple of the distance between the drone's position when the anomaly detection signal is received and the anomaly detection position.

[0019] According to a UAV inspection method provided by the present invention, the anomaly detection signal includes the azimuth information and distance information of the abnormal sound source;

[0020] Accordingly, determining the anomaly detection location based on the anomaly detection signal includes:

[0021] Determine the location of the drone when the anomaly detection signal is received;

[0022] The anomaly detection location is determined based on the drone's location, orientation information, and distance information.

[0023] The present invention also provides a drone inspection device, comprising:

[0024] The computing module is used to pause autonomous navigation and determine the location of the anomaly based on the anomaly detection signal if it receives an anomaly detection signal sent by the acoustic imaging component mounted on the UAV.

[0025] The control module is used to fly around the anomaly detection location and control the acoustic imaging component to capture multi-angle detection images of the anomaly detection location;

[0026] The cruise module is used to return to the position where the autonomous cruise was paused and to resume the autonomous cruise.

[0027] The present invention also provides a drone, comprising: a drone body and an acoustic imaging component, wherein the acoustic imaging component is mounted on the drone body and is communicatively connected to the drone body;

[0028] The acoustic imaging component is used to collect acoustic signals along the inspection path of the UAV body and send an abnormality detection signal to the UAV body when the acoustic signal is abnormal.

[0029] The UAV body is used to execute the above-described UAV inspection method when it receives the anomaly detection signal.

[0030] According to the present invention, a drone further includes: a remote control terminal corresponding to the drone body, the remote control terminal being configured with a display module, and the acoustic imaging component being communicatively connected to the remote control terminal;

[0031] The acoustic imaging component is also used to generate a real-time video signal and generate a heat map when the acoustic signal is abnormal. The heat map is then superimposed on the real-time video signal to obtain a superimposed signal.

[0032] The acoustic imaging component is also used to send the superimposed signal to the remote control terminal for display via the display module.

[0033] According to the present invention, a drone further includes: a remote control terminal corresponding to the drone body, the remote control terminal being configured with a display module, and the acoustic imaging component being communicatively connected to the remote control terminal;

[0034] The acoustic imaging component is also used to generate a real-time video signal, send the real-time video signal to the remote control terminal, and send the abnormality detection signal to the remote control terminal when the acoustic signal is abnormal.

[0035] The remote control terminal is also used to generate a heat map based on the anomaly detection signal, superimpose the heat map onto the real-time video signal to obtain a superimposed signal, and display it through the display module.

[0036] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the UAV inspection method as described above.

[0037] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the UAV inspection method as described above.

[0038] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the UAV inspection method as described above.

[0039] This invention provides a drone inspection method, apparatus, drone, electronic device, and storage medium. The method first pauses autonomous navigation upon receiving an anomaly detection signal from the acoustic imaging component mounted on the drone, and determines the anomaly detection location based on the signal. Then, it flies around the anomaly detection location, controlling the acoustic imaging component to capture multi-angle detection images of that location. Finally, it returns to the position where autonomous navigation was paused and resumes autonomous navigation. This drone inspection method intelligently switches its navigation state based on whether the drone receives an anomaly detection signal. After intelligent switching, it can capture multi-angle detection images of the anomaly detection location, providing professional inspectors with sufficient image information of the anomaly detection location. This allows professional inspectors to obtain sufficient information without repeated inspections, significantly reducing their workload, lowering labor costs, and improving inspection efficiency. Furthermore, because a single inspection captures the detection location and its multi-angle detection images, the effectiveness of the inspection process is enhanced, avoiding resource waste caused by multiple inspection processes. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on the drawings described below without creative effort.

[0041] Figure 1 This is a flowchart illustrating the UAV inspection method provided by the present invention;

[0042] Figure 2 This is a schematic diagram of the structure of the drone inspection device provided by the present invention;

[0043] Figure 3 This is one of the structural schematic diagrams of the UAV provided by the present invention;

[0044] Figure 4 This is the second structural schematic diagram of the UAV provided by the present invention;

[0045] Figure 5 This is the third structural schematic diagram of the UAV provided by the present invention;

[0046] Figure 6 This is a schematic diagram of the acoustic imaging component in the UAV provided by the present invention;

[0047] Figure 7 A flowchart illustrating the inspection method based on unmanned aerial vehicles provided by this invention;

[0048] Figure 8This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0050] The terms "first" and "second" in the specification and claims of this invention may explicitly or implicitly include one or more of those features. In the description of the invention, unless otherwise stated, "a plurality of" means two or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0051] Because existing inspection methods record limited information about anomalies when they exist on the target object, power line patrol personnel still need to conduct re-inspections. This not only increases labor costs and reduces inspection efficiency, but also weakens the effectiveness of the inspection process.

[0052] Based on this, this invention provides a drone inspection method to solve the above-mentioned technical problems existing in the prior art.

[0053] Figure 1 This is a flowchart illustrating a drone inspection method provided in an embodiment of the present invention, as shown below. Figure 1 As shown, the method includes:

[0054] S1. If an abnormality detection signal is received from the acoustic imaging component mounted on the drone, the autonomous cruise is paused, and the abnormality detection location is determined based on the abnormality detection signal.

[0055] S2, fly around the anomaly detection position, and control the acoustic imaging component to capture multi-angle detection images of the anomaly detection position;

[0056] S3, return to the position where the autonomous cruise was paused, and resume the autonomous cruise.

[0057] Specifically, the drone inspection method provided in this embodiment of the invention uses a drone as the executing entity. The drone may be equipped with an acoustic imaging component, and the drone can communicate with the acoustic imaging component. This acoustic imaging component can have built-in sound source localization and imaging algorithms, displaying the spatial distribution of sound sources in real time in the form of a heat map. It has functions such as partial discharge identification, gas leak detection, and abnormal noise localization; it can be used for indoor and outdoor online sound monitoring in industrial scenarios such as substations, chemical plants, and wind turbine nacelles.

[0058] Correspondingly, by mounting acoustic imaging components on drones, drones equipped with acoustic imaging components can perform routine inspections and fixed-point inspections of high-voltage lines in mid-air to detect partial discharges, as well as inspections of gas storage tanks to detect gas leaks and locate the leak points, and inspections of wind turbine nacelles to detect abnormal noises and locate the noise points.

[0059] Here, the drone can autonomously cruise the target area to complete the inspection task. Autonomous cruise refers to the drone flying according to a pre-set cruise path, monitoring and detecting the target area in real time during flight. During the drone's autonomous inspection, the acoustic imaging component can acquire inspection images and acoustic signals along the inspection path in real time, and send an anomaly detection signal to the drone when the acoustic signal is abnormal. This anomaly detection signal can include the azimuth information of the abnormal sound source's location and its distance from the acoustic imaging component. The abnormal sound source can be an abnormal target object within the acoustic imaging component's imaging area.

[0060] First, the drone can execute step S1, pausing autonomous cruise upon receiving an anomaly detection signal from the acoustic imaging component, and recording its current position. This position can be measured using the drone's built-in Global Positioning System (GPS). The drone's position can be represented by latitude and longitude.

[0061] Subsequently, the anomaly detection signal can be used to determine the anomaly detection location. This anomaly detection location can also be represented by latitude and longitude, for example, it can be calculated by combining the recorded UAV position with the azimuth and distance information in the anomaly detection signal.

[0062] Then, the drone can execute step S2, flying around the anomaly detection location and controlling the acoustic imaging component to capture multi-angle detection images of the anomaly detection location. Multi-angle detection images refer to detection images from multiple different angles relative to the anomaly detection location; here, multiple different angles refer to at least two different angles. In this process, a flight path can be planned first based on the anomaly detection location. The flight path can include multiple shooting points at different angles relative to the anomaly detection location. When the drone flies along the flight path and reaches each shooting point, it can control the acoustic imaging component to face the anomaly detection location and capture a detection image at the corresponding angle.

[0063] Finally, the drone can execute step S3. After the acoustic imaging component captures detection images from multiple angles, it can continue flying to the position where autonomous cruise is paused, which is the drone position recorded when autonomous cruise was paused in step S1. From this position, it can resume autonomous cruise to complete the remaining inspection tasks.

[0064] Therefore, it can be seen that the UAV has two cruise states during the entire inspection process: one is autonomous cruise state, in which the UAV flies according to a pre-set cruise path and monitors the target area in real time during flight; the other is multi-angle cruise state targeting the anomaly detection location after receiving an anomaly detection signal from the acoustic imaging component. The two cruise states are intelligently switched based on whether the UAV receives an anomaly detection signal.

[0065] The UAV inspection method provided in this embodiment of the invention first pauses autonomous navigation upon receiving an anomaly detection signal from the acoustic imaging component mounted on the UAV, and determines the anomaly detection location based on the anomaly detection signal. Then, it flies around the anomaly detection location, controlling the acoustic imaging component to capture multi-angle detection images of the anomaly detection location. Finally, it returns to the position where autonomous navigation was paused and resumes autonomous navigation. This UAV inspection method can intelligently switch the navigation state based on whether the UAV receives an anomaly detection signal, and can capture multi-angle detection images of the anomaly detection location after intelligent switching. This provides professional inspectors with sufficient image information of the anomaly detection location, allowing them to obtain sufficient information without re-inspection, greatly reducing the workload of professional inspectors, lowering labor costs, and improving inspection efficiency. Furthermore, since a single inspection process acquires a detection location and its multi-angle detection images, the effectiveness of the inspection process is enhanced, avoiding the resource waste caused by multiple inspection processes.

[0066] Based on the above embodiments, the UAV inspection method provided in this embodiment of the invention flies around the anomaly detection location and controls the acoustic imaging component to capture multi-angle detection images of the anomaly detection location, including:

[0067] Determine multiple shooting points of the acoustic imaging component at different angles relative to the anomaly detection location, and plan a flight path that flies sequentially from the anomaly detection location to each shooting point.

[0068] The system flies along the flight path and, upon reaching each shooting point, controls the acoustic imaging component to face the anomaly detection location and captures a detection image at the corresponding angle.

[0069] Specifically, in this embodiment of the invention, during the process of the UAV flying around the anomaly detection location and controlling the acoustic imaging component to capture multi-angle detection images of the anomaly detection location, multiple shooting points of the acoustic imaging component at different angles relative to the anomaly detection location can be determined first. Here, the multiple shooting points at different angles can be set around the anomaly detection location, and the distance between each shooting point and the anomaly detection location can be the same or different, and the spacing between each shooting point can be the same or different; no specific limitation is made here.

[0070] Subsequently, a flight path can be planned to fly sequentially from the anomaly detection location to each shooting point. This flight path includes all shooting points, and all shooting points are arranged in the order in which the drone passes through. The planning criteria for the flight path can comprehensively consider one or more factors such as the drone's flight time, flight length, flight altitude, and standby time. Other factors can also be added during the planning process, which are not specifically limited here.

[0071] Subsequently, the drone can fly along the aforementioned flight path, and upon reaching each shooting point, it can control itself to change its attitude so that the acoustic imaging component is oriented towards the anomaly detection location, thereby capturing a detection image at the corresponding angle of the anomaly detection location. Specifically, upon reaching each shooting point, the drone can pause its flight, then control the acoustic imaging component to take a picture, and after taking the picture, it continues flying to the next shooting point on the flight path. This improves the quality of the obtained detection images and prevents image quality degradation caused by drone vibrations during flight.

[0072] In this embodiment of the invention, by determining multiple shooting points at different angles and planning flight paths to obtain detection images at corresponding angles, the efficiency of shooting detection images can be improved, the inspection efficiency can be enhanced, and the control of the drone can be made more standardized.

[0073] Based on the above embodiments, the UAV inspection method provided in this embodiment of the invention, flying along the flight path, includes:

[0074] If there is an obstacle within the preset range of any shooting point, then skip that shooting point and continue flying to the next shooting point;

[0075] If there is an obstacle outside the preset range of any shooting point, a new sub-flight path is planned to the shooting point, and the aircraft flies along the sub-flight path to the shooting point.

[0076] Specifically, in this embodiment of the invention, if the UAV does not encounter any obstacles while flying along its flight path, it needs to fly to all the shooting points in sequence and capture detection images at the corresponding angles at each shooting point. However, if obstacles are encountered, different situations need to be handled separately.

[0077] In other words, for each shooting point on the flight path, the drone needs to determine whether there are obstacles within and outside a preset range. If obstacles exist within the preset range, it performs the operation in Scenario 1; if obstacles exist outside the preset range, it performs the operation in Scenario 2. The preset range can be the minimum area within which the drone can reach the corresponding shooting point by changing its path. It can be set as needed, for example, it can be set as a circular area centered on the shooting point with a preset radius, such as 0.5m, 1m, or 3m.

[0078] Scenario 1: Obstacles appear within the preset range of the shooting point. If an obstacle exists within the preset range of any shooting point, the camera will skip that shooting point and continue flying to the next shooting point. That is, the camera will abandon shooting at any shooting point because there is an obstacle within the preset range that cannot be avoided, and thus no detection image will be obtained from the corresponding angle.

[0079] Scenario 2: Obstacles appear outside the preset range of the shooting point. If there are obstacles outside the preset range of any shooting point, a new sub-flight path is planned for that shooting point, and the camera flies along the sub-flight path to that shooting point. In other words, although there are obstacles outside the preset range of any shooting point, they can be reached through the newly planned sub-flight path. Therefore, the camera can fly along the sub-flight path to that shooting point to take a picture and obtain a detection image at the corresponding angle.

[0080] In this embodiment of the invention, the presence of obstacles is taken into account during the flight of the UAV along its flight path, which makes the UAV inspection method more applicable.

[0081] Based on the above embodiments, the UAV inspection method provided in this embodiment of the invention determines the shooting points of the acoustic imaging component at multiple different angles relative to the anomaly detection location, including:

[0082] A preset spherical surface centered on the anomaly detection location is determined, and the shooting points are evenly distributed on the preset spherical surface;

[0083] Wherein, the radius of the preset sphere is a preset multiple of the distance between the drone's position when the anomaly detection signal is received and the anomaly detection position. The preset multiple can be less than or equal to 1, or greater than 1.

[0084] Specifically, when determining multiple shooting points at different angles, a preset sphere centered on the anomaly detection location can be first defined. The radius of this preset sphere can be equal to or smaller than the distance between the drone's position when it receives the anomaly detection signal from the acoustic imaging component and the anomaly detection location. Alternatively, the radius of this preset sphere can be larger than the distance between the drone's position when it receives the anomaly detection signal from the acoustic imaging component and the anomaly detection location.

[0085] Then, multiple shooting points at different angles are evenly distributed on the preset spherical surface. The number of shooting points can be set as needed. For example, six shooting points at different angles can be evenly distributed on the preset spherical surface, located at the top, bottom, left, right, front, and back of the drone's position.

[0086] When the radius of the preset sphere is equal to the distance between the drone's position and the anomaly detection position, the detection images obtained by the acoustic imaging component at each shooting point have the same shooting angle as the inspection images taken at the drone's position. However, when the radius of the preset sphere is smaller than the distance between the drone's position and the anomaly detection position, the shooting angle of the detection images obtained by the acoustic imaging component at each shooting point has a larger shooting angle than the inspection images taken at the drone's position. This can shorten the distance between the drone and the anomaly detection position, thus magnifying the anomaly detection position in the detection image and making it easier for professional inspectors to observe the details of the anomaly detection position.

[0087] When the radius of the preset sphere is greater than the distance between the drone position and the anomaly detection position, the shooting angle of the detection image obtained by the acoustic imaging component at each shooting point is smaller than the shooting angle of the inspection image obtained at the drone position. This can magnify the distance between the drone and the anomaly detection position, so that more of the environment around the anomaly detection position appears in the detection image, making it easier for professional inspectors to observe the surrounding environment of the anomaly detection position.

[0088] In this embodiment of the invention, by uniformly distributing multiple shooting points at different angles on a preset sphere centered on the anomaly detection location, professional inspectors can quickly pinpoint the anomaly detection location by observing the distribution of each detection image. Setting the radius of the preset sphere to be less than or equal to the distance between the drone's position and the anomaly detection location provides professional inspectors with multiple options, enhancing their drone inspection experience.

[0089] Based on the above embodiments, the anomaly detection signal includes the directional and distance information of the abnormal sound source;

[0090] Accordingly, determining the anomaly detection location based on the anomaly detection signal includes:

[0091] Determine the location of the drone when the anomaly detection signal is received;

[0092] The anomaly detection location is determined based on the drone's location, orientation information, and distance information.

[0093] Specifically, in this embodiment of the invention, since the anomaly detection signal may include the azimuth information and distance information of the abnormal sound source, when calculating the anomaly detection location, the position of the UAV when the anomaly detection signal is received can be determined first, and then the anomaly detection location can be determined by using the UAV position in combination with the azimuth information and distance information.

[0094] Here, a sphere can be drawn with the drone's location as the center and the distance information as the radius, and a straight line corresponding to the orientation information can be drawn, with the straight line passing through the drone's location. The intersection of the straight line and the sphere is the anomaly detection location.

[0095] In this embodiment of the invention, the drone can quickly obtain the anomaly detection location by combining the drone position recorded when receiving the anomaly detection signal with the anomaly detection signal, thereby improving the drone inspection efficiency.

[0096] like Figure 2 As shown, based on the above embodiments, this embodiment of the invention also provides a drone inspection device, including:

[0097] The calculation module 21 is used to pause autonomous cruise and determine the location of the anomaly based on the anomaly detection signal if it receives an anomaly detection signal sent by the acoustic imaging component mounted on the UAV.

[0098] Control module 22 is used to fly around the anomaly detection position and control the acoustic imaging component to capture multi-angle detection images of the anomaly detection position;

[0099] Cruise module 23 is used to return to the position where the autonomous cruise was paused and to resume the autonomous cruise.

[0100] Based on the above embodiments, the control module of the UAV inspection device provided in this embodiment of the invention is specifically used for:

[0101] Determine multiple shooting points of the acoustic imaging component at different angles relative to the anomaly detection location, and plan a flight path that flies sequentially from the anomaly detection location to each shooting point.

[0102] The system flies along the flight path and, upon reaching each shooting point, controls the acoustic imaging component to face the anomaly detection location and captures a detection image at the corresponding angle.

[0103] Based on the above embodiments, the control module of the UAV inspection device provided in this embodiment of the invention is specifically used for:

[0104] If there is an obstacle within the preset range of any shooting point, then skip that shooting point and continue flying to the next shooting point;

[0105] If there is an obstacle outside the preset range of any shooting point, a new sub-flight path is planned to the shooting point, and the aircraft flies along the sub-flight path to the shooting point.

[0106] Based on the above embodiments, the control module of the UAV inspection device provided in this embodiment of the invention is further specifically used for:

[0107] A preset spherical surface centered on the anomaly detection location is determined, and the shooting points are evenly distributed on the preset spherical surface;

[0108] Wherein, the radius of the preset sphere is a preset multiple of the distance between the drone's position and the anomaly detection position.

[0109] Based on the above embodiments, the UAV inspection device provided in this embodiment of the invention includes the location information and distance information of the abnormal sound source in the abnormal detection signal;

[0110] Accordingly, the computing module is specifically used for:

[0111] Determine the location of the drone when the anomaly detection signal is received;

[0112] The anomaly detection location is determined based on the drone's location, orientation information, and distance information.

[0113] Specifically, the functions of each module in the UAV inspection device provided in this embodiment of the invention correspond one-to-one with the operation flow of each step in the above method-like embodiments, and the achieved effects are also the same. For details, please refer to the above embodiments, and this will not be repeated in this embodiment of the invention.

[0114] like Figure 3 and Figure 4As shown, based on the above embodiments, this embodiment of the invention also provides a drone, including: a drone body 31 and an acoustic imaging component 32. The acoustic imaging component 32 is mounted on the drone body 31 via a bracket 30, and the acoustic imaging component 32 is communicatively connected to the drone body 31. The acoustic imaging component 32 is used to collect acoustic signals along the inspection path of the drone body 31, and sends an abnormality detection signal to the drone body 31 when the acoustic signal is abnormal.

[0115] The UAV body 31 is used to execute the UAV inspection method provided in the above embodiments when it receives an anomaly detection signal.

[0116] Specifically, in this embodiment of the invention, the drone body 31 refers to a drone without an acoustic imaging component. The initial cruise state of the drone body 31 is autonomous cruise. During autonomous cruise, the acoustic imaging component 32 can collect acoustic signals along the inspection path of the drone body 31 in real time, and send an abnormality detection signal to the drone body 31 when the acoustic signal is abnormal.

[0117] After receiving the anomaly detection signal sent by the acoustic imaging component 32, the UAV body 31 can execute the UAV inspection method provided in the above embodiments. By controlling whether the acoustic imaging component 32 sends an anomaly detection signal to the UAV body 31, the UAV body 31 can intelligently switch its cruise state. After intelligent switching, the acoustic imaging component 32 can be controlled to capture multi-angle detection images of the anomaly detection location, providing professional inspection personnel with sufficient image information of the anomaly detection location. This allows professional inspection personnel to obtain sufficient information without re-inspection, which can greatly reduce the workload of professional inspection personnel, reduce labor costs, and improve inspection efficiency.

[0118] Furthermore, because a single inspection process acquires a detection location and its multi-angle detection images, the effectiveness of the inspection process is enhanced, avoiding the waste of resources caused by multiple inspection processes.

[0119] like Figure 5 As shown, based on the above embodiments, the drone provided in this embodiment of the invention further includes: a remote control terminal 33 corresponding to the drone body 31, the remote control terminal 33 is equipped with a display module 34, and the acoustic imaging component 32 is communicatively connected to the remote control terminal 33.

[0120] The acoustic imaging component 32 is also used to generate a real-time video signal and generate a heatmap when the acoustic signal is abnormal. The heatmap is then superimposed on the real-time video signal to obtain a superimposed signal. The real-time video signal can be a real-time video stream signal.

[0121] The acoustic imaging component 32 is also used to send the superimposed signal to the remote control terminal 33, which is then displayed via the display module 34. Professional inspection personnel can more intuitively determine the location of anomalies by observing the content displayed on the display module 34 and identifying the specific location of the anomaly in the real-time video signal using a heat map.

[0122] In addition, the acoustic imaging component 32 is also used to send the real-time video signal to the remote control terminal 33 after generating the real-time video signal, and to send an anomaly detection signal to the remote control terminal 33 when the acoustic signal is abnormal. After receiving the anomaly detection signal and the superimposed signal, the remote control terminal 33 uses the anomaly detection signal to generate a heat map, and superimposes the heat map onto the real-time video signal to obtain the superimposed signal, which is then displayed through the display module.

[0123] The acoustic imaging component 32 only needs to acquire the real-time video signal and send it to the remote control terminal 33. Then, the remote control terminal 33 generates, overlays, and displays the heat map. This reduces the computational burden on the acoustic imaging component 32, making it more energy-efficient and with a longer battery life.

[0124] like Figure 6 As shown, the acoustic imaging component 32 may include a camera 321, a microphone array 322, an FPGA board 323, and an acoustic probe terminal service 324. The camera 321 and the FPGA board 323 are respectively connected to the acoustic probe terminal service 324, and the microphone array 322 is connected to the FPGA board 323. The acoustic probe terminal service 324 is used to control the FPGA board 323. The camera 321 can generate real-time video signals, and the microphone array 322 can collect acoustic signals along the inspection path of the UAV body 31.

[0125] The acoustic imaging component 32 is communicatively connected to the UAV body 31. The two can transmit real-time video streams and other data through the PSDK protocol, and transmit configuration information such as frequency through the MSDK protocol.

[0126] Figure 7 This is a flowchart illustrating an inspection method based on a drone provided in an embodiment of the present invention, as shown below. Figure 7 As shown, the method includes:

[0127] Intelligent cruise control of the drone itself;

[0128] Whether the acoustic imaging component collects abnormal acoustic signals and whether it sends an abnormality detection signal to the UAV body;

[0129] If the acoustic imaging component collects acoustic signals normally, the drone continues its autonomous cruise.

[0130] If the acoustic imaging component sends an anomaly detection signal to the drone body, the drone body will pause autonomous cruise when it receives the anomaly detection signal and record the drone's position when it receives the anomaly detection signal.

[0131] Calculate the anomaly detection location;

[0132] The drone flies around the anomaly detection location and controls the acoustic imaging component to capture multi-angle detection images of the anomaly detection location.

[0133] Return to the position where autonomous cruise was paused, and resume autonomous cruise.

[0134] Figure 8 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 8 As shown, the electronic device may include a processor 810, a communications interface 820, a memory 830, and a communication bus 840, wherein the processor 810, the communications interface 820, and the memory 830 communicate with each other via the communication bus 840. The processor 810 can call logical instructions in the memory 830 to execute the UAV inspection method provided in the above embodiments. The method includes: if an abnormal detection signal is received from an acoustic imaging component mounted on the UAV, pausing autonomous cruise and determining the abnormal detection location based on the abnormal detection signal; flying around the abnormal detection location and controlling the acoustic imaging component to capture multi-angle detection images of the abnormal detection location; returning to the position where the autonomous cruise was paused and resuming the autonomous cruise.

[0135] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0136] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the UAV inspection method provided in the above embodiments. The method includes: if an abnormal detection signal is received from an acoustic imaging component mounted on the UAV, pausing autonomous cruise and determining an abnormal detection location based on the abnormal detection signal; flying around the abnormal detection location and controlling the acoustic imaging component to capture multi-angle detection images of the abnormal detection location; returning to the position where the autonomous cruise was paused and continuing the autonomous cruise.

[0137] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the UAV inspection method provided in the above embodiments. The method includes: if an abnormal detection signal is received from an acoustic imaging component mounted on the UAV, pausing autonomous cruise and determining an abnormal detection location based on the abnormal detection signal; flying around the abnormal detection location and controlling the acoustic imaging component to capture multi-angle detection images of the abnormal detection location; returning to the position where the autonomous cruise was paused and continuing the autonomous cruise.

[0138] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0139] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0140] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An unmanned aerial vehicle inspection method, characterized in that, The method comprises the following steps: suspending autonomous cruising if an abnormality detection signal sent by an acoustic imaging assembly carried on the unmanned aerial vehicle is received, and determining an abnormality detection position based on the abnormality detection signal; flying around the abnormality detection position and controlling the acoustic imaging assembly to take multi-angle detection images of the abnormality detection position; the multi-angle detection images comprise detection images taken at multiple different angles of the unmanned aerial vehicle relative to the abnormality detection position on a flight path; returning to the position where the autonomous cruising is suspended and continuing the autonomous cruising; the determination of the shooting point positions comprises the following steps: determining a preset sphere with the abnormality detection position as the center and uniformly arranging the shooting point positions on the preset sphere; when the radius of the preset sphere is equal to the distance between the unmanned aerial vehicle position at which the abnormality detection signal is received and the abnormality detection position, the shooting angle of the detection image obtained by the acoustic imaging assembly at each shooting point position is the same as the shooting angle of the inspection image taken at the unmanned aerial vehicle position; when the radius of the preset sphere is smaller than the distance between the unmanned aerial vehicle position and the abnormality detection position, the shooting angle of the detection image obtained by the acoustic imaging assembly at each shooting point position is larger than the shooting angle of the inspection image taken at the unmanned aerial vehicle position; when the radius of the preset sphere is larger than the distance between the unmanned aerial vehicle position and the abnormality detection position, the shooting angle of the detection image obtained by the acoustic imaging assembly at each shooting point position is smaller than the shooting angle of the inspection image taken at the unmanned aerial vehicle position.

2. The unmanned aerial vehicle inspection method of claim 1, wherein, the flying around the abnormality detection position and controlling the acoustic imaging assembly to take multi-angle detection images of the abnormality detection position comprises the following steps: determining multiple different shooting point positions of the acoustic imaging assembly relative to the abnormality detection position and planning flight paths for flying around the abnormality detection position to each shooting point position in sequence; flying along the flight paths and controlling the acoustic imaging assembly to face the abnormality detection position to take detection images of corresponding angles when each shooting point position is reached.

3. The unmanned aerial vehicle inspection method of claim 2, wherein, the flying along the flight paths comprises the following steps: if there is an obstacle within a preset range of any shooting point position, the any shooting point position is skipped and the unmanned aerial vehicle continues to fly to the next shooting point position; if there is an obstacle outside a preset range of any shooting point position, a sub-flight path to the any shooting point position is re-planned and the unmanned aerial vehicle flies along the sub-flight path to the any shooting point position.

4. The unmanned aerial vehicle inspection method of claim 2, wherein, the radius of the preset sphere is a preset multiple of the distance between the unmanned aerial vehicle position at which the abnormality detection signal is received and the abnormality detection position.

5. The unmanned aerial vehicle inspection method of any one of claims 1-4, wherein, the abnormality detection signal comprises azimuth information and distance information of an abnormality sound source; correspondingly, the determination of the abnormality detection position based on the abnormality detection signal comprises the following steps: determining the unmanned aerial vehicle position at which the abnormality detection signal is received; determining the abnormality detection position based on the unmanned aerial vehicle position, the azimuth information and the distance information.

6. An unmanned aerial vehicle inspection device, characterized in that, The method comprises the following steps: suspending autonomous cruising if an abnormality detection signal sent by an acoustic imaging assembly carried on the unmanned aerial vehicle is received, and determining an abnormality detection position based on the abnormality detection signal; The control module is configured to control the acoustic imaging assembly to capture multi-angle detection images of the abnormality detection position when the unmanned aerial vehicle flies around the abnormality detection position. The cruise module is configured to return to the position where the autonomous cruise is paused and continue the autonomous cruise. The determination of the shooting point positions comprises: A preset sphere is determined with the abnormality detection position as the center, and the shooting point positions are evenly arranged on the preset sphere. When the radius of the preset sphere is equal to the distance between the unmanned aerial vehicle position when the abnormality detection signal is received and the abnormality detection position, the shooting angle of the detection image obtained by the acoustic imaging assembly at each shooting point position is the same as the shooting angle of the inspection image obtained at the unmanned aerial vehicle position. When the radius of the preset sphere is smaller than the distance between the unmanned aerial vehicle position and the abnormality detection position, the shooting angle of the detection image obtained by the acoustic imaging assembly at each shooting point position is larger than the shooting angle of the inspection image obtained at the unmanned aerial vehicle position. When the radius of the preset sphere is larger than the distance between the unmanned aerial vehicle position and the abnormality detection position, the shooting angle of the detection image obtained by the acoustic imaging assembly at each shooting point position is smaller than the shooting angle of the inspection image obtained at the unmanned aerial vehicle position.

7. A drone, characterized in that, Comprise: The unmanned aerial vehicle body and the acoustic imaging assembly are carried on the unmanned aerial vehicle body, and the acoustic imaging assembly is in communication connection with the unmanned aerial vehicle body. The acoustic imaging assembly is configured to collect acoustic wave signals on the inspection path of the unmanned aerial vehicle body and send an abnormality detection signal to the unmanned aerial vehicle body when the acoustic wave signals are abnormal. The unmanned aerial vehicle body is configured to execute the unmanned aerial vehicle inspection method according to any one of claims 1-5 when the abnormality detection signal is received.

8. The drone of claim 7, wherein, Further comprise: The remote control end corresponding to the unmanned aerial vehicle body is configured with a display module, and the acoustic imaging assembly is in communication connection with the remote control end. The acoustic imaging assembly is further configured to generate a real-time video signal and generate a heat map when the acoustic wave signals are abnormal, superimpose the heat map on the real-time video signal to obtain a superimposed signal, and send the superimposed signal to the remote control end for display through the display module. Further comprise:

9. The drone of claim 7, wherein, The remote control end corresponding to the unmanned aerial vehicle body is configured with a display module, and the acoustic imaging assembly is in communication connection with the remote control end. The acoustic imaging assembly is further configured to generate a real-time video signal, send the real-time video signal to the remote control end, and send the abnormality detection signal to the remote control end when the acoustic wave signals are abnormal. The remote control end is further configured to generate a heat map based on the abnormality detection signal, superimpose the heat map on the real-time video signal to obtain a superimposed signal, and display the superimposed signal through the display module. The computer program is executed by a processor to implement the unmanned aerial vehicle inspection method according to any one of claims 1-5.

10. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, ​

Images