Surface object recognition method and device, electronic equipment and storage medium

By transmitting sound wave signals to objects on the ground, receiving reflected signals and constructing a distance spectrum, and combining geometric principles to identify shapes, the problem of blind spots in optical methods in UAV operations is solved, and the accuracy of identifying objects on the ground is improved.

CN118938231APending Publication Date: 2024-11-12YUNNAN POWER GRID CO LTD NUJIANG POWER SUPPLY BUREAU
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410992278.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In drone operations, optical photography methods have blind spots in recognizing mirror-like or transparent objects, resulting in low accuracy in identifying surface objects. This is especially true in complex terrain and harsh environments where it is difficult to conduct landslide risk assessments manually.

Method used

By emitting sound wave signals to objects on the ground and receiving the reflected signals, a distance spectrum is constructed, and the shape of the objects on the ground is identified based on geometric principles. The reflection characteristics of sound wave signals are used to avoid light interference.

Benefits of technology

It improves the accuracy of surface object identification, especially for objects that are difficult to identify using optical measurement methods, such as mirrors or transparent objects, enabling more accurate identification and measurement.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118938231A_ABST
    Figure CN118938231A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a surface object recognition method and device, electronic equipment and a storage medium, and the method comprises the steps: transmitting a sound wave signal to a surface object during flight; receiving a reflection signal generated by the sound wave signal on the earth surface object; constructing a distance spectrum corresponding to the earth surface object according to the sound wave signal and the reflection signal; the shape of the surface object is identified based on peaks in the distance spectrum and geometry principles. According to the scheme, the accuracy of surface object recognition can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, electronic device and storage medium for identifying surface objects. Background Art

[0002] my country has currently built a long and multi-regional power transportation network. During the power transportation process, it is inevitable to pass through areas with complex geological factors, changeable climate conditions, and harsh environmental conditions such as mountains and plateaus. Transmission towers, as the connection point between high-voltage transmission lines and the ground, are often built on steep mountains far away from cities. These terrain conditions increase the possibility of landslide disasters. According to the summary report of the State Grid Electric Power Research Institute, from 2018 to 2021, there were 3,920 overhead transmission line towers affected by geological disasters. The main types of disasters were floods, landslides, and mining collapses, of which landslides accounted for nearly 25%. In many special terrains with high vegetation coverage, it is difficult to use manual means to investigate landslide risks. Therefore, it is of great significance to use drones in the maintenance of transmission lines.

[0003] Drone operations are usually suitable for some application scenarios that require close tracking of ground features, such as geological exploration, agricultural operations, environmental monitoring, etc. During these operations, surface objects need to be identified. The currently widely used optical photography method will be affected by light interference, such as blind spots in visual measurement of mirrors or transparent surface objects, resulting in low accuracy of recognition results. Summary of the invention

[0004] The embodiments of the present application provide a surface object recognition system, method, electronic device and storage medium, which can avoid errors in recognition caused by light interference when identifying surface objects, thereby improving the accuracy of surface object recognition.

[0005] In a first aspect, an embodiment of the present application provides a method for identifying a surface object, comprising:

[0006] While flying, it transmits acoustic signals to objects on the ground;

[0007] receiving a reflection signal generated by the acoustic wave signal from the surface object;

[0008] constructing a distance spectrum corresponding to the surface object according to the acoustic wave signal and the reflection signal;

[0009] Based on the peaks in the distance spectrum and geometric principles, the shape of the ground surface object is identified.

[0010] Optionally, in some embodiments of the present application, constructing a distance spectrum corresponding to the surface object according to the acoustic wave signal and the reflection signal includes:

[0011] Mixing the acoustic wave signal and the reflected signal to obtain a mixed signal;

[0012] Convert the mixed signal from the time domain to the frequency domain by Fourier transform to obtain a power spectrum corresponding to the mixed signal;

[0013] Based on the propagation speed of the sound wave in the medium and the peak frequency in the power spectrum, a distance spectrum corresponding to the surface object is constructed.

[0014] Optionally, in some embodiments of the present application, constructing the distance spectrum corresponding to the surface object based on the propagation speed of the sound wave in the medium and the peak frequency in the power spectrum includes:

[0015] Calculating the distance to the surface object based on the propagation speed of the sound wave in the medium and the peak frequency in the power spectrum;

[0016] A distance spectrum corresponding to the surface objects is constructed according to the distances between the surface objects and the peak frequencies in the power spectrum.

[0017] Optionally, in some embodiments of the present application, constructing a distance spectrum corresponding to the surface objects according to the distances between the surface objects and the peak frequencies in the power spectrum includes:

[0018] constructing an initial distance spectrum corresponding to the surface objects according to the distances between the surface objects and the peak frequencies in the power spectrum;

[0019] Identifying a main peak of the initial distance spectrum, and determining a target frequency point within a preset frequency range of the main peak;

[0020] A distance spectrum corresponding to the surface object is constructed based on the target frequency point, discrete Fourier transform and the initial distance spectrum.

[0021] Optionally, in some embodiments of the present application, identifying the shape of the surface object based on the peak value in the distance spectrum and the geometric principle includes:

[0022] determining an object edge corresponding to the surface object according to a peak value in the distance spectrum;

[0023] Based on the object edges and geometric principles, the shape of the surface object is identified.

[0024] Optionally, in some embodiments of the present application, the identifying the shape of the surface object based on the edge of the object and geometric principles includes:

[0025] Acquire a reference geometry image;

[0026] The shape of the surface object is identified based on the object edge, the reference geometric image and the geometric principle.

[0027] Optionally, in some embodiments of the present application, before constructing the distance spectrum corresponding to the surface object according to the acoustic wave signal and the reflection signal, the method further includes:

[0028] filtering the reflected signal;

[0029] The constructing the distance corresponding to the surface object according to the sound wave signal and the reflected signal includes: constructing the distance corresponding to the surface object according to the sound wave signal and the filtered reflected signal.

[0030] In a second aspect, an embodiment of the present application provides a surface object recognition device, including:

[0031] A transmitting module, used for transmitting acoustic wave signals to objects on the ground during flight;

[0032] A receiving module, used for receiving a reflection signal generated by the acoustic wave signal from the surface object;

[0033] A construction module, used to construct a distance spectrum corresponding to the surface object according to the acoustic wave signal and the reflection signal;

[0034] The recognition module is used to recognize the shape of the surface object based on the peak value in the distance spectrum and the geometric principle.

[0035] Correspondingly, the present application also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the steps of any of the above methods when executing the program.

[0036] The present application also provides a storage medium, wherein the storage medium stores a computer program, and the computer program implements any of the above methods when the computer program is executed by a processor.

[0037] The present application provides a method, device, electronic device and storage medium for identifying a surface object. During flight, an acoustic wave signal is transmitted to a surface object, and then a reflection signal generated by the acoustic wave signal on the surface object is received. Then, a distance spectrum corresponding to the surface object is constructed based on the acoustic wave signal and the reflection signal. Finally, the shape of the surface object is identified based on the peak value in the distance spectrum and the geometric principle. In the scheme for identifying a surface object provided in the present application, during flight, an acoustic wave signal is transmitted to a surface object, and then the shape of the surface object is identified based on the acoustic wave signal and the reflection signal generated by the acoustic wave signal on the surface object. In this way, the situation in which errors in identification caused by light interference when identifying a surface object can be avoided, thereby improving the accuracy of identifying a surface object. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0039] Figure 1 is a flow chart of a method for identifying a ground object provided in an embodiment of the present application;

[0040] Figure 2 is a schematic diagram of standing wave distance measurement in the surface object recognition method provided in an embodiment of the present application;

[0041] Figure 3 is a schematic diagram of the structure of a surface object recognition device provided in an embodiment of the present application;

[0042] Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are merely examples of systems and methods consistent with the examples detailed in the attached claims, or with some aspects of the present application.

[0044] It should be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover descriptions such as non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0045] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0046] In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present application, and have no specific meanings. Therefore, "module", "component" or "unit" can be used in a mixed manner.

[0047] Embodiments of the present application provide a method, device, electronic device, and storage medium for identifying surface objects.

[0048] The surface object recognition device can be deployed in a drone. A drone (UAV), also known as a remote-controlled aircraft or an unmanned aircraft system (UAS), is an aircraft that does not require a pilot to operate in the cabin. The drone can communicate with a server via wired or wireless means. The server can include an independently operated server or a distributed server, or a server cluster consisting of multiple servers. The terminal can include a mobile phone, a tablet computer or a personal computer (PC).

[0049] It should be noted that the order of description of the following embodiments is not intended to limit the priority order of the embodiments.

[0050] The present application provides a method for identifying a surface object, comprising: transmitting an acoustic wave signal to a surface object during flight; receiving a reflection signal generated by the acoustic wave signal at the surface object; constructing a distance spectrum corresponding to the surface object according to the acoustic wave signal and the reflection signal; and identifying the shape of the surface object based on a peak value in the distance spectrum and geometric principles.

[0051] See also Figure 1 , Figure 1 : is a flow chart of the surface object recognition method provided by the present application, and the surface object recognition method specifically includes the following process:

[0052] 101. Perform flight missions based on the built-in positioning system.

[0053] During the flight, the drone uses its acoustic sensor to emit sound wave signals to the ground. These sound wave signals will interact with ground objects. The sensor can be a microphone or other type of acoustic transmitter. The sound wave signal is an acoustic waveform emitted by the drone's acoustic sensor to interact with ground objects. This sound wave signal can be a continuous wave or a pulse wave. The frequency range of the sound wave signal is from the lowest frequency f min To the highest frequency f max , this frequency range determines the size and shape of objects that the sound wave signal can detect.

[0054] See also Figure 2 , the signal transmitted from the sensor to point x at time t is recorded as v Tr (t,x). Further, assume that the signal is:

[0055]

[0056] where f(τ) is the instantaneous frequency, defined as:

[0057]

[0058] A, c, θ are the sound amplitude, sound speed, and phase respectively; T represents the duration, f1 represents the lowest frequency, and f N Indicates the highest frequency, f w Indicates bandwidth f w =f N -f1. When the sound wave signal encounters a ground object, part of the sound wave will be reflected back. The strength and characteristics of the reflected signal depend on the surface characteristics and shape of the object.

[0059] The signal reflected by the stationary object at the distance sensor L is denoted as v Ref (t,x), the assumed model is as follows:

[0060]

[0061] Where γ and φ are reflection parameters that are constant over the frequency range of interest. The intensity and phase variation of the reflected signal depends on the surface characteristics of the object. For example, a smooth surface will produce a strong reflected signal, while a rough surface may weaken or scatter the reflected signal.

[0062] 102. Receive the reflected signal of the sound wave signal generated by the surface object.

[0063] Surface objects refer to ground objects that drones need to identify and measure when performing tasks. These objects can be natural landforms, man-made structures, or any other ground features. Surface objects can include transmission towers, buildings, roads, vegetation, landforms, etc. They can be naturally formed or artificially constructed. The purpose of drones identifying surface objects may include geological exploration, environmental monitoring, agricultural operations, disaster assessment, etc. For example, monitoring landslide risks near transmission lines, assessing the growth of agricultural crops, identifying and measuring terrain changes, etc. Different types of surface objects have different acoustic wave reflection characteristics. For example, hard rock surfaces will produce stronger reflection signals, while soft soil or vegetation may absorb more acoustic wave energy and produce weaker reflection signals. The shape and size of surface objects are key to identification and measurement. By analyzing the power spectrum and distance spectrum of the reflected signal, the edges and shapes of the objects can be determined. For example, a round transmission tower or an irregular landslide area. In some cases, optical measurement methods may be affected by light interference, resulting in poor recognition results. Acoustic signals are not affected by these interferences and can more accurately identify and measure surface objects.

[0064] 103. Construct a distance spectrum corresponding to the surface object based on the sound wave signal and the reflected signal.

[0065] The sound wave signal received by the drone and the reflected signal are mixed together to form a mixed signal. This mixed signal contains the information of the transmitted signal and the reflected signal. The mixed signal is converted from the time domain to the frequency domain through Fourier transform to obtain the power spectrum. The power spectrum is a function of frequency and shows the power of different frequency components.

[0066] like Figure 2 The origin v where the microphone is shown C (t,0)=v Tr (t,0)+v R The mixed signal v at (t,0) C (t,0) can be calculated as v C (t,0)=v Tr (t,0)+v R (t,0). Then v C The power of (t,0) becomes:

[0067]

[0068] The first and second terms on the right represent the power of the transmitted and received signals, which are constants. In the frequency domain, v C The power of is:

[0069]

[0070] Where C0 is the constant term of interference. Since the above formula is a biased cosine function, in the frequency range (f1, f N ) forms a pulse peak at the frequency of the cosine function. The power spectrum becomes a “distance spectrum” because it has a peak at L, indicating the distance to the object, as Figure 2 shown.

[0071] Optionally, in some embodiments of the present application, the step of “constructing a distance spectrum corresponding to the surface object according to the acoustic wave signal and the reflection signal” may specifically include:

[0072] The acoustic wave signal and the reflected signal are mixed to obtain a mixed signal;

[0073] The mixed signal is converted from the time domain to the frequency domain by Fourier transform to obtain the power spectrum corresponding to the mixed signal;

[0074] Based on the propagation speed of sound waves in the medium and the peak frequency in the power spectrum, the distance spectrum corresponding to the surface objects is constructed.

[0075] The result of Fourier transform is a complex function, and what is usually of interest is the square of its modulus, i.e., the power spectrum. The power spectrum shows the power of different frequency components, reflecting the frequency characteristics of the signal. The distance spectrum corresponding to the surface object is constructed using the propagation speed of sound waves in the medium and the peak frequency in the power spectrum. The distance spectrum is a frequency spectrum that represents the distance of an object, and its peak corresponds to the edge of the object. The calculation of the distance spectrum can be based on the following principle: the reflection of the sound wave signal on the surface of the object will form standing waves at specific frequencies, and the frequency of these standing waves is related to the distance of the object. By analyzing the peak in the distance spectrum, the edge of the object can be determined. The position of the peak corresponds to the distance of the edge of the object, so that the shape and size of the object can be inferred.

[0076] Optionally, in some embodiments of the present application, the step of “constructing a distance spectrum corresponding to the surface object based on the propagation speed of the sound wave in the medium and the peak frequency in the power spectrum” may specifically include:

[0077] Calculate the distance to the surface object based on the propagation speed of the sound wave in the medium and the peak frequency in the power spectrum;

[0078] According to the distances between the surface objects and the peak frequencies in the power spectrum, the distance spectrum corresponding to the surface objects is constructed.

[0079] The speed of sound waves in a medium refers to the distance that sound waves travel through the medium per unit time. It is the product of the frequency and wavelength of the sound wave. The speed of sound waves depends on the properties of the medium, such as density, elastic modulus, etc. The speed of sound waves will be different in different media. For example: In air, the speed of sound is about 343 m / s (at 20°C). In water, the speed of sound is about 1500 m / s. In solids, the speed of sound is usually faster than in liquids and gases. Temperature is an important factor affecting the speed of sound. Generally speaking, as the temperature increases, the speed of sound increases. This is because the increase in temperature increases the movement speed of the medium molecules, thereby accelerating the propagation of sound waves.

[0080] In the power spectrum, identify the peak frequency f peak , peak frequency f peak Corresponds to the frequency of the standing wave formed when the sound wave signal is reflected on the surface of an object. Using the propagation speed c of the sound wave in the medium and the peak frequency f peak , the distance d between the drone and the object can be calculated. The calculation formula is as follows:

[0081] Where: c is the propagation speed of sound waves in the medium, f peak is the peak frequency in the power spectrum, and d is the distance between the drone and the object. This formula is based on the standing wave theory. When the sound wave signal is reflected on the surface of an object, a standing wave is formed on the surface of the object. The frequency of the standing wave is related to the distance of the object, and the peak frequency corresponds to the frequency of the standing wave. Based on this, it can be used for drones to identify surface objects, especially in the case of objects that are difficult to identify with optical measurement methods, such as mirrors or transparent objects. Through the reflection characteristics of the sound wave signal, the drone can measure the distance of the surface object more accurately.

[0082] Optionally, in some embodiments of the present invention, the step of “constructing a distance spectrum corresponding to the surface objects according to the distances between the surface objects and the peak frequencies in the power spectrum” may specifically include:

[0083] According to the distances between the surface objects and the peak frequencies in the power spectrum, an initial distance spectrum corresponding to the surface objects is constructed;

[0084] Identify the main peak of the initial range spectrum and determine the target frequency point within a preset frequency range of the main peak;

[0085] Based on the target frequency points, discrete Fourier transform and initial distance spectrum, the distance spectrum corresponding to the surface object is constructed.

[0086] After determining the distance between the drone and the surface object, the distance d is associated with the frequency value in the power spectrum to form a preliminary distance estimation spectrum (i.e., the initial distance spectrum). The peaks in the initial distance spectrum usually correspond to the distance of the edge of the object. By analyzing these peaks, the distance between the drone and the object can be preliminarily estimated. The initial distance spectrum provides a basic distance estimate. In order to improve the recognition accuracy, more refined measurements are used to improve the resolution. The discrete Fourier transform can be used to perform denser sampling in a specific frequency range to obtain a higher-precision distance spectrum, as follows:

[0087] Assume a disk with radius R and distance L as the target object. For simplicity, the observation point is located on a straight line passing vertically through the center of the disk. Note that the chirp signal in a short time can be approximated as a sine wave, and the phase of the transmitted signal does not affect the distance spectrum. For simplicity, in the following analysis, the transmitted signal is modeled as a unit sound signal sinωt. In a ring with radius r and width dr at the origin x=0, the reflected sound signal with angular frequency ω is denoted by v Ref,r,ω (t,0)dr. Assuming that the gain coefficient and the reflected phase shift remain constant over the entire frequency range, we apply Lambert's law and the inverse distance law to model the reflected signal as follows:

[0088]

[0089] By comparing the above formula to v on disk Ref,r,ω (t,0)dr integration, get the reflected signal v Ref,ω The calculation formula of (t) is as follows:

[0090]

[0091] in,

[0092]

[0093] Then p(ω,0) can be expressed as:

[0094]

[0095] The above equation shows that the power spectrum p(ω,0) can be approximated by a constant and two sinc functions with coefficients a and b. Considering that ω is given in a finite frequency range, the "power spectrum" of p(ω,0) of ω forms a distance spectrum, which has two peaks at a and b, corresponding to the two edges of the disk.

[0096] Since the distance spectrum can be calculated by Fourier transform of the power spectrum p(f,0), fast Fourier transform is an effective calculation method. The conventional distance spectrum based on fast Fourier transform has uniform resolution, and the highest resolution of the distance spectrum is The present invention also proposes a method using discrete Fourier transform, which has dense query points around the first peak to calculate the distance spectrum. It is worth noting that the query points can be arbitrarily selected using discrete Fourier transform, and the obtained distance spectrum can have a higher resolution than that obtained using fast Fourier transform. However, since the discrete Fourier transform method requires more calculation, the present invention cascades the traditional fast Fourier transform-based distance spectrum to find a target area represented by the main peak, and then selects more refined query points around the main peak, thereby simultaneously obtaining high resolution and improving calculation efficiency.

[0097] 104. Identify the shape of surface objects based on the peaks in the distance spectrum and geometric principles.

[0098] For example, the edge of an object can be determined based on the peak in the distance spectrum. The location of the edge of an object can be determined by the distance corresponding to the peak. Then, combined with geometric principles such as straight lines, curves, angles, etc., the distance and direction of the edge of the object are analyzed to infer the shape of the object. For example: if the object is round, the distance of the edge will be symmetrically distributed. If the object is rectangular, the distance of the edge will show a regular rectangular pattern. In this way, the shape of the surface object can be identified.

[0099] Optionally, in some embodiments of the present application, the step of “identifying the shape of the surface object based on the peak value in the distance spectrum and the geometric principle” may specifically include:

[0100] Acquire a reference geometry image;

[0101] Recognize the shape of ground objects based on object edges, reference geometric images, and geometric principles.

[0102] For example, the position of the edge of the object can be determined by the distance corresponding to the peak value. Then, the shape enclosed by the edge of the object is compared with the preset geometric figure to determine the matching reference geometric image. Next, the parameters of the preset figure are adjusted to make it match the actual measurement data as much as possible, and the shape of the object is determined using geometric principles such as similarity and symmetry.

[0103] Specifically, the preset reference geometric images include the geometric images of the transmission tower, the geometric images of the house, and the geometric images of the transport vehicle. The geometric image of the transmission tower is determined as the matching reference geometric image through the object edge corresponding to the surface object. Finally, the shape of the object is determined to be the transmission tower by using geometric principles, such as similarity, symmetry, etc.

[0104] As can be seen from the above, the embodiment of the present application provides a method for identifying a surface object. During flight, an acoustic wave signal is transmitted to a surface object, and then a reflection signal generated by the acoustic wave signal on the surface object is received. Then, a distance spectrum corresponding to the surface object is constructed based on the acoustic wave signal and the reflection signal. Finally, the shape of the surface object is identified based on the peak value in the distance spectrum and the geometric principle. In the scheme for identifying a surface object provided in the present application, during flight, after transmitting an acoustic wave signal to a surface object, the shape of the surface object is identified based on the acoustic wave signal and the reflection signal generated by the acoustic wave signal on the surface object, and finally, based on the peak value in the distance spectrum and the geometric principle. Thus, the situation in which errors in identification caused by light interference when identifying a surface object can be avoided, thereby improving the accuracy of surface object identification.

[0105] In order to better implement the surface object recognition method of the present application embodiment, the present application embodiment also provides a surface object recognition device, wherein the meanings of the terms are the same as those in the above-mentioned surface object recognition system, and the specific implementation details can refer to the description in the system embodiment.

[0106] See also Figure 3 , Figure 3 The schematic diagram of the structure of the surface object recognition device provided in the embodiment of the present application, wherein the surface object recognition device may specifically include a transmitting module 201, a receiving module 202, a building module 203 and a recognition module 204, which may be specifically as follows:

[0107] The transmitting module 201 is used to transmit sound wave signals to surface objects during flight.

[0108] The receiving module 202 is used to receive the reflection signal generated by the acoustic wave signal from the surface object.

[0109] The construction module 203 is used to construct a distance spectrum corresponding to the surface object according to the acoustic wave signal and the reflection signal.

[0110] Optionally, in some embodiments of the present application, the construction module 203 may specifically include:

[0111] A mixing unit, used for mixing the acoustic wave signal and the reflected signal to obtain a mixed signal;

[0112] A conversion unit, used to convert the mixed signal from the time domain to the frequency domain through Fourier transform to obtain a power spectrum corresponding to the mixed signal;

[0113] The construction unit is used to construct a distance spectrum corresponding to the surface object based on the propagation speed of the sound wave in the medium and the peak frequency in the power spectrum.

[0114] Optionally, in some embodiments of the present application, the construction unit may specifically include:

[0115] A calculation subunit, for calculating the distance to the surface object based on the propagation speed of the sound wave in the medium and the peak frequency in the power spectrum;

[0116] The construction subunit is used to construct a distance spectrum corresponding to the surface objects according to the distances between the surface objects and the peak frequencies in the power spectrum.

[0117] Optionally, in some embodiments of the present application, the construction subunit may be specifically used for:

[0118] According to the distances between the surface objects and the peak frequencies in the power spectrum, an initial distance spectrum corresponding to the surface objects is constructed;

[0119] Identify the main peak of the initial range spectrum and determine the target frequency point within a preset frequency range of the main peak;

[0120] Based on the target frequency points, discrete Fourier transform and initial distance spectrum, the distance spectrum corresponding to the surface object is constructed.

[0121] The recognition module 204 is used to recognize the shape of the surface object based on the peak value in the distance spectrum and the geometric principle.

[0122] Optionally, in some embodiments of the present application, the identification module 204 may specifically include:

[0123] a determination unit, used for determining an object edge corresponding to the surface object according to a peak value in the distance spectrum;

[0124] The recognition unit is used to recognize the shape of the surface object based on the edge of the object and the geometric principle.

[0125] Optionally, in some embodiments of the present application, the recognition unit may be specifically used to: acquire a reference geometric image; and recognize the shape of a surface object based on an edge of the object, the reference geometric image, and geometric principles.

[0126] The embodiment of the present application provides a surface object recognition device, wherein the transmitting module 201 transmits an acoustic wave signal to the surface object during flight, and then the receiving module 202 receives the reflection signal generated by the acoustic wave signal on the surface object, and then the construction module 203 constructs a distance spectrum corresponding to the surface object according to the acoustic wave signal and the reflection signal, and finally, the recognition module 204 recognizes the shape of the surface object based on the peak value in the distance spectrum and the geometric principle. In the surface object recognition scheme provided by the present application, after transmitting an acoustic wave signal to the surface object during flight, the shape of the surface object is recognized based on the acoustic wave signal and the reflection signal generated by the acoustic wave signal on the surface object, and finally, based on the peak value in the distance spectrum and the geometric principle, thereby avoiding the situation in which the recognition error caused by light interference during the recognition of the surface object is avoided, and the accuracy of the recognition of the surface object is improved.

[0127] In addition, the present application also provides an electronic device, such as Figure 4 As shown, it shows a schematic diagram of the structure of the electronic device involved in the embodiment of the present application, specifically:

[0128] The electronic device may include components such as a processor 301 with one or more processing cores, a memory 302 with one or more computer-readable storage media, a power supply 303, and an input unit 304. Those skilled in the art will appreciate that Figure 4 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0129] The processor 301 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 302, and calling data stored in the memory 302, it executes various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. Optionally, the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 301.

[0130] The memory 302 can be used to store software programs and modules. The processor 301 executes various functional applications and surface object recognition methods by running the software programs and modules stored in the memory 302. The memory 302 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the electronic device, etc. In addition, the memory 302 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 302 can also include a memory controller to provide the processor 301 with access to the memory 302.

[0131] The electronic device also includes a power supply 303 for supplying power to each component. Preferably, the power supply 303 can be logically connected to the processor 301 through a power management system, so that the power management system can manage charging, discharging, power consumption and other functions. The power supply 303 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components.

[0132] The electronic device may further include an input unit 304, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0133] Although not shown, the electronic device may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 301 in the electronic device will load the executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 will run the application programs stored in the memory 302, thereby realizing various functions, as follows:

[0134] During flight, the aircraft transmits acoustic wave signals to surface objects; receives reflection signals generated by the acoustic wave signals on surface objects; constructs a distance spectrum corresponding to the surface objects based on the acoustic wave signals and reflection signals; and identifies the shape of the surface objects based on the peak values ​​in the distance spectrum and geometric principles.

[0135] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0136] The embodiment of the present application transmits an acoustic wave signal to a surface object during flight, then receives a reflection signal generated by the acoustic wave signal on the surface object, then constructs a distance spectrum corresponding to the surface object based on the acoustic wave signal and the reflection signal, and finally identifies the shape of the surface object based on the peak value in the distance spectrum and the geometric principle. In the surface object recognition scheme provided by the present application, after transmitting an acoustic wave signal to a surface object during flight, the shape of the surface object is identified based on the acoustic wave signal and the reflection signal generated by the acoustic wave signal on the surface object, and finally identifies the shape of the surface object based on the peak value in the distance spectrum and the geometric principle, thereby avoiding the situation in which the recognition of the surface object is caused by light interference and causes errors, thereby improving the accuracy of the recognition of the surface object.

[0137] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0138] To this end, an embodiment of the present application provides a storage medium in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps in any of the surface object recognition methods provided in the embodiments of the present application. For example, the instructions can execute the following steps:

[0139] During flight, the aircraft transmits acoustic wave signals to surface objects; receives reflection signals generated by the acoustic wave signals on surface objects; constructs a distance spectrum corresponding to the surface objects based on the acoustic wave signals and reflection signals; and identifies the shape of the surface objects based on the peak values ​​in the distance spectrum and geometric principles.

[0140] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0141] The storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0142] Since the instructions stored in the storage medium can execute the steps in any one of the surface object recognition methods provided in the embodiments of the present application, the beneficial effects that can be achieved by any one of the surface object recognition methods provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0143] The above is a detailed introduction to a surface object recognition method, device, electronic device and storage medium provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for identifying a surface object, characterized in that: include: While flying, it transmits acoustic signals to objects on the ground; receiving a reflection signal generated by the acoustic wave signal from the surface object; constructing a distance spectrum corresponding to the surface object according to the acoustic wave signal and the reflection signal; Based on the peaks in the distance spectrum and geometric principles, the shape of the ground surface object is identified.

2. The method for identifying a ground object according to claim 1, characterized in that: The step of constructing a distance spectrum corresponding to the surface object according to the acoustic wave signal and the reflection signal includes: Mixing the acoustic wave signal and the reflected signal to obtain a mixed signal; Convert the mixed signal from the time domain to the frequency domain by Fourier transform to obtain a power spectrum corresponding to the mixed signal; Based on the propagation speed of the sound wave in the medium and the peak frequency in the power spectrum, a distance spectrum corresponding to the surface object is constructed.

3. The method for identifying a ground object according to claim 2, characterized in that: The step of constructing a distance spectrum corresponding to the surface object based on the propagation speed of the sound wave in the medium and the peak frequency in the power spectrum includes: Calculating the distance to the surface object based on the propagation speed of the sound wave in the medium and the peak frequency in the power spectrum; A distance spectrum corresponding to the surface objects is constructed according to the distances between the surface objects and the peak frequencies in the power spectrum.

4. The method for identifying ground objects according to claim 3, characterized in that: The step of constructing a distance spectrum corresponding to the surface objects according to the distances between the surface objects and the peak frequencies in the power spectrum includes: constructing an initial distance spectrum corresponding to the surface objects according to the distances between the surface objects and the peak frequencies in the power spectrum; Identifying a main peak of the initial distance spectrum, and determining a target frequency point within a preset frequency range of the main peak; A distance spectrum corresponding to the surface object is constructed based on the target frequency point, discrete Fourier transform and the initial distance spectrum.

5. The method for identifying a ground object according to any one of claims 1 to 4, characterized in that: The identifying the shape of the surface object based on the peak value in the distance spectrum and the geometric principle comprises: determining an object edge corresponding to the surface object according to a peak value in the distance spectrum; Based on the object edges and geometric principles, the shape of the surface object is identified.

6. The method for identifying a ground object according to claim 5, characterized in that: The identifying the shape of the surface object based on the edge of the object and the geometric principle includes: Acquire a reference geometry image; The shape of the surface object is identified based on the object edge, the reference geometric image and the geometric principle.

7. The method for identifying a ground object according to any one of claims 1 to 4, characterized in that: Before constructing the distance spectrum corresponding to the surface object according to the sound wave signal and the reflection signal, the method further includes: filtering the reflected signal; The constructing the distance corresponding to the surface object according to the sound wave signal and the reflected signal includes: constructing the distance corresponding to the surface object according to the sound wave signal and the filtered reflected signal.

8. A surface object recognition device, characterized in that: include: A transmitting module, used to transmit acoustic wave signals to objects on the ground during flight; A receiving module, used for receiving a reflection signal generated by the acoustic wave signal from the surface object; A construction module, used to construct a distance spectrum corresponding to the surface object according to the acoustic wave signal and the reflection signal; The recognition module is used to recognize the shape of the surface object based on the peak value in the distance spectrum and the geometric principle.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program according to the steps of the method for identifying a ground object as claimed in any one of claims 1 to 7.

10. A storage medium, characterized in that: The device stores a computer program which can be loaded by a processor and execute the method for identifying a ground object according to any one of claims 1 to 7.