WO2021102993A1 - Environment detection method, electronic device and computer-readable storage medium - Google Patents

Abstract

An environment detection method, an electronic device, and a computer-readable storage medium. The method comprises: emitting environment detection sounds, and collecting the environment detection sounds to obtain target detection sounds (S101); performing feature extraction on the target detection sounds to obtain sound field features (S102): and according to the sound field features, determining the current environment in which an electronic device is located (S103). The described method improves the accuracy of detecting the environment in which an electronic device is located.

Description

Environmental detection method, electronic equipment and computer readable storage medium Technical field

This application relates to the technical field of electronic equipment, and in particular to an environment detection method, electronic equipment, and computer-readable storage media.

Background technique

With the widespread application of electronic devices, users have higher and higher performance requirements for electronic devices, especially for performance in harsh scenes. Among them, underwater scenes are a typical case. In underwater scenes, users generally have both safety and performance requirements. On the one hand, users want electronic equipment to detect that the electronic equipment is in the water and make safety reminders and protections, and on the other hand, they hope that the equipment can automatically switch underwater. The equipment-related configuration can work normally even underwater, such as taking photos or videos.

At present, underwater scene detection is mainly carried out by using the physical laws of underwater scenes through existing devices, such as detecting whether Bluetooth or other signals can be transmitted normally for underwater scene detection, or using the speaker of electronic equipment to emit sound, and the sound is received by the microphone. The sound path difference and time difference can be obtained, and the underwater scene detection is based on the sound path difference and time difference. However, signals such as Bluetooth can still be transmitted normally in shallow water, and the detection results will be biased, and the propagation path from the speaker to the microphone is not only the shell Outside air conduction or water conduction path, the sound wave of the speaker can often be transmitted to the microphone through the inside of the device, which will affect the analysis of the sound path difference and time difference, interfere with the underwater scene detection, and cause the detection result to be biased. Therefore, how to improve the detection accuracy of the environment in which the hydroelectronic equipment is located is a problem to be solved urgently.

Summary of the invention

Based on this, the present application provides an environment detection method, an electronic device, and a computer-readable storage medium, which aim to improve the detection accuracy of the environment in which the electronic device is located and improve user experience.

In the first aspect, this application provides an environmental detection method, including:

Emit the environment detection sound through the sound generator of the electronic device, and collect the environment detection sound through the sound receiver of the electronic device to obtain the collected target detection sound;

Performing feature extraction on the target detection sound to obtain sound field characteristics of the target detection sound;

The current environment in which the electronic device is located is determined according to the sound field characteristics, where the current environment includes an aquatic environment and an underwater environment.

In the second aspect, this application also provides an electronic device, the electronic device including a sounder, a sound receiver, and a processor;

The sound generator is used to emit environmental detection sounds;

The sound receiver is used to collect the environment detection sound to obtain the collected target detection sound;

The processor is used to implement the following steps:

Acquiring the target detection sound collected by the sound receiver;

Performing feature extraction on the target detection sound to obtain sound field characteristics of the target detection sound;

The current environment in which the electronic device is located is determined according to the sound field characteristics, where the current environment includes an aquatic environment and an underwater environment.

In the third aspect, the present application also provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor realizes the environment detection as described above. Method steps.

The embodiments of the application provide an environment detection method, electronic equipment, and computer-readable storage medium. By collecting environment detection sounds, target detection sounds are obtained, and feature extraction of the target detection sounds is performed to obtain the sound field characteristics of the target detection sounds. , And based on the sound field characteristics to determine the current environment in which the electronic device is located. Since the entire detection process does not involve the transmission of Bluetooth or other signals, nor does it involve the sound path difference and time difference of the sound, the current environment in which the electronic device is located can be detected , Which effectively improves the detection accuracy of the environment in which the electronic device is located, and greatly improves the user experience.

It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the application.

Description of the drawings

In order to explain the technical solutions of the embodiments of the present application more clearly, the following will briefly introduce the drawings used in the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present application. Ordinary technicians can obtain other drawings based on these drawings without creative work.

FIG. 1 is a schematic flowchart of steps of an environment detection method provided by an embodiment of the present application;

2 is a schematic diagram of the acoustic propagation path between the sound generator and the sound receiver in an embodiment of the present application;

3 is a schematic flowchart of sub-steps of the environment detection method in FIG. 1;

4 is a schematic flowchart of steps of another environment detection method provided by an embodiment of the present application;

FIG. 5 is a schematic block diagram of the structure of an electronic device according to an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

The flowchart shown in the drawings is only an example, and does not necessarily include all contents and operations/steps, nor does it have to be executed in the described order. For example, some operations/steps can also be decomposed, combined or partially combined, so the actual execution order may be changed according to actual conditions.

Hereinafter, some embodiments of the present application will be described in detail with reference to the accompanying drawings. In the case of no conflict, the following embodiments and features in the embodiments can be combined with each other.

Please refer to FIG. 1. FIG. 1 is a schematic flowchart of steps of an environment detection method provided by an embodiment of the present application. The environment detection method can be applied to electronic equipment to detect the environment in which the electronic equipment is located. Among them, electronic devices include cameras, mobile phones, tablet computers, and handheld PTZs.

Specifically, as shown in FIG. 1, the environment detection method includes step S101 to step S103.

S101: Emit an environment detection sound through a sounder of an electronic device, and collect the environment detection sound through a sound receiver of the electronic device to obtain the collected target detection sound.

Among them, the sound generator of the electronic device includes but not limited to the speaker and buzzer, the sound receiver includes but not limited to the single microphone and the dual microphone, and the environmental detection sound includes but not limited to the motor excitation sound, buzzer sound, prompt sound, voice And music, the motor excitation sound is the sound made when the motor is running, and the buzzer is the sound made by the buzzer when it is running. The environmental detection sound emitted by the sounder is simultaneously received by the sound receiver through the internal propagation path and the external propagation path, and the internal propagation path occupies the main part. Please refer to FIG. 2. FIG. 2 is a schematic diagram of the acoustic propagation path between the sound generator and the sound receiver in an embodiment of the application. As shown in FIG. 2, the sound generator 10 propagates the emitted environmental detection sound to the sound through the internal propagation path 1 The receiver 20 propagates the emitted environmental detection sound to the sound receiver 20 through the external propagation path 2 at the same time.

After the electronic device turns on the environmental detection function, the electronic device emits environmental detection sounds through the sounder at predetermined intervals or in real time, and collects the environmental detection sounds through the sound receiver of the electronic device to obtain target detection sounds. It should be noted that the aforementioned preset time can be set based on actual conditions, which is not specifically limited in this application.

In one embodiment, when the sounder of the electronic device emits the environment detection sound, the sound receiver of the electronic device is turned on, thereby controlling the sound receiver to collect the environment detection sound emitted by the sounder to obtain the target detection sound, and the sounder stops emitting At the same time as the environmental detection sound, the sound receiver is turned off to ensure that the obtained target detection sound is strictly synchronized in time with the emitted environmental detection sound, so as to facilitate the subsequent accurate extraction of acoustic features from the target detection sound.

In one embodiment, when the sound receiver is always working (such as recording or uninterrupted listening), when the sounder emits the environment detection sound, the time when the environment detection sound is emitted is recorded, and the sounder stops emitting the environment When detecting the sound, record the stop time of the environmental detection sound, and then extract the corresponding sound segment from the sound data received by the sound receiver according to the emitting time and the stop time, and filter the sound segment to obtain the target detection sound, which can guarantee The obtained target detection sound is strictly synchronized in time with the emitted environmental detection sound, which facilitates the subsequent accurate extraction of acoustic features from the target detection sound.

S102: Perform feature extraction on the target detection sound to obtain a sound field feature of the target detection sound.

After the target detection sound is obtained, feature extraction is performed on the target detection sound to obtain the sound field characteristics of the target detection sound. Among them, in the underwater rigid wall environment, the sound waves emitted by the sound source are continuously reflected and superimposed on the wall surface, which will increase the entire sound field; while in the water non-rigid wall environment, the sound waves emitted by the sound source are attenuated or even leaked on the non-rigid wall, and Attenuation is related to frequency. The sound field of a non-rigid wall environment above water is weaker than that of an underwater rigid wall environment, and the sound field characteristics include at least one of a time domain amplitude and a frequency domain amplitude.

In one embodiment, correction processing is performed on the target detection sound, so that the target detection sound after the correction processing is time-synchronized with the environment detection sound; the feature extraction is performed on the target detection sound after the correction processing to obtain the target detection sound. The sound field characteristics of the target detection sound. By ensuring that the target detection sound is strictly synchronized in time with the emitted environmental detection sound, it is convenient to accurately extract the acoustic characteristics from the target detection sound in the subsequent, thereby improving the detection accuracy of the environment in which the electronic device is located. Since the turn-on time and turn-off time of the sound generator and the sound receiver are strictly synchronized when collecting the target detection sound, the target detection sound may not be corrected, of course, the target detection sound may also be corrected, which is not specifically limited in this application. .

In an embodiment, as shown in FIG. 3, step S102 includes step S1021 to step S1023.

S1021, sampling the target detection sound to obtain a multi-frame time domain signal of the target detection sound.

After the target detection sound is collected, the target detection sound is sampled to obtain multi-frame time-domain signals of the target detection sound. Among them, the time domain signal of each frame can be expressed as:

x _l (n)=[x(Ml-N+1),...,x(Ml-1),x(Ml)],l=0,1,...,L, where N is Frame length, M is the frame shift, l is the frame number, L is the total number of frames of the target detection sound, the value range of _{N is 0.001f s} <N<f _s , and the value range of M is 0.01N<M<100N , F _s is the sampling frequency, and the frequency f _{s of the} target detection tone can be set based on actual conditions, which is not specifically limited in this application.

S1022: Perform frequency domain transformation on the multi-frame time-domain signal to obtain a multi-frame frequency-domain signal.

The frequency domain transform is performed on each frame of the time domain signal in the multi-frame time domain signal, and the frequency domain signal of each frame of the time domain signal can be obtained, thereby obtaining the multi-frame frequency domain signal. Among them, the frequency domain transform includes, but is not limited to, performing Fourier transform on time domain signals and performing wavelet transform on time domain signals.

In an embodiment, the multi-frame time-domain signal is windowed according to a preset window function; the multi-frame time-domain signal after the windowing process is subjected to frequency domain transformation to obtain the multi-frame frequency domain signal. Wherein, the preset window function includes at least one of the following: rectangular window, sinusoidal window, Hanning window, Hamming window and Gaussian window. By windowing the time-domain signal, spectral energy leakage can be reduced.

Exemplarily, a frame of time-domain signal after windowing can be expressed as: x′ _l (n)=x _l (n)w, where w is the window function of N points, and by comparing x′ _l (n) Carrying out frequency domain transformation, the corresponding frequency domain signal can be obtained as

S1023. Determine a sound field characteristic of the target detection sound according to the multi-frame frequency domain signal.

Specifically, a plurality of characteristic frequency domain amplitudes corresponding to each frame of the frequency domain signal are determined according to each frame of the frequency domain signal in the multi-frame frequency domain signal; The characteristic frequency domain amplitudes are fused to obtain multiple fused characteristic frequency domain amplitudes; the multiple fused characteristic frequency domain amplitudes are determined as the sound field characteristics of the target detection tone. Among them, by analyzing the frequency domain signal, multiple characteristic frequency domain amplitudes corresponding to the frequency domain signal can be obtained.

Among them, the method for determining the multiple characteristic frequency domain amplitudes of the frequency domain signal is specifically: calculating the frequency domain signal

_{The energies P 1,l} (n), P _2,l (n)...P _m,l (n) of m line spectra corresponding to frequencies f ₁ , f ₂ …, f _{m in}

0≤f ₁ ＜f ₂ ＜…＜f _m ＜f _s /2, 1≤m＜N/2, a _j is a weighting coefficient, Hm' and Lm' satisfy f _Lm' ≥max{0,(f _m' +f _m'-1 )/2)},f _Hm' ≤min{f _s /2,(f _m' +f _m'+1 )/2)}, so that the m characteristic frequencies of the frequency domain signal The domain amplitude is S _l (n)=[P _1,l (n), P _2,l (n)...P _m,l (n)].

In one embodiment, according to the multiple characteristic frequency domain amplitudes corresponding to each frame of frequency domain signal, the multiple characteristic frequency domain amplitudes corresponding to each frame of frequency domain signal are fused to obtain the frequency domain signal corresponding to each frame. The frequency domain amplitude of the fusion feature is obtained, and multiple fusion feature frequency domain amplitudes are obtained. Among them, the method of fusion of multiple characteristic frequency domain amplitudes is specifically: according to the multiple characteristic frequency domain amplitudes corresponding to each frame of frequency domain signal, calculating the arithmetic mean of the characteristic frequency domain amplitude of each frame of frequency domain signal, The geometric mean or median is determined, and the arithmetic mean, geometric mean, or median of the characteristic frequency domain amplitude of each frame of frequency domain signal is determined as the fused characteristic frequency domain amplitude corresponding to each frame of frequency domain signal. Exemplary, each of the frame frequency-domain signal X _l (n) corresponding to the plurality of frequency domain amplitude characteristic S _l (n) are fused, a plurality of fused features can be obtained in the frequency domain amplitude S _a (n) = [ P ₁ (n), P ₂ (n)...P _m (n)].

In an embodiment, the target detection sound is sampled to obtain a multi-frame time domain signal of the target detection sound; the sound field characteristics of the target detection sound are determined according to the time domain amplitude of the multi-frame time domain signal. Among them, the time domain signal of each frame can be expressed as:

x _l (n)=[x(Ml-N+1),...,x(Ml-1),x(Ml)],l=0,1,...,L,

Among them, N is the frame length, M is the frame shift, l is the frame number, L is the total number of frames of the target detection sound, the value range of _{N is 0.001f s} <N<f _s , and the value range of M is 0.01N <M<100N, f _s is the sampling frequency. It should be noted that the above-mentioned sampling frequency can be set based on actual conditions, which is not specifically limited in this application.

Specifically, the average value of the time domain amplitude of each frame of the time domain signal in the multi-frame time domain signal is obtained; the average value of the multi-frame time domain signal is fused, and the result after the fusion is determined as the target detection sound Sound field characteristics. Among them, the fusion method of the average value of the multi-frame time domain signal is specifically: obtaining the weighted fusion coefficient of each frame of time domain signal, and according to the weighted fusion coefficient of each frame of time domain signal and the time of each frame of time domain signal. The average value of the domain amplitude is fused to the average value of the multi-frame time domain signal to obtain the sound field characteristics of the target detection sound. By extracting the time domain amplitude of the time domain signal, the sound field characteristics of the target detection sound are determined, which requires low calculation performance of the electronic device, and the sound field characteristics of the target detection sound can be extracted without much computing resources.

Exemplarily, calculating the average value of the time domain amplitude of a frame of time domain signal, that is, calculating the average value of the time domain amplitude of x _l (n), can be expressed as: Q _l (n)=mean(abs(x _l (n))), where abs represents the absolute value operation, mean represents the averaging operation; in obtaining the average value of the time domain amplitude of each frame of time domain signal Q _l (n), l=1, 2,... After L, the average value of the time domain amplitude of each frame of time domain signal is fused to obtain the sound field characteristic Q _a (n) of the target detection sound.

S103: Determine the current environment in which the electronic device is located according to the sound field characteristics.

After the sound field characteristics of the target detection sound are determined, the current environment in which the electronic device is located is determined based on the sound field characteristics. Wherein, the current environment includes an aquatic environment and an underwater environment.

In an embodiment, the sound field characteristic threshold is acquired, and the current environment in which the electronic device is located is determined according to the sound field characteristic threshold and the sound field characteristics. If the sound field characteristic is greater than the sound field characteristic threshold, the current environment where the electronic device is located is determined The environment is an underwater environment; if the sound field characteristic is less than or equal to the sound field characteristic threshold, it is determined that the current environment in which the electronic device is located is an aquatic environment. Wherein, the sound field feature threshold is determined according to at least one of a first sound field feature set of the underwater environment and a second sound field feature set of the water environment, and the first sound field feature set includes the target detection sound of the underwater environment Multiple sound field features, and the second sound field feature set includes multiple sound field features of target detection sounds in the water environment.

Exemplarily, the first sound field feature set of the underwater environment is A={S _water,1 ,S _water,2 …S _water,l1 }, and the second sound field feature set of the water environment is B={S _air,1 ,S _air,2 …S _air,l2 }, where l1 and l2 can be set based on the actual situation, which is not specifically limited. Optionally, l1 and l2 are greater than or equal to 10. The sound field characteristic threshold can be determined by A={S _water,1 ,S _water,2 ...S _water,l1 } and/or B={S _air,1 ,S _air,2 ...S _air,l2}.

In one embodiment, a reference sound field characteristic is acquired, and the difference between the sound field characteristic of the target detection sound and the reference sound field characteristic is calculated, and the difference between the sound field characteristic of the target detection sound and the reference sound field characteristic is determined to determine the location of the electronic device. The current environment of the place. Wherein, the reference sound field characteristic is determined according to the first sound field characteristic set of the underwater environment or the second sound field characteristic set of the underwater environment.

Specifically, if the reference sound field feature is determined according to the first sound field feature set of the underwater environment, then if the difference between the sound field feature of the target detection sound and the reference sound field feature is less than the preset difference threshold, it can be determined The current environment in which the electronic device is located is an underwater environment, and if the difference between the sound field characteristics of the target detection sound and the reference sound field characteristics is greater than or equal to the preset difference threshold, it can be determined that the current environment in which the electronic device is located is water surroundings.

Specifically, if the reference sound field feature is determined according to the second sound field feature set of the aquatic environment, if the difference between the sound field feature of the target detection sound and the reference sound field feature is less than the preset difference threshold, the electronic device can be determined The current environment in which the electronic device is located is an underwater environment, and if the difference between the sound field characteristics of the target detection sound and the reference sound field characteristics is greater than or equal to the preset difference threshold, it can be determined that the current environment in which the electronic device is located is an underwater environment.

Specifically, the first sound field feature set of the underwater environment and the second sound field feature set of the water environment are acquired; the first mean value and the first standard deviation of the first sound field feature set are calculated, and the second sound field feature set is calculated The second mean value and the second standard deviation of the; according to the first mean value, the first standard deviation, the second mean value and the second standard deviation, the sound field characteristic threshold is determined.

Exemplarily, the first difference between the first mean and the second mean is calculated, and the second difference between the first standard deviation and the second standard deviation is calculated; according to the first difference and the second difference, Determine the candidate threshold coefficient that meets the preset conditions, and use the largest candidate threshold coefficient as the target threshold coefficient; calculate the first product of the first standard deviation and the target threshold coefficient, and calculate the sum of the first product and the first mean; The second product of the two standard deviations and the target threshold coefficient, and calculate the sum of the second product and the second mean; according to the sum of the first product and the first mean, and the sum of the second product and the second mean, Determine the threshold of sound field characteristics. The preset condition is that the target threshold coefficient is less than the ratio of the first difference to the second difference.

For example, the multi-frame frequency domain amplitude of the underwater environment is:

After fusion, the sound field characteristics of the underwater environment are obtained as [94 58 104], and the multi-frame frequency domain amplitude of the aquatic environment is:

After fusion, the sound field characteristics of the water environment are obtained as [16 7 11], the first sound field characteristic set of the underwater environment and the second sound field characteristic set of the water environment can be obtained through multiple collections, and then the first sound field characteristics The set and/or the second sound field feature set of the water environment may determine the sound field feature threshold.

In the environment detection method provided by the foregoing embodiment, the target detection sound is obtained by collecting the environment detection sound, and the feature extraction of the target detection sound is performed to obtain the sound field characteristics of the target detection sound, and based on the sound field characteristics, the location of the electronic device is determined In the current environment, since the entire detection process does not involve the transmission of Bluetooth or other signals, nor does it involve the sound path difference and time difference, the current environment in which the electronic device is located can be detected, which effectively improves the detection of the environment in which the electronic device is located. The accuracy greatly improves the user experience.

Please refer to FIG. 4, which is a schematic flowchart of the steps of another environment detection method provided by an embodiment of the present application.

Specifically, as shown in FIG. 4, the environment detection method includes steps S201 to S204.

S201: Emit an environment detection sound through a sounder of an electronic device, and collect the environment detection sound through a sound receiver of the electronic device to obtain the collected target detection sound.

After the electronic device turns on the environmental detection function, the electronic device emits environmental detection sounds through the sounder at predetermined intervals or in real time, and collects the environmental detection sounds through the sound receiver of the electronic device to obtain target detection sounds. It should be noted that the aforementioned preset time can be set based on actual conditions, which is not specifically limited in this application.

S202: Perform feature extraction on the target detection sound to obtain a sound field feature of the target detection sound.

After the target detection sound is obtained, feature extraction is performed on the target detection sound to obtain the sound field characteristics of the target detection sound. Among them, in the underwater rigid wall environment, the sound waves emitted by the sound source are continuously reflected and superimposed on the wall surface, which will increase the entire sound field; while in the water non-rigid wall environment, the sound waves emitted by the sound source are attenuated or even leaked on the non-rigid wall, and Attenuation is related to frequency. The sound field of a non-rigid wall environment above water is weaker than that of an underwater rigid wall environment, and the sound field characteristics include at least one of a time domain amplitude and a frequency domain amplitude.

S203. Input the sound field characteristics into a preset environment discrimination model to obtain an environment type label output by the preset environment discrimination model.

Wherein, the preset environment discrimination model is optimized based on the first sound field feature set of the underwater environment and the second sound field feature set of the water environment, and the environment discrimination model is a binary classification model or a neural network Model, through the first sound field feature set of the underwater environment and the second sound field feature set of the water environment to optimize the parameters of the two-class model or the neural network model to obtain the environment discrimination model. The neural network model includes, but is not limited to, a convolutional neural network, a recurrent neural network, and a recurrent convolutional neural network.

After the target detection sound is obtained, the sound field characteristics are input to the preset environment discrimination model to obtain the environment type label output by the preset environment discrimination model. Wherein, the environment type label includes a first preset label corresponding to an underwater environment and a second preset label corresponding to an aquatic environment. The following uses a two-class model to explain the construction process of the environmental discriminant model.

The sound field characteristics of the target detection sound in the water environment and the underwater environment are calculated many times in advance, and the first sound field feature set A={S _water,1 ,S _water,2 …S _water,l1 } and the water are obtained respectively. The second sound field feature set of the lower environment B={S _air,1 ,S _air,2 …S _air,l2 }, the label of set A is y _i =+1, the label of set B is y _j =-1,l1 , l2 is greater than 10, randomly mix all data to obtain sample data T={(x ₁ ,y ₁ ),(x ₂ ,y ₂ ),...,(x _N ,y _N )}, N=l1+l2.

Select the kernel function K(x, z) and the parameter C. The kernel function can be selected based on the actual situation. This manual takes the Gaussian kernel function as an example for explanation. Through the Gaussian kernel function and the parameter C, you can get:

Then through the sample data T = {(x ₁ ,y ₁ ),(x ₂ ,y ₂ ),...,(x _N ,y _N )} to find the optimal solution

Choose a positive component of ^{α *} _{0＜α j} ＜c, calculate

Finally, the decision function is constructed:

The constructed decision function is the environment discrimination model. It can be understood that the sound field characteristics of the target detection sound are input to the decision function, and when the output result is +1, it can be determined that the current environment of the electronic device is an underwater environment, and the output When the result is -1, it can be determined that the current environment of the electronic device is a water environment.

S204: Determine the current environment in which the electronic device is located according to the environment type label.

Specifically, it is determined whether the environment type label output by the environment discrimination model is the first preset label or the second preset label; if the environment type label output by the environment discrimination model is the first preset label, it is confirmed that the electronic device is located The current environment of is an underwater environment; if the environment type label output by the environment discrimination model is the second preset label, it is determined that the current environment in which the electronic device is located is an aquatic environment. Optionally, the first preset label is +1, and the second preset label is -1.

In an embodiment, when it is determined that the photographing device of the electronic device is in an underwater environment, the imaging parameters of the photographing device are adjusted. Wherein, the imaging parameter includes at least one of the following: exposure duration, aperture value, sensitivity value, and exposure gain. When the shooting device is in an underwater environment, adjusting the imaging parameters of the shooting device can improve the image quality of the shooting device and greatly improve the user experience.

In the environment detection method provided by the above-mentioned embodiments, the target detection sound is obtained by collecting the environment detection sound, and the feature extraction of the target detection sound is performed to obtain the sound field characteristics of the target detection sound, and the sound field characteristics of the target detection sound are obtained based on the sound field characteristics and the environment discrimination model, namely The current environment where the electronic device is located can be quickly and accurately determined, which greatly improves the user experience.

Please refer to FIG. 5, which is a schematic block diagram of an electronic device according to an embodiment of the present application. In an embodiment, the electronic device includes, but is not limited to, a camera, a mobile phone, a tablet computer, and a handheld pan/tilt. Further, the electronic device 300 includes a processor 301, a sounder 302, and a sound receiver 303. The processor 301, the sounder 302, and the sound receiver 303 are connected by a bus 304, such as I2C (Inter-integrated Circuit). bus.

Specifically, the processor 301 may be a micro-controller unit (MCU), a central processing unit (CPU), a digital signal processor (Digital Signal Processor, DSP), or the like.

Specifically, the sound generator 302 includes but is not limited to a speaker and a buzzer, and the sound receiver 303 includes but is not limited to a single microphone and a dual microphone.

Wherein, the sound generator 302 is used to emit environmental detection sounds;

The sound receiver 303 is configured to collect the environmental detection sound to obtain the collected target detection sound;

The processor 301 is configured to implement the following steps:

Acquiring the target detection sound collected by the sound receiver;

Performing feature extraction on the target detection sound to obtain sound field characteristics of the target detection sound;

The current environment in which the electronic device is located is determined according to the sound field characteristics, where the current environment includes an aquatic environment and an underwater environment.

Optionally, when the processor implements feature extraction of the target detection sound to obtain the sound field characteristics of the target detection sound, it is used to achieve:

Performing correction processing on the target detection sound, so that the target detection sound after the correction processing is synchronized with the environment detection sound;

Perform feature extraction on the target detection sound after the correction process to obtain the sound field characteristics of the target detection sound.

Optionally, when the processor implements feature extraction of the target detection sound to obtain the sound field characteristics of the target detection sound, it is used to achieve:

Sampling the target detection sound to obtain a multi-frame time domain signal of the target detection sound;

Performing frequency domain transformation on the multi-frame time domain signal to obtain a multi-frame frequency domain signal;

The sound field characteristic of the target detection sound is determined according to the multi-frame frequency domain signal.

Optionally, when the processor implements frequency domain transformation on the multi-frame time-domain signal to obtain a multi-frame frequency-domain signal, it is used to implement:

Performing windowing processing on the multi-frame time domain signal according to a preset window function;

Perform frequency domain transformation on the multi-frame time-domain signal after the windowing process to obtain the multi-frame frequency-domain signal.

Optionally, when the processor realizes the determination of the sound field characteristics of the target detection sound according to the multi-frame frequency domain signal, it is used to realize:

Determining multiple characteristic frequency domain amplitudes corresponding to each frame of frequency domain signal according to each frame of frequency domain signal in the multi-frame frequency domain signal;

Fusing multiple characteristic frequency domain amplitude values corresponding to each frame of the frequency domain signal in the multi-frame frequency domain signal to obtain multiple fused characteristic frequency domain amplitude values;

The frequency domain amplitudes of the multiple fusion features are determined as the sound field features of the target detection sound.

Optionally, when the processor implements feature extraction of the target detection sound to obtain the sound field characteristics of the target detection sound, it is used to achieve:

Sampling the target detection sound to obtain a multi-frame time domain signal of the target detection sound;

The sound field characteristic of the target detection sound is determined according to the time domain amplitude of the multi-frame time domain signal.

Optionally, when the processor realizes the determination of the sound field characteristics of the target detection sound according to the time domain amplitude of the multi-frame time domain signal, it is used to realize:

Obtain the average value of the time domain amplitude of each frame of the time domain signal in the multi-frame time domain signal;

The average value of the multi-frame time domain signals is fused, and the result after the fusion is determined as the sound field feature of the target detection sound.

Optionally, when the processor implements the determination of the current environment in which the electronic device is located according to the sound field characteristics, it is used to implement:

Acquiring a sound field characteristic threshold, where the sound field characteristic threshold is determined according to at least one of the first sound field characteristic set of the underwater environment and the second sound field characteristic set of the water environment;

The current environment where the electronic device is located is determined according to the sound field characteristic threshold value and the sound field characteristic.

Optionally, when the processor implements the acquisition of the sound field characteristic threshold, it is used to implement:

Acquiring the first sound field feature set of the underwater environment and the second sound field feature set of the water environment;

Calculating the first mean value and the first standard deviation of the first sound field feature set, and calculating the second mean value and the second standard deviation of the second sound field feature set;

According to the first mean value, the first standard deviation, the second mean value, and the second standard deviation, the sound field characteristic threshold is determined.

Optionally, when the processor realizes the determination of the current environment in which the electronic device is located according to the sound field characteristic threshold and the sound field characteristic, the processor is configured to realize:

If the sound field characteristic is greater than the sound field characteristic threshold, determining that the current environment in which the electronic device is located is an underwater environment;

If the sound field characteristic is less than or equal to the sound field characteristic threshold, it is determined that the current environment in which the electronic device is located is a water environment.

Optionally, when the processor implements the determination of the current environment in which the electronic device is located according to the sound field characteristics, it is used to implement:

Input the sound field characteristics into a preset environment discrimination model to obtain an environment type label output by the preset environment discrimination model;

The current environment in which the electronic device is located is determined according to the environment type label.

Optionally, the preset environment discrimination model is optimized based on the first sound field feature set of the underwater environment and the second sound field feature set of the water environment.

Optionally, the electronic equipment includes a photographing device; the processor implementation is also used to implement:

When it is determined that the photographing device is in an underwater environment, the imaging parameters of the photographing device are adjusted.

Optionally, the sound generator includes a speaker, a buzzer or a motor, and the sound receiver includes a microphone.

Optionally, the sound field characteristics include at least one of a time domain amplitude and a frequency domain amplitude.

It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the electronic device described above can refer to the corresponding process in the foregoing environmental detection method embodiment, which will not be repeated here. Go into details.

The embodiments of the present application also provide a computer-readable storage medium, the computer-readable storage medium stores a computer program, the computer program includes program instructions, and the processor executes the program instructions to implement the foregoing implementation The steps of the environmental detection method provided in the example.

Wherein, the computer-readable storage medium may be the internal storage unit of the electronic device described in any of the foregoing embodiments, such as the hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk equipped on the electronic device, a smart memory card (Smart Media Card, SMC), and a secure digital (Secure Digital, SD) ) Card, Flash Card, etc.

It should be understood that the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in the specification of this application and the appended claims, unless the context clearly indicates other circumstances, the singular forms "a", "an" and "the" are intended to include plural forms.

It should also be understood that the term "and/or" used in the specification of this application and the appended claims refers to any combination of one or more of the items listed in association and all possible combinations, and includes these combinations.

The above are only specific implementations of this application, but the protection scope of this application is not limited to this. Any person skilled in the art can easily think of various equivalents within the technical scope disclosed in this application. Modifications or replacements, these modifications or replacements shall be covered within the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

Claims (31)

1. An environment detection method, characterized in that it comprises:

   Emit the environment detection sound through the sound generator of the electronic device, and collect the environment detection sound through the sound receiver of the electronic device to obtain the collected target detection sound;

   Performing feature extraction on the target detection sound to obtain sound field characteristics of the target detection sound;

   The current environment in which the electronic device is located is determined according to the sound field characteristics, where the current environment includes an aquatic environment and an underwater environment.
2. The environment detection method according to claim 1, wherein the feature extraction of the target detection sound to obtain the sound field characteristics of the target detection sound comprises:

   Performing correction processing on the target detection sound, so that the target detection sound after the correction processing is synchronized with the environment detection sound;

   Perform feature extraction on the target detection sound after the correction process to obtain the sound field characteristics of the target detection sound.
3. The environment detection method according to claim 1 or 2, wherein the feature extraction of the target detection sound to obtain the sound field characteristics of the target detection sound comprises:

   Sampling the target detection sound to obtain a multi-frame time domain signal of the target detection sound;

   Performing frequency domain transformation on the multi-frame time domain signal to obtain a multi-frame frequency domain signal;

   The sound field characteristic of the target detection sound is determined according to the multi-frame frequency domain signal.
4. The environment detection method according to claim 3, wherein the performing frequency domain transformation on the multi-frame time domain signal to obtain the multi-frame frequency domain signal comprises:

   Performing windowing processing on the multi-frame time domain signal according to a preset window function;

   Perform frequency domain transformation on the multi-frame time-domain signal after the windowing process to obtain the multi-frame frequency-domain signal.
5. The environment detection method according to claim 3 or 4, wherein the determining the sound field characteristics of the target detection sound according to the multi-frame frequency domain signal comprises:

   Determining multiple characteristic frequency domain amplitudes corresponding to each frame of frequency domain signal according to each frame of frequency domain signal in the multi-frame frequency domain signal;

   Fusing multiple characteristic frequency domain amplitude values corresponding to each frame of the frequency domain signal in the multi-frame frequency domain signal to obtain multiple fused characteristic frequency domain amplitude values;

   The frequency domain amplitudes of the multiple fusion features are determined as the sound field features of the target detection sound.
6. The environment detection method according to any one of claims 1 to 5, wherein the feature extraction of the target detection sound to obtain the sound field characteristics of the target detection sound comprises:

   Sampling the target detection sound to obtain a multi-frame time domain signal of the target detection sound;

   The sound field characteristic of the target detection sound is determined according to the time domain amplitude of the multi-frame time domain signal.
7. The environment detection method according to claim 6, wherein the determining the sound field characteristics of the target detection sound according to the time domain amplitude of the multi-frame time domain signal comprises:

   Obtain the average value of the time domain amplitude of each frame of the time domain signal in the multi-frame time domain signal;

   The average value of the multi-frame time domain signals is fused, and the result after the fusion is determined as the sound field feature of the target detection sound.
8. The environment detection method according to any one of claims 1 to 7, wherein the determining the current environment in which the electronic device is located according to the characteristics of the sound field comprises:

   Acquiring a sound field characteristic threshold, where the sound field characteristic threshold is determined according to at least one of the first sound field characteristic set of the underwater environment and the second sound field characteristic set of the water environment;

   The current environment where the electronic device is located is determined according to the sound field characteristic threshold value and the sound field characteristic.
9. The environment detection method according to claim 8, wherein said acquiring a threshold value of a sound field feature comprises:

   Acquiring the first sound field feature set of the underwater environment and the second sound field feature set of the water environment;

   Calculating the first mean value and the first standard deviation of the first sound field feature set, and calculating the second mean value and the second standard deviation of the second sound field feature set;

   According to the first mean value, the first standard deviation, the second mean value, and the second standard deviation, the sound field characteristic threshold is determined.
10. The environment detection method according to claim 8 or 9, wherein the determining the current environment in which the electronic device is located according to the sound field characteristic threshold and the sound field characteristic comprises:

    If the sound field characteristic is greater than the sound field characteristic threshold, determining that the current environment in which the electronic device is located is an underwater environment;

    If the sound field characteristic is less than or equal to the sound field characteristic threshold, it is determined that the current environment in which the electronic device is located is a water environment.
11. The environment detection method according to any one of claims 1 to 10, wherein the determining the current environment in which the electronic device is located according to the characteristics of the sound field comprises:

    Input the sound field characteristics into a preset environment discrimination model to obtain an environment type label output by the preset environment discrimination model;

    The current environment in which the electronic device is located is determined according to the environment type label.
12. The environment detection method according to claim 11, wherein the preset environment discrimination model is optimized based on the first sound field feature set of the underwater environment and the second sound field feature set of the water environment.
13. The environment detection method according to any one of claims 1 to 12, wherein the electronic equipment comprises a photographing device; the method further comprises:

    When it is determined that the photographing device is in an underwater environment, the imaging parameters of the photographing device are adjusted.
14. The environment detection method according to claim 1 or 13, wherein the sound generator comprises a speaker, a buzzer or a motor, and the sound receiver comprises a microphone.
15. The environment detection method according to claim 1 or 13, wherein the sound field characteristics include at least one of a time domain amplitude and a frequency domain amplitude.
16. An electronic device, characterized in that the electronic device includes a sound generator, a sound receiver, and a processor;

    The sound generator is used to emit environmental detection sounds;

    The sound receiver is configured to collect the environmental detection sound to obtain the collected target detection sound;

    The processor is used to implement the following steps:

    Performing feature extraction on the target detection sound to obtain sound field characteristics of the target detection sound;

    The current environment in which the electronic device is located is determined according to the sound field characteristics, where the current environment includes an aquatic environment and an underwater environment.
17. The electronic device according to claim 16, wherein when the processor implements feature extraction of the target detection sound to obtain the sound field characteristics of the target detection sound, it is used to achieve:

    Performing correction processing on the target detection sound, so that the target detection sound after the correction processing is synchronized with the environment detection sound;

    Perform feature extraction on the target detection sound after the correction process to obtain the sound field characteristics of the target detection sound.
18. The electronic device according to claim 16 or 17, wherein when the processor implements feature extraction of the target detection sound to obtain the sound field characteristics of the target detection sound, it is used to achieve:

    Sampling the target detection sound to obtain a multi-frame time domain signal of the target detection sound;

    Performing frequency domain transformation on the multi-frame time domain signal to obtain a multi-frame frequency domain signal;

    The sound field characteristic of the target detection sound is determined according to the multi-frame frequency domain signal.
19. The electronic device according to claim 18, wherein when the processor implements frequency domain transformation on the multi-frame time-domain signal to obtain a multi-frame frequency-domain signal, it is used to implement:

    Performing windowing processing on the multi-frame time domain signal according to a preset window function;

    Perform frequency domain transformation on the multi-frame time-domain signal after the windowing process to obtain the multi-frame frequency-domain signal.
20. The electronic device according to claim 18 or 19, wherein when the processor realizes the determination of the sound field characteristics of the target detection sound according to the multi-frame frequency domain signal, it is used to realize:

    Determining multiple characteristic frequency domain amplitudes corresponding to each frame of frequency domain signal according to each frame of frequency domain signal in the multi-frame frequency domain signal;

    Fusing multiple characteristic frequency domain amplitude values corresponding to each frame of the frequency domain signal in the multi-frame frequency domain signal to obtain multiple fused characteristic frequency domain amplitude values;

    The frequency domain amplitudes of the multiple fusion features are determined as the sound field features of the target detection sound.
21. The electronic device according to any one of claims 16 to 20, wherein when the processor implements feature extraction of the target detection sound to obtain the sound field characteristics of the target detection sound, it is used to achieve:

    Sampling the target detection sound to obtain a multi-frame time domain signal of the target detection sound;

    The sound field characteristic of the target detection sound is determined according to the time domain amplitude of the multi-frame time domain signal.
22. 22. The electronic device according to claim 21, wherein when the processor realizes the determination of the sound field characteristic of the target detection sound according to the time domain amplitude of the multi-frame time domain signal, it is used to realize:

    Obtain the average value of the time domain amplitude of each frame of the time domain signal in the multi-frame time domain signal;

    The average value of the multi-frame time domain signals is fused, and the result after the fusion is determined as the sound field feature of the target detection sound.
23. The electronic device according to any one of claims 16 to 22, wherein, when the processor realizes the determination of the current environment in which the electronic device is located according to the characteristics of the sound field, it is configured to realize:

    Acquiring a sound field characteristic threshold, where the sound field characteristic threshold is determined according to at least one of the first sound field characteristic set of the underwater environment and the second sound field characteristic set of the water environment;

    The current environment where the electronic device is located is determined according to the sound field characteristic threshold value and the sound field characteristic.
24. The electronic device according to claim 23, wherein when the processor implements the acquisition of the sound field characteristic threshold, it is used to implement:

    Acquiring the first sound field feature set of the underwater environment and the second sound field feature set of the water environment;

    Calculating the first mean value and the first standard deviation of the first sound field feature set, and calculating the second mean value and the second standard deviation of the second sound field feature set;

    According to the first mean value, the first standard deviation, the second mean value, and the second standard deviation, the sound field characteristic threshold is determined.
25. The electronic device according to claim 23 or 24, wherein when the processor realizes the determination of the current environment in which the electronic device is located according to the sound field characteristic threshold and the sound field characteristic, the processor is configured to realize:

    If the sound field characteristic is greater than the sound field characteristic threshold, determining that the current environment in which the electronic device is located is an underwater environment;

    If the sound field characteristic is less than or equal to the sound field characteristic threshold, it is determined that the current environment in which the electronic device is located is a water environment.
26. The electronic device according to any one of claims 16 to 25, wherein when the processor realizes the determination of the current environment in which the electronic device is located according to the characteristics of the sound field, it is configured to realize:

    Input the sound field characteristics into a preset environment discrimination model to obtain an environment type label output by the preset environment discrimination model;

    The current environment in which the electronic device is located is determined according to the environment type label.
27. The electronic device according to claim 26, wherein the preset environment discrimination model is optimized based on the first sound field feature set of the underwater environment and the second sound field feature set of the water environment.
28. The electronic device according to any one of claims 16 to 27, wherein the electronic device comprises a photographing device; and the processor implementation is also used to implement:

    When it is determined that the photographing device is in an underwater environment, the imaging parameters of the photographing device are adjusted.
29. The electronic device according to claim 16 or 28, wherein the sound generator comprises a speaker, a buzzer or a motor, and the sound receiver comprises a microphone.
30. The electronic device according to claim 16 or 28, wherein the sound field characteristic comprises at least one of a time domain amplitude and a frequency domain amplitude.
31. A computer-readable storage medium, characterized in that, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor realizes as described in any one of claims 1 to 15 The environmental detection method described.

Images