Early warning method and system for abnormal event in public place, product and camera

Abstract

The invention provides an early warning method and system for an abnormal event in a public place, a product and a camera, and the method comprises the steps: monitoring an audio of the public place, and determining a sound source position corresponding to the audio when an abnormal sound appears; adjusting a preset camera to turn to a sound source position, collecting image information and sound information at the sound source and transmitting the image information and the sound information to a processor; the processor extracts depth feature information of the sound information and inputs the depth feature information into a public place abnormal sound discrimination network, whether the sound information is public place abnormal sound is determined, and if yes, the category of the public place abnormal sound is determined; and uploading the category of the abnormal sound in the public place and the audio and video data to a cloud platform so as to give out a warning prompt and push an alarm condition. By means of the technical scheme, when the abnormal sound appears in the public place, the category information of the sound is judged, the information and the collected audio and video data are uploaded to the cloud platform, meanwhile, an alarm is given out, follow-up investigation and evidence obtaining are facilitated, and police strength allocation of the abnormal event is facilitated for the police.

Description

Technical Field

[0001] The present invention relates to the field of audio and video technology, and in particular to an early warning method, system, product and camera for abnormal events in public places. Background Art

[0002] Abnormal events in public places are often accompanied by abnormal sounds such as explosions, gunshots and screams. These abnormal events are often sudden and uncertain. Therefore, in order to monitor abnormal events in public places in real time, a sound tracing and capturing system is widely used on the market. However, this sound tracing and capturing system is only suitable for noise excess monitoring and does not have the ability to analyze abnormal sounds in public places in real time. Summary of the invention

[0003] The embodiments of the present invention provide a method, system, product and camera for early warning of abnormal events in public places. When a sound higher than the ambient noise floor is detected, the category information of the sound is analyzed and an alarm is issued for the abnormal sound.

[0004] In order to achieve the above-mentioned purpose, on the one hand, a method for early warning of abnormal events in public places is provided, comprising:

[0005] Monitoring audio in a public place, and when the decibel value of the audio is higher than a predetermined noise index, determining the location of a sound source corresponding to the audio;

[0006] Adjusting the horizontal rotation angle and the vertical rotation angle of the preset camera to turn the camera toward the sound source position, collecting image information at the sound source position through the camera, collecting sound information at the sound source position through the preset microphone module, and transmitting the collected image information and sound information to the first processor;

[0007] The first processor uses a Transformer module to extract deep feature information of the sound information, and inputs the deep feature information into a pre-trained public place abnormal sound discrimination network to determine whether the sound information is an abnormal sound in a public place, and when the sound information is an abnormal sound in a public place, determine the category of the abnormal sound in a public place; wherein the category of the abnormal sound in a public place includes: explosion, gunshot and scream;

[0008] When the sound information is an abnormal sound in a public place, the first processor extracts key video frame data of the image information, and uploads the category of the abnormal sound in the public place, the sound information and the key video frame data to the cloud platform to issue a warning prompt and push an alarm.

[0009] Preferably, the method further comprises the following preprocessing step of the first processor on the sound information before extracting the depth feature information of the sound information:

[0010] Performing pre-emphasis processing on the sound information through a high-pass filter;

[0011] Divide the pre-emphasized signal into multiple short-time frames of a predetermined length, and the length of each frame shift is 1 / 2 to 1 / 3 of the frame length;

[0012] multiplying each of the short time frames by a predetermined window function;

[0013] Performing a fast Fourier transform on each frame signal to obtain a frequency spectrum and a time-phase spectrogram of the sound information, and then taking the square of the modulus of the frequency spectrum to obtain a power spectrum of the sound information;

[0014] A predetermined set of triangular filters with equal Mel scales is used to extract the frequency band of the power spectrum to obtain a Mel spectrogram; wherein the center frequencies of the set of triangular filters are equally spaced according to the Mel scale, the set of triangular filters covers the entire audio frequency range of the sound information, and the bandwidth of the set of triangular filters increases with the increase of frequency;

[0015] The logarithm of each frequency component of the mel-spectrogram is taken to obtain a logarithmic mel-spectrogram.

[0016] Preferably, the method described above determines the sound source position by means of a preset sound source tracing module, wherein the sound source tracing module is provided with a microphone array.

[0017] Preferably, in the method described above, the camera is a pan-tilt camera connected to the sound tracing module; the pan-tilt camera is correspondingly linked with the sound tracing module; the camera and the sound tracing module are pre-calibrated with reference coordinates.

[0018] Preferably, in the method described, the roll angle of the pan-tilt camera is 0 to 360 degrees, the pitch angle is -15 to 105 degrees, and the beam angle is less than 5 degrees.

[0019] Preferably, in the method, the position of the sound source module is fixed, and the step of adjusting the horizontal rotation angle and the vertical rotation angle of the preset camera to turn the camera to the sound source position includes:

[0020] Set the coordinates of the sound source tracing module to (0,0,0), the coordinates of the camera relative to the sound source tracing module to (x,y,z), the initial orientation of the camera to horizontal north, and the coordinates of the sound source relative to the fixed sound source tracing module to (1,m,n);

[0021] According to the geometric relationship, the horizontal rotation angle of the camera is calculated as follows: the north direction is represented as a unit vector, set to N = (0, 1, 0), the horizontal rotation angle μ is the vector The angle with the unit vector N, that is, μ = arccos((M·N) / M|)*(180 / π);

[0022] According to the geometric relationship, the vertical rotation angle of the camera is calculated as follows: the vertical upward direction is represented as a unit vector, set to C = (0, 0, 1), and the vertical rotation angle ε is the vector The angle with the unit vector C, that is, ε = arccos((M·C) / M)*(180 / π).

[0023] On the other hand, there is also provided an early warning system for abnormal events in public places for implementing the early warning method as described above, comprising:

[0024] A sound decibel collection and analysis module is used to monitor the audio in public places and determine whether the decibel value of the audio is higher than a predetermined ambient noise floor;

[0025] A sound source tracing module, used to determine the sound source position corresponding to the audio when the decibel value of the audio is higher than a predetermined ambient noise floor;

[0026] A camera is used to collect images of public places, and when the decibel value of the audio is higher than a predetermined ambient noise floor, adjust its own horizontal rotation angle and vertical rotation angle to turn the camera toward the sound source position, and transmit the image information at the sound source position collected by the camera and the sound information at the sound source position collected by the preset microphone module to the first processor;

[0027] The first processor is used to extract deep feature information of the sound information by using a Transformer module, and input the deep feature information into a pre-trained public place abnormal sound discrimination network to determine whether the sound information is an abnormal sound in a public place, and when the sound information is an abnormal sound in a public place, determine the category of the abnormal sound in a public place; wherein the category of the abnormal sound in a public place includes: explosions, gunshots and screams; when the sound information is an abnormal sound in a public place, extract key video frame data of the image information, and upload the category of the abnormal sound in a public place, the sound information and the key video frame data to a cloud platform to issue a warning prompt and push an alarm.

[0028] On the other hand, a computer-readable storage medium is provided, wherein at least one program is stored in the storage medium, and the at least one program is executed by a processor to implement the steps executed by the first processor in any of the early warning methods described above.

[0029] On the other hand, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the steps executed by the first processor in any of the above-mentioned early warning methods are implemented.

[0030] In another aspect, a camera for implementing the method for early warning of abnormal events in public places as described above is provided, the camera comprising:

[0031] An image acquisition module, used for acquiring images of public places;

[0032] The control module is used to adjust the horizontal rotation angle and the vertical rotation angle of the smart camera when the decibel value of the audio in the public place is higher than the predetermined ambient noise floor, so that the smart camera is turned toward the sound source position, and transmit the image information at the sound source position collected by the camera and the sound information at the sound source position collected by the preset microphone module to the first processor.

[0033] The above technical solution has the following technical effects:

[0034] The technical solution of the embodiment of the present invention can determine the source position of the abnormal sound in a public place, adjust the horizontal rotation angle and the vertical rotation angle of the preset camera to turn the camera to the sound source position, collect image information at the sound source through the camera and collect sound information at the sound source through the microphone module, and transmit the collected image information and sound information to the processor; the processor extracts the deep feature information of the sound information after pre-processing the sound information, and inputs the deep feature information into a pre-trained public place abnormal sound discrimination network to determine whether the sound information is an abnormal sound in a public place, such as whether it is a sporadic and isolated abnormal sound, such as an explosion, a gunshot, and a scream; if so, determine the category of the abnormal sound in the public place, and transmit the category information of the abnormal sound and the collected audio and video information to the cloud platform, and issue an alarm at the same time, so as to realize the timely push of public safety sound events to the back-end alarm, improve the accuracy, real-time and convenience of monitoring abnormal events in public places, and help the police understand the situation on the scene through the alarm information and make reasonable police force arrangements. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a flow chart of a method for early warning of abnormal events in public places according to an embodiment of the present invention;

[0036] Figure 2It is a structural schematic diagram of an early warning system for abnormal events in public places according to an embodiment of the present invention;

[0037] Figure 3 It is an example of an early warning system for abnormal events in public places according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] To further illustrate the various embodiments, the present invention provides drawings. These drawings are part of the disclosure of the present invention, which are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, a person of ordinary skill in the art should be able to understand other possible implementations and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0039] The present invention will now be further described with reference to the accompanying drawings and specific implementation methods.

[0040] Embodiment 1:

[0041] Figure 1 FIG. 1 is a flow chart of a method for early warning of abnormal events in public places according to an embodiment of the present invention. Figure 1 The early warning method for abnormal events in public places of this embodiment includes the following steps:

[0042] Monitor the audio in public places and determine the location of the sound source corresponding to the audio when the decibel value of the audio is higher than the predetermined noise index;

[0043] Adjust the horizontal rotation angle and the vertical rotation angle of the preset camera to turn the camera to the sound source position, collect image information at the sound source position through the camera, collect sound information at the sound source position through the preset microphone module, and transmit the collected image information and sound information to the first processor;

[0044] In a specific implementation, the first processor has voice analysis capabilities and can directly analyze and extract abnormal sounds in public places at the edge.

[0045] The first processor uses the Transformer module to extract deep feature information of the sound information, and inputs the deep feature information into a pre-trained public place abnormal sound discrimination network to determine whether the sound information is an abnormal sound in a public place, and when the sound information is an abnormal sound in a public place, judge the category of the abnormal sound in the public place; preferably, the above-mentioned identified abnormal sounds in public places are sporadic and isolated abnormal sounds under relevant background sounds, such as the categories of abnormal sounds in public places include: explosions, gunshots and screams; when the sound information is an abnormal sound in a public place, the first processor extracts key video frame data of the image information, and uploads the category of the abnormal sound in the public place, the sound information and the key video frame data to the cloud platform to issue a warning prompt and push the alarm.

[0046] In a specific implementation, before extracting the depth feature information of the sound information, the first processor also performs the following preprocessing steps on the sound information:

[0047] The sound information is pre-emphasized through a high-pass filter;

[0048] Divide the pre-emphasized signal into multiple short-time frames of a predetermined length, and the length of each frame shift is 1 / 2 to 1 / 3 of the frame length;

[0049] Multiply each short time frame by a predetermined window function;

[0050] Perform a fast Fourier transform on each frame of signal to obtain the spectrum and time-phase spectrogram of the sound information, and then take the square of the spectrum modulus to obtain the power spectrum of the sound information; use the fast Fourier transform (FFT) algorithm to convert the signal from the time domain to the frequency domain; take the square of the spectrum modulus to obtain the power spectrum, which is the energy of the signal at different frequencies; in this way, the time domain signal can be converted to the frequency domain in order to analyze the energy distribution of the signal at different frequencies;

[0051] A predetermined set of triangular filters with equal Mel scales are used to extract the frequency bands of the power spectrum to obtain a Mel spectrogram; wherein the center frequencies of a set of triangular filters are equally spaced according to the Mel scale, a set of triangular filters covers the entire audio frequency range of the sound information, and the bandwidth of a set of triangular filters increases with increasing frequency; the bandwidth of the filter increases with increasing frequency to simulate the characteristics of the human ear being sensitive to low frequencies and insensitive to high frequencies, so as to better reflect the differences in the perception of the human ear to different frequencies;

[0052] Taking the logarithm of each frequency component of the Mel spectrogram, we get a logarithmic Mel spectrogram. Taking the logarithm can reduce the dynamic range of the values, making the data easier to process and analyze. At the same time, the logarithm can also make the distinction between features more obvious.

[0053] In a specific implementation, the pre-emphasized signal is divided into multiple short-time frames with a length of 20-30ms. Abnormal sound signals in public places are non-stationary, and the framing operation ensures a smooth transition between frames and avoids discontinuity between frames.

[0054] In a specific implementation, the window function includes a Hamming window, a rectangular window, a Hanning window, etc. This can reduce spectrum leakage, make both ends of the frame transition smoothly to zero, and reduce the influence of the Gibbs Phenomenon.

[0055] In a specific implementation, the sound source position is determined by a pre-set sound source tracing module, and the sound source tracing module is provided with a microphone array.

[0056] In a specific implementation, the camera is a pan-tilt camera connected to a sound source tracing module; the pan-tilt camera and the sound source tracing module are correspondingly linked; the camera and the sound source tracing module are pre-calibrated with reference coordinates to ensure consistency of their directions.

[0057] In a specific implementation, the roll angle of the pan-tilt camera is 0 to 360 degrees, the pitch angle is -15 to 105 degrees, and the beam angle is less than 5 degrees.

[0058] In a specific implementation, the position of the sound source module is fixed, and the steps of adjusting the horizontal rotation angle and the vertical rotation angle of the preset camera to turn the camera to the sound source position include:

[0059] Set the coordinates of the sound source tracing module to (0,0,0), the coordinates of the camera relative to the sound source tracing module to (x,y,z), the initial direction of the camera to horizontal north, and the coordinates of the sound source relative to the fixed sound source tracing module to (1,m,n);

[0060] According to the geometric relationship, the calculation method of the horizontal rotation angle of the camera is as follows: the north direction is represented as a unit vector, set to N = (0, 1, 0), and the horizontal rotation angle μ is the vector The angle with the unit vector N, that is, μ = arccos((M·N) / M|)*(180 / π);

[0061] According to the geometric relationship, the vertical rotation angle of the camera is calculated as follows: the vertical upward direction is represented as a unit vector, set to C = (0, 0, 1), and the vertical rotation angle ε is the vector The angle with the unit vector C, that is, ε = arccos((M·C) / M)*(180 / π).

[0062] By utilizing the technical solution of the embodiments of the present invention, abnormal sounds in public places can be automatically monitored in real time, dangerous scenes can be intelligently identified, sound sources can be automatically located, and video can be linked to capture evidence and report dangerous situations, thereby improving the accuracy, real-time and convenience of safety monitoring in public places, and realizing the visualization of the monitoring process and real-time alarm linkage.

[0063] Embodiment 2:

[0064] The present invention also provides an early warning system for abnormal events in public places, comprising:

[0065] A sound decibel collection and analysis module is used to monitor the audio in public places and determine whether the decibel value of the audio is higher than a predetermined ambient noise floor;

[0066] A sound source tracing module, used to determine the sound source position corresponding to the audio when the decibel value of the audio is higher than a predetermined ambient noise floor;

[0067] A camera is used to collect images of public places, and when the decibel value of the audio is higher than a predetermined ambient noise floor, adjust its own horizontal rotation angle and vertical rotation angle to turn the camera toward the sound source position, and transmit the image information at the sound source position collected by the camera and the sound information at the sound source position collected by the preset microphone module to the first processor;

[0068] The first processor is used to extract deep feature information of the sound information by using a Transformer module, and input the deep feature information into a pre-trained public place abnormal sound discrimination network to determine whether the sound information is an abnormal sound in a public place, and when the sound information is an abnormal sound in a public place, determine the category of the abnormal sound in a public place; wherein the category of the abnormal sound in a public place includes: explosions, gunshots and screams; when the sound information is an abnormal sound in a public place, extract key video frame data of the image information, and upload the category of the abnormal sound in a public place, the sound information and the key video frame data to a cloud platform to issue a warning prompt and push an alarm.

[0069] Figure 2 FIG. 1 is a schematic diagram of the structure of an early warning system for abnormal events in public places according to an embodiment of the present invention. Figure 2 In this embodiment, the early warning system also includes: a warning light module for warning and a communication module for uploading data to the cloud platform; wherein the sound decibel collection and analysis module, the first processor, the warning light module, the communication module and the sound pickup module for collecting sound information at the sound source are integrated in the central processing module as an AI edge computing terminal.

[0070] Figure 3This is a specific implementation of the early warning system of an embodiment of the present invention. In this specific implementation, the central processing module and the sound tracing module are integrated in the same circuit board, which is installed in the black box 301 above the camera; the pan-tilt camera 302 is rotated, which is linked to the coordinates of the sound tracing module, with a roll angle of 0 to 360 degrees and a pitch angle of -15 to 105 degrees, and a beam angle of less than 5 degrees.

[0071] Embodiment three:

[0072] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method in the embodiment of the present invention are implemented.

[0073] If the module / unit integrated in the computer unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory) and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.

[0074] Embodiment 4:

[0075] The present invention also provides a computer program product, comprising a computer program, characterized in that when the computer program is executed by a processor, the steps of any of the method embodiments described above are implemented.

[0076] Embodiment five:

[0077] The present invention also provides a camera for realizing an early warning method for abnormal events in public places, the camera comprising:

[0078] An image acquisition module, used for acquiring images of public places;

[0079] The control module is used to adjust the horizontal rotation angle and the vertical rotation angle of the smart camera when the decibel value of the audio in the public place is higher than the predetermined ambient noise floor, so that the smart camera is turned toward the sound source position, and transmit the image information at the sound source position collected by the camera and the sound information at the sound source position collected by the preset microphone module to the first processor.

[0080] Although the present invention has been specifically shown and described in conjunction with the preferred embodiments, it should be understood by those skilled in the art that various changes may be made to the present invention in form and details without departing from the spirit and scope of the present invention as defined by the appended claims, all of which are within the scope of protection of the present invention.

Claims

1. A method for early warning of abnormal events in public places, characterized in that: include: Monitoring audio in a public place, and when the decibel value of the audio is higher than a predetermined noise index, determining the location of a sound source corresponding to the audio; Adjusting the horizontal rotation angle and the vertical rotation angle of the preset camera to turn the camera toward the sound source position, collecting image information at the sound source position through the camera, collecting sound information at the sound source position through the preset microphone module, and transmitting the collected image information and sound information to the first processor; The first processor uses a Transformer module to extract deep feature information of the sound information, and inputs the deep feature information into a pre-trained public place abnormal sound discrimination network to determine whether the sound information is an abnormal sound in a public place, and when the sound information is an abnormal sound in a public place, determine the category of the abnormal sound in a public place; wherein the category of the abnormal sound in a public place includes: explosion, gunshot and scream; When the sound information is an abnormal sound in a public place, the first processor extracts key video frame data of the image information, and uploads the category of the abnormal sound in the public place, the sound information and the key video frame data to the cloud platform to issue a warning prompt and push an alarm.

2. The early warning method according to claim 1, characterized in that: Before extracting the depth feature information of the sound information, the method further includes the following preprocessing steps performed by the first processor on the sound information: Performing pre-emphasis processing on the sound information through a high-pass filter; Divide the pre-emphasized signal into multiple short-time frames of a predetermined length, and the length of each frame shift is 1 / 2 to 1 / 3 of the frame length; multiplying each of the short time frames by a predetermined window function; Performing a fast Fourier transform on each frame signal to obtain a frequency spectrum and a time-phase spectrogram of the sound information, and then taking the square of the modulus of the frequency spectrum to obtain a power spectrum of the sound information; A predetermined set of triangular filters with equal Mel scales is used to extract the frequency band of the power spectrum to obtain a Mel spectrogram; wherein the center frequencies of the set of triangular filters are equally spaced according to the Mel scale, the set of triangular filters covers the entire audio frequency range of the sound information, and the bandwidth of the set of triangular filters increases with the increase of frequency; The logarithm of each frequency component of the mel-spectrogram is taken to obtain a logarithmic mel-spectrogram.

3. The early warning method according to claim 1, characterized in that: The sound source position is determined by a preset sound source tracing module, wherein a microphone array is provided inside the sound source tracing module.

4. The early warning method according to claim 3, characterized in that: The camera is a pan-tilt camera connected to the sound source tracing module; the pan-tilt camera is correspondingly linked with the sound source tracing module; the camera and the sound source tracing module are pre-calibrated with reference coordinates.

5. The early warning method according to claim 4, characterized in that: The roll angle of the pan-tilt camera is 0 to 360 degrees, the pitch angle is -15 to 105 degrees, and the beam angle is less than 5 degrees.

6. The early warning method according to claim 4, characterized in that: The position of the sound source module is fixed, and the step of adjusting the horizontal rotation angle and the vertical rotation angle of the preset camera to make the camera turn to the sound source position includes: Set the coordinates of the sound source tracing module to (0,0,0), the coordinates of the camera relative to the sound source tracing module to (x,y,z), the initial orientation of the camera to horizontal north, and the coordinates of the sound source relative to the fixed sound source tracing module to (1,m,n); According to the geometric relationship, the horizontal rotation angle of the camera is calculated as follows: the north direction is represented as a unit vector, set to N = (0, 1, 0), and the horizontal rotation angle μ is the vector The angle with the unit vector N, that is, μ = arccos((M·N) / M|)*(180 / π); According to the geometric relationship, the vertical rotation angle of the camera is calculated as follows: the vertical upward direction is represented as a unit vector, set to C = (0, 0, 1), and the vertical rotation angle ε is the vector The angle with the unit vector C, that is, ε = arccos((M·C) / M)*(180 / π).

7. An early warning system for abnormal events in public places using the early warning method described in any one of claims 1 to 6, characterized in that: include: A sound decibel collection and analysis module is used to monitor the audio in public places and determine whether the decibel value of the audio is higher than a predetermined ambient noise floor; A sound source tracing module, used to determine the sound source position corresponding to the audio when the decibel value of the audio is higher than a predetermined ambient noise floor; A camera is used to collect images of public places, and when the decibel value of the audio is higher than a predetermined ambient noise floor, adjust its own horizontal rotation angle and vertical rotation angle to turn the camera toward the sound source position, and transmit the image information at the sound source position collected by the camera and the sound information at the sound source position collected by the preset microphone module to the first processor; The first processor is used to extract deep feature information of the sound information by using a Transformer module, and input the deep feature information into a pre-trained public place abnormal sound discrimination network to determine whether the sound information is an abnormal sound in a public place, and when the sound information is an abnormal sound in a public place, determine the category of the abnormal sound in a public place; wherein the category of the abnormal sound in a public place includes: explosions, gunshots and screams; when the sound information is an abnormal sound in a public place, extract key video frame data of the image information, and upload the category of the abnormal sound in a public place, the sound information and the key video frame data to a cloud platform to issue a warning prompt and push an alarm.

8. A computer-readable storage medium, characterized in that: The storage medium stores at least one program, and the at least one program is executed by the processor to implement the steps executed by the first processor in the early warning method according to any one of claims 1 to 7.

9. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps performed by the first processor in the early warning method according to any one of claims 1 to 7 are implemented.

10. A camera for implementing the early warning method for abnormal events in public places as claimed in any one of claims 1 to 7, characterized in that: The camera comprises: An image acquisition module, used for acquiring images of public places; The control module is used to adjust the horizontal rotation angle and the vertical rotation angle of the smart camera when the decibel value of the audio in the public place is higher than the predetermined ambient noise floor, so that the smart camera is turned toward the sound source position, and transmit the image information at the sound source position collected by the camera and the sound information at the sound source position collected by the preset microphone module to the first processor.

Images