CN112509602A

CN112509602A - Home monitoring method, device, equipment and storage medium

Info

Publication number: CN112509602A
Application number: CN202011523857.3A
Authority: CN
Inventors: 郭俊雄; 王健宗
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2020-12-18
Filing date: 2020-12-18
Publication date: 2021-03-16

Abstract

The invention provides a home monitoring method, a home monitoring device, home monitoring equipment and a storage medium, wherein the method is simple and efficient, is reasonable and reliable in design, and can accurately detect a target sound source and realize timely home monitoring. The method comprises the steps of detecting pulse signals in sound source signals, extracting measurement characteristics by utilizing energy and statistical analysis, and finally obtaining target signals by utilizing threshold screening, so that the target sound sources can be accurately identified in non-stationary signals, the sounds needing to be detected can be identified in a noisy real environment, the purpose of medical sound source detection is achieved, and the sounds needing to be detected are extracted from continuous signal streams.

Description

Home monitoring method, device, equipment and storage medium

Technical Field

The invention relates to home health monitoring, in particular to a home monitoring method, a system, equipment and a storage medium.

Background

With the trend of aging of the population becoming more and more remarkable, more health facilities are required to ensure the health of the elderly. Especially for the elderly living alone, if an accident occurs and the elderly cannot know the accident at the first time, the treatment time may be delayed, and adverse effects may occur. In the traditional Chinese culture, the old people are not a good choice to be sent to a nursing home, so that how to monitor the health accident of the old people living alone at home in the first time is a critical problem.

At present, a common monitoring mode on the market is a household camera, and children can know that the old man plays at home to achieve the purpose of monitoring through the camera. For example, chinese patent CN108335458A discloses a household intelligent monitoring system and method for monitoring a house, which utilizes an intelligent robot to redefine a monitoring function through an intelligent manner of home-recognition, person-recognition, voice-recognition, posture-recognition, and heart-beat and body temperature-recognition, thereby preventing theft and intrusion, timely detecting and intervening an emergency situation that a child wants to leave a safe area and an old person suddenly encounters an urgent disease and cannot call for help, notifying a guardian, and preventing the situation from deteriorating; meanwhile, the nurse behavior is monitored, and the severe events which are expringed and abused are captured and identified in time, and the guardian is notified to prevent the condition from deteriorating; use image identification to give first place to, other ways are supplementary, but if the house is covered with the camera, to solitary old man or the personnel that need care for, can leak self privacy when monitored, make it invade. Therefore, a more concealed and accurate way to monitor is needed, and the sound monitoring alarm technology for specific sounds is a better choice.

There are various fields in signal detection, such as detection of digital signals in noise, radar signal detection and voice activity detection. There are many ways to define the measured features, including the probability of statistical modeling, energy, etc. Most of the detection systems currently available focus on detecting human speech, rather than impulsive sounds. Impulse sound detection is less studied. Some studies have only achieved good results in white noise. Most of the existing detection systems are concentrated in detecting human voice, and other sounds are removed as noise, but target sound signals are difficult to separate in a noisy environment, so that the detected object cannot be accurately detected, the detection accuracy and efficiency are low, and good home monitoring cannot be realized.

Disclosure of Invention

Aiming at the problems in the prior art, the invention provides a home monitoring method, a device, equipment and a storage medium, the method is simple and efficient, the design is reasonable and reliable, the target sound source can be accurately detected, and the timely home monitoring is realized.

The invention is realized by the following technical scheme:

a method for monitoring a living body at home,

collecting sound source signals in a home environment in real time;

detecting a pulse signal in a sound source signal;

analyzing the energy and statistics of the pulse signals to obtain the measurement characteristics of sound source detection;

and after the measurement characteristics are compared with the set threshold value, identifying to obtain a target signal of home monitoring, and transmitting the target signal to the monitoring terminal.

Preferably, impulse signal detection in the sound source signal is detected using a discrete wavelet transform.

Further, the wavelet basis in the discrete wavelet transform is generated by shifting and expanding the mother wavelet.

Still further, the mother wavelet is a multi-bayesian wavelet.

Preferably, the pulse signal is analyzed in terms of energy and statistics, and the method specifically comprises the following steps,

processing the pulse signal by a median filtering algorithm based on an energy condition to obtain a condition median filtering energy;

and (4) subtracting the signal energy of the pulse signal from the conditional median filtering energy to obtain the measurement characteristic of sound source detection.

Preferably, the real-time acquisition of the sound source signal x (t) in the domestic environment is represented as follows,

where t is time, u is time shift, k is a weighting constant, s is a scaling factor, ψ_u,s(t) is a general function of the wavelet transform.

A home-based monitoring device comprises a monitor unit,

the acquisition module is used for acquiring sound source signals in a home environment in real time;

the detection module is used for detecting a pulse signal in the sound source signal;

the analysis module is used for analyzing the energy and statistics of the pulse signals to obtain the measurement characteristics of sound source detection;

the comparison module is used for identifying and obtaining a target signal of home monitoring after comparing the measurement characteristic with a set threshold value;

and the transmission module is used for transmitting the target signal to the monitoring terminal.

Preferably, the analysis module is further configured to,

A home monitoring apparatus comprising a processor and a memory, the memory having stored thereon a computer program which, when executed by the processor, is capable of carrying out a method of home monitoring as claimed in any one of the preceding claims.

A computer-readable storage medium, having a computer program stored thereon, wherein the computer program, when executed by a processor, implements a method of home care as claimed in any one of the above.

Compared with the prior art, the invention has the following beneficial technical effects:

the invention detects the pulse signal in the sound source signal, utilizes energy and statistical analysis to realize the extraction of the measurement characteristics, and finally utilizes the threshold value to screen and obtain the target signal, thereby accurately identifying the target sound source in the unstable signal, ensuring that the sound required to be detected can be identified in the noisy real environment, achieving the purpose of medical sound source detection, and extracting the required sound from the continuous signal stream.

Drawings

Fig. 1 is a schematic flow chart of a home monitoring method according to an embodiment of the present invention.

Fig. 2 is a schematic flow chart illustrating signal processing in the home monitoring method according to the embodiment of the invention.

Fig. 3 is a block diagram of a home monitoring system according to an embodiment of the present invention.

Detailed Description

The present invention will now be described in further detail with reference to specific examples, which are intended to be illustrative, but not limiting, of the invention.

The embodiment of the invention provides a home monitoring method, a home monitoring device, a home monitoring equipment and a storage medium.

The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

For convenience of understanding, a specific flow of the embodiment of the present invention is described below, and referring to fig. 2, an embodiment of a home monitoring method according to the embodiment of the present invention includes:

step 101, collecting sound source signals in a home environment in real time;

it is understood that the main body of the step may be an acquisition module, and may also be a terminal, a device or a set of acquisition equipment, such as a microphone arranged singly or in a system, which is not limited herein. In the embodiment of the present invention, a microphone is taken as an example for explanation, and any one of the prior art may be used in a specific acquisition process to acquire sound in a home environment.

102, detecting a pulse signal in a sound source signal;

it is understood that the main body of the step may be the detection module, and may also be a terminal or a server, which is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject.

The server acquires the acquired sound source signals in the home environment, wherein the sound source signals are continuously acquired and transmitted, so that pulse signals in the sound source signals can be detected and identified in real time.

It should be noted that, after receiving a sound source signal of a monitored object, the server needs to perform detection processing on the sound source signal, and the signal after the detection processing can be better analyzed, so that the server finally recognizes more accurate information. This step of operation can also be done directly on the terminal by means of the processor. The signals obtained by subsequent processing are ensured to be more accurate and efficient as much as possible, high-quality parameters are provided for signal measurement feature extraction, and the subsequent processing quality and efficiency are improved.

In the preferred embodiment, the detection of the pulse signal in the sound source signal is specifically detected by using discrete wavelet transform;

wavelet transforms are often used for signal detection and audio processing due to their local characteristics in time-frequency space and non-uniform time-frequency resolution. In processing the sound source signal, continuous wavelets and their wavelet transforms need to be discretized. In general, a binary discrete process is used in computer implementation, and the wavelet subjected to the discretization and the corresponding wavelet transform are converted into discrete wavelet transform (DWT for short). In practice, the discrete wavelet transform is obtained by discretizing the scale and displacement of the continuous wavelet transform by a power of 2, and is also called binary wavelet transform.

Although the classical fourier transform may reflect the overall connotation of the signal, the representation is often not intuitive and noise can complicate the signal spectrum. In the field of signal processing, a family of bandpass filters has been used to decompose a signal into different frequency components, i.e., signal f (x) is fed to a family of bandpass filters hi (x).

Discrete Wavelet Transform (DWT) is used for the acquired sound source signals, the significance of wavelet decomposition is that the signals can be decomposed on different scales, and the selection of different scales can be determined according to different targets.

For many signals, the low frequency component is important, often implying a characteristic of the signal, while the high frequency component gives details or differences in the signal. Human voice, if the high frequency components are removed, sounds different from before, but still knows what is being said; if enough low frequency components are removed, some meaningless sound is heard. Approximation and detail are commonly used in wavelet analysis. Approximately represents the high-scale, i.e., low-frequency, information of the signal; the details represent the high scale, i.e. high frequency information, of the signal. Thus, the original signal passes through two mutual filters to produce two signals.

By continuously decomposing the approximate signal through a continuous decomposition process, the signal can be decomposed into a plurality of low-resolution components. In theory the decomposition can proceed without limitation, but in fact the decomposition can proceed until the detail (high frequency) contains only a single sample. Therefore, in practical applications, the appropriate number of decomposition layers is generally selected according to the characteristics of the signal or an appropriate standard.

In particular, all sound source signals x (t) can be decomposed into the function ψ_u,s(t) and weighted by k, u, s,

where t is time, u is time shift, k is a weighting constant, and s is a scaling factor. Function psi_u,sThe type of (t) is a generic function chosen accordingly, based on short-time fourier transformation ("frequency" analysis) or wavelet transformation ("time scale" analysis) of the sound source signal.

Discrete Wavelet Transform (DWT) has non-uniform frequency and time resolution. The reason why the DWT is used for pulse signal detection is that the time resolution in high frequency is high, and the time resolution in low frequency is poor, so that the time resolution in high frequency can be well reserved through the DWT, a time point corresponding to a sound source is obtained, and the detection precision and accuracy are improved. Where the wavelet basis is generated by a translation and dilation of the mother wavelet ψ. Dobesy wavelets are used as mother wavelets because they have good regularity for a large number of moments in the signal processing process.

103, analyzing the energy and statistics of the pulse signals to obtain the measurement characteristics of sound source detection; after the pulse signal is detected, the following operation is performed,

after the server acquires the pulse signals, based on an energy condition median filtering algorithm, energy and statistics analysis is carried out on the pulse signals after DWT; and extracting the measurement characteristics of the sound source information from the pulse signals by utilizing energy and statistical analysis.

It will be appreciated that in the acoustic source signal, very rich feature parameters are contained, and different feature vectors characterize different physical and acoustic meanings. The measurement characteristics extracted by the server have great significance for success or failure of sound source detection, and if appropriate measurement parameters are selected, the identification rate can be improved. The extraction of the measurement features is to extract or reduce the influence of information irrelevant to identification in the sound source signal as much as possible, reduce the data amount to be processed in the subsequent identification stage, and generate the measurement features representing the identification object information carried in the sound source signal.

Energy and statistical analysis is a statistical process to study and analyze vibrations and sound from an energy perspective. The basic idea is to avoid solving complex mathematical equations and instead study the transfer and balance of energy between the various parts of the system in a statistical way to obtain a concise physical solution.

Generally, in medical sound monitoring, the detection of sound source is crucial. Since once the sound source is lost (not detected) in the first step, the subsequent monitoring step cannot be performed. On the other hand, if many "false sound sources" are detected, the whole detection process tends to be saturated, so that the "true sound sources" cannot be accurately detected. Therefore, acoustic source detection is crucial.

Acoustic source detection is essentially the detection of a signal. Detection involves identifying the desired signal in a noisy environment. The assumption is that:

where o (t) is the signal being analyzed, b (t) is noise, and a (t) is the target signal to be detected. The basic function of the detection algorithm in the present invention is to extract some measured features or quantities from the input signal and compare these values to a threshold.

The method is based on an energy condition median filtering algorithm, the measurement characteristic is the difference between signal energy and condition median filtering energy, and a detection result is obtained after the measurement characteristic is compared with a set threshold value.

The pulse signal detected in the invention is actually an energy signal, namely an energy-limited signal; because in the usual home monitoring, the detection of the sound source is actually to acquire the specific sound source when an accident happens, the sound source has the characteristics of concentrated and limited energy and can not continuously occur within a limited time interval.

The energy signal itself is a pulsed signal, which is usually present only for a limited time interval. Of course, some energy signals exist in an infinite time interval, but the main part of the energy signals is concentrated in a finite time interval, and the signals can well represent the accidents in home monitoring, so that the energy signals in the sound source signals can be extracted in a pulse form through discrete wavelet transformation, the pulse signals of the energy signals are rectangular pulse signals, and the magnitude of the energy is the product of the amplitude and the pulse width of the rectangular pulse signals, so that the energy of the obtained pulse signals can be obtained very conveniently and quickly.

Based on energy conditionsMedian valueThe filtering algorithm actually utilizes a median filtering algorithm to well filter and eliminate noise points of energy signals represented by rectangular pulse signals, so that the characteristics of the energy are more concentrated; the basic principle of the technique is to substitute the value of a point in a digital image or digital sequence by the median of the values of points in a neighborhood of the point, so as to allow the surrounding points to be filteredPixelThe values are close to the true values, thereby eliminating isolated noise points. Therefore, the signal energy represented by the pulse signal can be represented as median filtering energy through a median filtering algorithm, each median filtering energy represents the statistical energy of the adjacent pulse signals, the statistical energy and the pulse signal energy are used for making a difference to obtain the measurement characteristic of the pulse signal, and what is actually represented is the protruding degree of the pulse signal energy relative to the adjacent pulse signal energy, so that the signal specificity is further enhanced; and finally, the projection degree is limited through a threshold value, and the screening of the excess energy is realized, so that other non-detection pulse signals in the sound source signal, such as the interference of continuous pulse signals, are further filtered, and the accident in the home monitoring can be more accurately detected and monitored.

Processing the pulse signal by a median filtering algorithm based on an energy condition to obtain a condition median filtering energy; the energy of the pulse signal is used as a processing object to perform median filtering processing, so that conditional median filtering energy is obtained and used as a reference, and the difference between each pulse signal and the reference is limited by a threshold value, so that a target sound source can be accurately identified in a non-stationary signal (such as the pulse signal), and the sound required to be detected can be identified in a noisy real environment.

And 104, comparing the measurement characteristics with a set threshold value, identifying to obtain a target signal of home monitoring, and transmitting the target signal to the monitoring terminal.

The above-mentioned process is actually embodied in the process of signal processing, i.e. the continuous change and utilization of signal types, as shown in fig. 2, the process of processing the sound source signal 201 by the home monitoring method according to one embodiment of the present invention is as follows,

carrying out Discrete Wavelet Transform (DWT) on the sound source signal 201 to obtain a pulse signal 202;

performing energy and statistical analysis on the pulse signal 202 to obtain a measurement characteristic 203;

judging the threshold value of the measurement characteristic 203 to obtain whether the corresponding sound source signal 201 is a target signal 204; and finally, screening the target signal 204.

An embodiment of the present invention also provides a home monitoring device, as shown in fig. 3, which includes,

the acquisition module 301 is used for acquiring a sound source signal in a home environment in real time;

a detection module 302, configured to detect a pulse signal in a sound source signal;

the analysis module 303 is configured to perform energy and statistical analysis on the pulse signal to obtain a measurement characteristic of sound source detection;

a comparison module 304, configured to compare the measurement characteristic with a set threshold, and identify and obtain a target signal of home monitoring;

a transmission module 305, configured to transmit the target signal to the monitoring terminal.

Wherein the analysis module 303 is further configured to,

An embodiment of the present invention further provides a home monitoring apparatus, including a processor and a memory, where the memory stores a computer program, and the computer program, when executed by the processor, can implement the home monitoring method according to any one of the above aspects.

An embodiment of the present invention further provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, or a volatile computer-readable storage medium, having a computer program stored thereon, where the computer program, when executed by a processor, implements the home monitoring method according to any of the above aspects.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.

Claims

1. A home-based monitoring method is characterized in that,

collecting sound source signals in a home environment in real time;

detecting a pulse signal in a sound source signal;

2. A home monitoring method according to claim 1, wherein the detection of the pulse signal in the acoustic source signal is detected using a discrete wavelet transform.

3. The method of claim 2, wherein the wavelet basis in the discrete wavelet transform is generated by shifting and expanding the mother wavelet.

4. The method of claim 3, wherein the mother wavelet is a Dobey wavelet.

5. The home monitoring method of claim 1, wherein the pulse signal is analyzed by energy and statistics, and the method further comprises the steps of,

6. The home monitoring method according to claim 1, wherein the real-time acquisition of the sound source signal x (t) in the home environment is represented as follows,

7. A home monitoring device is characterized by comprising,

8. The home monitoring device of claim 7, wherein said analyzing module is further configured to,

9. A home monitoring device comprising a processor and a memory, the memory having stored thereon a computer program which, when executed by the processor, is capable of carrying out a method of home monitoring according to any one of claims 1-6.

10. A computer-readable storage medium, having stored thereon a computer program, for implementing a method of home monitoring as claimed in any one of claims 1-6, when being executed by a processor.