CN105100758A - Method and equipment used for security and protection monitoring as well as camera - Google Patents
Method and equipment used for security and protection monitoring as well as camera Download PDFInfo
- Publication number
- CN105100758A CN105100758A CN201510639758.4A CN201510639758A CN105100758A CN 105100758 A CN105100758 A CN 105100758A CN 201510639758 A CN201510639758 A CN 201510639758A CN 105100758 A CN105100758 A CN 105100758A
- Authority
- CN
- China
- Prior art keywords
- information
- characteristic
- audio information
- audio
- alarm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012806 monitoring device Methods 0.000 claims description 15
- 238000005070 sampling Methods 0.000 claims description 11
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 9
- 229910002091 carbon monoxide Inorganic materials 0.000 claims description 9
- 239000000779 smoke Substances 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 description 12
- 230000002123 temporal effect Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004297 night vision Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Landscapes
- Alarm Systems (AREA)
Abstract
The embodiment of the invention provides a method and equipment used for security and protection monitoring as well as a camera. The method comprises the following steps: acquiring video information and audio information in a monitoring scene; judging whether the acquired audio information contains feature audio information or not; when the fact that the acquired audio information contains the feature audio information is judged, saving the video information and/or audio information acquired within the preset time period; generating alarm information corresponding to the feature audio information, and sending the alarm information to a client of a user. According to the embodiment of the invention, the problem that accidents in a monitored area cannot be automatically fed back in the conventional security and protection monitoring manner is solved.
Description
Technical Field
The invention relates to the technical field of security monitoring, in particular to a method and equipment for security monitoring and a camera.
Background
Security monitoring is used as an important means for realizing security control of the inside and the periphery of a monitored area, and is increasingly widely applied. The existing security monitoring method generally sends video and audio data of a monitoring site acquired in real time to monitoring personnel, and then the monitoring personnel manually control the safety of a monitoring area. However, there are many disadvantages to this approach of security monitoring that relies on manual operation. For example, for a monitoring area inside a home, it is not suitable to arrange a special monitoring person for manual monitoring due to its privacy. At this time, if there is no person at home, or only the old or the young are at home, if an accident occurs at home, for example: the existing household monitoring camera can record audio and video data, but cannot identify the situation occurring on the spot. In addition, although the conventional alarm device arranged in the household can detect smoke or carbon monoxide in the household and generate a large ringing sound, the household members with processing capability cannot know the situation of the site because the household members are not at home, so that the household members cannot process the smoke or carbon monoxide in time. If the disaster is serious and not dealt with in time, property and life safety is possibly endangered.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method, a device, and a camera for security monitoring, which solve the problem that an existing security monitoring method cannot automatically feed back an accident in a monitored area.
An embodiment of the present invention provides a security monitoring method, including:
collecting video information and audio information in a monitoring scene;
judging whether the collected audio information contains characteristic audio information or not;
when the characteristic audio information is judged to be contained, video information and/or audio information collected within a preset time period are/is saved; and
and generating alarm information corresponding to the characteristic audio information, and sending the alarm information to a client of a user.
Further, when it is determined that the characteristic audio information is included, the storing the video information and/or the audio information collected within the preset time period includes:
when the characteristic audio information is identified, video information and/or audio information collected within a period of time before and after the characteristic audio information is identified is stored; or
And when the characteristic audio information is identified, starting to acquire video information in a monitoring scene, and storing the video information and/or audio information in a preset time period after the characteristic audio information is identified.
Further, the storing the video information and/or the audio information collected within the preset time period includes:
storing the video information and/or the audio information collected in the preset time period in a local memory; and/or
And storing the video information and/or the audio information collected in the preset time period on a cloud server.
Further, when the video information and/or the audio information collected within the preset time period are stored on a cloud server, the generating of alarm information corresponding to the characteristic audio information and the sending of the alarm information to the client of the user include:
meanwhile, generating alarm information corresponding to the characteristic audio information, and sending the alarm information to the cloud server;
and the cloud server pushes the alarm information to a client of a user through a message pushing service.
Further, the method further comprises:
sending the video information and/or the audio information acquired in the preset time period to a client of a user together with the alarm information; or
And transmitting the video information and/or the audio information collected in the monitoring scene to the client of the user in real time while transmitting the alarm information to the client of the user.
Further, the method further comprises:
storing the association relation between the equipment for acquiring the video information and/or the audio information in the monitoring scene and the user client; wherein, generating alarm information corresponding to the characteristic audio information, and sending the alarm information to a client of a user comprises:
generating alarm information corresponding to the characteristic audio information, wherein the alarm information comprises an identifier corresponding to the equipment;
and sending the alarm information to a user client corresponding to the equipment according to the identifier corresponding to the equipment in the alarm information and the stored association relationship between the equipment and the user client.
Further, the determining whether the collected audio information includes characteristic audio information includes:
sampling the collected audio information into time domain audio information, and dividing the time domain audio information into a plurality of time domain information segments according to time;
respectively carrying out Fourier transform on the plurality of time domain information segments to obtain a plurality of frequency domain information segments;
intercepting the part of the frequency in the characteristic frequency range in each frequency domain information segment as a characteristic information segment;
judging whether the amplitude of each characteristic information segment meets a preset condition or not; if yes, recording the current characteristic information segment as an effective information segment; otherwise, recording the current characteristic information segment as an invalid information segment;
connecting time domain waveforms corresponding to all the effective information segments and the ineffective information segments according to the time sequence to obtain characteristic time domain waveforms; and
judging whether the characteristic time domain waveform is matched with the waveform parameter of the characteristic audio information; and if the audio information is matched with the characteristic audio information, judging that the audio information contains the characteristic audio information.
Further, the judging whether the amplitude of each feature information segment meets the preset condition includes:
and if the amplitude of the characteristic information segment is higher than a first threshold value, the preset condition is met.
Further, the judging whether the amplitude of each feature information segment meets the preset condition includes:
calculating the vibration quantity of at least one frequency point except the frequency point corresponding to the amplitude; and if the ratio of the amplitude to the vibration quantity of the at least one frequency point is higher than a second threshold value, determining that a preset condition is met.
Further, before intercepting a portion of each of the frequency-domain information segments having a frequency within a characteristic frequency range as a characteristic information segment, the method further comprises:
dividing each frequency domain information segment into a plurality of frequency bands according to frequency; wherein the plurality of frequency bands comprise frequency bands corresponding to characteristic frequency ranges;
calculating the average vibration quantity of each of the plurality of frequency bands;
calculating the ratio of the average vibration quantity of the frequency band corresponding to the characteristic frequency range to the sum of the average vibration quantities of all other frequency bands;
if the ratio is within a preset ratio range, it is determined that the current frequency domain information segment does not contain the characteristic information segment, and therefore, the part of the frequency within the characteristic frequency range in the current frequency domain information segment is not intercepted as the characteristic information segment.
Further, the characteristic audio information is characteristic audio information in preset alarm audio; the preset alarm audio comprises an alarm audio sent by a smoke alarm, an alarm audio sent by a carbon monoxide alarm and a pre-learned custom alarm audio.
Further, the client of the user is a portable mobile device.
An embodiment of the present invention provides a security monitoring apparatus, including: the device comprises a video acquisition device, an audio acquisition device, a processor, a storage device and a sending device; the video acquisition device, the audio acquisition device, the storage device and the sending device are respectively connected with the processor; wherein,
the processor comprises a receiving module, a judging module and an alarming module which are connected in sequence; the receiving module receives video information and audio information in a monitoring scene from the video acquisition device and the audio acquisition device respectively and transmits the video information and the audio information to the judging module; when the judgment module judges that the audio information contains the characteristic audio information, the judgment module sends the video information and the audio information collected in a preset time period to the storage device for storage, and informs the alarm module to generate alarm information corresponding to the characteristic audio information; and the alarm module sends the alarm information to a client of a user through the sending device.
Further, the storage device is a local memory or is located in a cloud server.
Further, when the storage device is a cloud server, the cloud server supports a message push service;
wherein, the alarm module sends the alarm information to a client of a user through the sending device, and the client comprises:
the alarm module sends the alarm information to the cloud server through the sending device;
and the cloud server pushes the alarm information to a client of a user through a message pushing service.
Further, the transmitting device supports wired network connections and/or wireless network connections.
Further, the video acquisition device is a CCD type optical image sensor or a CMOS type optical image sensor, and/or the video acquisition device includes a 360 ° rotating pan/tilt head.
Further, the security monitoring device further comprises one or more of the following devices connected to the processor:
a display device, an infrared illumination device, a speaker device, an apparatus rotation device, and an external interface device.
An embodiment of the present invention provides a camera, including any one of the security monitoring devices described above.
According to the security monitoring method, the security monitoring equipment and the camera for security monitoring provided by the embodiment of the invention, the function of intelligent listening and alarming for the monitored area is realized by acquiring the audio information of the monitored area and analyzing the characteristic audio information in the audio information. Even if no person exists in the monitoring area or the monitoring area is not monitored manually, the alarm information can be sent to a client of the user to remind the user to take corresponding measures. Meanwhile, when the collected audio information is judged to contain the characteristic audio information, the collected video information and/or audio information in the preset time period is saved, and the user can conveniently check and backtrack the accident condition of the monitoring site.
Drawings
Fig. 1 is a schematic flow chart of a security monitoring method according to an embodiment of the present invention.
Fig. 2 is a schematic flowchart of a method for identifying characteristic audio information in a security monitoring method according to an embodiment of the present invention.
Fig. 3 is a schematic structural diagram of a security monitoring device according to an embodiment of the present invention.
Fig. 4 is a schematic structural diagram of a security monitoring device according to another embodiment of the present invention.
Fig. 5 is a schematic structural diagram of a security monitoring device according to another embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a security monitoring method according to an embodiment of the present invention. As shown in fig. 1, the security monitoring method includes:
step 101: and collecting video information and audio information in the monitoring scene. The video information in the monitoring scene can be collected through a video collecting device similar to a camera, and the audio information in the monitoring scene can be collected through an audio collecting device similar to a microphone.
Step 102: and judging whether the collected audio information contains characteristic audio information.
In an embodiment of the present invention, the characteristic audio information may be characteristic audio information in a preset alarm audio. The preset alarm tones may include alarm tones emitted by smoke alarms, alarm tones emitted by carbon monoxide alarms, and alarm tones emitted by other types of alarms that are commercially available. It should be noted that although the various types of commercially available alarms have different specification parameters due to different manufacturers, the various alarm tones emitted by the commercially available alarms are in accordance with the corresponding security standards, which determine the frequency characteristics and time domain waveform characteristics of the different alarm sounds. The frequency characteristics and the time domain waveform characteristics are the characteristic audio information in the alarm audio, and the alarm content corresponding to the alarm audio can be distinguished according to the characteristic audio information.
For example, in U.S. security standards UL217, UL2034, UL464 and UL1971, the alarm audio of the smoke alarm complies with the "Temporal 3" standard, i.e., the alarm audio of one time includes three consecutive rings, each ring lasts about 500ms, the interval between two adjacent rings is about 500ms, and the sound frequency is between 2900 and 3500 Hz. The interval between two adjacent alarm sounds is about 1.5 seconds. It is calculated that the period of the alarm sound under the "Temporal 3" standard is about 4 seconds.
The standard of the alarm audio frequency 'Temporal 4', namely, the primary alarm sound, of the carbon monoxide alarm comprises four continuous sounds, wherein each sound lasts for about 100ms and is separated for about 100ms, and the sound frequency is 2900-3500 Hz. The interval between two adjacent alarm tones is about 5 seconds. It is calculated that the period of the alarm sound under the "Temporal 4" standard is within about 6 seconds.
The step of determining may be combined with time domain analysis and frequency domain analysis. The time domain analysis method is to analyze the magnitude of the sound vibration quantity at different time points and the relation between the envelope of the vibration quantity and time. The frequency domain analysis method is to analyze how many sounds with different frequencies are contained in an original sound signal in a period of time. Their phase relationship, and the effects superimposed on each other, can be analyzed. The sound in a specific frequency range can be found from the audio information through frequency domain analysis, the vibration quantity of the sound in the specific frequency range in a time domain space is calculated (the vibration quantity reflects the intensity of the sound, the sound intensity is expressed by decibel (dB), and the maximum value of the vibration quantity in a section of frequency range is the amplitude), the sound waveforms of the specific frequency range are matched with the sound waveform of the characteristic audio, and if the vibration quantity is matched with the sound waveform of the characteristic audio, the collected audio information can be considered to contain the characteristic audio information.
In another embodiment of the present invention, the step of determining may further adopt a "template matching" method. Using time domain waveform diagrams of various characteristic audios (such as characteristic audio of preset alarm audio) as templates, and saving the variants of the templates in various situations. And comparing the collected audio information with the template sounds to obtain a plurality of similarity values, and selecting the highest similarity value as a judgment result. However, this method of judgment requires pre-learning and storing many templates.
Thus, compared with the above-mentioned "template matching" method, the combination of the time domain analysis method and the frequency domain analysis method can realize the real-time identification of the characteristic audio information without depending on any template. The determination step of the combination of the time domain analysis method and the frequency domain analysis method will be described in detail later by a specific embodiment.
In one embodiment of the present invention, the preset alarm audio may also be a pre-learned custom alarm audio, i.e., pre-learned characteristic audio information in the beep or custom alarm sound (e.g., HELP!) of a certain alarm for identification in the captured audio information. The pre-learning mechanism can be implemented by using an audio pre-learning algorithm in the prior art, which is not limited in the present invention.
Step 103: and when the characteristic audio information is judged to be contained, storing the video information and/or the audio information collected within a preset time period. The specific storage location may be a local memory or may be on a cloud server. The 'preset time period' can be a period of time before and after the characteristic audio information is identified, so that a user can check the actual condition of a monitoring site in a period of time before and after an accident happens from the stored video information and/or audio information, judge the cause of the accident and confirm the authenticity of the alarm.
In another embodiment of the present invention, in order to save energy consumption for video capture, it is configured to start capturing video information in a monitored scene only when characteristic audio information in the captured audio information is identified, and at this time, only video information and/or audio information within a preset time period after the characteristic audio information is identified may be saved. Therefore, the 'preset time period' can be adjusted according to actual requirements and setting conditions, and the length and the time of the 'preset time period' are not limited by the invention.
Step 104: and generating alarm information corresponding to the characteristic audio information, and sending the alarm information to a client of the user. The alarm information can be preset specific character information, the identified characteristic audio information is different, and the content of the generated alarm information is also different (for example, fire alarm or carbon monoxide leakage alarm).
In an embodiment of the present invention, the video information and/or the audio information collected in the preset time period may also be sent to the client of the user together with the alarm information, or the video information and/or the audio information collected in the monitoring scene may be transmitted to the client of the user in real time while the alarm information is sent to the client of the user. Therefore, when receiving the alarm information, the user can observe the field situation of the accident in the monitoring area in real time, and the user can take corresponding measures in time.
In an embodiment of the present invention, the alarm information may be generated while storing the video information and/or the audio information acquired within the preset time period on the cloud server, and the alarm information is also sent to the cloud server. At this moment, the cloud server can directly push the alarm information to the client of the user through the message push service. The specific function of the message pushing service can be provided by a provider of the cloud server, and the alarm information can be pushed to a client of a user by the cloud server as long as corresponding parameters are set and the condition of sending the message is met.
In another embodiment of the present invention, the association relationship between the device for acquiring the video information and/or the audio information in the monitoring scene and the user client may also be saved, and the specific saved location may be a local memory or a cloud server. At this time, the generated alarm information may include an identifier corresponding to the device for acquisition, and according to the identifier and the stored association relationship between the device and the user client, the alarm information may be directly sent to the user client corresponding to the device.
For example, when the client of the user is a portable mobile device similar to a mobile phone and the device for collecting is a monitoring camera, after the user purchases the monitoring camera, the user needs to install corresponding client software (APP) on the handheld mobile device and register an account in the client software by using the mobile phone number. And associating the account with the identification of the monitoring camera, and storing the association relationship on a cloud server. When an accident occurs in the monitoring area and an alarm sound occurs, the generated alarm information is sent to the cloud server, the cloud server searches for corresponding account information according to the unique identification of the monitoring camera contained in the alarm information, and then the alarm information is sent to the portable mobile equipment of the user by the push service. The number of the portable mobile devices of the user can be multiple, and the message can be pushed as long as the client software (APP) is installed and the corresponding account is logged in once.
Fig. 2 is a schematic flowchart of a method for identifying characteristic audio information in a security monitoring method according to an embodiment of the present invention. As shown in fig. 2, the method includes:
step 201: sampling the acquired audio information into time domain audio information, and dividing the time domain audio information into a plurality of time domain information segments according to time.
The initially acquired audio information is an analog signal (analog signal) in electronics, and in order to determine whether the audio information contains characteristic audio information, the audio information in the state of the analog signal may be sampled into a digital signal (digital signal), which is generally referred to as AD conversion.
AD conversion has two most basic criteria: sampling rate (SampleRate) and Resolution (Resolution). The sampling rate is the sampling speed of the original signal, is usually the sampling times within 1 second, and is expressed by KHz or MHz, and the more the sampling times are, the higher the sampling rate is, the more accurate the expression of the original signal is. The resolution is the minimum value of the original signal sample, the smaller the value of the resolution, the more accurate the expression of the original signal, and the commonly used resolution is 8bits, 16bits or 24 bits. The AD sampling can convert audio information in a section of analog signal state into time domain audio information in a group of digital signal state, then the time domain audio information is divided into a plurality of time domain information sections according to time, and the part of each time domain information section in a characteristic frequency range is extracted through subsequent frequency domain analysis so as to carry out matching analysis with the preset alarm audio.
Step 202: and respectively carrying out Fourier transform on the plurality of time domain information segments to obtain a plurality of frequency domain information segments. The ordered data in the time domain information segment represents the amount of sound vibration versus time, referred to as the time domain space of the signal. The ordered data in the time domain space is fourier transformed (usually using: Discrete Fourier Transform (DFT) or Fast Fourier Transform (FFT)) to obtain the frequency domain space of the ordered data, i.e. the corresponding frequency domain information segment is obtained. The frequency domain coordinate system represents the relationship between frequency and sound intensity.
Step 203: and intercepting the part of the frequency in the characteristic frequency range in each frequency domain information segment as a characteristic information segment. The characteristic frequency range is a frequency range corresponding to the preset alarm audio, and therefore the characteristic frequency range is intercepted to eliminate the influence of other noises except the preset alarm audio. For example, the sound frequency of the alarm audio frequency of the smoke alarm conforming to the aforementioned "Temporal 3" standard and the sound frequency of the alarm audio frequency of the carbon monoxide alarm conforming to the aforementioned "Temporal 4" standard are both 2900-3500 Hz, when the smoke alarm audio frequency and the carbon monoxide alarm audio frequency in the collected audio information are to be identified, the part of each frequency domain information segment with the frequency ranging from 2900-3500 Hz is intercepted as the characteristic information segment for subsequent frequency domain analysis. Of course, if the current frequency domain information segment does not have a part in the range of 2900 to 3500Hz, it is considered that the alarm audio to be identified does not exist in the current frequency domain information segment, and therefore, the characteristic information segment does not exist.
Step 204: judging whether the amplitude of each characteristic information segment meets a preset condition or not; if yes, recording the current characteristic information segment as an effective information segment; otherwise, the current characteristic information segment is marked as an invalid information segment.
The frequency of each characteristic information segment is within the characteristic frequency range, so that the alarm audio to be identified is contained in each characteristic information segment. In an embodiment of the present invention, when the amplitude of a characteristic information segment is higher than the first threshold, the characteristic information segment is considered to correspond to a pulse of the preset alarm audio and is marked as a valid information segment. When the amplitude of a characteristic information segment is lower than a first threshold value, the characteristic information segment is considered to correspond to a pulse interval of the preset alarm audio and is marked as an invalid information segment. Therefore, after each characteristic information segment is judged, a plurality of valid information segments and a plurality of invalid information segments can be obtained, and the valid information segments and the invalid information segments respectively correspond to a certain period of time.
In another embodiment of the invention, in order to further eliminate the noise effect in the characteristic frequency range, a more accurate identification of the characteristic audio information is achieved. In the characteristic frequency range, the vibration amount of at least one frequency point other than the frequency point to which the amplitude corresponds can also be calculated. If the ratio of the amplitude to the vibration quantity of all the at least one frequency point is higher than the second threshold value and/or the amplitude is higher than the first threshold value, the preset condition is considered to be met and the information is recorded as the effective information segment.
Step 205: and connecting the time domain waveforms corresponding to all the effective information segments and the ineffective information segments according to the time sequence to obtain the characteristic time domain waveform. Specifically, the obtained plurality of valid information segments and the plurality of invalid information segments are converted into a time-domain spatial form and then connected in time sequence, so that a characteristic time-domain waveform of the acquired audio information in a characteristic frequency range is obtained.
Step 206: judging whether the characteristic time domain waveform is matched with the waveform parameter of the characteristic audio information; and if the audio information is matched with the characteristic audio information, judging that the audio information contains the characteristic audio information.
As described above, the characteristic audio information may be characteristic audio information in the preset alarm audio. Since the preset alarm audio is usually in accordance with the corresponding standard or is pre-learned, the waveform parameters of the sound waveform thereof are also determined, including the width of the pulse (ms, millisecond) and the width of the pulse pause (ms, millisecond). Therefore, whether the collected sound contains the characteristic audio information of the preset alarm audio can be visually judged by comparing the characteristic time domain waveform with the waveform parameters of the sound waveform of the preset alarm audio.
In an embodiment of the present invention, in order to further avoid "false alarm", it is further required to examine other frequency points in each frequency domain information segment except the characteristic frequency range to determine whether a signal in the characteristic frequency range is actually noise. The specific method comprises the following steps: before intercepting the part of the frequency in the characteristic frequency range in each frequency domain information segment as a characteristic information segment, dividing each frequency domain information segment into a plurality of frequency bands according to the frequency; the plurality of frequency bands include frequency bands corresponding to characteristic frequency ranges. For example, for a frequency domain information segment with a frequency range of 35Hz to 5500Hz, the frequency domain information segment is divided into 22 frequency bands, wherein the frequency bands comprise characteristic frequency range segments of 2900 to 3500Hz corresponding to the standards of "Temporal 3" and "Temporal 4". Then, the average vibration quantity of each of the plurality of frequency bands is calculated, and the ratio of the average vibration quantity of the frequency band corresponding to the characteristic frequency range to the sum of the average vibration quantities of all other frequency bands is calculated. If the ratio is within the preset ratio range, it can be determined that the sound corresponding to the part of the current frequency domain information segment within the characteristic frequency range is actually noise, and it can be determined that the current frequency domain information segment does not contain the characteristic information segment, so that it is not necessary to intercept the part of the current frequency domain information segment within the characteristic frequency range as the characteristic information segment.
Those skilled in the art will understand that the above-mentioned "first threshold", "second threshold" and "preset ratio range" can be adjusted according to the actually collected sound signal and the kind of the preset alarm audio, and the present invention does not limit the specific values of the "first threshold", "second threshold" and "preset ratio range".
Fig. 3 is a schematic structural diagram of a security monitoring device according to an embodiment of the present invention. As shown in fig. 3, the security monitoring apparatus includes: a video acquisition device 31, an audio acquisition device 32, a processor 33, a storage device 34 and a transmission device 35; the video capture device 31, the audio capture device 32, the storage device 34, and the transmission device 35 are respectively connected to the processor 33.
The processor 33 comprises a receiving module 331, a judging module 332 and an alarming module 333 which are connected in sequence; the receiving module 331 receives video information and audio information in the monitored scene from the video collecting device 31 and the audio collecting device 32, respectively, and transmits the video information and the audio information to the judging module 332; when the judgment module 332 judges that the audio information contains the characteristic audio information, the judgment module sends the video information and the audio information collected within the preset time period to the storage device 34 for storage, and notifies the alarm module 333 to generate alarm information corresponding to the characteristic audio information; the alarm module 333 sends alarm information to the client of the user through the sending device 35.
In an embodiment of the present invention, the storage device 34 may be a local storage or a cloud server. When the storage device 34 is a cloud server, the cloud server supports a message push service. At this time, as shown in fig. 4, the alarm module 333 may send the alarm information to the storage device 34 (cloud server) through the sending device 35, and the storage device 34 directly pushes the alarm information to the client of the user through the message push service.
In an embodiment of the present invention, the video capture device 31 is a CCD type optical image sensor or a CMOS type optical image sensor. The video capture device 31 may further comprise a 360 ° rotary pan/tilt head, so that the video capture device 31 may be rotated about its own axis during use to view a wider area. Of course, the video capture device 31 may be fixed at a certain position without a pan/tilt head, and monitor a certain fixed monitoring area.
Those skilled in the art will appreciate that while the above embodiments describe several modules of a security monitoring device, such partitioning is not mandatory. Indeed, the features and functionality of two or more of the modules described above may be embodied in one module according to embodiments of the invention. Conversely, the features and functions of one module described above may be further divided into embodiments by a plurality of modules. Those skilled in the art will appreciate that the solution of the present invention can be implemented in software, and in particular in the form of a computer program. For example, executable code may be stored in a memory such as RAM, ROM, hard disk, and/or any suitable storage medium, which when executed, may implement the functionality of the present invention as mentioned in the above embodiments.
It should be noted that embodiments of the present invention can also be realized in hardware or a combination of software and hardware. The hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the apparatus and methods described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided on a carrier medium such as a disk, CD-or DVD-ROM, programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier, for example. The apparatus and modules thereof of the present invention may be implemented by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., or by software executed by various types of processors, or by a combination of hardware circuits and software, such as firmware. For example, when the security monitoring apparatus provided in the embodiment of the present invention is implemented by hardware, the processor 33 may be a large-scale integrated circuit board, the receiving module 331 may be any commercially available sound processing device that performs sound signal sampling, the determining module 332 may be a signal processing device (e.g., a filter) that performs frequency determination or waveform processing on the processed sound signal, the alarm module 333 may be a relay device that generates an electronic signal representing alarm information, and the sending device 35 may be a commercially available network card device supporting wired network connection and/or wireless network connection.
Fig. 5 is a schematic structural diagram of a security monitoring device according to another embodiment of the present invention. Unlike the security monitoring device shown in fig. 3, the video information and the audio information collected within the preset time period are not stored in the local memory 41 of the security monitoring device shown in fig. 5, but are uploaded to the cloud server by the sending device 35 for storage. The program storage module 411 in the local storage 41 stores the code that needs to be executed by the processor 33, and the memory module 412 in the local storage 41 provides the hardware environment required for the program to run. The ac-dc conversion power supply 42 (independent device) is used for supplying power to the whole security monitoring device. In addition, the security monitoring device shown in fig. 4 further includes:
and the display device 43 is connected with the processor 33 and is used for displaying the current working state of the security monitoring equipment.
An infrared illumination device 44 is connected to the processor 33 for improving the video capture quality under night vision conditions.
A speaker device 45 connected to the processor 33 for generating an alarm sound while the characteristic audio information is recognized.
And the equipment rotating device 46 is connected with the processor 33 and is used for enabling the whole security monitoring equipment to rotate in place, so that the camera can see a wider range around.
An external interface device 47, such as a wired interface device, connected to the processor 33 is used to connect a wired network to the internet to complete data uploading when the transmitting device 35 supporting wireless transmission fails.
It will be understood by those skilled in the art that one or more of the display device 43, the infrared illumination device 44, the speaker device 45, the device rotation device 46 and the wired interface device 41 may be selectively added according to actual needs, or none of them may be added. The invention is not limited in this regard. Moreover, it should be further understood that the description only describes some key and not necessarily essential techniques and features, and may not describe features that may be implemented by those skilled in the art, in order not to obscure the embodiments of the invention.
An embodiment of the invention further provides camera equipment, and the structure of the security monitoring equipment is integrated in the camera equipment, so that the camera equipment has a function of listening and alarming.
According to the security monitoring method, the security monitoring equipment and the security monitoring camera provided by the embodiment of the invention, the function of intelligent listening and alarming for the monitored area is realized by acquiring the audio information of the monitored area and analyzing the characteristic audio information in the audio information. Even if no person exists in the monitoring area or the monitoring area is not monitored manually, the alarm information can be sent to a client of the user to remind the user to take corresponding measures. Meanwhile, when the collected audio information is judged to contain the characteristic audio information, the collected video information and/or audio information in the preset time period is saved, and the user can conveniently check and backtrack the accident condition of the monitoring site.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and the like that are within the spirit and principle of the present invention are included in the present invention.
Claims (12)
1. A security monitoring method is characterized by comprising the following steps:
collecting video information and audio information in a monitoring scene;
judging whether the collected audio information contains characteristic audio information or not;
when the characteristic audio information is judged to be contained, video information and/or audio information collected within a preset time period are/is saved; and
and generating alarm information corresponding to the characteristic audio information, and sending the alarm information to a client of a user.
2. The method of claim 1, wherein when it is determined that the characteristic audio information is included, the saving the video information and/or the audio information collected within a preset time period comprises:
when the characteristic audio information is identified, video information and/or audio information collected within a period of time before and after the characteristic audio information is identified is stored; or
And when the characteristic audio information is identified, starting to acquire video information in a monitoring scene, and storing the video information and/or audio information in a preset time period after the characteristic audio information is identified.
3. The method of claim 1, wherein saving the video information and/or audio information collected during the predetermined period of time comprises:
storing the video information and/or the audio information collected in the preset time period in a local memory; and/or
And storing the video information and/or the audio information collected in the preset time period on a cloud server.
4. The method according to claim 3, wherein when video information and/or audio information collected within the preset time period is saved on a cloud server, the generating and sending alarm information corresponding to the characteristic audio information to a client of a user comprises:
meanwhile, generating alarm information corresponding to the characteristic audio information, and sending the alarm information to the cloud server;
and the cloud server pushes the alarm information to a client of a user through a message pushing service.
5. The method of claim 1, wherein determining whether the collected audio information includes characteristic audio information comprises:
sampling the collected audio information into time domain audio information, and dividing the time domain audio information into a plurality of time domain information segments according to time;
respectively carrying out Fourier transform on the plurality of time domain information segments to obtain a plurality of frequency domain information segments;
intercepting the part of the frequency in the characteristic frequency range in each frequency domain information segment as a characteristic information segment;
judging whether the amplitude of each characteristic information segment meets a preset condition or not; if yes, recording the current characteristic information segment as an effective information segment; otherwise, recording the current characteristic information segment as an invalid information segment;
connecting time domain waveforms corresponding to all the effective information segments and the ineffective information segments according to the time sequence to obtain characteristic time domain waveforms; and
judging whether the characteristic time domain waveform is matched with the waveform parameter of the characteristic audio information; and if the audio information is matched with the characteristic audio information, judging that the audio information contains the characteristic audio information.
6. The method of claim 5, wherein determining whether the amplitude of each of the characteristic information segments satisfies a predetermined condition comprises:
and if the amplitude of the characteristic information segment is higher than a first threshold value, the preset condition is met.
7. The method of claim 5, wherein determining whether the amplitude of each of the characteristic information segments satisfies a predetermined condition comprises:
calculating the vibration quantity of at least one frequency point except the frequency point corresponding to the amplitude; and if the ratio of the amplitude to the vibration quantity of the at least one frequency point is higher than a second threshold value, determining that a preset condition is met.
8. The method of claim 5, wherein before truncating the portion of each of the frequency domain information segments having frequencies within the characteristic frequency range as a characteristic information segment, the method further comprises:
dividing each frequency domain information segment into a plurality of frequency bands according to frequency; wherein the plurality of frequency bands comprise frequency bands corresponding to characteristic frequency ranges;
calculating the average vibration quantity of each of the plurality of frequency bands;
calculating the ratio of the average vibration quantity of the frequency band corresponding to the characteristic frequency range to the sum of the average vibration quantities of all other frequency bands;
if the ratio is within a preset ratio range, it is determined that the current frequency domain information segment does not contain the characteristic information segment, and therefore, the part of the frequency within the characteristic frequency range in the current frequency domain information segment is not intercepted as the characteristic information segment.
9. The method according to claim 1, wherein the characteristic audio information is characteristic audio information in preset alarm audio; the preset alarm audio comprises an alarm audio sent by a smoke alarm, an alarm audio sent by a carbon monoxide alarm and a pre-learned custom alarm audio.
10. A security monitoring device, comprising: the device comprises a video acquisition device, an audio acquisition device, a processor, a storage device and a sending device; the video acquisition device, the audio acquisition device, the storage device and the sending device are respectively connected with the processor; wherein,
the processor comprises a receiving module, a judging module and an alarming module which are connected in sequence; the receiving module receives video information and audio information in a monitoring scene from the video acquisition device and the audio acquisition device respectively and transmits the video information and the audio information to the judging module; when the judgment module judges that the audio information contains the characteristic audio information, the judgment module sends the video information and the audio information collected in a preset time period to the storage device for storage, and informs the alarm module to generate alarm information corresponding to the characteristic audio information; and the alarm module sends the alarm information to a client of a user through the sending device.
11. The security monitoring device of claim 10, wherein the storage device is a local memory or a cloud server.
12. A camera comprising the security monitoring device of claim 10 or 11.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510639758.4A CN105100758B (en) | 2015-09-30 | 2015-09-30 | Method, equipment and camera for safety monitoring |
| US14/927,140 US20170092089A1 (en) | 2015-09-30 | 2015-10-29 | Security monitoring apparatus, camera having the same and security monitoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510639758.4A CN105100758B (en) | 2015-09-30 | 2015-09-30 | Method, equipment and camera for safety monitoring |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105100758A true CN105100758A (en) | 2015-11-25 |
| CN105100758B CN105100758B (en) | 2018-05-08 |
Family
ID=54580177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510639758.4A Active CN105100758B (en) | 2015-09-30 | 2015-09-30 | Method, equipment and camera for safety monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105100758B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107018372A (en) * | 2017-04-20 | 2017-08-04 | 深圳声联网科技有限公司 | Voice recognition monitoring record method and device |
| CN107274621A (en) * | 2017-08-02 | 2017-10-20 | 中消云（北京）物联网科技研究院有限公司 | For the video interactive system and method in fire-fighting monitoring management |
| CN107320892A (en) * | 2017-08-24 | 2017-11-07 | 中国空间技术研究院 | A kind of the Control System of Fire Pump |
| CN107426536A (en) * | 2017-05-26 | 2017-12-01 | 黄晓咏 | A kind of intelligent residential district manages communication system |
| CN107481470A (en) * | 2017-06-30 | 2017-12-15 | 何东波 | A kind of remote monitoring and automatic alarm method and device |
| CN108012123A (en) * | 2017-12-22 | 2018-05-08 | 蒙城县望槐信息科技有限责任公司 | A kind of video capture method based on sound source position |
| CN108012086A (en) * | 2017-12-22 | 2018-05-08 | 蒙城县望槐信息科技有限责任公司 | A kind of camera control system based on Internet of Things |
| CN108076316A (en) * | 2016-11-18 | 2018-05-25 | 杭州海康威视数字技术股份有限公司 | A kind of method, apparatus and system for identifying repacking vehicle |
| CN109697989A (en) * | 2018-12-26 | 2019-04-30 | 深圳创维数字技术有限公司 | Audio data processing method, server and readable storage medium storing program for executing |
| CN111301344A (en) * | 2018-12-11 | 2020-06-19 | 通用汽车环球科技运作有限责任公司 | Customized vehicle alerts based on electronic device identifiers |
| CN111770309A (en) * | 2020-06-24 | 2020-10-13 | 浙江大华技术股份有限公司 | Video uploading method and device, electronic equipment and storage medium |
| CN111866454A (en) * | 2020-07-02 | 2020-10-30 | 广州博冠智能科技有限公司 | Sound and image linkage detection early warning method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1149348A (en) * | 1994-03-04 | 1997-05-07 | 索尼克系统公司 | Siren detector |
| WO1997031437A1 (en) * | 1996-02-20 | 1997-08-28 | Sonic Systems | Digital sonic and ultrasonic communications networks |
| CN201051309Y (en) * | 2007-04-23 | 2008-04-23 | 凌子龙 | Car traffic violation whistling electronic police system |
| CN103674235A (en) * | 2014-01-03 | 2014-03-26 | 哈尔滨工业大学 | Single frequency alarm sound feature detection method on basis of STFT (Short-Time Fourier Transform) |
-
2015
- 2015-09-30 CN CN201510639758.4A patent/CN105100758B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1149348A (en) * | 1994-03-04 | 1997-05-07 | 索尼克系统公司 | Siren detector |
| WO1997031437A1 (en) * | 1996-02-20 | 1997-08-28 | Sonic Systems | Digital sonic and ultrasonic communications networks |
| CN201051309Y (en) * | 2007-04-23 | 2008-04-23 | 凌子龙 | Car traffic violation whistling electronic police system |
| CN103674235A (en) * | 2014-01-03 | 2014-03-26 | 哈尔滨工业大学 | Single frequency alarm sound feature detection method on basis of STFT (Short-Time Fourier Transform) |
Non-Patent Citations (1)
| Title |
|---|
| 张璐璐: "视频监控终端系统声音检测及告警功能软件设计", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108076316A (en) * | 2016-11-18 | 2018-05-25 | 杭州海康威视数字技术股份有限公司 | A kind of method, apparatus and system for identifying repacking vehicle |
| CN107018372A (en) * | 2017-04-20 | 2017-08-04 | 深圳声联网科技有限公司 | Voice recognition monitoring record method and device |
| CN107426536A (en) * | 2017-05-26 | 2017-12-01 | 黄晓咏 | A kind of intelligent residential district manages communication system |
| CN107481470A (en) * | 2017-06-30 | 2017-12-15 | 何东波 | A kind of remote monitoring and automatic alarm method and device |
| CN107274621A (en) * | 2017-08-02 | 2017-10-20 | 中消云（北京）物联网科技研究院有限公司 | For the video interactive system and method in fire-fighting monitoring management |
| CN107320892A (en) * | 2017-08-24 | 2017-11-07 | 中国空间技术研究院 | A kind of the Control System of Fire Pump |
| CN108012086A (en) * | 2017-12-22 | 2018-05-08 | 蒙城县望槐信息科技有限责任公司 | A kind of camera control system based on Internet of Things |
| CN108012123A (en) * | 2017-12-22 | 2018-05-08 | 蒙城县望槐信息科技有限责任公司 | A kind of video capture method based on sound source position |
| CN111301344A (en) * | 2018-12-11 | 2020-06-19 | 通用汽车环球科技运作有限责任公司 | Customized vehicle alerts based on electronic device identifiers |
| CN111301344B (en) * | 2018-12-11 | 2022-07-12 | 通用汽车环球科技运作有限责任公司 | Customized vehicle alerts based on electronic device identifiers |
| CN109697989A (en) * | 2018-12-26 | 2019-04-30 | 深圳创维数字技术有限公司 | Audio data processing method, server and readable storage medium storing program for executing |
| CN109697989B (en) * | 2018-12-26 | 2021-03-16 | 深圳创维数字技术有限公司 | Audio data processing method, server and readable storage medium |
| CN111770309A (en) * | 2020-06-24 | 2020-10-13 | 浙江大华技术股份有限公司 | Video uploading method and device, electronic equipment and storage medium |
| CN111866454A (en) * | 2020-07-02 | 2020-10-30 | 广州博冠智能科技有限公司 | Sound and image linkage detection early warning method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105100758B (en) | 2018-05-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105100758B (en) | Method, equipment and camera for safety monitoring | |
| US11276299B2 (en) | DIT monitoring apparatus and method | |
| US20220028237A1 (en) | Digital fingerprint tracking | |
| KR102034559B1 (en) | Appartus and method for monitoring security using variation of correlation coefficient pattern in sound field spectra | |
| US20170092089A1 (en) | Security monitoring apparatus, camera having the same and security monitoring method | |
| US20190246071A1 (en) | Building Monitoring System | |
| US10969506B1 (en) | System and methods for detecting gunshots | |
| CN204968034U (en) | A equipment and camera for security protection control | |
| US20140036056A1 (en) | Monitoring system and monitoring method thereof | |
| KR102048021B1 (en) | Method for monitoring adaptive sound field security of environmental noise | |
| CN207882987U (en) | inspection device | |
| JP2016171477A (en) | Remote operation support device, monitoring system, and remote operation support method | |
| CN220729581U (en) | Portable pressure pipeline leakage detection device | |
| CN112435423B (en) | Monitoring method and device | |
| CN211015806U (en) | Intrusion monitoring system | |
| CN114363580A (en) | Video monitoring method, device and equipment | |
| TW201933337A (en) | Wearable electronic device and noise eliminating method | |
| CN109194412A (en) | A kind of acoustic emission monitor(ing) warning device, system and method | |
| JP2017004180A (en) | Notification system, notification device, notification method, and notification program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Room 205, 3 Jinping Road, Ya'an Road, Nankai District, Tianjin (Science Park) Patentee after: Tianjin Hualai Technology Co.,Ltd. Address before: Room 205, 3 Jinping Road, Ya'an Road, Nankai District, Tianjin (Science Park) Patentee before: TIANJIN HUALAI TECHNOLOGY Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |