CN110532888A - A kind of monitoring method, apparatus and system - Google Patents
A kind of monitoring method, apparatus and system Download PDFInfo
- Publication number
- CN110532888A CN110532888A CN201910708296.5A CN201910708296A CN110532888A CN 110532888 A CN110532888 A CN 110532888A CN 201910708296 A CN201910708296 A CN 201910708296A CN 110532888 A CN110532888 A CN 110532888A
- Authority
- CN
- China
- Prior art keywords
- information
- monitored
- feature information
- area
- target
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a kind of monitoring methods, apparatus and system, it is related to security monitoring field, it can be analyzed and be judged to the biological behavior state occurred in area to be monitored automatically, relative to existing monitor mode, do not need have Security Personnel on duty always, the workload of Security Personnel is greatly reduced, and reduces and the careless omission occurred is analyzed and judged using behavior state of the manual type to the biology occurred in area to be monitored, improves monitoring efficiency.This method comprises: obtaining the biometric image information and biological sound information of area to be monitored;Judged in area to be monitored according to biometric image information and/or biological sound information with the presence or absence of target organism;If it is determined that there are target organisms in area to be monitored, prompt information is exported.The present invention is used for safety precaution.
Description
Technical field
The present invention relates to security monitoring field more particularly to a kind of monitoring methods, apparatus and system.
Background technique
Monitoring system is the important component of safety and protection system.In the prior art, currently used monitoring system
Predominantly video monitoring system is monitored and is remembered to the event of area to be monitored by the way of video record.When to
When monitoring area is abnormal event, administrative department can obtain valid data by it, timely to be located to anomalous event
Reason and reply, in particular for unexpected incidents.
When needing to be monitored the biology (human or animal) occurred in area to be monitored, such as when needs are monitored wait supervise
When whether in the hole the biology occurred in control region is or whether itself has risk, Security Personnel is usually relied on
The video record of area to be monitored is checked, then the behavior state of the biology occurred in area to be monitored is analyzed
Judgement, then obtains a result.This monitor mode needs to have Security Personnel on duty always, considerably increases the work of Security Personnel
It measures, and the analytical judgment for being difficult to protect positive Security Personnel is not slipped, that is to say, that this monitor mode not only monitoring efficiency
It is relatively low, and the accuracy judged to non-safety information is not also high.
Summary of the invention
The embodiment of the present invention provides a kind of monitoring method, apparatus and system, can go out automatically in area to be monitored
The behavior state of existing biology is analyzed and determined, relative to existing monitor mode, improves monitoring efficiency, and is improved pair
The accuracy that non-safety information is judged.
In order to achieve the above objectives, the embodiment of the present invention adopts the following technical scheme that
In a first aspect, the embodiment of the present invention provides a kind of monitoring method, comprising: obtain the biometric image letter of area to be monitored
Breath and biological sound information;Judged in area to be monitored according to biometric image information and/or biological sound information with the presence or absence of mesh
Mark biology;If it is determined that there are target organisms in area to be monitored, prompt information is exported.
Optionally, judged in area to be monitored according to biometric image information with the presence or absence of target organism, comprising: extract biology
Fisrt feature information in image information;Extract the second feature information in all target organism image informations in database;
Judge whether fisrt feature information matches with target second feature information;Target second feature information is all target organism images
The corresponding second feature information of any of information;If it is determined that fisrt feature information and target second feature information matches, then really
Determine in area to be monitored that there are target organisms.
Optionally, judged in area to be monitored according to biological sound information with the presence or absence of target organism, comprising: extract biology
Acoustic feature information in acoustic information;Judge the acoustic feature letter of the target organism stored in acoustic feature information and date library
Whether breath matches;If it is determined that the acoustic feature information matches of acoustic feature information and target organism, it is determined that in area to be monitored
There are target organisms.
Optionally, judged in area to be monitored according to biological sound information with the presence or absence of target organism, comprising: extract biology
Semantic feature information in acoustic information;Semantic feature information is converted to the text information of reflection semantic feature, and to text
Information carries out word segmentation processing;Whether judgement matches by the text information after word segmentation processing with the semantic sample prestored, if really
Surely by the text information after word segmentation processing and the semantic sample matches prestored, it is determined that it is raw that there are targets in area to be monitored
Object.
Optionally, monitoring method provided in an embodiment of the present invention determining in area to be monitored there are after target organism,
Further include: the location information of target organism is obtained, and location information is sent to monitor terminal.
Second aspect, the embodiment of the present invention also provide a kind of monitoring device, comprising: acquiring unit, it is to be monitored for obtaining
The biometric image information and biological sound information in region;Processing unit, the biometric image information for being obtained according to acquiring unit
And/or the biological sound information that acquiring unit obtains judges in area to be monitored with the presence or absence of target organism;Output unit is used for
It determines in area to be monitored in processing unit there are when target organism, exports prompt information.
Optionally, processing unit is specifically used for: extracting the fisrt feature letter in the biometric image information that acquiring unit obtains
Breath;Extract the second feature information in all target organism image informations stored in database;Judge fisrt feature information with
Whether target second feature information matches;Target second feature information is that any of all target organism image informations are corresponding
Second feature information;If it is determined that fisrt feature information and target second feature information matches, it is determined that exist in area to be monitored
Target organism.
Optionally, processing unit is specifically used for: extracting the acoustic feature letter in the biological sound information that acquiring unit obtains
Breath;Judge whether the acoustic feature information of the target organism stored in acoustic feature information and date library matches;If it is determined that acoustics
The acoustic feature information matches of characteristic information and target organism, it is determined that there are target organisms in area to be monitored.
Optionally, processing unit is specifically used for: extracting the semantic feature information in biological sound information;Semantic feature is believed
Breath is converted to the text information of reflection semantic feature, and carries out word segmentation processing to text information;Judgement is by after word segmentation processing
Text information whether matched with the semantic sample prestored, however, it is determined that text information after word segmentation processing and the language prestored
Adopted sample matches, it is determined that there are target organisms in area to be monitored.
Optionally, acquiring unit is also used to determine in area to be monitored in processing unit there are after target organism, obtains
The location information of target organism;Monitoring device provided in an embodiment of the present invention further includes transmission unit, for sending out location information
It send to monitor terminal.
The third aspect, the embodiment of the present invention also provide another monitoring device, including memory, processor, bus and logical
Believe interface;For storing computer executed instructions, processor is connect with memory by bus memory;When monitoring device is run
When, processor executes the computer executed instructions of memory storage, so that monitoring device executes the monitoring method such as first aspect.
Fourth aspect, the embodiment of the present invention also provide a kind of monitoring system, the monitoring device including such as second aspect.
Monitoring method provided in an embodiment of the present invention, apparatus and system, firstly, obtaining the biometric image letter of area to be monitored
Then breath and biological sound information judge whether deposit in area to be monitored according to biometric image information and/or biological sound information
In target organism, however, it is determined that there are target organisms in area to be monitored, export prompt information.In this way, the embodiment of the present invention provides
Technical solution, automatically to area to be monitored in such a way that Video Supervision Technique and image, voice recognition technology are combined
The behavior of the biology of interior appearance is analyzed and is judged, relative to existing monitor mode, does not need have Security Personnel artificial always
Analysis and judgement, greatly reduce the workload of Security Personnel, improve monitoring efficiency;Further, because not using artificial
Analysis also just reduces and is analyzed and judged using behavior state of the manual type to the biology occurred in area to be monitored
Existing careless omission, therefore, technical solution provided in an embodiment of the present invention can also be improved compared with the existing technology to dangerous letter
Cease the accuracy of judgement.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, required use in being described below to embodiment
Attached drawing be briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this
For the those of ordinary skill of field, without creative efforts, it can also be obtained according to these attached drawings others
Attached drawing.
Fig. 1 is a kind of flow diagram of monitoring method provided in an embodiment of the present invention;
Fig. 2 is the flow diagram of another monitoring method provided in an embodiment of the present invention;
Fig. 3 is a kind of structural schematic diagram of monitoring device provided in an embodiment of the present invention;
Fig. 4 is the structural schematic diagram of another monitoring device provided in an embodiment of the present invention;
Fig. 5 is the structural schematic diagram of another monitoring device provided in an embodiment of the present invention;
Fig. 6 is a kind of structural schematic diagram of monitoring system provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Using existing monitor mode, when being monitored to the biology (human or animal) occurred in area to be monitored, such as
It is whether in the hole or when whether itself has risk when needing to monitor the biology that occurs in area to be monitored, usually
It is to be checked by Security Personnel to the video record of area to be monitored, then to the row of the biology occurred in area to be monitored
It is analyzed and determined for state, is then obtained a result.This monitor mode is needed to have Security Personnel on duty always, be greatly increased
The workload of Security Personnel, and the analytical judgment for being difficult to protect positive Security Personnel do not slip, that is to say, that this monitoring side
Not only monitoring efficiency is relatively low for formula, but also the accuracy judged to non-safety information is not also high.
To solve the above problems, in a first aspect, as shown in Figure 1, the embodiment of the present invention provides a kind of monitoring method, including step
Rapid S100~S300:
S100, the biometric image information and biological sound information for obtaining area to be monitored.
Illustratively, in some embodiments, user can install photographic device and sound pick up equipment in area to be monitored,
The photographic device can be camera, which can be pick-up head, be covered using multiple cameras and pick-up head wait supervise
Region is controlled, biometric image information and biological sound information are acquired by camera and pick-up head.Biometric image information includes biology
Picture and/or biology video.It can be taken pictures by camera to the biology in area to be monitored and obtain picture or right
Biology video recording in area to be monitored obtains video.Wherein, it takes pictures between can be the time pre-set according to monitoring user
Picture is obtained every periodically taking pictures, and newest image in area to be monitored can then be obtained in real time by recording a video.Biological sound
Message breath, which can be, periodically records according to the time interval that monitoring user pre-sets to obtain, and is also possible in real time
Obtain the acoustic information of the biology occurred in area to be monitored.
S200, judged in area to be monitored according to biometric image information and/or biological sound information with the presence or absence of target life
Object.
Illustratively, in some embodiments, target organism includes biohazardous and biology in the hole.Herein
It is understood that biohazardous refers to aggressive biology, for example, the dog in manic phase, no wear are drawn
The pet (dog) of rope carries the people, police wanted circular personnel etc. of dangerous material (such as cutter);Biology in the hole refers to it
Itself is in dangerous situation, for example, the children in lost state, the people to fall in a swoon, injured people etc..
S300, if it is determined that there are target organism in area to be monitored, export prompt information.
Monitoring method provided in an embodiment of the present invention, firstly, obtaining the biometric image information and biology sound of area to be monitored
Then message breath judges raw with the presence or absence of target in area to be monitored according to biometric image information and/or biological sound information
Object, however, it is determined that there are target organisms in area to be monitored, export prompt information.In this way, technical side provided in an embodiment of the present invention
Case, automatically to occurring in area to be monitored by the way of combine Video Supervision Technique and image, voice recognition technology
The behavior of biology is analyzed and is judged, relative to existing monitor mode, does not need to have Security Personnel's manual analysis always and sentence
It is disconnected, the workload of Security Personnel is greatly reduced, monitoring efficiency is improved;Further, because not using manual analysis, also
Reduce and the careless omission occurred analyzed and judged using behavior state of the manual type to the biology occurred in area to be monitored,
Therefore, technical solution provided in an embodiment of the present invention can also be improved compared with the existing technology to non-safety information judgement
Accuracy.
Optionally, as shown in Fig. 2, in some embodiments of the invention, step S200 specifically include step S211~
S213:
Fisrt feature information in S211, extraction biometric image information.
Specifically, fisrt feature information can be a variety of different information of biology, for example, in the present embodiment, first
Characteristic information can include but is not limited to the characteristic information for the biology being set forth below:
The face feature information of personage and physical characteristic information, personage carry the characteristic information of cutter, and animal is not matched
Wear the characteristic information of traction rope.
The second feature information in all target organism image informations in S212, extraction database.
S213, judge whether fisrt feature information matches with target second feature information.
Wherein, target second feature information is the corresponding second feature letter of any of all target organism image informations
Breath;
If it is determined that fisrt feature information and target second feature information matches, then can determine that there are mesh in area to be monitored
Mark biology, executes step S300;If it is determined that fisrt feature information and target second feature information mismatch, then can determine wait supervise
It controls and target organism is not present in region, execute step S100.
Illustratively, in some embodiments, it can be carried out by biometric image information of the image recognition algorithm to acquisition
Identification, is analyzed by image analysis algorithm and extracts fisrt feature information biological in biometric image information, such as the face of people
Whether profile and height, pet wear traction rope etc., and are analyzed and extracted in database by image analysis algorithm and deposited in advance
The second feature information of the target organism of storage, such as the face contour and height of offender, pet do not wear traction rope etc.;
Then fisrt feature information is matched with target second feature information by matching algorithm.For example, can be by fisrt feature
Information is successively matched with each target second feature information, until having found can believe with fisrt feature in the database
The matched target second feature information of manner of breathing, then it is assumed that successful match;If not found in database and fisrt feature information phase
Matched target second feature information, then it is assumed that matching is unsuccessful.
Above-mentioned matching algorithm can be the calculation of specially AI (artificial intelligence, artificial intelligence) technology
Method is also possible to other programmed algorithms, as long as can be realized the comparative analysis of image, is not especially limited herein to it.
In order to better illustrate the monitoring method of this law embodiment offer, a concrete application scene is provided below.
Certain amusement of children garden provides not allow access into without the pet for wearing traction rope.If the amusement of children garden uses
When monitoring method provided in an embodiment of the present invention is monitored the amusement of children garden, the biology of the amusement of children garden is obtained
Image information extracts the fisrt feature information of the biometric image information.Pre-stored target organism image information in database
In include the image information for not wearing the pet of traction rope, extract the in all target organism image informations in database
Two characteristic informations, then second feature information includes that pet does not wear this characteristic information of traction rope.It will be appointed by matching algorithm
One fisrt feature information is matched with any second feature information, if matching, can determine the amusement of children garden memory
In target organism, i.e., without the pet for wearing traction rope, then export prompt information;If mismatching, the children can be determined
Travelling in garden, there is no target organisms, i.e., there is no the pets without wearing traction rope.In this way, provided in an embodiment of the present invention
Monitoring method, even if can also find occur not having in the garden in the case where monitoring on duty without Security Personnel
The pet of traction rope is worn, prompt information is issued, so that the Security Personnel of the garden is handled in time, for example, reminding the pet
Owner is that its pet wears traction rope.
Optionally, as shown in Fig. 2, in some embodiments of the invention, step S200 specifically include step S221~
S222:
Acoustic feature information in S221, extraction biological sound information.
Illustratively, in some embodiments, it for collecting the biological sound information of area to be monitored, can first carry out
Pretreatment, specifically include: acoustic signals be converted into digital signal, can to digital signal carry out end-point detection, speech enhan-cement,
Anti-aliasing filter and removal glottal excitation etc..After carrying out above-mentioned processing to biological sound information, extract in biological sound information
Acoustic feature information, specifically, acoustic feature information can include but is not limited to voiceprint.
S222, judge whether the acoustic feature information of the target organism stored in acoustic feature information and date library matches.
If it is determined that the acoustic feature information matches of acoustic feature information and target organism, then can determine in area to be monitored
There are target organisms, execute step S300;If it is determined that acoustic feature information and the acoustic feature information of target organism mismatch, then
It can determine that there is no target organisms in area to be monitored, execute step S100.
Illustratively, in some embodiments, the acoustic feature information of the target organism stored in database can be mesh
The phonetic reference template of biology is marked, such as the police order to arrest the phonetic reference template of personnel, the specially vocal print of police's wanted circular personnel
Reference template.
In order to better illustrate the monitoring method of this law embodiment offer, a concrete application scene is provided below.
When being monitored using monitoring method provided in an embodiment of the present invention to certain cell, the biological sound of the cell is obtained
Message breath, extracts the vocal print feature information in the biological sound information.It is previously stored with the police in database and orders to arrest personnel A's
Vocal print reference template.Extract the A's stored in obtained any vocal print feature information and date library by matching algorithm judgement
Whether vocal print reference template matches, if matching, it is determined that the cell memory target organism, i.e. A;If mismatching, do not know
Be not present target organism in the cell, i.e. A, in this way, monitoring method provided in an embodiment of the present invention, even if can not pacify
It in the case where guarantor person's monitoring on duty, can also find that A is appeared in the cell, prompt information be issued, so that the peace of the cell
Guarantor person is handled in time, for example, alarm.
Optionally, as shown in Fig. 2, in some embodiments of the invention, step S200 specifically include step S231~
S233:
Semantic feature information in S231, extraction biological sound information;
S232, the text information that semantic feature information is converted to reflection semantic feature, and text information is segmented
Processing;
Whether S233, judgement match by the text information after word segmentation processing with the semantic sample prestored.
If it is determined that the text information after word segmentation processing and the semantic sample matches prestored, then can determine to be monitored
There are target organisms in region, execute step S300;If it is determined that text information after word segmentation processing and the semanteme prestored
Sample mismatches, then can determine that there is no target organisms in area to be monitored, execute step S100.
Illustratively, in some embodiments, the semantic feature information in biological sound information is extracted, semantic feature is believed
Breath is converted to the text information of reflection semantic feature, and carries out word segmentation processing to text information, obtains keyword message, and prestores
Semantic sample matched, wherein the semantic sample prestored includes some specific keywords, for example, the keys such as " help "
Word.
In order to better illustrate the monitoring method of this law embodiment offer, a concrete application scene is provided below.
When use monitoring method provided in an embodiment of the present invention (has many trees, many place shootings to botanical garden in garden
Less than video) it is monitored.The biological sound information for obtaining the botanical garden extracts the semantic feature letter in the biological sound information
The semantic feature information is converted to the text information of reflection semantic feature, and carries out word segmentation processing to text information by breath.Number
It include " help " this kind of specific keywords in the semanteme sample according to semantic sample is prestored in library.Word segmentation processing will be passed through
Text information later is matched with the semantic sample prestored.If matching, can determine has tourist to need in the botanical garden
It succours, then exports prompt information.In this way, monitoring method provided in an embodiment of the present invention, even if can there is no security people
In the case where member's monitoring on duty, it can also find there is tourist to need to succour in the botanical garden, so that the Security Personnel in the botanical garden
Tourist B is succoured in time.
Further, refering to what is shown in Fig. 2, monitoring method provided in an embodiment of the present invention, is determining area to be monitored memory
After target organism, further includes:
Step S400, the location information of target organism is obtained, and location information is sent to monitor terminal.
Illustratively, the location information of target organism can be obtained directly from biometric image information, can also will acquire
The biometric image information of area to be monitored and the device number of biological sound information, and the device of each number is corresponded into monitoring
When the location information for needing to obtain target organism in the database is stored in advance in region, directly obtained from database.
Specifically, prompt information includes at least any one of acoustical signal, optical signal, electric signal or multinomial;It is also possible to
The other modes such as vibration, are not particularly limited herein.
For example, prompt information can link, indicator light and alarm (are also possible to functions of indicator light and alarm function
The combined aural and visual alarm of energy) issue signal.Indicator light can be by the difference of indicated color come to the life in area to be monitored
The situation of object is indicated.In the present embodiment, when occurring without target organism, the color of indicator light is in area to be monitored
Green, when having target organism to occur in area to be monitored, the color of indicator light is red, while interlink warning device issues alarm
Sound.
Monitoring method provided in an embodiment of the present invention, however, it is determined that not only defeated when thering is target organism to occur in area to be monitored
Prompt information is gone out, the location information of target organism can also be sent to monitor terminal.In this way, not only can be with automatic identification target
Biology, but also the position of target organism can be timely feedbacked, so that Security Personnel can handle related target person in time
Situation.
Further, monitoring method provided in an embodiment of the present invention, determine in area to be monitored there are target organism it
Afterwards, the status information of target organism can also be sent to monitor terminal.
Illustratively, a network linking can be sent to monitor terminal, prison can be checked by network by clicking the link
The biometric image information and biological sound information of the area to be monitored of photographic device and the sound pick up equipment shooting of control system, in this way,
User can understand the target organism situation of area to be monitored in more detail, to handle.
Wherein, monitor terminal can be computer, mobile phone, palm PC (personal digital assistant,
PDA), tablet computer and other video terminals.
Second aspect, as shown in figure 3, the embodiment of the present invention also provides a kind of monitoring device 30, comprising:
Acquiring unit 31, for obtaining the biometric image information and biological sound information of area to be monitored;
Processing unit 32, what biometric image information and/or acquiring unit 31 for being obtained according to acquiring unit 31 obtained
Biological sound information judges in area to be monitored with the presence or absence of target organism;
Output unit 33, for determining that output prompt is believed there are when target organism in area to be monitored in processing unit 32
Breath.
Illustratively, prompt information includes at least any one of acoustical signal, optical signal, electric signal or multinomial;It can also be with
It is the other modes such as vibration, is not particularly limited herein.
Illustratively, in some embodiments of the invention, processing unit 32 is specifically used for:
Extract the fisrt feature information in the biometric image information that acquiring unit 31 obtains;
Extract the second feature information in all target organism image informations stored in database;
Judge whether fisrt feature information matches with target second feature information;Target second feature information is all targets
The corresponding second feature information of any of biometric image information;
If it is determined that fisrt feature information and target second feature information matches, it is determined that it is raw that there are targets in area to be monitored
Object.
Illustratively, in some embodiments of the invention, processing unit 32 is specifically used for:
Extract the acoustic feature information in the biological sound information that acquiring unit 31 obtains;
Judge whether the acoustic feature information of the target organism stored in acoustic feature information and date library matches;
If it is determined that the acoustic feature information matches of acoustic feature information and target organism, it is determined that exist in area to be monitored
Target organism.
Illustratively, in some embodiments of the invention, processing unit 32 is specifically used for:
Extract the semantic feature information in the biological sound information that acquiring unit 31 obtains;
Semantic feature information is converted to the text information of reflection semantic feature;
Word segmentation processing is carried out to text information;
Judgement is matched by the text information after word segmentation processing with the semantic sample prestored;If it is determined that by participle
Text information after processing and the semantic sample matches prestored, it is determined that there are target organisms in area to be monitored.
Illustratively, in some embodiments of the invention, acquiring unit 31 is also used to determine in processing unit 32 wait supervise
There are the location informations for after target organism, obtaining target organism in control region;As shown in figure 4, monitoring device 30 further includes hair
Unit 34 is sent, for location information to be sent to monitor terminal 40.
The third aspect, refering to what is shown in Fig. 5, the embodiment of the present invention also provides another monitoring device 50, including memory 51,
Processor 52, bus 53 and communication interface 54;Memory 51 is for storing computer executed instructions, processor 52 and memory 51
It is connected by bus 53;When monitoring device operation, processor 52 executes the computer executed instructions that memory 51 stores, so that
Monitoring device executes such as monitoring method provided by the above embodiment.
In concrete implementation, as one embodiment, processor 52 (52-1 and 52-2) may include one or more
CPU, such as CPU0 and CPU1 shown in Fig. 5.And as one embodiment, monitoring device may include multiple processors 52,
Such as processor 52-1 and processor 52-2 shown in Fig. 5.Each of these processors 52 CPU can be a monokaryon
Processor (single-CPU) is also possible to a multi-core processor (multi-CPU).Here processor 52 can refer to one
Or multiple equipment, circuit, and/or the processing core for handling data (such as computer program instructions).
Memory 51 can be read-only memory 51 (read-only memory, ROM) or can store static information and refer to
The other kinds of static storage device enabled, random access memory (random access memory, RAM) or can store
The other kinds of dynamic memory of information and instruction, is also possible to Electrically Erasable Programmable Read-Only Memory
(electrically erasable programmable read-only memory, EEPROM), CD-ROM (compact
Disc read-only memory, CD-ROM) or other optical disc storages, optical disc storage (including compression optical disc, laser disc, light
Dish, Digital Versatile Disc, Blu-ray Disc etc.), magnetic disk storage medium or other magnetic storage apparatus or can be used in carry or
Store have instruction or data structure form desired program code and can by any other medium of computer access, but
It is without being limited thereto.Memory 51, which can be, to be individually present, and is connected by bus 53 with processor 52.Memory 51 can also and be located
Reason device 52 integrates.
In concrete implementation, memory 51, for storing the data in the application and executing the software program of the application
Corresponding computer executed instructions.Processor 52 can by running or executing the software program being stored in memory 51, with
And the data being stored in memory 51 are called, realize the various functions of monitoring device.
Communication interface 54 is used for and other equipment or communication, such as control using the device of any transceiver one kind
System processed, wireless access network (radio access network, RAN), WLAN (wireless local area
Networks, WLAN) etc..Communication interface 54 may include that receiving unit realizes that receive capabilities and transmission unit realize transmission
Function.
It is total to can be industry standard architecture (industry standard architecture, ISA) for bus 53
Line, external equipment interconnection (peripheral component interconnect, PCI) bus or extension Industry Standard Architecture
Structure (extended industry standard architecture, EISA) bus etc..The bus 53 can be divided into address
Bus, data/address bus, control bus etc..Only to be indicated with a thick line in Fig. 5, it is not intended that only one convenient for indicating
Bus or a type of bus.
Fourth aspect, refering to what is shown in Fig. 6, the embodiment of the present invention also provides a kind of monitoring system, the prison including second aspect
Control device 30.
Monitoring system provided in an embodiment of the present invention, due to the monitoring device 30 including second aspect, monitoring device 30 is wrapped
Acquiring unit 31, processing unit 32, output unit 33 are included, it is first when being monitored using the monitoring system to area to be monitored
First, acquiring unit 31 obtains the biometric image information and biological sound information of area to be monitored, secondly, processing unit 32 is according to obtaining
The biological sound information that the biometric image information and/or acquiring unit 31 for taking unit 31 to obtain obtain judges
No there are target organisms, determine in area to be monitored in processing unit 32 there are when target organism, export prompt information.In this way,
Technical solution provided in an embodiment of the present invention, by the way of combining Video Supervision Technique and image, voice recognition technology
Automatically the behavior of the biology occurred in area to be monitored is analyzed and is judged, relative to existing monitor mode, do not need one
Directly there are Security Personnel's manual analysis and judgement, greatly reduces the workload of Security Personnel, and reduce using manual type
Analyzed the behavior state of the biology occurred in area to be monitored and judged the careless omission occurred, therefore, the embodiment of the present invention
The technical solution of offer, improves monitoring efficiency compared with the existing technology.
Illustratively, refering to what is shown in Fig. 6, monitoring system provided in an embodiment of the present invention can specifically be divided into front end layer 1,
Service layer 2 and management level 3.
Front end layer 1 can specifically include camera 11 and pick-up head 12, and camera 11 is used to shoot the life of area to be monitored
Object image information, pick-up head 12 are used to pick up the biological sound information of area to be monitored.
Service layer 2 can specifically include the monitoring device 30 of second aspect, storage array 23, and storage array 23 is above-mentioned reality
Apply the database in example.
Wherein, the monitoring device 30 of second aspect be used for according to biometric image information and/or biological sound information judge to
It whether there is target organism in monitoring area;Storage array 23 is used to store the acoustics of target organism image information, target organism
Characteristic information, semantic sample.
Management level 3 can specifically include monitor terminal 40 and combined aural and visual alarm 41.
Those skilled in the art should be understood that embodiment of the disclosure can provide as method, system or computer journey
Sequence product.Therefore, complete hardware embodiment, complete software embodiment or combining software and hardware aspects can be used in the disclosure
The form of embodiment.Moreover, it wherein includes the calculating of computer usable program code that the disclosure, which can be used in one or more,
Machine can use the meter implemented in non-transient storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of calculation machine program product.
The disclosure is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present disclosure
Figure and/or block diagram describe.It is interpreted as to be realized by computer program instructions each in flowchart and/or the block diagram
The combination of process and/or box in process and/or box and flowchart and/or the block diagram.It can provide these computer journeys
Sequence instruct to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices processor with
A machine is generated, so that the instruction generation executed by computer or the processor of other programmable data processing devices is used for
Realize the dress for the function of specifying in one or more flows of the flowchart and/or one or more blocks of the block diagram
It sets.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.These computer program instructions can also be loaded into computer or the processing of other programmable datas is set
It is standby upper, so that execute series of operation steps on a computer or other programmable device to generate computer implemented processing,
To which instruction executed on a computer or other programmable device is provided for realizing in one process of flow chart or multiple streams
The step of function of being specified in journey and/or one or more blocks of the block diagram.
The above is only a specific embodiment of the invention, but scope of protection of the present invention is not limited thereto, any to be familiar with
In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by those skilled in the art, should all cover
Within protection scope of the present invention.Therefore, protection scope of the present invention should be subject to the protection scope in claims.
Claims (12)
1. a kind of monitoring method characterized by comprising
Obtain the biometric image information and biological sound information of area to be monitored;
Judged in the area to be monitored according to the biometric image information and/or the biological sound information with the presence or absence of mesh
Mark biology;
If it is determined that there are target organisms in the area to be monitored, prompt information is exported.
2. monitoring method according to claim 1, which is characterized in that described according to biometric image information judgement
It whether there is target organism in area to be monitored, comprising:
Extract the fisrt feature information in the biometric image information;
Extract the second feature information in all target organism image informations in database;
Judge whether the fisrt feature information matches with target second feature information;The target second feature information is all
The corresponding second feature information of any of the target organism image information;
If it is determined that the fisrt feature information and the target second feature information matches, it is determined that the area to be monitored memory
In target organism.
3. monitoring method according to claim 1, which is characterized in that described according to biological sound information judgement
It whether there is target organism in area to be monitored, comprising:
Extract the acoustic feature information in the biological sound information;
Judge whether the acoustic feature information of the target organism stored in acoustic feature information and date library matches;If
Determine the acoustic feature information matches of the acoustic feature information Yu the target organism, it is determined that the area to be monitored memory
In target organism.
4. monitoring method according to claim 1, which is characterized in that described according to biological sound information judgement
It whether there is target organism in area to be monitored, comprising:
Extract the semantic feature information in the biological sound information;
The semantic feature information is converted to the text information of reflection semantic feature, and the text information is carried out at participle
Reason;
Whether judgement matches by the text information after word segmentation processing with the semantic sample prestored, however, it is determined that passes through word segmentation processing
Text information later and the semantic sample matches prestored, it is determined that there are target organisms in the area to be monitored.
5. monitoring method according to any one of claims 1 to 4, which is characterized in that determining in the area to be monitored
There are after target organism, further includes:
The location information of the target organism is obtained, and the location information is sent to monitor terminal.
6. a kind of monitoring device characterized by comprising
Acquiring unit, for obtaining the biometric image information and biological sound information of area to be monitored;
Processing unit, the biometric image information and/or the acquiring unit for being obtained according to the acquiring unit obtain
The biological sound information judge in the area to be monitored with the presence or absence of target organism;
Output unit, for determining that output prompt is believed there are when target organism in the area to be monitored in the processing unit
Breath.
7. monitoring device according to claim 6, which is characterized in that the processing unit is specifically used for:
Extract the fisrt feature information in the biometric image information that the acquiring unit obtains;
Extract the second feature information in all target organism image informations stored in database;
Judge whether the fisrt feature information matches with target second feature information;The target second feature information is all
The corresponding second feature information of any of the target organism image information;
If it is determined that the fisrt feature information and the target second feature information matches, it is determined that the area to be monitored memory
In target organism.
8. monitoring device according to claim 6, which is characterized in that the processing unit is specifically used for:
Extract the acoustic feature information in the biological sound information that the acquiring unit obtains;
Judge whether the acoustic feature information of the target organism stored in acoustic feature information and date library matches;
If it is determined that the acoustic feature information matches of the acoustic feature information and the target organism, it is determined that the area to be monitored
There are target organisms in domain.
9. monitoring device according to claim 6, which is characterized in that the processing unit is specifically used for:
Extract the semantic feature information in the biological sound information;
The semantic feature information is converted to the text information of reflection semantic feature, and the text information is carried out at participle
Reason;
Whether judgement matches by the text information after word segmentation processing with the semantic sample prestored, however, it is determined that passes through word segmentation processing
Text information later and the semantic sample matches prestored, it is determined that there are target organisms in the area to be monitored.
10. according to the described in any item monitoring devices of claim 6~9, which is characterized in that further include transmission unit;
The acquiring unit is also used to determine in the area to be monitored in the processing unit there are after target organism, obtain
The location information of the target organism;
The transmission unit, the location information for obtaining the acquiring unit are sent to monitor terminal.
11. a kind of monitoring device, which is characterized in that including memory, processor, bus and communication interface;The memory is used
In storage computer executed instructions, the processor is connect with the memory by the bus;When the monitoring device is transported
When row, the processor executes the computer executed instructions of the memory storage, so that the monitoring device executes such as
The described in any item monitoring methods of Claims 1 to 5.
12. a kind of monitoring system, which is characterized in that including the described in any item monitoring devices of such as claim 6~10.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910708296.5A CN110532888A (en) | 2019-08-01 | 2019-08-01 | A kind of monitoring method, apparatus and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910708296.5A CN110532888A (en) | 2019-08-01 | 2019-08-01 | A kind of monitoring method, apparatus and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110532888A true CN110532888A (en) | 2019-12-03 |
Family
ID=68660497
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910708296.5A Pending CN110532888A (en) | 2019-08-01 | 2019-08-01 | A kind of monitoring method, apparatus and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110532888A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110956165A (en) * | 2020-02-25 | 2020-04-03 | 恒大智慧科技有限公司 | Intelligent community unbundling pet early warning method and system |
CN111259746A (en) * | 2020-01-09 | 2020-06-09 | 浙江新再灵科技股份有限公司 | Method and system for detecting pet guy rope in straight ladder |
CN111332889A (en) * | 2020-03-16 | 2020-06-26 | 成都新潮传媒集团有限公司 | Method and system for identifying pets in elevator |
CN111397621A (en) * | 2020-03-25 | 2020-07-10 | 咪咕互动娱乐有限公司 | Walking path planning method and device and storage medium |
CN111447410A (en) * | 2020-03-24 | 2020-07-24 | 安徽工程大学 | Dog state identification monitoring system and method |
CN112738471A (en) * | 2020-12-28 | 2021-04-30 | 詹晨 | Security monitoring data processing method based on Internet of things and artificial intelligence and cloud communication server |
CN113071965A (en) * | 2021-03-26 | 2021-07-06 | 广州广日电梯工业有限公司 | Elevator-based livestock monitoring method and elevator-based livestock monitoring device |
CN113965722A (en) * | 2021-09-10 | 2022-01-21 | 浙江西谷数字技术股份有限公司 | Intelligent community security monitoring system based on Internet of things |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104243894A (en) * | 2013-06-09 | 2014-12-24 | 中国科学院声学研究所 | Audio and video fused monitoring method |
CN106683361A (en) * | 2017-01-24 | 2017-05-17 | 宇龙计算机通信科技(深圳)有限公司 | Sound monitoring method and device |
CN107122807A (en) * | 2017-05-24 | 2017-09-01 | 努比亚技术有限公司 | A kind of family's monitoring method, service end and computer-readable recording medium |
CN109036461A (en) * | 2017-06-12 | 2018-12-18 | 杭州海康威视数字技术股份有限公司 | A kind of output method of notification information, server and monitoring system |
CN109598885A (en) * | 2018-12-21 | 2019-04-09 | 广东中安金狮科创有限公司 | Monitoring system and its alarm method |
CN109639700A (en) * | 2018-12-25 | 2019-04-16 | 深圳市天彦通信股份有限公司 | Personal identification method, device, equipment, cloud server and storage medium |
CN109657624A (en) * | 2018-12-21 | 2019-04-19 | 秒针信息技术有限公司 | Monitoring method, the device and system of target object |
CN109743541A (en) * | 2018-12-15 | 2019-05-10 | 深圳壹账通智能科技有限公司 | Intelligent control method, device, computer equipment and storage medium |
CN109993946A (en) * | 2017-12-29 | 2019-07-09 | 国民技术股份有限公司 | A kind of monitoring alarm method, camera, terminal, server and system |
-
2019
- 2019-08-01 CN CN201910708296.5A patent/CN110532888A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104243894A (en) * | 2013-06-09 | 2014-12-24 | 中国科学院声学研究所 | Audio and video fused monitoring method |
CN106683361A (en) * | 2017-01-24 | 2017-05-17 | 宇龙计算机通信科技(深圳)有限公司 | Sound monitoring method and device |
CN107122807A (en) * | 2017-05-24 | 2017-09-01 | 努比亚技术有限公司 | A kind of family's monitoring method, service end and computer-readable recording medium |
CN109036461A (en) * | 2017-06-12 | 2018-12-18 | 杭州海康威视数字技术股份有限公司 | A kind of output method of notification information, server and monitoring system |
CN109993946A (en) * | 2017-12-29 | 2019-07-09 | 国民技术股份有限公司 | A kind of monitoring alarm method, camera, terminal, server and system |
CN109743541A (en) * | 2018-12-15 | 2019-05-10 | 深圳壹账通智能科技有限公司 | Intelligent control method, device, computer equipment and storage medium |
CN109598885A (en) * | 2018-12-21 | 2019-04-09 | 广东中安金狮科创有限公司 | Monitoring system and its alarm method |
CN109657624A (en) * | 2018-12-21 | 2019-04-19 | 秒针信息技术有限公司 | Monitoring method, the device and system of target object |
CN109639700A (en) * | 2018-12-25 | 2019-04-16 | 深圳市天彦通信股份有限公司 | Personal identification method, device, equipment, cloud server and storage medium |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111259746A (en) * | 2020-01-09 | 2020-06-09 | 浙江新再灵科技股份有限公司 | Method and system for detecting pet guy rope in straight ladder |
CN110956165A (en) * | 2020-02-25 | 2020-04-03 | 恒大智慧科技有限公司 | Intelligent community unbundling pet early warning method and system |
CN111332889A (en) * | 2020-03-16 | 2020-06-26 | 成都新潮传媒集团有限公司 | Method and system for identifying pets in elevator |
CN111447410A (en) * | 2020-03-24 | 2020-07-24 | 安徽工程大学 | Dog state identification monitoring system and method |
CN111397621A (en) * | 2020-03-25 | 2020-07-10 | 咪咕互动娱乐有限公司 | Walking path planning method and device and storage medium |
CN111397621B (en) * | 2020-03-25 | 2023-10-17 | 咪咕互动娱乐有限公司 | Method, device and storage medium for planning walk path |
CN112738471A (en) * | 2020-12-28 | 2021-04-30 | 詹晨 | Security monitoring data processing method based on Internet of things and artificial intelligence and cloud communication server |
CN113071965A (en) * | 2021-03-26 | 2021-07-06 | 广州广日电梯工业有限公司 | Elevator-based livestock monitoring method and elevator-based livestock monitoring device |
CN113965722A (en) * | 2021-09-10 | 2022-01-21 | 浙江西谷数字技术股份有限公司 | Intelligent community security monitoring system based on Internet of things |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110532888A (en) | A kind of monitoring method, apparatus and system | |
US20180121738A1 (en) | Systems and methods for supplementing captured data | |
CN109255288A (en) | A kind of road surface breakage detection method, device and terminal device | |
CN113673459B (en) | Video-based production and construction site safety inspection method, system and equipment | |
WO2019127271A1 (en) | Warning method, device, storage medium and server regarding physical conflict behavior | |
US20190171740A1 (en) | Method and system for modifying a search request corresponding to a person, object, or entity (poe) of interest | |
CN110309735A (en) | Exception detecting method, device, server and storage medium | |
CN107590953B (en) | Alarm method and system of intelligent wearable device and terminal device | |
CN111191507A (en) | Safety early warning analysis method and system for smart community | |
CN111523362A (en) | Data analysis method and device based on electronic purse net and electronic equipment | |
CN117079299B (en) | Data processing method, device, electronic equipment and storage medium | |
CN111091044A (en) | Network appointment-oriented in-vehicle dangerous scene identification method | |
NL2037440A (en) | A method, system, and medium for intelligent recognition of fishing activities based on image processing | |
CN111860071A (en) | Method and device for identifying an item | |
CN111723767B (en) | Image processing method, device and computer storage medium | |
CN112738471A (en) | Security monitoring data processing method based on Internet of things and artificial intelligence and cloud communication server | |
RU2684484C1 (en) | Method and cognitive system for video analysis, monitoring, control of driver and vehicle state in real time | |
CN111259698B (en) | Method and device for acquiring image | |
CN109858829A (en) | Hidden danger accident early warning method based on block chain | |
CN116012905A (en) | Driver road anger disease recognition and warning system | |
CN113762092A (en) | Hospital user medical alarm detection method, system, robot and storage medium | |
CN113342978A (en) | City event processing method and device | |
CN112750274A (en) | Facial feature recognition-based aggregation early warning system, method and equipment | |
US11145196B2 (en) | Cognitive-based traffic incident snapshot triggering | |
CN112200145A (en) | Remote identification method for public security |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191203 |