CN109614906A - A kind of security system and security alarm method based on deep learning - Google Patents
A kind of security system and security alarm method based on deep learning Download PDFInfo
- Publication number
- CN109614906A CN109614906A CN201811466946.1A CN201811466946A CN109614906A CN 109614906 A CN109614906 A CN 109614906A CN 201811466946 A CN201811466946 A CN 201811466946A CN 109614906 A CN109614906 A CN 109614906A
- Authority
- CN
- China
- Prior art keywords
- moving object
- information
- type
- image information
- described image
- 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
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Abstract
The embodiment of the present invention provides a kind of security system based on deep learning and security alarm method, provided system includes: image collecting device, for carrying out Image Acquisition to monitoring area, image information is obtained, and described image information is sent to moving object identification module;The anticipation information, if judgement knows in described image information to include moving object, is sent to identification module for carrying out moving object identification to described image information by moving object identification module;Categorization module obtains the type of the moving object for identifying by preset identification model to the moving object in the figure information;Alarm module then sends warning message when judging to know the type of the moving object as target type.System provided in an embodiment of the present invention identifies the type of dynamic object when detecting dynamic object, identifies automatically to the moving target in region to realize system, reduces artificial workload.
Description
Technical field
The present embodiments relate to field of security technology more particularly to a kind of security systems and security protection based on deep learning
Alarm method.
Background technique
Security system is that intrusion alarm system, the video peace that product and other Related products are constituted are taken precautions against with application safety
The system of anti-monitoring system, gateway control system, anti-explosion safety inspection etc.;Or it is combined or is collected for subsystem by these systems
At electronic system or network.Security system on the market is generally made of inductor, monitor and control host at present, is incuded
Device and monitor are linked with control host respectively.Its work step are as follows: inductor generates inductive signal, and inductive signal is passed
It is defeated to arrive control host;Control host receives inductive signal and alarms, while inductor sends warning message to the movement of user
Equipment;The image information that control host saves monitor acquisition is checked for user.
In the prior art, security system relies primarily on the visual determination of people and the automatic sensing of inductor, but due to
The reason of inductor working principle and installation site, can have the case where wrong report, fail to report;Field large-scale for factory, market etc.
Institute, monitor need someone on duty in turn, and a monitoring personnel can not supervise multiple video images simultaneously, and can not be long when
Between stare at monitoring TV, meanwhile, security system can be only done the storage record of the video in the time, lack to the intelligence of video content
Analysis, only can provide evidence for ex-post analysis.
Summary of the invention
The embodiment of the present invention provides a kind of security system based on deep learning and security alarm method, existing to solve
Security system relies primarily on the visual determination of people in technology and the automatic sensing of inductor has the case where wrong report, fail to report, simultaneously
Need staff on duty for a long time, the excessively high problem of cost of labor.
In a first aspect, the embodiment of the present invention provides a kind of security system based on deep learning, comprising:
Image collecting device obtains image information, and by described image information for carrying out Image Acquisition to monitoring area
It is sent to moving object identification module;
Moving object identification module, for carrying out moving object identification to described image information, if the figure is known in judgement
As including moving object in information, then the anticipation information is sent to identification module;
Categorization module is obtained for being identified by preset identification model to the moving object in the figure information
The type of the moving object;
Alarm module then sends warning message when judging to know the type of the moving object as target type.
Wherein, the alarm module further include: mobile communication submodule, for knowing the class of the moving object when judgement
When type is people, warning message and described image information are sent to the user terminal.
Wherein, the categorization module is specially the classifier based on SVM optimization algorithm.
Wherein, in the categorization module further include: training submodule, for being carried out by training sample set to identification model
Training obtains the preset identification model.
Wherein, the moving object identification module is specifically used for, by weighted average to every in described image information
One frame image carries out background modeling, detects the moving object in the figure information.
Wherein, the system also includes alarms, for receiving the alarm signal of user terminal by the communication submodule
Breath, and according to the warning message alarm for opening.
Second aspect, the embodiment of the present invention provide a kind of security alarm method, comprising:
Image Acquisition is carried out to monitoring area, obtains image information, and described image information is sent to moving object and is known
Other module;
Moving object identification is carried out to described image acquisition information, if it includes movement that judgement, which is known in described image information,
The anticipation information is then sent to identification module by object;
The moving object in the figure information is identified by preset identification model, obtains the moving object
Type;
When judging to know the type of the moving object as target type, then warning message is sent.
System and method provided in an embodiment of the present invention, it is dynamic when detecting to progress dynamic object identification in monitoring area
When state object, the type of dynamic object is identified, and is alarmed according to the type of dynamic object, to realize
System automatically identifies the moving target in region, reduces artificial workload, pays close attention to and takes the photograph in real time without staff
As the image condition in head, intelligent monitoring is realized, intelligent alarm improves the user experience of alarm system.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the structural schematic diagram for the security system based on deep learning that one embodiment of the invention provides;
Fig. 2 is the flow diagram for the security alarm method that one embodiment of the invention provides;
Fig. 3 is the work flow diagram of system in the security alarm method that one embodiment of the invention provides;
Motion estimate flow diagram in the security alarm method that Fig. 4 provides for one embodiment of the invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
With reference to Fig. 1, Fig. 1 is the structural schematic diagram for the security system based on deep learning that one embodiment of the invention provides,
Provided system includes: image collecting device 11, moving object identification module 12, categorization module 13 and alarm module 14.
Wherein, image collecting device 11 is used to carry out Image Acquisition to monitoring area, obtains image information, and by the figure
As information is sent to moving object identification module;
Moving object identification module 12 is used to carry out moving object identification to described image information, if the figure is known in judgement
As including moving object in information, then the anticipation information is sent to identification module;
Categorization module 13 is obtained for being identified by preset identification model to the moving object in the figure information
The type of the moving object;
Alarm module 14 then sends warning message when judging to know the type of the moving object as target type.
Specifically, image collecting device, which is mounted on, needs monitoring area, Image Acquisition carried out to monitoring area, and by image
Information is transferred to processor, is provided with moving object identification module in the processor, the image arrived to image acquisition device
Information is identified, wherein image collecting device can be common monitoring camera, or with taking the photograph for infrared function
It, can be to carrying out continuing camera shooting in certain area as head.
Moving object identification module adjusts background model by dynamic and handles image information, when monitoring area goes out
When existing moving target, categorization module is positioned and is identified to moving target, judges the type of moving target, wherein moving object
Body identification module mainly passes through motion detecting, to identify that, with the presence or absence of moving object in image information, motion detecting is generally also named
Mobile detection is usually used in unattended monitoring video recording and automatic alarm.The figure collected by camera according to different frame rates
As that can be calculated and compared by CPU according to certain algorithm, when picture changes, if someone passes by, camera lens is moved, and is calculated
The number that comparison result obtains can be more than threshold value and indicate that system can make corresponding processing automatically.
When it includes moving object that moving object identification module, which recognizes in image information, then pass through preset model pair
It include that the image information of moving object is identified that in the concrete realization, preset model can be neural network model,
It can be SVM classifier model, main function is to identify the type of the moving object in image information, and by moving object
The type of body informs alarm module.
Alarm module is in knowing image information after the type of moving object, when the type for determining moving object is preset
When target type, then warning message can be sent to user, such as the movement when target type is people, in discovery image information
When object is people, then warning message can be sent to user, when moving object is other biological, then can send general information
User is notified, so that user carries out corresponding countermeasure according to moving object type.
By this system, to dynamic object identification is carried out in monitoring area, when detecting dynamic object, to dynamic
The type of object is identified, and is alarmed according to the type of dynamic object, to realize system automatically in region
Moving target is identified, artificial workload is reduced, and pays close attention to the image condition in camera in real time without staff, real
Intelligent monitoring is showed, intelligent alarm improves the user experience of alarm system.
On the basis of the above embodiments, the alarm module further include: mobile communication submodule, for knowing when judgement
When the type of the moving object is people, warning message and described image information are sent to the user terminal.
It by warning message and can include moving object specifically, also including mobile communication submodule in alarm module
The image information of body is sent on the user terminal of distal end, wherein mobile communication submodule is specially 2G, 3G or 4G communication mould
Block, the type of user terminal include mobile phone, tablet computer and other kinds of operation control terminal, further, mobile device
Information can remotely be received and can be with remote control security system.
By this system, remote monitoring is realized, staff can remotely receive the warning message of security system, together
When security system can be controlled in distal end, the flexibility that the system of improving uses.
On the basis of the above embodiments, the categorization module is specially the classifier based on SVM optimization algorithm.Described point
In generic module further include: training submodule obtains described preset for being trained by training sample set to identification model
Identification model.
Specifically, categorization module is specially the classifier based on SVM optimization algorithm, it also include training module in system,
By way of deep learning, classifier is trained using training sample set, and then obtains preset disaggregated model.Having
During body is realized, learner model is optimized using adaptability moment estimation method under the conditions of soft sparse constraint, is allowed to
It is run on small size, low power consuming devices.The purpose of sparse signal representation is exactly in given super complete dictionary with as far as possible
Few atom indicates signal, can obtain the more succinct representation of signal, so that us be made more easily to obtain signal
Middle contained information, it is more convenient that further signal is processed, such as compression, coding.
On the basis of the above embodiments, the moving object identification module is specifically used for, by weighted average to institute
The each frame image stated in image information carries out background modeling, detects the moving object in the figure information.
Specifically, the weighted average for the prior image frame that system uses cooperates present frame in moving object identification process
It carries out background modeling and detects moving target, can dynamically adjust background, eliminate influence of the environment to system.
On the basis of the above embodiments, the system also includes alarms, for being received by the communication submodule
The warning message of user terminal, and according to the warning message alarm for opening.
Specifically, further including onsite alarming device in system, if moving target is people, safety device can be existing by alarm
Field alarms and sends user mobile phone for target image, and user can take further measures or close alarm according to character relation
Device, if target is other biological, safety device can send images to user mobile phone, and user can be with remote opening onsite alarming
Device draws back biology with fear or ignores this information.
With reference to Fig. 2, Fig. 2 is the flow diagram for the security alarm method that one embodiment of the invention provides, provided side
Method includes:
S201 carries out Image Acquisition to monitoring area, obtains image information, and described image information is sent to moving object
Body identification module;
S202 carries out moving object identification to described image acquisition information, includes if judgement is known in described image information
There is moving object, then the anticipation information is sent to identification module;
S203 identifies the moving object in the figure information by preset identification model, obtains the movement
The type of object;
S204 then sends warning message when judging to know the type of the moving object as target type.
Specifically, carrying out Image Acquisition to monitoring area by camera, and image information is transferred to processor, located
Reason device in be provided with moving object identification module, to image acquisition device to image information identify, wherein image
Acquisition device can be common monitoring camera, or the camera with infrared function, it can be in certain area
It carries out continuing camera shooting.
Moving object identification module adjusts background model by dynamic and handles image information, when monitoring area goes out
When existing moving target, categorization module is positioned and is identified to moving target, judges the type of moving target, wherein moving object
Body identification module mainly passes through motion detecting, to identify in image information with the presence or absence of moving object.
When it includes moving object that moving object identification module, which recognizes in image information, then pass through preset model pair
It include that the image information of moving object is identified that in the concrete realization, preset model can be neural network model,
It can be SVM classifier model, main function is to identify the type of the moving object in image information, and by moving object
The type of body informs alarm module.
Alarm module is in knowing image information after the type of moving object, when the type for determining moving object is preset
When target type, then warning message can be sent to user, such as the movement when target type is people, in discovery image information
When object is people, then warning message can be sent to user, when moving object is other biological, then can send general information
User is notified, so that user carries out corresponding countermeasure according to moving object type.
In an overall workflow, refering to what is shown in Fig. 3, Fig. 3 is the security alarm side that one embodiment of the invention provides
In method, the work flow diagram of system, implementation step is as follows, and camera is arranged in monitoring area, connect with safety device,
Safety device is placed indoors, safety device receives camera acquired image information.Safety device is depending on the site environment
Dynamic adjustment background model simultaneously handles the image information received.When the changes of threshold in image information is greater than the set value, place
Reason device can position the moving target in image, and classify to moving target, as shown in figure 4, Fig. 4 is one embodiment of the invention
Motion estimate flow diagram in the security alarm method of offer.If target is people, safety device can pass through alarm
Onsite alarming simultaneously sends user mobile phone for target image, and user can take further measures or close report according to character relation
If alert device target is other biological, safety device can send images to user mobile phone, and user can be reported with remote opening scene
Device is warned to draw back biology with fear or ignore this information.User can manipulate the switch of security system by mobile device remote.
On the basis of the above embodiments, described when judging to know the type of the moving object as target type, then
The step of sending warning message specifically includes: when judging to know the type of the moving object as people, by warning message and institute
Image information is stated to be sent to the user terminal.
The method also includes: identification model is trained by training sample set, obtains the preset identification mould
Type.
Described the step of carrying out moving object identification to described image acquisition information, specifically includes: by weighted average pair
Each frame image in described image information carries out background modeling, detects the moving object in the figure information.
It by warning message and can include moving object specifically, also including mobile communication submodule in alarm module
The image information of body is sent on the user terminal of distal end, wherein mobile communication submodule is specially 2G, 3G or 4G communication mould
Block, the type of user terminal include mobile phone, tablet computer and other kinds of operation control terminal, further, mobile device
Information can remotely be received and can be with remote control security system.
Categorization module is specially the classifier based on SVM optimization algorithm, also includes training module in system, passes through depth
The mode of study is trained classifier using training sample set, and then obtains preset disaggregated model.It is implementing
In, learner model is optimized using adaptability moment estimation method under the conditions of soft sparse constraint, is allowed in corpusculum
It is run in product, low power consuming devices.
In to moving object identification process, by using prior image frame weighted average cooperation present frame carried on the back
Scape modeling detection moving target, can dynamically adjust background, eliminate influence of the environment to system.
In conclusion system and method provided in an embodiment of the present invention, can moving target in automatic detection zone, no
Need to be artificial on duty, reduce artificial workload;Security system can identify moving target, be carried out according to target category corresponding
Processing, user can manipulate system remote by mobile device, improve the flexibility of system.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features;
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (10)
1. a kind of security system based on deep learning characterized by comprising
Image collecting device obtains image information, and described image information is sent for carrying out Image Acquisition to monitoring area
Give moving object identification module;
Moving object identification module, for carrying out moving object identification to described image information, if judgement knows that described image is believed
Include moving object in breath, then the anticipation information is sent to identification module;
Categorization module, for being identified by preset identification model to the moving object in the figure information, described in acquisition
The type of moving object;
Alarm module then sends warning message when judging to know the type of the moving object as target type.
2. system according to claim 1, which is characterized in that the alarm module further include: mobile communication submodule is used
In when judging to know the type of the moving object as people, warning message and described image information are sent to the user terminal.
3. system according to claim 1, which is characterized in that the categorization module is specially based on SVM optimization algorithm
Classifier.
4. system according to claim 3, which is characterized in that in the categorization module further include: training submodule is used for
Identification model is trained by training sample set, obtains the preset identification model.
5. system according to claim 1, which is characterized in that the moving object identification module is specifically used for, by adding
Weight average value carries out background modeling to each frame image in described image information, detects the moving object in the figure information.
6. system according to claim 1, which is characterized in that the system also includes alarms, for by described logical
Believe that submodule receives the warning message of user terminal, and according to the warning message alarm for opening.
7. a kind of security alarm method based on the security system as claimed in claim 1 to 7 based on deep learning, special
Sign is, comprising:
Image Acquisition is carried out to monitoring area, obtains image information, and described image information is sent to moving object identification mould
Block;
Moving object identification is carried out to described image acquisition information, if judgement knows in described image information to include moving object
The anticipation information is then sent to identification module by body;
The moving object in the figure information is identified by preset identification model, obtains the class of the moving object
Type;
When judging to know the type of the moving object as target type, then warning message is sent.
8. the method according to the description of claim 7 is characterized in that described when judging to know the type of the moving object as mesh
When marking type, then the step of sending warning message, specifically includes:
When judging to know the type of the moving object as people, warning message and described image information are sent to user's end
End.
9. the method according to the description of claim 7 is characterized in that the method also includes:
Identification model is trained by training sample set, obtains the preset identification model.
10. the method according to the description of claim 7 is characterized in that described carry out moving object to described image acquisition information
The step of identification, specifically includes:
Background modeling is carried out to each frame image in described image information by weighted average, is detected in the figure information
Moving object.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811466946.1A CN109614906A (en) | 2018-12-03 | 2018-12-03 | A kind of security system and security alarm method based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811466946.1A CN109614906A (en) | 2018-12-03 | 2018-12-03 | A kind of security system and security alarm method based on deep learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109614906A true CN109614906A (en) | 2019-04-12 |
Family
ID=66006765
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811466946.1A Pending CN109614906A (en) | 2018-12-03 | 2018-12-03 | A kind of security system and security alarm method based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109614906A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110060440A (en) * | 2019-05-14 | 2019-07-26 | 三峡大学 | A kind of intelligent warning system for transmission line of electricity external force damage prevention |
CN110119730A (en) * | 2019-06-03 | 2019-08-13 | 齐鲁工业大学 | A kind of monitor video processing method, system, terminal and storage medium |
CN110381293A (en) * | 2019-06-18 | 2019-10-25 | 平安国际智慧城市科技股份有限公司 | Video monitoring method, device and computer readable storage medium |
CN110415267A (en) * | 2019-08-15 | 2019-11-05 | 利卓创新(北京)科技有限公司 | A kind of online thermal infrared target identification device of low-power consumption and working method |
CN111833373A (en) * | 2020-06-01 | 2020-10-27 | 浙江双视红外科技股份有限公司 | Infrared monitoring method, device and system based on moving object in target environment |
CN112016414A (en) * | 2020-08-14 | 2020-12-01 | 熵康(深圳)科技有限公司 | Method and device for detecting high-altitude parabolic event and intelligent floor monitoring system |
CN113159729A (en) * | 2021-05-08 | 2021-07-23 | 国网青海省电力公司西宁供电公司 | Point table checking system and method for shortening point table checking time |
CN113381510A (en) * | 2021-06-02 | 2021-09-10 | 深圳市莱达四维信息科技有限公司 | One-key sequential control video double-confirmation system for transformer substation |
CN113705472A (en) * | 2021-08-30 | 2021-11-26 | 平安国际智慧城市科技股份有限公司 | Abnormal camera checking method, device, equipment and medium based on image recognition |
CN114332743A (en) * | 2022-03-09 | 2022-04-12 | 深圳海润游艇码头工程有限公司 | Yacht wharf monitoring and alarming method and system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101017573A (en) * | 2007-02-09 | 2007-08-15 | 南京大学 | Method for detecting and identifying moving target based on video monitoring |
CN102833636A (en) * | 2012-08-10 | 2012-12-19 | 深圳市同洲电子股份有限公司 | Security monitoring system based on intelligent television and security monitoring method thereof |
CN104899559A (en) * | 2015-05-25 | 2015-09-09 | 江苏大学 | Rapid pedestrian detection method based on video monitoring |
CN106372576A (en) * | 2016-08-23 | 2017-02-01 | 南京邮电大学 | Deep learning-based intelligent indoor intrusion detection method and system |
-
2018
- 2018-12-03 CN CN201811466946.1A patent/CN109614906A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101017573A (en) * | 2007-02-09 | 2007-08-15 | 南京大学 | Method for detecting and identifying moving target based on video monitoring |
CN102833636A (en) * | 2012-08-10 | 2012-12-19 | 深圳市同洲电子股份有限公司 | Security monitoring system based on intelligent television and security monitoring method thereof |
CN104899559A (en) * | 2015-05-25 | 2015-09-09 | 江苏大学 | Rapid pedestrian detection method based on video monitoring |
CN106372576A (en) * | 2016-08-23 | 2017-02-01 | 南京邮电大学 | Deep learning-based intelligent indoor intrusion detection method and system |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110060440A (en) * | 2019-05-14 | 2019-07-26 | 三峡大学 | A kind of intelligent warning system for transmission line of electricity external force damage prevention |
CN110119730A (en) * | 2019-06-03 | 2019-08-13 | 齐鲁工业大学 | A kind of monitor video processing method, system, terminal and storage medium |
CN110381293A (en) * | 2019-06-18 | 2019-10-25 | 平安国际智慧城市科技股份有限公司 | Video monitoring method, device and computer readable storage medium |
CN110415267A (en) * | 2019-08-15 | 2019-11-05 | 利卓创新(北京)科技有限公司 | A kind of online thermal infrared target identification device of low-power consumption and working method |
CN111833373B (en) * | 2020-06-01 | 2024-01-23 | 浙江双视科技股份有限公司 | Infrared monitoring method, device and system based on moving object in target environment |
CN111833373A (en) * | 2020-06-01 | 2020-10-27 | 浙江双视红外科技股份有限公司 | Infrared monitoring method, device and system based on moving object in target environment |
CN112016414A (en) * | 2020-08-14 | 2020-12-01 | 熵康(深圳)科技有限公司 | Method and device for detecting high-altitude parabolic event and intelligent floor monitoring system |
CN113159729A (en) * | 2021-05-08 | 2021-07-23 | 国网青海省电力公司西宁供电公司 | Point table checking system and method for shortening point table checking time |
CN113381510B (en) * | 2021-06-02 | 2023-01-24 | 深圳市莱达四维信息科技有限公司 | One-key sequential control video double-confirmation system for transformer substation |
CN113381510A (en) * | 2021-06-02 | 2021-09-10 | 深圳市莱达四维信息科技有限公司 | One-key sequential control video double-confirmation system for transformer substation |
CN113705472A (en) * | 2021-08-30 | 2021-11-26 | 平安国际智慧城市科技股份有限公司 | Abnormal camera checking method, device, equipment and medium based on image recognition |
CN113705472B (en) * | 2021-08-30 | 2024-01-26 | 平安国际智慧城市科技股份有限公司 | Abnormal camera investigation method, device, equipment and medium based on image identification |
CN114332743A (en) * | 2022-03-09 | 2022-04-12 | 深圳海润游艇码头工程有限公司 | Yacht wharf monitoring and alarming method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109614906A (en) | A kind of security system and security alarm method based on deep learning | |
CN107911653B (en) | Intelligent video monitoring module, system, method and storage medium for residence | |
CN105913559B (en) | A kind of ATM in bank intelligent control method based on body-sensing technology | |
US20170155877A1 (en) | System and method for predicting patient falls | |
CN105426820B (en) | More people's anomaly detection methods based on safety monitoring video data | |
CN107818312A (en) | A kind of embedded system based on abnormal behaviour identification | |
CN209543514U (en) | Monitoring and alarm system based on recognition of face | |
CN109377697A (en) | Rapid Alarm method of disposal under a kind of intensive camera head environment | |
CN110381298A (en) | A kind of method, apparatus and system of tunnel video monitoring | |
CN107463887A (en) | Train driver gesture intelligence inspection system and intelligent inspection method | |
WO2016077468A1 (en) | System and method for inhibiting or causing automated actions based on person locations estimated from multiple video sources | |
CN116563797B (en) | Monitoring management system for intelligent campus | |
CN109544870A (en) | Alarm decision method and intelligent monitor system for intelligent monitor system | |
CN114218992A (en) | Abnormal object detection method and related device | |
CN115205581A (en) | Fishing detection method, fishing detection device and computer readable storage medium | |
KR20110079939A (en) | Image sensing agent and security system of usn complex type | |
CN113033521B (en) | Perimeter dynamic early warning method and system based on target analysis | |
CN111414829B (en) | Method and device for sending alarm information | |
CN106128105B (en) | A kind of traffic intersection pedestrian behavior monitoring system | |
CN104392201A (en) | Human fall identification method based on omnidirectional visual sense | |
Worrakulpanit et al. | Human fall detection using standard deviation of C-motion method | |
CN113420739B (en) | Intelligent emergency monitoring method and system based on neural network and readable storage medium | |
CN109815828A (en) | Realize the system and method for initiative alarming or help-seeking behavior detection control | |
CN116740874A (en) | Intrusion detection method and related device | |
KR20220067271A (en) | Image acquisition apparatus and image acquisition method |
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 |
Application publication date: 20190412 |
|
RJ01 | Rejection of invention patent application after publication |