CN107358778A - A kind of fire-alarm of combination KNN algorithms - Google Patents

A kind of fire-alarm of combination KNN algorithms Download PDF

Info

Publication number
CN107358778A
CN107358778A CN201710630768.0A CN201710630768A CN107358778A CN 107358778 A CN107358778 A CN 107358778A CN 201710630768 A CN201710630768 A CN 201710630768A CN 107358778 A CN107358778 A CN 107358778A
Authority
CN
China
Prior art keywords
module
alarm
fire
central processing
processing module
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
Application number
CN201710630768.0A
Other languages
Chinese (zh)
Inventor
谢明鸿
黄秋萍
张亚飞
王帅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Kunming University of Science and Technology
Original Assignee
Kunming University of Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Kunming University of Science and Technology filed Critical Kunming University of Science and Technology
Priority to CN201710630768.0A priority Critical patent/CN107358778A/en
Publication of CN107358778A publication Critical patent/CN107358778A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B17/00Fire alarms; Alarms responsive to explosion
    • G08B17/06Electric actuation of the alarm, e.g. using a thermally-operated switch
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B17/00Fire alarms; Alarms responsive to explosion
    • G08B17/10Actuation by presence of smoke or gases, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B25/00Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
    • G08B25/01Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
    • G08B25/08Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using communication transmission lines
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B29/00Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
    • G08B29/18Prevention or correction of operating errors
    • G08B29/185Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system
    • G08B29/188Data fusion; cooperative systems, e.g. voting among different detectors

Abstract

The present invention relates to a kind of fire-alarm of combination KNN algorithms, belong to safety monitoring technology field.The present invention includes central processing module, Smoke Sensor, alarm module, memory module, photographing module, point-type step differential temp type detector, locating module.Wherein KNN theories of algorithm are simple, it is easy to realize.The present invention can not only be quickly and accurately positioned out the particular location of fire alarm, and the assigned number set is sent in the form of short message, and it can also recognize the situation of scene of fire by memory module in the very first time, effectively and rationally to organize to rescue, casualties and property loss are reduced to greatest extent.

Description

A kind of fire-alarm of combination KNN algorithms
Technical field
The present invention relates to a kind of fire-alarm of combination KNN algorithms, belong to safety monitoring technology field.
Background technology
Fire serious threat the life of people, and the development to our security of the lives and property and country causes huge Loss.Security against fire is the cardinal task of each enterprise, and the emphasis of fire-fighting work is mainly aimed at prevention, combined prevention with fire fighting. Substantial amounts of smoke particle can be all usually produced when fire occurs, so the concentration of smoke particle turns into judges whether that fire occurs The important evidence of calamity.Meanwhile temperature can be caused to raise rapidly during fire generation, front and rear temperature difference on fire is very big.Generally fire Calamity scene is all relative closure, it is difficult to the concrete condition of scene of fire is observed from the external world in the very first time, can not be efficiently accurate Really organize to rescue.Smoke alarm is widely used that on present society, with the pollution of air, or some specific fields Institute, the granule density in air is higher, so as to easily reach predetermined value, produces the situation of false alarm.Will not although can ensure that Fail to report, but the accuracy rate of its alarm reduces, it is also possible to the great loss caused by wrong report.
So being badly in need of one kind can accurately alarm, and the fire-alarm of the situation of scene of fire can be grasped in the very first time.
The content of the invention
The technical problem to be solved in the present invention is:The present invention provides a kind of fire-alarm of combination KNN algorithms, for Solution alarm accuracy rate is not high, and the situation of scene of fire can not be grasped in the very first time, can not accurate judgement specific position on fire The problem of putting, and can not be just notify related personnel in time in the Initial Stage of Fire stage the problem of.
The technical scheme is that:A kind of fire-alarm of combination KNN algorithms, including central processing module 1, smog pass Sensor 2, alarm module 3, memory module 4, photographing module 5, point-type step differential temp type detector 6, locating module 7;
The central processing module module 1 connects multiple Smoke Sensors 2, alarm module 3 by electric signal, memory module 4, taken the photograph As module 5, multiple point-type step differential temp type detectors 6, locating module 7;
The multiple Smoke Sensor 2 is used to measure the smokescope in respective position range respectively, and is obtained measured Data send central processing module 1 to;
The alarm module 3 includes buzzer and SIM card, after central processing module 1 sends alarm command, will be reported by SIM card Alert information and specific alert locations are sent to the assigned number pre-set;
The memory module 4 is divided for dynamic storage cell and non-volatile memory cells, when detect fire occurs when data It is saved in non-volatile memory cells, is stored data into when being not detected by fire in dynamic storage cell;
The photographing module 5 includes infrared pick-up head and monitoring camera, and infrared pick-up hair goes out infrared radiation object, Diffusing reflection occurs for infrared ray, and the camera that is monitored receives, so as to form video image.
The central processing module 1 passes through electric signal and multiple Smoke Sensors 2 and multiple point-type step differential temp type detectors 6 It is connected, only when the smokescope that Smoke Sensor 2 measures exceedes preset value, while point-type step differential temp type detector 6 is surveyed The temperature rate-of-rise measured can just send alarm command also above preset value, central processing module 1, otherwise continue to monitor.
The central processing module 1 includes DSP, arm processor, A/D converter, electricity accumulating unit, graphics processing unit, nothing Line transmitter unit and communication unit.
Infrared camera in the multiple Smoke Sensor 2 and photographing module 5 is equally spaced in the area monitored In domain.
The locating module 7 realizes positioning by detecting the intensity of Wi-Fi signal with reference to KNN algorithms, and in centre When reason module 1 sends alarm command, positional information is sent to assigned number by alarm module 3 by the form of short message.
The memory module 4 is divided for overlayable dynamic storage cell and non-volatile memory cells, when central processing mould , can be by the smokescope data that in-site measurement obtains and the video image storage that photographing module 5 obtains after block 1 sends alarm command Data and video when uploading into non-volatile memory cells and simultaneously and be saved in high in the clouds, and not sending alarm command can be followed It is stored in dynamic storage cell to ring cover, when resulting video image is not clear enough, the figure in central processing module 1 As processing module can carry out image enhancement processing.
The localization method of locating module 7, first pass through Wi-Fi Info radio network informations and obtain near current location RSSI received signal strength indicator device information, local AP undetermined signal intensity and physical address are measured, recycle machine Learn related matching algorithm, measured data is contrasted with the data stored in a program, searches one group and measurement allusion quotation The data of type matching, the particular location of tested point is estimated using KNN algorithms.
The present invention operation principle be:
This alarm is applied to the places such as each factory, market, school, residential block.Central processing module 1 passes through electric signal and smog Sensor 2, alarm module 3, memory module 4, photographing module 5, point-type step differential temp type detector 6, locating module 7 are connected.To cigarette Mist sensor 2 and point-type step differential temp type detector 6 set a concentration threshold and temperature rate-of-rise threshold value respectively, when detected value is same When being more than or equal to the two threshold values, central processing module 1 sends alarm command, while by the smokescope and video at scene Image storage is into the non-volatile memory cells in memory module 4 and synchronized upload is to high in the clouds, hereafter in real time by live feelings Condition preserves until the data detected are less than the threshold value set.After sending alarm command, locating module will be first according to each The data-evaluation such as the position of Smoke Sensor and smokescope, rate of rise in temperature goes out point of origin position, then by particular location Assigned number is sent in the form of short message together with warning message, facilitates relevant staff rapidly to organize to rescue.Positioning Module is to first pass through Wi-Fi Info to obtain RSSI information near current location, using the Wi-Fi Manager class libraries increased income, Facilitate application program and Wi-Fi connection, all AP focuses in the range of equipment communication can pass through packaged Wi-Fi scannings Function scanning is arrived, while can also show SSID, MAC Address, IP and the RSSI of quantified processing of access point.Recycle machine Learn related matching algorithm, measured data is contrasted with the data stored in a program, searches one group and measurement allusion quotation The data of type matching.RSSI from j-th AP is received by tested point and i-th of reference point is received from j-th of AP RSSI value calculate Euclidean distance dis.Each reference point has two parameters, and first is in a certain reception in the position Wi-Fi1 signal intensity, second is signal intensity in another reception Wi-Fi2 in the position.Then KNN algorithms are utilized Select K reference point from small to large in dis, calculate the seat of tested point using averaging method by reference to the actual coordinate of point Mark, and then estimate the position of tested point.The Thoughts of KNN algorithms are:Training sample set is obtained by pretreatment, and will instruction Practice sample set to be saved in memory module, and each data have a label in sample set, in sample set each data with it is affiliated Corresponding relation of classifying is known, after inputting the test sample data of no label, according to the Euclidean distance dis degree being previously set Amount calculates each test sample and the distance of training sample, selects K closest training samples, is then based on ballot side Test sample labeled as the most classification of occurrence number in K training sample, is extracted the most like data of feature in sample set by formula Tag along sort.
The beneficial effects of the invention are as follows:
1st, Smoke Sensor used herein and point-type step differential temp type detector monitor simultaneously, only reach both default simultaneously It during value, can just start alarm module, double shield, improve the accuracy of alarm;
2nd, the particular location and warning message of fire are sent to assigned number in the very first time of alarm, are easy to related work people Member's efficiently tissue rescue.This alarm has electricity accumulating unit to can fully ensure that its normal use, and graphics processing unit can be with The video image inadequate to definition carries out image procossing;
3rd, the smokescope of scene of fire and video image are preserved, beneficial to analysis the reason for fire occurs afterwards and Investigation.Power storage module in central processing module has fully ensured that the normal use of in case of emergency alarm;
4th, different places can be directed to and environment uses the sensor of different types.The theory of KNN algorithms is simple, realizes and holds Easily.
Brief description of the drawings
Fig. 1 is the overall structure block diagram of the present invention;
Fig. 2 is the flow chart of the KNN algorithms of the present invention;
Fig. 3 is the alarm flow figure of the present invention.
Each label in Fig. 1:1- central processing modules;2- smoke alarms;3- alarm modules;4- memory modules;5- is imaged Module;6- point-type step differential temp type detectors;7- locating modules.
Embodiment
Below in conjunction with the accompanying drawings and specific embodiment, the invention will be further described.
Embodiment 1:As Figure 1-3, a kind of fire-alarm of combination KNN algorithms, including central processing module 1, cigarette Mist sensor 2, alarm module 3, memory module 4, photographing module 5, point-type step differential temp type detector 6, locating module 7;
The central processing module module 1 connects multiple Smoke Sensors 2, alarm module 3 by electric signal, memory module 4, taken the photograph As module 5, multiple point-type step differential temp type detectors 6, locating module 7;
The multiple Smoke Sensor 2 is used to measure the smokescope in respective position range respectively, and is obtained measured Data send central processing module 1 to;
The alarm module 3 includes buzzer and SIM card, after central processing module 1 sends alarm command, will be reported by SIM card Alert information and specific alert locations are sent to the assigned number pre-set;
The memory module 4 is divided for dynamic storage cell and non-volatile memory cells, when detect fire occurs when data It is saved in non-volatile memory cells, is stored data into when being not detected by fire in dynamic storage cell;
The photographing module 5 includes infrared pick-up head and monitoring camera, and infrared pick-up hair goes out infrared radiation object, Diffusing reflection occurs for infrared ray, and the camera that is monitored receives, so as to form video image.
Preferably, the central processing module 1 passes through electric signal and multiple Smoke Sensors 2 and multiple point-type step differential temp types Detector 6 is connected, only when the smokescope that Smoke Sensor 2 measures exceedes preset value, while the detection of point-type step differential temp type Temperature rate-of-rise measured by device 6 can just send alarm command, otherwise continue also above preset value, central processing module 1 Monitoring.
Preferably, the central processing module 1 includes DSP, arm processor, A/D converter, electricity accumulating unit, image procossing Unit, wireless transmitting unit and communication unit.
Preferably, the infrared camera in the multiple Smoke Sensor 2 and photographing module 5, which is equally spaced, is being supervised In the region of control.
Preferably, the locating module 7 realizes positioning by detecting the intensity of Wi-Fi signal with reference to KNN algorithms, and When central processing module 1 sends alarm command, positional information is sent to specified number by alarm module 3 by the form of short message Code.
Preferably, the memory module 4 is divided for overlayable dynamic storage cell and non-volatile memory cells, works as center , can be by the smokescope data that in-site measurement obtains and the video figure that photographing module 5 obtains after processing module 1 sends alarm command Data and video when uploading into non-volatile memory cells and simultaneously as storage and is saved in high in the clouds, and not sending alarm command Just it is stored in dynamic storage cell to recyclable covering, when resulting video image is not clear enough, central processing module 1 In image processing module can carry out image enhancement processing.
Preferably, the localization method of locating module 7, it is attached to first pass through Wi-Fi Info radio network informations acquisition current location Near RSSI received signal strength indicator device information, local AP undetermined signal intensity and physical address are measured, recycled The related matching algorithm of machine learning, measured data is contrasted with the data stored in a program, searches one group and survey The data of amount typical case's matching, the particular location of tested point is estimated using KNN algorithms.
The specific embodiment of the present invention is explained in detail above in conjunction with accompanying drawing, but the present invention is not limited to above-mentioned reality Example is applied, can also be on the premise of present inventive concept not be departed from those of ordinary skill in the art's possessed knowledge Various changes can be made.

Claims (7)

  1. A kind of 1. fire-alarm of combination KNN algorithms, it is characterised in that:Including central processing module(1), Smoke Sensor (2), alarm module(3), memory module(4), photographing module(5), point-type step differential temp type detector(6), locating module(7);
    The central processing module module(1)Multiple Smoke Sensors are connected by electric signal(2), alarm module(3), storage mould Block(4), photographing module(5), multiple point-type step differential temp type detectors(6), locating module(7);
    The multiple Smoke Sensor(2)It is used to measure the smokescope in respective position range respectively, and will be measured To data send central processing module to(1);
    The alarm module(3)Including buzzer and SIM card, central processing module(1)After sending alarm command, pass through SIM card Warning message and specific alert locations are sent to the assigned number pre-set;
    The memory module(4)It is divided into dynamic storage cell and non-volatile memory cells, when detecting generation fire number According to being saved in non-volatile memory cells, stored data into when being not detected by fire in dynamic storage cell;
    The photographing module(5)Including infrared pick-up head and monitoring camera, infrared pick-up hair goes out infrared radiation thing Diffusing reflection occurs for body, infrared ray, and the camera that is monitored receives, so as to form video image.
  2. 2. the fire-alarm of combination KNN algorithms according to claim 1, it is characterised in that:The central processing module (1)Pass through electric signal and multiple Smoke Sensors(2)And multiple point-type step differential temp type detectors(6)It is connected, only works as smog Sensor(2)The smokescope measured exceedes preset value, while point-type step differential temp type detector(6)Measured temperature rises Speed is also above preset value, central processing module(1)Alarm command can be just sent, otherwise continues to monitor.
  3. 3. the fire-alarm of combination KNN algorithms according to claim 1, it is characterised in that:The central processing module (1)Including DSP, arm processor, A/D converter, electricity accumulating unit, graphics processing unit, wireless transmitting unit and communication unit.
  4. 4. the fire-alarm of combination KNN algorithms according to claim 1, it is characterised in that:The multiple smog sensing Device(2)And photographing module(5)In infrared camera be equally spaced in the region monitored.
  5. 5. the fire-alarm of combination KNN algorithms according to claim 2, it is characterised in that:The locating module(7)It is logical The intensity of detection Wi-Fi signal is crossed, positioning is realized with reference to KNN algorithms, and in central processing module(1)Send alarm command When, alarm module(3)Positional information is sent to assigned number by the form of short message.
  6. 6. the fire-alarm of combination KNN algorithms according to claim 3, it is characterised in that:The memory module(4)Point For overlayable dynamic storage cell and non-volatile memory cells, work as central processing module(1)After sending alarm command, it can incite somebody to action The smokescope data and photographing module that in-site measurement obtains(5)Obtained video image storage is into non-volatile memory cells And upload simultaneously and be saved in high in the clouds, and the data and video when not sending alarm command are stored in dynamic with being just recycled covering and deposited In storage unit.
  7. 7. the fire-alarm of combination KNN algorithms according to claim 3, it is characterised in that:First pass through Wi-Fi Info Radio network information obtains the RSSI received signal strength indicator device information near current location, measures local AP's undetermined Signal intensity and physical address, the related matching algorithm of machine learning is recycled, to number of the measured data with storage in a program According to being contrasted, the data of one group and measurement typical case's matching are searched, the particular location of tested point is estimated using KNN algorithms.
CN201710630768.0A 2017-07-28 2017-07-28 A kind of fire-alarm of combination KNN algorithms Pending CN107358778A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710630768.0A CN107358778A (en) 2017-07-28 2017-07-28 A kind of fire-alarm of combination KNN algorithms

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710630768.0A CN107358778A (en) 2017-07-28 2017-07-28 A kind of fire-alarm of combination KNN algorithms

Publications (1)

Publication Number Publication Date
CN107358778A true CN107358778A (en) 2017-11-17

Family

ID=60285678

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710630768.0A Pending CN107358778A (en) 2017-07-28 2017-07-28 A kind of fire-alarm of combination KNN algorithms

Country Status (1)

Country Link
CN (1) CN107358778A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108764399A (en) * 2018-05-22 2018-11-06 东南大学 A kind of RFID tag sorting technique and device based on kNN
CN109003354A (en) * 2018-05-25 2018-12-14 淮南万泰电气有限公司 A kind of substation's wisdom environmental management system
CN109272696A (en) * 2018-08-27 2019-01-25 出门问问信息科技有限公司 Electronic equipment
CN109300276A (en) * 2018-07-27 2019-02-01 昆明理工大学 A kind of car inside abnormity early warning method based on Fusion
CN109443421A (en) * 2018-09-13 2019-03-08 东南大学 A kind of NB-IoT wireless humiture sensor
CN110619730A (en) * 2018-06-20 2019-12-27 能美防灾株式会社 Fire detector

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102385785A (en) * 2011-11-07 2012-03-21 河南理工大学 Electrical fire accident pre-warning and alarming device for low-voltage switch and low-voltage distribution box
JP2012088752A (en) * 2010-10-15 2012-05-10 Yazaki Corp Fire alarm and mobile phone
CN202715165U (en) * 2012-02-14 2013-02-06 王子麟 Intelligent smoke differential temperature fire extinguishing sensor
CN103049976A (en) * 2012-11-30 2013-04-17 浙江工商大学 Multi-parameter fire detection node based on wireless sensor network
CN105521580A (en) * 2014-10-24 2016-04-27 无锡蓝阳谐波科技有限公司 Intelligent fire extinguishing system based on internet of things technology
CN205582185U (en) * 2016-03-01 2016-09-14 上海杰东系统工程控制有限公司 Long -range fire alarm device based on GSM network
CN106448021A (en) * 2016-10-20 2017-02-22 安徽天枢信息科技有限公司 Linkage smoke alarm system for civil air defense project
CN106491322A (en) * 2016-12-14 2017-03-15 西安邮电大学 Blind-man crutch control system and method based on OpenCV image recognitions
CN106781173A (en) * 2015-11-22 2017-05-31 天津安捷公共设施服务有限公司 Intelligent fire warning device

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012088752A (en) * 2010-10-15 2012-05-10 Yazaki Corp Fire alarm and mobile phone
CN102385785A (en) * 2011-11-07 2012-03-21 河南理工大学 Electrical fire accident pre-warning and alarming device for low-voltage switch and low-voltage distribution box
CN202715165U (en) * 2012-02-14 2013-02-06 王子麟 Intelligent smoke differential temperature fire extinguishing sensor
CN103049976A (en) * 2012-11-30 2013-04-17 浙江工商大学 Multi-parameter fire detection node based on wireless sensor network
CN105521580A (en) * 2014-10-24 2016-04-27 无锡蓝阳谐波科技有限公司 Intelligent fire extinguishing system based on internet of things technology
CN106781173A (en) * 2015-11-22 2017-05-31 天津安捷公共设施服务有限公司 Intelligent fire warning device
CN205582185U (en) * 2016-03-01 2016-09-14 上海杰东系统工程控制有限公司 Long -range fire alarm device based on GSM network
CN106448021A (en) * 2016-10-20 2017-02-22 安徽天枢信息科技有限公司 Linkage smoke alarm system for civil air defense project
CN106491322A (en) * 2016-12-14 2017-03-15 西安邮电大学 Blind-man crutch control system and method based on OpenCV image recognitions

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
邓中亮等: "《室内外无线定位与导航》", 31 December 2013, 北京邮电大学出版社 *

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108764399A (en) * 2018-05-22 2018-11-06 东南大学 A kind of RFID tag sorting technique and device based on kNN
CN108764399B (en) * 2018-05-22 2021-03-19 东南大学 kNN-based RFID tag classification method and device
CN109003354A (en) * 2018-05-25 2018-12-14 淮南万泰电气有限公司 A kind of substation's wisdom environmental management system
CN109003354B (en) * 2018-05-25 2021-05-04 淮南万泰电气有限公司 Intelligent environment management system for transformer substation
CN110619730B (en) * 2018-06-20 2021-07-16 能美防灾株式会社 Fire detector
CN110619730A (en) * 2018-06-20 2019-12-27 能美防灾株式会社 Fire detector
CN109300276A (en) * 2018-07-27 2019-02-01 昆明理工大学 A kind of car inside abnormity early warning method based on Fusion
CN109272696A (en) * 2018-08-27 2019-01-25 出门问问信息科技有限公司 Electronic equipment
CN109443421A (en) * 2018-09-13 2019-03-08 东南大学 A kind of NB-IoT wireless humiture sensor

Similar Documents

Publication Publication Date Title
CN107358778A (en) A kind of fire-alarm of combination KNN algorithms
Tabar et al. Smart home care network using sensor fusion and distributed vision-based reasoning
CN102282594B (en) System and method for detection of EAS marker shielding
US7295106B1 (en) Systems and methods for classifying objects within a monitored zone using multiple surveillance devices
JP2006311111A (en) Position sensing system and method for sensing position
CN109765539A (en) Indoor user behavior monitoring method and apparatus, electrical equipment and home furnishing monitoring system
CN108389351A (en) Tag match, fence border control method, apparatus and storage medium
KR101553000B1 (en) Video surveillance system and method using beacon, and object managing apparatus therefor
CN106448023A (en) Fire disaster smoke alarm with storage function
CN105894703A (en) Intelligent monitoring method, device and system based on WiFi
CN104796204B (en) A kind of metal based on wireless network carries detection method
CN105575034A (en) Image processing and analysis method of double-waveband forest fireproof intelligent monitoring software
CN107103300A (en) One kind is left the post detection method and system
CN108303673A (en) A kind of UWB 3 D positioning systems based on video auxiliary positioning
CN109740411A (en) Intelligent monitor system, monitoring method based on recognition of face and quickly go out alarm method
CN111508194A (en) Intelligent building monitoring system based on big data
WO2018232849A1 (en) Method and system for monitoring workshop environment based on internet of things
CN105957169B (en) A kind of detection method based on ibeacon technologies, apparatus and system
CN105824040A (en) System and method of automatically detecting and alarming tap water radiation pollution
US8441349B1 (en) Change detection in a monitored environment
CN206039759U (en) High -voltage testing human protection system
Dibitonto et al. Fusion of radio and video localization for people tracking
KR101679597B1 (en) System for managing objects and method thereof
CN106502115A (en) A kind of intelligent home control system and method based on GPS technology
CN209433517U (en) It is a kind of based on more flame images and the fire identification warning device for combining criterion

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: 20171117