CN102902954A - Pedestrian detection system and method based on internet-of-things intelligent household security gateway - Google Patents
Pedestrian detection system and method based on internet-of-things intelligent household security gateway Download PDFInfo
- Publication number
- CN102902954A CN102902954A CN201210312444XA CN201210312444A CN102902954A CN 102902954 A CN102902954 A CN 102902954A CN 201210312444X A CN201210312444X A CN 201210312444XA CN 201210312444 A CN201210312444 A CN 201210312444A CN 102902954 A CN102902954 A CN 102902954A
- Authority
- CN
- China
- Prior art keywords
- internet
- pedestrian
- things
- module
- interface
- 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
Images
Abstract
The invention discloses a pedestrian detection system and a pedestrian detection method based on an internet-of-things intelligent household security gateway, belonging to the field of internet-of-things information transmission and management. The method comprises the steps of: training a support vector machine (SVM) classifier in an offline mode according to a target sample to be detected; performing feature extraction on a video frame acquired in a security gateway system to obtain a feature vector; detecting the feature vector by utilizing the SVM classifier, and judging whether pedestrians occur in the video frame through a discrimination function; if so, positioning the pedestrians through a positioning frame, and judging the identity of the positioned pedestrians. According to the method, the intelligent household security gateway has accurate pedestrian detection and identification capacity on the original stable and practical basis, the false alarm rate of the security gateway system is reduced, the detection rate of the system is improved, and the reliability of the system is enhanced.
Description
Technical field
The present invention relates to Internet of Things communication and management domain, relate in particular to a kind of pedestrian detecting system and method for the Smart Home safety-protection gateway based on Internet of Things.
Background technology
Constantly bringing forth new ideas of technology of Internet of things, driven internet of things equipment variation, make its more perfect function.Along with the demand of technology of Internet of things in the wired home security protection constantly enlarges, although hardware device and software systems constantly improve, but still there is the higher problem of rate of false alarm of monitoring the pedestrian.
Summary of the invention
The object of the invention is to overcome defective and the deficiency of prior art, a kind of pedestrian detecting system and method for the Smart Home safety-protection gateway based on Internet of Things are provided, have solved current technology of Internet of things high problem of pedestrian detection rate of false alarm in smart home security system.
For achieving the above object, the present invention is achieved through the following technical solutions:
A kind of pedestrian detection method of the Smart Home safety-protection gateway based on Internet of Things, described method comprises the steps:
According to target sample to be measured, off-line training svm classifier device;
In real time the frame of video of safety-protection gateway system acquisition is carried out feature extraction and obtain proper vector;
Utilize described svm classifier device to detect described proper vector, judge by discriminant function whether frame of video has the pedestrian;
If any, pedestrian's identity after then carrying out the pedestrian location and judge the location by posting.
Described step of carrying out pedestrian location by posting further comprises, when the posting that detects the pedestrian exceeds the threshold value of setting, by face recognition technology people's face is positioned, and by mating with family's face database of setting up in advance, judge the identity of the pedestrian after locating.
Described family's face database of setting up in advance obtains by Hidden Markov Model (HMM) (HMM) training or obtains by specific neural network model simulation.
Describedly in real time the frame of video of safety-protection gateway system acquisition is carried out the step that feature extraction obtains proper vector and comprise, utilize Harr feature and extension feature thereof to extract pedestrian's gray feature, and utilize HOG operator extraction pedestrian contour feature.
The present invention also discloses a kind of pedestrian detecting system of the Smart Home safety-protection gateway based on Internet of Things, and described system comprises Internet of Things wireless energy control units, expanding element and terminal signaling collecting unit,
Described terminal signaling collecting unit gathers for the video image to the security protection zone and described transmission of video images is arrived the Internet of Things wireless energy control units;
Described Internet of Things wireless energy control units is used in real time the frame of video that gathers being closed in security protection net system and carries out feature extraction acquisition proper vector, utilizes the svm classifier device that trains to detect described proper vector, judges by discriminant function whether frame of video has the pedestrian; If any, pedestrian's identity after then carrying out the pedestrian location and judge the location by posting;
Described expanding element is used for each functional interface of Internet of Things wireless energy control units is expanded, carry out information interaction by each functional interface after the described expansion and long distance wireless node, and the information after the processing of Internet of Things wireless energy control units is fed back to the terminal signaling collecting unit.
Described Internet of Things wireless energy control units comprises core processor, memory modules, outer memory module and clock module, described core processor is connected with outer memory module with memory modules, and the pedestrian to the security protection zone detects by svm classifier device and Hidden Markov Model (HMM).
Described terminal signaling collecting unit comprises front end sensors.
Described expanding element comprises camera module, audio-frequency module, GSM/GPRS module, WIFI module, SD card interface, OTG interface, USB interface, RS-232 interface, Ethernet interface, display, keystroke interface, ZIGBEE module, bluetooth module, infrared module, alarm module and radio-frequency module.
Radio-frequency module or ZIGBEE module and the Internet of Things wireless energy control units of described terminal signaling collecting unit by 433Mhz carried out information interaction.
Described Internet of Things wireless energy control units is carried out information interaction by GSM/GPRS module or WIFI module or Ethernet interface set of data signals composite signal bag and remote monitoring node and the management node after with all processing of sending from the terminal signaling collecting unit.
Technical scheme of the present invention, Internet of Things intelligent security guard gateway with pedestrian detection and face identification functions is provided, can guarantee that the intelligent security guard gateway system is on original stable, practical basis, has the more accurately ability of pedestrian detection and identification, reduced the false alarm rate of safety-protection gateway system, improve the verification and measurement ratio of system, strengthened the reliability of system.
Description of drawings
The pedestrian detecting system structural drawing based on the Smart Home safety-protection gateway of Internet of Things that Fig. 1 provides for the specific embodiment of the invention;
The pedestrian detection method process flow diagram based on the Smart Home safety-protection gateway of Internet of Things that Fig. 2 provides for the specific embodiment of the invention;
The design sketch based on the pedestrian detection method of the Smart Home safety-protection gateway of Internet of Things that Fig. 3 provides for the specific embodiment of the invention.
Embodiment
The invention will be further described below in conjunction with drawings and Examples.
The pedestrian detecting system structural drawing based on the Smart Home safety-protection gateway of Internet of Things that Fig. 1 provides for the specific embodiment of the invention.As shown in Figure 1, described system adopts layering hub-and-spoke network topology structure, this system comprises Internet of Things wireless energy control units 101, expanding element 102 and terminal signaling collecting unit 103, and described terminal signaling collecting unit 103 gathers for the video image to the security protection zone and described transmission of video images is arrived Internet of Things wireless energy control units 101; Described Internet of Things wireless energy control units 101 is used in real time the frame of video of safety-protection gateway system acquisition being carried out feature extraction and obtains proper vector, utilizes the svm classifier device that trains to detect described proper vector, judges by discriminant function whether frame of video has the pedestrian; If any, pedestrian's identity after then carrying out the pedestrian location and judge the location by posting; Described expanding element 102 is used for each functional interface of Internet of Things wireless energy control units is expanded, carry out information interaction by each functional interface after the described expansion and remote monitoring node and management node, and the information after the Internet of Things wireless energy control units processed feeds back to the terminal signaling collecting unit.
Described Internet of Things wireless energy control units 101 comprises core processor 1011, memory modules 1012, outer memory module 1013 and clock module 1014, described core processor is connected with outer memory module with memory modules, and the pedestrian to the security protection zone detects by svm classifier device and Hidden Markov Model (HMM) (HMM).Described terminal signaling collecting unit 103 comprises front end sensors 1031; Described expanding element comprises camera module, audio-frequency module, GSM/GPRS module, WIFI module, display apparatus module, keystroke interface, ZIGBEE module, bluetooth module, infrared module, radio-frequency module, SD card interface, OTG interface, USB interface, RS-232 interface and Ethernet interface etc.Wherein, camera module can gather the pedestrian and the unusual personnel that enter within doors in a defence area; Propaganda directed to communicate in audio-frequency module realization scene; GSM/GPRS module realization front end node abnormal information is informed the transmitting-receiving of user and multimedia message; The SD card interface can access jumbo SD card (such as the SD card of 4G, 8G etc.), is used for the dynamic data of storage system; USB interface can realize the unloading of data; WIFI module and ethernet module can be realized the remote transmission of information etc.The driver of modules all realizes in embedded OS, and application program only needs calling interface just can realize the normal operation of module.
System Working Principle is as follows: the radio-frequency module of main control system by core processor expansion and the realization of Zigbee module gather the information of the radio node that sends from each terminal signaling collecting unit and process, and utilize the mode of note and multimedia message to notify user mobile phone and receive the note order by gsm module or GPRS module and carry out subsequent treatment, thereby realize the Internet of Things controlled in wireless.The terminal signaling collecting unit comprises front end sensors, and front end sensors has 433M radio frequency and ZigBee module.Front end sensors, also claim detector (radio node), by selecting a kind of communication (such as 433Mhz radio-frequency module or ZigBee module) that image data is wirelessly transmitted to the Internet of Things wireless energy control units, by the Internet of Things wireless energy control units to data analysis, process, judgement makes decisions, result is also fed back to front end sensors by identical wireless transmission method, realize remote wireless monitoring, simultaneously, the Internet of Things wireless energy control units is processed the data of all the sensors collection by analysis, Weighted Fusion forms information, by the information interaction that realizes remote monitoring node and management node based on internet internet and the GSM mobile communications network of WIFI.Management node is often referred to user's PC or cell management center, is responsible for the user is connected to the network.The user only need just can realize in the IP address of internet browser input management node the control to management node, realizes the configuration of whole network, sets relevant monitoring task or the monitor message of checking all the sensors.
In the present embodiment, the S3C2440A of Internet of Things wireless energy control units employing Samsung or ARM9 embedded chip are as core processor, use the SDRAM of 64M byte as the memory bar of system's operation, the NAND FALSH of 128M byte reaches as high as 400MHz as the storage medium of system software after system's operation dominant frequency frequency multiplication; Expanding element comprises: OTG interface, USB interface, GSM/GPRS interface, RS-232 interface, Ethernet interface, SD card interface, display interface, bus expansion interface, keystroke interface, power input interface, audio output interface and camera module, ZIGBEE module, bluetooth module, WIFI module, gsm module, infrared module and backup battery.
Whole system mainly realizes the safety-protection system linkage work, and the data transmission of the induction of front end various kinds of sensors, sensor and core processor, core processor and user's wireless information interaction and user are to the functions such as controlled in wireless of system.Adopt technical scheme of the present invention, can keep total system to stablize, be convenient to expand, can be conducive to the realization of Internet of Things intelligent wireless safety-protection system function.
The pedestrian detection method process flow diagram based on the Smart Home safety-protection gateway of Internet of Things that Fig. 2 provides for the specific embodiment of the invention.As shown in Figure 2, the method comprises the steps:
S1: according to target sample to be measured, off-line training svm classifier device;
The sorter off-line training creates the training objective sample, and training sample is divided into positive example sample and negative data, and wherein the positive example sample refers to target sample to be checked, and negative data refers to other any image.For positive sample, common way is first all positive samples to be cut, and size is done regular (namely zoom to and specify size).This programme adopts some sections of actual monitored videos, and every section video comprises some two field pictures, comprising pedestrian's image and background image.In each two field picture, select the pedestrian by manual mode frame, as the positive sample of training.
S2: in real time the frame of video of safety-protection gateway system acquisition is carried out feature extraction and obtain proper vector;
Describedly in real time the frame of video of safety-protection gateway system acquisition is carried out the step that feature extraction obtains proper vector and comprise, utilize Harr feature and extension feature thereof to extract pedestrian's gray feature, and utilize HOG operator extraction pedestrian contour feature.Can realize by prior art for feature extraction.
Harr is characterized as a kind of simple rectangular characteristic, and what its value was black rectangle and white rectangle in the gray-scale value sum in zone corresponding to image subwindow is poor, the grey scale change of reflection image local.The Harr feature is divided three classes: edge feature, linear feature, central feature and diagonal line feature are combined into feature templates.Determining that the quantity of Harr feature after the characteristic formp just depends on the size of training sample image matrix, feature templates is placed arbitrarily in subwindow, and a kind of form is called a kind of feature, and the feature of finding out all subwindows is the basis of carrying out the weak typing training.
For the impact on pedestrian detection such as the outward appearance of eliminating the people and other environmental factors, adopt histograms of oriented gradients (HOG), add up first, more a plurality of fritters are merged into a large zone, by the direction histogram of gradients being carried out the computings such as normalization, improve the robustness of algorithm at last.
The HOG feature extraction:
Standardization gamma space and color space: the furnishing image standardizes;
Compute gradient: the one dimension gradient of computed image.The differentiate operation not only can be caught profile, and the shadow and some texture informations can also further as be used up according to effect;
Cell gradient projection: for the local figure zone provides a coding, can keep simultaneously the posture of human object in the image and the hyposensitiveness perception of outward appearance.Graphical window is divided into several zonules, these zones are called as " cell ", then one dimension histogram of gradients or the edge direction with all pixels in each cell is added to wherein, the direction histogram that this is basic is mapped on the fixing angle at last, has just formed final feature.
Homogenization histogram of gradients in the piece: contrast normalization, can further compress illumination, Shadow and edge.
Collect the HOG feature: all overlapping pieces in the detection window are carried out the collection of HOG feature, and they are combined into final proper vector classification use.
S3: utilize described svm classifier device to detect described proper vector, judge by discriminant function whether frame of video has the pedestrian;
S4: if any, then carry out the pedestrian location by posting.
Wherein, the step of carrying out the pedestrian location by posting further comprises, when the pedestrian zone that detects exceeds the threshold value of posting setting, by face recognition technology people's face is positioned, and by mating with family's face database of setting up in advance, judge the identity of the pedestrian after locating.
Described family's face database of setting up in advance obtains by Hidden Markov Model (HMM) (HMM) training or obtains by specific neural network model simulation.
The design sketch based on the pedestrian detection method of the Smart Home safety-protection gateway of Internet of Things that Fig. 3 provides for the specific embodiment of the invention.As shown in Figure 3, this video comprises 232 frames, the target less, and when target runs into other pedestrians in traveling process, and target is not blocked, and under the impact of trees inverted image, automobile, utilizes the particle filter of color histogram can realize correct tracking.
Adopt technical scheme of the present invention, can guarantee that the Internet of Things intelligent safety and defence system is on original stable, practical basis, has the more accurately ability of pedestrian detection and identification, driven the application in wired home safety-protection gateway system of pattern classification and recognition technology, simultaneously, the introducing of detection, tracking, recognizer has reduced the false alarm rate of safety-protection gateway system, improve the verification and measurement ratio of system, strengthened the reliability of system.
Above-mentioned only is preferred embodiment of the present invention and institute's application technology principle, anyly is familiar with those skilled in the art in the technical scope that the present invention discloses, and the variation that can expect easily or replacement all should be encompassed in protection scope of the present invention.
Claims (10)
1. pedestrian detection method based on the Smart Home safety-protection gateway of Internet of Things, described method comprises the steps:
According to target sample to be measured, off-line training svm classifier device;
In real time the frame of video of safety-protection gateway system acquisition is carried out feature extraction and obtain proper vector;
Utilize described svm classifier device to detect described proper vector, judge by discriminant function whether frame of video has the pedestrian;
If any, pedestrian's identity after then carrying out the pedestrian location and judge the location by posting.
2. the pedestrian detection method of the Smart Home safety-protection gateway based on Internet of Things according to claim 1, it is characterized in that, described step of carrying out pedestrian location by posting further comprises, when the posting that detects the pedestrian exceeds the threshold value of setting, by face recognition technology people's face is positioned, and by mating with family's face database of setting up in advance, judge the identity of the pedestrian after locating.
3. the pedestrian detection method of the Smart Home safety-protection gateway based on Internet of Things according to claim 2, it is characterized in that, described family's face database of setting up in advance obtains by Hidden Markov Model (HMM) (HMM) training or obtains by specific neural network model simulation.
4. the pedestrian detection method of the Smart Home safety-protection gateway based on Internet of Things according to claim 1 and 2, it is characterized in that, describedly in real time the frame of video of safety-protection gateway system acquisition is carried out the step that feature extraction obtains proper vector and comprise, utilize Harr feature and extension feature thereof to extract pedestrian's gray feature, and utilize HOG operator extraction pedestrian contour feature.
5. the pedestrian detecting system based on the Smart Home safety-protection gateway of Internet of Things is characterized in that, described system comprises Internet of Things wireless energy control units, expanding element and terminal signaling collecting unit,
Described terminal signaling collecting unit gathers for the video image to the security protection zone and described transmission of video images is arrived the Internet of Things wireless energy control units;
Described Internet of Things wireless energy control units is used in real time the frame of video of safety-protection gateway system acquisition being carried out feature extraction and obtains proper vector, utilizes the svm classifier device that trains to detect described proper vector, judges by discriminant function whether frame of video has the pedestrian; If any, pedestrian's identity after then carrying out the pedestrian location and judge the location by posting;
Described expanding element is used for each functional interface of Internet of Things wireless energy control units is expanded, carry out information interaction by each functional interface after the described expansion and long distance wireless node, and the information after the processing of Internet of Things wireless energy control units is fed back to the terminal signaling collecting unit.
6. the pedestrian detecting system of the Smart Home safety-protection gateway based on Internet of Things according to claim 5, it is characterized in that, described Internet of Things wireless energy control units comprises core processor, memory modules, outer memory module and clock module, described core processor is connected with outer memory module with memory modules, and the pedestrian to the security protection zone detects by svm classifier device and Hidden Markov Model (HMM) (HMM).
7. the Smart Home safety-protection gateway system based on Internet of Things according to claim 5 is characterized in that, described terminal signaling collecting unit comprises front end sensors.
8. the pedestrian detecting system of the Smart Home safety-protection gateway based on Internet of Things according to claim 5, it is characterized in that, described expanding element comprises camera module, audio-frequency module, GSM/GPRS module, WIFI module, SD card interface, OTG interface, USB interface, RS-232 interface, Ethernet interface, display interface device, keystroke interface, ZIGBEE module, bluetooth module, infrared module, alarm module and radio-frequency module.
9. the Smart Home safety-protection gateway system based on Internet of Things according to claim 5 is characterized in that, radio-frequency module or ZIGBEE module and the Internet of Things wireless energy control units of described terminal signaling collecting unit by 433Mhz carried out information interaction.
10. the Smart Home safety-protection gateway system based on Internet of Things according to claim 8, it is characterized in that, described Internet of Things wireless energy control units is carried out information interaction by GSM/GPRS module or WIFI module or Ethernet interface set of data signals composite signal bag and remote monitoring node and the management node after with all processing of sending from the terminal signaling collecting unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210312444XA CN102902954A (en) | 2012-08-29 | 2012-08-29 | Pedestrian detection system and method based on internet-of-things intelligent household security gateway |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210312444XA CN102902954A (en) | 2012-08-29 | 2012-08-29 | Pedestrian detection system and method based on internet-of-things intelligent household security gateway |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102902954A true CN102902954A (en) | 2013-01-30 |
Family
ID=47575176
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210312444XA Pending CN102902954A (en) | 2012-08-29 | 2012-08-29 | Pedestrian detection system and method based on internet-of-things intelligent household security gateway |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102902954A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103441890A (en) * | 2013-08-18 | 2013-12-11 | 安徽斯玛特物联网科技有限公司 | Performance testing method for internet of things |
| CN104216294A (en) * | 2014-09-16 | 2014-12-17 | 黄河科技学院 | Intelligent household control system and method |
| CN104905770A (en) * | 2014-03-13 | 2015-09-16 | 南京理工大学 | Human health state detection system based on internet of things and SVM analysis |
| CN106597363A (en) * | 2016-10-27 | 2017-04-26 | 中国传媒大学 | Pedestrian location method in indoor WLAN environment |
| CN107563275A (en) * | 2017-07-11 | 2018-01-09 | 青岛理工大学 | A kind of face identification method combined with BIM |
| CN108334840A (en) * | 2018-02-01 | 2018-07-27 | 福州大学 | Pedestrian detection method based on deep neural network under traffic environment |
| CN109118703A (en) * | 2018-07-19 | 2019-01-01 | 苏州菲丽丝智能科技有限公司 | A kind of intelligent household security system and its working method |
| CN109450942A (en) * | 2018-12-25 | 2019-03-08 | 北京戴纳实验科技有限公司 | A kind of safety detection method and its detection device of laboratory management system for internet of things |
Citations (9)
| 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 |
| CN101454811A (en) * | 2006-06-06 | 2009-06-10 | 三星电子株式会社 | Home security applications for television with digital video cameras |
| CN101526997A (en) * | 2009-04-22 | 2009-09-09 | 无锡名鹰科技发展有限公司 | Embedded infrared face image identifying method and identifying device |
| CN101551934A (en) * | 2009-05-15 | 2009-10-07 | 东北大学 | Device and method for monitoring fatigue driving of driver |
| CN101556724A (en) * | 2008-04-09 | 2009-10-14 | 中国科学院半导体研究所 | Safety management system of optical fiber perimeter and pattern recognition method thereof |
| CN101853381A (en) * | 2009-03-31 | 2010-10-06 | 华为技术有限公司 | Method and device for acquiring video subtitle information |
| CN201628997U (en) * | 2009-08-05 | 2010-11-10 | 匡伟 | Camera attendance machine with backstage comparison |
| US20110274314A1 (en) * | 2010-05-05 | 2011-11-10 | Nec Laboratories America, Inc. | Real-time clothing recognition in surveillance videos |
| CN202306275U (en) * | 2011-10-10 | 2012-07-04 | 上海企想信息技术有限公司 | IOT intelligent home experimental system |
-
2012
- 2012-08-29 CN CN201210312444XA patent/CN102902954A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101454811A (en) * | 2006-06-06 | 2009-06-10 | 三星电子株式会社 | Home security applications for television with digital video cameras |
| CN101017573A (en) * | 2007-02-09 | 2007-08-15 | 南京大学 | Method for detecting and identifying moving target based on video monitoring |
| CN101556724A (en) * | 2008-04-09 | 2009-10-14 | 中国科学院半导体研究所 | Safety management system of optical fiber perimeter and pattern recognition method thereof |
| CN101853381A (en) * | 2009-03-31 | 2010-10-06 | 华为技术有限公司 | Method and device for acquiring video subtitle information |
| CN101526997A (en) * | 2009-04-22 | 2009-09-09 | 无锡名鹰科技发展有限公司 | Embedded infrared face image identifying method and identifying device |
| CN101551934A (en) * | 2009-05-15 | 2009-10-07 | 东北大学 | Device and method for monitoring fatigue driving of driver |
| CN201628997U (en) * | 2009-08-05 | 2010-11-10 | 匡伟 | Camera attendance machine with backstage comparison |
| US20110274314A1 (en) * | 2010-05-05 | 2011-11-10 | Nec Laboratories America, Inc. | Real-time clothing recognition in surveillance videos |
| CN202306275U (en) * | 2011-10-10 | 2012-07-04 | 上海企想信息技术有限公司 | IOT intelligent home experimental system |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103441890A (en) * | 2013-08-18 | 2013-12-11 | 安徽斯玛特物联网科技有限公司 | Performance testing method for internet of things |
| CN104905770A (en) * | 2014-03-13 | 2015-09-16 | 南京理工大学 | Human health state detection system based on internet of things and SVM analysis |
| CN104216294A (en) * | 2014-09-16 | 2014-12-17 | 黄河科技学院 | Intelligent household control system and method |
| CN106597363A (en) * | 2016-10-27 | 2017-04-26 | 中国传媒大学 | Pedestrian location method in indoor WLAN environment |
| CN107563275A (en) * | 2017-07-11 | 2018-01-09 | 青岛理工大学 | A kind of face identification method combined with BIM |
| CN108334840A (en) * | 2018-02-01 | 2018-07-27 | 福州大学 | Pedestrian detection method based on deep neural network under traffic environment |
| CN109118703A (en) * | 2018-07-19 | 2019-01-01 | 苏州菲丽丝智能科技有限公司 | A kind of intelligent household security system and its working method |
| CN109450942A (en) * | 2018-12-25 | 2019-03-08 | 北京戴纳实验科技有限公司 | A kind of safety detection method and its detection device of laboratory management system for internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102902954A (en) | Pedestrian detection system and method based on internet-of-things intelligent household security gateway | |
| Zou et al. | Occupancy detection in the office by analyzing surveillance videos and its application to building energy conservation | |
| CN109670441A (en) | A kind of realization safety cap wearing knows method for distinguishing, system, terminal and computer readable storage medium | |
| CN108351967A (en) | A kind of plurality of human faces detection method, device, server, system and storage medium | |
| CN102164270A (en) | Intelligent video monitoring method and system capable of exploring abnormal events | |
| CN102915638A (en) | Surveillance video-based intelligent parking lot management system | |
| CN104933819A (en) | Alarm device based on face recognition and sign recognition and alarm method | |
| CN105574497A (en) | Mall people counting system and counting method based on face detection | |
| CN202940921U (en) | Real-time monitoring system based on face identification | |
| CN105187786A (en) | Voice prompting method of intelligent cat eye, and intelligent cat eye | |
| US11935378B2 (en) | Intrusion detection methods and devices | |
| CN210110004U (en) | Oil field behavior monitoring system based on artificial intelligence | |
| CN103324919A (en) | Video monitoring system based on face recognition and data processing method thereof | |
| CN110738289A (en) | Multi-dimensional linkage comprehensive studying and judging device for electric power operation standardization and using method thereof | |
| CN108805184B (en) | Image recognition method and system for fixed space and vehicle | |
| CN105574498A (en) | Face recognition system and recognition method based on customs security check | |
| CN102867214B (en) | Counting management method for people within area range | |
| CN110674753A (en) | Theft early warning method, terminal device and storage medium | |
| CN105095891A (en) | Human face capturing method, device and system | |
| CN202976124U (en) | Passenger detection system of intelligent household security gateway based on Internet-of-things | |
| CN204759662U (en) | Alarm based on face identification and sign discernment | |
| CN203287954U (en) | Card punching system based on human face recognition | |
| CN105825631B (en) | fatigue detection method and system based on video intelligent algorithm | |
| US20220335725A1 (en) | Monitoring presence or absence of an object using local region matching | |
| CN115810161A (en) | Transformer substation fire identification method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into 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: 20130130 |