CN103164923A - Home safety monitoring system and method - Google Patents
Home safety monitoring system and method Download PDFInfo
- Publication number
- CN103164923A CN103164923A CN2011104159649A CN201110415964A CN103164923A CN 103164923 A CN103164923 A CN 103164923A CN 2011104159649 A CN2011104159649 A CN 2011104159649A CN 201110415964 A CN201110415964 A CN 201110415964A CN 103164923 A CN103164923 A CN 103164923A
- Authority
- CN
- China
- Prior art keywords
- image
- human
- dimensional
- personnel
- guarded region
- 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
Landscapes
- Emergency Alarm Devices (AREA)
Abstract
A home safety monitoring system is applied to a monitoring host which is electrically connected with a plurality of camera devices installed in a plurality of sub areas of a monitoring area. The system comprises an image shooting module, a human-form detection module and an alarm module, wherein the image shooting module is used for controlling the plurality of camera devices to continuously shoot images of the sub areas of the monitoring area to obtain real-time three-dimensional images in the sub areas, the human-form detection module is used for carrying out image analysis of each shot three-dimensional image, detecting whether a three-dimensional human-form image exists in each three-dimensional image or not, continuously analyzing the three-dimensional human-form image when the three-dimensional human-form image is detected, and detecting whether personnel in the monitoring area are in danger or not, the alarm module is used for raising alarm information and informing relevant personnel when personnel in the monitoring area are detected to be in danger, and relevant personnel can timely process the dangerous situation. The invention further provides a home safety monitoring method.
Description
Technical field
The present invention relates to safety monitoring technology, relate in particular to a kind of domestic safety monitoring system and method.
Background technology
In life, the special populations such as weak old man and infant need to have the special messenger to nurse at home, to prevent dangerous generation.Yet, be that the mode of looking after needs the long-time property on your toes of caregiver by the people, easily produce tired.In addition, for weak old man, many families,, may cause serious injury the old man if fail in time to be found in case the old man occurs accidentally falling down when waiting accident all without special messenger nurse.
Summary of the invention
In view of above content, be necessary to provide a kind of domestic safety monitoring system, be applied in monitoring host computer, this monitoring host computer is connected with a plurality of camera device electronics in a plurality of subregions that are arranged on a guarded region.This system comprises: image acquisition module is used for controlling described a plurality of camera device and continues all subregion of described guarded region is carried out filming image, to obtain the real-time three-dimensional image in all subregion; The human type detection module, be used for that each Zhang San who absorbs is tieed up image and carry out image analysing computer, whether have three-dimensional human-like image in the detecting 3-dimensional image, and when detecting three-dimensional human-like image, continue the human-like image of this three-dimensional is analyzed, whether have personnel to cause danger in the detecting guarded region; And alarm modules, when being used for having personnel to cause danger in detecting guarded region, sending a warning and notify the related personnel, so that this related personnel in time processes this unsafe condition.
Also be necessary to provide a kind of domestic safety monitoring method, be applied in monitoring host computer, a plurality of camera device electronics in this monitoring host computer and a plurality of subregions that are arranged on a guarded region are connected.The method comprises: the image capturing step, and control described a plurality of camera devices and continue all subregion of described guarded region is carried out filming image, to obtain the real-time three-dimensional image in all subregion; The human type detection step, each Zhang San who absorbs is tieed up image carry out image analysing computer, whether have three-dimensional human-like image in the detecting 3-dimensional image, and when detecting three-dimensional human-like image, continue the human-like image of this three-dimensional is analyzed, whether have personnel to cause danger in the detecting guarded region; And the alarm step, when having personnel to cause danger in detecting guarded region, send a warning and notify the related personnel, so that this related personnel in time processes this unsafe condition.
Compared to prior art, domestic safety monitoring system and method for the present invention, can control camera device to whether having personnel to cause danger in guarded region or existing potential danger to carry out Real Time Monitoring, in time notify the related personnel when monitoring danger or potential danger, effectively raise the safety and reliability of domestic safety monitoring.
Description of drawings
Fig. 1 is the hardware schematic diagram of domestic safety monitoring system running environment of the present invention.
Fig. 2 is the schematic diagram that the camera device in Fig. 1 is installed in respectively all subregion of guarded region.
Fig. 3 uses rectangle frame to demarcate the schematic diagram of the three-dimensional human-like image that detects.
Fig. 4 is the process flow diagram of domestic safety monitoring method of the present invention preferred embodiment.
The main element symbol description
| Monitoring |
1 |
| |
2 |
| |
3 |
| The domestic |
10 |
| Storer | 11 |
| Processor | 12 |
| |
101 |
| The human |
102 |
| |
103 |
| Rectangle | M0，M1 |
Following embodiment further illustrates the present invention in connection with above-mentioned accompanying drawing.
Embodiment
As shown in Figure 1, be the hardware schematic diagram of domestic safety monitoring system running environment of the present invention.This domestic safety monitoring system 10 is arranged in a monitoring host computer 1.Monitoring host computer 1 is connected with a plurality of camera device 2 electronics, or connect by network service, continue the real-time imaging in shooting particular home life zone (hereinafter to be referred as " guarded region ") with these a plurality of camera devices 2 of use, thereby realization is to the regional imaging monitoring of this life.In addition, this monitoring host computer 1 also connects an alarm device 3.This monitoring host computer 1 can be the opertaing devices such as computing machine, server.
Described a plurality of camera device 2 is mounted respectively in a plurality of subregions of described guarded region.For example shown in Figure 2, suppose that the present embodiment uses Cam1, Cam2,2 pairs of guarded regions shown in Figure 2 of 6 camera devices such as Cam6 carry out imaging monitoring, this Cam1, Cam2,, Cam6 is installed in respectively in the subregions such as parlor, room and balcony of this guarded region, thereby this guarded region is carried out the full-view image monitoring.In addition, if when the user does not need wherein one or more subregions are monitored, the user optionally closes the camera device 2 in respective sub-areas, only parton zone is wherein monitored.
In the present embodiment, described camera device 2 is the degree of depth camera device of a kind of use degree of depth sensing (depth-sensing) technology, by active illumination, special scenes is launched light beam, and calculate the distance (depth of view information) between object in this camera device 2 and scene by mistiming or the phase differential that calculates folded light beam, and then obtain one group of 3-dimensional image that comprises depth of view information.For example, this camera device 2 can be a kind of time flight (Time of Flight, TOF) video camera that absorbs 3-dimensional image.
Described domestic safety monitoring system 10 comprises image acquisition module 101, human type detection module 102 and alarm modules 103.This domestic safety monitoring system 10 can be stored in storer 11, and is controlled the execution of this domestic safety monitoring system 10 by processor 12.
Described image acquisition module 101 is used for controlling described a plurality of camera device 2 to be continued all subregion of guarded region is carried out filming image, to obtain the real-time three-dimensional image in all subregion.In the present embodiment, this image acquisition module 101 can be controlled the unlatching of described camera device 2 or close, and makes the user can optionally open as required or close wherein one or more camera devices 2, only imaging monitoring is carried out in the parton zone.
Described human type detection module 102 is tieed up image for each Zhang San who uses human-like detection techniques to picked-up and is carried out image analysing computer, whether has three-dimensional human-like image in the detecting 3-dimensional image.
In the present embodiment, described human type detection module 102 can be used human-like characteristic information statistic law, feature samples pairing comparision (Template Matching Method), and the three-dimensional human-like image in the described 3-dimensional image of the human type detection technology such as human-like tagsort method detecting.Take the feature samples pairing comparision as example, this human type detection module 102 can be detected three-dimensional human-like image by following steps.
At first, collect in advance the human-like feature samples of some and the non-human-like feature samples of some, for example, collect a large amount of human-like images such as front, side and the back side.
Then, with neural network (Artificial Neural Network) training patterns, human-like feature samples and the non-human-like feature samples collected are trained (Training), obtain a human-like image sample database.If do not use the neural network training patterns, also can change with the Ada-Boost classification described human-like feature samples and non-human-like feature samples are carried out classification based training, obtain described human-like image sample database.
At last, the 3-dimensional image of the above-mentioned all subregion of obtaining and the human-like sample in described human-like image sample database are analyzed, judge whether there is three-dimensional human-like image in this 3-dimensional image.
In addition, described human type detection module 102 also is used for when the 3-dimensional image at described guarded region detects three-dimensional human-like image, continue the human-like image of this three-dimensional is analyzed, whether having personnel to cause danger in the detecting guarded region, such as wrestling or fall in a swoon etc.Particularly, this human type detection module 102 is analyzed the three-dimensional human-like image that detects in the following manner.
At first, human type detection module 102 uses a rectangle that the three-dimensional human-like image that detects is demarcated, for example shown in Figure 3, use rectangle M0 to demarcate the three-dimensional human-like image that detects, and calculate the length (H) of the human-like image of this three-dimensional and the ratio of wide (W).
Then, human type detection module 102 continues the length of the human-like image of this three-dimensional and wide ratio are calculated, whether the variation that judges the length of the human-like image of this three-dimensional and wide ratio surpasses a default ratio and has continued a schedule time, and for example the variation of long and wide ratio is over 60% and continued 30 seconds.When the variation of the length of the human-like image of this three-dimensional and wide ratio has surpassed described default ratio and has continued the described schedule time, can judge in described guarded region has personnel to cause danger, for example there are personnel fall down and do not stand up voluntarily, for example shown in the rectangle M1 of Fig. 3.
Described alarm modules 103 is used for sending a warning and notifying the related personnel, so that this related personnel in time processes this unsafe condition when having personnel to cause danger in described guarded region.Particularly, this alarm modules 103 sends a warning by described alarm device 3.For example, when described alarm device 3 was an acoustic-optic alarm, this alarm modules 103 can be controlled this alarm device 3 and send the audible and visible alarm signal.Maybe when this alarm device 3 when possessing the communication device of message sending function, this alarm modules 103 can be controlled this alarm device 3 and send notes to related personnel's hand-held device, so that described unsafe condition is informed this related personnel.
In addition, described human type detection module 102 also is used for analyzing the 3-dimensional image of the specific subregion of described guarded region, the 3-dimensional image in for example in Fig. 2, Cam6 monitors balcony zone, detect the three-dimensional human-like image that whether has specific monitored personnel (as the infant) in the 3-dimensional image of this specific subregion, whether these specific monitored personnel enter in this specific subregion with judgement, thereby determine whether there is potential danger in this specific subregion.Herein, this human type detection module 102 equally can be by human-like sample pairing comparision, the three-dimensional human-like image sample (as infant's three-dimensional human-like image sample) of the 3-dimensional image of described specific subregion with these specific monitored personnel that set up in advance is analyzed, thereby detects whether occur described specific monitored personnel in described specific subregion.These specific monitored personnel's human-like image sample can be by pre-save in described storer 11.
Described alarm modules 103 also is used for when detecting described specific monitored personnel when entering described specific subregion, controlling alarm device 3 sends a warning, notifying in this specific subregion of described related personnel has specific monitored personnel to enter, and may have potential danger.
As shown in Figure 4, be the process flow diagram of domestic safety monitoring method of the present invention preferred embodiment.
Step S01, described image acquisition module 101 control described a plurality of camera device 2 and continue all subregion of guarded region is carried out filming image, to obtain the real-time three-dimensional image in all subregion.
Step S02, the described human type detection module 102 human-like detection techniques of use are tieed up image to each Zhang San who absorbs and are carried out image analysing computer, whether have three-dimensional human-like image in the detecting 3-dimensional image.This human type detection module 102 can be used human-like characteristic information statistic law, feature samples pairing comparision (Template Matching Method), and the three-dimensional human-like image in the described 3-dimensional image of the human type detection technology such as human-like tagsort method detecting.
Step S03, when detecting three-dimensional human-like image in the 3-dimensional image at described guarded region, whether described human type detection module 102 continues the human-like image of this three-dimensional is analyzed, have personnel to cause danger in the detecting guarded region.
Step S04, when having personnel to cause danger in detecting described guarded region, described alarm modules 103 control alarm devices 3 send a warning and notify the related personnel, so that this related personnel in time processes this unsafe condition.
In addition, described human type detection module 102 is further analyzed the 3-dimensional image of specific subregion in described guarded region, the 3-dimensional image in for example in Fig. 2, Cam6 monitors balcony zone, detect the three-dimensional human-like image that whether has specific monitored personnel (as the infant) in the 3-dimensional image of this specific subregion, whether these specific monitored personnel enter in this specific subregion with judgement, thereby determine whether there is potential danger in this specific subregion.When detecting described specific monitored personnel when entering described specific subregion, described alarm modules 103 sends a warning, and notifying in this specific subregion of described related personnel has specific monitored personnel to enter, and may have potential danger.
Above embodiment is only unrestricted in order to technical scheme of the present invention to be described, although with reference to preferred embodiment, the present invention is had been described in detail, those of ordinary skill in the art is to be understood that, can modify or be equal to replacement technical scheme of the present invention, and not break away from the spirit and scope of technical solution of the present invention.
Claims (10)
1. a domestic safety monitoring method, be applied in monitoring host computer, and a plurality of camera device electronics in this monitoring host computer and a plurality of subregions that are arranged on a guarded region are connected, and it is characterized in that, the method comprises:
The image capturing step is controlled described a plurality of camera devices and is continued all subregion of described guarded region is carried out filming image, to obtain the real-time three-dimensional image in all subregion;
The human type detection step, each Zhang San who absorbs is tieed up image carry out image analysing computer, whether have three-dimensional human-like image in the detecting 3-dimensional image, and when detecting three-dimensional human-like image, continue the human-like image of this three-dimensional is analyzed, whether have personnel to cause danger in the detecting guarded region; And
The alarm step when having personnel to cause danger in detecting guarded region, sends a warning and notifies the related personnel, so that this related personnel in time processes this unsafe condition.
2. domestic safety monitoring method as claimed in claim 1, it is characterized in that, described human type detection step also comprises: analyze in described guarded region the 3-dimensional image of specific subregion, detect the three-dimensional human-like image that whether has specific monitored personnel in the 3-dimensional image of this particular sub-area; And
Described alarm step also comprises: when having specific monitored personnel's three-dimensional human-like image in the 3-dimensional image that detects described specific subregion, send a warning, notify in this specific subregion of described related personnel and have potential danger.
3. domestic safety monitoring method as claimed in claim 2, it is characterized in that, described human type detection step is by being analyzed the three-dimensional human-like image sample of the 3-dimensional image of described specific subregion with the described specific monitored personnel that set up in advance, thereby detects whether occur these specific monitored personnel in described specific subregion.
4. domestic safety monitoring method as claimed in claim 1, is characterized in that, described human type detection step is used human-like characteristic information statistic law, feature samples pairing comparision, or the three-dimensional human-like image in the described 3-dimensional image of human-like tagsort method detecting.
5. domestic safety monitoring method as claimed in claim 1, is characterized in that, whether described human type detection step is judged in the following manner has personnel to cause danger in described guarded region:
Use a rectangle that the three-dimensional human-like image that detects is demarcated, and calculate the length of the human-like image of this three-dimensional and wide ratio; And
Continue the length of the human-like image of this three-dimensional and wide ratio are calculated, whether the variation that judges the length of the human-like image of this three-dimensional and wide ratio surpasses a default ratio and has continued a schedule time, when the variation of the length of the human-like image of this three-dimensional and wide ratio surpassed described default ratio and continued the described schedule time, judging in described guarded region had personnel to cause danger.
6. a domestic safety monitoring system, be applied in monitoring host computer, and this monitoring host computer is connected with a plurality of camera device electronics in a plurality of subregions that are arranged on a guarded region, it is characterized in that, this system comprises:
Image acquisition module is used for controlling described a plurality of camera device and continues all subregion of described guarded region is carried out filming image, to obtain the real-time three-dimensional image in all subregion;
The human type detection module, be used for that each Zhang San who absorbs is tieed up image and carry out image analysing computer, whether have three-dimensional human-like image in the detecting 3-dimensional image, and when detecting three-dimensional human-like image, continue the human-like image of this three-dimensional is analyzed, whether have personnel to cause danger in the detecting guarded region; And
Alarm modules when being used for having personnel to cause danger in detecting guarded region, sending a warning and notifies the related personnel, so that this related personnel in time processes this unsafe condition.
7. domestic safety monitoring as claimed in claim 6 system, it is characterized in that, described human type detection module also is used for analyzing the 3-dimensional image of the specific subregion of described guarded region, detects the three-dimensional human-like image that whether has specific monitored personnel in the 3-dimensional image of this particular sub-area; And
Described alarm modules also is used for sending a warning when there is specific monitored personnel's three-dimensional human-like image in the 3-dimensional image that detects described specific subregion, notifies in this specific subregion of described related personnel and has potential danger.
8. domestic safety monitoring as claimed in claim 7 system, it is characterized in that, described human type detection module is by being analyzed the three-dimensional human-like image sample of the 3-dimensional image of described specific subregion with the described specific monitored personnel that set up in advance, thereby detects whether occur these specific monitored personnel in described specific subregion.
9. domestic safety monitoring as claimed in claim 6 system, is characterized in that, described human type detection module is used human-like characteristic information statistic law, feature samples pairing comparision, or the three-dimensional human-like image in the described 3-dimensional image of human-like tagsort method detecting.
10. domestic safety monitoring as claimed in claim 6 system, is characterized in that, whether described human type detection step is judged in the following manner has personnel to cause danger in described guarded region:
Use a rectangle that the three-dimensional human-like image that detects is demarcated, and calculate the length of the human-like image of this three-dimensional and wide ratio; And
Continue the length of the human-like image of this three-dimensional and wide ratio are calculated, whether the variation that judges the length of the human-like image of this three-dimensional and wide ratio surpasses a default ratio and has continued a schedule time, when the variation of the length of the human-like image of this three-dimensional and wide ratio surpassed described default ratio and continued the described schedule time, judging in described guarded region had personnel to cause danger.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011104159649A CN103164923A (en) | 2011-12-14 | 2011-12-14 | Home safety monitoring system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011104159649A CN103164923A (en) | 2011-12-14 | 2011-12-14 | Home safety monitoring system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103164923A true CN103164923A (en) | 2013-06-19 |
Family
ID=48587975
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011104159649A Pending CN103164923A (en) | 2011-12-14 | 2011-12-14 | Home safety monitoring system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103164923A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109658675A (en) * | 2017-10-12 | 2019-04-19 | 日立乐金光科技株式会社 | Rule of life measures system and rule of life measuring method |
| CN110059657A (en) * | 2019-04-25 | 2019-07-26 | 北京旷视科技有限公司 | Records handling method, apparatus, electronic equipment and computer readable storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020171551A1 (en) * | 2001-03-15 | 2002-11-21 | Eshelman Larry J. | Automatic system for monitoring independent person requiring occasional assistance |
-
2011
- 2011-12-14 CN CN2011104159649A patent/CN103164923A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020171551A1 (en) * | 2001-03-15 | 2002-11-21 | Eshelman Larry J. | Automatic system for monitoring independent person requiring occasional assistance |
Non-Patent Citations (1)
| Title |
|---|
| 黄彬: "智能空间中人的行为识别与理解", 《中国博士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109658675A (en) * | 2017-10-12 | 2019-04-19 | 日立乐金光科技株式会社 | Rule of life measures system and rule of life measuring method |
| CN110059657A (en) * | 2019-04-25 | 2019-07-26 | 北京旷视科技有限公司 | Records handling method, apparatus, electronic equipment and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tzeng et al. | Design of fall detection system with floor pressure and infrared image | |
| WO2017125094A1 (en) | Body fall smart control system and method therefor | |
| US7859419B2 (en) | Smoke detecting method and device | |
| CN105100689B (en) | ATM video frequency monitoring method and device | |
| KR101309366B1 (en) | System and Method for Monitoring Emergency Motion based Image | |
| CN109377697A (en) | Rapid Alarm method of disposal under a kind of intensive camera head environment | |
| CN109102677A (en) | Construction site safety monitoring system and method | |
| TWI460686B (en) | Family safety surveillance system and method | |
| CN110989594A (en) | Intelligent robot inspection system and method | |
| KR100927776B1 (en) | Hazardous Behavior Monitoring System | |
| CN106127814A (en) | A kind of wisdom gold eyeball identification gathering of people is fought alarm method and device | |
| EP2000952A2 (en) | Smoke detecting method and device | |
| CN113887445A (en) | Method and system for identifying standing and loitering behaviors in video | |
| KR101075550B1 (en) | Image sensing agent and security system of USN complex type | |
| CN113175996A (en) | Temperature monitoring method and device, computer readable storage medium and computer equipment | |
| CN106448055B (en) | Monitoring alarm method and device | |
| CN201516026U (en) | Infrared body temperature detecting instrument | |
| CN103164923A (en) | Home safety monitoring system and method | |
| CN112576310B (en) | Tunnel security detection method and system based on robot | |
| WO2011108913A1 (en) | A tracking and movement monitoring system and a method thereof | |
| CN116883946B (en) | Method, device, equipment and storage medium for detecting abnormal behaviors of old people in real time | |
| CN110300280A (en) | A kind of scenic spot passenger flow monitoring system | |
| KR101415848B1 (en) | Monitering apparatus of school-zone using detection of human body and vehicle | |
| KR102081577B1 (en) | Intelligence Fire Detecting System Using CCTV | |
| CN113420739B (en) | Intelligent emergency monitoring method and system based on neural network and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130619 |