CN107886677A - A kind of the elderly's gait household monitoring system based on Kinect - Google Patents
A kind of the elderly's gait household monitoring system based on Kinect Download PDFInfo
- Publication number
- CN107886677A CN107886677A CN201711167250.4A CN201711167250A CN107886677A CN 107886677 A CN107886677 A CN 107886677A CN 201711167250 A CN201711167250 A CN 201711167250A CN 107886677 A CN107886677 A CN 107886677A
- Authority
- CN
- China
- Prior art keywords
- kinect
- data
- raspberry
- patient
- warning message
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
Abstract
The invention discloses a kind of the elderly's gait household monitoring system based on Kinect, including computer monitoring client, router, some Kinect sensors, some Raspberry Pis, management equipment, the Kinect sensor is connected by USB line with the Raspberry Pi, the Raspberry Pi carries out wireless connection by the router and the computer monitoring client, and the Kinect sensor is used to gather image information;The Raspberry Pi is used to drive the image information of Kinect sensor acquisition monitors environment, receives the image information from Kinect sensor and send image information to the computer monitoring client.The present invention carries out real-time manikin extraction in monitors environment and contrasted with National Officer's database so as to complete to monitor in real time, more intelligent, realizes the high efficiency of monitoring.
Description
Technical field
The present invention relates to a kind of monitoring system, specifically a kind of the elderly's gait household monitoring system based on Kinect.
Background technology
With the rapid development of contemporary scientific technology, many monitoring systems with the addition of more advanced technology so that monitoring
System is more and more intelligent.Current Indoor Monitoring System only have simple behavioural analysis to monitored object, video record and
Real-time alert etc., but to the entrance of stranger, monitoring system can not react to that, it is necessary to which people judges there is paper
Mention, the detection of human body target in video is realized based on OpenCV storehouses, but need each of Computer real-time processing video
Frame, it is computationally intensive and someone's invasion can only be judged it cannot be determined whether be stranger, it is unable to reach intelligent security guard effect.
The appearance of Kinect depth cameras, allows computer vision field to be developed rapidly.Kinect is in family intelligent monitoring system
Application in system, intelligent monitoring, bone tracking energy are realized using the key characteristic of Kinect bone tracking and recognition of face
Human body information is effectively distinguished at night, blocks, rotate and face blocks and can be also identified even if body, can also can by detection
It is doubtful to act to implement to alarm, but this type of alarm needs to establish a number of behavior storehouse, and only by detecting behavior spy
Sign can not effectively judge whether it is invader, and Kinect must connect with main frame.
The content of the invention
It is above-mentioned to solve it is an object of the invention to provide a kind of the elderly's gait household monitoring system based on Kinect
The problem of being proposed in background technology.
To achieve the above object, the present invention provides following technical scheme:
A kind of the elderly's gait household monitoring system based on Kinect, including it is computer monitoring client, router, some
Kinect sensor, some Raspberry Pis, management equipment, the Kinect sensor are connected by USB line with the Raspberry Pi, institute
State Raspberry Pi and wireless connection is carried out by the router and the computer monitoring client, the Kinect sensor is used for
Gather image information;The Raspberry Pi is used to drive the image information of Kinect sensor acquisition monitors environment, reception to come from
The image information of Kinect sensor and image information is sent to the computer monitoring client;The computer monitoring
Client is used to receive the image information of Raspberry Pi transmission, manikin extraction is completed by snake algorithms and establishes human body
Database;Management equipment, to Kinect sensor obtain color image data, depth image data, joint point data and
Voice data is handled and analyzed, and sends warning message according to analysis result;Alarm module, sent according to management equipment
Warning message carries out audio alert;Wireless communication module, for warning message to be sent into user, and receive the finger of user
Lead suggestion;Mobile terminal, for the warning message received to be carried out into real-time display, and the guiding opinion that user is proposed is sent out
Send management equipment back to, remind care provider to be handled.
As the further scheme of the present invention:The quantity of the Kinect sensor is 4, and the quantity of the Raspberry Pi is 4;
4 Kinect sensors are arranged in monitored space into square profile, for obtaining the three-dimensional point cloud atlas in monitor area.
As further scheme of the invention:The management equipment includes data processing module, for coloured image
Data, depth image data, joint point data and voice data are filtered processing, and build skeleton vector model,
Calculate skeleton characteristic matrix;Database, for storing the data for handling and classifying through data processing module;Action is known
Other and determination module, judge patient's action whether in dangerous dynamic according to the skeleton characteristic matrix of patient's current action
In the range of making data, warning message is sent if patient's action belongs to dangerous play;Locus determination module, according to pass
Node data calculates coordinate of the patient in ward, patient coordinate is judged whether in movable alarm region, if patient is in
Movable alarm then sends warning message in region;Sound identification module, for carrying out speech recognition to voice data, remind monitoring
Personnel timely respond to the requirement of patient;If during instruction containing distress call in voice data, send warning message;Human-computer interaction
Module, including for showing coloured image, the display unit of depth image and warning message content and for called data storehouse
Monitoring data, patient information and the instruction input unit for inputting control instruction of middle storage.
Compared with prior art, the beneficial effects of the invention are as follows:The present invention carries out real-time human mould in monitors environment
Type is extracted and contrasted with National Officer's database so as to complete to monitor in real time, more intelligent, realizes the high efficiency of monitoring.
Brief description of the drawings
Fig. 1 is the structural representation of the elderly's gait household monitoring system based on Kinect.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other under the premise of creative work is not made
Embodiment, belong to the scope of protection of the invention.
Referring to Fig. 1, in the embodiment of the present invention, a kind of the elderly's gait household monitoring system based on Kinect, including
Computer monitoring client, router, some Kinect sensors, some Raspberry Pis, management equipment, the Kinect sensor
It is connected by USB line with the Raspberry Pi, the Raspberry Pi is carried out by the router and the computer monitoring client
Wireless connection, the Kinect sensor are used to gather image information;The Raspberry Pi is used to drive Kinect sensor to obtain
The image information of monitors environment, receive the image information from Kinect sensor and send image information to the calculating
Machine monitoring client;The computer monitoring client is used for the image information, complete by snake algorithms for receiving Raspberry Pi transmission
Adult body model extraction and establish somatic data storehouse;Management equipment, the color image data obtained to Kinect sensor, depth
Degree view data, joint point data and voice data are handled and analyzed, and send warning message according to analysis result;Report
Alert module, the warning message sent according to management equipment carry out audio alert;Wireless communication module, for warning message to be sent
To user, and receive the guiding opinion of user;Mobile terminal, for the warning message received to be carried out into real-time display,
And the guiding opinion for proposing user sends back management equipment, care provider is reminded to be handled.
The quantity of the Kinect sensor is 4, and the quantity of the Raspberry Pi is 4;4 Kinect sensors are into just
Square distributing installation is in monitored space, for obtaining the three-dimensional point cloud atlas in monitor area.
The management equipment includes data processing module, for counting color image data, depth image data, joint
According to this and voice data is filtered processing, and builds skeleton vector model, calculates skeleton characteristic matrix;Number
According to storehouse, for storing the data for handling and classifying through data processing module;Action recognition and determination module, currently moved according to patient
The skeleton characteristic matrix of work judges whether patient's action is in the range of dangerous play data, if patient acts
Belong to dangerous play and then send warning message;Locus determination module, patient is calculated in ward according to joint point data
Coordinate, patient coordinate is judged whether in movable alarm region, alarm signal is sent if patient is in movable alarm region
Breath;Sound identification module, for carrying out speech recognition to voice data, care provider is reminded to timely respond to the requirement of patient;If
In voice data during instruction containing distress call, warning message is sent;Human-computer interaction module, including for showing cromogram
Picture, depth image and the display unit of warning message content and the monitoring data for being stored in called data storehouse, Bing Renxin
Cease and input the instruction input unit of control instruction.
The implementation steps of the present invention are as follows:
Coloured image and depth image in S1,4 Kinect acquisition monitorings regions, so as to obtain the three-dimensional point in monitor area
Cloud atlas;
S2, in three-dimensional point cloud atlas, Raspberry Pi obtain human body movable information, obtain the initial outline of human body;
S3, according to the initial outline of human body, computer monitoring client extracts the three-dimensional shape features of human body, obtains human body three-dimensional
Space coordinates and human parameters;
S4, repeat step S1-S3, computer monitoring client establish somatic data storehouse;
S5, Kinect are monitored in real time, if someone occurs in monitor video, the 3D shape that Raspberry Pi extracts this human body is special
Sign, and itself and somatic data storehouse are matched;If pairing result is stranger, starts warning system and alarmed.
Further, in the step S2, Raspberry Pi obtains the movable information of human body using frame difference method.
Further, in the step S3, computer monitoring client extracts the 3D shape of human body using snake algorithms
Feature.
Further, the human parameters of the step S3 includes:Human height, brachium, leg length and head size.
Further, the step S4 Computer monitor clients establish somatic data storehouse, and somatic data storehouse also needs to record
Enter the personal information of each human body, the personal information includes name, numbering and fingerprint.
Further, start warning system in the step S5 to be alarmed, type of alarm includes audio alert and calculating
The warning at machine monitoring client control interface, after starting alarm, computer monitoring client records stranger's is included in time, people
Body three dimensional space coordinate and human parameters, the human parameters include:Human height, brachium, leg length and head size.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, Er Qie
In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, embodiment all should be regarded as exemplary, and be nonrestrictive, the scope of the present invention is by appended power
Profit requires rather than described above limits, it is intended that all in the implication and scope of the equivalency of claim by falling
Change is included in the present invention.Any reference in claim should not be considered as to the involved claim of limitation.
Moreover, it will be appreciated that although the present specification is described in terms of embodiments, not each embodiment is only wrapped
Containing an independent technical scheme, this narrating mode of specification is only that those skilled in the art should for clarity
Using specification as an entirety, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
It is appreciated that other embodiment.
Claims (3)
- A kind of 1. the elderly's gait household monitoring system based on Kinect, it is characterised in that including computer monitoring client, Router, some Kinect sensors, some Raspberry Pis, management equipment, the Kinect sensor pass through USB line and the tree The connection of certain kind of berries group, the Raspberry Pi carries out wireless connection by the router and the computer monitoring client, described Kinect sensor is used to gather image information;The Raspberry Pi is used for the image for driving Kinect sensor to obtain monitors environment Information, receive the image information from Kinect sensor and send image information to the computer monitoring client; The computer monitoring client is used to receive the image information of Raspberry Pi transmission, carried by snake algorithms completion manikin Take and establish somatic data storehouse;Management equipment, to Kinect sensor obtain color image data, depth image data, Joint point data and voice data are handled and analyzed, and send warning message according to analysis result;Alarm module, according to The warning message that management equipment is sent carries out audio alert;Wireless communication module, for warning message to be sent into user, and Receive the guiding opinion of user;Mobile terminal, for the warning message received to be carried out into real-time display, and user is carried The guiding opinion gone out sends back management equipment, reminds care provider to be handled.
- 2. the elderly's gait household monitoring system according to claim 1 based on Kinect, it is characterised in that described The quantity of Kinect sensor is 4, and the quantity of the Raspberry Pi is 4;4 Kinect sensors are installed into square profile In monitored space, for obtaining the three-dimensional point cloud atlas in monitor area.
- 3. the elderly's gait household monitoring system according to claim 1 based on Kinect, it is characterised in that the pipe Reason equipment includes data processing module, for color image data, depth image data, joint point data and voice data Processing is filtered, and builds skeleton vector model, calculates skeleton characteristic matrix;Database, for storing The data for handling and classifying through data processing module;Action recognition and determination module, according to the skeleton of patient's current action Characteristic matrix judges whether patient's action is in the range of dangerous play data, if patient's action belongs to dangerous play Then send warning message;Locus determination module, coordinate of the patient in ward is calculated according to joint point data, judges patient Coordinate sends warning message whether in movable alarm region if patient is in movable alarm region;Speech recognition mould Block, for carrying out speech recognition to voice data, care provider is reminded to timely respond to the requirement of patient;If contain in voice data During the instruction of distress call, warning message is sent;Human-computer interaction module, including for show coloured image, depth image and The display unit of warning message content and the monitoring data for being stored in called data storehouse, patient information simultaneously input control instruction Instruction input unit.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711167250.4A CN107886677A (en) | 2017-11-21 | 2017-11-21 | A kind of the elderly's gait household monitoring system based on Kinect |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711167250.4A CN107886677A (en) | 2017-11-21 | 2017-11-21 | A kind of the elderly's gait household monitoring system based on Kinect |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107886677A true CN107886677A (en) | 2018-04-06 |
Family
ID=61778339
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711167250.4A Pending CN107886677A (en) | 2017-11-21 | 2017-11-21 | A kind of the elderly's gait household monitoring system based on Kinect |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107886677A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109326081A (en) * | 2018-11-09 | 2019-02-12 | 复旦大学 | Old man family nurse early warning system and health Evaluation method based on Internet of Things |
CN110119697A (en) * | 2019-04-28 | 2019-08-13 | 华东交通大学 | A kind of Method of Gait Feature Extraction system based on Kinect device |
CN112000219A (en) * | 2020-03-30 | 2020-11-27 | 华南理工大学 | Movable gesture interaction device and method for augmented reality game |
CN112102585A (en) * | 2019-06-18 | 2020-12-18 | 广东点讯智能科技有限公司 | Intelligent behavior analysis system applied to old age support place |
CN112571426A (en) * | 2020-11-30 | 2021-03-30 | 重庆优乃特医疗器械有限责任公司 | 3D posture detection and analysis system and method |
-
2017
- 2017-11-21 CN CN201711167250.4A patent/CN107886677A/en active Pending
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109326081A (en) * | 2018-11-09 | 2019-02-12 | 复旦大学 | Old man family nurse early warning system and health Evaluation method based on Internet of Things |
CN110119697A (en) * | 2019-04-28 | 2019-08-13 | 华东交通大学 | A kind of Method of Gait Feature Extraction system based on Kinect device |
CN112102585A (en) * | 2019-06-18 | 2020-12-18 | 广东点讯智能科技有限公司 | Intelligent behavior analysis system applied to old age support place |
CN112000219A (en) * | 2020-03-30 | 2020-11-27 | 华南理工大学 | Movable gesture interaction device and method for augmented reality game |
CN112000219B (en) * | 2020-03-30 | 2022-06-14 | 华南理工大学 | Movable gesture interaction method for augmented reality game |
CN112571426A (en) * | 2020-11-30 | 2021-03-30 | 重庆优乃特医疗器械有限责任公司 | 3D posture detection and analysis system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107886677A (en) | A kind of the elderly's gait household monitoring system based on Kinect | |
CN105913559B (en) | A kind of ATM in bank intelligent control method based on body-sensing technology | |
CN104680525A (en) | Automatic human body fall-down detection method based on Kinect depth image | |
CN103366565B (en) | Method and system of detecting pedestrian running red light based on Kinect | |
CN106951849B (en) | Monitoring method and system for preventing children from accidents | |
CN111814601A (en) | Video analysis method combining target detection and human body posture estimation | |
CN107247945A (en) | A kind of ward sufferer monitor system and monitoring method based on Kinect device | |
CN103957387B (en) | A kind of security protection channel sundries detection method and detection system | |
US20220366697A1 (en) | Image processing method and apparatus, electronic device and storage medium | |
CN105940434A (en) | Information processing device, information processing method, and program | |
CN100464348C (en) | Video frequency monitoring, identification intelligont device and technical method | |
CN110428449A (en) | Target detection tracking method, device, equipment and storage medium | |
CN111401296A (en) | Behavior analysis method, equipment and device | |
CN205751110U (en) | Classroom based on image procossing intelligent management system | |
CN111629184A (en) | Video monitoring alarm system and method capable of identifying personnel in monitoring area | |
KR20220109694A (en) | Service system for the elderly living alone using companion robots, and method thereof | |
TWI713368B (en) | Image device and method for detecting a thief | |
Belbachir et al. | Event-driven feature analysis in a 4D spatiotemporal representation for ambient assisted living | |
CN113384267A (en) | Fall real-time detection method, system, terminal equipment and storage medium | |
Fern'ndez-Caballero et al. | HOLDS: Efficient fall detection through accelerometers and computer vision | |
CN106803937A (en) | A kind of double-camera video frequency monitoring method and system with text log | |
KR20130094488A (en) | System and method for monitoring emergency motion based image | |
CN112597961B (en) | Interest target extraction method and system based on big data | |
CN109327681A (en) | A kind of specific people identifies warning system and its method | |
CN203025900U (en) | Face recognition alarm apparatus |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180406 |