CN114758417A - Intelligent old-age-protecting sensing control method - Google Patents
Intelligent old-age-protecting sensing control method Download PDFInfo
- Publication number
- CN114758417A CN114758417A CN202210373671.7A CN202210373671A CN114758417A CN 114758417 A CN114758417 A CN 114758417A CN 202210373671 A CN202210373671 A CN 202210373671A CN 114758417 A CN114758417 A CN 114758417A
- Authority
- CN
- China
- Prior art keywords
- contour
- image
- database
- trunk
- old
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims description 21
- 238000004364 calculation method Methods 0.000 claims description 20
- 239000003086 colorant Substances 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 10
- 230000000694 effects Effects 0.000 claims description 7
- 238000005314 correlation function Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 239000013598 vector Substances 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 2
- 230000010354 integration Effects 0.000 claims description 2
- 230000001953 sensory effect Effects 0.000 claims 2
- 230000000474 nursing effect Effects 0.000 abstract description 9
- 206010000117 Abnormal behaviour Diseases 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 208000024827 Alzheimer disease Diseases 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- 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
-
- 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
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0407—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis
- G08B21/043—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis detecting an emergency event, e.g. a fall
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B3/00—Audible signalling systems; Audible personal calling systems
- G08B3/10—Audible signalling systems; Audible personal calling systems using electric transmission; using electromagnetic transmission
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/12—Messaging; Mailboxes; Announcements
- H04W4/14—Short messaging services, e.g. short message services [SMS] or unstructured supplementary service data [USSD]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/90—Services for handling of emergency or hazardous situations, e.g. earthquake and tsunami warning systems [ETWS]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Networks & Wireless Communication (AREA)
- Theoretical Computer Science (AREA)
- Electromagnetism (AREA)
- Gerontology & Geriatric Medicine (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Psychology (AREA)
- Environmental & Geological Engineering (AREA)
- Public Health (AREA)
- Psychiatry (AREA)
- Image Analysis (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The invention belongs to the field of image acquisition and identification, and particularly relates to human body image acquisition, positioning, tracking, dangerous action identification and remote information prompt. The invention can identify and judge the abnormal behaviors of the old people such as falling, dangerous object touch and the like through limb actions, and has the functions of voice and remote prompt for guardians. Meanwhile, the temperature and the light of the living space environment of the old are detected, the on-off state of the air conditioner and the lamp is automatically controlled, the old can be monitored and cared in real time for 24 hours, and the device is suitable for multiple occasions such as families, hospitals and nursing homes.
Description
The technical field is as follows:
the invention belongs to the field of image acquisition and identification, mainly relates to human body image acquisition, positioning, tracking, dangerous action identification and remote information prompt, and provides an intelligent old-age protection sensing and control method.
The background art comprises the following steps:
the aging degree of the world is increasingly increased, the population of the old people in China exceeds two hundred million, and the disabled old people account for 6.4 percent. Wherein the serious disability accounts for 10.6 percent, and the labor intensity and responsibility pressure for nursing the old people are getting bigger and bigger. At present, artificial nursing is still the main old people care mode in China, but the artificial nursing is difficult to realize all-weather real-time error-free old people care, and when the old people are not in the sight of nursing staff, the dangerous conditions of falling, touching, gas and the like of some sick old people cannot be found and rescued in time.
Although the existing household video monitoring products have the conventional functions of home care, old people watching, mobile phone monitoring, human shape detection, video playback and the like, a large amount of monitoring videos need to be checked manually, and the sudden situation of the old people is difficult to find in time.
The invention content is as follows:
the invention aims to:
the invention provides an intelligent old-age care sensing and controlling method, and aims to solve the problems that manual care is difficult to realize all-weather real-time error-free nursing of old people, and the old people with dangerous conditions such as falling, touch, electricity, gas and the like cannot be found and rescued in time.
The technical scheme is as follows:
an intelligent old-age protection sensing control method is characterized by comprising the following steps:
the method comprises the following steps that (A) a tested object is put on a designed special garment, sleeves, trouser legs and a body trunk of the garment are respectively marked with different colors, a human body and an activity space environment are scanned, an actual image is collected and stored, and the collected image is subjected to binarization processing and normalization processing;
(II) color area segmentation and contour recognition: identifying areas corresponding to colors in the acquired images by using an identification database, determining areas and contours of left and right arms, left and right legs, a trunk and the like according to the areas of the colors, and normalizing the areas and the contours according to the length-width ratio of the identification database; tracking the measured object according to the determined area and the outline of the measured object;
(III) contour closing treatment: for the contour extracted in the step (two), if the contour is incomplete, closing processing is carried out, and pixels of the part of the contour which is not closed are filled to form a complete trunk contour and a complete body contour;
(IV) outline non-closing treatment: aiming at the contour extracted in the step (II), closing processing is carried out, and the area of each region is directly obtained by utilizing integration for the region of the non-closed contour; according to the followingRecognition databaseDetermining the length and width of each region, and further directly determining the outline of each part and the overall outline of the body;
(V) matching calculation: and (3) performing correlation matching calculation on the regions and the contours determined in the steps (two), (three) and (four) and the regions and the contours in the database respectively, wherein a correlation function c (x, y) is calculated according to the following formula:
wherein w (s, t) represents the image of the region and contour determined in the steps (two), (three), and (four), s, t is the position coordinates of a point in the image, and K, J represents the length and width of the image;
f (x, y) represents an image of the region and contour in the database, x, y being the position coordinates of a point in the image, N, M representing the length and width of the image;
x=0,1,2,...N-K,y=0,1,2,...M-J
The larger the correlation result value is, the more matching is shown, so that if the correlation result value is matched with the falling state in the database, the object is preliminarily determined to be in the falling state;
(VI) calculating an angle: respectively calculating the angles between the two arms, the two legs and the body trunk and the ground, and the angles between the two arms, the two legs and the body trunk, wherein the angle calculation formula is as follows:
cosθ=ab/(|a|·|b|) (2)
where a and b are normal vectors to the plane of each region;
(VII) judging a falling state: and (V) matching calculation is carried out to further judge on the basis of preliminarily judging the falling state, if the length-width ratio of the areas of the two legs, the two arms and the trunk of the body is less than 1 and the calculated angle in the step (VI) is approximate to 0 or 180 degrees, a specific error value is set according to practical application, the falling state is confirmed, the falling information of the old is issued, and a guardian is prompted.
The identification database in the step (II) is established in the following way:
the method comprises the steps of putting a special garment designed on a cared object, selecting the color of the garment to be different from the living environment, scanning the human body and the environment of the activity space by a camera, respectively making the object to be tested in a normal state, a falling state and a falling-over state, collecting and storing actual images, carrying out color identification and contour extraction on the collected images, determining the total areas and contours of the left arm, the right arm, the left leg, the right leg, the trunk and the body, simultaneously setting the direction vertical to the ground to be long and the direction parallel to the ground to be wide, determining the length-width ratio of each area, carrying out normalization processing on the collected images, and forming an identification database comprising an area color library, a binarization library, a contour library and the like.
The image acquisition part is used for acquiring images by controlling a camera through a cradle head by a motor, selecting a light sensor to measure the ambient brightness, and controlling the automatic on-off of an electric lamp so as to control the ambient brightness; selecting a temperature sensor to measure the ambient temperature and controlling the automatic on-off of the air conditioner; and selecting a voice module and a wireless module to realize voice broadcasting and data remote transmission.
The advantages and effects are as follows:
the invention can detect the falling state of the old all day in real time, and can automatically identify and alarm, thereby having important value for assisting children and medical care to take care of the old.
Different from the existing home video monitoring, the invention has the following characteristics:
(1) the camera is controlled to rotate to collect images, the position of the old man is identified by using a matching algorithm, the camera is controlled to automatically track the old man, abnormal states such as falling of the old man and the like are judged by limb actions, voice and short message alarm prompting can be performed, a sensor does not need to be installed on the old man, and non-contact detection is realized.
(2) The environmental space of the activities of the old people is detected in real time, and warm prompts are provided for the old people when the old people touch dangerous goods such as electricity, gas and the like. Self-adaptive to parameters such as ambient light, temperature and the like to realize automatic on and off of equipment such as lamps, air conditioners and the like
(3) The intelligent sensing and controlling method is specially designed for the old people needing to be cared for, plays a role in assisting nursing staff in monitoring the old people, ensures that the old people are in a monitoring range all day long on one hand, greatly reduces the burden of medical staff and children on the other hand, and has important social significance and wide application prospect. The method mainly comprises two functions, wherein one function is used for positioning and tracking the cared old people and automatically judging and identifying dangerous actions, the dangerous state alarm is directly carried out, the video does not need to be checked manually, and the other function is used for detecting the space environment of the life of the old people and adaptively switching on and off equipment such as an air conditioner and the like, so that the old people are in a comfortable environment.
(4) An intelligent sensing and control method is designed based on an STM32 single chip microcomputer, abnormal behaviors such as falling of the old and touching of dangerous objects can be judged through limb action recognition, and the intelligent sensing and control method has the functions of voice and remote prompting of a guardian. Simultaneously to the temperature of old man living space environment, light detect and the on off state of automatic control air conditioner and lamp, realize guarding in real time and caring for the old man 24 hours, the device is applicable to a plurality of occasions such as family, hospital and asylum for the aged.
Description of the drawings:
FIG. 1 is a schematic view of the color setting of the present invention;
FIG. 2 is a diagram of the sensing and controlling instrument according to the present invention;
FIG. 3 is a flow chart of the present invention.
The specific implementation mode is as follows:
the invention provides an action recognition method and algorithm based on general characteristics, and the method and the algorithm are easy to realize in an embedded mode. The cradle head is used for controlling the image acquisition sensor to scan and acquire images, the abnormal actions of the old people are quickly positioned, tracked and identified through the provided identification method, and then alarm information is given. Mainly aims at the elderly needing to be cared for, in particular to the elderly who suffer from Alzheimer's disease, Parkinson and the like and need all-weather care, and assists nursing personnel such as children, medical care and the like to nurse the elderly.
The method comprises the following steps:
(1) establishing a database, designing special clothes, marking sleeves and trouser legs with different colors respectively, then collecting images to carry out normalization processing and contour processing, and forming a color library, a binarization library and a contour library.
(2) And controlling a camera to scan the human body and the activity space environment, acquiring an actual image, storing the actual image, performing binarization processing and performing normalization processing.
(3) Color region segmentation and contour recognition
According to the database arranged in the invention, the areas corresponding to the colors in the collected image are identified, so that the areas and the contours of the left arm, the right arm, the left leg, the right leg and the body are determined, the positions of the tested object and the four limbs are determined, and the tested object is tracked.
(4) Contour closure processing
And (4) performing closing processing on the extracted contour, and performing pixel filling by using least square fitting to form a complete closed contour of each region.
(5) Non-closed area
And (3) performing closure processing on the originally extracted contour, performing area integral calculation on the non-closed contour at the same time, and performing normalization processing to ensure that the ratio of the non-closed contour is consistent with that of the database.
(6) Matching calculation
And (3) respectively carrying out correlation matching calculation on the regions and the outlines determined in the steps (2), (3) and (4) and the regions and the outlines in the database, wherein a correlation function c (x, y) is calculated according to the following formula:
wherein w (s, t) represents the image of the region and contour determined in steps (2), (3) and (4), s, t is the position coordinates of a point in the image, and K, J represents the length and width of the image;
f (x, y) represents an image of the region and contour in the database, x, y being the position coordinates of a point in the image, N, M representing the length and width of the image;
x=0,1,2,...N-K,y=0,1,2,...M-J
and performing correlation matching calculation based on the closed area and the non-closed area of the outline respectively, and determining the posture of the object to be side and the positions of the arms and the legs.
(7) Tilt angle and aspect ratio calculation
Respectively calculating the angles between the two arms, the two legs and the body trunk and the ground, and the angles between the two arms, the two legs and the body trunk, wherein the angle calculation formula is as follows:
cosθ=ab/(|a|·|b|) (2)
Where a and b are normal vectors to the plane of each region;
and calculating the inclination angle of the body according to the arms, the legs and the trunk area, and calculating the length-width ratio of the arms, the legs and the trunk area.
(8) Fall to state prediction and determination
And predicting whether the tested object is in a falling trend or not according to the body inclination angle and the length-width ratio calculated by the arms, the legs and the trunk area, and further determining the falling state.
In the image acquisition part, a motor controls a camera to acquire images through a holder, a light sensor is selected to measure the ambient brightness, and the lamp is controlled to be automatically turned on and off. And selecting a temperature sensor to measure the ambient temperature and controlling the air conditioner to be automatically turned on and off. And selecting a voice module and a wireless module to realize voice broadcasting and data remote transmission.
The invention is further described with reference to the following figures and specific examples:
(1) FIG. 1 is a schematic diagram of color setup according to the present invention, a database is built according to the diagram, sleeves and trouser legs are respectively marked with different colors, and then images are collected for normalization processing and contour processing to form a color library, a binarization library and a contour library.
(2) Fig. 2 is a composition diagram of the sensing and controlling instrument of the present invention, which controls the camera to scan the human body and the activity space environment, collects the actual image, stores, performs binarization processing, and performs normalization processing.
(3) Color region segmentation and contour recognition
According to the database arranged in the invention, the areas corresponding to colors in the acquired image are identified, so that the areas and the contours of the left arm, the right arm, the left leg, the right leg and the body are determined, the positions of the tested object and the four limbs are determined, and the tested object is tracked.
(4) Contour closure processing
And (4) performing closing processing on the extracted contour, and performing pixel filling by using least square fitting to form a complete closed contour of each region.
(5) Non-closed area
And (3) performing closure processing on the originally extracted contour, performing area integral calculation on the non-closed contour at the same time, and performing normalization processing to ensure that the ratio of the non-closed contour is consistent with that of the database.
(6) Matching calculation
And (3) respectively carrying out correlation matching calculation on the regions and the outlines determined in the steps (2), (3) and (4) and the regions and the outlines in the database, wherein a correlation function c (x, y) is calculated according to the following formula:
wherein w (s, t) represents the image of the region and contour determined in steps (2), (3) and (4), s, t is the position coordinates of a point in the image, and K, J represents the length and width of the image;
f (x, y) represents an image of the region and contour in the database, x, y being the position coordinates of a point in the image, N, M representing the length and width of the image;
x=0,1,2,...N-K,y=0,1,2,...M-J
The larger the value of the correlation result is, the more the correlation result is matched, so that if the correlation result is matched with the falling state in the database, the object is preliminarily judged to be in the falling state;
(7) tilt angle and aspect ratio calculation
Respectively calculating the angles between the two arms, the two legs and the body trunk and the ground, and the angles between the two arms, the two legs and the body trunk, wherein the angle calculation formula is as follows:
cosθ=ab/(|a|·|b|) (2)
where a and b are normal vectors to the plane of each region;
and performing correlation matching calculation based on the closed area and the non-closed area of the outline respectively, and determining the posture of the object to be side and the positions of the arms and the legs. And calculating the inclination angle of the body according to the arms, the legs and the trunk area, and simultaneously calculating the length-width ratio of the arms, the legs and the trunk area.
(8) Drop to state prediction and determination
And predicting whether the tested object is in a falling trend according to the body inclination angle and the length-width ratio calculated by the arms, the legs and the trunk area, and further determining the falling state.
Fig. 3 is a flow chart of the present invention, which first ensures that the system can be successfully connected to the guardian's handset, setting one or more timings, and then sending a voice broadcast each time the set time is reached. Then the motor controls a camera to collect images through a holder, clothes of the old people are compared with clothes which are input into a database in advance by using a color identification matching method, and the old people can be quickly and accurately identified and tracked after matching is successful; the camera can track the old people all the time and judge whether the old people fall down or touch dangerous goods in real time through limb movement comparison, once abnormal conditions occur, the camera can immediately wake up an alarm and send out a prompt of danger and please keep away from the old people, and if the old people fall down or fall down, the camera can remotely transmit data to the end of a nursing person at the first time to know the dangerous conditions and take safety measures. Besides the main functions, the system also has some daily functions, firstly an environment brightness parameter is set, a light sensor is selected to measure the environment brightness, when the ambient brightness is judged to reach the set parameter, a guardian can control the on and off of the electric lamp, and if the ambient brightness does not reach the set parameter, the ambient brightness is judged again until the ambient brightness reaches the set parameter; setting an environment temperature parameter, selecting a temperature sensor to measure the environment temperature, controlling the on and off of the air conditioner by a guardian after judging that the ambient temperature reaches the set parameter, and judging the ambient temperature again until the set parameter is reached if the ambient temperature does not reach the set parameter. And after the complete function is judged, returning to the function of reminding the old people to take the medicine according to the set time, and repeatedly and circularly judging all the functions.
Claims (3)
1. An intelligent old-age protection sensing control method is characterized by comprising the following steps:
the method comprises the following steps that (I) a special garment designed for a tested object is worn, sleeves, trouser legs and a body part of the garment are respectively marked with different colors, a human body and a motion space environment are scanned, an actual image is collected and stored, binarization processing is carried out on the collected image, and normalization processing is carried out;
(II) color area segmentation and contour recognition: identifying areas corresponding to colors in the acquired image by using an identification database, determining areas and contours of a left arm, a right arm, a left leg, a right leg, a trunk area and the contours according to the areas of the colors, and normalizing the areas and the contours according to the length-width ratio of the identification database; tracking the measured object according to the determined area and contour of the measured object;
(III) contour closing treatment: for the contour extracted in the step (two), if the contour is incomplete, closing processing is carried out, and pixels of the part of the contour which is not closed are filled to form a complete trunk contour and a complete body contour;
(IV) outline non-closing treatment: for the contour extracted in the step (two), while closing processing is carried out, the area of each region is directly obtained by utilizing integration for the region of the non-closed contour; according to Recognition databaseDetermining the length and width of each region, and further directly determining the contour of each part and the overall contour of the body;
(V) matching calculation: and (3) performing correlation matching calculation on the regions and the contours determined in the steps (two), (three) and (four) and the regions and the contours in the database respectively, wherein a correlation function c (x, y) is calculated according to the following formula:
wherein w (s, t) represents the image of the region and contour determined in the steps (two), (three), and (four), s, t is the position coordinates of a point in the image, and K, J represents the length and width of the image;
f (x, y) represents an image of the region and contour in the database, x, y being the position coordinates of a point in the image, N, M representing the length and width of the image;
x=0,1,2,...N-K,y=0,1,2,...M-J
the larger the correlation result value is, the more matching is shown, so that if the correlation result value is matched with the falling state in the database, the object is preliminarily determined to be in the falling state;
(VI) calculating an angle: respectively calculating the angles between the two arms, the two legs and the body trunk and the ground, and the angles between the two arms, the two legs and the body trunk, wherein the angle calculation formula is as follows:
cosθ=ab/(|a|·|b|) (2)
where a and b are normal vectors to the plane of each region;
(VII) judging a falling state: and (V) matching calculation is carried out to further judge on the basis of preliminarily judging the falling state, if the length-width ratio of the areas of the two legs, the two arms and the trunk of the body is less than 1 and the calculated angle in the step (VI) is approximate to 0 or 180 degrees, a specific error value is set according to practical application, the falling state is confirmed, the falling information of the old is issued, and a guardian is prompted.
2. The intelligent old-age protection and sensory control method according to claim 1, wherein: the identification database in the step (II) is established in the following way:
the method comprises the steps of putting a special garment designed on a cared object, selecting the color of the garment to be different from the living environment, scanning the human body and the environment of the activity space by a camera, respectively making the object to be tested in a normal state, a falling state and a falling-over state, collecting and storing actual images, carrying out color identification and contour extraction on the collected images, determining the total areas and contours of the left arm, the right arm, the left leg, the right leg, the trunk and the body, simultaneously setting the direction vertical to the ground to be long and the direction parallel to the ground to be wide, determining the length-width ratio of each area, carrying out normalization processing on the collected images, and forming an identification database comprising an area color library, a binarization library, a contour library and the like.
3. The intelligent old-age protection and sensory control method according to claim 1, wherein:
the image acquisition part is used for acquiring images by controlling a camera through a tripod head by a motor, selecting a light sensor to measure the ambient brightness, and controlling the automatic on/off of an electric lamp so as to control the ambient brightness; selecting a temperature sensor to measure the ambient temperature and controlling the automatic on/off of the air conditioner; and selecting a voice module and a wireless module to realize voice broadcasting and data remote transmission.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2021103878412 | 2021-04-12 | ||
CN202110387841 | 2021-04-12 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114758417A true CN114758417A (en) | 2022-07-15 |
CN114758417B CN114758417B (en) | 2024-04-02 |
Family
ID=82329113
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210373671.7A Active CN114758417B (en) | 2021-04-12 | 2022-04-11 | Intelligent aging protection sensing and controlling method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114758417B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103325080A (en) * | 2013-06-21 | 2013-09-25 | 电子科技大学 | Gerocamium intelligent nursing system and method based on Internet of Things technology |
CN103517042A (en) * | 2013-10-17 | 2014-01-15 | 吉林大学 | Nursing home old man dangerous act monitoring method |
CN106503643A (en) * | 2016-10-18 | 2017-03-15 | 上海电力学院 | Tumble detection method for human body |
WO2017125094A1 (en) * | 2016-01-22 | 2017-07-27 | 苏州望湖房地产开发有限公司 | Body fall smart control system and method therefor |
EP3418991A1 (en) * | 2016-01-22 | 2018-12-26 | Suzhou Ling Wei Technology Co., Ltd. | Body fall smart control system and method therefor |
CN109670396A (en) * | 2018-11-06 | 2019-04-23 | 华南理工大学 | A kind of interior Falls Among Old People detection method |
-
2022
- 2022-04-11 CN CN202210373671.7A patent/CN114758417B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103325080A (en) * | 2013-06-21 | 2013-09-25 | 电子科技大学 | Gerocamium intelligent nursing system and method based on Internet of Things technology |
CN103517042A (en) * | 2013-10-17 | 2014-01-15 | 吉林大学 | Nursing home old man dangerous act monitoring method |
WO2017125094A1 (en) * | 2016-01-22 | 2017-07-27 | 苏州望湖房地产开发有限公司 | Body fall smart control system and method therefor |
EP3418991A1 (en) * | 2016-01-22 | 2018-12-26 | Suzhou Ling Wei Technology Co., Ltd. | Body fall smart control system and method therefor |
CN106503643A (en) * | 2016-10-18 | 2017-03-15 | 上海电力学院 | Tumble detection method for human body |
CN109670396A (en) * | 2018-11-06 | 2019-04-23 | 华南理工大学 | A kind of interior Falls Among Old People detection method |
Non-Patent Citations (1)
Title |
---|
陈伊凡;胡立夫;冯俊;: "一种基于姿态识别的老人监护系统", 中国科技信息, no. 15, 1 August 2020 (2020-08-01) * |
Also Published As
Publication number | Publication date |
---|---|
CN114758417B (en) | 2024-04-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109961058B (en) | Non-contact fall detection method and device | |
JP6150207B2 (en) | Monitoring system | |
US20200221977A1 (en) | Display control device, display control system, display control method, display control program, and recording medium | |
US7106885B2 (en) | Method and apparatus for subject physical position and security determination | |
Tzeng et al. | Design of fall detection system with floor pressure and infrared image | |
WO2016143641A1 (en) | Posture detection device and posture detection method | |
US20190034713A1 (en) | Method and apparatus for health and safety momitoring of a subject in a room | |
US11622703B2 (en) | Respiration monitor | |
Chen et al. | Remote recognition of in-bed postures using a thermopile array sensor with machine learning | |
JP6822328B2 (en) | Watching support system and its control method | |
JP2014106636A (en) | Watching support device | |
Dovgan et al. | Intelligent elderly-care prototype for fall and disease detection | |
US20150248754A1 (en) | Method and Device for Monitoring at Least One Interior Space of a Building, and Assistance System for at Least One Interior Space of a Building | |
CN111898580A (en) | System, method and equipment for acquiring body temperature and respiration data of people wearing masks | |
CN117690159B (en) | Infant groveling and sleeping monitoring method, device and equipment based on multi-mode data fusion | |
CN114758417A (en) | Intelligent old-age-protecting sensing control method | |
CN113516008A (en) | Human body movement abnormity monitoring system based on human body skeleton key points | |
CN108846996B (en) | Tumble detection system and method | |
CN111513745A (en) | Intelligent non-contact CT body position recognition device used in high-risk environment | |
CN110495874B (en) | Information processing method and electronic equipment | |
Dubois et al. | Detecting and preventing falls with depth camera, tracking the body center | |
Cheng et al. | A surveillance robot with human recognition based on video and audio | |
TWI796786B (en) | Tracking and identification monitoring system and method based on thermal image | |
He et al. | Night-time monitoring system for getting-up action of older person based on single camera and infrared reflective sheet | |
CN115965993A (en) | Tracking, identifying and monitoring system and method based on thermal image |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |