CN111685633A - Tumble detection method - Google Patents
Tumble detection method Download PDFInfo
- Publication number
- CN111685633A CN111685633A CN202010712076.2A CN202010712076A CN111685633A CN 111685633 A CN111685633 A CN 111685633A CN 202010712076 A CN202010712076 A CN 202010712076A CN 111685633 A CN111685633 A CN 111685633A
- Authority
- CN
- China
- Prior art keywords
- human body
- distance
- characteristic data
- actual
- detection
- 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
Classifications
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47K—SANITARY EQUIPMENT NOT OTHERWISE PROVIDED FOR; TOILET ACCESSORIES
- A47K13/00—Seats or covers for all kinds of closets
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47K—SANITARY EQUIPMENT NOT OTHERWISE PROVIDED FOR; TOILET ACCESSORIES
- A47K13/00—Seats or covers for all kinds of closets
- A47K13/10—Devices for raising and lowering, e.g. tilting or lifting mechanisms; Collapsible or rotating seats or covers
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47K—SANITARY EQUIPMENT NOT OTHERWISE PROVIDED FOR; TOILET ACCESSORIES
- A47K13/00—Seats or covers for all kinds of closets
- A47K13/24—Parts or details not covered in, or of interest apart from, groups A47K13/02 - A47K13/22, e.g. devices imparting a swinging or vibrating motion to the seats
Abstract
The invention relates to a tumble detection method, which comprises the following steps of acquiring an actual distance matrix between a human body and a preset position in real time; step two, converting the actual distance matrix into a horizontal distance matrix; extracting actual human body curve characteristic data in the horizontal distance matrix; step four, comparing and analyzing the actual human body curve characteristic data with the standard human body curve characteristic data after the human body falls down; step five, executing corresponding operation according to the comparison analysis result; and step six, informing the falling rescue personnel to implement the falling rescue for the falling rescue personnel. The method comprises the steps of obtaining an actual distance matrix in real time, converting the actual distance matrix into a horizontal distance matrix, extracting actual human body curve characteristic data, comparing the actual human body curve characteristic data with standard human body curve characteristic data after the human body falls down, and informing a fall rescuer to implement fall rescue on the fall rescuer when the similarity of the actual human body curve characteristic data and the standard human body curve characteristic data is larger than or equal to a similarity threshold value, so that accurate detection on the fall of the human body is realized.
Description
Technical Field
The invention belongs to the technical field of ToF sensor control, and particularly relates to a tumble detection method.
Background
At present, falls have become a public health event in China, and have become the leading cause of injury and death of the elderly over 65 years old. The first reason for a fall is that the physical function of a person is reduced, and with the increase of the physical function of the person, the nervous system, the vision, the hearing, the sensory system and the balance are all reduced, which is one of the most common reasons for the fall. The second factor is a pathological factor, and many people often see unstable walking on the street, such as cerebral thrombosis sequelae or cerebrovascular diseases; in addition, there are also some diseases of the cerebellum, and frequent walking and shaking can cause falls due to pathological factors.
Therefore, the system has very important significance and value for detecting and reminding people after falling on the premise of effectively preventing falling. The detection method for falling down of the personnel in the market mostly adopts a camera for detection, for example, in a nursing home or a hospital, a specially-arranged monitoring room and a camera are provided, and the falling-down personnel can be found and measures can be taken under the condition of monitoring the safety condition. However, the detection method for the falling of the personnel needs special personnel to monitor at any moment, the labor consumption is high when the detection method is used, and the personnel can not even find the falling personnel due to the fact that the personnel leave a monitoring room or the attention is not concentrated, so that the problem that the falling of the personnel can not be accurately detected is caused, and the problem that the treatment of the falling personnel is delayed is further caused. Therefore, there is a need for a fall detection method.
Disclosure of Invention
The invention aims to provide a tumble detection method, and aims to solve the technical problem that people can not be accurately detected to tumble in the prior art.
In order to achieve the above object, an embodiment of the present invention provides a fall detection method, including the following steps:
step one, acquiring an actual distance matrix between a human body and a preset position in real time;
step two, converting the actual distance matrix obtained in the step one into a horizontal distance matrix of the human body relative to a preset reference surface;
extracting actual human body curve characteristic data corresponding to the human body surface in the horizontal distance matrix obtained in the step two, wherein the actual human body curve characteristic data at least comprises the human body front side characteristic data, the human body back side characteristic data and the human body side surface characteristic data;
comparing and analyzing the actual human body curve characteristic data obtained in the step three with standard human body curve characteristic data calibrated in advance relative to the preset reference surface after the human body falls, wherein the standard human body curve characteristic data after the human body falls comprises human body curve characteristic data when the human body falls;
step five, according to the comparison analysis result, executing the following operations:
(1) if the similarity between the actual human body curve characteristic data and the standard human body curve characteristic data calibrated in advance relative to the preset reference plane is smaller than a preset similarity threshold, turning to the first step;
(2) if the actual human body curve characteristic data and the standard human body curve characteristic data calibrated in advance relative to the preset reference surface are larger than or equal to a preset similarity threshold, turning to a sixth step;
and step six, informing the falling rescue personnel to implement the falling rescue for the falling rescue personnel.
In order to achieve the above object, an embodiment of the present invention further provides a fall detection method, where the fall detection method is performed based on a fall detection system, and the fall detection system includes a distance detection calculation unit, a feature recognition processing unit, and a fall detection control unit, which are sequentially connected; the tumble detection method specifically comprises the following steps:
step one, acquiring an actual distance matrix between a human body and a preset position in real time through the distance detection and calculation unit;
secondly, converting the actual distance matrix obtained in the first step into a horizontal distance matrix of the human body relative to a preset reference surface through the characteristic identification processing unit;
extracting actual human body curve characteristic data corresponding to the surface of the human body in the horizontal distance matrix obtained in the step two through the characteristic identification processing unit, wherein the actual human body curve characteristic data at least comprises the human body front characteristic data, the human body back characteristic data and the human body side characteristic data;
comparing and analyzing the actual human body curve characteristic data obtained in the step three with standard human body curve characteristic data calibrated in advance relative to the preset reference surface after the human body falls through the characteristic identification processing unit, wherein the standard human body curve characteristic data after the human body falls comprise human body curve characteristic data when the human body falls;
step five, according to the comparison analysis result, executing the following operations:
(1) judging whether the similarity between the actual human body curve characteristic data and the standard human body curve characteristic data calibrated in advance relative to the preset reference plane is smaller than a preset similarity threshold value through the characteristic identification processing unit, and turning to the first step;
(2) judging whether the similarity between the actual human body curve characteristic data and the standard human body curve characteristic data calibrated in advance relative to the preset reference plane after the human body falls over is larger than or equal to a preset similarity threshold value through the characteristic identification processing unit, and turning to a sixth step;
and step six, informing the falling rescue workers to implement falling rescue through the falling detection control unit.
In order to achieve the above object, an embodiment of the present invention further provides a fall detection method, which specifically includes the following steps:
step one, installing a light emitter and an optical imaging lens of the falling detection system at the preset position;
secondly, a modulator of the distance detection and calculation unit generates a modulation signal, and after the generated modulation signal is transmitted to the light emitter, the light emitter emits corresponding modulation light outwards;
step three, the modulated light emitted by the light emitter is reflected to an optical imaging lens after encountering a human body serving as a measured object;
fourthly, receiving reflected modulated light reflected back by a photosensitive detector lattice positioned at the rear side of the optical imaging lens in the distance detection and calculation unit through the lens, and enabling a distance calculator of the distance detection and calculation unit to reflect the phase difference and the period of the modulated light through the reflected modulated light and the emitted modulated light, wherein the formula is based on:
calculating to obtain an actual distance matrix from the measured object to the photosensitive detector dot matrix;
fifthly, the distance converter of the characteristic identification processing unit bases the received actual distance matrix of the human body and the photosensitive detector dot matrix on a formula
Converting the distance matrix into a horizontal distance matrix of the human body relative to the lattice plane of the photosensitive detector, and transmitting the horizontal distance matrix to a characteristic comparison processor of a characteristic identification processing unit, wherein QQ 'is actual distance data of the human body and the lattice of the photosensitive detector, and (x', y ') and O' F are known parameters in the lattice of the photosensitive detector;
sixthly, extracting actual human body curve characteristic data corresponding to the surface of the human body in the horizontal distance matrix obtained in the step two by a characteristic comparison processor of the characteristic identification processing unit, wherein the actual human body curve characteristic data at least comprises the human body front characteristic data, the human body back characteristic data and the human body side characteristic data;
and step seven, based on the comparative analysis result in the step six, executing the following control operation:
when the characteristic identification processing unit judges that the similarity between the actual human body curve characteristic data and the standard human body curve characteristic data calibrated in advance relative to the preset reference surface is smaller than a preset similarity threshold, turning to a second step;
when the similarity between the actual human body curve characteristic data and the standard human body curve characteristic data calibrated in advance relative to the preset reference surface is judged to be more than or equal to a preset similarity threshold value through the characteristic identification processing unit, turning to the step eight;
and step eight, the fall detection control unit informs fall rescuers to implement fall rescue for the fall rescuers.
One or more technical schemes in the fall detection method provided by the embodiment of the invention have at least one of the following technical effects:
(1) the method comprises the steps of firstly obtaining an actual distance matrix between a human body and a preset position in real time, then converting the actual distance matrix into a horizontal distance matrix, then extracting actual human body curve characteristic data, then comparing and analyzing the actual human body curve characteristic data and standard human body curve characteristic data after falling, and when the similarity between the actual human body curve characteristic data and the standard human body curve characteristic data after falling is more than or equal to a similarity threshold value, informing a falling rescue worker to implement falling rescue on the falling worker, so that the accurate detection of the falling of the worker is realized;
(2) the invention realizes the accuracy of fall detection based on the ToF sensor, can be applied to nursing homes and hospitals, can also be applied to other scenes such as kindergartens and the like, and has wide popularization and application prospects.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a schematic overall structure diagram of a fall detection system according to an embodiment of the present invention;
fig. 2 is a schematic view of the light path structure of the light beam emission and reflection detection of the distance detection computing unit in the fall detection system according to the present invention;
FIG. 3 is a schematic diagram of the actually measured distance between the measured point of the measured human body and the photosensitive detector dot matrix;
FIG. 4 is a schematic illustration of the conversion of the measured distance of FIG. 3 to a horizontal distance;
FIG. 5 is a schematic diagram of a corresponding structure of light paths between a measured point in a measured space and a photosensitive detection pixel point in a photosensitive detector dot matrix;
FIG. 6 is a schematic diagram of a distance conversion structure for converting the actual measurement distance between the measured point in the measured space and the photosensitive detection pixel point into the horizontal distance between the measured point in the measured space and the lattice plane of the photosensitive detector;
FIG. 7 is a simulated state diagram of a person walking in accordance with one embodiment of the present invention;
FIG. 8 is a diagram of a simulation state of a human body when walking normally according to an embodiment of the present invention;
FIG. 9 is a diagram illustrating a simulated state of a human body falling in accordance with an embodiment of the present invention;
fig. 10 is a schematic diagram of the measured distance between the surface of the human body and the distance detection and calculation unit when the human body falls down in fig. 9 being converted into a horizontal distance;
FIG. 11 is a simulated state diagram of a human walking device according to another embodiment of the present invention;
FIG. 12 is a diagram illustrating a simulated state of a human body falling in accordance with another embodiment of the present invention;
fig. 13 is a schematic view of a mounting state simulation structure of the fall detection system according to the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be illustrative of the embodiments of the present invention, and should not be construed as limiting the invention.
In the description of the embodiments of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience in describing the embodiments of the present invention and simplifying the description, but do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the embodiments of the present invention, "a plurality" means two or more unless specifically limited otherwise.
In the embodiments of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," "fixed," and the like are to be construed broadly, e.g., as being fixedly connected, detachably connected, or integrated; can be mechanically or electrically connected; either directly or indirectly through intervening media, either internally or in any other relationship. Specific meanings of the above terms in the embodiments of the present invention can be understood by those of ordinary skill in the art according to specific situations.
In one embodiment of the present invention, as shown in fig. 1, there is provided a fall detection system including a distance detection calculation unit, a feature recognition processing unit, and a fall detection control unit, which are connected in this order.
As shown in fig. 13, the distance detection calculating unit is installed at a predetermined position, in this embodiment, the predetermined position is the top of a room, and the number of the distance detection calculating units is one.
It should be noted that the position of the distance detection and calculation unit is not limited to be installed on the top of a room, that is, the predetermined position is not limited to the top of a room, and the predetermined position is set by a person skilled in the art according to various application scenarios and comprehensive consideration of factors such as room formats, room area sizes, home layout in a room space, and the like, and the predetermined position is selected only by ensuring that a detection area is enlarged as much as possible; of course, the number of the distance detection calculating units is not limited to the above one, and a plurality of the distance detection calculating units may be provided according to actual requirements, so as to ensure that the detection regions of the distance detection calculating units cover all regions in the space.
The distance detection and calculation unit is configured to detect an actual distance between the human body and the predetermined position in real time based on a time-of-flight principle, where the actual distance is a multi-point distance corresponding to a plurality of position points, that is, a distance matrix, and it can also be understood that the distance detection and calculation unit obtains the actual distance matrix between the human body and the predetermined position in real time through detection.
Referring to fig. 1, the distance detection and calculation unit includes a light emitter, a modulator, an optical imaging lens, a photosensitive detector dot matrix, a controller and a distance calculator, the controller is connected to the modulator and the photosensitive detector dot matrix and is used for providing modulation control signals to the modulator, the modulator is connected to the light emitter and is used for providing modulation signals to light beams emitted by the light emitter, and the modulator is further connected to the photosensitive detector dot matrix and is used for providing basic modulation information. The light emitter is preferably an infrared light emitter and is used for emitting modulated light beams to a measured object, the modulated light beams reach the surface of the measured object, are reflected by the surface of the measured object and then enter the optical imaging lens, are input to the photosensitive detector dot matrix after being shaped by the optical imaging lens, the photosensitive detector dot matrix is connected with the distance calculator, and outputs the reflected beam signal to a distance calculator, which performs necessary processing such as noise removal filtering and A/D conversion on the reflected beam, calculating to obtain the distance information between the position point of the measured object reflecting the reflected light beam and the photosensitive detection pixel point in the photosensitive detector lattice receiving the reflected light beam, and the distance information and the relevant position information of the photosensitive detection pixel point are transmitted to a controller, and the controller further transmits the relevant information to a feature identification processing unit.
Preferably, the distance detection calculation unit may be implemented using any one of a 3D sensor, a ToF time-of-flight sensor, a DVS, a structured light sensor, and the like. The following specifically describes the process of calculating the actual distance matrix between the human body and the predetermined position by the distance detection calculation unit based on the ToF time-of-flight principle:
the distance detection calculation unit generates modulated infrared light through a light emitter of the distance detection calculation unit and emits the modulated infrared light outwards, the modulated infrared light is reflected to form reflected infrared light after meeting a measured object, and the reflected infrared light is received by a photosensitive detector dot matrix behind the reflected infrared light after passing through an optical imaging lens of the distance detection calculation unit. The emission modulated infrared light and the reflected infrared light of the distance detection calculation unit are both in sine wave form, and can be expressed in a functional form as follows: the function expression for emitting modulated infrared light is:
the functional expression for reflected infrared light is:
t is a time parameter;
a is the amplitude of the modulated infrared light;
t is the sine wave period;
kA is the amplitude of the reflected infrared light;
k is an attenuation coefficient;
and n is noise wave received and not reflected by the light source of the light emitter of the distance detection calculation unit.
Therefore, the delay time from the emission of the modulated infrared light to the reception of the reflected infrared light formed by the modulated infrared light, i.e., the elapsed flight time of the infrared light:
wherein T is the modulation wave period.
In the time period from the time when the light emitter emits the modulated infrared light to the time when the photosensitive detector receives the reflected infrared light reflected by the measured object, the flying distance of the infrared light is as follows:
where c is the speed of light, i.e. about 3 × 108m/s。
Therefore, the distance between the measured object reflecting the infrared light and the photosensitive detector dot matrix of the distance detection and calculation unit is as follows:
thus, the distance between the measured object and the photosensitive detector dot matrix can be calculated based on the sine wave period of the modulated infrared light and the signal phase difference of the reflected infrared light received by the photosensitive detection pixel point and the modulated infrared light emitted by the light emitter, the distance calculator transmits the sine wave period and the signal phase difference to the distance calculator, and the distance calculator calculates the actual measurement distance between the measured object and the photosensitive detector dot matrix based on the formula, namely the actual distance matrix.
The photosensitive detector lattice in the distance detection and calculation unit of the invention is provided with a plurality of photosensitive detection pixel points which are arranged in a matrix array form, each photosensitive detection pixel point can be used as an independent photosensitive detector element, thus, the light emitter emits modulated infrared light once outwards, the modulated infrared light is reflected by a plurality of points on the surface of a measured object and then is respectively incident on the corresponding photosensitive detection pixel points in the photosensitive detector lattice, namely, each photosensitive detection pixel point in the photosensitive detector lattice can collect the reflected infrared light and obtain a sensing distance, finally, the actual measurement distance of each frame detected by the photosensitive detector lattice corresponds to an actual distance matrix, the actual measurement distance between each reflection point on the surface of the measured object and the corresponding photosensitive detection pixel point which receives the reflected light of the point is combined with the reflection point to form two-dimensional distance distribution, as shown in fig. 2.
Thus, the distance detection and calculation unit can calculate and obtain an actual distance matrix between the human body and the preset position. Then, the distance detection calculation unit sends an actual distance matrix between the human body and the preset position to the feature recognition processing unit, and the feature recognition processing unit further processes the actual distance matrix.
Further, referring to fig. 1, the feature recognition processing unit includes a communication interface module, a distance converter, a feature comparison processor, a standard feature storage and an output module, the communication interface module is connected to the controller of the distance detection computing unit, the distance converter is connected to the communication interface module, the feature comparison processor is connected to the distance converter, the standard feature storage is connected to the feature comparison processor, and the output module is connected to the feature comparison processor.
The feature recognition processing unit is configured to convert the actual distance matrix calculated by the distance detection calculating unit into a horizontal distance matrix of the human body relative to a predetermined reference surface, and the working process of the feature recognition processing unit is specifically described as follows:
firstly, the actual distance acquired by the distance detection and calculation unit is the linear distance between each measured point and the corresponding photosensitive detection pixel point in the distance detection and calculation unit, and the whole distance detection and calculation unit can be regarded as a circle center particle for easy understanding.
Next, taking the process of detecting the whole human body by the distance detection and calculation unit as an example, referring to fig. 3 to 4, in this embodiment, the distance detection and calculation unit uses the ToF sensor, and the whole ToF sensor can be used as a mass point, and it can be seen from the figure that when the included angle between the ToF sensor and the detected region of the human body is too large, both the measured distances d1 and d5 are far greater than d 3. If the actual measurement distances d1 and d5 are directly adopted for human body identification, the difference between the characteristics reflected by the distances and the characteristics of the human body is large, and the human body identification precision is greatly reduced.
Firstly, as shown in fig. 5-6, a light beam reflected by each measured point Qn in the measured area a of the human body is focused by an optical imaging lens and then enters a corresponding photosensitive detection pixel point in a photosensitive detector lattice, and the distance between the measured point Qn of each human body and the corresponding photosensitive detection pixel point can be directly calculated after the photosensitive detection pixel point transmits related phase and frequency information to a distance calculator, and further, if the distance between the measured point Qn of the human body and the corresponding photosensitive detection pixel point is to be converted into a horizontal distance between the measured point Qn of the human body and a lattice plane of the photosensitive detector, an inclination angle of a straight line connecting the measured point Qn of the human body and the corresponding photosensitive detection pixel point with respect to the lattice plane of the photosensitive detector needs to be known, as shown in an enlarged light path structure diagram shown in fig. 6, after being reflected by a certain human body measuring point Q in a human body measured area A, a modulated light beam generated by the light reflector passes through an optical imaging lens in the distance detection calculation unit and is focused on a corresponding photosensitive detection pixel point Q 'in a photosensitive detector dot matrix behind the modulated light beam, and a plane B where the photosensitive detector dot matrix is located serves as a horizontal distance reference plane and extends to the plane B'. Taking an orthographic projection central point O 'of an optical center F of the optical imaging lens in a photosensitive detector lattice plane B (namely the intersection point of a central normal of the optical imaging lens and the photosensitive detector lattice plane B) as a coordinate origin, establishing a coordinate system X' O 'Y' in the photosensitive detector lattice plane B, wherein FO 'is vertical to the plane B, wherein the distance between the position Q' (X ', Y') of each photosensitive detection pixel point in the photosensitive detector lattice plane B in the X 'O' Y 'plane coordinate and FO' belongs to the known quantity in each distance detection calculation unit, because the position of each photosensitive detection pixel point in the photosensitive detector lattice of each distance detection unit and the distance between the optical imaging lens and the photosensitive detector lattice plane are fixed and initially calibrated, specific position coordinate information and distance information are written in the initialization process. And each distance detection calculation unit transmits the position coordinate information of each photosensitive detection pixel point in the photosensitive detector dot matrix and the distance information between the optical imaging lens and the photosensitive detector dot matrix plane to a distance converter of the characteristic identification processing unit together with the measured actual distance between the measured point and the corresponding photosensitive detection pixel point.
Thus, the distance between a certain human body measured point Q and the corresponding photosensitive detection pixel point Q' in the measured area A can be converted into the horizontal distance d between the human body measured point Q and the lattice plane of the photosensitive detector according to the following formula:
horizontal distance d ═ QC ═ QQ · cos (a)
Wherein
As described above, for each distance detection computing unit, the position coordinate information (x ', y ') of each photosensitive detection pixel point and the distance information O ' F between the optical imaging lens and the photosensitive detector lattice plane are distance detectionThe inherent information of the measuring and calculating unit belongs to the known information parameters, and the distance QQ' between each measured person and the corresponding photosensitive detection pixel point can be obtained through a formula
Calculated by a distance calculator of a distance detection calculation unit. After the distance detection and calculation unit transmits the calculated distance QQ 'and the position coordinate information (x', y ') of the corresponding photosensitive detection pixel point and the distance information O' F between the optical imaging lens and the photosensitive detector lattice plane to the feature recognition and processing unit, the distance converter therein calculates the horizontal distance from the measured point of the human body to the photosensitive detector lattice plane based on the following formula:
the horizontal distance d is associated with the position coordinate information (x ', y') of the photosensitive detection pixel point, so that each photosensitive detection pixel point corresponds to a horizontal distance, and finally a horizontal distance distribution matrix is formed corresponding to the position information of all photosensitive detection pixel points on the photosensitive detector dot matrix, so that after a frame distance matrix detected by the distance detection calculation unit is obtained, the horizontal distance matrix from each measured point to the plane where the photosensitive detector dot matrix is located can be obtained through a distance converter, that is, the distances d1, d2, d3 and d4 … … in fig. 3 are converted into the corresponding distances d1 ', d 2', d3 'and d 4' … … in fig. 4, and the horizontal distance matrix distribution is formed by combining the position information of the corresponding photosensitive pixel points associated with the distances.
Thus, after the distance converter in the feature recognition processing unit performs the distance conversion operation, the actual distance matrix between the human body and the distance detection calculating unit can be converted into the horizontal distance matrix of the human body corresponding to the actual distance matrix relative to the preset reference plane.
And the converted horizontal distance matrix is sent to the feature comparison processor of the feature identification processing unit by the distance detection calculation unit, and the feature identification processing unit extracts the actual human body curve feature data corresponding to the human body surface in the horizontal distance matrix. The actual human body curve characteristic data at least comprises the human body front characteristic data, the human body back characteristic data and the human body side characteristic data. Specifically, the human body positive feature data comprises a nose, a mouth, a chin and/or a neck of the human body face; the human body back characteristic data comprises the back of the head of the human body and/or the back of the neck of the human body; the body side feature data includes body shoulders, arms, and/or hands.
Referring to fig. 7, in this embodiment, the distance detection calculating unit is installed in the middle of the top of the wall of the room, the detection view angle of the distance detection calculating unit faces the room, when the user moves to a position a1 in fig. 7, the front face of the user faces the distance detection calculating unit, and at this time, the feature recognition processing unit extracts actual human body curve feature data corresponding to the surface of the human body in the horizontal distance matrix as human body front face feature data of the user. When the user moves to a position A2 in FIG. 7, the side of the user faces the distance detection calculation unit, and the feature recognition processing unit extracts the actual human body curve feature data corresponding to the human body surface in the horizontal distance matrix as the human body side feature data of the user. When the user moves to a position a3 in fig. 7, the back of the user faces the distance detection calculation unit, and at this time, the feature recognition processing unit extracts the actual human body curve feature data corresponding to the human body surface in the horizontal distance matrix as the human body side feature data of the user.
After the actual human body curve characteristic data are extracted, the characteristic comparison processor compares and analyzes the actual human body curve characteristic data with standard human body curve characteristic data after the human body falls down, wherein the standard human body curve characteristic data are calibrated in advance relative to the preset reference surface. The following two results are obtained after alignment analysis, which are as follows:
(1) when the characteristic comparison processor judges that the similarity between the actual human body curve characteristic data and the standard human body curve characteristic data calibrated in advance relative to the preset reference surface is smaller than a preset similarity threshold value, the human body curve characteristic of the human body is not matched with the curve characteristic of the human body after falling, namely the human body does not fall, and therefore related personnel are not required to be informed to rescue.
(2) When the characteristic comparison processor judges that the similarity between the actual human body curve characteristic data and the standard human body curve characteristic data calibrated in advance relative to the preset reference surface is greater than or equal to a preset similarity threshold value, the human body curve characteristic of the human body is matched with the curve characteristic of the human body after falling, namely the human body falls and needs rescue.
Specifically, when the feature comparison processor determines whether the similarity between the actual body curve feature data and the standard body curve feature data calibrated in advance relative to the predetermined reference plane is a preset similarity threshold, referring to fig. 8 to 10, in this embodiment, the predetermined reference plane is perpendicular to the ground. When the person moves towards the distance detection and calculation unit, the characteristic recognition processing unit converts to obtain that the horizontal distance matrix is the human body curve contour formed by the human body front as shown in fig. 8, when the person slides to the right, the state that the actual human body slides is shown in fig. 9, the characteristic recognition processing unit converts to obtain that the horizontal distance matrix is the human body curve contour as shown in fig. 10, the comparison between fig. 8 and fig. 10 can discover that when the person falls, the human body curve obtained by the characteristic recognition processing unit is zigzag, and the head height of the person when falling is far lower than the head height of the person when the person normally walks, so that the human body curve when the person normally walks has obvious difference, and thus, whether the person falls can be more accurately judged by judging, and rescue can be accurately implemented.
In another embodiment of the present invention, referring to fig. 11 to 12, the predetermined reference plane is parallel to the ground, and when a person falls, referring to fig. 12, the human body curve obtained by the feature recognition processing unit is more tortuous, and the area of the ground covered by the falling person is larger, and in addition, the height of the top of the head of the falling person is also far lower than the height of the top of the head of the person when the person normally walks, so that the human body curve when the person normally walks has a significant difference, and thus, by such judgment, whether the person falls or not can be more accurately judged, thereby accurately performing rescue. It should be noted that the predetermined reference surface is obtained by installing the ToF sensor according to the actual application requirement by a person skilled in the art, and is not limited to the installation manners of the two predetermined reference surfaces, as long as the characteristic curve of the surface of the human body can be accurately identified.
The standard human body curve characteristic data after falling comprises human body curve characteristic data when the human body falls. The human body curve characteristic data when the human body falls are stored in the characteristic identification processing unit in advance, and the human body curve characteristic data when the human body falls comprise various human body curve characteristic data when the human body falls, and are stored in the characteristic identification processing unit in advance.
And when the human body is judged to have fallen, the characteristic identification processing unit sends a data packet to the fall detection control unit so as to inform the fall rescue personnel to implement fall rescue on the fall rescue personnel. The data packet at least comprises address information (such as a house number) where the distance detection and calculation unit is located and fall time information, wherein the address information and the fall time information are prestored in the feature identification processing unit when the distance detection and calculation unit is installed.
Specifically, the fall detection control unit comprises a network system and a terminal device, wherein the network system is connected with the output module, and the terminal device is connected with the network system.
The data packet is sent to the network system by the characteristic comparison processor through the output module, and the sending mode can be a wireless mode such as wifi, Bluetooth and the like or a wired mode, namely, the data packet is directly sent through a network cable. The network system can be a cloud server or the like.
And the network system sends the data packet to the terminal equipment, the terminal equipment is at least a mobile phone or a computer, and the terminal equipment receives the data packet and obtains the address information and the fall time information through analysis, so that the fall personnel are rescued according to the address information and the fall time information.
Finally, a fall detection method based on the fall detection system of the present invention is briefly described:
step one, installing a light emitter and an optical imaging lens of the falling detection system at the preset position;
secondly, a modulator of the distance detection and calculation unit generates a modulation signal, and after the generated modulation signal is transmitted to the light emitter, the light emitter emits corresponding modulation light outwards;
step three, the modulated light emitted by the light emitter is reflected to an optical imaging lens after encountering a human body serving as a measured object;
fourthly, receiving reflected modulated light reflected back by a photosensitive detector lattice positioned at the rear side of the optical imaging lens in the distance detection and calculation unit through the lens, and enabling a distance calculator of the distance detection and calculation unit to reflect the phase difference and the period of the modulated light through the reflected modulated light and the emitted modulated light, wherein the formula is based on:
calculating to obtain an actual distance matrix from the measured object to the photosensitive detector dot matrix;
fifthly, the distance converter of the characteristic identification processing unit bases the received actual distance matrix of the human body and the photosensitive detector dot matrix on a formula
Converting the distance matrix into a horizontal distance matrix of the human body relative to the lattice plane of the photosensitive detector, and transmitting the horizontal distance matrix to a characteristic comparison processor of a characteristic identification processing unit, wherein QQ 'is actual distance data of the human body and the lattice of the photosensitive detector, and (x', y ') and O' F are known parameters in the lattice of the photosensitive detector;
sixthly, extracting actual human body curve characteristic data corresponding to the human body surface in the horizontal distance matrix obtained in the step two by a characteristic comparison processor of the characteristic identification processing unit, wherein the actual human body curve characteristic data at least comprises the human body front characteristic data, the human body back characteristic data and the human body side characteristic data,
and step seven, based on the comparative analysis result in the step six, executing the following control operation:
(1) when the characteristic identification processing unit judges that the similarity between the actual human body curve characteristic data and the standard human body curve characteristic data calibrated in advance relative to the preset reference surface is smaller than a preset similarity threshold, turning to a second step;
(2) when the similarity between the actual human body curve characteristic data and the standard human body curve characteristic data calibrated in advance relative to the preset reference surface is judged to be more than or equal to a preset similarity threshold value through the characteristic identification processing unit, turning to the step eight;
and step eight, the fall detection control unit informs fall rescuers to implement fall rescue for the fall rescuers.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (12)
1. A fall detection method is characterized by comprising the following steps:
step one, acquiring an actual distance matrix between a human body and a preset position in real time;
step two, converting the actual distance matrix obtained in the step one into a horizontal distance matrix of the human body relative to a preset reference surface;
extracting actual human body curve characteristic data corresponding to the human body surface in the horizontal distance matrix obtained in the step two, wherein the actual human body curve characteristic data at least comprises the human body front side characteristic data, the human body back side characteristic data and the human body side surface characteristic data;
comparing and analyzing the actual human body curve characteristic data obtained in the step three with standard human body curve characteristic data calibrated in advance relative to the preset reference surface after the human body falls, wherein the standard human body curve characteristic data after the human body falls comprises human body curve characteristic data when the human body falls;
step five, according to the comparison analysis result, executing the following operations:
(1) if the similarity between the actual human body curve characteristic data and the standard human body curve characteristic data calibrated in advance relative to the preset reference plane is smaller than a preset similarity threshold, turning to the first step;
(2) if the actual human body curve characteristic data and the standard human body curve characteristic data calibrated in advance relative to the preset reference surface are larger than or equal to a preset similarity threshold, turning to a sixth step;
and step six, informing the falling rescue personnel to implement the falling rescue for the falling rescue personnel.
2. The fall detection method according to claim 1, characterized in that said fourth step comprises the following steps:
(1) after the human body falls down, calibrating a horizontal mapping contour formed by horizontal distances of all characteristic points on the surface of the human body relative to the preset reference surface in advance as body curve characteristic data of the standard human body after falling down;
(2) and comparing and analyzing the actual human body curve characteristic data with the standard human body curve characteristic data after the human body falls down.
3. The fall detection method according to claim 1, characterized in that said human body positive feature data comprise the nose, mouth, chin and/or neck of the human body face; the human body back characteristic data comprises the back of the head of the human body and/or the back of the neck of the human body; the body side feature data includes body shoulders, arms, and/or hands.
4. The fall detection method according to claim 1, characterized in that said step one comprises the following steps:
(1) installing the light emitter and the optical imaging lens at the preset position, and enabling the light emitter and the optical imaging lens to be opposite to the upper part of the writing plane;
(2) generating a modulation signal to a light emitter through a modulator, and emitting a modulated detection light beam outwards by the light emitter;
(3) when a detection light beam emitted by the light emitter meets a human body, the detection light beam is reflected to the optical imaging lens after passing through the human body;
(4) the photosensitive detector lattice behind the optical imaging lens receives the reflected light beam via the optical imaging lens and determines the phase difference and period between the reflected light beam and the emitted light beam based on the formula
And calculating to obtain the actual distance between the human body reflection part of the reflected light beam and the corresponding photosensitive detection pixel point in the photosensitive detector lattice receiving the reflected light beam, wherein the distance is used as the actual distance between the human body and the preset position.
5. The fall detection method according to claim 1, characterized in that said second step specifically comprises the following steps:
(1) selecting the preset reference surface as a plane where the photosensitive detector lattice is located, and establishing a plane coordinate system on the preset reference surface, wherein the origin of coordinates is an intersection point of a normal line passing through the optical center of the optical imaging lens and the preset reference surface, and the distance between the origin of coordinates and the optical center is marked as O' F;
(2) converting the actual distance between the human body reflecting part of the reflected light beam and the corresponding photosensitive detection pixel point in the photosensitive detector lattice receiving the reflected light beam into the horizontal distance between the human body reflecting part and the preset reference surface by the following formula:
wherein, QQ ' is the actual distance between the human body reflective part of the reflected light beam and the corresponding photosensitive detection pixel in the photosensitive detector lattice receiving the reflected light beam, and (x ', y ') is the position coordinate of the corresponding photosensitive detection pixel in the plane coordinate system of the predetermined reference plane.
6. A fall detection method is characterized in that the fall detection method is carried out based on a fall detection system, and the fall detection system comprises a distance detection and calculation unit, a characteristic identification processing unit and a fall detection control unit which are sequentially connected; the tumble detection method specifically comprises the following steps:
step one, acquiring an actual distance matrix between a human body and a preset position in real time through the distance detection and calculation unit;
secondly, converting the actual distance matrix obtained in the first step into a horizontal distance matrix of the human body relative to a preset reference surface through the characteristic identification processing unit;
extracting actual human body curve characteristic data corresponding to the surface of the human body in the horizontal distance matrix obtained in the step two through the characteristic identification processing unit, wherein the actual human body curve characteristic data at least comprises the human body front characteristic data, the human body back characteristic data and the human body side characteristic data;
comparing and analyzing the actual human body curve characteristic data obtained in the step three with standard human body curve characteristic data calibrated in advance relative to the preset reference surface after the human body falls through the characteristic identification processing unit, wherein the standard human body curve characteristic data after the human body falls comprise human body curve characteristic data when the human body falls;
step five, according to the comparison analysis result, executing the following operations:
(1) judging whether the similarity between the actual human body curve characteristic data and the standard human body curve characteristic data calibrated in advance relative to the preset reference plane is smaller than a preset similarity threshold value through the characteristic identification processing unit, and turning to the first step;
(2) judging whether the similarity between the actual human body curve characteristic data and the standard human body curve characteristic data calibrated in advance relative to the preset reference plane after the human body falls over is larger than or equal to a preset similarity threshold value through the characteristic identification processing unit, and turning to a sixth step;
and step six, informing the falling rescue workers to implement falling rescue through the falling detection control unit.
7. The fall detection method according to claim 6, wherein said distance detection calculation unit comprises a light emitter, a modulator, an optical imaging lens, a photosensitive detector matrix, a controller and a distance calculator; the controller is connected with the modulator and the photosensitive detector dot matrix, the modulator is connected with the light emitter and the photosensitive detector dot matrix, the light emitter is used for emitting modulated detection light beams, the detection light beams are reflected by a human body as a detected object and then are incident to the optical imaging lens, and the detection light beams are input to the photosensitive detector dot matrix after being shaped by the optical imaging lens, the photosensitive detector lattice is arranged right behind the optical imaging lens and connected to the distance calculator, the distance calculator calculates actual distance information between the measured object and the photosensitive detector dot matrix based on the reflected light beam information received by the photosensitive detector dot matrix, and the actual distance information and the inherent information of the photosensitive detector lattice are transmitted to a controller, and then the controller transmits the related information to the characteristic identification processing unit.
8. The fall detection method according to claim 7, wherein said photo detector lattice has a plurality of photo detection pixels arranged in a matrix array, each photo detection pixel being an individual photo detector element, modulated detection beams emitted by the light emitter are reflected by multiple points on the surface of a detected object and then are respectively incident on corresponding photosensitive detection pixel points of the photosensitive detector lattice, each photosensitive detection pixel point of the photosensitive detector lattice receives a reflected light beam from a corresponding reflection point on the surface of the measured object, the actual distance information calculated by the distance calculator is an actual distance matrix corresponding to the position of each reflecting point of the measured object, and the horizontal distance information obtained by converting the actual distance information is converted into a horizontal distance matrix corresponding to the position of each photosensitive detection pixel point of the photosensitive detector dot matrix by the characteristic identification processing unit.
9. The fall detection method according to claim 8, characterized in that the modulated detection beam emitted by said light emitter is a sine wave, a pulsed wave or other periodic modulated wave; the distance calculator calculates the actual distance between a certain reflection point of the measured object and the photosensitive detection pixel point corresponding to the photosensitive detector lattice based on the following formula:
wherein: c is the speed of light, T is the period of the modulated wave,
the phase difference between the reflected light beam received by the corresponding photosensitive detection pixel point and the corresponding detection light beam emitted by the light emitter is obtained.
10. The fall detection method according to claim 9, wherein the feature recognition processing unit comprises a communication interface module, a distance converter, a feature comparison processor, a standard feature memory and an output module, the communication interface module is connected to the controller of the distance detection computing unit, the distance converter is connected to the communication interface module, the feature comparison processor is connected to the distance converter, the standard feature memory is connected to the feature comparison processor, the output module is connected to the feature comparison processor;
the distance converter converts an actual distance matrix between the human body and the distance detection calculation unit into a horizontal distance matrix of the human body relative to a plane where the photosensitive detector lattice is located, and then transmits the horizontal distance matrix to the characteristic comparison processor;
an intelligent control trigger area is arranged in the characteristic comparison processor, the characteristic comparison processor judges whether the human body is positioned in the intelligent control trigger area of the falling detection system or not according to the horizontal distance matrix, if the human body is detected to be positioned in the intelligent control trigger area, actual human body curve characteristic data corresponding to the surface of the human body in the horizontal distance matrix are extracted, and the actual human body curve characteristic data are compared and analyzed with standard human body curve characteristic data calibrated in advance relative to the preset reference surface after the human body falls; if the similarity between the actual human body curve characteristic data and the standard human body curve characteristic data after falling is larger than or equal to a preset similarity threshold value, the falling detection control unit informs the falling rescue staff of implementing the falling rescue to the falling staff.
11. The fall detection method according to claim 10, characterized in that said distance converter converts the actual distance matrix into the horizontal distance matrix by:
firstly, the distance converter converts the measured distance between each reflection point on the surface of the measured object and the corresponding photosensitive detection pixel point into the horizontal distance of the reflection point on the surface of the measured object relative to the plane where the photosensitive detector lattice is located according to the following formula:
the QQ' is the measured distance between the surface reflection point of the measured object and the corresponding photosensitive detection pixel point, and is calculated by a distance calculator in the distance detection calculation unit; (x ', y') is the position coordinate of the corresponding photosensitive detection pixel point in the photosensitive detector lattice plane coordinate system; o' F is the distance between the optical center of the optical imaging lens and the origin of coordinates in the lattice plane coordinate system of the photosensitive detector; d is the horizontal distance of the reflection point on the surface of the measured object relative to the plane where the photosensitive detector lattice is located;
the photosensitive detector lattice plane coordinate system refers to: the method comprises the following steps of taking an intersection point of a straight line which passes through the optical center of the optical imaging lens and is perpendicular to the plane where a photosensitive detector dot matrix is located and the plane where the photosensitive detector dot matrix is located as a coordinate origin, and establishing a coordinate system in the plane where the photosensitive detector dot matrix is located, wherein the position coordinate of each photosensitive detection pixel point in the photosensitive detector dot matrix plane coordinate system and the distance between the optical center of the optical imaging lens and the coordinate origin belong to known quantities;
and secondly, the distance converter correlates each horizontal distance obtained by conversion with the position of the corresponding photosensitive detection pixel point to form the horizontal distance matrix.
12. The fall detection method according to any one of claims 6 to 11, characterized in that it comprises in particular the following steps:
step one, installing a light emitter and an optical imaging lens of the falling detection system at the preset position;
secondly, a modulator of the distance detection and calculation unit generates a modulation signal, and after the generated modulation signal is transmitted to the light emitter, the light emitter emits corresponding modulation light outwards;
step three, the modulated light emitted by the light emitter is reflected to an optical imaging lens after encountering a human body serving as a measured object;
fourthly, receiving reflected modulated light reflected back by a photosensitive detector lattice positioned at the rear side of the optical imaging lens in the distance detection and calculation unit through the lens, and enabling a distance calculator of the distance detection and calculation unit to reflect the phase difference and the period of the modulated light through the reflected modulated light and the emitted modulated light, wherein the formula is based on:
calculating to obtain an actual distance matrix from the measured object to the photosensitive detector dot matrix;
fifthly, the distance converter of the characteristic identification processing unit bases the received actual distance matrix of the human body and the photosensitive detector dot matrix on a formula
Converting the distance matrix into a horizontal distance matrix of the human body relative to the lattice plane of the photosensitive detector, and transmitting the horizontal distance matrix to a characteristic comparison processor of a characteristic identification processing unit, wherein QQ 'is actual distance data of the human body and the lattice of the photosensitive detector, and (x', y ') and O' F are known parameters in the lattice of the photosensitive detector;
sixthly, extracting actual human body curve characteristic data corresponding to the human body surface in the horizontal distance matrix obtained in the step two by a characteristic comparison processor of the characteristic identification processing unit, wherein the actual human body curve characteristic data at least comprises the human body front characteristic data, the human body back characteristic data and the human body side characteristic data,
and step seven, based on the comparative analysis result in the step six, executing the following control operation:
(1) when the characteristic identification processing unit judges that the similarity between the actual human body curve characteristic data and the standard human body curve characteristic data calibrated in advance relative to the preset reference surface is smaller than a preset similarity threshold, turning to a second step;
(2) when the similarity between the actual human body curve characteristic data and the standard human body curve characteristic data calibrated in advance relative to the preset reference surface is judged to be more than or equal to a preset similarity threshold value through the characteristic identification processing unit, turning to the step eight;
and step eight, the fall detection control unit informs fall rescuers to implement fall rescue for the fall rescuers.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010195028.0A CN111265139A (en) | 2020-03-19 | 2020-03-19 | Intelligent toilet seat control method |
| CN2020101950280 | 2020-03-19 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111685633A true CN111685633A (en) | 2020-09-22 |
Family
ID=70992506
Family Applications (13)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010195028.0A Pending CN111265139A (en) | 2020-03-19 | 2020-03-19 | Intelligent toilet seat control method |
| CN202010712063.5A Pending CN111685632A (en) | 2020-03-19 | 2020-07-22 | Handrail elevator cover plate detection method |
| CN202010712077.7A Pending CN111759215A (en) | 2020-03-19 | 2020-07-22 | Automatic door opening and closing control method |
| CN202010712064.XA Pending CN111759214A (en) | 2020-03-19 | 2020-07-22 | Automatic door opening and closing control method |
| CN202010712052.7A Pending CN111759213A (en) | 2020-03-19 | 2020-07-22 | Elevator fault monitoring method |
| CN202010713410.6A Active CN111671352B (en) | 2020-03-19 | 2020-07-22 | Automatic door induction triggering area adjusting method |
| CN202010713409.3A Pending CN111685634A (en) | 2020-03-19 | 2020-07-22 | Elevator door opening and closing control method |
| CN202010713421.4A Pending CN111685636A (en) | 2020-03-19 | 2020-07-22 | Intelligent control method and device for electric appliance |
| CN202010712076.2A Pending CN111685633A (en) | 2020-03-19 | 2020-07-22 | Tumble detection method |
| CN202010712086.6A Pending CN111759216A (en) | 2020-03-19 | 2020-07-22 | Automatic door opening and closing control method |
| CN202010711979.9A Active CN111759212B (en) | 2020-03-19 | 2020-07-22 | Intelligent toilet seat control method |
| CN202010712031.5A Pending CN111685631A (en) | 2020-03-19 | 2020-07-22 | People flow monitoring method at handrail elevator cover plate |
| CN202010713417.8A Pending CN111685635A (en) | 2020-03-19 | 2020-07-22 | Human body sitting posture correction method |
Family Applications Before (8)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010195028.0A Pending CN111265139A (en) | 2020-03-19 | 2020-03-19 | Intelligent toilet seat control method |
| CN202010712063.5A Pending CN111685632A (en) | 2020-03-19 | 2020-07-22 | Handrail elevator cover plate detection method |
| CN202010712077.7A Pending CN111759215A (en) | 2020-03-19 | 2020-07-22 | Automatic door opening and closing control method |
| CN202010712064.XA Pending CN111759214A (en) | 2020-03-19 | 2020-07-22 | Automatic door opening and closing control method |
| CN202010712052.7A Pending CN111759213A (en) | 2020-03-19 | 2020-07-22 | Elevator fault monitoring method |
| CN202010713410.6A Active CN111671352B (en) | 2020-03-19 | 2020-07-22 | Automatic door induction triggering area adjusting method |
| CN202010713409.3A Pending CN111685634A (en) | 2020-03-19 | 2020-07-22 | Elevator door opening and closing control method |
| CN202010713421.4A Pending CN111685636A (en) | 2020-03-19 | 2020-07-22 | Intelligent control method and device for electric appliance |
Family Applications After (4)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010712086.6A Pending CN111759216A (en) | 2020-03-19 | 2020-07-22 | Automatic door opening and closing control method |
| CN202010711979.9A Active CN111759212B (en) | 2020-03-19 | 2020-07-22 | Intelligent toilet seat control method |
| CN202010712031.5A Pending CN111685631A (en) | 2020-03-19 | 2020-07-22 | People flow monitoring method at handrail elevator cover plate |
| CN202010713417.8A Pending CN111685635A (en) | 2020-03-19 | 2020-07-22 | Human body sitting posture correction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (13) | CN111265139A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112669567A (en) * | 2020-12-18 | 2021-04-16 | 广东智源信达工程有限公司 | Linkage control method and system for endowment monitoring alarm and video monitoring |
| CN113593181A (en) * | 2021-07-14 | 2021-11-02 | 三偲科技(北京)有限公司 | Safety early warning method and device based on intelligent slippers |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111265139A (en) * | 2020-03-19 | 2020-06-12 | 广东蓝水花智能电子有限公司 | Intelligent toilet seat control method |
| CN112270815B (en) * | 2020-12-23 | 2021-03-16 | 四川写正智能科技有限公司 | Read-write gesture recognition method and system based on smart watch |
| CN113009897A (en) * | 2021-03-09 | 2021-06-22 | 北京灵汐科技有限公司 | Control method and device of intelligent household appliance, intelligent household appliance and storage medium |
| CN113341737B (en) * | 2021-05-18 | 2023-11-10 | 珠海格力电器股份有限公司 | Control method, system, device, equipment and storage medium of intelligent household equipment |
| CN113460839B (en) * | 2021-07-23 | 2023-08-01 | 深圳市爱深盈通信息技术有限公司 | Elevator door control method and anti-pinch detection module |
| CN113585913B (en) * | 2021-07-28 | 2022-09-09 | 广东蓝水花智能电子有限公司 | Automatic door and method for setting triggering area of automatic door |
| CN114360235A (en) * | 2022-01-12 | 2022-04-15 | 广东蓝水花智能电子有限公司 | Toilet seat control method and system based on FMCW microwave inductor |
| CN114384824A (en) * | 2022-01-12 | 2022-04-22 | 广东蓝水花智能电子有限公司 | Intelligent toilet control method and device |
| CN115676565B (en) * | 2022-10-12 | 2023-11-21 | 宁波微科光电股份有限公司 | Elevator door opening and closing protection method and system based on laser intelligent light curtain |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103654596A (en) * | 2012-09-26 | 2014-03-26 | 大老巷护康科技股份有限公司 | Toilet seat measuring, mounting and fixing method |
| CN105160285A (en) * | 2015-06-09 | 2015-12-16 | 贾勇哲 | Method and system for recognizing human body tumble automatically based on stereoscopic vision |
| CN109110603A (en) * | 2017-06-22 | 2019-01-01 | 株式会社日立大厦系统 | elevator and escalator |
| CN111265139A (en) * | 2020-03-19 | 2020-06-12 | 广东蓝水花智能电子有限公司 | Intelligent toilet seat control method |
Family Cites Families (74)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| NL83894C (en) * | 1952-09-04 | |||
| FR2670225A1 (en) * | 1990-12-10 | 1992-06-12 | Denance Raymond | W.C. OF WHICH THE RELEASE OF THE COLUMN OF RINSING WATER PRESSURES THE BOWL OF WHICH THE CLOSURE IS HERMETIC. |
| CN2814436Y (en) * | 2005-04-21 | 2006-09-06 | 太阳自动门(天津)有限公司 | Adjustable induction angle and range radar inductor |
| JP5022809B2 (en) * | 2007-08-01 | 2012-09-12 | 株式会社日立ビルシステム | Abnormality monitoring device in elevator car |
| JP4606475B2 (en) * | 2008-03-12 | 2011-01-05 | 株式会社日立製作所 | Elevator door control system and method |
| WO2010017318A2 (en) * | 2008-08-05 | 2010-02-11 | Mr Technology Inc. | Differential gradiometric magnetometer, system and method of use |
| CN101644074A (en) * | 2008-08-07 | 2010-02-10 | 台达电子工业股份有限公司 | Flushing device and flushing control method thereof |
| JP4753320B2 (en) * | 2008-09-09 | 2011-08-24 | 東芝エレベータ株式会社 | Escalator monitoring system |
| CN101483001A (en) * | 2009-01-04 | 2009-07-15 | 北京中星微电子有限公司 | Video-based intrusion detection method, detection apparatus and chip |
| EP2208831A1 (en) * | 2009-01-20 | 2010-07-21 | Geberit International AG | Method and electronic control device for contact-less control of a sanitary assembly |
| JP5600399B2 (en) * | 2009-05-19 | 2014-10-01 | 株式会社日立製作所 | Elevator equipment |
| CN101630410B (en) * | 2009-08-18 | 2011-08-17 | 北京航空航天大学 | Human body sitting posture judgment method based on single camera |
| CN201538630U (en) * | 2009-09-11 | 2010-08-04 | 包文丽 | Drive device of elevator |
| CN102096801A (en) * | 2009-12-14 | 2011-06-15 | 北京中星微电子有限公司 | Sitting posture detecting method and device |
| CN102009883B (en) * | 2010-12-22 | 2012-12-26 | 日立电梯（中国）有限公司 | Position detector for elevator cage |
| WO2012155828A1 (en) * | 2011-05-17 | 2012-11-22 | 厦门松霖卫厨有限公司 | Toilet seat having vibrating alarm |
| CN102496232B (en) * | 2011-12-12 | 2014-05-07 | 杭州市电力局 | Transmission facility monitoring method and system |
| CN103158634B (en) * | 2011-12-14 | 2014-12-24 | 苏州万隆汽车零部件股份有限公司 | Pixel splicing type interior trimming automobile door |
| KR20130085589A (en) * | 2012-01-20 | 2013-07-30 | 김성훈 | Sanitary toilet |
| CN102633173B (en) * | 2012-05-04 | 2014-10-15 | 林创鲁 | System and method for monitoring operation state of elevator car |
| CN103803387A (en) * | 2012-11-08 | 2014-05-21 | 华升富士达电梯有限公司 | Elevator door equipment for elevator and control method thereof |
| CN103910259A (en) * | 2013-01-06 | 2014-07-09 | 左跃进 | Special removable wellhead cover plate device for safety component inspection equipment of elevator |
| JP5784051B2 (en) * | 2013-01-07 | 2015-09-24 | 東芝エレベータ株式会社 | Elevator system |
| CN103303779A (en) * | 2013-06-25 | 2013-09-18 | 康力电梯股份有限公司 | Monitoring system of escalator machine room cover plate |
| CN103383802A (en) * | 2013-06-26 | 2013-11-06 | 上海斐讯数据通信技术有限公司 | Sitting posture reminding system |
| CN103499819B (en) * | 2013-09-22 | 2015-06-24 | 中国科学院光电技术研究所 | Measuring device and method for target line-of-sight angel offset and distance |
| CN103679174A (en) * | 2013-12-04 | 2014-03-26 | 中国科学院深圳先进技术研究院 | Shape descriptor generating method and device |
| CN104933816B (en) * | 2014-03-17 | 2017-08-11 | 南充鑫源通讯技术有限公司 | The distance of reaction method to set up and device of a kind of automatic sensing safety-protection system |
| CN103870659B (en) * | 2014-03-28 | 2016-12-07 | 吉林大学 | A kind of fault of numerical control machine tool analyzes method |
| CN103908064A (en) * | 2014-04-03 | 2014-07-09 | 安徽海聚信息科技有限责任公司 | Intelligent desk with sitting posture correcting function and correcting method implemented by intelligent desk |
| JP6795136B2 (en) * | 2014-05-08 | 2020-12-02 | オプテックス株式会社 | Active object detection sensor |
| CN104190837A (en) * | 2014-07-17 | 2014-12-10 | 奚进洲 | Method and device for monitoring running state of cold header |
| CN204175091U (en) * | 2014-09-21 | 2015-02-25 | 王俭俭 | Automatic door control system |
| CN106032232B (en) * | 2015-03-11 | 2018-10-19 | 上海三菱电梯有限公司 | The identification device of lift car place holder and recognition methods |
| CN104909232A (en) * | 2015-06-29 | 2015-09-16 | 周志鸿 | Elevator operation height detection device and system |
| CN105060043B (en) * | 2015-07-14 | 2017-03-29 | 日立电梯（中国）有限公司 | A kind of device for making car door sill align with landing sill |
| JP6480824B2 (en) * | 2015-07-27 | 2019-03-13 | 株式会社日立製作所 | Distance image sensor parameter adjustment method, parameter adjustment apparatus, and elevator system |
| CN105110113A (en) * | 2015-07-28 | 2015-12-02 | 苏州汇川技术有限公司 | Elevator floor leveling position control system and method |
| CN105016186A (en) * | 2015-07-31 | 2015-11-04 | 苏州宏展信息科技有限公司 | Safety interlocking system for escalator |
| CN205041993U (en) * | 2015-09-25 | 2016-02-24 | 惠州莫思特科技有限公司 | Automatic escape device |
| CN105540363A (en) * | 2015-12-16 | 2016-05-04 | 中冶南方（武汉）自动化有限公司 | Group control system for multi-car elevators and safety control method thereof |
| JP6068694B1 (en) * | 2016-01-13 | 2017-01-25 | 東芝エレベータ株式会社 | Elevator boarding detection system |
| CN111784615A (en) * | 2016-03-25 | 2020-10-16 | 北京三星通信技术研究有限公司 | Method and device for processing multimedia information |
| EP3443300A4 (en) * | 2016-04-14 | 2019-10-09 | Origin Wireless, Inc. | Methods, apparatus, servers, and systems for object tracking |
| CN107304024A (en) * | 2016-04-19 | 2017-10-31 | 广东蓝水花智能电子有限公司 | A kind of handrail elevator safety guard |
| CN205603023U (en) * | 2016-04-19 | 2016-09-28 | 广东蓝水花智能电子有限公司 | Handrail elevator safety arrangement |
| US10241514B2 (en) * | 2016-05-11 | 2019-03-26 | Brain Corporation | Systems and methods for initializing a robot to autonomously travel a trained route |
| CN205713015U (en) * | 2016-05-25 | 2016-11-23 | 杭州智仁建筑工程有限公司 | A kind of high security building foot support |
| CN205740002U (en) * | 2016-06-17 | 2016-11-30 | 广东蓝水花智能电子有限公司 | A kind of handrail elevator direction indicating device |
| CN105967037B (en) * | 2016-06-17 | 2018-07-06 | 广东蓝水花智能电子有限公司 | A kind of handrail elevator direction indicating device |
| CN106223435B (en) * | 2016-07-18 | 2019-02-22 | 京东方科技集团股份有限公司 | A kind of closestool |
| CN106108760B (en) * | 2016-08-25 | 2018-11-06 | 京东方科技集团股份有限公司 | A kind of intelligent closestool |
| JP6949851B2 (en) * | 2016-08-29 | 2021-10-13 | ナブテスコ株式会社 | Sensor detection area adjustment system, automatic door sensor, marker and sensor detection area adjustment method |
| CN206142587U (en) * | 2016-08-30 | 2017-05-03 | 住友富士电梯有限公司 | Elevator intelligence infrared curtain |
| CN106395538B (en) * | 2016-12-06 | 2019-03-12 | 宁波永良电梯技术发展有限公司 | Lift car stops detection system and its detection method |
| CN206380151U (en) * | 2017-01-19 | 2017-08-04 | 深圳市犇拓电子科技有限公司 | A kind of environment sensing identification control device based on light sensation radar |
| CN106959864A (en) * | 2017-03-31 | 2017-07-18 | 维沃移动通信有限公司 | A kind of adjusting method and mobile terminal of interface display effect |
| CN106920371A (en) * | 2017-04-01 | 2017-07-04 | 浙江陀曼精密机械有限公司 | A kind of ultrasonic wave sitting posture seat detection system and its detection method |
| CN107038786A (en) * | 2017-04-28 | 2017-08-11 | 深圳市新和创软件有限公司 | Gate inhibition's face identification method and its system |
| DE112017007678T5 (en) * | 2017-06-22 | 2020-03-05 | Mitsubishi Electric Corporation | Elevator device |
| US10610069B2 (en) * | 2018-01-06 | 2020-04-07 | Kohler Co. | Toilet seat and hinge |
| CN108416256A (en) * | 2018-01-17 | 2018-08-17 | 南京邮电大学 | The family's cloud intelligent monitor system and monitoring method of feature based identification |
| CN108470373B (en) * | 2018-02-14 | 2019-06-04 | 天目爱视（北京）科技有限公司 | It is a kind of based on infrared 3D 4 D data acquisition method and device |
| CN108810255A (en) * | 2018-05-22 | 2018-11-13 | 深圳奥比中光科技有限公司 | User health is urged to use the method and intelligent mobile terminal of intelligent mobile terminal |
| CN108706429A (en) * | 2018-06-12 | 2018-10-26 | 佛山市灏金赢科技有限公司 | A kind of elevator door closing control system and control method |
| CN108875701A (en) * | 2018-07-11 | 2018-11-23 | 温州亿通自动化设备有限公司 | A kind of inlet/outlet passenger number automatic statistics method |
| CN109019280A (en) * | 2018-08-16 | 2018-12-18 | 合肥工业大学 | Escalator operation quality determining method |
| CN209220104U (en) * | 2018-08-23 | 2019-08-09 | 深圳市博电电子技术有限公司 | A kind of toilet seat Intelligent cover plate and intellectual water closet |
| CN109188723A (en) * | 2018-11-01 | 2019-01-11 | 许姜严 | A kind of spectacle-frame and myopia prevention system based on flight time distance detection device |
| CN109850730A (en) * | 2018-11-20 | 2019-06-07 | 日立楼宇技术（广州）有限公司 | The discrepancy door control method of particular space, device and system |
| CN109236107A (en) * | 2018-11-26 | 2019-01-18 | 上海钛米机器人科技有限公司 | A kind of control method of automatically-controlled door, device, system and storage medium |
| CN109763738A (en) * | 2019-01-30 | 2019-05-17 | 东莞市桥特电子科技有限公司 | A kind of automatically-controlled door |
| CN110037602B (en) * | 2019-04-22 | 2024-04-12 | 恒洁智能卫浴(深圳)有限公司 | Toilet cover plate, toilet and toilet control method |
| CN110292386B (en) * | 2019-06-24 | 2020-09-04 | 中国地质大学（武汉） | Human body sitting posture detection system and method based on video information and piezoelectric information |
-
2020
- 2020-03-19 CN CN202010195028.0A patent/CN111265139A/en active Pending
- 2020-07-22 CN CN202010712063.5A patent/CN111685632A/en active Pending
- 2020-07-22 CN CN202010712077.7A patent/CN111759215A/en active Pending
- 2020-07-22 CN CN202010712064.XA patent/CN111759214A/en active Pending
- 2020-07-22 CN CN202010712052.7A patent/CN111759213A/en active Pending
- 2020-07-22 CN CN202010713410.6A patent/CN111671352B/en active Active
- 2020-07-22 CN CN202010713409.3A patent/CN111685634A/en active Pending
- 2020-07-22 CN CN202010713421.4A patent/CN111685636A/en active Pending
- 2020-07-22 CN CN202010712076.2A patent/CN111685633A/en active Pending
- 2020-07-22 CN CN202010712086.6A patent/CN111759216A/en active Pending
- 2020-07-22 CN CN202010711979.9A patent/CN111759212B/en active Active
- 2020-07-22 CN CN202010712031.5A patent/CN111685631A/en active Pending
- 2020-07-22 CN CN202010713417.8A patent/CN111685635A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103654596A (en) * | 2012-09-26 | 2014-03-26 | 大老巷护康科技股份有限公司 | Toilet seat measuring, mounting and fixing method |
| CN105160285A (en) * | 2015-06-09 | 2015-12-16 | 贾勇哲 | Method and system for recognizing human body tumble automatically based on stereoscopic vision |
| CN109110603A (en) * | 2017-06-22 | 2019-01-01 | 株式会社日立大厦系统 | elevator and escalator |
| CN111265139A (en) * | 2020-03-19 | 2020-06-12 | 广东蓝水花智能电子有限公司 | Intelligent toilet seat control method |
Non-Patent Citations (1)
| Title |
|---|
| 李文龙: "基于2D/3D数据融合的位姿测量方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112669567A (en) * | 2020-12-18 | 2021-04-16 | 广东智源信达工程有限公司 | Linkage control method and system for endowment monitoring alarm and video monitoring |
| CN113593181A (en) * | 2021-07-14 | 2021-11-02 | 三偲科技(北京)有限公司 | Safety early warning method and device based on intelligent slippers |
| CN113593181B (en) * | 2021-07-14 | 2022-08-26 | 三偲科技(北京)有限公司 | Safety early warning method and device based on intelligent slippers |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111759213A (en) | 2020-10-13 |
| CN111685636A (en) | 2020-09-22 |
| CN111685635A (en) | 2020-09-22 |
| CN111671352A (en) | 2020-09-18 |
| CN111685634A (en) | 2020-09-22 |
| CN111759215A (en) | 2020-10-13 |
| CN111759212B (en) | 2022-05-13 |
| CN111685632A (en) | 2020-09-22 |
| CN111265139A (en) | 2020-06-12 |
| CN111671352B (en) | 2022-05-13 |
| CN111759212A (en) | 2020-10-13 |
| CN111759216A (en) | 2020-10-13 |
| CN111685631A (en) | 2020-09-22 |
| CN111759214A (en) | 2020-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111685633A (en) | Tumble detection method | |
| US10709359B2 (en) | Systems and methods for dynamically identifying a patient support surface and patient monitoring | |
| WO2021174841A1 (en) | Temperature measurement method, temperature measurement apparatus, electronic device and computer-readable storage medium | |
| CN111538030A (en) | Method, system, and non-transitory computer readable medium for detecting human activity | |
| WO2021063046A1 (en) | Distributed target monitoring system and method | |
| KR20140110484A (en) | Risk behavior detection method using image information | |
| CN111429515A (en) | Learning method of robot obstacle avoidance behavior based on deep learning | |
| CN210784297U (en) | Intelligent morning examination robot based on oral cavity temperature measurement | |
| TWI681740B (en) | Seat cushion | |
| CN113589296A (en) | Human body sitting posture detection device and method | |
| CN210090677U (en) | Laser positioning device | |
| JP2015191268A (en) | Person's head detection device and posture estimation device | |
| Siciliano et al. | A networked multisensor system for ambient assisted living application | |
| CN111419109B (en) | High-precision intelligent toilet seat control system and control method | |
| KR20220071622A (en) | System and method for management of hospital room | |
| KR20230158474A (en) | sensing system | |
| CN209514646U (en) | A kind of personnel's disengaging field Intelligent statistical device | |
| KR101518306B1 (en) | Simulation method for fire-training using 3-Dimensional stereo-scopic image generation technique | |
| CN208156682U (en) | Biological identification device with sensing image sound | |
| CN110898404A (en) | Deep vision anti-collision swimming goggles | |
| CN111272288A (en) | Body temperature automatic measuring device and method based on cooperative robot | |
| CN111387865B (en) | Intelligent closestool control method | |
| KR20230052170A (en) | Apparatus and method for monitoring inactive livestock | |
| WO2023145216A1 (en) | Wearable monitoring device | |
| CN111395472B (en) | Intelligent closestool gesture control method |
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 |