CN115273401A - Method and system for automatically sensing falling of person - Google Patents
Method and system for automatically sensing falling of person Download PDFInfo
- Publication number
- CN115273401A CN115273401A CN202210924798.3A CN202210924798A CN115273401A CN 115273401 A CN115273401 A CN 115273401A CN 202210924798 A CN202210924798 A CN 202210924798A CN 115273401 A CN115273401 A CN 115273401A
- Authority
- CN
- China
- Prior art keywords
- person
- sensing
- falling
- personnel
- positioning
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000008569 process Effects 0.000 claims abstract description 11
- 230000008447 perception Effects 0.000 claims description 19
- 230000001133 acceleration Effects 0.000 claims description 17
- 238000006073 displacement reaction Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 7
- 238000001931 thermography Methods 0.000 claims description 5
- 238000009826 distribution Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 abstract description 5
- 230000033001 locomotion Effects 0.000 abstract description 3
- 238000004364 calculation method Methods 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 239000007787 solid Substances 0.000 description 3
- 241001465754 Metazoa Species 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000009429 distress Effects 0.000 description 2
- 238000007667 floating Methods 0.000 description 2
- 238000003331 infrared imaging Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
- G08B21/0438—Sensor means for detecting
- G08B21/0476—Cameras to detect unsafe condition, e.g. video cameras
Abstract
The invention relates to a method and a system for automatically sensing the falling of a person, wherein the method tracks the person in an area of a designated range by using sensing equipment and marks key persons; sensing and judging the falling or suspected falling state of the person, and positioning and assisting the falling person in a combined mode; correspondingly, the system is provided with a plurality of sensing units in the electronic fence, so that the trajectory of the person is tracked, the control end processes the information returned by the sensing units, the key person is marked, the falling state or suspected falling state of the person is sensed and judged, and the falling person is positioned and rescued. The invention carries out grading tracking on the personnel, so that the resource is not wasted, and the overall calculation amount is lower; acquiring the falling state and/or suspected falling state of key personnel based on the centroid movement and confidence algorithm, and assisting the key personnel in time; positioning in a combined mode to acquire positioning information more quickly; is particularly suitable for outdoor open large space with blind areas.
Description
Technical Field
The present invention relates to signaling or calling devices; an instruction-transmitting device; the technical field of alarm devices, in particular to a method and a system for automatically sensing the falling of a person.
Background
The intelligent community is a new idea of community management, is a new mode of social management innovation under new situation, fully utilizes the integrated application of new generation information technologies such as Internet of things, cloud computing, mobile internet and the like, and provides a safe, comfortable and convenient modern and intelligent living environment for residents in the community, thereby forming a community with a new management form based on informatization and intelligent social management and service.
Along with the popularization of the intelligent community, the dependence on informatization is gradually increased, the interaction between people is gradually reduced, the intensity of informatization and humanistic care cannot be balanced in many fields, for example, in an open space in the community, when people fall down, the people cannot be found at the first time, the rescue work is delayed, and when the fall-down conditions occur to old people or children, the caused consequences cannot be predicted.
In the prior art, fall identification includes contact and non-contact modes; the contact type identification is probably more effective for children, but the contact type identification is often not accepted by the old people, so that the guardian can not obtain the falling information of the old people at the first time; the non-contact identification is usually realized by adopting an infrared imaging mode, but due to the limitation of infrared imaging, the monitoring field cannot be subjected to global coverage, the communication effect is unstable, and the implementation difficulty is high.
Chinese patent "method and apparatus for fall detection, fall detection system, storage medium" (publication No. CN114758475 a) discloses that the state of an indoor person is obtained; under the condition that the falling state of the indoor personnel is preliminarily judged, the mobile equipment is controlled to move to the position of the indoor personnel; controlling the mobile equipment to acquire indoor personnel image information; determining whether the indoor personnel is in a falling state or not according to the image information; the state of indoor personnel is acquired through equipment with a detection function, and the mobile equipment is controlled to carry out further identification and confirmation under the condition that the indoor user is judged to be possibly in a falling state at present; after the mobile equipment moves to the position where the indoor personnel are located, acquiring image information of the indoor personnel from multiple angles, and further determining whether the indoor personnel are in a falling state; the current state of the user can be accurately acquired by the camera, and the applicability of the falling detection system is improved.
The Chinese patent 'a non-contact type indoor personnel fall identification method based on an internet of things platform' (publication number CN 112435440A) discloses that a captured infrared thermal image containing indoor personnel thermal information is transmitted to a cloud server in real time through an NB-IoT narrowband wireless communication module, meanwhile, falling alarm information of personnel is returned to a monitoring device installed in an indoor monitoring area, bidirectional wireless connection is achieved, a local gateway and a central network are not needed, industrial-level system reliability is achieved, and therefore a home broadband network is not needed to be connected, and wide-coverage non-contact type indoor personnel fall identification is achieved; the intelligent and quick identification of the falling behavior is realized through the process of collecting NB-IoT narrowband transmission through infrared thermal images at low resolution, enhancing the resolution of the infrared thermal images, extracting and falling the human body posture features, returning falling information to a guardian mobile phone and sending alarm information to an alarm device to give an alarm sound.
However, the above techniques all focus on indoor space, which has inherent advantages for the resolution of image information, and in fact, these techniques cannot be applied to the recognition of a person falling in an open environment; further, in addition to identifying a person falling, it is also necessary to quickly locate the person in an open space outdoors, which is not possible with the above-described technique.
Disclosure of Invention
The invention solves the problems in the prior art and provides a method and a system for automatically sensing the falling of a person.
The invention adopts the technical scheme that a method for automatically sensing the falling of a person is used for tracking the person in a specified range by sensing equipment and marking key persons; the falling state or suspected falling state of the person is sensed and judged, and the falling person is positioned and assisted in a combined mode.
Preferably, the method comprises the steps of:
step 1: for any sensing device, acquiring an initial sensing image in an appointed range of the sensing device as a background image, and marking an interested region;
and 2, step: updating the perception image of the current perception device, when the difference value between the perception image at any moment and the background image in the interested area is larger than a threshold value, carrying out the next step, otherwise, repeating the step 2;
and 3, step 3: making a difference between the perception image at the current moment and the background image, and setting a minimum circumscribed rectangle for a plurality of image elements with difference values larger than a threshold value in an interested area; if the current minimum circumscribed rectangle has displacement in a plurality of subsequent frames, performing the next step, otherwise, giving up tracking, and repeating the step 2;
and 4, step 4: obtaining the height and width ratio corresponding to the current minimum circumscribed rectangle, if the preset requirement is met, considering that the tracked object is a person, carrying out the next step, otherwise, giving up the tracking, and repeating the step 2;
and 5: judging key personnel for the personnel corresponding to the current minimum circumscribed rectangle, if the personnel are preset key personnel, marking, and leading the sequence of the marked personnel in the tracking list; in the tracking process, if a falling state and/or a suspected falling state occur, the combined mode is started to position and assist the falling person, otherwise, the tracking is continued until the current person is sensed by the next sensing device or enters a safe area.
Preferably, in the step 5, the key personnel are the old and the children;
acquiring the displacement speed of the personnel corresponding to the current minimum circumscribed rectangle, and acquiring other angle circumscribed rectangles of the personnel corresponding to the current minimum circumscribed rectangle;
if the height and width ratio corresponding to the current minimum circumscribed rectangle and the circumscribed rectangles with other angles meets the preset condition and the displacement speed is less than the preset value, judging that the current person is an old person;
and if the height and width ratio corresponding to the current minimum circumscribed rectangle are within the preset range and the height is within the preset range, judging that the current person is a child.
Preferably, in the step 5, for any minimum bounding rectangle, the centroid position is calibrated; and acquiring the acceleration of the centroid corresponding to the minimum circumscribed rectangle in the vertical direction, acquiring the height and width ratio of the current minimum circumscribed rectangle if the acceleration in the vertical direction jumps, and defining the falling state of the person corresponding to the minimum circumscribed rectangle with the height and width ratio meeting preset conditions.
Preferably, in the step 5, if a blind area exists between the specified ranges of any 2 or more sensing devices, the traveling direction of a key person in the sensing device through which the first key person passes is obtained, and the passing confidence of the corresponding other sensing devices is calculated; if any other sensing equipment does not sense the appearance of the key personnel within the preset time, judging that the current key personnel is in a suspected falling state, and positioning the fallen key personnel in sequence by taking the passing confidence coefficient from high to low as a standard.
Preferably, the combined mode comprises a first positioning mode and a second positioning mode;
the first positioning mode is used for acquiring the falling state or suspected falling state of a person and positioning the falling or suspected falling position information;
the second positioning mode is that other people report the situations of the fallen or suspected fallen people and position the fallen or suspected fallen position information.
Preferably, in the second positioning mode, if a plurality of other people initiate reporting from different positions, the position information and the reporting time of the reporting point are obtained, and the distribution of the fallen or suspected fallen position area is calculated.
A system for automatically sensing a fall of a person using the method, the system comprising:
the sensing units are arranged in the electronic fence and used for tracking the tracks of the personnel in the area with the designated range;
the plurality of calling positioning units are arranged in the electronic fence and used for calling and positioning the falling state of the person;
and the control end is used for processing the information returned by the sensing unit, marking key personnel, sensing and judging the falling state or suspected falling state of the personnel, positioning the falling personnel and dispatching rescue.
Preferably, the sensing unit comprises a camera and an unmanned aerial vehicle; the sensing image of the camera is a continuous image corresponding to the video frame, and the sensing image of the unmanned aerial vehicle is a thermal imaging image; unmanned aerial vehicle disposes public address unit for realize speech output at the in-process of location and rescue.
Preferably, the distress call positioning unit comprises a mobile terminal and a fixed-point calling device.
The invention provides a method and a system for automatically sensing the falling of a person, wherein the method tracks the person in an area of a designated range by using sensing equipment and marks key persons; sensing and judging the falling state or suspected falling state of the person, and positioning and assisting the falling person in a combined mode; correspondingly, the system takes the application range of the electronic fence surrounding system as a sensing area, a plurality of sensing units are arranged in the electronic fence, the trajectory of people in the area in the designated range is tracked, information returned by the sensing units is processed by a control end, important people are marked, the falling state or suspected falling state of the people is sensed and judged, and the fallen people are positioned and rescued.
The invention has the beneficial effects that:
(1) The method comprises the following steps of carrying out hierarchical tracking on personnel in a specified area range, paying special attention to key personnel, ensuring that resources are not wasted and the overall calculation amount is low;
(2) Obtaining the falling state and/or suspected falling state of key personnel based on the centroid movement and confidence algorithm, and ensuring that the key personnel can be assisted in time;
(3) The falling person is positioned in a combined mode in the assistance process, and the positioning information can be acquired more quickly in an outdoor open space;
(4) Is particularly suitable for outdoor open large space with blind areas.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
fig. 2 is a schematic diagram of acceleration jump in embodiment 3 of the present invention, which corresponds to the states of normal walking, falling, and squatting, respectively;
FIG. 3 is a schematic view of embodiment 4 of the present invention;
FIG. 4 is a diagram illustrating a second positioning mode in embodiment 5 of the present invention;
fig. 5 is a schematic diagram of the system structure of the present invention, and arrows indicate the direction of signal or data transmission.
Detailed Description
The present invention is described in further detail with reference to the following examples, but the scope of the present invention is not limited thereto.
The invention relates to a method for automatically sensing the falling of a person, which is characterized in that a sensing device is used for tracking the trajectory of the person in an area within a specified range and marking key persons; and sensing and judging the falling state or suspected falling state of the person, and positioning and assisting the falling person in a combined mode.
In the present invention, the area of the designated range refers to an area having the designated range for each sensing device, and the space surrounded by all the sensing devices covers the whole area.
In the present invention, the area within the designated area includes an open type park and the interior of a building, and generally does not include an independent living room.
In the present invention, embodiments are given for practical applications of the present method and system.
Example 1
As shown in fig. 1, the method comprises the steps of:
step 1: for any sensing device, acquiring an initial sensing image in an appointed range of the sensing device as a background image, and marking an interested region;
in step 1, no matter what kind of sensing device, it needs to obtain the sensing image in the designated range in the sensing process, so it is necessary to use the initial sensing image as the background image.
In the invention, because the perceived area is generally positioned at an angle of shooting from high to low, the range of the monitored perception is larger in fact, and the monitored perception cannot be better concentrated, and more invalid information is easy to appear, so that the region of interest is divided into the perceived image of the perception device firstly, namely, the perceived image is mainly compared with the information in the region of interest, and other interference information, such as article falling, background shaking caused by wind and the like, is not concerned.
And 2, step: updating the perception image of the current perception device, and when the difference value between the perception image at any moment and the background image in the region of interest is larger than a threshold value, performing the next step, otherwise, repeating the step 2;
and 3, step 3: making a difference between the perception image at the current moment and the background image, and setting a minimum circumscribed rectangle for a plurality of image elements with difference values larger than a threshold value in an interested area; if the current minimum circumscribed rectangle has displacement in a plurality of subsequent frames, performing the next step, otherwise, giving up tracking, and repeating the step 2;
in the invention, when the difference value between the perception image and the background image at any moment in the interesting region is larger than the threshold value, the appearance of a foreign person or article in the current perception range is indicated, so that the difference between the perception image and the background image at the current moment needs to be made, actually, the difference is made between pixel points, pixel points with the difference value larger than the threshold value are reserved, the pixel points point to the corresponding foreign person or article, but the pixel points are obviously not enough only to be packed, and the boundary of the pixel points often has a certain loss, so that the reserved pixel points are framed by a circumscribed rectangle to obtain a minimum circumscribed rectangle which can surround and identify the current foreign person or article.
In the invention, because the minimum circumscribed rectangle may be a person or an object, whether the current minimum circumscribed rectangle has displacement in a plurality of subsequent frames or not is judged, if yes, the minimum circumscribed rectangle is generally passed by the person and needs subsequent perception judgment, and if not, the minimum circumscribed rectangle is generally an object and gives up tracking.
In the present invention, the threshold in step 2 needs to be adjusted according to the light variation, the image resolution, etc., which is easily understood by those skilled in the art, and can also be self-adjusted by the controller through the sensing of the light variation.
In the present invention, several frames in step 3 typically cover a 5 minute time.
And 4, step 4: obtaining the height and width ratio corresponding to the current minimum circumscribed rectangle, if the preset requirement is met, considering that the tracked object is a person, carrying out the next step, otherwise, giving up tracking, and repeating the step 2;
in the invention, the corresponding height and width ratio of the minimum circumscribed rectangle is used for identifying whether the framed object is a human, an animal or a light object (the light object can also be blown to generate displacement); generally, as a human walking upright, the height-width ratio of a human body is more than 1, while an animal is generally less than 1, and the height-width ratio of a light object is not fixed and is easy to fluctuate greatly in the floating process, so that a tracking object can be quickly identified and tracking of a person can be focused on.
And 5: judging key personnel for the personnel corresponding to the current minimum circumscribed rectangle, if the personnel are preset key personnel, marking, and leading the sequence of the marked personnel in the tracking list; in the tracking process, if a falling state and/or a suspected falling state occur, the combined mode is started to position and assist the falling person, otherwise, the tracking is continued until the current person is sensed by the next sensing device or enters a safe area.
In the invention, for key personnel, the tracked weight of the key personnel needs to be improved, the falling state and/or suspected falling state of the key personnel can be sensed in the first time, and rescue can be carried out in time.
In the invention, all the sensing devices are networked, and when a person leaves the sensing range of the previous sensing device, the following sensing device realizes subsequent tracking after sensing the person; a secure enclave is then generally referred to as an independent, private residence space.
Example 2
On the basis of the embodiment 1, in the step 5, the key personnel are the old and the children;
acquiring the displacement speed of the personnel corresponding to the current minimum circumscribed rectangle, and acquiring other angle circumscribed rectangles of the personnel corresponding to the current minimum circumscribed rectangle;
if the height and width ratio corresponding to the current minimum circumscribed rectangle and the circumscribed rectangles with other angles meets the preset condition and the displacement speed is less than the preset value, judging that the current person is an old person;
and if the height and the width ratio corresponding to the current minimum circumscribed rectangle are within the preset range and the height is within the preset range, judging that the current person is a child.
In the embodiment, the elderly and children (generally speaking, in the case of exclusive walking) are limited to be elderly and children because they have a certain difficulty in calling for help after falling over and have a longer response time than people in other age groups.
In this embodiment, the determination of whether the elderly person is determined by combining the shape and the displacement speed, and generally, the preset conditions that the shape characteristics of the elderly person should satisfy include:
(1) Different height and width ratios can occur from the front side and the back side or the left side and the right side, which can be obtained through the angle transformation of the sensing equipment;
(2) The height and width ratio of the elderly is typically closer to 1.2.
In this embodiment, the number of the other angle circumscribed rectangles is generally 1~2, and the height and width ratio of the other angle circumscribed rectangles exceeds the difference of other people.
In this embodiment, the determination of the old person also needs to satisfy that the displacement speed is obviously smaller than the average speed of the adult, and the current person is determined to be the old person under the condition that the two conditions are met.
In this embodiment, the determination of whether the child is a child is mainly performed through the shape, generally speaking, the size of the child has a large floating ratio, and at this time, the height needs to be screened, and the corresponding person is determined to be the child, and the general height is defined as 50cm to 130cm.
Example 3
In the step 5, the centroid position of any minimum circumscribed rectangle is calibrated; and acquiring the acceleration of the centroid corresponding to the minimum circumscribed rectangle in the vertical direction, acquiring the height and width ratio of the current minimum circumscribed rectangle if the acceleration in the vertical direction jumps, and defining the falling state of the person corresponding to the minimum circumscribed rectangle with the height and width ratio meeting preset conditions.
In this embodiment, the behavior characteristics when falling are defined:
(1) The mass center generates large fluctuation in the speed in the vertical direction;
(2) The height of the mass center is basically kept unchanged in a short time after the land falls;
(3) After falling down, the height and width ratio of the minimum external rectangle is obviously changed, and the minimum external rectangle is generally laid down;
the situation that needs to be excluded here is a squat state.
In this embodiment, the center of mass corresponding to any person is generally located at the upper position of the waist, i.e., the minimum circumscribed rectangle is set to "2x,y,w,h]X and y are x coordinate and y coordinate of lower left corner, w is width, and h is height, then the centroid is generally at (x 1, y 1), where x1= x +0.5w, y1= y +0.45h;
recording the position of the mass center of the personnel in the continuous three-frame image, obtaining the speed of the personnel in the current frame in the vertical direction, and obtaining the acceleration of the personnel in the current frame in the vertical direction through the speed of the personnel in the current frame and the speed of the personnel in the previous frame, namely the speed difference between the personnel in the current frame and the previous frame;
when the person is in a normal walking state, the acceleration of the mass center in the vertical direction is in a relatively stable fluctuation state, and when the person falls or squats, the fluctuation of the acceleration of the mass center in the vertical direction is obviously increased; as shown in fig. 2, the asterisk indicates the change of the acceleration in the vertical direction when the person normally walks, the acceleration in the vertical direction of the centroid fluctuates up and down with a regular small range of motion and is relatively stable, the solid line indicates the change of the acceleration in the vertical direction when the person takes a tumbling action, the two actions of falling and climbing from the ground generate relatively large acceleration fluctuation in the vertical direction and are significantly larger than the state during normal walking, the acceleration in the vertical direction only generates small fluctuation before the person falls and does not get up, the fluctuation degree is significantly smaller than the fluctuation during normal walking, and the dotted line indicates the change of the acceleration in the vertical direction when the person takes a squatting action, is similar to the tumbling action and also generates relatively large speed fluctuation in the vertical direction; based on the above, when the acceleration of the person in the vertical direction is within a preset range, the falling behavior is judged to possibly occur;
in the process of falling and squatting behaviors, the height-width ratio of the minimum circumscribed rectangle is reduced, but the height-width ratio of the falling behavior is reduced more obviously, so that the falling behavior and the squatting behavior can be further distinguished by setting a threshold value, generally speaking, the falling behavior is judged when the threshold value is 0.75, and the falling behavior is judged when the threshold value is less than 0.75, otherwise the squatting behavior is judged.
Example 4
As shown in fig. 3, in step 5, if a blind area exists between the specified ranges of any 2 or more sensing devices, obtaining the traveling direction of a key person in the sensing device through which the first key person passes, and calculating the passing confidence of the corresponding other sensing devices; if any other sensing equipment does not sense the appearance of the key personnel within the preset time, judging that the current key personnel is in a suspected falling state, and positioning the fallen key personnel in sequence by taking the passing confidence coefficient from high to low as a standard.
In this embodiment, for a blind area where any 2 or more sensing devices are closed, for example, an area O in the figure, the corresponding possible paths include A, B, C, D, E, F, and assuming that the sensing device through which the first sensing person passes is the sensing device in the path a, and the traveling direction of the sensing person in the process of sensing is the direction of the solid arrow, the included angle between the B, C, D, E, F five paths (generally, the midpoint of the intersection) and the solid arrow is calculated, and the smaller the angle, the higher the passing confidence of the corresponding path is, and as in the figure, the confidence sequence of the B, C, D, E, F five paths is E, D, C, F, B.
In this embodiment, within a preset time, if any other sensing device does not sense the appearance of the key person, it is determined that the current key person is in a suspected falling state, and the preset time is generally calculated according to the walking speed of the current person.
In this embodiment, if it is determined that the person is in a suspected falling state, the important fallen persons are located in sequence by using the passing confidence as a criterion from high to low, and are more likely to be close to the path with the high passing confidence, as shown in fig. 2, the area near E is heavily found.
Example 5
The combined mode comprises a first positioning mode and a second positioning mode;
the first positioning mode is used for acquiring the falling state or suspected falling state of a person and positioning the falling or suspected falling position information;
the second positioning mode is that other people report the situations of the fallen or suspected fallen people and position information of the fallen or suspected fallen people.
In the second positioning mode, if a plurality of other persons initiate reporting from different positions, the position information and the reporting time of a reporting point are obtained, and the regional distribution of the falling or suspected falling position is calculated.
In this embodiment, the first positioning mode refers to that a person is provided with a device for positioning itself, so that direct positioning can be achieved.
In this embodiment, the second positioning mode is to perform positioning by other people, and since a plurality of positioning people may occur, in addition to obtaining the positioning of the mobile terminals of other people, a fixed-point calling device is often disposed in the smart community, and the positioning accuracy of the fixed-point calling device is higher, but the positioning of the mobile terminal near a fallen person is often denser, as shown in fig. 4, when performing positioning in the second positioning mode, a solid circle is the fixed-point calling device, which has high accuracy and large coverage area, and its confidence coefficient is generally higher, and 2 hollow circles are the positioning and signal coverage surfaces of other people near the fallen person who initiate a call through the mobile terminal, and although the accuracy is not as good as that of the fixed-point calling device, they are denser, so that the confidence coefficient can be appropriately increased, and in this case, it is a better choice to start positioning and search for the fallen person from the signal staggered position of 3 call sources.
As shown in fig. 5, the invention also relates to a system for automatically sensing the fall of a person, which adopts the method, and the system comprises:
the sensing units are arranged in the electronic fence and used for tracking the tracks of the personnel in the area with the designated range;
the plurality of calling positioning units are arranged in the electronic fence and used for calling and positioning the falling condition of the personnel;
and the control end is used for processing the information returned by the sensing unit, marking key personnel, sensing and judging the falling state or suspected falling state of the personnel, positioning the falling personnel and dispatching rescue.
The sensing unit comprises a camera and an unmanned aerial vehicle; the sensing image of the camera is a continuous image corresponding to the video frame, and the sensing image of the unmanned aerial vehicle is a thermal imaging image; unmanned aerial vehicle disposes public address unit for realize speech output at the in-process of location and rescue.
The calling positioning unit comprises a mobile terminal and a fixed-point calling device.
In the present invention, it is obvious that all the units in the system have application boundaries, i.e. electronic fences, for enclosing the range of application of the system as a sensing area.
According to the invention, the camera serves as a sensing unit and can acquire continuous video images, and the unmanned aerial vehicle can carry the far infrared sensor to acquire a thermal imaging picture, particularly a thermal imaging picture of a sensing blind area, so that the positioning of a fallen person can be conveniently and rapidly acquired.
In the invention, the sound amplifying unit configured by the unmanned aerial vehicle can be convenient for rescue workers to call, manually guide ground personnel to rescue and the like.
In the invention, the mobile terminal generally uses a mobile phone and a built-in positioning function thereof to realize distress positioning, which is a content easily understood by a person skilled in the art; the fixed-point calling device is a remote calling device disposed in the electronic fence, and is generally connected to the control end through an underground cable, so as to achieve precise positioning and long-term availability.
In order to implement the above embodiments, a computer-readable storage medium is provided, on which an ant colony algorithm-based intelligent elevator-booking program is stored, and when the program is executed by a processor, the ant colony algorithm-based intelligent elevator-booking method is implemented, which mainly solves the problem of unordered elevator-booking in the prior art, so that a user can successfully board an elevator from a departure floor to an arrival floor within a planning time.
In order to implement the above embodiments, the present invention further relates to a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the intelligent ladder-closing method based on the ant colony algorithm is provided.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (9)
1. A method for automatically sensing a fall of a person, comprising: tracking the person in a region in a specified range by using a sensing device, and marking key persons; sensing and judging the falling state or suspected falling state of the person, and positioning and assisting the falling person in a combined mode; the method comprises the following steps:
step 1: for any sensing device, acquiring an initial sensing image in an appointed range of the sensing device as a background image, and marking an interested region;
step 2: updating the perception image of the current perception device, and when the difference value between the perception image at any moment and the background image in the region of interest is larger than a threshold value, performing the next step, otherwise, repeating the step 2;
and step 3: making a difference between the perception image at the current moment and the background image, and setting a minimum circumscribed rectangle for a plurality of image elements with difference values larger than a threshold value in an interested area; if the current minimum circumscribed rectangle has displacement in a plurality of subsequent frames, performing the next step, otherwise, giving up tracking, and repeating the step 2;
and 4, step 4: obtaining the height and width ratio corresponding to the current minimum circumscribed rectangle, if the preset requirement is met, considering that the tracked object is a person, carrying out the next step, otherwise, giving up tracking, and repeating the step 2;
and 5: judging key personnel for the personnel corresponding to the current minimum circumscribed rectangle, if the personnel are preset key personnel, marking, and leading the sequence of the marked personnel in the tracking list; in the tracking process, if a falling state and/or a suspected falling state occur, the combined mode is started to position and assist the falling person, otherwise, the tracking is continued until the current person is sensed by the next sensing device or enters a safe area.
2. A method for automatically perceiving a fall of a person as claimed in claim 1, wherein: in the step 5, key personnel are the old and children;
acquiring the displacement speed of the personnel corresponding to the current minimum circumscribed rectangle, and acquiring other angle circumscribed rectangles of the personnel corresponding to the current minimum circumscribed rectangle;
if the height and width ratio corresponding to the current minimum circumscribed rectangle and the circumscribed rectangles with other angles meets the preset condition and the displacement speed is less than the preset value, judging that the current person is an old person;
and if the height and the width ratio corresponding to the current minimum circumscribed rectangle are within the preset range and the height is within the preset range, judging that the current person is a child.
3. A method for automatically perceiving a fall of a person as claimed in claim 1, wherein: in the step 5, calibrating the centroid position of any minimum circumscribed rectangle; and acquiring the acceleration of the centroid corresponding to the minimum circumscribed rectangle in the vertical direction, acquiring the height and width ratio of the current minimum circumscribed rectangle if the acceleration in the vertical direction jumps, and defining the falling state of the person corresponding to the minimum circumscribed rectangle with the height and width ratio meeting the preset conditions.
4. A method for automatically perceiving a fall of a person as claimed in claim 1, wherein: in the step 5, if a blind area exists in the specified range of any 2 or more sensing devices, acquiring the traveling direction of a key person in the sensing device through which the first key person passes, and calculating the passing confidence of the corresponding other sensing devices; if any other sensing equipment does not sense the appearance of the key personnel within the preset time, judging that the current key personnel is in a suspected falling state, and positioning the fallen key personnel in sequence by taking the passing confidence coefficient from high to low as a standard.
5. A method for automatically perceiving a fall of a person as claimed in claim 1, wherein: the combined mode comprises a first positioning mode and a second positioning mode;
the first positioning mode is used for acquiring the falling state or suspected falling state of a person and positioning the falling or suspected falling position information;
the second positioning mode is that other people report the situations of the fallen or suspected fallen people and position the fallen or suspected fallen position information.
6. A method of automatically perceiving a fall of a person as claimed in claim 5, wherein: in the second positioning mode, if a plurality of other persons initiate reporting from different positions, the position information and the reporting time of a reporting point are obtained, and the distribution of the falling or suspected falling position areas is calculated.
7. A system for automatically sensing a fall of a person using the method of claim 1~6 comprising: the system comprises:
the sensing units are arranged in the electronic fence and used for tracking the tracks of the personnel in the area with the designated range;
the plurality of calling positioning units are arranged in the electronic fence and used for calling and positioning the falling state of the person;
and the control end is used for processing the information returned by the sensing unit, marking key personnel, sensing and judging the falling state or suspected falling state of the personnel, positioning the falling personnel and dispatching rescue.
8. The system for automatically sensing a fall of a person according to claim 7, wherein: the sensing unit comprises a camera and an unmanned aerial vehicle; the sensing image of the camera is a continuous image corresponding to the video frame, and the sensing image of the unmanned aerial vehicle is a thermal imaging image; unmanned aerial vehicle disposes public address unit for realize speech output at the in-process of location and rescue.
9. The system for automatically perceiving a fall of a person as claimed in claim 7, wherein: the calling positioning unit comprises a mobile terminal and a fixed-point calling device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210924798.3A CN115273401A (en) | 2022-08-03 | 2022-08-03 | Method and system for automatically sensing falling of person |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210924798.3A CN115273401A (en) | 2022-08-03 | 2022-08-03 | Method and system for automatically sensing falling of person |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115273401A true CN115273401A (en) | 2022-11-01 |
Family
ID=83748133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210924798.3A Pending CN115273401A (en) | 2022-08-03 | 2022-08-03 | Method and system for automatically sensing falling of person |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115273401A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116567425A (en) * | 2023-07-04 | 2023-08-08 | 北京华卫迪特健康科技有限公司 | Wisdom endowment is with integrated control management device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108805021A (en) * | 2018-04-27 | 2018-11-13 | 西安理工大学 | The real-time individual tumble behavioral value alarm method of feature based operator |
| CN109145696A (en) * | 2017-06-28 | 2019-01-04 | 安徽清新互联信息科技有限公司 | A kind of Falls Among Old People detection method and system based on deep learning |
| CN110477925A (en) * | 2019-08-23 | 2019-11-22 | 广东省智能制造研究所 | A kind of fall detection for home for the aged old man and method for early warning and system |
| CN111353367A (en) * | 2019-08-19 | 2020-06-30 | 深圳市鸿合创新信息技术有限责任公司 | Face attendance checking method, device, equipment and storage medium based on thermal imaging |
| CN113197568A (en) * | 2021-04-19 | 2021-08-03 | 深圳市安全守护科技有限公司 | Fall reminding method, device, equipment and computer readable storage medium |
| CN113688734A (en) * | 2021-08-25 | 2021-11-23 | 燕山大学 | Old man falling detection method based on FPGA heterogeneous acceleration |
| CN113793475A (en) * | 2021-08-05 | 2021-12-14 | 南京信息职业技术学院 | System and method for detecting falling of old people in key area |
| CN114269243A (en) * | 2020-03-19 | 2022-04-01 | 株式会社日立制作所 | Fall risk evaluation system |
| CN114676956A (en) * | 2022-01-04 | 2022-06-28 | 哈尔滨工业大学（威海） | Old man's risk early warning system that tumbles based on multidimensional data fusion |
-
2022
- 2022-08-03 CN CN202210924798.3A patent/CN115273401A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109145696A (en) * | 2017-06-28 | 2019-01-04 | 安徽清新互联信息科技有限公司 | A kind of Falls Among Old People detection method and system based on deep learning |
| CN108805021A (en) * | 2018-04-27 | 2018-11-13 | 西安理工大学 | The real-time individual tumble behavioral value alarm method of feature based operator |
| CN111353367A (en) * | 2019-08-19 | 2020-06-30 | 深圳市鸿合创新信息技术有限责任公司 | Face attendance checking method, device, equipment and storage medium based on thermal imaging |
| CN110477925A (en) * | 2019-08-23 | 2019-11-22 | 广东省智能制造研究所 | A kind of fall detection for home for the aged old man and method for early warning and system |
| CN114269243A (en) * | 2020-03-19 | 2022-04-01 | 株式会社日立制作所 | Fall risk evaluation system |
| CN113197568A (en) * | 2021-04-19 | 2021-08-03 | 深圳市安全守护科技有限公司 | Fall reminding method, device, equipment and computer readable storage medium |
| CN113793475A (en) * | 2021-08-05 | 2021-12-14 | 南京信息职业技术学院 | System and method for detecting falling of old people in key area |
| CN113688734A (en) * | 2021-08-25 | 2021-11-23 | 燕山大学 | Old man falling detection method based on FPGA heterogeneous acceleration |
| CN114676956A (en) * | 2022-01-04 | 2022-06-28 | 哈尔滨工业大学（威海） | Old man's risk early warning system that tumbles based on multidimensional data fusion |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116567425A (en) * | 2023-07-04 | 2023-08-08 | 北京华卫迪特健康科技有限公司 | Wisdom endowment is with integrated control management device |
| CN116567425B (en) * | 2023-07-04 | 2023-09-05 | 北京华卫迪特健康科技有限公司 | Wisdom endowment is with integrated control management device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11875656B2 (en) | Virtual enhancement of security monitoring | |
| CN107045623B (en) | Indoor dangerous condition warning method based on human body posture tracking analysis | |
| US8681223B2 (en) | Video motion detection, analysis and threat detection device and method | |
| CN106875629B (en) | Home-based endowment system based on somatosensory network and control method thereof | |
| KR101644443B1 (en) | Warning method and system using prompt situation information data | |
| US20210241468A1 (en) | Systems and methods for intelligent video surveillance | |
| CN110533553A (en) | Service providing method and device | |
| WO2021082112A1 (en) | Neural network training method, skeleton diagram construction method, and abnormal behavior monitoring method and system | |
| US20210241597A1 (en) | Smart surveillance system for swimming pools | |
| CA3126835A1 (en) | Smart surveillance system for swimming pools | |
| US20220139199A1 (en) | Accurate digital security system, method, and program | |
| KR20140110484A (en) | Risk behavior detection method using image information | |
| CN115273401A (en) | Method and system for automatically sensing falling of person | |
| CN113723369B (en) | Control method, control device, electronic equipment and storage medium | |
| Taghvaei et al. | Autoregressive-moving-average hidden Markov model for vision-based fall prediction—An application for walker robot | |
| JP2007018324A (en) | Apparatus, method and program for detecting intruding object by image processing | |
| JP5418938B2 (en) | Group behavior estimation apparatus and service providing system | |
| WO2022204153A1 (en) | Image based tracking system | |
| CN114120368A (en) | Target detection method and detection equipment | |
| JP5567725B2 (en) | Group behavior estimation device | |
| JP2023079291A (en) | Image processing device, image processing method, and program | |
| JP2021096840A (en) | Security system and program | |
| DE102023127347A1 (en) | PASSENGER IDENTIFICATION SYSTEMS AND METHODS USING MOTION CAPTURE | |
| US20240153109A1 (en) | Image based tracking system | |
| JP6730953B2 (en) | Terminal position estimating apparatus, program and method in consideration of moving object recognition information |
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 |