CN115849124A - Method, device, equipment and medium for identifying falling of people in elevator - Google Patents
Method, device, equipment and medium for identifying falling of people in elevator Download PDFInfo
- Publication number
- CN115849124A CN115849124A CN202211231519.1A CN202211231519A CN115849124A CN 115849124 A CN115849124 A CN 115849124A CN 202211231519 A CN202211231519 A CN 202211231519A CN 115849124 A CN115849124 A CN 115849124A
- Authority
- CN
- China
- Prior art keywords
- elevator
- behavior
- fall
- falling
- identifying
- 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 28
- 238000012544 monitoring process Methods 0.000 claims abstract description 49
- 230000009471 action Effects 0.000 claims abstract description 35
- 230000006399 behavior Effects 0.000 claims description 80
- 230000015654 memory Effects 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 claims description 2
- 206010016173 Fall Diseases 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 238000012216 screening Methods 0.000 description 4
- 230000003542 behavioural effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 208000030090 Acute Disease Diseases 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Landscapes
- Indicating And Signalling Devices For Elevators (AREA)
Abstract
The invention discloses a method, a device, equipment and a medium for identifying falling of people in an elevator, which comprise the following steps: when a fall early warning signal is detected, taking the current moment as the starting moment, and acquiring a monitoring video within a preset time period; based on the monitoring video, recognizing the behavior action of a preset target object to generate a recognition result; when the target object falls down in the elevator based on the identification result, sending alarm information; whether personnel fall in the elevator is judged in a mode of combining the generated fall early warning signal with the identification of the monitoring video, so that the accuracy of a judgment result is improved, corresponding emergency measures can be taken at the first time of a fall incident, the number of times of accidents caused by untimely discovery is reduced to a great extent, and the life safety of people is indirectly guaranteed.
Description
Technical Field
The invention relates to the field of detection, in particular to a method, a device, equipment and a medium for identifying falling of people in an elevator.
Background
Falling is an accident that may occur in the life of the old, office workers and patients, and falling is an embodiment of many acute diseases, and if after falling, the patient is not treated in time in the first time, and may have life risks in serious cases. The elevator is a visible transportation tool everywhere in our life, and the elevator becomes a place where falling accidents often happen due to the limitation of elevator space and air circulation.
Therefore, if the function of detecting a fall of a person is available in the elevator, the occurrence of an accident can be reduced to a large extent.
Disclosure of Invention
Therefore, the technical problem to be solved by the present invention is to overcome the defect in the prior art that whether a person falls down in an elevator cannot be detected, so as to provide a method, an apparatus, a device and a medium for identifying the person falling down in the elevator.
In a first aspect, the present invention provides a method for identifying a person falling down in an elevator, including:
when a falling early warning signal is detected, taking the current moment as the starting moment, acquiring a monitoring video within a preset time period, wherein the falling early warning signal is generated according to an object in an elevator; based on the monitoring video, identifying the behavior action of a preset target object to generate an identification result; and when the target object is determined to fall down in the elevator based on the identification result, giving alarm information.
According to the scheme, when a falling early warning signal is monitored, a monitoring video in the elevator within a preset time period taking the current time as the starting time is obtained, when a falling signal is determined to be generated for a target object according to the obtained monitoring video, behavior and actions of the target object in the monitoring video are identified, whether the target object falls down or not is verified according to an identification result, and when the target object falls down, alarm information is sent out so that a worker can give corresponding rescue measures according to the alarm information; according to the method, whether the target object falls down in the elevator is judged in a mode of combining the detected fall early warning signal with the identification of the monitoring video, so that the accuracy of the judgment result is improved, corresponding emergency measures can be taken at the first time of the fall event, the times of accidents caused by untimely discovery are greatly reduced, and the life safety of people is indirectly guaranteed.
With reference to the first aspect, in a first embodiment of the first aspect, the detecting a fall early warning signal includes:
when detecting that at least one object exists in the elevator, judging whether the object has falling signs or not based on the object behavior signal; when the subject has evidence of falling, a fall early warning signal is generated.
With reference to the first aspect, in a second embodiment of the first aspect, the determining whether the subject has evidence of a fall based on the behavioral signal of the subject includes:
determining a height of the object based on the behavior signal of the object; and when the height of the object is lower than a preset threshold value, determining that the object has the falling sign.
The height of this object is confirmed through the action signal of a certain object that receives to this embodiment, judges whether this object has the sign of tumbleing according to the height, has carried out primary screening to all objects in the elevator through this mode, when all objects in the elevator of the certainty do not have the sign of tumbleing, then need not generate the early warning signal of tumbleing, just also need not acquire the surveillance video and discern the surveillance video. Therefore, the workload is reduced and the working efficiency is improved by primarily screening the target object in the mode.
With reference to the first aspect, in a third embodiment of the first aspect, identifying a behavior action of a target object based on a surveillance video, and generating an identification result includes:
determining a behavior track of a target object in a preset time period based on behavior of the target object in a monitoring video; and identifying the behavior track by using a pre-constructed track prediction model to generate an identification result.
In the embodiment, the behavior track of the target object is determined by monitoring the behavior action of the target object in the video, the behavior track of the target object is identified by using a pre-established track prediction model, an identification result is generated, and whether the target object falls down is judged according to the identification result; in the scheme, the behavior track is identified by using the track prediction model, whether a falling event exists is identified more carefully after the falling early warning signal is received, and some false actions similar to falling can be eliminated by the method, so that the identification result is more accurate.
In a second aspect, the present invention provides an apparatus for identifying a person falling down in an elevator, comprising:
the acquisition module is used for acquiring a monitoring video within a preset time period by taking the current moment as an initial moment when the falling early warning signal is detected, wherein the falling early warning signal is generated according to an object in the elevator; the identification module is used for identifying the behavior action of a preset target object based on the monitoring video to generate an identification result; and the warning module is used for sending warning information when the target object falls down in the elevator based on the identification result.
With reference to the second aspect, in a first embodiment of the second aspect, the obtaining module includes:
the judgment sub-module is used for judging whether the object has falling signs or not based on the behavior signal of the object when the behavior signal of at least one object in the elevator is detected; and the generation submodule is used for generating a fall early warning signal when the subject has the fall signs.
With reference to the second aspect, in a second embodiment of the second aspect, the determining sub-module includes:
a first determination unit for determining a height of the object based on the behavior signal of the object; and the second determining unit is used for determining that the object has falling signs when the height of the object is lower than a preset threshold value.
In a third embodiment of the second aspect, in combination with the second aspect, the identification module includes:
the determining submodule is used for determining a behavior track of the target object in a preset time period based on the behavior of the target object in the monitored video; and the recognition submodule is used for recognizing the behavior track by utilizing the pre-constructed track prediction model to generate a recognition result.
In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory being adapted to store a computer program which, when executed by the processor, causes the processor to carry out a method of identifying a fall of a person in an elevator as claimed in any of the claims.
In a fourth aspect, the present invention provides a computer-readable storage medium for storing computer instructions which, when executed by a processor, implement a method for identifying a fall of a person in an elevator as claimed in any one of the above aspects.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a method for identifying a person falling down in an elevator according to an embodiment of the present invention;
fig. 2 is a connection diagram of an apparatus for recognizing a fall of a person in an elevator according to an embodiment of the present invention;
fig. 3 is a connection diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention discloses a method for identifying falling of people in an elevator, which comprises the following steps of:
step S1: when the early warning signal for falling is detected, the current moment is taken as the starting moment, the monitoring video in the preset time period is obtained, and the early warning signal for falling is generated according to the object in the elevator.
Specifically, the fall early warning signal is only used for indicating that an object in the current elevator falls, and the object in the elevator cannot be directly determined to fall. Therefore, after the fall early warning signal is detected, the current moment is taken as the starting moment, and the monitoring video within a period of time after the starting moment, namely the monitoring video within the preset period of time, is obtained; the fall early warning signal can be generated by any object existing in the elevator, and the object is not necessarily a person and can be other life bodies; the current time refers to the time when the fall warning signal is detected, and the preset time period includes, but is not limited to, a time period from when a person carelessly falls to when the person recovers to stand by himself/herself under a good physical condition, such as 3 seconds or 5 seconds.
Illustratively, in one embodiment, the preset time period is 5 seconds, and the preset time period is 8:25: a fall warning signal is detected at 25, then 8:25: and 25, acquiring a monitoring video in the elevator within 5 seconds as a starting moment, namely 8:25:25 to 8:25: surveillance video within 30 segments.
Step S2: and identifying the behavior action of the preset target object based on the monitoring video to generate an identification result.
Specifically, when a monitoring video is acquired, whether a target object exists in the monitoring video needs to be determined, wherein the target object refers to a person in an elevator; and when the target object does not exist in the monitoring video, ignoring the falling alarm signal, and when the target object exists in the monitoring video, identifying the behavior action of the target object in the monitoring video and generating an identification result.
Specifically, in an embodiment, after the surveillance video is acquired, first, each object existing in the surveillance video may be identified. When the target object does not exist in the surveillance video as a result of identification, the falling early warning signal can be ignored, and when the target object exists in the surveillance video as a result of identification, the target object can be locked, the behavior action corresponding to the target object in the surveillance video is extracted, the extracted behavior action is identified, and a corresponding identification result is generated. The behavior and the action of the target object can be recognized by using a visual recognition algorithm or a trained recognition model of the behavior and the action and other tools or methods; behavioral actions include, but are not limited to, walking, squatting, leaning against a wall, sitting, falling, and the like.
Exemplarily, after an object existing in a surveillance video is primarily identified, 3 persons are detected in the surveillance video, at this time, 3 target objects in the surveillance video are locked, and behavior actions of the 3 target objects in the surveillance video are identified by using a visual identification algorithm to obtain an identification result; as in this embodiment, the recognition result may be that the target object 1 squats down, the target object 2 stands, and the target object 3 falls.
And step S3: and when the target object is determined to fall down in the elevator based on the identification result, giving alarm information.
Specifically, whether the target object in the elevator falls down is determined according to the recognition result of the behavior and the action of the target object in the monitoring video, when the recognition result indicates that the target object falls down, alarm information can be sent immediately, the alarm information can be a sound prompt, a signal lamp prompt or a voice broadcast prompt, and after receiving the alarm information, a worker can immediately process a falling event.
According to the scheme, when a falling early warning signal is monitored, a monitoring video in the elevator within a preset time period with the current time as the starting time is acquired, whether the falling early warning signal is generated by a target object is judged according to the acquired monitoring video, when the falling early warning signal is generated by the target object, behavior and action of the target object in the monitoring video are identified, whether the target object falls down or not is verified according to the identification result of the behavior and action of the target object in the monitoring video, and when the target object falls down, alarm information is sent out so that a worker can give corresponding rescue measures according to the alarm information; according to the invention, whether the target object in the elevator falls down is judged by combining the detected falling-down early warning signal with the identification of the monitoring video, so that the accuracy of the judgment result is improved, and therefore, corresponding emergency measures can be taken at the first time when a falling-down event occurs, the times of accidents caused by untimely discovery are greatly reduced, and the life safety of people is indirectly ensured.
In an optional embodiment, the detecting a fall warning signal comprises:
when detecting that at least one object exists in the elevator, judging whether the object has falling signs or not based on the object behavior signal; when the subject has evidence of falling, a fall warning signal is generated.
Illustratively, in one embodiment, each object existing in the elevator can be continuously detected, when the behavior signal of at least one object existing in the elevator is detected, the behavior signal of the object is collected, the height of the object, corresponding to the behavior signal, from the top of the elevator is determined according to the behavior signal of the object, whether the object in the elevator has the evidence of falling or not is judged according to the height, when the object has the evidence of falling, a falling early warning signal is generated, and when the object does not have the evidence of falling, the behavior signal of each object in the elevator is continuously detected. Wherein the subject may be any living body with vital signs, the behavior signal may be a signal generated by any minor behavior of the subject, such as a signal generated based on the act of squatting, a signal generated based on leaning, etc.; the evidence of falling is a description that the existing information meets part of the premise of falling, but whether an object falls cannot be directly determined according to the existing information, for example, when a child sits on the ground in the current elevator, sitting is an important premise that the child can judge falling but not a unique premise, so that the child can be judged to have the evidence of falling according to the information.
Illustratively, if there are 2 people, one dog, in the elevator at present, then there are 3 objects in the elevator at this time, person 1, person 2, dog 1. Respectively detecting action signals of each object, wherein if at a certain moment, a person 1 depends on the inner wall of the elevator, a person 2 squats down to tie a shoelace, and the dog 1 does not act; since any one of the tiny behavior signals causes the distance from the object to the top of the elevator to change, whether the object has the falling sign can be judged according to the distance from the object to the top of the elevator corresponding to each behavior signal of the object in the elevator.
For example, personnel 2 become the shoelace of squatting by standing, and at this moment, can detect personnel 2's action signal squat promptly, and the action signal of squat must make the distance increase of 2 the highest departments of personnel's health to the elevator top then, then need further judge personnel 2 according to the reference standard of sign of falling and whether have the sign of falling at this moment, when there being the sign of falling, can generate a early warning signal of falling. When monitoring the early warning signal of falling, can tentatively judge that probably there is personnel in the elevator to fall, at this moment, the moment that just can monitor the early warning signal of falling is the inception moment, acquires the surveillance video in the elevator within 5 seconds, further confirms whether there is personnel to fall in the elevator according to the surveillance video.
In an optional embodiment, the determining whether the subject has evidence of a fall based on the behavioral signal of the subject includes:
determining a height of the object based on the behavior signal of the object; and when the height of the object is lower than a preset threshold value, determining that the object has the falling sign.
For example, the distance from the current object to the top of the elevator can be determined through the collected behavior signals of the object, so that the height from the object to the ground can be determined according to the distance from the object to the top of the elevator and the height from the elevator, and when the height from the object to the ground is lower than a preset threshold value, the current object can be determined to have a falling sign.
Exemplarily, assuming that the height of the elevator is 2.5 meters, 2 persons are present in the elevator, the height of person 1 is 0.9 meters, the height of person 2 is 1.5 meters, the preset threshold value is 0.5 meters, and when person 1 squats down to tie the shoelace, it is detected that the distance to the top of the elevator is 2.1 meters; the height of the person 1 who squats down to tie the shoelace is 0.4 m determined according to the distance from the person 1 to the top of the elevator and the height of the elevator itself, and the person 1 is determined to have a fall sign because 0.4 m <0.5 m.
In another embodiment, in order to avoid the above misjudgment, it may be further configured to, when the fall early warning signal is detected twice within the preset time period, take the time when the fall early warning signal is detected for the second time as the starting time, and obtain the monitoring video in the elevator within the preset time period. For example, when the person 1 squats down to tie the shoelace, the system can preliminarily judge that the shoelace has the falling signs because the height of the person is smaller than the preset threshold value, and therefore a first falling early warning signal can be generated; if the person 1 finishes the action of tying the shoelace and keeps standing within the preset time period, the second fall warning signal does not exist within the preset time period, and in this case, the monitoring video in the elevator does not need to be acquired. In such a way, the situation of misjudgment can be reduced, and thus the accuracy of the fall early warning signal is improved.
The height of this object is confirmed through the action signal of a certain object that receives to this embodiment, judges whether this object has the sign of tumbleing according to the height, has carried out primary screening to all objects in the elevator through this mode, when all objects in the elevator of the affirmation do not have the sign of tumbleing, then need not generate the early warning signal of tumbleing, just also need not acquire the surveillance video and discern the surveillance video. Therefore, the workload is reduced and the working efficiency is improved by primarily screening the target object in the mode.
In an optional embodiment, the identifying the behavior action of the target object based on the monitoring video and generating the identification result includes:
determining a behavior track of a target object in a preset time period based on behavior actions of the target object in a monitoring video; and identifying the behavior track by using a pre-constructed track prediction model to generate an identification result.
For example, when a fall warning signal is monitored and a monitoring video in an elevator within a preset time period is acquired, whether a preset target object, i.e., a person, exists in the monitoring video needs to be detected first; when people exist in the monitoring video, the behavior actions of each person in the monitoring video are extracted, and behavior tracks corresponding to the people are formed according to the behavior actions of each person in the monitoring video. In the embodiment, the behavior track of each person can be identified by using a pre-constructed track prediction model, and an identification result is generated; the pre-constructed trajectory prediction model is an optimized model obtained through a large number of trajectory training processes, and the specific training process belongs to the prior art and is not described herein again.
For example, suppose that the two-time fall warning signal is caused by a child lying on the ground to play in the elevator, at this time, the child can be roughly identified as standing-falling-creeping according to the node of the behavior track of the child, and after the behavior track of the child is identified, the generated identification result is creeping.
For example, assuming that the two fall warning signals are caused by the falling of the old man, at this time, the old man can be roughly identified as standing-relying-falling-lying on side according to the node of the behavior track of the old man, and the old man does not act after lying on side, and the behavior track of the old man is identified by using the track prediction model, and the old man falls as a result of the identification.
In the embodiment, the behavior track of the target object is determined by monitoring the behavior action of the target object in the video, the behavior track of the target object is identified by using a pre-established track prediction model, an identification result is generated, and whether the target object falls down is judged according to the identification result; in the scheme, the behavior track is identified by using the track prediction model, whether a falling event exists is identified more carefully after the falling early warning signal is received, and some false actions similar to falling can be eliminated by the method, so that the identification result is more accurate.
The invention discloses a device for identifying falling of people in an elevator, which comprises the following modules as shown in figure 2:
the obtaining module 21 is configured to obtain a monitoring video within a preset time period by using the current time as an initial time when a fall early warning signal is detected, where the fall early warning signal is generated according to an object in an elevator.
And the identification module 22 is configured to identify a behavior action of a preset target object based on the monitoring video, and generate an identification result.
And the alarm module 23 is used for sending alarm information when the target object is determined to fall down in the elevator based on the identification result.
In an optional embodiment, the obtaining module includes:
the judgment sub-module is used for judging whether the object has falling signs or not based on the behavior signal of the object when the behavior signal of at least one object in the elevator is detected; and the generation submodule is used for generating a fall early warning signal when the subject has the fall signs.
In an alternative embodiment, the determining sub-module includes:
a first determination unit for determining a height of the object based on the behavior signal of the object; and the second determining unit is used for determining that the object has falling signs when the height of the object is lower than a preset threshold value.
In an alternative embodiment, the identification module includes:
the determining submodule is used for determining a behavior track of the target object in a preset time period based on the behavior of the target object in the monitored video; and the recognition submodule is used for recognizing the behavior track by utilizing the pre-constructed track prediction model to generate a recognition result.
The present embodiment provides a computer device, as shown in fig. 3, the computer device may include at least one processor 31, at least one communication interface 32, at least one communication bus 33, and at least one memory 34, where the communication interface 32 may include a Display screen (Display) and a Keyboard (Keyboard), and the optional communication interface 32 may further include a standard wired interface and a standard wireless interface. The Memory 34 may be a high-speed RAM (Random Access Memory) or a non-volatile Memory, such as at least one disk Memory. The memory 34 may optionally be at least one memory device located remotely from the processor 31. Wherein the processor 31 may be combined with the apparatus described in fig. 3, an application program is stored in the memory 34, and the processor 31 calls the program code stored in the memory 34 for performing the method of identifying a fallen person in an elevator of any of the above-described method embodiments.
The communication bus 33 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus 33 may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 3, but that does not indicate only one bus or one type of bus.
The memory 34 may include a volatile memory (RAM), such as a random-access memory (RAM); the memory may also include a non-volatile memory (english: flash memory), such as a Hard Disk Drive (HDD) or a solid-state drive (SSD); the memory 34 may also comprise a combination of the above kinds of memories.
The processor 31 may be a Central Processing Unit (CPU), a Network Processor (NP), or a combination of CPU and NP.
The processor 31 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a Programmable Logic Device (PLD), or a combination thereof. The PLD may be a Complex Programmable Logic Device (CPLD), a field-programmable gate array (FPGA), a General Array Logic (GAL), or any combination thereof. Optionally, the memory 34 is also used to store program instructions. The processor 31 may call program instructions to implement the method of identifying a person falling within an elevator in any of the embodiments of the present invention.
The present embodiment provides a computer-readable storage medium storing computer-executable instructions that can perform the method for identifying a person falling in an elevator in any of the above-described method embodiments. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD), a Solid State Drive (SSD), or the like; the storage medium may also comprise a combination of memories of the kind described above.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.
Claims (10)
1. A method for identifying the fall of a person in an elevator is characterized by comprising the following steps:
when a falling early warning signal is detected, taking the current moment as the starting moment, and acquiring a monitoring video within a preset time period, wherein the falling early warning signal is generated according to an object in an elevator;
based on the monitoring video, recognizing the behavior action of a preset target object to generate a recognition result;
and sending alarm information when the target object is determined to fall down in the elevator based on the identification result.
2. The method for identifying the falling of the people in the elevator according to claim 1, wherein the detection of the falling warning signal specifically comprises:
when detecting that at least one behavior signal of the object exists in the elevator, judging whether the object has falling signs or not based on the behavior signal of the object;
generating the fall warning signal when the subject has evidence of a fall.
3. The method for identifying the fall of the person in the elevator according to claim 2, wherein the determining whether the object has the evidence of the fall based on the behavior signal of the object comprises:
determining a height of the object based on the behavior signal of the object;
determining that the subject has evidence of falling when the height of the subject is below a preset threshold.
4. The method for identifying the fall of the person in the elevator according to claim 1, wherein the identifying the behavior and the action of the target object based on the monitoring video to generate an identification result comprises:
determining a behavior track of the target object in the preset time period based on the behavior action of the target object in the monitoring video;
and identifying the behavior track by using a pre-constructed track prediction model to generate the identification result.
5. An apparatus for identifying a person falling within an elevator, comprising:
the system comprises an acquisition module, a storage module and a control module, wherein the acquisition module is used for acquiring a monitoring video within a preset time period by taking the current moment as an initial moment when a falling early warning signal is detected, and the falling early warning signal is generated according to an object in the elevator;
the identification module is used for identifying the behavior action of a preset target object based on the monitoring video to generate an identification result;
and the warning module is used for sending warning information when the target object is determined to fall down in the elevator based on the identification result.
6. The device for identifying a person who falls down in an elevator according to claim 5, wherein the acquisition module comprises:
the judgment sub-module is used for judging whether the object has falling signs or not based on the behavior signal of the object when the behavior signal of at least one object in the elevator is detected;
a generation submodule for generating the fall warning signal when the subject has evidence of a fall.
7. The device for identifying a person who has fallen down in an elevator according to claim 6, wherein the determination submodule includes:
a first determination unit for determining a height of the object based on a behavior signal of the object;
a second determination unit, configured to determine that there is an evidence of a fall for the subject when the height of the subject is below a preset threshold.
8. The device for identifying a person who has fallen down in an elevator according to claim 5, wherein the identification module includes:
the determining submodule is used for determining a behavior track of the target object in the preset time period based on the behavior action of the target object in the monitoring video;
and the recognition submodule is used for recognizing the behavior track by utilizing a pre-constructed track prediction model to generate a recognition result.
9. A computer device, comprising: a memory and a processor, communicatively connected to each other, the memory for storing a computer program which, when executed by the processor, causes the processor to carry out a method of identifying a fall of a person in an elevator as claimed in any one of claims 1 to 4.
10. A computer-readable storage medium for storing computer instructions which, when executed by a processor, implement the method of identifying a fall of a person in an elevator according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211231519.1A CN115849124A (en) | 2022-10-09 | 2022-10-09 | Method, device, equipment and medium for identifying falling of people in elevator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211231519.1A CN115849124A (en) | 2022-10-09 | 2022-10-09 | Method, device, equipment and medium for identifying falling of people in elevator |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115849124A true CN115849124A (en) | 2023-03-28 |
Family
ID=85661350
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211231519.1A Pending CN115849124A (en) | 2022-10-09 | 2022-10-09 | Method, device, equipment and medium for identifying falling of people in elevator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115849124A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106530611A (en) * | 2016-09-28 | 2017-03-22 | 北京奇虎科技有限公司 | Terminal, and method and apparatus of detecting fall of human body |
| CN108840192A (en) * | 2018-08-14 | 2018-11-20 | 北京瑞特森传感科技有限公司 | A kind of monitoring method of elevator, device, electronic equipment and storage medium |
| CN111627185A (en) * | 2019-02-27 | 2020-09-04 | 富士通株式会社 | Fall alarm method and device and fall detection system |
| EP3461780B1 (en) * | 2017-09-29 | 2021-05-26 | Otis Elevator Company | Mechanical hoistway access control device |
| CN114359814A (en) * | 2022-01-12 | 2022-04-15 | 平安科技（深圳）有限公司 | Fall detection method, device, equipment and storage medium |
-
2022
- 2022-10-09 CN CN202211231519.1A patent/CN115849124A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106530611A (en) * | 2016-09-28 | 2017-03-22 | 北京奇虎科技有限公司 | Terminal, and method and apparatus of detecting fall of human body |
| EP3461780B1 (en) * | 2017-09-29 | 2021-05-26 | Otis Elevator Company | Mechanical hoistway access control device |
| CN108840192A (en) * | 2018-08-14 | 2018-11-20 | 北京瑞特森传感科技有限公司 | A kind of monitoring method of elevator, device, electronic equipment and storage medium |
| CN111627185A (en) * | 2019-02-27 | 2020-09-04 | 富士通株式会社 | Fall alarm method and device and fall detection system |
| CN114359814A (en) * | 2022-01-12 | 2022-04-15 | 平安科技（深圳）有限公司 | Fall detection method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 万航;陈立潮;潘理虎;谢斌红;张英俊;: "基于智能视频监控的老人跌倒识别算法研究", 太原科技大学学报, no. 04, 15 August 2013 (2013-08-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107146386B (en) | Abnormal behavior detection method and device, and user equipment | |
| CN105354956B (en) | The cloud computing platform and method analyzed based on data mining and big data | |
| CN112489368A (en) | Intelligent falling identification and detection alarm method and system | |
| CN110801593B (en) | Extremely early fire early warning system and method fusing multi-mode data | |
| US20180008169A1 (en) | Analysis of fall severity of fall detection system and wearing apparatus | |
| CN111241913A (en) | Method, device and system for detecting falling of personnel | |
| JP2018072881A (en) | Fire disaster monitoring system | |
| KR100916960B1 (en) | Monitoring system in railway station | |
| CN111739243B (en) | D-S evidence theory-based fire state detection method | |
| CN102280002A (en) | Dual-mode alarm device and method capable of decreasing false alarm rate | |
| CN106586747A (en) | Elevator operation monitoring method and device | |
| CN110633652A (en) | Unexpected situation determination method and device and electronic equipment | |
| CN115849124A (en) | Method, device, equipment and medium for identifying falling of people in elevator | |
| CN112017401A (en) | Alarm system for monitoring the safety of persons, corresponding method and storage medium | |
| CN101635083A (en) | Event detecting method and event detecting device | |
| KR20150080128A (en) | Fire fight safety system for architecture using alalog address type sensor | |
| CN113936293A (en) | Video information-based off-duty personnel detection method, control device and storage medium | |
| CN111126100B (en) | Alarm method, alarm device, electronic equipment and storage medium | |
| KR101629219B1 (en) | An elevator monitor that restricts access through face recognition | |
| CN211827514U (en) | Fall alarm device and system | |
| CN111797802B (en) | Escalator unsafe behavior real-time early warning method based on AI vision | |
| CN114314243A (en) | Elevator overload alarm system and method based on video identification technology | |
| CN113420626A (en) | Construction site safety behavior judging method and storage device | |
| CN113158847A (en) | Unsafe behavior detection method based on artificial intelligence | |
| CN111568427A (en) | System and method for monitoring activity state of old people |
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 |