Elevator remote safety early warning method and system
Through the image, video and audio information in the elevator, determine the identity and behavior of passengers, identify special groups and implement early warning strategies, the problem of insufficient identification of safety hazards for special groups in the existing technology is solved, and timely warning of special groups in the elevator is achieved and security.
Patent Information
- Application Number
- CN202411211154.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-30
- Publication Date
- 2024-11-12
AI Technical Summary
The existing elevator safety warning system mainly focuses on the elevator's own failures. It fails to effectively identify and warn of safety hazards in special groups (such as blind people, elderly people, children) in the elevator, making it difficult for these groups to misuse the elevator or be trapped passively. Get timely help.
By obtaining the image, video and audio information in the elevator, we judge the number and identity of passengers, and based on the specific judgment information, whether the passenger is a special group. If it is a special group, an elevator warning strategy is implemented, such as opening the elevator door and sending an alarm message.
It improves the accuracy of identifying special groups, promptly warns and solves the safety hazards of special groups in the elevator, and avoids safety risks caused by mistakenly entering the elevator.
Smart Images

Figure CN118929370A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of elevator operation warning, and in particular to an elevator remote safety warning method and system. Background Art
[0002] Elevator safety warning is now considered a technology used to monitor the operating status of elevators and detect potential safety hazards in advance. This technology collects data through sensors and other monitoring equipment installed on the elevator, and then uses data analysis and intelligent algorithms to determine whether the elevator has a fault or abnormality, and issues a warning notification when necessary.
[0003] At present, the elevator safety warning system mainly focuses on the possible faults of the elevator's main structure during operation, such as unstable operation caused by the wear of the elevator bearing, the failure of the elevator door opening or closing mechanism, and the failure of the elevator sensor. However, the safety of the passengers riding the elevator is often limited. Because it is generally believed that as long as the elevator itself can operate safely, the safety of the passengers can be ensured. At the same time, almost all elevators today are equipped with calling devices and video monitoring devices. If passengers encounter problems in the elevator, they can use the calling device to seek help. Therefore, it is generally believed that if the elevator can operate safely, the passengers are safe in the elevator. For some special groups, they cannot use the calling device independently, nor can they identify the floor signs in the elevator, resulting in the inability to use the elevator safely and reasonably, which easily causes special groups to be trapped and locked in the elevator due to improper use of the elevator or passively due to the automatic closing of the elevator door. Although the elevator is equipped with a video monitoring device, it generally only plays a recording role. If the monitor conducts real-time monitoring, not only does the monitor need to stay by the camera monitoring device all the time, but also needs to have rich experience and be able to identify the group as a special group through a single image information, and that the special group has encountered problems and needs help. In this way, it is not only difficult to help the special group, but also more time and energy are wasted.
[0004] In order to provide corresponding assistance to special groups and reduce the occurrence of safety problems, elevators are currently being modified to assist special groups in their use. However, special groups include not only the blind, but also the elderly and children who do not have the ability to recognize the floor signs and call device signs in the elevator. At present, the widespread modification of elevators in the market is more based on the needs of the blind. Although it has solved the safety problem of blind people when riding elevators to a certain extent, this kind of elevator modification is not only costly, but has not been invested in real life on a large scale.
[0005] In the prior art, the patent application number CN112184737A is a detection and alarm system for children riding alone in elevators based on image analysis. The multi-camera is used as an information collection port to read the distance data of people entering the elevator. The RGB camera extracts the portrait area in the photo when the elevator is opened, imports the area back into the photo taken, reads some features of the portrait in the photo taken, and scans it through the TOF camera to establish a three-dimensional model of the person. Then, it is combined with some feature data of the portrait to establish a real three-dimensional portrait model, so as to determine whether there are children entering the elevator, and then all the real three-dimensional model data in the elevator are compared with the pre-stored information in the database to determine whether the child entering the elevator is alone, so as to alarm. This patent can only alarm for children entering the elevator, which has certain limitations. At the same time, the international "Convention on the Rights of the Child" defines children as anyone under the age of 18. In reality, children who can independently and clearly control the elevator account for a large proportion, and most of these children should not belong to special groups. Therefore, this patent can only identify children, and special groups are not only children. Therefore, this patent cannot solve the problem of safety hazards caused by special groups mistakenly entering the elevator. Summary of the invention
[0006] In order to solve the problem of preventing special groups from mistakenly entering the elevator during normal operation of the elevator, thereby causing safety hazards to special groups, the first solution provides an elevator remote safety warning method, including: S1, obtaining the number of passengers in the elevator; S2, if there is only one passenger in the elevator, judging the identity of the passenger; wherein the passenger's identity includes adults and children; S3, based on the passenger's identity, judging whether the passenger is a special group according to the target judgment information; S4, if the passenger is a special group, executing the elevator warning strategy.
[0007] Beneficial effect: Different from the prior art, the technical problem solved by the first solution is that when the elevator is operating normally, the passengers in the elevator may be special groups, and special groups are prone to safety hazards due to their own limitations when riding the elevator. Therefore, the safety hazard of the elevator is not only caused by the abnormal operation of the elevator itself, but also may be caused by special groups when riding the elevator.
[0008] Secondly, the first solution can determine the identity of special groups, and adopt different target determination information according to the identity of special groups to determine whether the passenger belongs to the special group, thereby improving the accuracy of identifying special groups.
[0009] Preferably, the process further includes S201: if the height of the passenger is higher than a first height threshold, the passenger is an adult; otherwise, the passenger is a child.
[0010] Beneficial effect: By determining the identity of a passenger by height, the identity of the passenger can be determined simply, directly and efficiently.
[0011] Preferably, the first height threshold is 138 cm.
[0012] Beneficial effects: There is an obvious height difference between adults and children. Height recognition can improve the difference between adults and children, so as to achieve more accurate identification of children and adults.
[0013] Preferably, the target determination information includes image information in the elevator, audio information in the elevator, video information in the elevator and elevator operation status information.
[0014] Beneficial effect: The target determination information is further limited, and through the specific target determination information, it is possible to accurately determine whether passengers of different identities belong to special groups.
[0015] Preferably, it also includes S301, when the passenger is a child, the target determination information is: if there is a "crying sound" in the audio information in the elevator, or the expression of the child in the image information in the elevator is "sad", then the child belongs to a special group.
[0016] Beneficial effect: Such judgment information can be used to accurately analyze whether a child belongs to a special group.
[0017] Preferably, it also includes S302, when the passenger is an adult, the target determination information is: within the first time, the adult in the video information in the elevator did not operate the buttons in the elevator, or operated the buttons in the elevator multiple times, then the adult belongs to a special group.
[0018] Beneficial effect: Such determination information can be used to accurately analyze whether an adult belongs to a special group.
[0019] Preferably, the first time is 10s.
[0020] Beneficial effect: Within 10 seconds, if an adult does not operate the buttons in the elevator, or operates the buttons in the elevator multiple times, it is judged as
[0021] Preferably, the special group is a group that does not have the ability to recognize the floor identification and the identification of the calling device in the elevator.
[0022] Beneficial effect: Accurately divide the characteristic range to which special groups belong.
[0023] Preferably, the elevator early warning strategy includes opening the elevator door and sending an alarm message.
[0024] Beneficial effect: By keeping the elevator door in an open state and sending an alarm message, the potential safety hazard of the elevator can be effectively solved.
[0025] The second scheme provides an elevator remote safety warning system, which executes an elevator remote safety warning method of the first scheme, including: a monitoring module, used to obtain image information, video information and audio information in the elevator; a passenger number judgment module, used to judge the number of passengers in the elevator according to the image information; a passenger identity judgment module, used to judge the identity of the passenger according to a first height threshold; a special group judgment module, used to judge whether the passenger belongs to a special group based on the identity of the passenger and according to target judgment information; an early warning module, used to implement an elevator early warning strategy when a passenger is judged to be a special group.
[0026] Beneficial effects: This solution can accurately identify whether a passenger belongs to a special group, thereby determining whether to initiate a remote safety warning for the elevator. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] Figure 1 The figure is a schematic diagram of a remote safety warning method for an elevator according to the first embodiment of the present invention. DETAILED DESCRIPTION
[0028] The following embodiments of the technical solution of the present invention are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and are therefore only used as examples, and cannot be used to limit the protection scope of the present invention.
[0029] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by those skilled in the art to which the present invention belongs.
[0030] Embodiment 1
[0031] like Figure 1 As shown, this embodiment provides an elevator remote safety warning method, including:
[0032] S1, obtain the number of passengers in the elevator.
[0033] Specifically, the monitoring device in the elevator obtains the image information, video information and audio information in the elevator and sends it to the elevator remote safety alarm center. The elevator remote safety alarm center determines the number of passengers based on the image information in the elevator.
[0034] S2, if there is only one passenger in the elevator, determine the identity of the passenger; the passenger's identity includes adults and children.
[0035] Specifically, when the elevator remote safety alarm center determines that the number of passengers is one person based on the image information in the elevator, it further determines the identity of the passenger. The elevator remote safety alarm center identifies the identity of the passenger based on the target determination information. In the prior art, most image information recognitions determine the age of the passenger by face. In this embodiment, it is only necessary to determine whether it is a child or an adult, without analyzing the specific age. Therefore, in order to further improve the speed of image recognition, it is only necessary to determine whether the passenger's height is less than 138cm. If the passenger's height is less than 138cm, the passenger is determined to be a child. If the passenger's height is higher than 138cm, it is directly determined to be an adult. Among them, 138cm is the first height threshold.
[0036] S3, based on the passenger's identity, determine whether the passenger belongs to a special group according to the target determination information.
[0037] Specifically, the monitoring device in the elevator obtains target determination information, and the target determination information includes the image information, video information and audio information in the elevator described in S1. The target determination information includes the image information, audio information and video information in the current elevator. When the elevator remote safety alarm center receives the target determination information sent by the monitoring device, it identifies whether the passenger is a child based on the image information in the elevator. In this embodiment, simply determining whether a child is alone in the elevator does not mean that the child will have safety problems. Because children can be divided into two types, one is a child who has the ability to recognize the floor signs and call device signs in the elevator; the other is a child who does not have the ability to recognize the floor signs and call device signs in the elevator. The age of children who do not have the ability to recognize the floor signs and call device signs in the elevator is relatively young, and entering the elevator may be a mistake. Once mistakenly entering, it will easily cause safety problems. For example, in the normal operation of the elevator, when a child enters the elevator, the elevator door will automatically close. Since the child does not recognize the floor signs and call devices in the elevator, he cannot save himself and can only be forced to wait until someone else takes the elevator before being rescued.
[0038] To further improve accuracy, it is determined whether the child is a child who does not have the ability to recognize the floor signs and call device signs in the elevator. The facial expression of the child is determined based on the image information. If the facial expression is "sad"; or if there is "crying" in the audio information; whether the child's facial expression is "sad" or the audio information contains "crying", it is determined that the child in the elevator does not have the ability to recognize the floor signs and call device signs in the elevator. According to the current international "Convention on the Rights of the Child", children are defined as anyone under the age of 18. Most children under the age of 18 have the ability to recognize the signs of the elevator floors and the signs of the call devices in the elevator. Only a few children who are younger or mentally retarded do not have the ability to recognize the signs of the elevator floors and the signs of the call devices in the elevator. These groups should be special groups and should require elevator remote safety warnings.
[0039] Specifically, the elevator remote safety alarm center is provided with a database, and the "sad" expression of the child's face is stored in the database. Combined with the image recognition algorithm of the current prior art, the image information returned by the monitoring device is compared with the "sad" expression of the child's face stored in the database to see if the comparison is successful. If successful, the child's face is in a sad state, and the child is directly identified as a special group. The prior art generally requires the analysis of the child's expression to analyze the state of the child's expression, so as to further determine whether the child is a special group. However, this embodiment is different. This embodiment directly compares with the sad expression in the database, which speeds up the recognition speed. Since the special group enters the elevator, the elevator door will close automatically soon, so the special group needs to be identified before the elevator door closes automatically. Therefore, for the technical solution of this embodiment, it is necessary to quickly and timely identify the special group, and at the same time accurately identify whether the passenger is a special group, so as to effectively implement the elevator safety warning method. Since the monitoring device is generally arranged above the corner of the elevator, most passengers will turn their backs to the monitoring device after entering the elevator, so it is difficult for the monitoring device to obtain the child's facial expression. In order to further accurately identify whether the child is a special group, the sound sensor in the monitoring device is used to collect audio information. Since the child is alone in the elevator at this time, there is generally no other noisy sound in the elevator, so only the audio information needs to be analyzed by the elevator remote safety alarm center. In the audio information, if the sound intensity within 4 seconds is between 70-90 decibels, it is considered that the audio information contains "crying", that is, the child is judged to be a special group.
[0040] For example, the patent application number CN112184737A described in the background technology is a detection and alarm system for children riding alone in elevators based on image analysis. This patent uses multiple cameras to scan, then builds a three-dimensional model of the person, and then makes a judgment. Through such layer-by-layer analysis, it is possible that the child has closed the elevator door and used the elevator. At the same time, the international "Convention on the Rights of the Child" defines children as anyone under the age of 18. Under this definition, only a small number of children do not have the ability to recognize the floor signs and call device signs in the elevator.
[0041] When the passenger in the elevator is an adult, it is determined whether the adult has the ability to recognize the floor signs and the signs of the call device in the elevator. For example, a blind person, or a passenger with senile dementia, or a passenger with Alzheimer's disease does not have the ability to recognize the floor signs and the signs of the call device in the elevator.
[0042] In the prior art, such as a multi-channel fusion elevator auxiliary system and method with patent application number CN202011551708.8, the patent uses the camera and microphone in the crowd recognition module to collect video and audio data from multiple angles or directions to train the model. Then the collected video and audio data are trained by the automatic answering module for training the automatic answering model. The training model is collected according to the behavior analysis module and the inferred suspicious behavior related information is connected to the relevant security system. This patent is suitable for use by special groups, such as blind people entering the elevator. This patent uses cameras and microphones and builds models to identify whether the passenger is a special group. Like this, the monitoring device is used to distinguish whether the passenger is a special group. Because the blind, or passengers with Alzheimer's disease, who do not have the cognitive ability for the floor signs and call device signs in the elevator, are difficult to distinguish from the body characteristics, so the monitoring device collects their body data and audio data to distinguish whether they are special groups. This has poor accuracy and requires a training model, which not only requires a large amount of training data, but also has a high training cost. At the same time, when there are many passengers in the elevator, the complexity of the monitoring device's recognition increases, thereby reducing the accuracy of the recognition.
[0043] In this embodiment, the elevator remote safety alarm center obtains the elevator operation status, including whether the floor identification key in the elevator is lit, that is, whether the passenger presses the floor identification key. According to the video information analysis, if the passenger does not operate the elevator within 10 seconds or the passenger presses at least three floor identification keys according to the operation status of the elevator, it is determined that the passenger does not have the ability to recognize the floor identification in the elevator and the identification of the calling device.
[0044] S4: If the passenger belongs to a special group, the elevator early warning strategy is executed.
[0045] Specifically, if the elevator remote safety alarm center determines that the passenger is a special group, the elevator early warning measurement is performed. The elevator early warning strategy includes keeping the elevator door open, and the worker remotely calls back to the elevator to help the special group by voice. The elevator remote safety alarm center is a terminal in this embodiment. The monitoring device includes a monitoring camera and a sound sensor. The monitoring device is installed at a diagonal angle to the elevator door, and the monitoring camera is installed on the top of the inner wall of the elevator and faces the elevator door. The sound sensor is installed close to the monitoring camera. The layout of the monitoring device can refer to the existing technology.
[0046] The beneficial effects of this embodiment
[0047] Existing technologies either modify elevators to help special groups, but this is relatively costly; or they can only be linked to image algorithm models and image recognition. Since it is difficult to distinguish special groups from images alone, whether in terms of height, body shape or expression, this has poor accuracy and requires a large amount of data to train the model, which is time-consuming and complicated.
[0048] Compared with the prior art that uses image algorithm models and image recognition to identify special groups, although image recognition technology can play a certain role in identifying special groups, since the performance characteristics of special groups are people who do not have the cognitive ability to recognize the floor signs and call device signs in the elevator, this embodiment no longer relies entirely on image recognition technology to identify special groups like the prior art, but identifies whether they belong to special groups based on the behavioral habits of special groups including body movements. However, special groups include people with Alzheimer's disease, senile dementia, the blind, or some children who do not have the ability to recognize floor signs and call devices in elevators. Such age gaps are large, and it is difficult to determine whether a passenger belongs to a special group by identifying their appearance. Therefore, it is necessary to further accurately determine whether a passenger of this type belongs to a special group based on the classification of different types of passengers.
[0049] Secondly, in steps S2 and S3 of this embodiment, the identity of the passenger is first determined. The behavioral habits, such as body movements, of passengers with different identities vary greatly. Especially when riding in an elevator, it is necessary to determine whether the passenger belongs to a special group in a very short time in order to achieve timely remote safety warning of the elevator.
[0050] Next, the passenger's identity is determined based on his height, which not only takes a short time, but the surveillance cameras are usually located in the corners. After entering the elevator, the passengers are usually facing the elevator door with their backs to the health camera. It is difficult to determine whether the passenger is a child or an adult from facial recognition. Judging by height can help to improve the accuracy of recognition.
[0051] Moreover, in S3, passengers of different identities are identified in different ways, that is, the target determination information is different. When the passenger is a child, by determining the state of his / her facial expression or whether he / she is crying, it can be accurately determined that when a child takes the elevator alone in an unfamiliar environment, he / she is prone to emotional excitement and sadness when he / she encounters something that he / she cannot solve. Therefore, it can be accurately determined that the child does not have the ability to recognize the floor signs and call devices in the elevator. When the passenger is an adult, by determining whether the adult can freely operate the elevator, that is, indirectly judging the adult's behavior habits such as body movements through the detection of elevator button operation, such identification is more accurate; at the same time, since the passenger operates the elevator button with his / her back to the surveillance camera, it is blocked by the passenger's body, and it is difficult for the surveillance camera to obtain whether the passenger has operated the elevator. Therefore, it is not easy to identify the passenger's body movements based on the single surveillance camera set in the elevator.
[0052] Finally, the existing technology only uses image recognition and the establishment of algorithm models to identify whether a passenger is a special group in an integrated manner, relying on image recognition to identify faces and body movements. However, in common elevators, only one surveillance camera is installed above the corner of the elevator. If the faces and body movements of passengers are to be accurately identified, the elevator needs to be modified and more cameras installed to obtain all-round passenger data. However, this not only increases the modification cost, but also makes it more complicated to use.
[0053] Embodiment 2
[0054] This embodiment provides an elevator remote safety warning system, which executes an elevator remote safety warning method in embodiment one. An elevator remote safety warning system includes a monitoring module, a passenger quantity judgment module, a passenger identity judgment module, a special group judgment module and an early warning module. The monitoring module includes a monitoring device provided in the elevator, which is used to obtain image information, video information and audio information in the elevator through the monitoring device. The passenger quantity judgment module is used to judge the number of passengers in the elevator according to the image information. The passenger identity judgment module is used to judge the identity of the passenger according to the first height threshold. The special group judgment module is used to judge whether the passenger belongs to a special group based on the identity of the passenger and the target judgment information. The early warning module is used to implement the elevator early warning strategy when the passenger is judged to be a special group.
[0055] This embodiment is a brief description, and specific reference may be made to the technical details provided in Embodiment 1.
[0056] In this specification, a lot of specific details are described. However, it is understood that embodiments of the present invention can be put into practice without these specific details. In some examples, known methods, systems and techniques are not shown in detail so as not to obscure the understanding of this specification. In the description of this specification, the description of reference terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" etc. means that the specific features, methods, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of this specification.
[0057] In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, systems, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples without contradiction.
[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.
Claims
1. A remote safety early warning method for an elevator, characterized in that: include: S1, obtain the number of passengers in the elevator; S2, if there is only one passenger in the elevator, determine the identity of the passenger; the passenger's identity includes adults and children; S3, based on the passenger's identity, judging whether the passenger belongs to a special group according to the target determination information; S4: If the passenger belongs to a special group, the elevator early warning strategy is executed.
2. A remote safety early warning method for an elevator according to claim 1, characterized in that: The process also includes S201: if the height of the passenger is higher than a first height threshold, the passenger is an adult; otherwise, the passenger is a child.
3. A remote safety early warning method for an elevator according to claim 2, characterized in that: The first height threshold is 138cm.
4. A remote safety early warning method for an elevator according to claim 1, characterized in that: The target determination information includes image information in the elevator, audio information in the elevator, video information in the elevator, and elevator operation status information.
5. A remote safety early warning method for an elevator according to claim 4, characterized in that: It also includes S301, when the passenger is a child, the target judgment information is: if the audio information in the elevator contains "crying" or the expression of the child in the image information in the elevator is "sad", then the child belongs to a special group.
6. A remote safety early warning method for an elevator according to claim 4, characterized in that: It also includes S302, when the passenger is an adult, the target judgment information is: within the first time, the adult in the video information in the elevator did not operate the buttons in the elevator, or operated the buttons in the elevator multiple times, then the adult belongs to a special group.
7. An elevator remote safety warning method according to claim 6, characterized in that: The first time is 10s.
8. The elevator remote safety warning method according to claim 1, characterized in that: The special group is a group that does not have the ability to recognize the floor signs in the elevator and the signs of the calling device.
9. An elevator remote safety warning method according to claim 1, characterized in that: The elevator early warning strategy includes opening the elevator door and sending an alarm message.
10. An elevator remote safety warning system, characterized in that: An elevator remote safety warning method implemented in any one of claims 1 to 9 comprises: Monitoring module, used to obtain image information, video information and audio information in the elevator; A passenger number determination module is used to determine the number of passengers in the elevator based on image information; A passenger identity determination module, used to determine the identity of the passenger according to the first height threshold; A special group determination module is used to determine whether a passenger belongs to a special group based on the identity of the passenger and the target determination information; The early warning module is used to implement the elevator early warning strategy when passengers are judged to be special groups.
