An elevator fall warning system based on image recognition technology

Abstract

The present invention discloses an elevator fall warning system based on image recognition technology, which specifically relates to the field of image recognition technology, including a monitoring area division module, a fall data acquisition module, a data preprocessing module, a data analysis module, a comprehensive data analysis module, a judgment module and a human-computer interaction module. The present invention determines a sub-time monitoring area and a sub-area monitoring area through a monitoring area division module, collects data of changes caused by a single human body fall in an elevator through a fall data acquisition module, performs a series of processing and analysis on the collected data through a data preprocessing module and a data analysis module, calculates a comprehensive fall assessment index through a comprehensive data analysis module, and judges whether a passenger falls in the elevator by comparing it with the warning value of the comprehensive fall assessment index established by the judgment module, and transmits the alarm information to relevant staff through a human-computer interaction module.

Description

Technical Field

[0001] The present invention relates to the field of image recognition technology, and more specifically, to an elevator fall warning system based on image recognition technology. Background Art

[0002] As an important means of transportation in modern cities, the safety and reliability of elevators are directly related to the safety of people's lives and property. The occurrence of elevator failures brings safety hazards to people's travel. With the aging of the global population, the elderly use elevators more frequently in their daily lives. Due to the decline in physical function, the elderly are more likely to fall in the elevator and have accidents. Therefore, the development of an elevator fall warning system has become an important measure to meet the safety needs of the elderly. The fall warning system can monitor the posture and movements of passengers in real time through sensors when passengers enter the elevator or the elevator is running. Once a potential risk of falling is detected, an alarm will be immediately issued and corresponding safety measures will be taken.

[0003] The traditional elevator fall warning system includes a data acquisition module, a data analysis and processing module, a warning and alarm module, a communication and transmission module, and a monitoring and display module. The data acquisition module collects various data inside and outside the elevator through sensors; the data analysis and processing module is used to analyze and process the collected data, and use the preset algorithm to identify the passenger's fall behavior or predict the risk of falling; the warning and alarm module is used to send an alarm signal to the monitoring center based on the detected signal; the communication and transmission module is responsible for realizing the communication between the modules within the system and the information transmission between the system and external devices; the monitoring and display module is connected to the monitoring center to display the operating status of the elevator and the behavior of passengers in real time. The elevator fall warning system is of great significance in improving passenger safety, enhancing the convenience of elevator use, promoting intelligent and humanized development, reducing social costs, and promoting the improvement of relevant laws and regulations.

[0004] However, in actual use, it still has some shortcomings, such as the collected data is not comprehensive enough. The traditional elevator fall warning system only determines whether a passenger has fallen in the elevator by monitoring the images in the elevator. The collected data is not comprehensive enough and cannot accurately reflect the real-time situation in the elevator; the feedback results are not intuitive enough. The traditional elevator fall warning system needs to perform a series of processing and analysis on the collected images, and judge whether a passenger has fallen through a preset algorithm. It cannot intuitively obtain the situation of passengers falling in the elevator. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an elevator fall warning system based on image recognition technology, which solves the problems raised in the above-mentioned background technology through the following scheme.

[0006] To achieve the above object, the present invention provides the following technical solution: an elevator fall warning system based on image recognition technology, comprising:

[0007] Monitoring area division module: used to determine a single sub-time monitoring area, and divide the time from the moment a person enters the elevator to the moment he gets off the elevator into a single sub-time monitoring area according to a time length of 1 second, and mark them as 1, 2, ..., i, ..., n in sequence, and divide the bottom of the elevator into a single sub-area monitoring area in an equal area division manner, and mark them as 1, 2, ..., j, ..., k in sequence;

[0008] Fall data collection module: used to collect data on changes caused by a single person falling in the elevator, including a human change data collection unit and an elevator change data collection unit, and pass the collected data to the data preprocessing module;

[0009] Data preprocessing module: including a human body change data preprocessing unit and an elevator change data preprocessing unit, used to preprocess and analyze the human body change data and elevator change data collected by the fall data collection module, and pass the results to the data analysis module;

[0010] Data analysis module: including a human body change data analysis unit and an elevator change data analysis unit, which are used to process the body position change evaluation value, body angle change evaluation value, elevator force change evaluation value and elevator kinetic energy change evaluation value obtained by the data preprocessing module, and transmit the results to the comprehensive data analysis module;

[0011] Comprehensive data analysis module: including a comprehensive data analysis unit, used to comprehensively process and analyze the human body change assessment index and the elevator change assessment index obtained by the data analysis module, and transmit the processing results to the judgment module;

[0012] Judgment module: used to establish a comprehensive fall assessment index warning value, and to judge whether there is a passenger fall in the elevator by comparing the calculated comprehensive fall assessment index with the comprehensive fall assessment index warning value, and to pass the judgment result to the human-computer interaction module;

[0013] Human-computer interaction module: used to send alarm information to the elevator control center based on the information transmitted by the judgment module, and notify relevant staff of the passenger's condition in the elevator.

[0014] Preferably, the human body change data acquisition unit is used to collect body position change parameters and body angle change parameters, and the body position change parameters include the instantaneous height difference of the head position, the instantaneous height difference of the shoulder position, the instantaneous height difference of the knee position, and the human body aspect ratio, which are marked as H and H respectively. h , H s , H k and Ra , the body angle change parameters include the human body pitch angle, human body roll angle and human body yaw angle, which are marked as θ p ,θ r and θ y .

[0015] Preferably, the elevator change data acquisition unit is used to collect elevator force change parameters and elevator operation state change parameters, the elevator force change parameters include the pressure on the elevator, marked as F, and the elevator operation state change parameters include the overall kinetic energy value of the elevator, marked as E K .

[0016] Preferably, the human body change data preprocessing unit is used to process the body position change parameters and body angle change parameters collected by the fall data collection module, and calculate the body position change evaluation value and the body angle change evaluation value, and the body position change evaluation value is specifically expressed as:

[0017]

[0018] y Li represents the estimated value of the body position change of a single person in the elevator in the monitoring area at the i-th sub-time, H hi It represents the instantaneous height difference of the head position of a single person in the elevator in the monitoring area at the ith sub-time, H si It represents the instantaneous height difference of the shoulder position of a single person in the elevator in the monitoring area at the ith sub-time, H ki R represents the instantaneous height difference of the knee position of a single person in the elevator in the monitoring area at the ith sub-time. ai represents the aspect ratio of a single person in the elevator in the i-th sub-time monitoring area, δ1, δ2, δ3 and δ4 represent the influence coefficients of the instantaneous height difference of the head position, the instantaneous height difference of the shoulder position, the instantaneous height difference of the knee position and the aspect ratio of the human body on the body position change evaluation value respectively; the body angle change evaluation value is specifically expressed as:

[0019]

[0020] y Ai represents the body angle change evaluation value of a single person in the elevator in the i-th sub-time monitoring area, θ pi represents the human body pitch angle of a single person in the elevator in the monitoring area of ​​the i-th sub-time, θ ri represents the human body roll angle of a single person in the elevator in the i-th sub-time monitoring area, θ yi represents the yaw angle of a single person in the elevator in the i-th sub-time monitoring area, δ5, δ6 and δ7 respectively represent the influence coefficients of the human pitch angle, human roll angle and human yaw angle on the body angle change evaluation value.

[0021] Preferably, the elevator change data preprocessing unit is used to process the elevator force change parameters and the elevator operation state change parameters collected by the fall data collection module, and calculate the elevator force change evaluation value and the elevator operation state change evaluation value, and the elevator force change evaluation value is specifically expressed as:

[0022]

[0023] y 压i represents the elevator force change evaluation value in the monitoring area at the ith sub-time, F ij F represents the pressure on the elevator floor in the jth sub-area monitoring area detected by the elevator in the i-th sub-time monitoring area. (i-1)j It indicates the pressure of the elevator floor in the jth sub-area monitoring area detected by the elevator in the i-1th sub-time monitoring area; the evaluation value of the elevator kinetic energy change is specifically expressed as:

[0024]

[0025] y 动i represents the elevator kinetic energy change evaluation value in the i-th sub-time monitoring area, E Ki It represents the total kinetic energy value of the elevator detected in the i-th sub-time monitoring area, E K标i It represents the real-time total kinetic energy value of the elevator when there is no passenger falling in the monitoring area of ​​the i-th sub-time and the elevator is operating normally. When the elevator is in an accelerated motion state,

[0026]

[0027] m represents the total mass of the elevator including all objects inside the elevator, F 上i represents the upward force acting on the elevator detected in the i-th sub-time monitoring area, F 下i represents the downward force acting on the elevator detected in the i-th sub-time monitoring area, t i represents the i-th moment of the elevator motion. When the elevator is in a uniform motion state,

[0028]

[0029] t n1 It is the moment when the elevator stops accelerating, F 上n1 The upward force F is the force exerted on the elevator when it stops accelerating. 下n1 It indicates the downward force on the elevator when it stops accelerating.

[0030]

[0031] Preferably, the human body change data analysis unit is used to establish a human body change data analysis model, import the body position change evaluation value and the body angle change evaluation value into the human body change data analysis model, and calculate the human body change evaluation index, which is specifically expressed as:

[0032]

[0033] y 1i represents the passenger body change assessment index of the elevator in the monitoring area at the i-th sub-time, y Li represents the estimated value of the body position change of a single person in the monitoring area of ​​the elevator at the i-th sub-time, y Ai represents the body angle change evaluation value of a single person in the elevator monitoring area at the i-th sub-time, Δy L Denotes the estimated value of the body position change of a normal single person without falling, Δy A represents the body angle change assessment value of a normal single human body when no one falls, α1 and α2 respectively represent the influence coefficients of the body position change assessment value and the body angle change assessment value on the human body change assessment index.

[0034] Preferably, the elevator change data analysis unit is used to establish an elevator change data analysis model, import the elevator force change evaluation value and the elevator kinetic energy change evaluation value into the elevator change data analysis model, and calculate the elevator change evaluation index, which is specifically expressed as:

[0035]

[0036] y 2i represents the elevator change evaluation index in the i-th sub-time monitoring area, y 压i represents the elevator force change evaluation value in the monitoring area at the ith sub-time, y 动i represents the elevator kinetic energy change evaluation value in the i-th sub-time monitoring area, Δy 压 It represents the normal force change assessment value of the elevator when no one falls. β1 and β2 respectively represent the influence coefficients of the elevator force change assessment value and the elevator kinetic energy change assessment value on the elevator change assessment index.

[0037] Preferably, the comprehensive data analysis unit is used to establish a comprehensive data analysis model, import the human body change assessment index and the elevator change assessment index into the comprehensive data analysis model, and calculate the comprehensive fall assessment index, which is specifically expressed as:

[0038]

[0039] η irepresents the comprehensive fall assessment index of passengers in the elevator monitoring area at the i-th sub-time, y 1i represents the passenger body change assessment index of the elevator in the monitoring area at the i-th sub-time, y 2i represents the elevator change assessment index of the elevator in the i-th sub-time monitoring area, Δy2 represents the allowable elevator change assessment value difference under normal circumstances, γ1 and γ2 represent the influence coefficients of the human body change assessment index and the elevator change assessment index on the comprehensive fall assessment index, respectively.

[0040] Preferably, the comprehensive fall assessment index warning value is marked as η w , when η i <η w When η , it means that there is no passenger falling in the monitoring area of ​​the ith sub-time, the elevator is in normal operation, and sends "0" to the human-computer interaction module; when η i >η w When , it means that a passenger falls in the elevator monitoring area at the i-th sub-time, and a "1" is sent to the human-computer interaction module.

[0041] Technical effects and advantages of the present invention:

[0042] 1. The present invention collects data on changes caused by a single person falling in the elevator through a fall data collection module, and judges whether a passenger has fallen in the elevator from two dimensions: human body change data and elevator change data, so as to more comprehensively and objectively reflect the situation inside the elevator and provide effective data support for subsequent analysis and judgment;

[0043] 2. The present invention performs a series of processing and analysis on the collected data through the data preprocessing module and the data analysis module, and calculates the comprehensive fall assessment index through the comprehensive data analysis module. By comparing it with the warning value of the comprehensive fall assessment index established by the judgment module, it is determined whether there is a passenger falling in the elevator, so that the situation in the elevator is clearly displayed, and an alarm message is sent to relevant staff through the human-computer interaction module, so that relevant measures can be taken in time to deal with emergency situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a schematic diagram of the overall structure of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] As attached Figure 1 An elevator fall warning system based on image recognition technology is shown, comprising a monitoring area division module, a fall data acquisition module, a data preprocessing module, a data analysis module, a comprehensive data analysis module, a judgment module and a human-computer interaction module.

[0047] The output end of the monitoring area division module is connected to the input end of the fall data acquisition module, the output end of the fall data acquisition module is connected to the input end of the data preprocessing module, the output end of the data preprocessing module is connected to the input end of the data analysis module, the output end of the data analysis module is connected to the input end of the comprehensive data analysis module, the output end of the comprehensive data analysis module is connected to the input end of the judgment module, and the output end of the judgment module is connected to the input end of the human-computer interaction module.

[0048] The monitoring area division module is used to determine a single sub-time monitoring area, and divides the time from the moment a person enters the elevator to the moment he gets off the elevator into a single sub-time monitoring area according to a time length of 1 second, and marks them as 1, 2, ..., i, ..., n in sequence, and divides the bottom of the elevator into single sub-area monitoring areas in an equal-area division manner, and marks them as 1, 2, ..., j, ..., k in sequence.

[0049] The fall data collection module is used to collect data on changes caused by a single human fall in an elevator, including a human change data collection unit and an elevator change data collection unit, and transmits the collected data to a data preprocessing module.

[0050] The human body change data acquisition unit is used to collect body position change parameters and body angle change parameters, and the body position change parameters include the instantaneous height difference of the head position, the instantaneous height difference of the shoulder position, the instantaneous height difference of the knee position, and the aspect ratio of the human body, which are marked as H h , H s , H k and R a , the body angle change parameters include the human body pitch angle, human body roll angle and human body yaw angle, which are marked as θ p ,θ r and θ y .

[0051] What needs to be specifically explained in this embodiment is that first, the camera in the elevator is used to monitor and collect images of passengers in the elevator in real time, and the collected images are denoised to improve the image quality. Next, the images are adjusted to a consistent size and grayscaled. The edge detection, corner point extraction and texture analysis methods are used to extract the characteristic information of the human body from the preprocessed images. The trained human body detection model is used to perform human body recognition on the images to obtain the position of the human body, and based on this, the instantaneous height difference of the head position, the instantaneous height difference of the shoulder position, the instantaneous height difference of the knee position and the aspect ratio of the human body are calculated.

[0052] It should be specifically explained in this embodiment that the pitch angle refers to the rotation angle around the longitudinal axis of the human body, the roll angle refers to the rotation angle around the transverse axis of the body, and the yaw angle refers to the rotation angle of the human body or head around the axis perpendicular to the ground and pointing to the left and right sides of the body.

[0053] The elevator change data acquisition unit is used to collect elevator force change parameters and elevator operation state change parameters. The elevator force change parameters include the pressure on the elevator, marked as F, and the elevator operation state change parameters include the overall kinetic energy value of the elevator, marked as E K .

[0054] In this embodiment, it is necessary to specifically explain that the elevator dynamometer is used to monitor the change of gravity of the object in the process of elevator operation in real time; the instantaneous kinetic energy device is used to monitor the total kinetic energy value E of the elevator in real time. K , use a radar speed meter to measure the real-time speed v of the elevator during movement, and measure the mass of the elevator car, including the sum of the mass of the passengers and cargo in the elevator m 总 , calculate the total kinetic energy value E of the elevator K =(m 总 ×v 2 ) / 2.

[0055] The data preprocessing module includes a human body change data preprocessing unit and an elevator change data preprocessing unit, which are used to preprocess and analyze the human body change data and elevator change data collected by the fall data collection module, and transmit the results to the data analysis module.

[0056] The human body change data preprocessing unit is used to process the body position change parameters and body angle change parameters collected by the fall data collection module, and calculate the body position change evaluation value and the body angle change evaluation value. The body position change evaluation value is specifically expressed as:

[0057]

[0058] y Li represents the estimated value of the body position change of a single person in the elevator in the monitoring area at the i-th sub-time, H hiIt represents the instantaneous height difference of the head position of a single person in the elevator in the monitoring area at the ith sub-time, H si It represents the instantaneous height difference of the shoulder position of a single person in the elevator in the monitoring area at the ith sub-time, H ki R represents the instantaneous height difference of the knee position of a single person in the elevator in the monitoring area at the ith sub-time. ai represents the aspect ratio of a single person in the elevator in the i-th sub-time monitoring area, δ1, δ2, δ3 and δ4 represent the influence coefficients of the instantaneous height difference of the head position, the instantaneous height difference of the shoulder position, the instantaneous height difference of the knee position and the aspect ratio of the human body on the body position change evaluation value respectively; the body angle change evaluation value is specifically expressed as:

[0059]

[0060] y Ai represents the body angle change evaluation value of a single person in the elevator in the i-th sub-time monitoring area, θ pi represents the human body pitch angle of a single person in the elevator in the monitoring area of ​​the i-th sub-time, θ ri represents the human body roll angle of a single person in the elevator in the i-th sub-time monitoring area, θ yi represents the yaw angle of a single person in the elevator in the i-th sub-time monitoring area, δ5, δ6 and δ7 respectively represent the influence coefficients of the human pitch angle, human roll angle and human yaw angle on the body angle change evaluation value.

[0061] The elevator change data preprocessing unit is used to process the elevator force change parameters and the elevator operation state change parameters collected by the fall data collection module, and calculate the elevator force change evaluation value and the elevator operation state change evaluation value. The elevator force change evaluation value is specifically expressed as:

[0062]

[0063] y 压i represents the elevator force change evaluation value in the monitoring area at the ith sub-time, F ij F represents the pressure on the elevator floor in the jth sub-area monitoring area detected by the elevator in the i-th sub-time monitoring area. (i-1)j It indicates the pressure of the elevator floor in the jth sub-area monitoring area detected by the elevator in the i-1th sub-time monitoring area; the evaluation value of the elevator kinetic energy change is specifically expressed as:

[0064]

[0065] y 动i represents the elevator kinetic energy change evaluation value in the i-th sub-time monitoring area, E KiIt represents the total kinetic energy value of the elevator detected in the i-th sub-time monitoring area, E K标i It represents the real-time total kinetic energy value of the elevator when there is no passenger falling in the monitoring area of ​​the i-th sub-time and the elevator is operating normally. When the elevator is in an accelerated motion state,

[0066]

[0067] m represents the total mass of the elevator including all objects inside the elevator, F 上i represents the upward force acting on the elevator detected in the i-th sub-time monitoring area, F 下i represents the downward force acting on the elevator detected in the i-th sub-time monitoring area, t i represents the i-th moment of the elevator motion. When the elevator is in a uniform motion state,

[0068]

[0069] t n1 It is the moment when the elevator stops accelerating, F 上n1 The upward force F is the force exerted on the elevator when it stops accelerating. 下n1 It indicates the downward force on the elevator when it stops accelerating.

[0070]

[0071] The data analysis module includes a human body change data analysis unit and an elevator change data analysis unit, which are used to process the body position change evaluation value, body angle change evaluation value, elevator force change evaluation value and elevator kinetic energy change evaluation value obtained by the data preprocessing module, and pass the results to the comprehensive data analysis module.

[0072] The human body change data analysis unit is used to establish a human body change data analysis model, import the body position change evaluation value and the body angle change evaluation value into the human body change data analysis model, and calculate the human body change evaluation index, which is specifically expressed as:

[0073]

[0074] y 1i represents the passenger body change assessment index of the elevator in the monitoring area at the i-th sub-time, y Li represents the estimated value of the body position change of a single person in the monitoring area of ​​the elevator at the i-th sub-time, y Ai represents the body angle change evaluation value of a single person in the elevator monitoring area at the i-th sub-time, Δy L Denotes the estimated value of the body position change of a normal single person without falling, ΔyA represents the body angle change assessment value of a normal single human body when no one falls, α1 and α2 respectively represent the influence coefficients of the body position change assessment value and the body angle change assessment value on the human body change assessment index.

[0075] The elevator change data analysis unit is used to establish an elevator change data analysis model, import the elevator force change evaluation value and the elevator kinetic energy change evaluation value into the elevator change data analysis model, and calculate the elevator change evaluation index, which is specifically expressed as:

[0076]

[0077] y 2i represents the elevator change evaluation index in the i-th sub-time monitoring area, y 压i represents the elevator force change evaluation value in the monitoring area at the ith sub-time, y 动i represents the elevator kinetic energy change evaluation value in the i-th sub-time monitoring area, Δy 压 It represents the normal force change assessment value of the elevator when no one falls. β1 and β2 respectively represent the influence coefficients of the elevator force change assessment value and the elevator kinetic energy change assessment value on the elevator change assessment index.

[0078] The comprehensive data analysis module includes a comprehensive data analysis unit, which is used to comprehensively process and analyze the human body change assessment index and the elevator change assessment index obtained by the data analysis module, and transmit the processing results to the judgment module.

[0079] The comprehensive data analysis unit is used to establish a comprehensive data analysis model, import the human body change assessment index and the elevator change assessment index into the comprehensive data analysis model, and calculate the comprehensive fall assessment index, which is specifically expressed as:

[0080]

[0081] η i represents the comprehensive fall assessment index of passengers in the elevator monitoring area at the i-th sub-time, y 1i represents the passenger body change assessment index of the elevator in the monitoring area at the i-th sub-time, y 2i represents the elevator change assessment index of the elevator in the i-th sub-time monitoring area, Δy2 represents the allowable elevator change assessment value difference under normal circumstances, γ1 and γ2 represent the influence coefficients of the human body change assessment index and the elevator change assessment index on the comprehensive fall assessment index, respectively.

[0082] The judgment module is used to establish a comprehensive fall assessment index warning value, and judge whether there is a passenger fall in the elevator by comparing the calculated comprehensive fall assessment index with the comprehensive fall assessment index warning value, and pass the judgment result to the human-computer interaction module.

[0083] The comprehensive fall assessment index warning value is marked as η w , when η i <η w When η , it means that there is no passenger falling in the monitoring area of ​​the ith sub-time, the elevator is in normal operation, and sends "0" to the human-computer interaction module; when η i >η w When , it means that a passenger falls in the elevator monitoring area at the i-th sub-time, and a "1" is sent to the human-computer interaction module.

[0084] The human-computer interaction module is used to send alarm information to the elevator control center according to the information transmitted by the judgment module, and inform relevant staff that there is a passenger in the elevator.

[0085] What needs to be specifically explained in this embodiment is that the human-computer interaction module needs to send information on whether to alarm to the elevator control center based on the data transmitted by the judgment module. When the judgment module sends "0", it means that the elevator is in normal operation, and the elevator fall warning system continues to monitor the situation in the elevator. When the judgment module sends "1", it means that a passenger has fallen in the elevator, and an alarm signal is immediately sent to the elevator control center to remind relevant staff to pay attention to the situation in the elevator so that relevant measures can be taken in time to deal with emergencies.

[0086] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0087] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An elevator fall warning system based on image recognition technology, characterized in that: include: Monitoring area division module: used to determine a single sub-time monitoring area, and divide the time from the moment a person enters the elevator to the moment he gets off the elevator into a single sub-time monitoring area according to a time length of 1 second, and mark them as 1, 2, ..., i, ..., n in sequence, and divide the bottom of the elevator into a single sub-area monitoring area in an equal area division manner, and mark them as 1, 2, ..., j, ..., k in sequence; Fall data collection module: used to collect data on changes caused by a single person falling in the elevator, including a human change data collection unit and an elevator change data collection unit, and pass the collected data to the data preprocessing module; The human body change data acquisition unit is used to collect body position change parameters and body angle change parameters, and the body position change parameters include the instantaneous height difference of the head position, the instantaneous height difference of the shoulder position, the instantaneous height difference of the knee position, and the aspect ratio of the human body, which are marked as H h , H s , H k and R a , the body angle change parameters include the human body pitch angle, human body roll angle and human body yaw angle, which are marked as θp, θ r and θ y ; The elevator change data acquisition unit is used to collect elevator force change parameters and elevator operation state change parameters. The elevator force change parameters include the pressure on the elevator, marked as F, and the elevator operation state change parameters include the overall kinetic energy value of the elevator, marked as E K ; Data preprocessing module: including a human body change data preprocessing unit and an elevator change data preprocessing unit, used to preprocess and analyze the human body change data and elevator change data collected by the fall data collection module, and pass the results to the data analysis module; The human body change data preprocessing unit is used to process the body position change parameters and body angle change parameters collected by the fall data collection module, and calculate the body position change evaluation value and the body angle change evaluation value. The body position change evaluation value is specifically expressed as: y Li represents the estimated value of the body position change of a single person in the elevator in the monitoring area at the i-th sub-time, H hi It represents the instantaneous height difference of the head position of a single person in the elevator in the monitoring area at the ith sub-time, H si It represents the instantaneous height difference of the shoulder position of a single person in the elevator in the monitoring area at the ith sub-time, H ki R represents the instantaneous height difference of the knee position of a single person in the elevator in the monitoring area at the ith sub-time. ai represents the aspect ratio of a single person in the elevator in the i-th sub-time monitoring area, δ1, δ2, δ3 and δ4 represent the influence coefficients of the instantaneous height difference of the head position, the instantaneous height difference of the shoulder position, the instantaneous height difference of the knee position and the aspect ratio of the human body on the body position change evaluation value respectively; the body angle change evaluation value is specifically expressed as: y Ai represents the body angle change evaluation value of a single person in the elevator in the i-th sub-time monitoring area, θ pi represents the human body pitch angle of a single person in the elevator in the monitoring area of ​​the i-th sub-time, θ ri represents the human body roll angle of a single person in the elevator in the i-th sub-time monitoring area, θ yi represents the yaw angle of a single person in the elevator in the i-th sub-time monitoring area, δ5, δ6 and δ7 represent the influence coefficients of the human body pitch angle, human body roll angle and human body yaw angle on the body angle change evaluation value respectively; The elevator change data preprocessing unit is used to process the elevator force change parameters and the elevator operation state change parameters collected by the fall data collection module, and calculate the elevator force change evaluation value and the elevator operation state change evaluation value. The elevator force change evaluation value is specifically expressed as: y 压i represents the elevator force change evaluation value in the monitoring area at the ith sub-time, F ij F represents the pressure on the elevator floor in the jth sub-area monitoring area detected by the elevator in the i-th sub-time monitoring area. (i-1)j It indicates the pressure of the elevator floor in the jth sub-area monitoring area detected by the elevator in the i-1th sub-time monitoring area; the evaluation value of the elevator kinetic energy change is specifically expressed as: y 动i It represents the evaluation value of the elevator kinetic energy change in the monitoring area of ​​the ith sub-time, E Ki It represents the total kinetic energy value of the elevator detected in the i-th sub-time monitoring area, E K标i It represents the real-time total kinetic energy value of the elevator when there is no passenger falling in the monitoring area of ​​the i-th sub-time and the elevator is operating normally. When the elevator is in an accelerated motion state, m represents the total mass of the elevator including all objects inside the elevator, F 上i represents the upward force acting on the elevator detected in the i-th sub-time monitoring area, F 下i represents the downward force acting on the elevator detected in the i-th sub-time monitoring area, t i represents the i-th moment of the elevator motion. When the elevator is in a uniform motion state, t n1 It is the moment when the elevator stops accelerating, F 上n1 The upward force F is the force exerted on the elevator when it stops accelerating. 下n1 It indicates the downward force on the elevator when it stops accelerating. Data analysis module: including a human body change data analysis unit and an elevator change data analysis unit, which are used to process the body position change evaluation value, body angle change evaluation value, elevator force change evaluation value and elevator kinetic energy change evaluation value obtained by the data preprocessing module, and transmit the results to the comprehensive data analysis module; The human body change data analysis unit is used to establish a human body change data analysis model, import the body position change evaluation value and the body angle change evaluation value into the human body change data analysis model, and calculate the human body change evaluation index, which is specifically expressed as: y 1i represents the passenger body change assessment index of the elevator in the monitoring area at the i-th sub-time, y Li represents the estimated value of the body position change of a single person in the monitoring area of ​​the elevator at the i-th sub-time, y Ai represents the body angle change evaluation value of a single person in the elevator monitoring area at the i-th sub-time, Δy L Denotes the estimated value of the body position change of a normal single person without falling, Δy A represents the body angle change assessment value of a normal single human body when no one falls, α1 and α2 represent the influence coefficients of the body position change assessment value and the body angle change assessment value on the human body change assessment index respectively; The elevator change data analysis unit is used to establish an elevator change data analysis model, import the elevator force change evaluation value and the elevator kinetic energy change evaluation value into the elevator change data analysis model, and calculate the elevator change evaluation index, which is specifically expressed as: y 2i represents the elevator change evaluation index in the i-th sub-time monitoring area, y 压i represents the elevator force change evaluation value in the monitoring area at the ith sub-time, y 动i represents the elevator kinetic energy change evaluation value in the i-th sub-time monitoring area, Δy 压 represents the normal elevator force change assessment value when no one falls, β1 and β2 represent the influence coefficients of the elevator force change assessment value and the elevator kinetic energy change assessment value on the elevator change assessment index respectively; Comprehensive data analysis module: including a comprehensive data analysis unit, used to comprehensively process and analyze the human body change assessment index and the elevator change assessment index obtained by the data analysis module, and transmit the processing results to the judgment module; The comprehensive data analysis unit is used to establish a comprehensive data analysis model, import the human body change assessment index and the elevator change assessment index into the comprehensive data analysis model, and calculate the comprehensive fall assessment index, which is specifically expressed as: η i represents the comprehensive fall assessment index of passengers in the elevator monitoring area at the i-th sub-time, y 1i represents the passenger body change assessment index of the elevator in the monitoring area at the i-th sub-time, y 2i represents the elevator change assessment index of the elevator in the i-th sub-time monitoring area, Δy2 represents the difference of the elevator change assessment value allowed under normal circumstances, γ1 and γ2 represent the influence coefficients of the human body change assessment index and the elevator change assessment index on the comprehensive fall assessment index respectively; Judgment module: used to establish a comprehensive fall assessment index warning value, and to judge whether there is a passenger fall in the elevator by comparing the calculated comprehensive fall assessment index with the comprehensive fall assessment index warning value, and to pass the judgment result to the human-computer interaction module; Human-computer interaction module: used to send alarm information to the elevator control center based on the information transmitted by the judgment module, and notify relevant staff of the passenger's condition in the elevator.

2. The elevator fall warning system based on image recognition technology according to claim 1 is characterized in that: The comprehensive fall assessment index warning value is marked as η w , when η i <η w When η, it means that there is no passenger falling in the elevator monitoring area of ​​the i-th sub-time, the elevator is in normal operation, and sends "0" to the human-computer interaction module; when η i >η w When , it means that a passenger falls in the elevator monitoring area of ​​the i-th sub-time, and sends "1" to the human-computer interaction module.

Images