Elevator electric vehicle identification method and system based on anomaly detection

Abstract

The invention relates to the technical field of elevator electric vehicle recognition, in particular to an elevator electric vehicle recognition method and system based on anomaly detection, and the method comprises the following steps: extracting the edge contour of an object in a picture frame by frame based on the picture data of an elevator camera and light curtain infrared signal data; the method comprises the following steps: separating an object from a background region by edge detection, recording a width-to-height ratio of an object edge, calculating a change characteristic of an edge form on a time axis, and generating an object edge form data set; by dynamically extracting the edge contour of an object, combining with light curtain signal data, analyzing the width-to-height ratio and the motion trail of the object, and combining with comprehensive analysis of shielding time, light curtain signal frequency and reflection intensity, the accuracy of shielding behavior recording is improved, and accurate recording of abnormal behaviors of the electric vehicle is realized by utilizing correlation verification of load change and trail data. And elevator locking, voice warning and linkage alarm mechanisms are triggered through real-time feedback, and comprehensive guarantee is provided for safe operation of the elevator.

Description

Technical Field

[0001] The present invention relates to the technical field of elevator electric vehicle identification, and in particular to an elevator electric vehicle identification method and system based on abnormality detection. Background Art

[0002] The field of elevator electric vehicle identification technology includes monitoring of elevator operation status and detection and analysis of electric vehicle entry and exit behavior. The core content of this technical field is to identify and process abnormal behavior in the elevator based on elevator operation data, video surveillance data and other sensor collection information. The overall elevator electric vehicle identification technology involves many contents, including elevator status information collection and transmission, elevator usage behavior analysis, object identification and classification, elevator safety analysis and detection, etc., and provides technical support for elevator safety management through information collection, analysis and feedback mechanism.

[0003] Among them, the elevator electric vehicle identification method based on anomaly detection refers to the identification and analysis of the behavior of electric vehicles entering the elevator by building a model and method based on anomaly detection. In view of the abnormal situations that may exist when electric vehicles enter and exit the elevator, the data collected by the elevator sensor and the image information obtained by video surveillance are combined with specific signal processing methods and classification algorithms to realize the identification of electric vehicle characteristics. Specifically, it includes steps such as behavior detection based on the operating status of the elevator, extraction of electric vehicle appearance features through image analysis, and classification and judgment based on multimodal data fusion, forming a technical process for electric vehicle identification.

[0004] The existing technology usually relies on a single data source for identifying electric vehicles entering elevators, such as simple feature extraction and judgment through elevator operation status or video surveillance data, lacking deep fusion and dynamic analysis of multi-dimensional data, resulting in low recognition accuracy. The analysis of object morphological features is limited to static or low-dimensional parameters, such as a single aspect ratio or image contour, and fails to combine dynamic behavior data with light curtain signal changes for in-depth judgment, which is prone to misjudgment in complex scenarios. For the recording and evaluation of occlusion behavior, it mostly relies on simple field of view occlusion information, lacks comprehensive analysis of occlusion duration, frequency and its correlation with light curtain signals, and cannot effectively establish a complete abnormal behavior chain, resulting in some abnormal situations being difficult to accurately capture. In addition, the existing technology lacks the correlation verification between load changes and object behavior, and simply relies on a certain feature to identify abnormal behavior, which may lead to misjudgment of events in multi-target scenes. At the same time, in the handling process after the abnormal event occurs, the existing technology has a lag in triggering and responding to the linkage mechanism, and the alarm and control fail to form efficient coordination, which limits the overall safety of elevator operation management, directly affects the comprehensiveness and timeliness of abnormal behavior identification and handling of electric vehicles in elevators, and there are major safety hazards. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an elevator electric vehicle identification method and system based on abnormality detection.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions: A method for identifying an elevator electric vehicle based on abnormality detection comprises the following steps: S1: Based on the image data of the elevator camera and the infrared signal data of the light curtain, the edge contour of the object during the door opening is extracted frame by frame, the width-to-height ratio of the object is analyzed, the contour closure parameters are calculated, the width of the light curtain crossing path and the reflection intensity data are associated, the object morphological characteristics and signal path are identified and processed, and the object geometric characteristics determination result is generated; S2: Based on the determination result of the geometric characteristics of the object, the width-to-height ratio and the range of change of the continuous motion trajectory of the target object are analyzed, the object morphological characteristics and position offset data are combined, the light curtain signal crossing speed and reflection intensity fluctuation are counted, the geometric morphological data and speed fluctuation are compared, and the target object characteristic matching result is generated; S3: Based on the target object characteristic matching result, extract the elevator camera field of view occlusion time period and change area, count the light curtain triggering frequency and reflection change during the occlusion time, analyze the occlusion duration and frequency, calculate the occlusion duration and frequency overlap rate, combine the occlusion data for comparative analysis, and generate abnormal occlusion behavior chain record results; S4: Based on the abnormal occlusion behavior chain record results, analyze the load change before and after the door is opened, verify the load change value and the object trajectory data extracted by the light curtain, select the event chain whose trajectory behavior is consistent with the load change, analyze the behavior pattern and occlusion characteristics in the event chain, and generate an abnormal behavior record of the electric vehicle; S5: Based on the abnormal behavior record of the electric vehicle, the recorded data is transmitted to the elevator control mechanism, the elevator door is triggered to lock and a voice warning is issued, the data is uploaded to the remote monitoring mechanism, the building alarm mechanism is linked, and the elevator abnormal status event response result is generated.

[0007] As a further solution of the present invention, the object geometric characteristic determination result includes object edge contour parameters, aspect ratio analysis results, contour closure parameters, crossing path width characteristics, and reflection intensity characteristics; the target object characteristic matching result includes object aspect ratio characteristics, motion trajectory range characteristics, position offset data, crossing speed characteristics, and reflection intensity fluctuation characteristics; the abnormal occlusion behavior chain record result includes occlusion time period data, occlusion area change characteristics, light curtain signal trigger frequency statistics, reflection change accumulation characteristics, and occlusion duration frequency overlap rate; the electric vehicle abnormal behavior record includes load change characteristics, trajectory behavior chain, event chain pattern characteristics, and occlusion characteristic analysis results; the elevator abnormal state event response result includes door lock trigger signal, voice warning instruction, remote monitoring upload data, and building alarm linkage mechanism.

[0008] As a further solution of the present invention, based on the image data of the elevator camera and the infrared signal data of the light curtain, the edge contour of the object during the door opening is extracted frame by frame, the width-to-height ratio of the object is analyzed, the contour closure parameter is calculated, the width of the light curtain crossing path and the reflection intensity data are associated, and the object morphological characteristics and signal path are identified and processed. The specific steps of generating the object geometric characteristic determination result are as follows: S101: Based on the image data of the elevator camera and the infrared signal data of the light curtain, the edge contours of the objects in the image during the door opening are extracted frame by frame, the object and the background area are separated by edge detection, the width and height ratio of the object edge is recorded, and the change characteristics of the edge morphology on the time axis are calculated to generate the object edge morphology data set; S102: Based on the object edge morphology data set, calculate the edge data closure parameter, compare the geometric positions of the edge start point and the edge end point, determine the contour closure, analyze the spatial continuity of the closure change between frames, perform curve fitting on the edge closure degree, record key feature points, and generate edge contour closure feature data; S103: Based on the edge contour closure feature data, combined with the crossing path width and reflection intensity information of the light curtain infrared signal data, the spatial correlation between the signal path and the contour closure parameters is analyzed, and the object feature mapping relationship is constructed through a matrix of multi-dimensional characteristic data to generate the object geometric characteristic analysis results.

[0009] As a further solution of the present invention, the edge closure deviation value calculation formula is specifically: ; in, represents the closure deviation value, Representative The horizontal coordinate of the frame edge starting point, Representative The vertical coordinate of the starting point of the frame edge, Representative The horizontal coordinate of the end point of the frame edge, Representative The vertical coordinate of the end point of the frame edge, Representative The area of ​​the frame enclosed region, Represents the total number of frames. is the circumference constant.

[0010] As a further solution of the present invention, based on the determination result of the geometric characteristics of the object, the specific steps of analyzing the width-to-height ratio of the target object and the range of change of the continuous motion trajectory, combining the object morphological characteristics and position offset data, counting the light curtain signal crossing speed and reflection intensity fluctuation, comparing the geometric morphological data and speed fluctuation, and generating the target object characteristic matching result are as follows: S201: extracting the range of the target object's aspect ratio change based on the object geometric characteristic determination result, grouping the target object according to the width and height data between frames, calculating the ratio change of each group, statistically analyzing the frequency distribution of the ratio change interval, extracting the key points of the continuous change trend on the time axis, and generating the target object's aspect ratio change data; S202: Based on the target object aspect ratio change data, combined with the motion trajectory and position offset data, analyzing the change amplitude of each frame position in the trajectory, calculating the cumulative displacement in the change direction, screening key points with abnormal offset characteristics for the trajectory curve, and generating the target object trajectory and position feature data; S203: Based on the target object trajectory and position feature data, combined with the crossing speed and reflection intensity fluctuation range of the light curtain signal, the time nodes of the signal parameters and the trajectory change characteristics are compared, and the parameter correlation between the corresponding signal data and the geometric characteristics is statistically analyzed to generate a target object characteristic matching result.

[0011] As a further solution of the present invention, based on the target object characteristic matching result, the elevator camera field of view obstruction time period and change area are extracted, the light curtain triggering frequency and reflection change during the obstruction time are counted, the obstruction duration and frequency are analyzed, the obstruction duration and frequency overlap rate are calculated, and the obstruction data are combined for comparative analysis to generate the abnormal obstruction behavior chain record results. The specific steps are as follows: S301: Based on the target object characteristic matching result, extract the occlusion time period and change area in the elevator camera field of view, detect the boundary point position of the occlusion area frame by frame, record the area change value of the occlusion area on the time axis, count the trend of the occlusion area change and the boundary stability, and generate occlusion time and area change data; S302: Based on the shading time and area change data, extract the frequency and reflection intensity of the light curtain trigger signal within the shading time period, synchronously analyze the light curtain signal change amplitude and the shading time in the time interval, calculate the overlap ratio between the two, select the characteristic interval matching the shading and the signal, and generate the shading time and light curtain trigger frequency relationship data; S303: Based on the relationship data between the occlusion time and the light curtain triggering frequency, extract the change in the occlusion area and the light curtain signal triggering parameters, perform segmented comparison on the signal and occlusion data, record the correlation between the signal anomaly and the regional fluctuation at the time node, extract and classify the abnormal related behaviors, and generate the abnormal occlusion behavior chain record results.

[0012] As a further solution of the present invention, the calculation formula of the overlap intensity value of the occlusion and light curtain signal is specifically: ; in, Represents the overlapping intensity value of the occlusion and light curtain signals. Representative The trigger frequency change of the light curtain signal within a period of time, Representative The duration of a period of time, Representative The area value of the segment occlusion region, is the circumference constant, Represents the total number of occlusion time periods, Represents the total number of time periods for signal triggering. Representative The time value of the segment signal trigger.

[0013] As a further solution of the present invention, based on the abnormal occlusion behavior chain record results, the load change before and after the door is opened is analyzed, the load change value and the object trajectory data extracted by the light curtain are verified, the event chain whose trajectory behavior is consistent with the load change is screened, and the behavior pattern and occlusion characteristics in the event chain are analyzed. The specific steps of generating the abnormal behavior record of the electric vehicle are as follows: S401: Based on the abnormal occlusion behavior chain recording results, extract the elevator load change data before and after the door is opened, statistically analyze the load change data of each frame on the time axis, record the load change value of each frame, calculate the load change trend, and mark the time point of significant change to generate load change and time series data; S402: Based on the load change and time series data, verify the load change value and the object trajectory data extracted by the light curtain, extract the synchronization of the load change event and the trajectory behavior in the time axis, filter and match the event chain according to the change range, and count the event correlation characteristics to generate load and trajectory event chain data; S403: Based on the load and trajectory event chain data, the corresponding relationship between the continuity of the behavior pattern in the event chain and the occlusion characteristics is analyzed, the trajectory change and occlusion behavior association parameters are calculated, the abnormal behavior characteristics are screened and sorted, and the abnormal behavior record of the electric vehicle is generated.

[0014] As a further solution of the present invention, based on the abnormal behavior record of the electric vehicle, the recorded data is transmitted to the elevator control mechanism, the elevator door is locked and a voice warning is issued, the data is uploaded to the remote monitoring mechanism, the building alarm mechanism is linked, and the specific steps of generating the elevator abnormal state event response result are: S501: Based on the abnormal behavior record of the electric vehicle, the recorded data is transmitted to the elevator control mechanism, the abnormal behavior feature data is analyzed and the corresponding control parameters are obtained, the locking function of the elevator door is started, the voice warning device is triggered and the response status is recorded, and the elevator locking and voice warning response data are generated; S502: Based on the elevator locking and voice warning response data, upload abnormal behavior records and elevator operation status data to the remote monitoring mechanism, establish a data transmission network interface and monitor data transmission integrity, record feedback status information of the remote monitoring mechanism, and generate remote monitoring abnormal behavior upload results; S503: Based on the remote monitoring abnormal behavior upload result, the building alarm mechanism is linked, the abnormal behavior data is analyzed to trigger the alarm condition and synchronize the control parameters, the alarm device in the building is started and the alarm response time and execution status are recorded, and the elevator abnormal status event response result is generated.

[0015] Based on the same inventive concept, an elevator electric vehicle identification system based on abnormality detection is also proposed, comprising: The object edge extraction module extracts the edge contour of the object during the door opening frame by frame based on the image data of the elevator camera and the infrared signal data of the light curtain, calculates the contour closure parameters, associates the width of the light curtain crossing path with the reflection intensity data, and generates the object geometric characteristic determination result; The target characteristic analysis module analyzes the width-to-height ratio and the range of change of the continuous motion trajectory of the target object based on the determination result of the geometric characteristics of the object, counts the crossing speed of the light curtain signal and the fluctuation of the reflection intensity, compares the geometric shape data with the speed fluctuation, and generates the target object characteristic matching result; The abnormal occlusion analysis module extracts the occlusion time period and change area of ​​the elevator camera's field of view based on the target object characteristic matching result, counts the light curtain triggering frequency and reflection change during the occlusion time, calculates the occlusion duration and frequency overlap rate, and compares and analyzes the occlusion data to generate abnormal occlusion behavior chain record results; The load behavior verification module analyzes the load change before and after the door is opened based on the abnormal occlusion behavior chain record results, verifies the load change value and the object trajectory data extracted by the light curtain, selects the event chain with consistent trajectory behavior and load change, and generates an abnormal behavior record of the electric vehicle; The abnormal event response module transmits the recorded data to the elevator control mechanism based on the abnormal behavior record of the electric vehicle, triggers the elevator door to lock and issue a voice warning, links the building alarm mechanism, and generates an elevator abnormal state event response result.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by dynamically extracting the edge contour of the object and combining it with the light curtain signal data, analyzing the object's width-to-height ratio and movement trajectory, and combining the comprehensive analysis of the occlusion time, light curtain signal frequency and reflection intensity, the accuracy of the occlusion behavior record is improved, and the correlation verification between load changes and trajectory data is used to achieve accurate recording of abnormal behavior of electric vehicles, and real-time feedback is used to trigger the elevator locking, voice warning and linkage alarm mechanism, providing comprehensive protection for the safe operation of the elevator. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 It is a schematic diagram of the steps of the present invention.

[0019] Figure 2 It is a flow chart of the steps of S1 of the present invention.

[0020] Figure 3 This is a flow chart of the steps of S2 of the present invention.

[0021] Figure 4 This is a flow chart of the steps of S3 of the present invention.

[0022] Figure 5 This is a flow chart of the steps of S4 of the present invention.

[0023] Figure 6 This is a flow chart of the steps of S5 of the present invention.

[0024] Figure 7 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0025] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0026] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0027] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0028] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0029] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0030] See also Figure 1 , an elevator electric vehicle identification method based on abnormality detection, comprising the following steps: S1: Based on the image data of the elevator camera and the infrared signal data of the light curtain, the edge contour of the object during the door opening is extracted frame by frame, the width-to-height ratio of the object is analyzed, the contour closure parameters are calculated, the width of the light curtain crossing path and the reflection intensity data are associated, the object morphological characteristics and signal path are identified and processed, and the object geometric characteristics determination result is generated; S2: Based on the results of the object's geometric characteristics, the target object's width-to-height ratio and the range of change in the continuous motion trajectory are analyzed. The object's morphological characteristics and position offset data are combined to count the light curtain signal's crossing speed and reflection intensity fluctuations. The geometric morphological data and speed fluctuations are compared to generate the target object's characteristic matching results. S3: Based on the target object feature matching results, extract the elevator camera field of view occlusion time period and change area, count the light curtain triggering frequency and reflection changes during the occlusion time, analyze the occlusion duration and frequency, calculate the occlusion duration and frequency overlap rate, combine the occlusion data for comparative analysis, and generate abnormal occlusion behavior chain record results; S4: Based on the abnormal occlusion behavior chain record results, analyze the load changes before and after the door is opened, verify the load change value and the object trajectory data extracted by the light curtain, select the event chain with consistent trajectory behavior and load change, analyze the behavior pattern and occlusion characteristics in the event chain, and generate abnormal behavior records of electric vehicles; S5: Based on the abnormal behavior records of electric vehicles, the recorded data is transmitted to the elevator control mechanism, which triggers the elevator door to lock and issue a voice warning. The data is uploaded to the remote monitoring mechanism, linked to the building alarm mechanism, and the elevator abnormal status event response result is generated.

[0031] The results of object geometric characteristic determination include object edge contour parameters, aspect ratio analysis results, contour closure parameters, crossing path width characteristics, and reflection intensity characteristics. The results of target object characteristic matching include object aspect ratio characteristics, motion trajectory range characteristics, position offset data, crossing speed characteristics, and reflection intensity fluctuation characteristics. The results of abnormal occlusion behavior chain recording include occlusion time period data, occlusion area change characteristics, light curtain signal trigger frequency statistics, reflection change accumulation characteristics, and occlusion duration frequency overlap rate. The abnormal behavior records of electric vehicles include load change characteristics, trajectory behavior chains, event chain pattern characteristics, and occlusion characteristic analysis results. The results of elevator abnormal state event response include door lock trigger signals, voice warning commands, remote monitoring upload data, and building alarm linkage mechanisms.

[0032] See also Figure 2 , the specific steps of S1 are: S101: Based on the image data of the elevator camera and the infrared signal data of the light curtain, the edge contours of the objects in the image during the door opening are extracted frame by frame, the object and the background area are separated by edge detection, the width and height ratio of the object edge is recorded, and the change characteristics of the edge morphology on the time axis are calculated to generate the object edge morphology data set; The edge contours of objects in the picture are extracted through intra-frame analysis. First, the gradient edge detection technology is used to calculate the gradient strength and direction of each pixel in the image. The Sobel operator or Canny algorithm is used to complete edge detection, eliminate the noise background and separate the foreground object. Then, the preliminary contour of the object edge is constructed by connecting the edge pixels, and the width and height of the edge contour are measured in pixels. The aspect ratio is calculated and stored. Combined with time series analysis, the change characteristics are obtained by curve fitting of the edge morphology change, and an object edge morphology dataset is generated.

[0033] S102: Based on the object edge morphology data set, calculate the edge data closure parameter, compare the geometric positions of the edge start point and the end point, determine the contour closure, analyze the spatial continuity of the closure change between frames, perform curve fitting on the edge closure degree, record key feature points, and generate edge contour closure feature data; The calculation formula of edge closure deviation value is as follows: ; in, represents the closure deviation value, Representative The horizontal coordinate of the frame edge starting point, Representative The vertical coordinate of the starting point of the frame edge, Representative The horizontal coordinate of the end point of the frame edge, Representative The vertical coordinate of the end point of the frame edge, Representative The area of ​​the frame enclosed region, Represents the total number of frames.

[0034] The parameters involved are as follows: : Closure deviation value, used to evaluate the overall deviation between the object edge closure and the ideal circular closure area.

[0035] : No. The horizontal and vertical coordinates of the starting point of the frame edge are extracted by the edge detection algorithm to determine the starting point of the edge of the object in the video frame. They can be obtained using the pixel coordinate measurement tool, and the measurement accuracy should match the frame resolution.

[0036] : No. The horizontal and vertical coordinates of the end point of the frame edge are used to extract the end point position of the edge of the object in the video frame through the edge detection algorithm.

[0037] : No. The area of ​​the closed region at the edge of the frame is obtained by calculating the closed contour of the edge points within the frame. The area is calculated using pixel measurement, which multiplies the number of pixels in the closed contour area by the area of ​​a single pixel.

[0038] : Total number of frames, used to average the deviation values ​​of all frames. The number of frames is directly calculated from the video length and frame rate.

[0039] : Constant pi, used to calculate the radius of an ideal circle from its area.

[0040] Specific calculation derivation process: Given a video with 5 frames, a total resolution of 1920×1080, and a frame rate of 30 frames per second, the extracted edge start and end coordinates and closed area area data are as follows: the start coordinates of the first frame are (100, 200), the end coordinates are (400, 600), and the closed area area is 50265 pixels; the start coordinates of the second frame are (150, 250), the end coordinates are (420, 590), and the closed area area is 48750 pixels; the start coordinates of the third frame are (120, 220), the end coordinates are (410, 620), and the closed area area is 51500 pixels; the start coordinates of the fourth frame are (130, 210), the end coordinates are (430, 610), and the closed area area is 50500 pixels; the start coordinates of the fifth frame are (140, 230), the end coordinates are (440, 620), the closed area is 49800 pixels; the Euclidean distance between the start point and the end point is calculated in the first frame: ; Ideal circle radius: ; Absolute value of deviation: ; In the second frame, the Euclidean distance between the start point and the end point is calculated: ; Ideal circle radius: ; Absolute value of deviation: ; The third frame calculates the Euclidean distance between the start point and the end point: ; Ideal circle radius: ; Absolute value of deviation: ; The fourth frame calculates the Euclidean distance between the start point and the end point: ; Ideal circle radius: ; Absolute value of deviation: ; In the fifth frame, the Euclidean distance between the start point and the end point is calculated: ; Ideal circle radius: ; Absolute value of deviation: ; Closure deviation value calculation: ; Result description: The closure deviation value is 357.69, indicating that there is a certain geometric deviation between the object edge and the ideal closed contour. This value is used for subsequent feature fitting and key point extraction to further describe the changing characteristics of the edge closure shape.

[0041] S103: Based on the edge contour closure feature data, combined with the crossing path width and reflection intensity information of the light curtain infrared signal data, the spatial correlation between the signal path and the contour closure parameters is analyzed, and the object feature mapping relationship is constructed by matrix through the multi-dimensional characteristic data to generate the object geometric characteristic analysis result; Firstly, the infrared crossing path of the light curtain signal is measured at the pixel level. The time series data of the infrared signal intensity is collected by the sensor. The width of the path is calculated by analyzing the reflection intensity of the optical path. Then, the edge contour closure parameter is associated with the light curtain signal path width in the spatial dimension. By constructing a feature mapping matrix, the infrared signal intensity of each spatial point is mapped to the specific position on the geometric feature. Then, the correlation between the path width and the closure characteristics in the multidimensional matrix in the time series is analyzed, and finally the geometric characteristic analysis results of the object are generated.

[0042] See also Figure 3 , the specific steps of S2 are: S201: based on the result of the object geometric characteristic determination, extract the range of the target object's aspect ratio change, group the frame width and height data, calculate the ratio change of each group, count the frequency distribution of the ratio change interval, extract the key points of the continuous change trend on the time axis, and generate the target object's aspect ratio change data; First, each frame of the image is partitioned and calibrated, and the width and height boundaries are detected. The specific values ​​of width and height are digitized using the pixel measurement method, the aspect ratio of each group of frames is calculated, and the ratio values ​​are divided and counted according to intervals. The frequency distribution of the ratio changes in each interval is statistically analyzed, and then the continuity trend of the ratio change data on the time axis is analyzed. The key points with significant continuous change trends in the frame sequence are extracted, and their specific positions on the time axis are marked, and finally the aspect ratio change data of the target object is generated.

[0043] S202: Based on the target object width-to-height ratio change data, combined with the motion trajectory and position offset data, analyze the change amplitude of each frame position in the trajectory, calculate the cumulative displacement in the change direction, select key points with abnormal offset characteristics for the trajectory curve, and generate the target object trajectory and position feature data; Filter the key points with abnormal deviation characteristics according to the trajectory curve, according to the formula: ; Calculate the change in position of each frame and accumulate the displacement. and Respectively represent The horizontal and vertical coordinates of the object in the frame, represents the cumulative displacement of the trajectory, Indicates the total number of frames.

[0044] The trajectory change amplitude is accumulated by calculating the Euclidean distance of the position coordinates of adjacent frames to characterize the trajectory change trend. In the calculation, the center of gravity of the object in each frame is located, its horizontal and vertical coordinates are extracted, and the distance values ​​between adjacent frames are calculated and accumulated. In an example, assuming that the total number of frames is 5, and the frame sequence coordinates are (10,20), (13,24), (18,30), (22,36), (25,40), the distances between adjacent frames are: Frame 1 to Frame 2: ; Frame 2 to Frame 3: ; After repeated calculations, the cumulative displacement is: ; The result shows that the trajectory of the object has changed significantly. By analyzing the cumulative displacement curve, the key points of abnormal offset characteristics can be marked, and finally the trajectory and position feature data of the target object can be generated.

[0045] S203: Based on the target object trajectory and position feature data, combined with the crossing speed and reflection intensity fluctuation range of the light curtain signal, the time nodes of the signal parameters and the trajectory change characteristics are compared, and the parameter correlation between the corresponding signal data and the geometric characteristics is statistically analyzed to generate the target object characteristic matching result; By calculating the average crossing time of the crossing path and the peak fluctuation of the reflection intensity, the degree of correlation between them and the spatial position characteristics of the trajectory is analyzed, and the dynamic position changes of the trajectory data in the geometric characteristics are mapped using a two-dimensional correlation matrix to finally generate the characteristic matching results of the target object.

[0046] See also Figure 4 , the specific steps of S3 are: S301: Based on the target object feature matching result, extract the occlusion time period and change area in the elevator camera field of view, detect the boundary point position of the occlusion area frame by frame, record the area change value of the occlusion area on the time axis, count the trend of the occlusion area change and the boundary stability, and generate occlusion time and area change data; The outer boundary of the occlusion area is extracted as a set of pixel points using an edge detection algorithm. The area of ​​the minimum circumscribed rectangle of these boundary points is calculated frame by frame as the area value of the occlusion area. The area change of each frame is associated with the time axis to form time series data of the occlusion area. Trend analysis is performed on these data, and the interval distribution of the occlusion area change amplitude is statistically analyzed. The stability of the occlusion boundary points is calculated, and its change range is characterized by the mean and variance. Finally, the occlusion time and area change data are generated.

[0047] S302: Based on the shading time and area change data, the frequency and reflection intensity of the light curtain trigger signal in the shading time period are extracted, the light curtain signal change amplitude and the shading time in the time interval are synchronously analyzed, the overlapping ratio between the two is calculated, the characteristic interval matching the shading and the signal is screened, and the relationship data between the shading time and the light curtain trigger frequency is generated; The calculation formula for the overlapping intensity value of the occlusion and light curtain signal is as follows: ; in, Represents the overlapping intensity value of the occlusion and light curtain signals. Representative The trigger frequency change of the light curtain signal within a period of time, Representative The duration of a period of time, Representative The area value of the segment occlusion region, is the circumference constant, Represents the total number of occlusion time periods, Represents the total number of time periods for signal triggering. Representative The time value of the segment signal trigger.

[0048] The parameters involved are as follows: : The overlap intensity value of the occlusion and light curtain signals, indicating the degree of dynamic overlap between the two.

[0049] : No. The change in the trigger frequency of the light curtain signal within a period of time is calculated by monitoring the number of signal triggers of the light curtain sensor, and the increment or decrement of the trigger frequency is calculated in times per second.

[0050] : No. The duration of a period of time is obtained by recording the time interval of the occlusion, in seconds.

[0051] : No. The area value of the segment occlusion area is calculated by the image edge detection technology to calculate the number of pixels in the occlusion area, combined with the pixel area (assuming that the area of ​​a single pixel is 0.01 square centimeters) for conversion. The unit is square centimeters.

[0052] : Constant pi, used to calculate the equivalent circular radius of the occluded area, the value is 3.14159.

[0053] : Total number of occlusion time periods, indicating the total number of occlusion event segments divided.

[0054] : The total number of time periods triggered by the signal, indicating the total number of time periods of the light curtain signal triggering event.

[0055] : No. The time value of the segment signal trigger is obtained through the time record of the light curtain signal, in seconds.

[0056] Parameter assignment and calculation: The following parameters were obtained from monitoring in a certain scene: the frequency change of the light curtain signal triggering in the first period was 10 times per second, the duration was 5 seconds, and the area of ​​the blocked area was 31416 square pixels; the frequency change of the light curtain signal triggering in the second period was 15 times per second, the duration was 6 seconds, and the area of ​​the blocked area was 45239 square pixels; the frequency change of the light curtain signal triggering in the third period was 8 times per second, the duration was 4 seconds, and the area of ​​the blocked area was 20106 square pixels. The time periods for the light curtain signal triggering were 5 seconds, 6 seconds, and 4 seconds respectively.

[0057] The calculation of the equivalent circular radius of the first segment occlusion calculation is: ; The area adjustment values ​​are: ; The calculation of the equivalent circular radius of the second segment occlusion calculation is: ; The area adjustment values ​​are: ; The calculation of the equivalent circular radius of the third segment occlusion calculation is: ; The area adjustment values ​​are: ; Total occlusion overlap value calculation: ; Total signal time calculation: ; Calculation of overlapping intensity values ​​of occlusion and light curtain signals: ; Result description: The overlap intensity value of the occlusion and light curtain signal is 1224, which indicates the comprehensive correlation degree between the area and time of the occlusion event and the trigger frequency of the light curtain signal in time and space. This value is further used to screen the characteristic interval matching the occlusion and signal, and provide a quantitative basis for generating the relationship data between the occlusion time and the light curtain trigger frequency.

[0058] S303: Based on the data on the relationship between the blocking time and the light curtain triggering frequency, the change in the blocking area and the light curtain signal triggering parameters are extracted, the signal and blocking data are compared in sections, the correlation between the signal anomaly and the regional fluctuation at the time node is recorded, the abnormal related behaviors are extracted and classified, and the abnormal blocking behavior chain record results are generated; The segmented analysis method is used to compare the time series data of the blocked area and the time node data of the light curtain signal segment by segment, and the dynamic change value of the blocked area is associated with the fluctuation range of the light curtain signal trigger amplitude. The associated fluctuation value of the blocked area is recorded at the time node of the abnormal triggering of the light curtain signal, and the associated behaviors are classified. Different fluctuation characteristics are marked as independent behavior chains, and based on the statistical results of the fluctuations, the behavior chains are sorted and classified in chronological order, and finally the abnormal occlusion behavior chain record results are generated.

[0059] See also Figure 5 , the specific steps of S4 are: S401: Based on the abnormal occlusion behavior chain recording results, extract the elevator load change data before and after the door is opened, statistically analyze the load change data of each frame on the time axis, record the load change value of each frame, calculate the load change trend, and mark the time point of significant change to generate load change and time series data; First, the door opening time node is calibrated on the time axis, and the load data recorded by the elevator load sensor frame by frame is collected, and the change value of each frame of load data is extracted. The load difference between adjacent frames is accumulated, and the load change trend is calculated. The frames with a load change amplitude greater than the threshold are marked as significant change time points, and the complete load change data is generated in combination with the time series, finally forming the load change and time series data.

[0060] S402: Based on the load change and time series data, verify the load change value and the object trajectory data extracted by the light curtain, extract the synchronization of the load change event and the trajectory behavior in the time axis, filter and match the event chain according to the change range, and count the event correlation characteristics to generate load and trajectory event chain data; Extract the synchronization of load change events and trajectory behavior according to the formula: ; Calculate the correlation ratio between load change events and trajectory behavior. Indicates Change value of table section load, Indicates the load change time period. Indicates The displacement change value of the segment trajectory behavior, Indicates the correlation ratio between load change and trajectory behavior.

[0061] The correlation between load change and trajectory behavior is obtained by calculating the ratio of load change value to trajectory displacement change value. For each time interval, the load change and the cumulative displacement change of trajectory behavior are counted, compared and the synchronization ratio is calculated. In an example, assuming that the time segment is 3 segments, the load change values ​​are 50, 40, and 60 (unit: kilograms), the corresponding time periods are 2, 3, and 1 (unit: seconds), and the trajectory behavior displacement changes are 10, 15, and 5 (unit: meters), respectively. Then: Cumulative value of load change: ; Track behavior displacement accumulation value: ; The correlation ratio between load change and trajectory behavior: ; The results show that load changes and trajectory behavior are strongly correlated. By analyzing the correlation ratio, matching event chains can be screened out and load and trajectory event chain data can be generated.

[0062] S403: Based on the load and trajectory event chain data, the corresponding relationship between the continuity of the behavior pattern in the event chain and the occlusion characteristics is analyzed, the trajectory change and the occlusion behavior correlation parameters are calculated, the abnormal behavior characteristics are screened and sorted, and the abnormal behavior record of the electric vehicle is generated; Using the segmented comparison method of trajectory position and occlusion time series data, the fluctuation range of trajectory change and occlusion behavior is calculated segment by segment, the event segments related to trajectory characteristics in occlusion behavior are screened, and the associated data of abnormal behavior is recorded and sorted. By classifying the characteristics of each abnormal behavior chain, the behavior that does not conform to the association rules of trajectory behavior continuity and occlusion characteristics is marked as abnormal, and finally the abnormal behavior record of electric vehicles is generated.

[0063] See also Figure 6 , the specific steps of S5 are: S501: Based on the abnormal behavior record of the electric vehicle, the recorded data is transmitted to the elevator control mechanism, the abnormal behavior feature data is analyzed and the corresponding control parameters are obtained, the locking function of the elevator door is started, the voice warning device is triggered and the response status is recorded, and the elevator locking and voice warning response data are generated; By parsing the behavioral feature parameters contained in the abnormal behavior record data, extracting the key control parameters, using the elevator door lock control module to start the locking function, calling the voice warning device to trigger the warning sound effect, and recording the response status of the locking function and the warning device, the response status data and the control parameters are stored in correspondence to form the elevator locking and voice warning response data, and finally generate a complete elevator control response data set.

[0064] S502: Based on the elevator lock and voice warning response data, upload the abnormal behavior record and elevator operation status data to the remote monitoring mechanism, establish a data transmission network interface and monitor the data transmission integrity, record the feedback status information of the remote monitoring mechanism, and generate the remote monitoring abnormal behavior upload result; Establish a data transmission network interface and monitor transmission integrity according to the formula: ; Calculate the ratio of data transmission integrity. Where, Indicates The amount of data transferred per record, Indicates the amount of received data corresponding to the feedback, A ratio that indicates transmission integrity.

[0065] Data transmission integrity is calculated by monitoring the cumulative difference between the amount of data transmitted and the amount of data received. For each transmission record, count the amount of data transmitted and received, calculate the cumulative difference, and divide it by the cumulative value of the amount of data transmitted to get the transmission integrity ratio. In an example, assuming that there are 3 records, the amount of data transmitted is 1000, 800, and 600 (in bytes), and the amount of data received is 980, 760, and 580 (in bytes), then: Cumulative transmission difference: ; Cumulative transfer volume: ; Transmission Integrity Ratio: ; The result shows that the data transmission integrity reaches 96.7%. By analyzing this ratio, the data transmission status of the remote monitoring mechanism can be monitored and the remote monitoring abnormal behavior upload results can be generated.

[0066] S503: Based on the upload results of remote monitoring abnormal behavior, the building alarm mechanism is linked, the abnormal behavior data is analyzed to trigger the alarm conditions and synchronize the control parameters, the alarm device in the building is activated and the alarm response time and execution status are recorded, and the elevator abnormal status event response result is generated; By analyzing the triggering alarm conditions and associated control parameters in the abnormal behavior data, extracting the abnormal feature information associated with the alarm, calling the alarm device module to start the alarm sound effect, calibrating the specific time node of the alarm trigger, and recording the operating response status of the alarm module, forming record data of the alarm trigger time and execution status, combining the trigger condition parameters with the linkage response rules of the building alarm mechanism, and generating the elevator abnormal status event response results.

[0067] See also Figure 7 , an elevator electric vehicle identification system based on abnormality detection, comprising: The object edge extraction module extracts the edge contour of the object during the door opening frame by frame based on the image data of the elevator camera and the infrared signal data of the light curtain, calculates the contour closure parameters, associates the width of the light curtain crossing path with the reflection intensity data, and generates the object geometric characteristic determination result; The target characteristic analysis module analyzes the width-to-height ratio and continuous motion trajectory variation range of the target object based on the object geometric characteristic determination results, counts the light curtain signal crossing speed and reflection intensity fluctuations, compares the geometric shape data with speed fluctuations, and generates the target object characteristic matching results; The abnormal occlusion analysis module extracts the occlusion time period and change area of ​​the elevator camera's field of view based on the target object feature matching results, counts the light curtain triggering frequency and reflection changes during the occlusion time, calculates the occlusion duration and frequency overlap rate, and compares and analyzes the occlusion data to generate abnormal occlusion behavior chain record results; The load behavior verification module analyzes the load changes before and after the door is opened based on the abnormal occlusion behavior chain record results, verifies the load change value and the object trajectory data extracted by the light curtain, selects the event chain with consistent trajectory behavior and load change, and generates abnormal behavior records of electric vehicles; The abnormal event response module is based on the abnormal behavior records of electric vehicles, transmits the recorded data to the elevator control mechanism, triggers the elevator door to lock and issue a voice warning, links the building alarm mechanism, and generates an abnormal elevator status event response result.

[0068] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for identifying elevator electric vehicles based on abnormality detection, characterized in that: The following steps are involved: S1: Based on the image data of the elevator camera and the infrared signal data of the light curtain, the edge contour of the object during the door opening is extracted frame by frame, the width-to-height ratio of the object is analyzed, the contour closure parameters are calculated, the width of the light curtain crossing path and the reflection intensity data are associated, the object morphological characteristics and signal path are identified and processed, and the object geometric characteristics determination result is generated; S2: Based on the determination result of the geometric characteristics of the object, the width-to-height ratio and the range of change of the continuous motion trajectory of the target object are analyzed, the object morphological characteristics and position offset data are combined, the light curtain signal crossing speed and reflection intensity fluctuation are counted, the geometric morphological data and speed fluctuation are compared, and the target object characteristic matching result is generated; S3: Based on the target object characteristic matching result, extract the elevator camera field of view occlusion time period and change area, count the light curtain triggering frequency and reflection change during the occlusion time, analyze the occlusion duration and frequency, calculate the occlusion duration and frequency overlap rate, combine the occlusion data for comparative analysis, and generate abnormal occlusion behavior chain record results; S4: Based on the abnormal occlusion behavior chain record results, analyze the load change before and after the door is opened, verify the load change value and the object trajectory data extracted by the light curtain, select the event chain whose trajectory behavior is consistent with the load change, analyze the behavior pattern and occlusion characteristics in the event chain, and generate an abnormal behavior record of the electric vehicle; S5: Based on the abnormal behavior record of the electric vehicle, the recorded data is transmitted to the elevator control mechanism, the elevator door is triggered to lock and a voice warning is issued, the data is uploaded to the remote monitoring mechanism, the building alarm mechanism is linked, and the elevator abnormal status event response result is generated.

2. The elevator electric vehicle identification method based on abnormality detection according to claim 1 is characterized in that: The object geometric characteristic determination result includes object edge contour parameters, aspect ratio analysis results, contour closure parameters, crossing path width characteristics, and reflection intensity characteristics; the target object characteristic matching result includes object aspect ratio characteristics, motion trajectory range characteristics, position offset data, crossing speed characteristics, and reflection intensity fluctuation characteristics; the abnormal occlusion behavior chain record result includes occlusion time period data, occlusion area change characteristics, light curtain signal trigger frequency statistics, reflection change accumulation characteristics, and occlusion duration frequency overlap rate; the electric vehicle abnormal behavior record includes load change characteristics, trajectory behavior chain, event chain pattern characteristics, and occlusion characteristic analysis results; the elevator abnormal state event response result includes door lock trigger signal, voice warning command, remote monitoring upload data, and building alarm linkage mechanism.

3. The elevator electric vehicle identification method based on abnormality detection according to claim 1 is characterized in that: Based on the image data of the elevator camera and the infrared signal data of the light curtain, the edge contour of the object during the door opening is extracted frame by frame, the width-to-height ratio of the object is analyzed, the contour closure parameters are calculated, the width of the light curtain crossing path and the reflection intensity data are associated, and the object morphological characteristics and signal path are identified and processed. The specific steps for generating the object geometric characteristic determination result are as follows: S101: Based on the image data of the elevator camera and the infrared signal data of the light curtain, the edge contours of the objects in the image during the door opening are extracted frame by frame, the object and the background area are separated by edge detection, the width and height ratio of the object edge is recorded, and the change characteristics of the edge morphology on the time axis are calculated to generate the object edge morphology data set; S102: Based on the object edge morphology data set, calculate the edge data closure parameter, compare the geometric positions of the edge start point and the edge end point, determine the contour closure, analyze the spatial continuity of the closure change between frames, perform curve fitting on the edge closure degree, record key feature points, and generate edge contour closure feature data; S103: Based on the edge contour closure feature data, combined with the crossing path width and reflection intensity information of the light curtain infrared signal data, the spatial correlation between the signal path and the contour closure parameters is analyzed, and the object feature mapping relationship is constructed through a matrix of multi-dimensional characteristic data to generate the object geometric characteristic analysis results.

4. The elevator electric vehicle identification method based on abnormality detection according to claim 3 is characterized in that: The edge closure deviation value calculation formula is specifically: ； in, represents the closure deviation value, Representative The horizontal coordinate of the frame edge starting point, Representative The vertical coordinate of the starting point of the frame edge, Representative The horizontal coordinate of the end point of the frame edge, Representative The vertical coordinate of the end point of the frame edge, Representative The area of ​​the frame enclosed region, Represents the total number of frames. is the circumference constant.

5. The elevator electric vehicle identification method based on abnormality detection according to claim 1 is characterized in that: Based on the determination result of the geometric characteristics of the object, the specific steps of analyzing the width-to-height ratio of the target object and the range of change of the continuous motion trajectory, combining the object morphological characteristics and position offset data, counting the light curtain signal crossing speed and reflection intensity fluctuations, and comparing the geometric morphological data with speed fluctuations to generate the target object characteristic matching result are as follows: S201: extracting the range of the target object's aspect ratio change based on the object geometric characteristic determination result, grouping the target object according to the width and height data between frames, calculating the ratio change of each group, statistically analyzing the frequency distribution of the ratio change interval, extracting the key points of the continuous change trend on the time axis, and generating the target object's aspect ratio change data; S202: Based on the target object aspect ratio change data, combined with the motion trajectory and position offset data, analyzing the change amplitude of each frame position in the trajectory, calculating the cumulative displacement in the change direction, screening key points with abnormal offset characteristics for the trajectory curve, and generating the target object trajectory and position feature data; S203: Based on the target object trajectory and position feature data, combined with the crossing speed and reflection intensity fluctuation range of the light curtain signal, the time nodes of the signal parameters and the trajectory change characteristics are compared, and the parameter correlation between the corresponding signal data and the geometric characteristics is statistically analyzed to generate a target object characteristic matching result.

6. The elevator electric vehicle identification method based on abnormality detection according to claim 1 is characterized in that: Based on the target object characteristic matching results, extract the elevator camera field of view occlusion time period and change area, count the light curtain trigger frequency and reflection change during the occlusion time, analyze the occlusion duration and frequency, calculate the occlusion duration and frequency overlap rate, combine the occlusion data for comparative analysis, and generate the abnormal occlusion behavior chain record results in the following specific steps: S301: Based on the target object characteristic matching result, extract the occlusion time period and change area in the elevator camera field of view, detect the boundary point position of the occlusion area frame by frame, record the area change value of the occlusion area on the time axis, count the trend of the occlusion area change and the boundary stability, and generate occlusion time and area change data; S302: Based on the shading time and area change data, extract the frequency and reflection intensity of the light curtain trigger signal within the shading time period, synchronously analyze the light curtain signal change amplitude and the shading time in the time interval, calculate the overlap ratio between the two, select the characteristic interval matching the shading and the signal, and generate the shading time and light curtain trigger frequency relationship data; S303: Based on the relationship data between the occlusion time and the light curtain triggering frequency, extract the change in the occlusion area and the light curtain signal triggering parameters, perform segmented comparison on the signal and occlusion data, record the correlation between the signal anomaly and the regional fluctuation at the time node, extract and classify the abnormal related behaviors, and generate the abnormal occlusion behavior chain record results.

7. The elevator electric vehicle identification method based on abnormality detection according to claim 6 is characterized in that: The calculation formula of the overlap intensity value of the shielding and light curtain signals is specifically as follows: ； in, Represents the overlapping intensity value of the occlusion and light curtain signals. Representative The trigger frequency change of the light curtain signal within a period of time, Representative The duration of a period of time, Representative The area value of the segment occlusion region, is the circumference constant, Represents the total number of occlusion time periods, Represents the total number of time periods for signal triggering. Representative The time value of the segment signal trigger.

8. The elevator electric vehicle identification method based on abnormality detection according to claim 1 is characterized in that: Based on the abnormal occlusion behavior chain record results, analyze the load change before and after the door is opened, verify the load change value and the object trajectory data extracted by the light curtain, select the event chain with consistent trajectory behavior and load change, analyze the behavior pattern and occlusion characteristics in the event chain, and generate the specific steps of abnormal behavior record of electric vehicles as follows: S401: Based on the abnormal occlusion behavior chain recording results, extract the elevator load change data before and after the door is opened, statistically analyze the load change data of each frame on the time axis, record the load change value of each frame, calculate the load change trend, and mark the time point of significant change to generate load change and time series data; S402: Based on the load change and time series data, verify the load change value and the object trajectory data extracted by the light curtain, extract the synchronization of the load change event and the trajectory behavior in the time axis, filter and match the event chain according to the change range, and count the event correlation characteristics to generate load and trajectory event chain data; S403: Based on the load and trajectory event chain data, the corresponding relationship between the continuity of the behavior pattern in the event chain and the occlusion characteristics is analyzed, the trajectory change and occlusion behavior association parameters are calculated, the abnormal behavior characteristics are screened and sorted, and the abnormal behavior record of the electric vehicle is generated.

9. The elevator electric vehicle identification method based on abnormality detection according to claim 1 is characterized in that: Based on the abnormal behavior record of the electric vehicle, the recorded data is transmitted to the elevator control mechanism, the elevator door is locked and a voice warning is issued, the data is uploaded to the remote monitoring mechanism, the building alarm mechanism is linked, and the specific steps of generating the elevator abnormal state event response result are: S501: Based on the abnormal behavior record of the electric vehicle, the recorded data is transmitted to the elevator control mechanism, the abnormal behavior feature data is analyzed and the corresponding control parameters are obtained, the locking function of the elevator door is started, the voice warning device is triggered and the response status is recorded, and the elevator locking and voice warning response data are generated; S502: Based on the elevator locking and voice warning response data, upload abnormal behavior records and elevator operation status data to the remote monitoring mechanism, establish a data transmission network interface and monitor data transmission integrity, record feedback status information of the remote monitoring mechanism, and generate remote monitoring abnormal behavior upload results; S503: Based on the remote monitoring abnormal behavior upload result, the building alarm mechanism is linked, the abnormal behavior data is analyzed to trigger the alarm condition and synchronize the control parameters, the alarm device in the building is started and the alarm response time and execution status are recorded, and the elevator abnormal status event response result is generated.

10. An elevator electric vehicle identification system based on abnormality detection, characterized in that: According to an elevator electric vehicle identification method based on abnormality detection according to any one of claims 1 to 9, the system comprises: The object edge extraction module extracts the edge contour of the object during the door opening frame by frame based on the image data of the elevator camera and the infrared signal data of the light curtain, calculates the contour closure parameters, associates the width of the light curtain crossing path with the reflection intensity data, and generates the object geometric characteristic determination result; The target characteristic analysis module analyzes the width-to-height ratio and the range of change of the continuous motion trajectory of the target object based on the determination result of the geometric characteristics of the object, counts the crossing speed of the light curtain signal and the fluctuation of the reflection intensity, compares the geometric shape data with the speed fluctuation, and generates the target object characteristic matching result; The abnormal occlusion analysis module extracts the occlusion time period and change area of ​​the elevator camera's field of view based on the target object characteristic matching result, counts the light curtain triggering frequency and reflection change during the occlusion time, calculates the occlusion duration and frequency overlap rate, and compares and analyzes the occlusion data to generate abnormal occlusion behavior chain record results; The load behavior verification module analyzes the load change before and after the door is opened based on the abnormal occlusion behavior chain record results, verifies the load change value and the object trajectory data extracted by the light curtain, selects the event chain with consistent trajectory behavior and load change, and generates an abnormal behavior record of the electric vehicle; The abnormal event response module transmits the recorded data to the elevator control mechanism based on the abnormal behavior record of the electric vehicle, triggers the elevator door to lock and issue a voice warning, links the building alarm mechanism, and generates an elevator abnormal state event response result.

Images