Security video monitoring system based on big data

Abstract

The invention discloses a security video monitoring system based on big data, which comprises a data acquisition module, a security detection module and an early warning management module, and is characterized in that the data acquisition module is used for collecting visual images in a community, real-time weight of a target object in an elevator and face recognition comprehensive data of a community owner; the safety detection module is used for detecting whether community owners have the intention of pushing the electric bicycles into the elevator or not and detecting whether a target object crosses the border or not, and the early warning management module is used for giving an alarm to the owners with the intention of pushing the electric bicycles into the elevator and controlling the elevator not to be carried. The data acquisition module, the safety detection module and the early warning management module are electrically connected with one another, the data acquisition module comprises a visual module, a data input module and a weighing module, the visual module is used for shooting visual images of a target area in a community in real time, and the system has the advantage of improving accuracy and safety.

Description

Technical Field

[0001] The present invention relates to the technical field of security video monitoring, and in particular to a security video monitoring system based on big data. Background Art

[0002] With the rapid development of big data and the Internet of Things, big data and the Internet of Things have been widely used, especially in the field of security video surveillance.

[0003] At present, accidents caused by electric bicycles occur frequently in residential buildings. Almost all communities require that electric bicycles are prohibited from being parked in the corridors of floors. However, in order to save the cost of charging electric bicycles, some people still secretly park electric bicycles in the corridors in front of their homes to charge, which poses a huge safety hazard. Although communities are now basically equipped with video surveillance systems to monitor the security of the communities, most existing technologies use manual detection methods to supervise surveillance videos. Due to too many surveillance images, manual detection cannot detect problems in time, resulting in safety hazards. Moreover, even if a small number of video surveillance systems use cross-border detection methods to detect target objects in the area, since the target objects are at the edge of the detection area and the identified feature nodes are incomplete, the system cannot mark the edge frame of the target object according to the feature nodes, which can easily cause the system to fail to detect the edge frame, resulting in the system being unable to accurately determine whether the target object has crossed the boundary, resulting in missed judgments, and affecting the accuracy of the system's judgment. Therefore, it is very necessary to design a security video surveillance system and method based on big data to improve accuracy and security. Summary of the invention

[0004] The purpose of the present invention is to provide a security video monitoring system and method based on big data to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a security video monitoring system and method based on big data, comprising a data acquisition module, a safety detection module and an early warning management module, characterized in that: the data acquisition module is used to collect visual images in a community, the real-time weight of a target object in an elevator and comprehensive face recognition data of community owners, the safety detection module is used to detect whether a community owner has the intention to push an electric bicycle into an elevator and whether the target object has crossed the boundary, the early warning management module is used to issue an alarm to an owner who has pushed an electric bicycle into an elevator and control the elevator not to carry the electric bicycle, and the data acquisition module, the safety detection module and the early warning management module are electrically connected to each other;

[0006] The vehicle detection module includes a first detection submodule, a second detection submodule and a face recognition submodule, wherein the first detection submodule is used to detect whether the owner waiting for the elevator intends to push the electric bicycle into the elevator, the second detection submodule is used to detect whether the owner is carrying a portable electric bicycle in the elevator, and the face recognition module is used to identify the owner's face data and analyze the owner's address;

[0007] The area detection module includes an edge analysis submodule, a compensation analysis submodule and a timing analysis submodule. The edge analysis submodule is used to identify the edge features of the target object and mark the edge frame. The compensation analysis submodule is used to analyze the target object and complete the target object according to the features in the edge frame of the target object. The timing analysis submodule is used to record the length of time the target object stays in the target area.

[0008] According to the above technical solution, the data acquisition module includes a visual module, a data entry module and a weighing module. The visual module is used to capture the visual image of the target area in the community in real time, the data entry module is used to enter the visual image of the community owner into the system, and the weighing module is used to measure the total weight carried by the elevator when the owner takes the elevator.

[0009] According to the above technical solution, the safety detection module includes a vehicle detection module, which is used to analyze whether there are owners pushing electric bicycles into the elevator inside and outside the elevator, and adjust the operation of the elevator according to the analysis results.

[0010] According to the above technical solution, the security detection module also includes an area detection module, which is used to analyze whether there is a target object crossing the target area, and issue an alarm to the property manager based on the analysis result.

[0011] According to the above technical solution, the early warning management module includes an elevator adjustment module and an early warning module. The elevator adjustment module is used to adjust the operation mode of the elevator according to the vehicle analysis results inside and outside the elevator, and the early warning module is used to issue an alarm to the property manager based on the vehicle detection results and the area detection results.

[0012] According to the above technical solution, the security video monitoring method mainly includes the following steps:

[0013] Step S1: collect visual images of the target area in real time through the visual module, enter the facial data of the community owners into the system through the data entry module, and measure the weight carried by the elevator in real time through the weighing module;

[0014] Step S2: After the owner presses the elevator button, the system sends an electrical signal to trigger the vehicle detection module to start, and begins to analyze whether the owner intends to push the electric bicycle into the elevator, and adjusts the operation of the elevator according to the analysis results;

[0015] Step S3: When detecting the target area, the system starts the area detection module, starts analyzing the target object in the target area, and determines whether the target object crosses the boundary according to the analysis result;

[0016] Step S4: When the owner intends to push the electric bicycle into the elevator or the target object crosses the boundary, the system issues an alarm through the early warning module to remind the property manager of the potential safety hazard.

[0017] According to the above technical solution, step S2 further includes the following steps:

[0018] Step S21: retrieve the visual image of the target area, scan and identify the contour feature nodes in the visual image, connect the human contour feature nodes and the electric bicycle contour nodes respectively, build a contour model, and compare the electric bicycle contour model in the database. If the similarity is greater than the system-set threshold, it is marked that the owner intends to push the electric bicycle into the elevator. The system issues an alarm through the early warning module to remind the owner not to push the electric bicycle into the elevator, and controls the elevator not to stay on this floor through the elevator adjustment module. When the similarity is less than the system-set threshold, the system continues to detect;

[0019] Step S22: Identify the number of electric bicycles and people in the image. When the number of electric bicycles is less than the number of people waiting, the elevator runs normally. If it is identified that the owner pushes the electric bicycle into the elevator, the elevator is controlled to enter the overload mode, and the early warning module reminds the owner again not to push the electric bicycle into the elevator. Otherwise, the elevator starts normally.

[0020] Step S23: Obtain the visual image captured by the visual module in the elevator, identify the contour nodes of the electric bicycle in the visual image, and when the number of identified contour nodes is greater than or equal to the system set threshold, the system controls the elevator to enter the overload mode, and reminds the owner again through the early warning module not to push the electric bicycle into the elevator.

[0021] According to the above technical solution, step S23 further includes the following steps:

[0022] Step S231: When the identified contour node is smaller than the threshold, the sleeve diameter and cuff diameter of the owner's forearm are identified. If the difference between the sleeve diameter and the cuff diameter is greater than the threshold set by the system, the corresponding owner's weight influence coefficient α in the system database is retrieved according to the difference, the owner's height and waist circumference are measured, and the corresponding standard weight K1 and the waist circumference influence coefficient β in the database are retrieved according to the height and waist circumference. The owner's estimated weight is calculated by the formula M=K1*α*β, where M represents the owner's estimated weight. The difference W between the elevator load and the sum of the owners' weights is calculated by the formula. If the difference W is greater than the threshold set by the system, it is marked that there is a portable electric bicycle in the current elevator, otherwise the detection continues;

[0023] When the owner leaves the elevator, the difference between the current elevator load and the weight of all the owners in the elevator is calculated. If the difference is less than the minimum threshold at this time, it means that the owner carrying the portable electric vehicle has gotten off the elevator. The visual image in the elevator is retrieved, the owner's facial data is scanned and recognized, and the owner's address is identified. The system then issues an alarm to remind the property manager to admonish the owner. Otherwise, the system continues to detect.

[0024] According to the above technical solution, step S3 further includes the following steps:

[0025] Step S31: retrieve the visual image of the target area, scan and identify the feature nodes of all target objects in the image, compare the database according to the feature nodes of the target object, select all models with a similarity greater than a set threshold to complete the target object, overlap and fuse all models, identify the edge nodes of the fused model, select the model with a rectangular box according to the edge nodes, establish a coordinate system, identify the coordinates of the edge box vertices, and pass through multiple tangents of the edge box vertices. If the tangent has an intersection with the surface where the target detection area is located, the target object is marked as out of bounds pending, otherwise it is marked as not out of bounds;

[0026] Step S32: Identify the mark in the target object. If there is an out-of-bounds mark in the target object, start the timing module, otherwise continue to detect. When the timing ends, perform an out-of-bounds detection on the target object. If the target object still crosses the boundary, it is confirmed that the target object has crossed the boundary. The system issues an alarm to remind the property manager to handle it with all his heart. Otherwise, mark the target object as not crossing the boundary and continue to detect.

[0027] According to the above technical solution, the detection results of the first detection submodule and the second detection submodule are identified in step S4. If the detection results show that the owner pushes the electric bicycle into the elevator, the elevator is adjusted to be unresponsive to the floor command, and an alarm is issued through the early warning module to remind the property manager to give advice. Otherwise, the system continues to detect, thereby preventing the owner from secretly bringing the electric bicycle upstairs, causing a fire, and further improving the safety of the community.

[0028] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention detects whether the owner is pushing an electric bicycle when the owner is waiting for the elevator, and then controls the elevator not to pass through this floor, so as to prevent the owner who is lucky enough to secretly bring the electric bicycle to the corridor to charge, thereby reducing the risk of fire and greatly improving the safety of the community. By detecting whether there is an electric bicycle again in the elevator, it can be avoided that the owner presses the elevator in advance and waits for the elevator to arrive before pushing the electric bicycle into the elevator to avoid the first detection, thereby causing the owner to still bring the electric bicycle upstairs, resulting in safety hazards, thereby greatly improving safety. By comparing the real-time load-bearing weight of the elevator with the total weight of the owners, it can be prevented that the owner secretly carries the electric bicycle upstairs, thereby reducing the safety hazards of the community and greatly improving the safety of the community. By analyzing whether the target object is in the same space as the target area, and re-detecting the target object that crosses the boundary after the timing ends, it can avoid the influence of environmental factors on the accuracy of the target object detection result, and at the same time, it can also avoid the target object only making a short stay system alarm, causing the target object to leave when the property manager handles it, resulting in a waste of the property manager's energy and time, thereby greatly improving the accuracy of the system detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0030] Figure 1 It is a schematic diagram of the system module composition of the present invention. DETAILED DESCRIPTION

[0031] 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.

[0032] See also Figure 1The present invention provides a technical solution: a security video monitoring system and method based on big data, including a data acquisition module, a safety detection module and an early warning management module, characterized in that: the data acquisition module is used to collect visual images in the community, the real-time weight of the target object in the elevator and the face recognition comprehensive data of the community owner, the safety detection module is used to detect whether the community owner has the intention to push the electric bicycle into the elevator and whether the target object has crossed the boundary, the early warning management module is used to issue an alarm to the owner who has pushed the electric bicycle into the elevator and control the elevator not to carry the electric bicycle, and the data acquisition module, the safety detection module and the early warning management module are electrically connected to each other;

[0033] The vehicle detection module includes a first detection submodule, a second detection submodule and a face recognition submodule. The first detection submodule is used to detect whether the owner waiting for the elevator intends to push the electric bicycle into the elevator. The second detection submodule is used to detect whether the owner is carrying a portable electric bicycle in the elevator. The face recognition module is used to identify the owner's face data and analyze the owner's address.

[0034] The area detection module includes an edge analysis submodule, a compensation analysis submodule and a timing analysis submodule. The edge analysis submodule is used to identify the edge features of the target object and mark the edge frame. The compensation analysis submodule is used to analyze the target object and complete the target object according to the features in the edge frame of the target object. The timing analysis submodule is used to record the length of time the target object stays in the target area.

[0035] The data acquisition module includes a visual module, a data entry module and a weighing module. The visual module is used to capture the visual image of the target area in the community in real time. The data entry module is used to enter the visual image of the community owners into the system. The weighing module is used to measure the total weight carried by the elevator when the owners take the elevator.

[0036] The safety detection module includes a vehicle detection module, which is used to analyze whether there are owners pushing electric bicycles into the elevator inside and outside the elevator, and adjust the operation of the elevator according to the analysis results.

[0037] The security detection module also includes an area detection module, which is used to analyze whether there is a target object crossing the target area and send an alarm to the property manager based on the analysis results.

[0038] The early warning management module includes an elevator adjustment module and an early warning module. The elevator adjustment module is used to adjust the elevator's operating mode according to the vehicle analysis results inside and outside the elevator. The early warning module is used to issue alarms to the property manager based on the vehicle detection results and area detection results.

[0039] The security video surveillance method mainly includes the following steps:

[0040] Step S1: collect visual images of the target area in real time through the visual module, enter the facial data of the community owners into the system through the data entry module, and measure the weight carried by the elevator in real time through the weighing module;

[0041] Step S2: After the owner presses the elevator button, the system sends an electrical signal to trigger the vehicle detection module to start, and begins to analyze whether the owner intends to push the electric bicycle into the elevator, and adjusts the operation of the elevator according to the analysis results;

[0042] Step S3: When detecting the target area, the system starts the area detection module, starts analyzing the target object in the target area, and determines whether the target object crosses the boundary according to the analysis result;

[0043] Step S4: When the owner intends to push the electric bicycle into the elevator or the target object crosses the boundary, the system issues an alarm through the early warning module to remind the property manager of the potential safety hazard.

[0044] Step S2 further comprises the following steps:

[0045] Step S21: Retrieve the visual image of the target area, scan and identify the contour feature nodes in the visual image, connect the human body contour feature nodes and the electric bicycle contour nodes respectively, build a contour model, and compare the electric bicycle contour model in the database. If the similarity is greater than the system-set threshold, it is marked that the owner intends to push the electric bicycle into the elevator. The system issues an alarm through the early warning module to remind the owner not to push the electric bicycle into the elevator, and controls the elevator not to stay on this floor through the elevator adjustment module. When the similarity is less than the system-set threshold, the system continues to detect whether the owner is pushing the electric bicycle while the owner is waiting for the elevator, and then controls the elevator not to pass through this floor, which can prevent the lucky owner from secretly taking the electric bicycle to the corridor to charge, thereby reducing the risk of fire and greatly improving the safety of the community;

[0046] Step S22: Identify the number of electric bicycles and people in the image. When the number of electric bicycles is less than the number of people waiting, the elevator runs normally. If it is identified that the owner pushes the electric bicycle into the elevator, the elevator is controlled to enter the overload mode, and the early warning module reminds the owner again not to push the electric bicycle into the elevator. Otherwise, the elevator starts normally, thereby preventing electric bicycles from going upstairs, reducing safety hazards and improving safety.

[0047] Step S23: Acquire the visual image taken by the visual module in the elevator, identify the contour nodes of the electric bicycle in the visual image, and when the number of identified contour nodes is greater than or equal to the threshold set by the system, it means that the electric bicycle has entered the elevator. The system controls the elevator to enter the overload mode, and reminds the owner again through the early warning module not to push the electric bicycle into the elevator. By detecting whether there is an electric bicycle again in the elevator, it can avoid the owner pressing the elevator button in advance and waiting for the elevator to arrive before pushing the electric bicycle into the elevator, thereby avoiding the first detection, which may result in the owner still being able to bring the electric bicycle upstairs, causing a safety hazard, thereby greatly improving safety.

[0048] Step S23 further includes the following steps:

[0049] Step S231: When the identified contour node is smaller than the threshold, the sleeve diameter and cuff diameter of the owner's forearm are identified. If the difference between the sleeve diameter and the cuff diameter is greater than the threshold set by the system, the corresponding owner's weight influence coefficient α in the system database is retrieved according to the difference, the owner's height and waist circumference are measured, and the corresponding standard weight K1 and the waist circumference influence coefficient β in the database are retrieved according to the height and waist circumference. The owner's estimated weight is calculated by the formula M=K1*α*β, where M represents the owner's estimated weight. The difference W between the elevator load and the sum of the owners' weights is calculated by the formula. If the difference W is greater than the threshold set by the system, it is marked that there is a portable electric bicycle in the current elevator, otherwise the detection continues;

[0050] When the owner leaves the elevator, the difference between the current elevator load-bearing weight and the total weight of the owners in the elevator is calculated. If the difference is less than the minimum threshold at this time, it means that the owner carrying the portable electric vehicle has got off the elevator. The visual image in the elevator is retrieved, the owner's facial data is scanned and recognized, and the owner's address is identified. The system issues an alarm to remind the property manager to admonish the owner. Otherwise, the system continues to detect. By comparing the real-time load-bearing weight of the elevator with the total weight of the owners, it can prevent owners from secretly carrying electric bicycles upstairs, thereby reducing safety hazards in the community and greatly improving the safety of the community.

[0051] Step S3 further includes the following steps:

[0052] Step S31: retrieve the visual image of the target area, scan and identify the feature nodes of all target objects in the image, compare the database according to the feature nodes of the target object, select all models with a similarity greater than a set threshold to complete the target object, overlap and fuse all models, identify the edge nodes of the fused model, select the model with a rectangular box according to the edge nodes, establish a coordinate system, identify the coordinates of the edge box vertices, and multiple tangents through the edge box vertices. If there are several points between the tangent and the surface where the target detection area is located, the target object is marked as out-of-bounds pending, otherwise it is marked as not out-of-bounds;

[0053] Step S32: Identify the mark in the target object. If there is an out-of-bounds pending mark in the target object, start the timing module, otherwise continue to detect. When the timing ends, perform an out-of-bounds detection on the target object. If the target object still crosses the boundary, it is confirmed that the target object has crossed the boundary, and the system issues an alarm to remind the property manager to handle it with all his heart. Otherwise, mark the target object as not crossing the boundary and continue to detect. By analyzing whether the target object is in the same space as the target area and re-detecting the out-of-bounds target object after the timing ends, the influence of environmental factors on the accuracy of the target object detection results can be avoided. At the same time, it can also avoid the system alarm when the target object only makes a short stay, causing the target object to leave when the property manager is handling it, resulting in a waste of the property manager's energy and time, thereby greatly improving the accuracy of the system detection.

[0054] In step S4, the detection results of the first detection submodule and the second detection submodule are identified. If the detection results show that the owner pushes the electric bicycle into the elevator, the elevator is adjusted to be unresponsive to the floor command, and an alarm is issued through the early warning module to remind the property manager to give advice. Otherwise, the system continues to detect, thereby preventing the owner from secretly bringing the electric bicycle upstairs, causing a fire, and further improving the safety of the community.

[0055] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0056] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A security video monitoring method based on big data, characterized in that: It uses a security video monitoring system based on big data, which includes a data acquisition module, a safety detection module and an early warning management module. The data acquisition module is used to collect visual images in the community, the real-time weight of the target object in the elevator and the comprehensive face recognition data of the community owners. The safety detection module is used to detect whether the community owners have the intention to push the electric bicycle into the elevator and whether the target object has crossed the boundary. The early warning management module is used to issue an alarm to the owner who has pushed the electric bicycle into the elevator and control the elevator not to carry the electric bicycle. The data acquisition module, the safety detection module and the early warning management module are electrically connected to each other; The safety detection module includes a vehicle detection module, which is used to analyze whether there is an owner pushing an electric bicycle into the elevator inside and outside the elevator, and adjust the operation of the elevator according to the analysis result; The safety detection module also includes an area detection module, which is used to analyze whether there is a target object crossing the target area, and send an alarm to the property manager according to the analysis result; The vehicle detection module includes a first detection submodule, a second detection submodule and a face recognition submodule, wherein the first detection submodule is used to detect whether the owner waiting for the elevator intends to push the electric bicycle into the elevator, the second detection submodule is used to detect whether the owner is carrying a portable electric bicycle in the elevator, and the face recognition submodule is used to identify the owner's face data and analyze the owner's address; The area detection module includes an edge analysis submodule, a compensation analysis submodule and a timing analysis submodule. The edge analysis submodule is used to identify the edge features of the target object and mark the edge frame. The compensation analysis submodule is used to analyze the target object and complete the target object according to the features of the target object edge frame. The timing analysis submodule is used to record the length of time the target object stays in the target area. The data acquisition module includes a visual module, a data entry module and a weighing module. The visual module is used to capture the visual image of the target area in the community in real time. The data entry module is used to enter the visual image of the community owner into the system. The weighing module is used to measure the total weight carried by the elevator when the owner takes the elevator. The early warning management module includes an elevator adjustment module and an early warning module. The elevator adjustment module is used to adjust the operation mode of the elevator according to the analysis results of vehicles inside and outside the elevator. The early warning module is used to issue an alarm to the property manager according to the vehicle detection results and the area detection results. The security video monitoring method comprises the following steps: Step S1: collect visual images of the target area in real time through the visual module, enter the facial data of the community owners into the system through the data entry module, and measure the weight carried by the elevator in real time through the weighing module; Step S2: After the owner presses the elevator button, the system sends an electrical signal to trigger the vehicle detection module to start, and begins to analyze whether the owner intends to push the electric bicycle into the elevator, and adjusts the operation of the elevator according to the analysis results; Step S3: When detecting the target area, the system starts the area detection module, starts analyzing the target object in the target area, and determines whether the target object crosses the boundary according to the analysis result; Step S4: When the owner intends to push the electric bicycle into the elevator or the target object crosses the boundary, the system issues an alarm through the early warning module to remind the property manager of the potential safety hazard; The step S2 further comprises the following steps: Step S21: retrieve the visual image of the target area, scan and identify the contour feature nodes in the visual image, connect the human contour feature nodes and the electric bicycle contour nodes respectively, build a contour model, and compare the electric bicycle contour model in the database. If the similarity is greater than the system-set threshold, it is marked that the owner intends to push the electric bicycle into the elevator. The system issues an alarm through the early warning module to remind the owner not to push the electric bicycle into the elevator, and controls the elevator not to stay on this floor through the elevator adjustment module. When the similarity is less than the system-set threshold, the system continues to detect; Step S22: Identify the number of electric bicycles and people in the image. When the number of electric bicycles is less than the number of people waiting, the elevator runs normally. If it is identified that the owner pushes the electric bicycle into the elevator, the elevator is controlled to enter the overload mode, and the early warning module reminds the owner again not to push the electric bicycle into the elevator. Otherwise, the elevator starts normally. Step S23: Obtain the visual image captured by the visual module in the elevator, identify the contour nodes of the electric bicycle in the visual image, and when the number of identified contour nodes is greater than or equal to the threshold set by the system, the system controls the elevator to enter the overload mode, and reminds the owner again not to push the electric bicycle into the elevator through the early warning module; The step S23 further comprises the following steps: Step S231: When the identified contour node is smaller than the threshold, the sleeve diameter and cuff diameter of the owner's forearm are identified. If the difference between the sleeve diameter and the cuff diameter is greater than the threshold set by the system, the corresponding owner's weight influence coefficient α in the system database is retrieved according to the difference, the owner's height and waist circumference are measured, and the corresponding standard weight K1 and the waist circumference influence coefficient β in the database are retrieved according to the height and waist circumference. The owner's estimated weight is calculated by the formula M=K1*α*β, where M represents the owner's estimated weight. The difference W between the elevator load and the sum of the owners' weights is calculated by the formula. If the difference W is greater than the threshold set by the system, it is marked that there is a portable electric bicycle in the current elevator, otherwise the detection continues; When the owner leaves the elevator, the difference between the current elevator load and the weight of the owners in the elevator is calculated. If the difference is less than the minimum threshold, it means that the owner carrying the portable electric vehicle has left the elevator. The visual image in the elevator is retrieved, the owner's face data is scanned and recognized, and the owner's address is identified. The system issues an alarm to remind the property manager to admonish the owner. Otherwise, the system continues to detect. In step S4, the detection results of the first detection submodule and the second detection submodule are identified. If the detection results show that the owner pushes the electric bicycle into the elevator, the elevator is adjusted to be unresponsive to the floor command, and an alarm is issued through the early warning module to remind the property manager to give advice. Otherwise, the system continues to detect, thereby preventing the owner from secretly bringing the electric bicycle upstairs, causing a fire, and further improving the safety of the community.

Images