A method for monitoring electric vehicle parking in corridors based on edge computing

Abstract

The embodiment of the present invention discloses a corridor electric vehicle parking monitoring method based on edge computing, which relates to the field of edge computing technology. The method comprises: collecting images in the target corridor in real time through a camera; according to the images in the target corridor, identifying whether there is an electric vehicle in the image in the target corridor through a preset electric vehicle recognition algorithm of the edge computing system; if there is an electric vehicle in the image in the target corridor, determining whether the current electric vehicle is in a stationary state through the edge computing system; if the current electric vehicle is in a stationary state, sending an alarm message to the owner group corresponding to the building number where the target corridor is located. The present invention can intelligently and real-time monitor the situation of electric vehicles parked in the corridor, and automatically send an alarm message to the owner when there is an electric vehicle in the corridor, urging the owner to move the electric vehicle out of the corridor as soon as possible.

Description

Technical Field

[0001] The present invention belongs to the field of edge computing technology, and in particular relates to a corridor electric vehicle parking monitoring method based on edge computing. Background Art

[0002] Electric vehicles are popular among users because of their small size, convenience in traffic jams, long driving range and low price. As the number of electric vehicles increases, parking spaces for electric vehicles become tight. In order to facilitate use, parking and charging, a large number of owners choose to use corridors to park electric vehicles.

[0003] Parking electric vehicles in corridors has serious consequences and is also very dangerous. Residential corridors are not spacious to begin with, and parking electric vehicles will block the escape route, hindering escape and rescue when a fire occurs. In addition, when owners charge electric vehicles in corridors, if the electric vehicle circuit is aging, the insulation layer is broken, and the battery is short-circuited, it is easy to cause a fire. Since the material of electric vehicles is flammable, once an electric vehicle catches fire, it will release a large amount of toxic smoke. In addition, because the corridor is narrow, it is easy to cause a chain combustion of electric vehicles, making it difficult for people to escape and further causing casualties. Therefore, it is imperative to prohibit electric vehicles from being parked in corridors. It must be prohibited.

[0004] At present, the solutions to prevent electric vehicles from being parked in corridors are, first, to increase publicity efforts to let owners know the dangers of parking electric vehicles in corridors, and to set up special parking spots for electric vehicles so that electric vehicles have a place to park. However, for convenience, residents still often park electric vehicles in corridors, resulting in this solution being ineffective. The second is to arrange staff to patrol the corridors regularly, including on-site patrols and remote video patrols, which has reduced the number of electric vehicles parked in corridors to a certain extent. However, this solution is not smart enough, has high labor costs, and there are also cases of missed inspections. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a corridor electric vehicle parking monitoring method based on edge computing, which is used to solve the existing solution of preventing electric vehicles from parking in corridors, which is not intelligent enough, has high labor costs, and has the problem of missed detection. The present invention can monitor the parking of electric vehicles in the corridor intelligently and in real time through the edge computing system, and automatically send an alarm message to the owner when there is an electric vehicle in the corridor, urging the owner to move the electric vehicle out of the corridor as soon as possible.

[0006] An embodiment of the present invention provides a method for monitoring electric vehicle parking in a corridor based on edge computing, comprising:

[0007] The image in the target corridor is collected in real time through the camera;

[0008] According to the image in the target corridor, identifying whether there is an electric vehicle in the image in the target corridor by using a preset electric vehicle recognition algorithm of the edge computing system;

[0009] If there is an electric vehicle in the image of the target corridor, determine whether the electric vehicle is currently stationary through the edge computing system;

[0010] If the electric vehicle is currently stationary, an alarm message will be sent to the owner group corresponding to the building number of the target corridor.

[0011] In an optional embodiment, the alarm information includes at least: the building number of the target corridor and picture information of the target corridor where the electric vehicle exists.

[0012] In an optional embodiment, the preset electric vehicle recognition algorithm is an electric vehicle image feature recognition algorithm based on a preset electric vehicle feature library.

[0013] In an optional embodiment, if there is an electric vehicle in the image in the target corridor, determining whether the electric vehicle is currently in a stationary state through the edge computing system includes:

[0014] If there is an electric vehicle in the image in the target corridor, then record the initial time when the electric vehicle is first identified in the image in the target corridor and the pixel coordinates corresponding to the identified electric vehicle in the image in the target corridor;

[0015] Using a preset electric vehicle recognition algorithm of the edge computing system, the electric vehicle in at least seven frames of images in the target corridor continuously collected by the camera from the initial moment is identified, and the pixel coordinates corresponding to the current electric vehicle in each frame of the image in the target corridor are recorded;

[0016] Calculate the determination value of whether the electric vehicle is currently in a stationary state according to the first formula;

[0017] Determine whether the current determination value of the electric vehicle is in a stationary state is equal to 0;

[0018] If the determination value of whether the electric vehicle is currently in a stationary state is equal to 0, it is determined that the electric vehicle is currently in a non-stationary state; otherwise, it is determined that the electric vehicle is currently in a stationary state;

[0019] After sending the alarm information to the owner group corresponding to the building number where the target corridor is located, the method further includes:

[0020] According to the second formula, the control interval between the time of sending the next alarm information and the time of sending the current alarm information is calculated;

[0021] When the time interval between the current time and the time of sending the current alarm information reaches the control interval length, the alarm information is sent again to the owner group corresponding to the building number where the target corridor is located;

[0022] Among them, the first formula is:

[0023]

[0024] In the first formula, E(t) represents the determination value of whether the electric vehicle is in a stationary state at time t; t represents the current time; [I k (a),J k (a)] represents the coordinates of the ath pixel point belonging to the current electric vehicle in the image of the kth frame in the target corridor that has been recorded starting from the initial moment; I k-1 (a) represents the coordinates of the ath pixel belonging to the current electric vehicle in the image of the target corridor in the k-1th frame recorded from the initial moment; || represents the absolute value; K(t) represents the total number of frames of the image of the target corridor continuously captured by the camera from the initial moment to the moment t; n represents the minimum value of the total number of pixels belonging to the current electric vehicle in the images of the target corridor in each frame continuously captured by the camera from the initial moment to the moment t;

[0025] The second formula is:

[0026]

[0027] In the second formula, T[m(t)+1] represents the control interval between the time when the m(t)+1th alarm message is sent and the time when the m(t)th alarm message is sent; m(t) represents the total number of alarm messages that have been sent at the current moment; T0 represents the preset interval between the time when the second alarm message is sent and the time when the first alarm message is sent; t0 represents the initial moment when the current electric vehicle is first recognized to exist in the image in the target corridor.

[0028] In an optional embodiment, after determining that the electric vehicle is currently in a non-stationary state, the method further includes:

[0029] The preset voice is continuously played in the target corridor until the edge computing system recognizes the electric vehicle in the image of the target corridor in the previous frame but fails to recognize the electric vehicle in the image of the target corridor in the next adjacent frame.

[0030] In an optional embodiment, the continuously playing a preset voice in the target corridor includes:

[0031] Determine the current voice reminder control volume value according to the third formula;

[0032] Control the loudspeaker in the target corridor to play the preset voice at the current voice reminder control volume value, and add 1 to the recorded number of times the preset voice has been played corresponding to the current electric vehicle; wherein the initial value of the number of times the preset voice has been played corresponding to the current electric vehicle is 0;

[0033] Wherein, the third formula is:

[0034]

[0035] In the third formula, G(t) represents the current voice reminder control volume value; G0 represents the initial volume value when the speaker is just started; G max represents the maximum volume value of the speaker; Y(t) represents the number of times the preset voice has been played corresponding to the current electric vehicle at the current moment.

[0036] In an optional embodiment, sending the alarm information to the owner group corresponding to the building number where the target corridor is located also includes:

[0037] The alarm information is sent to a designated computer in the current community monitoring room for display.

[0038] In an optional embodiment, the step of sending the alarm information to a designated computer in the current community monitoring room for display includes:

[0039] Count the total number N of alarm information to be sent to the designated computer at the current moment;

[0040] When the total number N of alarm information to be sent to the designated computer at the current moment is greater than 1, the first rectangle corresponding to the size of the designated computer display screen is divided into at least N parts, and the size of each second rectangle is obtained;

[0041] Adjust the display size of the image in the target corridor in each alarm information to be sent to the designated computer at the current moment to the size of the second rectangle, to obtain N updated alarm information;

[0042] The updated N alarm information are sent to the display screen of the designated computer for tiled display.

[0043] The present invention provides a corridor electric vehicle parking monitoring method based on edge computing, which first collects and acquires images in the target corridor in real time, then determines whether there are electric vehicles in a stationary state in the images in the target corridor through the edge computing system, and finally sends an alarm message to the owner group corresponding to the building number where the target corridor is located when there are electric vehicles in a stationary state. The present invention can monitor the parking of electric vehicles in the corridor intelligently and in real time through the edge computing system, and automatically send an alarm message to the owner when there is an electric vehicle in the corridor, urging the owner to move the electric vehicle out of the corridor as soon as possible. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative work.

[0045] Figure 1 A flow chart of a corridor electric vehicle parking monitoring method based on edge computing provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0047] It should be clear that the described embodiments are only some embodiments of the present invention, not all 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.

[0048] Figure 1 A flow chart of a method for monitoring electric vehicle parking in corridors based on edge computing provided by an embodiment of the present invention. Figure 1 The method comprises the following steps S101-S104:

[0049] S101: Collect images in the target corridor in real time through a camera.

[0050] S102: Based on the image in the target corridor, identify whether there is an electric vehicle in the image in the target corridor through a preset electric vehicle recognition algorithm of the edge computing system; if yes, execute S103.

[0051] Preferably, the preset electric vehicle recognition algorithm is an electric vehicle image feature recognition algorithm based on a preset electric vehicle feature library. The electric vehicle features are extracted through big data analysis technology and stored in the preset electric vehicle feature library, so that based on this preset electric vehicle feature library, it is convenient to effectively identify whether there is an electric vehicle from the picture information, and it has the advantage of high recognition accuracy.

[0052] S103: Determine whether the electric vehicle is currently in a stationary state through the edge computing system; if so, execute S104.

[0053] S104: Send an alarm message to the owner group corresponding to the building number where the target corridor is located.

[0054] Preferably, the alarm information includes at least: the building number of the target corridor and picture information of the target corridor where the electric vehicle is present. The owner can determine whether it is his own electric vehicle or an electric vehicle of a familiar owner based on the alarm information, thereby urging the owner to move the electric vehicle out of the corridor as soon as possible, thereby improving the safety of the corridor.

[0055] The beneficial effects of the above technical solution are as follows: the embodiment of the present invention provides a corridor electric vehicle parking monitoring method based on edge computing, firstly, real-time acquisition of images in the target corridor, then the edge computing system is used to determine whether there are stationary electric vehicles in the images in the target corridor, and finally, when there are stationary electric vehicles, an alarm message is sent to the owner group corresponding to the building number where the target corridor is located. The present invention can monitor the parking of electric vehicles in the corridor intelligently and in real time through the edge computing system, and automatically send an alarm message to the owner when there is an electric vehicle in the corridor, urging the owner to move the electric vehicle out of the corridor as soon as possible.

[0056] As an optional embodiment, the step S103 may include the following steps S201-S206:

[0057] S201: Recording the initial moment when the electric vehicle is first recognized to exist in the image in the target corridor and the corresponding pixel coordinates of the electric vehicle in the image in the target corridor.

[0058] S202: Using a preset electric vehicle recognition algorithm of the edge computing system, identify electric vehicles in at least seven frames of images in the target corridor continuously captured by the camera starting from the initial moment, and record the corresponding pixel coordinates of the current electric vehicle in each frame of the image in the target corridor.

[0059] S203: Calculate a determination value of whether the electric vehicle is currently in a stationary state according to the first formula.

[0060] Among them, the first formula is:

[0061]

[0062] In the first formula, E(t) represents the determination value of whether the electric vehicle is in a stationary state at time t; t represents the current time; [I k (a),J k (a)] represents the coordinates of the ath pixel point belonging to the current electric vehicle in the image of the kth frame in the target corridor that has been recorded starting from the initial moment; I k-1(a) represents the coordinates of the ath pixel belonging to the current electric vehicle in the image of the target corridor in the k-1th frame recorded from the initial moment; || represents the absolute value; K(t) represents the total number of frames of the image of the target corridor continuously captured by the camera from the initial moment to moment t; n represents the minimum value of the total number of pixels belonging to the current electric vehicle in each frame of the image of the target corridor continuously captured by the camera from the initial moment to moment t. For example: if K(t) = 7, the total number of pixels belonging to the current electric vehicle identified from the consecutive 1st to 7th frames of images are 200, 180, 120, 135, 140, 128, and 117, respectively, then n = 117.

[0063] S204: Determine whether the current determination value of whether the electric vehicle is in a stationary state is equal to 0; if so, execute step S205; otherwise, execute step S206.

[0064] S205: Determine whether the electric vehicle is currently in a non-stationary state.

[0065] S206: Determine that the electric vehicle is currently in a stationary state.

[0066] In this embodiment, after step S104, the following steps S301-S302 may also be included:

[0067] S301: Calculate the control interval between the time of sending the next alarm information and the time of sending the current alarm information according to the second formula.

[0068] Wherein, the second formula is:

[0069]

[0070] In the second formula, T[m(t)+1] represents the control interval between the time when the m(t)+1th alarm message is sent and the time when the m(t)th alarm message is sent; m(t) represents the total number of alarm messages that have been sent at the current moment; T0 represents the preset interval between the time when the second alarm message is sent and the time when the first alarm message is sent; t0 represents the initial moment when the current electric vehicle is first recognized to exist in the image in the target corridor.

[0071] S302: When the time interval between the current moment and the moment of sending the current alarm information reaches the control interval, the alarm information is sent again to the owner group corresponding to the building number where the target corridor is located.

[0072] The beneficial effects of the above technical solution are as follows: using the first formula (1) to determine whether the electric vehicle is currently in a stationary state according to the pixel coordinates of the electric vehicle in each frame of the monitoring screen (i.e., the image in the target corridor), and then knowing whether there is a person moving the electric vehicle through the movement of the electric vehicle, so as to automatically and intelligently perform different operation processes according to different situations, reflecting the intelligent characteristics of the system; then using the second formula (2) to control the interval time of sending alarm information to the owner group of the corresponding building number according to the length of time the electric vehicle is detected, and then constantly urging the current safety hazards of the owners of the building number, so as to effectively and timely eliminate the hazards.

[0073] As an optional embodiment, after the step S205 determines that the current electric vehicle is in a non-stationary state, the method provided by the present invention may further include: continuously playing a preset voice in the target corridor until the edge computing system recognizes the electric vehicle in the image in the target corridor in the previous frame but fails to recognize the electric vehicle in the image in the target corridor in the next adjacent frame.

[0074] The beneficial effect of the above technical solution is: when an owner is moving an electric vehicle in the corridor, such as riding an electric vehicle in and out of the corridor, playing a preset voice can allow the owner to drive the electric vehicle out of the corridor, effectively improving the safety of the corridor.

[0075] As an optional embodiment, the continuously playing the preset voice in the target corridor may include the following steps S401-S402:

[0076] S401: Determine the current voice reminder control volume value according to the third formula;

[0077] Wherein, the third formula is:

[0078]

[0079] In the third formula, G(t) represents the current voice reminder control volume value; G0 represents the initial volume value when the speaker is just started; G max represents the maximum volume value of the speaker; Y(t) represents the number of times the preset voice has been played corresponding to the current electric vehicle at the current moment.

[0080] S402: Control the loudspeaker in the target corridor to play the preset voice at the current voice reminder control volume value, and add 1 to the recorded number of times the preset voice has been played corresponding to the current electric vehicle; wherein the initial value of the number of times the preset voice has been played corresponding to the current electric vehicle is 0.

[0081] The beneficial effect of the above technical solution is: the third formula (3) is used to control the real-time volume of the speaker according to the length of time the electric vehicle is detected, so as to warn the owner who puts the electric vehicle in the corridor with a continuously increasing volume, so as to urge the owner to remove the electric vehicle from the corridor as soon as possible, and then promptly urge the elimination of safety hazards.

[0082] As an optional embodiment, the step S104 further includes: sending the alarm information to a designated computer in the current community monitoring room for display.

[0083] The beneficial effect of the above technical solution is that when an electric vehicle is found parked in the corridor, the alarm information is promptly sent to the designated computer in the community monitoring room for display, so that the monitoring personnel and / or community security and / or management personnel can be informed of the situation in time, so as to facilitate timely response and disposal measures to eliminate safety hazards.

[0084] As an optional embodiment, sending the alarm information to a designated computer in the current community monitoring room for display may include the following steps S501-S504:

[0085] S501: Counting the total number N of alarm information to be sent to the designated computer at the current moment;

[0086] S502: When the total number N of alarm information to be sent to the designated computer at the current moment is greater than 1, the first rectangle corresponding to the size of the designated computer display screen is divided into at least N parts to obtain the size of each second rectangle;

[0087] S503: adjusting the display size of the image in the target corridor in each alarm information to be sent to the designated computer at the current moment to the size of the second rectangle, to obtain N updated alarm information;

[0088] S504: Send the updated N alarm information to the display screen of the designated computer for tiled display.

[0089] Preferably, in step S502, when the total number N of alarm information is an odd number greater than 1, the first rectangle corresponding to the size of the designated computer display screen is divided into at least M equal parts, M=N+1, then in S504, the designated computer screen can be divided into M display areas in the form of a matrix, and the images in the target corridor in the updated N alarm information can be displayed in N display areas of the M display areas in the form of a matrix divided on the designated computer screen, and the building number of the target corridor in the alarm information can be displayed in the form of a floating window on the image of the corresponding target corridor.

[0090] The beneficial effects of the above technical solution are: the size of the picture in each target corridor (or the photo of the electric vehicle in the picture) displayed on the computer is automatically adjusted according to the number of alarm messages, so that all alarm messages can be displayed on the computer, which is convenient for monitoring personnel and / or community security and / or management personnel to fully understand the parking situation of electric vehicles in all corridors in the community, facilitate the implementation of response measures, and improve the safety of the community.

[0091] It can be seen from the contents of the above embodiments that an edge computing system is added to the camera to obtain the monitoring situation of the entire corridor, and an alarm reminder is issued when an electric vehicle appears in the corridor monitoring screen (i.e., the image in the corridor); and when the monitoring of the entire corridor identifies the appearance of an electric vehicle in the monitoring screen, first determine whether the electric vehicle is in a stationary state. If the electric vehicle is in a stationary state, take a photo of the electric vehicle (i.e., the picture information in the corridor), and generate an alarm message in combination with the building number where the current corridor is located, and send the alarm message to the owner group of the corresponding building number, and display the electric vehicle photo in the alarm message on the computer in the community security room and mark the corresponding building number, and automatically adjust the size of each electric vehicle photo displayed on the computer according to the number of alarm messages; if the electric vehicle is in a non-stationary state, control the speaker installed in the corridor where the monitoring system is located to give a voice reminder and control the real-time volume of the speaker according to the length of time the electric vehicle is detected, thereby urging personnel to remove the electric vehicle from the corridor.

[0092] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 An apparatus for the method specified in one or more blocks.

[0093] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 The method specified in one or more boxes.

[0094] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of a method specified in one or more boxes.

[0095] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these changes and variations. The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A corridor electric vehicle parking monitoring method based on edge computing, characterized in that: include: The image in the target corridor is collected in real time through the camera; According to the image in the target corridor, a preset electric vehicle recognition algorithm of the edge computing system is used to identify whether there is an electric vehicle in the image in the target corridor; If there is an electric vehicle in the image of the target corridor, determine whether the electric vehicle is currently stationary through the edge computing system; If the electric vehicle is currently stationary, an alarm message will be sent to the owner group corresponding to the building number of the target corridor; If there is an electric vehicle in the image of the target corridor, the edge computing system is used to determine whether the electric vehicle is currently stationary, including: If there is an electric vehicle in the image in the target corridor, then record the initial time when the electric vehicle is first identified in the image in the target corridor and the pixel coordinates corresponding to the identified electric vehicle in the image in the target corridor; Using a preset electric vehicle recognition algorithm of the edge computing system, the electric vehicle in at least seven frames of images in the target corridor continuously collected by the camera from the initial moment is identified, and the pixel coordinates corresponding to the current electric vehicle in each frame of the image in the target corridor are recorded; Calculate the determination value of whether the electric vehicle is currently in a stationary state according to the first formula; Determine whether the current determination value of the electric vehicle is in a stationary state is equal to 0; If the determination value of whether the electric vehicle is currently in a stationary state is equal to 0, it is determined that the electric vehicle is currently in a non-stationary state; otherwise, it is determined that the electric vehicle is currently in a stationary state; After sending the alarm information to the owner group corresponding to the building number where the target corridor is located, the method further includes: According to the second formula, the control interval between the time of sending the next alarm information and the time of sending the current alarm information is calculated; When the time interval between the current time and the time of sending the current alarm information reaches the control interval length, the alarm information is sent again to the owner group corresponding to the building number where the target corridor is located; Among them, the first formula is: In the first formula, E(t) represents the determination value of whether the electric vehicle is in a stationary state at time t; t represents the current time; [I k (a),J k (a)] represents the coordinates of the ath pixel point belonging to the current electric vehicle in the image of the kth frame in the target corridor that has been recorded starting from the initial moment; I k-1 (a) represents the coordinates of the ath pixel belonging to the current electric vehicle in the image of the target corridor in the k-1th frame recorded from the initial moment; || represents the absolute value; K(t) represents the total number of frames of the image of the target corridor continuously captured by the camera from the initial moment to the moment t; n represents the minimum value of the total number of pixels belonging to the current electric vehicle in the images of the target corridor in each frame continuously captured by the camera from the initial moment to the moment t; The second formula is: In the second formula, T[m(t)+1] represents the control interval between the time when the m(t)+1th alarm message is sent and the time when the m(t)th alarm message is sent; m(t) represents the total number of alarm messages that have been sent at the current moment; T0 represents the preset interval between the time when the second alarm message is sent and the time when the first alarm message is sent; t0 represents the initial moment when the current electric vehicle is first recognized to exist in the image in the target corridor.

2. The method for monitoring electric vehicle parking in corridors based on edge computing according to claim 1, characterized in that: The alarm information at least includes: the building number of the target corridor and the picture information of the target corridor where the electric vehicle exists.

3. The method for monitoring electric vehicle parking in corridors based on edge computing according to claim 1, characterized in that: The preset electric vehicle recognition algorithm is an electric vehicle image feature recognition algorithm based on a preset electric vehicle feature library.

4. The method for monitoring electric vehicle parking in corridors based on edge computing according to claim 1, characterized in that: After determining that the electric vehicle is currently in a non-stationary state, the following steps are also included: The preset voice is continuously played in the target corridor until the edge computing system recognizes the electric vehicle in the image of the target corridor in the previous frame but fails to recognize the electric vehicle in the image of the target corridor in the next adjacent frame.

5. The method for monitoring electric vehicle parking in corridors based on edge computing according to claim 4, characterized in that: The continuously playing the preset voice in the target corridor includes: Determine the current voice reminder control volume value according to the third formula; Control the loudspeaker in the target corridor to play the preset voice at the current voice reminder control volume value, and add 1 to the recorded number of times the preset voice has been played corresponding to the current electric vehicle; wherein the initial value of the number of times the preset voice has been played corresponding to the current electric vehicle is 0; Wherein, the third formula is: In the third formula, G(t) represents the current voice reminder control volume value; G0 represents the initial volume value when the speaker is just started; G max represents the maximum volume value of the speaker; Y(t) represents the number of times the preset voice has been played corresponding to the current electric vehicle at the current moment.

6. The method for monitoring electric vehicle parking in corridors based on edge computing according to claim 2, characterized in that: The sending of alarm information to the owner group corresponding to the building number where the target corridor is located also includes: The alarm information is sent to a designated computer in the current community monitoring room for display.

7. The method for monitoring electric vehicle parking in corridors based on edge computing according to claim 6, characterized in that: The step of sending the alarm information to a designated computer in the current community monitoring room for display includes: Count the total number N of alarm information to be sent to the designated computer at the current moment; When the total number N of alarm information to be sent to the designated computer at the current moment is greater than 1, the first rectangle corresponding to the size of the designated computer display screen is divided into at least N parts, and the size of each second rectangle is obtained; Adjust the display size of the image in the target corridor in each alarm information to be sent to the designated computer at the current moment to the size of the second rectangle, to obtain N updated alarm information; The updated N alarm information are sent to the display screen of the designated computer for tiled display.

Images