CN114735559B - Elevator monitoring system and method based on image recognition - Google Patents
Elevator monitoring system and method based on image recognition Download PDFInfo
- Publication number
- CN114735559B CN114735559B CN202210411488.1A CN202210411488A CN114735559B CN 114735559 B CN114735559 B CN 114735559B CN 202210411488 A CN202210411488 A CN 202210411488A CN 114735559 B CN114735559 B CN 114735559B
- Authority
- CN
- China
- Prior art keywords
- elevator
- time
- door
- area
- monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 100
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000008569 process Effects 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000004888 barrier function Effects 0.000 abstract description 5
- 238000012806 monitoring device Methods 0.000 description 13
- 230000002159 abnormal effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000000630 rising effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000009194 climbing Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/0006—Monitoring devices or performance analysers
- B66B5/0012—Devices monitoring the users of the elevator system
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B13/00—Doors, gates, or other apparatus controlling access to, or exit from, cages or lift well landings
- B66B13/24—Safety devices in passenger lifts, not otherwise provided for, for preventing trapping of passengers
- B66B13/26—Safety devices in passenger lifts, not otherwise provided for, for preventing trapping of passengers between closing doors
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/0006—Monitoring devices or performance analysers
- B66B5/0018—Devices monitoring the operating condition of the elevator system
- B66B5/0031—Devices monitoring the operating condition of the elevator system for safety reasons
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/02—Applications of checking, fault-correcting, or safety devices in elevators responsive to abnormal operating conditions
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B50/00—Energy efficient technologies in elevators, escalators and moving walkways, e.g. energy saving or recuperation technologies
Landscapes
- Indicating And Signalling Devices For Elevators (AREA)
- Elevator Door Apparatuses (AREA)
Abstract
The application is applicable to the technical field of video processing, and particularly relates to an elevator monitoring system and method based on image recognition, wherein the method comprises the following steps: acquiring a real-time elevator monitoring video; identifying an elevator button area in a real-time elevator monitoring video, and determining the floor where the current elevator is located; object identification is carried out on the elevator door area, whether an obstacle affecting the closing of the elevator door exists or not is judged, and if the elevator door area is shielded, the elevator door area is regarded as an obstacle-free area; judging whether an object moves along a door gap in the elevator door area; if the object moves along the door gap, an alarm is sent out and an emergency stop instruction is sent out to the elevator; if an obstacle is detected, a prompt voice is sent out, and an instruction for prohibiting closing is sent out to the elevator. According to the application, whether the barrier exists or not can be judged by monitoring the elevator door area, and then, after the door is closed, objects at the door gap can be monitored to prevent the elevator door from clamping the objects to run, so that the safety of a user is protected to the greatest extent.
Description
Technical Field
The application belongs to the technical field of video processing, and particularly relates to an elevator monitoring system and method based on image recognition.
Background
The monitoring system is also called a closed-circuit television monitoring system, and a typical monitoring system mainly comprises five parts, namely front-end audio and video acquisition equipment, audio and video transmission equipment and rear-end storage, control and display equipment, wherein the rear-end equipment can be further divided into central control equipment and sub-control equipment. The front-end and back-end devices may be configured in a variety of ways, and the connection between them (also referred to as a transmission system) may be implemented in a variety of ways, such as coaxial cable, twisted pair, fiber optics, microwave, wireless, etc.
In the current buildings, elevators are basically provided, and in order to ensure the safety of the elevators, the elevators are correspondingly provided with monitoring devices, and in the background, the conditions in the elevators can be checked through the monitoring devices, so that the elevator is convenient and safe to use.
However, the current monitoring device in the elevator can only play a role of recording, and cannot identify emergency events occurring in the elevator, so that danger is easy to occur when accidents occur in the elevator.
Disclosure of Invention
The embodiment of the application aims to provide an elevator monitoring method based on image recognition, which aims to solve the problem in the third part of the background technology.
The embodiment of the application is realized in such a way that an elevator monitoring method based on image recognition comprises the following steps:
acquiring a real-time elevator monitoring video, wherein a monitoring range contained in the real-time elevator monitoring video at least covers an elevator door and an elevator button area;
identifying an elevator button area in a real-time elevator monitoring video, determining the floor where the current elevator is located, and calculating the current floor through the elevator running time when the elevator button area is shielded;
object identification is carried out on the elevator door area, whether an obstacle affecting the closing of the elevator door exists or not is judged, and if the elevator door area is shielded, the elevator door area is regarded as an obstacle-free area;
after the elevator door is closed, continuously monitoring the elevator door area, and judging whether an object moves along a door gap in the elevator door area;
if the object moves along the door gap, an alarm is sent out and an emergency stop instruction is sent out to the elevator;
if an obstacle affecting the closing of the elevator is detected, a prompt voice is sent out, and an instruction for prohibiting the closing is sent out to the elevator.
Preferably, the step of calculating the current floor through the running time of the elevator specifically includes:
inquiring the floor where the elevator stops last time, and calling the time of closing the elevator door when the elevator continues to run at the floor, wherein the time is defined as starting time;
determining the time for opening an elevator door when an elevator reaches a current floor through a real-time elevator monitoring video, and defining the time as stopping time;
and calculating the running time according to the starting time and the stopping time, calculating the number of floors moved by the elevator in the running process according to the historical data, and determining the current floor of the elevator.
Preferably, the step of identifying the object in the elevator door area and judging whether there is an obstacle affecting the closing of the elevator door specifically includes:
extracting a picture of an elevator door area from a real-time elevator monitoring video, and carrying out gray processing on the picture;
carrying out linearization processing on the image after gray level processing, identifying elevator doors in the image after linearization, and judging whether lines between the elevator doors are continuous or not;
if the lines between the elevator doors are discontinuous, then an obstacle is considered to be present.
Preferably, after the elevator door is closed, the elevator door area is continuously monitored, and whether an object moves along the door gap in the elevator door area is judged, which specifically comprises the following steps:
the position of the elevator door is identified in real time, and after the elevator door is determined to be closed, the video of the elevator door area is analyzed in real time;
the method comprises the steps of extracting pictures from videos of an elevator door area, comparing two adjacent pictures, and comparing the changes of door seam positions in the two pictures;
when the position of the door gap is detected to be blocked and the blocked position is gradually raised, the object is determined to move along the door gap.
Preferably, in the step of sending out an alarm and sending out an emergency stop instruction to the elevator, the alarm content comprises words and voice prompts.
Preferably, when the obstacle is removed, the elevator door is permitted to close.
Another object of an embodiment of the present application is to provide an elevator monitoring system based on image recognition, the system including:
the data acquisition module is used for acquiring real-time elevator monitoring videos, and the monitoring range contained in the real-time elevator monitoring videos at least covers elevator doors and elevator button areas;
the elevator positioning module is used for identifying an elevator button area in the real-time elevator monitoring video, determining the floor where the current elevator is located, and calculating the current floor through the elevator running time when the elevator button area is shielded;
the obstacle detection module is used for carrying out object identification on the elevator door area, judging whether an obstacle affecting the door closing of the elevator exists or not, and if the elevator door area is shielded, the elevator door area is regarded as an obstacle-free area;
the operation monitoring module is used for continuously monitoring the elevator door area after the elevator door is closed and judging whether an object in the elevator door area moves along a door gap or not;
if the object moves along the door gap, an alarm is sent out and an emergency stop instruction is sent out to the elevator;
if an obstacle affecting the closing of the elevator is detected, a prompt voice is sent out, and an instruction for prohibiting the closing is sent out to the elevator.
Preferably, the elevator positioning module comprises:
the floor inquiry unit is used for inquiring the floor where the elevator stops last time and calling the time for closing the elevator door when the elevator continues to run at the floor, and the time is defined as starting time;
the stop timing unit is used for determining the time for opening the elevator door when the elevator reaches the current floor through the real-time elevator monitoring video, and the time is defined as the stop time;
and the time calculation unit is used for calculating the running time according to the starting time and the stopping time, calculating the number of floors moved by the elevator in the running process according to the historical data and determining the current floor of the elevator.
Preferably, the obstacle detection module includes:
the image processing unit is used for extracting a picture of the elevator door area from the real-time elevator monitoring video and carrying out gray processing on the picture;
and the obstacle recognition unit is used for carrying out linearization processing on the image after gray level processing, recognizing elevator doors in the image after linearization, judging whether lines between the elevator doors are continuous or not, and if the lines between the elevator doors are discontinuous, considering that an obstacle exists.
Preferably, the operation monitoring module includes:
the door closing identification unit is used for identifying the position of the elevator door in real time, and analyzing the video of the elevator door area in real time after determining that the elevator door is closed;
the picture comparison unit is used for extracting pictures of videos of the elevator door area, comparing two adjacent pictures and comparing the change of the door seam position in the two pictures;
and the real-time monitoring unit is used for judging that an object moves along the door gap when the position of the door gap is detected to be shielded and the shielded position is gradually raised.
According to the elevator monitoring method based on image recognition, whether the barrier exists or not can be judged by monitoring the elevator door area, and then after the door is closed, objects at the door gap can be monitored, so that the elevator door can be prevented from clamping the objects to run, and the safety of a user is protected to the greatest extent.
Drawings
Fig. 1 is a flowchart of an elevator monitoring method based on image recognition according to an embodiment of the present application;
fig. 2 is a flowchart of steps for calculating a current floor from an elevator run time provided by an embodiment of the present application;
fig. 3 is a flowchart of a step of identifying an object in an elevator door area and determining whether an obstacle affecting the closing of the elevator door exists according to an embodiment of the present application;
fig. 4 is a flowchart of steps for continuously monitoring an elevator door area after an elevator door provided by an embodiment of the present application is closed, and determining whether an object in the elevator door area moves along a door gap;
fig. 5 is a schematic diagram of an elevator monitoring system based on image recognition according to an embodiment of the present application;
fig. 6 is a schematic diagram of an elevator positioning module according to an embodiment of the present application;
fig. 7 is a schematic diagram of an obstacle detection module according to an embodiment of the present application;
fig. 8 is a schematic diagram of an operation monitoring module according to an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
It will be understood that the terms "first," "second," and the like, as used herein, may be used to describe various elements, but these elements are not limited by these terms unless otherwise specified. These terms are only used to distinguish one element from another element. For example, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script, without departing from the scope of this disclosure.
In the current buildings, elevators are basically provided, and in order to ensure the safety of the elevators, the elevators are correspondingly provided with monitoring devices, and in the background, the conditions in the elevators can be checked through the monitoring devices, so that the elevator is convenient and safe to use. However, the current monitoring device in the elevator can only play a role of recording, and cannot identify emergency events occurring in the elevator, so that danger is easy to occur when accidents occur in the elevator.
According to the application, whether the barrier exists or not can be judged by monitoring the elevator door area, and then, after the door is closed, objects at the door gap can be monitored to prevent the elevator door from clamping the objects to run, so that the safety of a user is protected to the greatest extent.
As shown in fig. 1, a flowchart of an elevator monitoring method based on image recognition according to an embodiment of the present application is provided, where the method includes:
s100, acquiring a real-time elevator monitoring video, wherein a monitoring range contained in the real-time elevator monitoring video at least covers an elevator door and an elevator button area.
In the step, a real-time elevator monitoring video is acquired, the number of passengers in a monitoring range is counted, the total number of passengers is determined, when the passenger is identified, the face identification is carried out on the passenger entering the elevator, the number of passengers entering the elevator is determined according to the number of passengers on the face, the load of the elevator is analyzed in real time, the number of passengers reduced is determined according to the change of the load of the elevator, and therefore the number of passengers in each time is determined; the elevator is characterized in that a monitoring device is arranged in each elevator, the monitoring device is used for shooting the situation in the elevator, the installation position of the monitoring device is away from the elevator door and shooting is carried out on the elevator door, so that the face is conveniently identified, in the elevator, two common abnormal situations are that sundries are located at the position of the elevator door, and the elevator door still can be closed because the size of the sundries and other barriers is small and are not easy to identify by the elevator, and the elevator door is extruded and is easy to be dangerous.
S200, identifying an elevator button area in the real-time elevator monitoring video, determining the floor where the current elevator is located, and calculating the current floor through the elevator running time when the elevator button area is shielded.
In this step, the elevator button area in the real-time elevator monitoring video is identified, the indication lamp which is lighted in the elevator button area is identified by utilizing the means of image identification, so that the current elevator stopping position is judged, because it is very important for a background manager to know the elevator position, once abnormal conditions occur, the rescue time can be shortened according to the elevator position to reach the corresponding place rapidly, and conditions are created for rescue, but in the elevator operation process, the elevator button area is always blocked, so that the condition that the elevator cannot be identified easily exists, and at this time, the elevator position can be determined by calculating according to the elevator operation speed and the elevator operation time.
S300, object identification is carried out on the elevator door area, whether an obstacle affecting the closing of the elevator door exists or not is judged, and if the elevator door area is shielded, the elevator door area is regarded as an obstacle-free area.
In the step, object identification is carried out on the elevator door area, namely whether sundries and the like exist at the position of the elevator door or not is judged by utilizing an image identification technology, when an obstacle exists, the elevator door is not allowed to be closed, the elevator is protected, the obstacle is also protected, the danger is avoided, and if the obstacle does not exist, normal closing can be carried out; when the obstacle is removed, the elevator door is permitted to close.
And S400, after the elevator door is closed, continuously monitoring the elevator door area to judge whether an object moves along the door gap in the elevator door area.
In the step, after the elevator door is closed, continuously monitoring the elevator door area, and monitoring the door seam position to judge whether an object moves along the door seam or not, wherein when sundries are clamped, the sundries are pulled up by a traction rope along with the rising of the elevator and climb along the position of the door seam, and when the object at the door seam position is monitored, the object is detected to be abnormal, even if a background person is notified, and the elevator stops running; in the step of sending out the alarm and sending out the emergency stop instruction to the elevator, the alarm content comprises characters and voice prompts.
As shown in fig. 2, as a preferred embodiment of the present application, the step of calculating the current floor by the elevator operation time specifically includes:
s201, inquiring the floor where the elevator stops last time, and calling the time when the elevator door is closed when the elevator continues to run at the floor, wherein the time is defined as starting time.
In this step, the floor where the elevator was last stopped is queried, and the current elevator stopping position needs to be determined every time the elevator stops, specifically, the determination can be performed by adopting an image recognition mode, and of course, the current elevator stopping position can also be directly obtained from the control equipment of the elevator, of course, the process is finished mainly by means of image recognition for the additionally installed monitoring equipment, and when the button area of the elevator is blocked, the time for closing the elevator door when the elevator continues to run on the floor is immediately called, and is defined as the starting time.
S202, determining the time when an elevator door is opened when the elevator reaches the current floor through real-time elevator monitoring videos, and defining the time as stopping time.
In the step, the time for opening the elevator door when the elevator reaches the current floor is determined through the real-time elevator monitoring video, namely, when the elevator reaches the floor where the elevator stops, the time for opening the elevator door is determined according to the opening time of the elevator door in the monitoring video, and the opening time of the elevator door is determined and defined as the stop time.
S203, calculating the running time according to the starting time and the stopping time, calculating the number of floors moved by the elevator in the running process according to the historical data, and determining the current floor of the elevator.
In this step, the difference between the starting time and the stopping time is calculated, that is, the time of the elevator running is known, and since the speed of the elevator running is known, it can be estimated according to the historical running time, for example, in the historical data, the time required for climbing two floors is 10 seconds, the time of terrible third floors is 15 seconds, so that the floor of the elevator running is estimated according to the current running time, and since the starting floor is already known, the floor of the elevator stopping at this time can be determined.
As shown in fig. 3, as a preferred embodiment of the present application, the step of performing object recognition on the elevator door area to determine whether there is an obstacle affecting the closing of the elevator door specifically includes:
s301, extracting a picture of an elevator door area from a real-time elevator monitoring video, and carrying out gray processing on the picture.
In the step, the picture of the elevator door area is extracted from the real-time elevator monitoring video, namely the video of the elevator door area in the real-time elevator monitoring video is singly cut out and converted into a picture frame by frame, and then gray processing is carried out on all the pictures to reduce the data processing amount.
S302, carrying out linearization processing on the image after gray level processing, identifying elevator doors in the image after linearization, judging whether lines between the elevator doors are continuous or not, and if the lines between the elevator doors are discontinuous, regarding that an obstacle exists.
In this step, the image after the gradation processing is subjected to the linearization processing, and the image is converted into an image mainly composed of lines, and since the elevator door is composed of lines, the edges of the bottom of the elevator are also composed of lines, and therefore, whether an obstacle exists can be judged according to the continuity of the lines.
As shown in fig. 4, as a preferred embodiment of the present application, after the elevator door is closed, the step of continuously monitoring the elevator door area to determine whether there is an object moving along the door gap in the elevator door area specifically includes:
s401, identifying the position of the elevator door in real time, and analyzing videos of the elevator door area in real time after determining that the elevator door is closed.
S402, extracting pictures of videos of the elevator door area, comparing two adjacent pictures, and comparing the changes of the door seam positions in the two pictures.
In the step, whether the elevator door is in a closed state is judged through image recognition, when the elevator door is closed, picture extraction is started to video of an elevator door area, then whether an object in the video rises along a door gap is analyzed, and in the step, the process can be completed through image comparison, namely, two adjacent picture frames in the video are compared, so that the trend of the object is analyzed.
S403, when the position of the door gap is detected to be blocked and the blocked position is gradually raised, determining that an object moves along the door gap.
In this step, when an object is detected to rise along the door seam, it is indicated that there is an object stuck between the elevator doors, braking needs to be performed in time, and relevant personnel are notified to check and process.
As shown in fig. 5, an elevator monitoring system based on image recognition according to an embodiment of the present application includes:
the data acquisition module 100 is configured to acquire a real-time elevator monitoring video, where a monitoring range included in the real-time elevator monitoring video at least covers an elevator door and an elevator button area.
In the system, a data acquisition module 100 acquires a real-time elevator monitoring video, counts the number of passengers in a monitoring range, determines the total number of passengers, performs face recognition on the number of passengers entering an elevator during recognition, determines the number of passengers entering the elevator according to the number of passengers on the face, performs real-time analysis on the load of the elevator, and determines the number of passengers reduced according to the change of the load of the elevator, thereby determining the number of passengers each time; the elevator is characterized in that a monitoring device is arranged in each elevator, the monitoring device is used for shooting the situation in the elevator, the installation position of the monitoring device is away from the elevator door and shooting is carried out on the elevator door, so that the face is conveniently identified, in the elevator, two common abnormal situations are that sundries are located at the position of the elevator door, and the elevator door still can be closed because the size of the sundries and other barriers is small and are not easy to identify by the elevator, and the elevator door is extruded and is easy to be dangerous.
The elevator positioning module 200 is configured to identify an elevator button area in a real-time elevator monitoring video, determine a floor where a current elevator is located, and calculate the current floor through elevator running time when the elevator button area is blocked.
In the system, the elevator positioning module 200 identifies the elevator button area in the real-time elevator monitoring video, and identifies the indication lamp which is lighted in the elevator button area by utilizing the means of image identification, so that the current elevator stopping position is judged, because it is very important for a background manager to know the elevator position, once abnormal conditions occur, the elevator can rapidly reach the corresponding place according to the elevator position, the rescue time can be shortened, conditions are created for rescue, but in the elevator operation process, the elevator button area is always shielded, so that the condition that the elevator cannot be identified easily exists, and at the moment, the elevator position can be determined by calculating according to the elevator operation speed and the elevator operation time.
The obstacle detection module 300 is configured to perform object recognition on the elevator door area, determine whether an obstacle affecting the door closing of the elevator exists, and consider that there is no obstacle if the elevator door area is blocked.
In the system, the obstacle detection module 300 performs object recognition on the elevator door area, namely, whether sundries exist at the position of the elevator door or not is judged by utilizing an image recognition technology, if an obstacle exists, the elevator door is not allowed to be closed, the elevator is protected, the obstacle is also protected, the danger is avoided, and if no obstacle exists, normal closing can be performed; when the obstacle is removed, the elevator door is permitted to close.
The operation monitoring module 400 is configured to continuously monitor the elevator door area after the elevator door is closed, and determine whether an object in the elevator door area moves along the door gap.
In the system, the operation monitoring module 400 continuously monitors the elevator door area after the elevator door is closed, monitors the door seam position to judge whether an object moves along the door seam, because when sundries are clamped, the sundries are pulled up by a traction rope along with the rising of the elevator and climb along the position of the door seam, and when the object at the door seam position is detected to move, the object is regarded as abnormal, even if a background person is informed, and the elevator stops operating; in the step of sending out the alarm and sending out the emergency stop instruction to the elevator, the alarm content comprises characters and voice prompts.
As shown in fig. 6, as a preferred embodiment of the present application, the elevator positioning module 200 includes:
the floor inquiry unit 201 is configured to inquire the floor where the elevator was stopped last time, and call the time when the elevator door is closed when the elevator continues to run at the floor, which is defined as the start time.
In this module, the floor inquiry unit 201 inquires the floor where the elevator was stopped last time, and when the elevator stops each time, the current elevator stopping position needs to be determined, specifically, the current elevator stopping position can be determined by adopting an image recognition mode, and of course, the current elevator stopping position can also be directly obtained from the control device of the elevator, and of course, for the additionally installed monitoring device, the above process is finished mainly by means of image recognition, when the button area of the elevator is blocked, the time for closing the elevator door when the elevator continues to run on the floor is immediately called, and the starting time is defined.
A stop timing unit 202 is used for determining the time when the elevator door is opened when the elevator reaches the current floor through real-time elevator monitoring video, and the time is defined as the stop time.
In this module, the stop timing unit 202 determines, through the real-time elevator monitoring video, the time when the elevator door is opened when the elevator reaches the current floor, that is, when the elevator reaches the floor where the elevator stops, determining according to the opening time of the elevator door in the monitoring video, and determining the opening time of the elevator door, which is defined as the stop time.
The time calculating unit 203 is configured to calculate an operation time according to the start time and the stop time, calculate the number of floors moved by the elevator in the current operation according to the history data, and determine the current floor where the elevator is located.
In this module, the time calculation unit 203 calculates the difference between the start time and the stop time, that is, the time of the current elevator operation, and since the speed of the elevator operation is known, it is of course also possible to calculate according to the historical operation time, for example, in the historical data, the time required for climbing two floors is 10 seconds, the time of terrible three floors is 15 seconds, so that the floor moved this time is calculated according to the current operation time, and since the start floor is already known, the floor stopped this time can be determined.
As shown in fig. 7, as a preferred embodiment of the present application, the obstacle detection module 300 includes:
the image processing unit 301 is configured to extract a picture of an elevator door region from a real-time elevator monitoring video, and perform gray-scale processing on the picture.
In this module, the image processing unit 301 extracts the picture of the elevator door area from the real-time elevator monitoring video, that is, the video of the elevator door area in the real-time elevator monitoring video is individually cut out and converted into a picture of one frame by one frame, and then gray-scale processing is performed on all the pictures to reduce the data processing amount.
The obstacle recognition unit 302 is configured to perform a linearization process on the image after the gray-scale process, recognize elevator doors in the image after the linearization, determine whether lines between the elevator doors are continuous, and consider that an obstacle exists if the lines between the elevator doors are discontinuous.
In this module, the obstacle recognition unit 302 performs the linearization processing on the image after the gray processing, and the image is converted into a picture mainly including lines, and since the elevator door is composed of lines, the edges of the bottom of the elevator are also composed of lines, so that whether an obstacle exists can be determined according to the continuity of the lines.
As shown in fig. 8, as a preferred embodiment of the present application, the operation monitoring module 400 includes:
the door closing recognition unit 401 is configured to recognize the position of the elevator door in real time, and analyze the video of the elevator door area in real time after determining that the elevator door is closed.
In this module, the door closing recognition unit 401 determines whether the elevator door is in a closed state by image recognition, when the elevator door is closed, it starts to extract the picture of the video of the elevator door area, and then analyzes whether there is an object in the video rising along the door gap.
The picture comparison unit 402 is configured to extract a picture of the video of the elevator door region, compare two adjacent pictures, and compare the change of the door seam position in the two pictures.
And the real-time monitoring unit 403 is configured to determine that an object moves along the door gap when the door gap is detected to be blocked and the blocked position gradually rises.
In the module, when an object is detected to rise along a door seam, namely that the object is clamped between elevator doors, the elevator door is required to be braked in time, and related personnel are informed to check and process.
It should be understood that, although the steps in the flowcharts of the embodiments of the present application are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in various embodiments may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
Those skilled in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by a computer program for instructing relevant hardware, where the program may be stored in a non-volatile computer readable storage medium, and where the program, when executed, may include processes in the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
The foregoing description of the preferred embodiments of the application is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the application.
Claims (8)
1. An elevator monitoring method based on image recognition, the method comprising:
acquiring a real-time elevator monitoring video, wherein a monitoring range contained in the real-time elevator monitoring video at least covers an elevator door and an elevator button area;
identifying an elevator button area in a real-time elevator monitoring video, determining the floor where the current elevator is located, and calculating the current floor through the elevator running time when the elevator button area is shielded;
object identification is carried out on the elevator door area, whether an obstacle affecting the closing of the elevator door exists or not is judged, and if the elevator door area is shielded, the elevator door area is regarded as an obstacle-free area;
after the elevator door is closed, continuously monitoring the elevator door area, and judging whether an object moves along a door gap in the elevator door area;
if the object moves along the door gap, an alarm is sent out and an emergency stop instruction is sent out to the elevator;
if an obstacle affecting the closing of the elevator is detected, a prompt voice is sent out, and an instruction for prohibiting the closing is sent out to the elevator;
after the elevator door is closed, continuously monitoring the elevator door area, and judging whether an object moves along a door gap in the elevator door area or not, wherein the method specifically comprises the following steps:
the position of the elevator door is identified in real time, and after the elevator door is determined to be closed, the video of the elevator door area is analyzed in real time;
the method comprises the steps of extracting pictures from videos of an elevator door area, comparing two adjacent pictures, and comparing the changes of door seam positions in the two pictures;
when the position of the door gap is detected to be blocked and the blocked position is gradually raised, the object is determined to move along the door gap.
2. The elevator monitoring method based on image recognition according to claim 1, wherein the step of calculating the current floor by the elevator operation time specifically comprises:
inquiring the floor where the elevator stops last time, and calling the time of closing the elevator door when the elevator continues to run at the floor, wherein the time is defined as starting time;
determining the time for opening an elevator door when an elevator reaches a current floor through a real-time elevator monitoring video, and defining the time as stopping time;
and calculating the running time according to the starting time and the stopping time, calculating the number of floors moved by the elevator in the running process according to the historical data, and determining the current floor of the elevator.
3. The method for monitoring an elevator based on image recognition according to claim 1, wherein the step of performing object recognition on an elevator door area to determine whether an obstacle affecting the closing of the elevator door exists comprises:
extracting a picture of an elevator door area from a real-time elevator monitoring video, and carrying out gray processing on the picture;
and carrying out linearization processing on the image after gray level processing, identifying elevator doors in the image after linearization, judging whether lines between the elevator doors are continuous, and if the lines between the elevator doors are discontinuous, regarding that an obstacle exists.
4. The elevator monitoring method based on image recognition according to claim 1, wherein in the step of issuing an alarm and giving an emergency stop instruction to the elevator, the alarm content includes text and voice prompts.
5. The image recognition-based elevator monitoring method of claim 1, wherein the obstacle is removed, permitting the elevator door to be closed.
6. An elevator monitoring system based on image recognition, the system comprising:
the data acquisition module is used for acquiring real-time elevator monitoring videos, and the monitoring range contained in the real-time elevator monitoring videos at least covers elevator doors and elevator button areas;
the elevator positioning module is used for identifying an elevator button area in the real-time elevator monitoring video, determining the floor where the current elevator is located, and calculating the current floor through the elevator running time when the elevator button area is shielded;
the obstacle detection module is used for carrying out object identification on the elevator door area, judging whether an obstacle affecting the door closing of the elevator exists or not, and if the elevator door area is shielded, the elevator door area is regarded as an obstacle-free area;
the operation monitoring module is used for continuously monitoring the elevator door area after the elevator door is closed and judging whether an object in the elevator door area moves along a door gap or not;
if the object moves along the door gap, an alarm is sent out and an emergency stop instruction is sent out to the elevator;
if an obstacle affecting the closing of the elevator is detected, a prompt voice is sent out, and an instruction for prohibiting the closing is sent out to the elevator;
the operation monitoring module includes:
the door closing identification unit is used for identifying the position of the elevator door in real time, and analyzing the video of the elevator door area in real time after determining that the elevator door is closed;
the picture comparison unit is used for extracting pictures of videos of the elevator door area, comparing two adjacent pictures and comparing the change of the door seam position in the two pictures;
and the real-time monitoring unit is used for judging that an object moves along the door gap when the position of the door gap is detected to be shielded and the shielded position is gradually raised.
7. The image recognition-based elevator monitoring system of claim 6, wherein the elevator positioning module comprises:
the floor inquiry unit is used for inquiring the floor where the elevator stops last time and calling the time for closing the elevator door when the elevator continues to run at the floor, and the time is defined as starting time;
the stop timing unit is used for determining the time for opening the elevator door when the elevator reaches the current floor through the real-time elevator monitoring video, and the time is defined as the stop time;
and the time calculation unit is used for calculating the running time according to the starting time and the stopping time, calculating the number of floors moved by the elevator in the running process according to the historical data and determining the current floor of the elevator.
8. The image recognition-based elevator monitoring system of claim 6, wherein the obstacle detection module comprises:
the image processing unit is used for extracting a picture of the elevator door area from the real-time elevator monitoring video and carrying out gray processing on the picture;
and the obstacle recognition unit is used for carrying out linearization processing on the image after gray level processing, recognizing elevator doors in the image after linearization, judging whether lines between the elevator doors are continuous or not, and if the lines between the elevator doors are discontinuous, considering that an obstacle exists.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210411488.1A CN114735559B (en) | 2022-04-19 | 2022-04-19 | Elevator monitoring system and method based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210411488.1A CN114735559B (en) | 2022-04-19 | 2022-04-19 | Elevator monitoring system and method based on image recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114735559A CN114735559A (en) | 2022-07-12 |
| CN114735559B true CN114735559B (en) | 2023-10-31 |
Family
ID=82280910
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210411488.1A Active CN114735559B (en) | 2022-04-19 | 2022-04-19 | Elevator monitoring system and method based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114735559B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1179585A (en) * | 1997-09-09 | 1999-03-23 | Hitachi Ltd | Elevator car position detecting device |
| DE10017333A1 (en) * | 2000-04-07 | 2001-10-18 | Pilz Gmbh & Co | Protective device for safeguarding a dangerous area and method for checking its functional safety has an image capture unit with an image sensor containing multiple light-sensitive image points. |
| JP2009051615A (en) * | 2007-08-27 | 2009-03-12 | Mitsubishi Electric Building Techno Service Co Ltd | Elevator device |
| JP2009113932A (en) * | 2007-11-07 | 2009-05-28 | Mitsubishi Electric Corp | Entrance/exit device of elevator |
| JP2011093702A (en) * | 2009-11-02 | 2011-05-12 | Toshiba Elevator Co Ltd | Object caught-in detecting system of elevator |
| JP2012176837A (en) * | 2011-02-28 | 2012-09-13 | Hitachi Ltd | Elevator |
| JP6081555B1 (en) * | 2015-11-11 | 2017-02-15 | 東芝エレベータ株式会社 | Elevator control device that can carry pets |
| CN106966278A (en) * | 2016-01-13 | 2017-07-21 | 东芝电梯株式会社 | The seating detecting system of elevator |
| CN206367970U (en) * | 2017-01-04 | 2017-08-01 | 樱花电梯（中山）有限公司 | A kind of elevator anti-pinch device |
| KR101929838B1 (en) * | 2017-07-14 | 2018-12-17 | 전남대학교산학협력단 | A safety elevator equipped with a device for sensing the insertion of a pet's neck collar |
| CN110002305A (en) * | 2018-12-25 | 2019-07-12 | 浙江新再灵科技股份有限公司 | A kind of elevator door suture detection method and system based on computer vision technique |
| CN110745675A (en) * | 2019-10-17 | 2020-02-04 | 宁波微科光电股份有限公司 | Elevator protection method based on TOF camera |
| CN112850396A (en) * | 2019-11-28 | 2021-05-28 | 宁波微科光电股份有限公司 | Elevator foreign matter detection method and system, computer storage medium and elevator |
| CN113291944A (en) * | 2021-05-21 | 2021-08-24 | 南京喜诗图家具有限公司 | Pet safety protection equipment is used to elevator |
| CN114022767A (en) * | 2021-11-04 | 2022-02-08 | 上海擎朗智能科技有限公司 | Elevator floor positioning method and device, terminal equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1345444B1 (en) * | 2002-03-11 | 2006-03-01 | Inventio Ag | Video survielance system with 3d CCD image sensor and infra red light source |
| WO2007138688A1 (en) * | 2006-05-31 | 2007-12-06 | Mitsubishi Electric Corporation | Slide door device and elevator |
-
2022
- 2022-04-19 CN CN202210411488.1A patent/CN114735559B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1179585A (en) * | 1997-09-09 | 1999-03-23 | Hitachi Ltd | Elevator car position detecting device |
| DE10017333A1 (en) * | 2000-04-07 | 2001-10-18 | Pilz Gmbh & Co | Protective device for safeguarding a dangerous area and method for checking its functional safety has an image capture unit with an image sensor containing multiple light-sensitive image points. |
| JP2009051615A (en) * | 2007-08-27 | 2009-03-12 | Mitsubishi Electric Building Techno Service Co Ltd | Elevator device |
| JP2009113932A (en) * | 2007-11-07 | 2009-05-28 | Mitsubishi Electric Corp | Entrance/exit device of elevator |
| JP2011093702A (en) * | 2009-11-02 | 2011-05-12 | Toshiba Elevator Co Ltd | Object caught-in detecting system of elevator |
| JP2012176837A (en) * | 2011-02-28 | 2012-09-13 | Hitachi Ltd | Elevator |
| JP6081555B1 (en) * | 2015-11-11 | 2017-02-15 | 東芝エレベータ株式会社 | Elevator control device that can carry pets |
| CN106966278A (en) * | 2016-01-13 | 2017-07-21 | 东芝电梯株式会社 | The seating detecting system of elevator |
| CN206367970U (en) * | 2017-01-04 | 2017-08-01 | 樱花电梯（中山）有限公司 | A kind of elevator anti-pinch device |
| KR101929838B1 (en) * | 2017-07-14 | 2018-12-17 | 전남대학교산학협력단 | A safety elevator equipped with a device for sensing the insertion of a pet's neck collar |
| CN110002305A (en) * | 2018-12-25 | 2019-07-12 | 浙江新再灵科技股份有限公司 | A kind of elevator door suture detection method and system based on computer vision technique |
| CN110745675A (en) * | 2019-10-17 | 2020-02-04 | 宁波微科光电股份有限公司 | Elevator protection method based on TOF camera |
| CN112850396A (en) * | 2019-11-28 | 2021-05-28 | 宁波微科光电股份有限公司 | Elevator foreign matter detection method and system, computer storage medium and elevator |
| CN113291944A (en) * | 2021-05-21 | 2021-08-24 | 南京喜诗图家具有限公司 | Pet safety protection equipment is used to elevator |
| CN114022767A (en) * | 2021-11-04 | 2022-02-08 | 上海擎朗智能科技有限公司 | Elevator floor positioning method and device, terminal equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114735559A (en) | 2022-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107539855B (en) | The detection method and system of Elevator landing failure | |
| US20190359451A1 (en) | Elevator door monitoring system, elevator system and elevator door monitoring method | |
| CN110830765A (en) | Gate control method, system, gate, computer device and storage medium | |
| KR102477061B1 (en) | Apparatus and method for monitoring vehicle in parking lot | |
| EP3527525A1 (en) | Elevator door control system for detection of obstacle trapping | |
| CN112743549A (en) | Robot control method, system, robot and program product | |
| CN108147246B (en) | Elevator safety monitoring method, device, system and medium | |
| CN107464416B (en) | Semi-automatic driving method and system for bus | |
| CN109019225B (en) | Detection method and system for early warning of door closing risk of abnormally blocked elevator | |
| CN110930569B (en) | Security check control method and system | |
| US20140266683A1 (en) | System and method of anomaly detection | |
| JP2013107749A (en) | Elevator security system | |
| CN110127477B (en) | Elevator control method and device based on pit accumulated water and computer equipment | |
| CN112357707B (en) | Elevator detection method and device, robot and storage medium | |
| CN114735559B (en) | Elevator monitoring system and method based on image recognition | |
| CN110697529A (en) | Method and device for detecting trapping of elevator and computer equipment | |
| CN112885013A (en) | Monitoring and early warning method and device and readable storage medium | |
| CN112349015A (en) | Shelter management and control system and method based on Internet of things | |
| CN105608773B (en) | A kind of entrance vehicle fast passing methods, devices and systems | |
| CN109779445B (en) | Fire door control method and device, computer equipment and storage medium | |
| CN112597950A (en) | Safety monitoring method and device for mechanical equipment | |
| CN117172970A (en) | Wisdom property management platform | |
| CN114701934B (en) | Security control method, device and system for elevator, cloud platform and storage medium | |
| CN116128169A (en) | Multisystem linkage control method and device for intelligent transportation | |
| KR101504607B1 (en) | Elevator safety management system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |