CN113723349A - Elevator real-time monitoring method, device, system and server - Google Patents
Elevator real-time monitoring method, device, system and server Download PDFInfo
- Publication number
- CN113723349A CN113723349A CN202111060093.3A CN202111060093A CN113723349A CN 113723349 A CN113723349 A CN 113723349A CN 202111060093 A CN202111060093 A CN 202111060093A CN 113723349 A CN113723349 A CN 113723349A
- Authority
- CN
- China
- Prior art keywords
- video analysis
- video stream
- server
- algorithm
- video
- 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.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The present disclosure provides a method, a device, a system and a server for elevator real-time monitoring, wherein the method comprises the following steps: acquiring a video stream sent by at least one camera device through a local area network, and determining a target video analysis algorithm corresponding to the video stream; and analyzing the video stream based on the target video analysis algorithm to obtain a video analysis result. The embodiment of the disclosure can reduce the cost of video streaming.
Description
Technical Field
The invention relates to the technical field of monitoring, in particular to a method, a device and a system for monitoring an elevator in real time and a server.
Background
With the development of economic technology, the use of elevators has become widespread. If an accident occurs, the elevator can have serious consequences and even cause casualties, so that the safe operation of the elevator is more and more emphasized. At present, a monitoring camera is arranged in an elevator, video stream of the monitoring camera is transmitted to a server through a wide area network, and the server analyzes the video stream. Since the video stream occupies a large bandwidth, the cost of transmitting the video stream over the wide area network is high.
Disclosure of Invention
The embodiment of the disclosure provides a real-time elevator monitoring method, a real-time elevator monitoring device, a real-time elevator monitoring system and a real-time elevator monitoring server, and aims to solve the problem that in the prior art, the cost of transmitting video streams through a wide area network is high.
In order to solve the technical problem, the invention is realized as follows:
in a first aspect, an embodiment of the present disclosure provides a method for monitoring an elevator in real time, where the method includes:
acquiring a video stream sent by at least one camera device through a local area network, and determining a target video analysis algorithm corresponding to the video stream;
and analyzing the video stream based on the target video analysis algorithm to obtain a video analysis result.
In a second aspect, an embodiment of the present disclosure provides an elevator real-time monitoring system, which includes at least one camera device for monitoring an elevator, a first server communicatively connected to the at least one camera device via a local area network, a client communicatively connected to the first server via the local area network, and a second server communicatively connected to the first server via a wide area network, where:
the first server is used for acquiring a video stream sent by the at least one camera device through the local area network, sending the video stream to the client, and determining a target video analysis algorithm corresponding to the video stream;
the first server is used for analyzing the video stream based on the target video analysis algorithm to obtain a video analysis result, and sending the video analysis result to the second server and the client.
In a third aspect, an embodiment of the present disclosure provides an elevator real-time monitoring apparatus, where the apparatus includes:
the system comprises a determining module, a processing module and a processing module, wherein the determining module is used for acquiring a video stream sent by at least one camera device through a local area network and determining a target video analysis algorithm corresponding to the video stream;
and the analysis module is used for analyzing the video stream based on the target video analysis algorithm to obtain a video analysis result.
In a fourth aspect, an embodiment of the present disclosure provides a server, where the server is a first server, and includes: a memory, a processor and a program stored on the memory and executable on the processor, which program, when executed by the processor, carries out the steps in the method for real-time monitoring of an elevator according to the first aspect.
In a fifth aspect, the disclosed embodiments provide a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps in the elevator real-time monitoring method according to the first aspect.
In the embodiment of the disclosure, a video stream sent by at least one camera device is obtained through a local area network, and a target video analysis algorithm corresponding to the video stream is determined; and analyzing the video stream based on the target video analysis algorithm to obtain a video analysis result. Therefore, the video stream of the camera equipment is acquired through the local area network, the transmission of the video stream is fast and stable, and the cost of the video stream transmission can be reduced; and the video stream is analyzed through a target video analysis algorithm corresponding to the video stream, so that the accuracy of video analysis can be improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings needed to be used in the description of the embodiments of the present disclosure will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a flowchart of a method for monitoring an elevator in real time according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of an elevator real-time monitoring system provided by an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an elevator real-time monitoring device provided by an embodiment of the invention;
fig. 4 is a schematic structural diagram of a server according to an embodiment of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are some, not all, embodiments of the present disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a flowchart of a real-time elevator monitoring method according to an embodiment of the present disclosure, as shown in fig. 1, including the following steps:
Wherein the at least one camera device may be distributed in different elevators or may be distributed in the same elevator. The camera device can be used for monitoring the elevator.
In addition, the determining a target video analysis algorithm corresponding to the video stream may include: determining a target object type of an object included in the video stream; determining a target video analysis algorithm corresponding to the target object type from a plurality of video analysis algorithms, the plurality of video analysis algorithms corresponding to a plurality of object types one-to-one, the plurality of object types including the target object type; alternatively, the determining a target video analysis algorithm corresponding to the video stream may include: and receiving a target video analysis algorithm which is sent by the client and used for carrying out video analysis on the video stream.
And 102, analyzing the video stream based on the target video analysis algorithm to obtain a video analysis result.
Wherein the elevator real-time monitoring method can be applied to the first server. The elevator real-time monitoring system may comprise said first server. The elevator real-time monitoring system can comprise at least one camera device for monitoring an elevator, a first server in communication connection with the at least one camera device through a local area network, a client in communication connection with the first server through the local area network, and a second server in communication connection with the first server through a wide area network. The first server may send the video stream to the client over the local area network in real-time and send the video analysis results to the second server over the wide area network. Further, in a time period with a better network state or a smaller number of people using the network, the first server may send the stored video stream to the second server for backup storage through the wide area network.
In addition, taking a target video analysis algorithm as a motion detection algorithm as an example, the video analysis result may include an alarm picture and/or an alarm video; taking the target video analysis algorithm as an algorithm for comparing target objects as an example, the video analysis result may include a video stream including a preset duration of the target object.
It should be noted that, at present, transmitting the monitoring video through the wan for analysis may occupy a large amount of network resources, is relatively high in cost, and is easily affected by the network states of both the sending and receiving parties, and when the network state of the sending party or the receiving party is relatively poor, the real-time performance may be relatively poor. In the embodiment, the video stream of the camera equipment is acquired through the local area network, the video stream transmission is fast and stable, the cost of the video stream transmission can be reduced, and the problem of poor real-time performance caused by network faults is avoided; moreover, the system is convenient to maintain by privatizing deployment of the local area network.
In the embodiment of the disclosure, a video stream sent by at least one camera device is obtained through a local area network, and a target video analysis algorithm corresponding to the video stream is determined; and analyzing the video stream based on the target video analysis algorithm to obtain a video analysis result. Therefore, the video stream of the camera equipment is acquired through the local area network, the transmission of the video stream is fast and stable, and the cost of the video stream transmission can be reduced; and the video stream is analyzed through a target video analysis algorithm corresponding to the video stream, so that the accuracy of video analysis can be improved.
Optionally, after analyzing the video stream based on the target video analysis algorithm, the method may further include:
and sending the video analysis result to a second server through a wide area network.
The second server can be a cloud server, the storage space of the cloud server is large, and the storage resources occupied by the video analysis results are far smaller than the video stream, so that a large number of video analysis results can be stored through the cloud server, and long-time events can be traced conveniently.
In addition, the first server may also transmit a video stream of the at least one image pickup apparatus to the second server through the wide area network.
In the embodiment, the video analysis result is sent to the second server through the wide area network, so that the video analysis result can be stored through the second server, the video analysis result occupies a smaller bandwidth, and the cost of wide area network transmission can be reduced; and the video analysis result can be stored for a longer time through the second server.
Optionally, the analyzing the video stream based on the target video analysis algorithm includes:
and searching the target object in the video stream under the condition that the target video analysis algorithm is an algorithm for target object comparison.
Wherein the object type of the target object may include at least one of: human face, battery car, animal, fighting behavior, flame. If the type of the target object is a human face, the target video analysis algorithm can be an algorithm for comparing the human faces of related personnel and can also be an algorithm for monitoring whether the elevator taking personnel get the frame or not, so that whether the related personnel exist in the elevator or not and whether the frame-taking action exists or not can be monitored in real time; if the type of the target object is the battery car, the target video analysis algorithm can be an algorithm for comparing the battery cars, so that whether the battery cars enter the elevator can be monitored in real time; if the type of the target object is an animal, the target video analysis algorithm can be an algorithm for comparing the animal, so that whether a pet enters the elevator or not can be monitored in real time; if the type of the target object is flame, the target video analysis algorithm can be an algorithm for flame comparison, so that whether a fire occurs in the elevator can be monitored in real time.
It should be noted that, in the face comparison scenario related to the embodiment of the present disclosure, an obvious identifier needs to be set in a public area, for example, an elevator, so as to identify that the public area is provided with a monitoring device for face comparison, and the monitoring device arranged in the public area is used for maintaining public safety.
In addition, in the case that the target video analysis algorithm is an algorithm for flame comparison, the target video analysis algorithm may be an algorithm for detecting a smoke feature or a bright fire brightness feature, and when the smoke feature or the bright fire brightness feature is detected, it may be considered that a flame is detected. Under the condition that the target video analysis algorithm is used for monitoring whether the elevator taking personnel get the elevator or not, if the target video analysis algorithm detects that the bodies of the two elevator taking personnel are contacted for multiple times within the preset contact duration and/or the moving speed of the arms of the elevator taking personnel is greater than the preset speed, the elevator taking personnel can be considered to have the behavior of getting the elevator. For example, the arms of two elevator passengers are contacted for multiple times within the preset contact time and the moving speed of the arm of at least one elevator passenger is greater than the preset speed, it can be considered that the elevator passengers have a fighting behavior, and the preset contact time may be a shorter time, for example, 10s, 30s, or 5min, and the like.
In the embodiment, under the condition that the target video analysis algorithm is an algorithm for comparing target objects, the target objects are searched in the video stream, so that whether people taking the elevator get on the shelf or not, whether related people exist in the elevator or not, whether a battery car enters the elevator or not, whether pets enter the elevator or whether fire occurs in the elevator or not can be monitored.
Optionally, the determining a target video analysis algorithm corresponding to the video stream includes:
determining a target object type of an object included in the video stream;
determining a target video analysis algorithm corresponding to the target object type from a plurality of video analysis algorithms, the plurality of video analysis algorithms corresponding to a plurality of object types one-to-one, the plurality of object types including the target object type.
The object types can include human faces, battery cars, animals, fighting behaviors or flames, and the like. The video analysis algorithm may be expressed in the form of a neural network model, and the first server may store model parameters of a plurality of neural network models, and the plurality of neural network models may correspond to a plurality of the object types one to one, for example, the plurality of neural network models may include a neural network model for comparing faces of related persons, a neural network model for comparing battery cars, a neural network model for comparing animals, a neural network model for monitoring whether persons on an elevator ride fight, and a neural network model for comparing flames. The first server can analyze the target object type of the object in the video stream through the neural network model for determining the object type, and determine the neural network model corresponding to the target object type to perform video analysis on the video stream, so that the accuracy of video analysis can be improved.
It should be noted that, when the video stream includes at least two object types, the video stream may be respectively input into the neural network models corresponding to the at least two object types, and video analysis may be respectively performed.
In this embodiment, a target object type of an object included in the video stream is determined; determining a target video analysis algorithm corresponding to the target object type from a plurality of video analysis algorithms, the plurality of video analysis algorithms corresponding to a plurality of object types one-to-one, the plurality of object types including the target object type. Therefore, the target object can be compared by adopting a target video analysis algorithm corresponding to the type of the target object, and the accuracy of comparison of the target object is higher.
Optionally, the determining a target object type of an object included in the video stream includes:
performing video analysis according to a general video analysis algorithm for judging the object type to obtain the target object type of the object included in the video stream;
analyzing the video stream based on the target video analysis algorithm to obtain a video analysis result, wherein the video analysis result comprises:
and under the condition that the target object types are multiple, analyzing the video stream by adopting a plurality of target video analysis algorithms which are in one-to-one correspondence with the target object types to obtain a plurality of video analysis results.
The video analysis algorithm can be expressed in the form of a neural network model, the general video analysis algorithm can be a general video analysis model, and the video stream can be input into the general video analysis model for video analysis to obtain the target object type of the object included in the video stream. For example, the general video analysis model may output a probability value of an object type of an object included in the video stream, and an object type having a probability value greater than a preset threshold may be determined as the target object type. The preset threshold may be 50%, 70%, 85%, etc. For example, if the preset threshold is 70%, the probability value of the object type of the object included in the video stream being a human face is 80%, the probability value of the object type being an animal is 90%, and the probability value of the object type being an electric vehicle is 20%, the target object type may include a person and an animal.
In one embodiment, the target object types can include faces, battery cars and animals, the target video analysis algorithms can be algorithms for comparing the faces of related people, algorithms for comparing the battery cars and algorithms for comparing the animals, and the target video analysis algorithms can be adopted to analyze video streams respectively, so that whether related people exist in an elevator or not can be monitored in real time, whether the battery cars enter the elevator or not can be monitored in real time, and whether pets enter the elevator or not can be monitored in real time.
In this embodiment, the video stream is analyzed by using a plurality of target video analysis algorithms corresponding to the plurality of target object types one to one, so that missing of analysis objects can be avoided, and accuracy of comparison of the target objects can be further improved.
Optionally, the method may further include:
and sending the video analysis result and the video stream of the at least one camera device to a client through the local area network.
The client and the first server can be connected through a local area network.
In this embodiment, the video analysis result and the video stream of the at least one image pickup device are sent to the client through the local area network, so that the client can obtain the video analysis result in real time, and the client can watch the video stream in real time, the video stream transmission is fast and stable, and the cost of the video stream transmission can be reduced.
Optionally, the method further includes:
sending the video analysis result to a second server through a wide area network;
and sending alarm information, the video analysis result and the video stream of the at least one camera device to a client through the local area network.
In this embodiment, the video analysis result is sent to the second server via the wide area network, and the video analysis result can be stored for a long time by the second server; the local area network sends the warning information, the video analysis result and the video stream of the at least one camera device to the client, so that warning can be timely given to staff at the client side, the client acquires the video stream through the local area network, the video stream transmission is rapid and stable, and the cost of the video stream transmission can be reduced
Optionally, after the target object is found in the video stream, the method may further include:
if the target object is found, sending a video stream containing the preset time length of the target object to a second server through a wide area network, and sending alarm information and the video stream containing the preset time length of the target object to a client through the local area network;
wherein the video analysis result comprises a video stream containing a preset duration of the target object.
In addition, the preset time length can be 1min, 3min or 5min, and the like, and can be set according to actual requirements.
In the embodiment, the video stream containing the preset time length of the target object is sent to the second server through the wide area network, and the warning information and the video stream containing the preset time length of the target object are sent to the client through the local area network, so that a warning can be given to a worker at the client side in time to prompt the worker to pay attention to the target object; and the alert related video stream can be stored by the second server.
The embodiment of the present disclosure further provides an elevator real-time monitoring system, where the elevator real-time monitoring system includes at least one camera device for monitoring an elevator, a first server communicatively connected to the at least one camera device through a local area network, a client communicatively connected to the first server through the local area network, and a second server communicatively connected to the first server through a wide area network, where:
the first server is used for acquiring a video stream sent by the at least one camera device through the local area network, sending the video stream to the client, and determining a target video analysis algorithm corresponding to the video stream;
the first server is used for analyzing the video stream based on the target video analysis algorithm to obtain a video analysis result, and sending the video analysis result to the second server and the client.
Wherein the at least one camera device may be distributed in different elevators or may be distributed in the same elevator. The camera device can be used for monitoring the elevator. The client may be configured to obtain, by the first server, the video analysis result stored on the second server.
In addition, taking a target video analysis algorithm as a motion detection algorithm as an example, the video analysis result may include an alarm picture and/or an alarm video; taking the target video analysis algorithm as an algorithm for comparing target objects as an example, the video analysis result may include a video stream including a preset duration of the target object.
It should be noted that the first server may send the video analysis result and the video stream of the at least one image capture device to the second server. The second server may be used to store video analysis results and may also be used to store the complete video stream. When the first server uploads the video analysis result and/or the video stream to the second server, a download link or a log can be generated at the same time and fed back to the client through the background service component, so that the client side can obtain the video analysis result and/or the video stream through the download link or the log.
In the embodiment of the present disclosure, the first server is configured to acquire a video stream sent by the at least one image capturing device through the local area network, send the video stream to the client, and determine a target video analysis algorithm corresponding to the video stream; the first server is used for analyzing the video stream based on the target video analysis algorithm to obtain a video analysis result, and sending the video analysis result to the second server and the client. Therefore, the first server acquires the video stream of the camera equipment through the local area network and sends the video stream to the client, the video stream transmission is fast and stable, and the video stream transmission cost can be reduced; and the video stream is analyzed through a target video analysis algorithm corresponding to the video stream, so that the accuracy of video analysis can be improved.
Optionally, the first server includes a streaming media component, an algorithm service component, and a message component;
the streaming media component is used for acquiring a video stream sent by the at least one camera device through the local area network;
the algorithm service component is used for receiving the video stream sent by the streaming media component through the local area network;
the algorithm service component is used for acquiring algorithm parameters corresponding to the target video analysis algorithm from the message component;
the algorithm service component is used for analyzing the video stream according to the algorithm parameters corresponding to the target video analysis algorithm to obtain the video analysis result.
Wherein, the process of analyzing the video stream by the algorithm service component can be as follows: searching the target object in the video stream under the condition that the target video analysis algorithm is an algorithm for target object comparison; and if the target object is found, sending alarm information to a client through the local area network, and sending a video stream containing preset duration of the target object to the message component. And the message component sends the video stream containing the preset duration of the target object to the second server through a wide area network. In one embodiment, the message component may send a video stream containing the preset duration of the target object to the background service component, and the background service component sends the video stream containing the preset duration of the target object to the second server.
In the embodiment, the algorithm service component acquires the algorithm parameters corresponding to the target video analysis algorithm and analyzes the video stream, so that the independent algorithm service components can be conveniently arranged in each area by processing the calculation tasks through the independent components, a distributed architecture is realized, and the execution efficiency of the calculation tasks can be improved.
Optionally, the first server further includes a background service component, and the background service component is in communication connection with the message component;
the background service component is used for sending the algorithm parameters corresponding to the target video analysis algorithm to the algorithm service component through the message component and receiving the video analysis result sent by the algorithm service component.
The background service component can be in communication connection with the second server through the wide area network, and the second server is used for receiving the video analysis result sent by the background service component through the wide area network.
In the embodiment, the background service component sends the algorithm parameters corresponding to the target video analysis algorithm to the algorithm service component through the message component, so that the client can issue the algorithm parameters through the background service component, and the algorithm parameters can be updated conveniently in real time; and the background service component receives the video analysis result sent by the algorithm service component and can send the video analysis result to a second server for storage.
Optionally, the first server is configured to store the video stream corresponding to a first preset number of days, the second server is configured to store the video analysis result corresponding to a second preset number of days, and the first preset number of days is smaller than the second preset number of days.
Wherein, the first preset number of days may be 5 days, or 7 days, or 10 days, etc. The second predetermined number of days may be 30 days, or 60 days, or 90 days, etc. In this embodiment, the first preset number of days and the second preset number of days are not limited.
In addition, the second server may be used to store the video analysis results, and may also be used to store the complete video stream at the same time. For example, the second server may store the video analysis result and the video stream corresponding to the second preset number of days at the same time, so that the video stream can be retained for a longer time by the second server.
In the embodiment, the video stream corresponding to the first preset number of days is stored through the first server, and the video analysis result corresponding to the second preset number of days is stored through the second server, so that the video stream in a short time can be stored through the first server, the video analysis result in a long time can be stored through the second server, and important events can be traced back in a later period while the storage pressure is reduced.
As a specific embodiment, as shown in fig. 2, the camera device, the streaming media component and the algorithm service component for monitoring the elevator may be deployed in the same building of a certain campus, the client may be deployed in another building of the campus, and the message component and the background service component may be deployed outside the campus or may be deployed in the campus. The camera device, the streaming media component, the algorithm service component and the client can be deployed in the same local area network. The message component and the background service component may be deployed under the local area network or may be deployed under a wide area network.
In addition, the streaming media component may be a zlmedia kit streaming media component, the message component may be a RabbitMq message component, and the OSS (Open Storage Service) Service may be a cloud Service provided by an OSS cloud server. The background service component can be an elevator background service component.
Specifically, the elevator real-time monitoring method can comprise the following processes:
the camera equipment of the park elevator provides monitoring video;
acquiring a video stream shot by a camera device by a ZLMediKit streaming media component of a first server deployed in the park;
the algorithm service component of the first server acquires the video stream of the streaming media component and the algorithm parameters of the message component RabbitMq for video analysis;
the algorithm service component sends the video analysis result to the message component RabbitMq;
the message component RabbitMq can be provided with an issuing algorithm parameter queue and a video analysis result queue, wherein the issuing algorithm parameter queue is used for storing algorithm parameters to be issued for video analysis, and the video analysis result queue is used for storing video analysis results.
And the algorithm parameter issuing queue is that the background service component sends the configuration information required by the algorithm analysis service component to the message queue, the algorithm analysis service component monitors the message queue, and the algorithm analysis process is started according to the configuration information after the message is received.
The video analysis result queue is that the algorithm analysis service component reports the analyzed result to the message queue, and the background service component monitors the message queue, acquires the result of the algorithm analysis and uploads the analysis result to the OSS server.
And the OSS cloud server stores the video analysis result, stores the picture and the video, and generates a corresponding label and a corresponding download link for the client to check and download.
The client deployed in the park can directly view the monitoring video of the ZLMediatikat streaming media component through the local area network, and can also access the background service component through the Internet to obtain a video analysis result and pictures and videos on the OSS cloud server. The client can also be used for elevator parameter configuration.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an elevator real-time monitoring apparatus according to an embodiment of the present invention, and as shown in fig. 3, an elevator real-time monitoring apparatus 200 includes:
the determining module 201 is configured to acquire a video stream sent by at least one image capturing device through a local area network, and determine a target video analysis algorithm corresponding to the video stream;
an analysis module 202, configured to analyze the video stream based on the target video analysis algorithm to obtain a video analysis result.
Optionally, the analysis module 202 is specifically configured to:
and searching the target object in the video stream under the condition that the target video analysis algorithm is an algorithm for target object comparison.
Optionally, the determining module 201 is specifically configured to:
acquiring a video stream sent by at least one camera device through a local area network, and determining a target object type of an object included in the video stream;
determining a target video analysis algorithm corresponding to the target object type from a plurality of video analysis algorithms, the plurality of video analysis algorithms corresponding to a plurality of object types one-to-one, the plurality of object types including the target object type.
Optionally, the determining module 201 is further specifically configured to:
performing video analysis according to a general video analysis algorithm for judging the object type to obtain the target object type of the object included in the video stream;
the analysis module 202 is specifically configured to:
and under the condition that the target object types are multiple, analyzing the video stream by adopting a plurality of target video analysis algorithms which are in one-to-one correspondence with the target object types to obtain a plurality of video analysis results.
Optionally, the analysis module 202 is further configured to:
sending the video analysis result to a second server through a wide area network;
and sending alarm information, the video analysis result and the video stream of the at least one camera device to a client through the local area network.
The elevator real-time monitoring device can realize each process realized in the method embodiment of fig. 1, and can achieve the same technical effect, and is not described herein again to avoid repetition.
As shown in fig. 4, an embodiment of the present disclosure further provides a server 300, where the server is a first server, and includes: the elevator real-time monitoring method comprises a memory 302, a processor 301 and a program which is stored in the memory 302 and can run on the processor 301, wherein when the program is executed by the processor 301, each process of the elevator real-time monitoring method embodiment is realized, the same technical effect can be achieved, and details are not repeated here to avoid repetition.
The embodiment of the present disclosure further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the elevator real-time monitoring method embodiment, and can achieve the same technical effect, and in order to avoid repetition, the details are not repeated here. The computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present disclosure.
While the disclosed embodiments have been described in connection with the appended drawings, the present invention is not limited to the specific embodiments described above, which are intended to be illustrative rather than limiting, and it will be appreciated by those of ordinary skill in the art that, in light of the teachings of the present invention, many modifications may be made without departing from the spirit and scope of the invention as set forth in the appended claims.
Claims (11)
1. A method for real-time monitoring of an elevator, the method comprising:
acquiring a video stream sent by at least one camera device through a local area network, and determining a target video analysis algorithm corresponding to the video stream;
and analyzing the video stream based on the target video analysis algorithm to obtain a video analysis result.
2. The method of claim 1, wherein analyzing the video stream based on the target video analysis algorithm comprises:
and searching the target object in the video stream under the condition that the target video analysis algorithm is an algorithm for target object comparison.
3. The method of claim 2, wherein determining a target video analysis algorithm corresponding to the video stream comprises:
determining a target object type of an object included in the video stream;
determining a target video analysis algorithm corresponding to the target object type from a plurality of video analysis algorithms, the plurality of video analysis algorithms corresponding to a plurality of object types one-to-one, the plurality of object types including the target object type.
4. The method of claim 3, wherein the determining a target object type for an object included in the video stream comprises:
performing video analysis according to a general video analysis algorithm for judging the object type to obtain the target object type of the object included in the video stream;
analyzing the video stream based on the target video analysis algorithm to obtain a video analysis result, wherein the video analysis result comprises:
and under the condition that the target object types are multiple, analyzing the video stream by adopting a plurality of target video analysis algorithms which are in one-to-one correspondence with the target object types to obtain a plurality of video analysis results.
5. The method of claim 1, further comprising:
sending the video analysis result to a second server through a wide area network;
and sending alarm information, the video analysis result and the video stream of the at least one camera device to a client through the local area network.
6. An elevator real-time monitoring system, comprising at least one camera device for monitoring an elevator, a first server communicatively connected to the at least one camera device via a local area network, a client communicatively connected to the first server via the local area network, and a second server communicatively connected to the first server via a wide area network, wherein:
the first server is used for acquiring a video stream sent by the at least one camera device through the local area network, sending the video stream to the client, and determining a target video analysis algorithm corresponding to the video stream;
the first server is used for analyzing the video stream based on the target video analysis algorithm to obtain a video analysis result, and sending the video analysis result to the second server and the client.
7. The system of claim 6, wherein the first server comprises a streaming media component, an algorithmic service component, and a messaging component;
the streaming media component is used for acquiring a video stream sent by the at least one camera device through the local area network;
the algorithm service component is used for receiving the video stream sent by the streaming media component through the local area network;
the algorithm service component is used for acquiring algorithm parameters corresponding to the target video analysis algorithm from the message component;
the algorithm service component is used for analyzing the video stream according to the algorithm parameters corresponding to the target video analysis algorithm to obtain the video analysis result.
8. The system of claim 7, wherein the first server further comprises a background services component, the background services component communicatively coupled to the messaging component;
the background service component is used for sending the algorithm parameters corresponding to the target video analysis algorithm to the algorithm service component through the message component and receiving the video analysis result sent by the algorithm service component.
9. The system of claim 6, wherein the first server is configured to store the video stream corresponding to a first preset number of days, and the second server is configured to store the video analysis result corresponding to a second preset number of days, and the first preset number of days is smaller than the second preset number of days.
10. An elevator real-time monitoring apparatus, characterized in that the apparatus comprises:
the system comprises a determining module, a processing module and a processing module, wherein the determining module is used for acquiring a video stream sent by at least one camera device through a local area network and determining a target video analysis algorithm corresponding to the video stream;
and the analysis module is used for analyzing the video stream based on the target video analysis algorithm to obtain a video analysis result.
11. A server, the server being a first server, comprising: memory, processor and program stored on the memory and executable on the processor, which when executed by the processor implements the steps in the elevator real-time monitoring method according to any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111060093.3A CN113723349A (en) | 2021-09-10 | 2021-09-10 | Elevator real-time monitoring method, device, system and server |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111060093.3A CN113723349A (en) | 2021-09-10 | 2021-09-10 | Elevator real-time monitoring method, device, system and server |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113723349A true CN113723349A (en) | 2021-11-30 |
Family
ID=78683253
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111060093.3A Pending CN113723349A (en) | 2021-09-10 | 2021-09-10 | Elevator real-time monitoring method, device, system and server |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113723349A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114363579A (en) * | 2022-01-21 | 2022-04-15 | 中国铁塔股份有限公司 | Monitoring video sharing method and device and electronic equipment |
CN115209179A (en) * | 2022-05-27 | 2022-10-18 | 浪潮通信技术有限公司 | Video data processing method and device |
-
2021
- 2021-09-10 CN CN202111060093.3A patent/CN113723349A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114363579A (en) * | 2022-01-21 | 2022-04-15 | 中国铁塔股份有限公司 | Monitoring video sharing method and device and electronic equipment |
CN114363579B (en) * | 2022-01-21 | 2024-03-19 | 中国铁塔股份有限公司 | Method and device for sharing monitoring video and electronic equipment |
CN115209179A (en) * | 2022-05-27 | 2022-10-18 | 浪潮通信技术有限公司 | Video data processing method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113723349A (en) | Elevator real-time monitoring method, device, system and server | |
CN211293956U (en) | AI-based identification and alarm system for abnormal agent on construction site | |
CN103391432A (en) | Intelligent video monitoring system for safety early warning of scenic spots and monitoring method | |
CN107818312A (en) | A kind of embedded system based on abnormal behaviour identification | |
CN109993946A (en) | A kind of monitoring alarm method, camera, terminal, server and system | |
CA2904187A1 (en) | Method and system for prompt video-data message transfer to personal devices | |
JP7160454B2 (en) | Method, apparatus and system, electronic device, computer readable storage medium and computer program for outputting information | |
US8365871B2 (en) | Electronic device and method for monitoring an elevator | |
CN114971409B (en) | Smart city fire monitoring and early warning method and system based on Internet of things | |
WO2020042637A1 (en) | Supervision method, apparatus and system, cloud server and storage medium | |
CN110928305B (en) | Patrol method and system for patrol robot of railway passenger station | |
CN105103204B (en) | Safety message network and the method for reporting network for operational safety | |
CN113095161B (en) | Dangerous behavior identification method and device, terminal equipment and computer storage medium | |
KR101475177B1 (en) | Emergency call-closed circuit television system and method thereof | |
CN112330930A (en) | Urban tunnel traffic monitoring method, system and platform | |
CN112419639A (en) | Video information acquisition method and device | |
CN111908288A (en) | TensorFlow-based elevator safety system and method | |
CN114900513B (en) | Remote pet safety alarm system | |
CN116704644A (en) | Automobile management and control platform based on cloud data processing and multi-source data analysis | |
CN115880631A (en) | Power distribution station fault identification system, method and medium | |
CN114463873A (en) | Patrol system for community | |
CN112512017A (en) | Information processing method and device for remotely monitoring state of intelligent vehicle-mounted networking terminal | |
CN107483544A (en) | A kind of intelligent movable monitoring system and monitoring method | |
CN112419638B (en) | Method and device for acquiring alarm video | |
CN113489939A (en) | Intelligent monitoring method and system for power transmission line construction site |
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 |