CN112511803A - Water flow management system, method and equipment based on cloud edge end - Google Patents
Water flow management system, method and equipment based on cloud edge end Download PDFInfo
- Publication number
- CN112511803A CN112511803A CN202011311399.7A CN202011311399A CN112511803A CN 112511803 A CN112511803 A CN 112511803A CN 202011311399 A CN202011311399 A CN 202011311399A CN 112511803 A CN112511803 A CN 112511803A
- Authority
- CN
- China
- Prior art keywords
- water area
- video
- video data
- area monitoring
- platform
- 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
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2187—Live feed
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/433—Content storage operation, e.g. storage operation in response to a pause request, caching operations
- H04N21/4334—Recording operations
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Alarm Systems (AREA)
Abstract
The application discloses rivers management system based on cloud limit end, management system includes: the water area monitoring equipment is used for acquiring video data of a water area; the video data management platform is used for acquiring video data of the plurality of water area monitoring devices and carrying out corresponding processing to generate live broadcast videos and/or recorded broadcast videos of the water area monitoring devices; the system is connected with the cloud platform, and when an instruction that the cloud platform acquires a live video and/or a recorded broadcast video of the corresponding water area monitoring equipment is received, the live video and/or the recorded broadcast video of the corresponding water area monitoring equipment is sent to the cloud platform; and the cloud platform is used for acquiring the live broadcast video and/or recorded broadcast video of the corresponding water area monitoring equipment and sending the live broadcast video and/or recorded broadcast video to the monitoring platform. According to the method and the system, when the communication network is not good, the video data shot by the corresponding water area by each monitoring device can be acquired faster through the video data management platform, so that the working efficiency of water area management personnel on water area management is improved.
Description
Technical Field
The application relates to the field of water conservancy communication, in particular to a water flow management system, method and device based on cloud edge terminals.
Background
Water is a source of all things, so that people can live only with water without boiling all the time, and all things in the world can generate vitality and have vitality.
At present, with the development of work and the increase of population, the ecological environment becomes worse and worse, a large amount of water resources are polluted, and therefore, the increase of the management and protection of the water area is an important task. Most of the existing water areas are monitored and managed manually by matching workers with monitoring equipment, then information data of each water area are managed, finally information data of the water areas are obtained, and management and protection are carried out on the corresponding water areas according to the information data of the water areas.
However, in the existing water area management process, because the geographical position of part of water flow is far away, the water area management cannot be timely and effectively performed because the patrol and supervision cannot be performed in place.
Disclosure of Invention
The embodiment of the application provides a water flow management system, method and device based on a cloud edge end, and solves the problem of low water area management work efficiency.
In one aspect, an embodiment of the present application provides a water flow management system based on a cloud edge, and the management system includes: the water area monitoring equipment is used for acquiring video data of a water area; the video data management platform is connected with the plurality of water area monitoring devices and is used for acquiring video data of the plurality of water area monitoring devices and carrying out corresponding processing so as to generate live broadcast videos and/or recorded broadcast videos of the water area monitoring devices; the system is connected with the cloud platform, and when an instruction that the cloud platform acquires a live video and/or a recorded broadcast video of the corresponding water area monitoring equipment is received, the live video and/or the recorded broadcast video of the corresponding water area monitoring equipment is sent to the cloud platform; and the cloud platform is used for acquiring the live broadcast video and/or recorded broadcast video of the corresponding water area monitoring equipment and sending the live broadcast video and/or recorded broadcast video to the monitoring platform.
In one example, the video data management platform comprises a live streaming media server and a video processing server; the live broadcast streaming media server is connected with the plurality of water area monitoring devices and used for acquiring video data of the plurality of water area monitoring devices and sending the video data to the video processing server; receiving detection results of video data of a plurality of water area monitoring devices sent by a video processing server to generate live videos of the monitoring devices; the system is connected with the cloud platform, and when an instruction that the cloud platform acquires the live video of the corresponding water area monitoring device is received, the live video of the corresponding water area monitoring device is sent to the cloud platform; the video processing server is used for receiving the video data of the plurality of water area monitoring devices and detecting the video data of the plurality of water area monitoring devices through the detection neural network model so as to determine whether a preset target exists in the video data; and sending the detection result of the video data to the live streaming media server.
In one example, the detection neural network model includes a water floating detection neural network model and a water invader detection neural network model, and the preset target includes a water floating object and a water invader.
In one example, a cloud platform includes a model training server; the model training server is connected with the video processing server and used for training video data samples of the water area monitoring equipment to generate a detection neural network model and sending the detection neural network model to the video processing server; and when receiving an updating instruction of the monitoring platform, training the latest video data samples of the water area monitoring devices uploaded by the monitoring platform to obtain an updated detection neural network model, and issuing the updated detection neural network model to the video processing server.
In one example, a video data management platform includes a recorded streaming media server; the recording and playing streaming media server is connected with the plurality of water area monitoring devices and is used for acquiring video data of the plurality of water area monitoring devices; and the cloud platform is connected with the recording and broadcasting video monitoring device and is used for sending the recording and broadcasting video of the corresponding water area monitoring device to the cloud platform when receiving the instruction that the cloud platform acquires the recording and broadcasting video of the corresponding water area monitoring device.
In one example, the video data management platform further comprises a data center server; and the data center server is used for storing recorded and broadcast videos of the plurality of water area monitoring devices.
In one example, a cloud platform includes a rebroadcast streaming server; and the live broadcast streaming media server is used for acquiring the live broadcast video and/or recorded broadcast video of the corresponding water area monitoring equipment from the video data management platform when receiving an instruction that the monitoring platform acquires the live broadcast video and/or recorded broadcast video of the corresponding water area monitoring equipment.
In one example, the cloud platform further comprises a device registry server; the device registration center server is used for registering each device in the video data management platform and a plurality of water area monitoring devices so as to establish association between each water area monitoring device and each device in the video data management platform; wherein, each waters is monitored and is clapped equipment and carry corresponding identification.
On the other hand, an embodiment of the present application provides a water flow management method based on a cloud edge, which is applied to the water flow management system based on a cloud edge, and the management method includes: the video data management platform is used for acquiring video data from the plurality of water area monitoring devices and carrying out corresponding processing to generate live broadcast videos and/or recorded broadcast videos of the water area monitoring devices; and when receiving an instruction that the cloud platform acquires the live video and/or the recorded broadcast video of the corresponding water area monitoring equipment, sending the live video and/or the recorded broadcast video of the corresponding water area monitoring equipment to the cloud platform, so that the cloud platform sends the live video and/or the recorded broadcast video of the corresponding water area monitoring equipment to the monitoring platform.
In another aspect, an embodiment of the present application provides a water flow management device based on a cloud edge end, where the management device includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to: the video data management platform is used for acquiring video data from the plurality of water area monitoring devices and carrying out corresponding processing to generate live broadcast videos and/or recorded broadcast videos of the water area monitoring devices; and when receiving an instruction that the cloud platform acquires the live video and/or the recorded broadcast video of the corresponding water area monitoring equipment, sending the live video and/or the recorded broadcast video of the corresponding water area monitoring equipment to the cloud platform, so that the cloud platform sends the live video and/or the recorded broadcast video of the corresponding water area monitoring equipment to the monitoring platform.
Based on the foregoing description, it can be understood by those skilled in the art that, according to the water flow management system, method and device based on the cloud edge provided in the embodiment of the present application, when a communication network is not good, video data shot by each monitoring device for a corresponding water area can be obtained faster through the video data management platform, so that the work efficiency of water area management by a water area manager for water area management is improved.
Furthermore, real-time live broadcast of the water area is realized through the video data management platform, early warning is carried out in a fastest and optimal mode, management personnel are effectively assisted to handle the live broadcast, the phenomena of misinformation and missing report are reduced to the maximum extent, recording and broadcasting of the water area are realized through the video data management platform, playback of video data can be provided for the water area management personnel, and the water area management personnel can track the live broadcast afterwards even if abnormal conditions occur.
Furthermore, the positions of the floaters and the invaders in the water area are determined by registering each device and a plurality of monitoring devices in the video data management platform, so that water area managers can timely handle the floaters in the water area and timely keep the invaders away from the water area.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a schematic view of a cloud-side-based water flow management system according to an embodiment of the present disclosure;
fig. 2 is a flowchart of a cloud-side-based water flow management method according to an embodiment of the present disclosure;
fig. 3 is a schematic view of a water flow management device based on a cloud edge end according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. 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 application.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Fig. 1 is a schematic view of a water flow management system based on a cloud edge end according to an embodiment of the present application.
As shown in fig. 1, the water flow management system at least comprises: the system comprises a cloud platform 100, a monitoring platform 200, a video data management platform 300, and a plurality of water area monitoring devices, including a monitoring device 410, a monitoring device 420, a monitoring device 430, and the like.
The cloud platform 100 includes a live streaming server 110, a model training server 120, a model warehouse server 130, and a device registry server 140, and the video data management platform 300 includes a live streaming server 310, a recorded streaming server 320, a video processing server 330, and a data center server 340. The plurality of water area monitoring devices are end devices, the video data management platform 300 is a side device, and the cloud device at least comprises a cloud platform 100 and a monitoring platform 200.
It should be noted that the water flow management system according to the embodiment of the present application is provided with a plurality of water area monitoring devices, each monitoring device of the plurality of water area monitoring devices is connected to the video data management platform 300 by wire, the number of the monitoring devices may be one, or may be provided in plurality, as shown in fig. 1, each monitoring device is provided with a monitoring device 410, a monitoring device 420, and a monitoring device 430.
Further, the video data management platform 300 is connected to the cloud platform 100, and the cloud platform 100 is connected to the monitoring platform 200.
The video data management platform 300 cannot communicate with the monitoring platform 200, and therefore, the interaction with the monitoring platform 200 is realized through the cloud platform 100.
Specifically, the video data management platform 300 is wirelessly connected to the cloud platform 100, and the cloud platform 100 is wirelessly or wired connected to the monitoring platform 200. If the monitoring terminal of the monitoring platform 200 is a computer, the cloud platform 100 and the monitoring platform 200 are connected by wire, and the monitoring terminal of the monitoring platform 200 is a mobile terminal, the cloud platform 100 and the monitoring platform 200 are connected wirelessly.
Further, the live streaming server 310 is connected to a plurality of water area monitoring devices, and is connected to the video processing server 330 and the relay streaming server 110.
The recording streaming media server 320 is connected with a plurality of water area monitoring devices, connected with the data center server 340, and connected with the broadcasting streaming media server 110.
In addition, the video processing server 330 is also connected to the model training server 120. The rebroadcast streaming server 110 is also connected to the monitoring platform 200.
In an example of the present application, the plurality of water area monitoring devices are mainly used for acquiring video data of a water area, and may specifically be devices having a camera shooting function, which is not described herein again.
The identity identification may be specifically a mode for implementing an identity authentication function, for example, digital numbering is performed on each water area monitoring device, and letter numbering is performed on each water area monitoring device, which is not limited herein.
The video data management platform 300 is mainly configured to obtain video data of the plurality of water area monitoring devices, and perform corresponding processing on the video data of the plurality of water area monitoring devices to generate live videos and/or recorded and broadcast videos of the water area monitoring devices.
How the video data management platform 300 generates live video of each water area monitoring device is described in detail below.
Specifically, first, the live streaming server 310 uses FFmbeg tool (FFmpeg is a set of open source computer programs that can be used to record, convert digital audio and video, and convert them into streams), and pulls the video data of several waters monitoring devices through RTSP protocol. Secondly, the live streaming media server 310 obtains video data of a plurality of water area monitoring devices through an RTMP protocol. Thirdly, the live streaming media server 310 encodes the video data of the plurality of water area monitoring devices, and pushes the encoded video data of the plurality of water area monitoring devices to the video processing server 330.
Further, the video processing server 330 first decodes the encoded video data of the plurality of water area monitoring devices, and then obtains the video data of the plurality of water area monitoring devices by reading the RTMP protocol. Secondly, the video processing server 330 obtains the detection result of the video data of the plurality of water area monitoring devices by detecting the video data of the plurality of water area monitoring devices of the neural network model, so as to determine whether a preset target exists in the video data. Again, the video processing server 330 pushes the detection result to the live streaming server 310 using the FFmbeg tool.
The detection neural network model in the video processing server 330 at least includes a floater detection neural network model and an invader detection neural network model, and the preset target at least includes a water floater and a water invader. The floater detection neural network model is used for detecting whether floaters exist in video data of the monitoring equipment in the water areas, and the floaters can be any objects harmful to rivers, such as garbage of plastic bottles, plastic bags and the like, and are not limited herein. And under the condition that the floating objects exist in the video data of the monitoring equipment in a plurality of water areas, marking the floating objects. The mark may be made in any manner with a distinguishing function, such as a rectangular frame, a color distinction, etc., and is not limited herein.
In addition, the invader detecting neural network model is used for detecting whether invaders exist in the video data of the plurality of water area monitoring devices, and the invaders can be persons or vehicles placed beside rivers, such as bicycles, electric vehicles and the like, and are not limited herein. And under the condition that the invaders exist in the video data of the plurality of water area monitoring devices, marking the invaders. The mark may be made in any manner with a distinguishing function, such as a rectangular frame, a color distinction, etc., and is not limited herein.
The person in the art can understand that, the video processing server 330 in the embodiment of the present application can detect whether there is a person intrusion in the video data of the plurality of water area surveillance devices through the intruder detection neural network model, so especially for children, the children can be prevented from playing at the river in time, further, the children can be found in time to carelessly fall into the river, so as to perform rescue measures, and further, for the place of water depth, the children can be prevented from swimming in time.
Further, the live streaming media server 310 obtains the detection result of the video data of the plurality of water area monitoring devices from the video processing server 330 by decoding, and performs live broadcast on the video data of the plurality of water area monitoring devices carrying the detection result in real time, and when the video data of the plurality of water area monitoring devices has a floating object or an intruding object, the live streaming media server 310 alarms and sends the alarm to the cloud platform 100, and the cloud platform 100 notifies the monitoring platform 200. The alarm may be given in any manner having a function of notifying monitoring personnel, for example, a large monitoring screen in the monitoring platform 200 may make a buzzing sound, or a mobile terminal of the monitoring platform 200 may receive a short message.
The following describes in detail how the video data management platform 300 generates recorded videos of each water area surveillance device.
Specifically, first, the streaming media server 320 uses FFmbeg tool (FFmpeg is a set of open source computer programs that can be used to record, convert digital audio and video, and convert them into streams), and pulls the video data of several waters monitoring devices through RTSP protocol. Secondly, the streaming media recording server 310 obtains the video data of the plurality of water area surveillance devices through the RTMP protocol. Thirdly, the recorded streaming media server 320 sends the video data obtained by the plurality of water area monitoring devices to the data center server 340 for storage.
After the recorded streaming media server 310 acquires the video data of the plurality of water area monitoring devices, the video data acquired by the plurality of water area monitoring devices may be transmitted to the data center server 340 for storage, or may be stored in a local end. The time length for storing the recorded and broadcast video data can be set according to actual requirements, for example, the recorded and broadcast video data only retains the data of the latest 7 days, which is not limited herein.
Further, the recorded and played streaming media server 310 sends the corresponding recorded and played video to the cloud platform 100 when receiving an instruction from the cloud platform 100 to acquire the recorded and played video of the water area monitoring device in a specific time period.
As can be understood by those skilled in the art, the embodiment of the application can meet the requirement of a user for watching video playback through recorded and played video, and can perform post-event tracking when abnormal conditions occur. And the recorded and broadcast video data is stored in the video data management platform 300, so that the partial loss of the recorded and broadcast video data caused in the process of uploading to the cloud platform 100 is avoided under the condition that the outdoor network is poor.
And the cloud platform 100 is configured to acquire a live video and/or a recorded video of the corresponding water area monitoring device, and send the live video and/or the recorded video to the monitoring platform 200.
Based on different scenes, different working requirements and different target detections in the actual working process, a corresponding service cluster building mode can be adopted, for example, a cloud platform 100 environment can be built by using kubernets, which is abbreviated as K8s, and is an abbreviation formed by replacing 8 characters "ubernet" with 8 characters, and is an open source, and is used for managing containerized applications on a plurality of hosts in a cloud platform. Further, in order to better detect the issuing of the neural network model, a docker is installed in the kubernets cluster to manage the model and issue the model. Further, the file system of the OSS may be used, the OSS being a distributed object storage service providing an object storage service in the form of a Key-Value pair.
Specifically, the streaming media server 110 is mainly used to obtain a live video from the video data management platform 300. When receiving the live video instruction of the specific time period for acquiring the corresponding water area monitoring device from the monitoring platform 200, the live video instruction of the specific time period for acquiring the corresponding water area monitoring device from the monitoring platform 200 is sent to the live streaming media server 310, and the live video of the specific time period for acquiring the corresponding water area monitoring device from the live streaming media server 310 is returned to the monitoring platform 200.
In addition, the broadcast streaming server 110 is also mainly used for acquiring recorded and broadcast videos from the video data management platform 300. When receiving the recorded broadcast video instruction of the specific time period for acquiring the corresponding water area monitoring device from the monitoring platform 200, the broadcast streaming media server 110 sends the broadcast streaming media server 320 the live video instruction of the specific time period for acquiring the corresponding water area monitoring device from the monitoring platform 200, acquires the recorded broadcast video of the specific time period for acquiring the corresponding water area monitoring device from the broadcast streaming media server 310, and returns the recorded broadcast video to the monitoring platform 200.
Further, the model training server 120 is mainly used for training the neural network model for detection in the video data processing server 330, and the model warehouse server 130 is mainly used for storing the neural network model for detection trained by the model training server 120. The model training server 120 pre-trains the video data of the plurality of water area monitoring devices, so as to obtain an initial detection neural network model.
And the model training server 120 trains the initial detection neural network model according to the water area video data sample uploaded by the monitoring platform 200 to obtain a trained detection neural network model. The model training server 130 trains the water area video data samples uploaded by the monitoring platform 200 through preset weights.
It should be noted that the training method of the initial neural network model may be any feasible method, for example, training all of the head and the backbone of the neural network model to obtain the initial neural network model.
Further, the model training server 120 sends the trained neural network model to the video processing server 330, so that the video processing server 330 detects the acquired video data captured by the plurality of water area monitoring devices through detecting the neural network model, and determines whether the video data captured by the plurality of water area monitoring devices has a floating object or an intruding object.
When the neural network model needs to be updated, the monitoring platform 200 uploads the water area video data sample for updating the neural network model again, and the model training server 120 trains the initial neural network model to obtain the updated neural network model according to the water area video data sample for updating the neural network model uploaded again by the monitoring platform 200. And adding 1 to the version number of the updated detection neural network model on the basis of the version number of the detection neural network model to be updated.
As can be understood by those skilled in the art, in the embodiment of the present application, the model training server 120 trains the detection neural network model and updates the detection neural network model, so that the updated detection neural network model can be issued to the video data processing server 330 in real time, and the video data processing server 330 can more accurately detect the video data of the plurality of water area monitoring devices, and better adapt to different scenes of each water area.
The device registration center server 140 registers a plurality of water area monitoring devices with the live broadcast streaming media server 310, the recorded broadcast streaming media server 320, the video processing server 330 and the data center server 340, so that each device of the video data platform 300 is associated with the plurality of water area monitoring devices, and the monitoring platform 200 can obtain the geographical position of each water area monitoring device according to the identity of each water area monitoring device, thereby determining the position of the floating object or the invader.
The monitoring platform 200 initiates a live watching instruction of a corresponding water area monitoring device to the relay streaming media server 110 of the cloud platform 100 through a preset inlet at the monitoring platform 200, the relay streaming media server 110 sends the live watching instruction to the video data management platform 300, and the video data management platform 300 pushes the live inlet to the relay streaming media server 110, so that the monitoring platform 200 watches live video.
Further, in the video data of the plurality of water area monitoring devices, the monitoring personnel of the monitoring platform 200 obtain the geographic position of the corresponding water area monitoring device through the identity of the corresponding water area monitoring device for the water area with the floating object or the invader, so as to determine the position of the floating object or the invader.
In addition, in the monitoring platform 200, a recorded broadcast watching instruction is initiated to the broadcast streaming media server 110 of the cloud platform 100 through a preset entry, the broadcast streaming media server 110 sends the recorded broadcast watching instruction to the video data management platform 300, and the video data management platform 300 pushes the recorded broadcast video entry to the broadcast streaming media server 110, so that the monitoring platform 200 watches the recorded broadcast video.
It should be noted that the instruction of the live broadcast video and/or the recorded broadcast video includes the identity of each water area monitoring device and the timestamp of the live broadcast video corresponding to each water area monitoring device, that is, the instruction includes the live broadcast video and/or the recorded broadcast video of the specific time period of the specific water area monitoring device.
Based on the foregoing description, it can be understood by those skilled in the art that, in the water flow management system based on the cloud edge end provided in the embodiment of the present application, when a communication network is not good, the video data taken by each monitoring device for a corresponding water area can be acquired faster through the video data management platform 300, so that the work efficiency of the water area management personnel for water area management is improved.
Furthermore, real-time live broadcast of the water area is realized through the video data management platform 300, early warning is carried out in a fastest and optimal mode, management personnel are effectively assisted to handle the live broadcast, the phenomena of false alarm and missing report are reduced to the maximum extent, recording and broadcasting of the water area are realized through the video data management platform 300, playback of video data can be provided for the water area management personnel, and the water area management personnel can track the live broadcast afterwards even if abnormal conditions occur.
Furthermore, the positions of the floaters and the invaders in the water area are determined by registering each device and a plurality of monitoring devices in the video data management platform, so that water area managers can timely handle the floaters in the water area and timely keep the invaders away from the water area.
According to the above description, the embodiment of the present application further provides a management method applied in the cloud-edge-based water flow management system as described above, as shown in fig. 2.
S201, the video data management platform 300 acquires video data from the plurality of water area monitoring devices.
S202, the video data management platform 300 performs corresponding processing on the video data to generate a live video and/or a recorded video of each water area monitoring device.
Specifically, the video data management platform 300 performs corresponding processing on the video data to generate a live video of each water area surveillance device, including:
first, the live streaming server 310 obtains video data of a plurality of water area monitoring devices. Secondly, the live streaming media server 310 encodes the video data of the plurality of water area monitoring devices, and pushes the encoded video data of the plurality of water area monitoring devices to the video processing server 330. Thirdly, the video processing server 330 decodes the encoded video data of the plurality of water area monitoring devices to obtain the video data of the plurality of water area monitoring devices. Then, the video processing server 330 obtains the detection result of the video data of the plurality of water area monitoring devices by detecting the video data of the plurality of water area monitoring devices of the neural network model, so as to determine whether a preset target exists in the video data. Finally, the video processing server 330 uses the FFmbeg tool to push the detection result to the live streaming server 310.
The detection neural network model in the video processing server 330 at least includes a floater detection neural network model and an invader detection neural network model, and the preset target at least includes a water floater and a water invader. The floater detection neural network model is used for detecting whether floaters exist in video data of the monitoring equipment in the water areas, and the floaters can be any objects harmful to rivers, such as garbage of plastic bottles, plastic bags and the like, and are not limited herein.
In addition, the invader detecting neural network model is used for detecting whether invaders exist in the video data of the plurality of water area monitoring devices, and the invaders can be persons or vehicles placed beside rivers, such as bicycles, electric vehicles and the like, and are not limited herein.
Further, the video data management platform 300 performs corresponding processing on the video data to generate recorded and broadcast videos of the monitoring devices in each water area, including:
first, the recorded streaming media server 320 acquires video data of a plurality of water area monitoring devices, and the recorded streaming media server 320 transmits the video data acquired by the plurality of water area monitoring devices to the data center server 340 for storage.
After the recorded streaming media server 310 acquires the video data of the plurality of water area monitoring devices, the video data acquired by the plurality of water area monitoring devices may be transmitted to the data center server 340 for storage, or may be stored in a local end. The time length for storing the recorded and broadcast video data can be set according to actual requirements, for example, the recorded and broadcast video data only retains the data of the latest 7 days, which is not limited herein.
S203, the video data management platform 300 receives an instruction that the cloud platform 100 acquires a live video and/or a recorded video of a corresponding water area surveillance device.
Specifically, the video data management platform 300 receives an instruction from the live streaming server 110 to acquire a live video. The instruction of the live video comprises an identity of each water area monitoring device and a timestamp of the live video corresponding to each water area monitoring device.
In addition, the video data management platform 300 receives an instruction from the broadcast streaming server 110 to acquire the recorded video. The recorded and broadcast video instruction comprises the identity of each water area monitoring device and the timestamp of the recorded and broadcast video corresponding to each water area monitoring device.
S204, the video data management platform 300 sends the live video and/or recorded broadcast video of the corresponding water area surveillance device to the cloud platform 100, so that the cloud platform 100 sends the live video and/or recorded broadcast video of the corresponding water area surveillance device to the monitoring platform 200.
Based on the same idea, some embodiments of the present application further provide a device corresponding to the above method.
As shown in fig. 3, the water flow management device includes a processor, optionally a memory and a bus on a hardware level, and furthermore allows the hardware required by other services to be included.
The memory is used for storing an execution instruction, and the execution instruction is a computer program capable of being executed. Further, the memory may include a memory and a non-volatile memory (non-volatile memory) and provide execution instructions and data to the processor. Illustratively, the Memory may be a high-speed Random-Access Memory (RAM), and the non-volatile Memory may be at least 1 disk Memory.
Wherein the bus is used to interconnect the processor, the memory, and the network interface. The bus may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 3, but this does not indicate only one bus or one type of bus.
In a possible implementation manner of the above management method, the processor may first read the corresponding execution instruction from the nonvolatile memory to the memory and then execute the execution instruction, or may first obtain the corresponding execution instruction from another device and then execute the execution instruction. The processor can implement the management method in any of the above management method embodiments of the present application when executing the execution instruction stored in the memory.
It will be appreciated by those skilled in the art that the above management method can be applied to a processor, and can also be implemented by means of a processor. Illustratively, the processor is an integrated circuit chip having the capability to process signals. In the process of executing the management method by the processor, the steps of the management method can be completed by an integrated logic circuit in the form of hardware or instructions in the form of software in the processor. Further, the Processor may be a general-purpose Processor, such as a Central Processing Unit (CPU), a Network Processor (NP), a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, a microprocessor, or any other conventional Processor.
Those skilled in the art will also understand that the steps of the above management method embodiments of the present application may be performed by a hardware decoding processor, or may be performed by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, eprom, registers, and other storage media that are well known in the art. The storage medium is located in the memory, and the processor reads the information in the memory and then completes the execution of the steps in the management method embodiment in combination with the hardware of the processor.
So far, the technical solutions of the embodiments of the present application have been described in conjunction with the foregoing embodiments, but it is easily understood by those skilled in the art that the scope of the embodiments of the present application is not limited to these specific embodiments. Without departing from the technical principles of the embodiments of the present application, a person skilled in the art may split and combine the technical solutions in the above embodiments, and may make equivalent changes or substitutions on the related technical features, and any changes, equivalents, improvements, and the like made within the technical idea and/or technical principles of the embodiments of the present application will fall within the protective scope of the embodiments of the present application.
Claims (10)
1. A cloud-side based water flow management system, the management system comprising:
the water area monitoring equipment is used for acquiring video data of a water area;
the video data management platform is connected with the plurality of water area monitoring devices and is used for acquiring video data of the plurality of water area monitoring devices and carrying out corresponding processing so as to generate live broadcast videos and/or recorded broadcast videos of the water area monitoring devices; and are
The system comprises a cloud platform, a monitoring device and a control device, wherein the cloud platform is connected with the cloud platform and sends a live video and/or a recorded broadcast video of the corresponding water area monitoring device to the cloud platform when receiving an instruction that the cloud platform obtains the live video and/or the recorded broadcast video of the corresponding water area monitoring device;
and the cloud platform is used for acquiring the live broadcast video and/or recorded broadcast video of the corresponding water area monitoring equipment and sending the live broadcast video and/or recorded broadcast video to the monitoring platform.
2. The management system of claim 1, wherein the video data management platform comprises a live streaming server, a video processing server;
the live broadcast streaming media server is connected with the plurality of water area monitoring devices and used for acquiring video data of the plurality of water area monitoring devices and sending the video data to the video processing server; and are
Receiving detection results of video data of the plurality of water area monitoring devices sent by the video processing server to generate live videos of the plurality of monitoring devices; and are
The system is connected with the cloud platform, and when an instruction that the cloud platform acquires the live video of the corresponding water area monitoring device is received, the live video of the corresponding water area monitoring device is sent to the cloud platform;
the video processing server is used for receiving the video data of the plurality of water area monitoring devices and detecting the video data of the plurality of water area monitoring devices through a detection neural network model so as to determine whether a preset target exists in the video data; and are
And sending the detection result of the video data to the live streaming media server.
3. The management system of claim 2, wherein the neural network model comprises a water floating detection neural network model and a water invader detection neural network model, and the predetermined target comprises a water floating object and a water invader.
4. The management system of claim 2, wherein the cloud platform comprises a model training server;
the model training server is connected with the video processing server and used for training the video data samples of the plurality of water area monitoring devices to generate the detection neural network model and sending the detection neural network model to the video processing server; and are
And when an updating instruction of the monitoring platform is received, training the latest video data samples of the plurality of water area monitoring devices uploaded by the monitoring platform to obtain an updated detection neural network model, and issuing the updated detection neural network model to the video processing server.
5. The management system of claim 1, wherein the video data management platform comprises a recorded streaming server;
the recording and playing streaming media server is connected with the plurality of water area monitoring devices and is used for acquiring video data of the plurality of water area monitoring devices; and are
And the cloud platform is connected and used for sending the recorded and broadcast video of the corresponding water area monitoring equipment to the cloud platform when receiving the instruction that the cloud platform acquires the recorded and broadcast video of the corresponding water area monitoring equipment.
6. The management system of claim 5, wherein the video data management platform further comprises a data center server;
and the data center server is used for storing recorded and broadcast videos of the plurality of water area monitoring devices.
7. The management system according to any one of claims 1 to 6, wherein the cloud platform comprises a streaming media server;
and the rebroadcasting streaming media server is used for acquiring the live broadcast video and/or recorded broadcast video of the corresponding water area monitoring equipment from the video data management platform when receiving the instruction that the monitoring platform acquires the live broadcast video and/or recorded broadcast video of the corresponding water area monitoring equipment.
8. The management system of claim 7, wherein the cloud platform further comprises a device registry server;
the device registration center server is used for registering each device in the video data management platform and the plurality of water area monitoring devices so as to establish association between each water area monitoring device and each device in the video data management platform; and the monitoring equipment in each water area carries a corresponding identity mark.
9. A cloud-edge-based water flow management method, which is applied to the cloud-edge-based water flow management system according to any one of claims 1 to 8, and comprises:
the video data management platform is used for acquiring video data from the plurality of water area monitoring devices and carrying out corresponding processing to generate live broadcast videos and/or recorded broadcast videos of the water area monitoring devices; and are
When an instruction that a cloud platform acquires live videos and/or recorded broadcast videos of corresponding water area monitoring equipment is received, the live videos and/or recorded broadcast videos of the corresponding water area monitoring equipment are sent to the cloud platform, so that the cloud platform sends the live videos and/or recorded broadcast videos of the corresponding water area monitoring equipment to a monitoring platform.
10. A cloud-side based water flow management device, the management device comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
the video data management platform is used for acquiring video data from the plurality of water area monitoring devices and carrying out corresponding processing to generate live broadcast videos and/or recorded broadcast videos of the water area monitoring devices; and are
When an instruction that a cloud platform acquires live videos and/or recorded broadcast videos of corresponding water area monitoring equipment is received, the live videos and/or recorded broadcast videos of the corresponding water area monitoring equipment are sent to the cloud platform, so that the cloud platform sends the live videos and/or recorded broadcast videos of the corresponding water area monitoring equipment to a monitoring platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011311399.7A CN112511803A (en) | 2020-11-20 | 2020-11-20 | Water flow management system, method and equipment based on cloud edge end |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011311399.7A CN112511803A (en) | 2020-11-20 | 2020-11-20 | Water flow management system, method and equipment based on cloud edge end |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112511803A true CN112511803A (en) | 2021-03-16 |
Family
ID=74960029
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011311399.7A Pending CN112511803A (en) | 2020-11-20 | 2020-11-20 | Water flow management system, method and equipment based on cloud edge end |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112511803A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113630463A (en) * | 2021-08-09 | 2021-11-09 | 成都华栖云科技有限公司 | Kubedead-based intelligent classroom recording and broadcasting terminal equipment management system and method |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103325216A (en) * | 2012-03-23 | 2013-09-25 | 罗普特（厦门）科技集团有限公司 | Water conservancy flood prevention monitoring early warning method and system based on video monitoring |
| CN104079892A (en) * | 2014-07-17 | 2014-10-01 | 山东同方焮通经贸有限公司 | Video cloud monitoring method and system based on Internet |
| WO2017054101A1 (en) * | 2015-09-30 | 2017-04-06 | 苏州富米信息技术有限公司 | Cloud of things online monitoring general platform system |
| CN108028909A (en) * | 2016-08-08 | 2018-05-11 | 深圳秦云网科技有限公司 | Wisdom monitors cloud transcoding platform |
| CN108419058A (en) * | 2018-05-29 | 2018-08-17 | 陕西大航联科电子技术有限公司 | IoT-based video surveillance system |
| CN110298640A (en) * | 2019-08-05 | 2019-10-01 | 软通动力信息技术有限公司 | A kind of lake information management system |
| CN111060079A (en) * | 2019-12-31 | 2020-04-24 | 华东理工大学 | River foreign matter identification method and river foreign matter monitoring platform system |
| CN111721361A (en) * | 2020-06-29 | 2020-09-29 | 杭州鲁尔物联科技有限公司 | Embankment monitoring system, method and equipment |
| CN111815916A (en) * | 2020-08-06 | 2020-10-23 | 汪先锋 | Monitoring and early warning method and system for target area and mobile terminal |
| CN111901566A (en) * | 2020-07-29 | 2020-11-06 | 浪潮云信息技术股份公司 | Monitoring data storage system and storage method |
-
2020
- 2020-11-20 CN CN202011311399.7A patent/CN112511803A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103325216A (en) * | 2012-03-23 | 2013-09-25 | 罗普特（厦门）科技集团有限公司 | Water conservancy flood prevention monitoring early warning method and system based on video monitoring |
| CN104079892A (en) * | 2014-07-17 | 2014-10-01 | 山东同方焮通经贸有限公司 | Video cloud monitoring method and system based on Internet |
| WO2017054101A1 (en) * | 2015-09-30 | 2017-04-06 | 苏州富米信息技术有限公司 | Cloud of things online monitoring general platform system |
| CN108028909A (en) * | 2016-08-08 | 2018-05-11 | 深圳秦云网科技有限公司 | Wisdom monitors cloud transcoding platform |
| CN108419058A (en) * | 2018-05-29 | 2018-08-17 | 陕西大航联科电子技术有限公司 | IoT-based video surveillance system |
| CN110298640A (en) * | 2019-08-05 | 2019-10-01 | 软通动力信息技术有限公司 | A kind of lake information management system |
| CN111060079A (en) * | 2019-12-31 | 2020-04-24 | 华东理工大学 | River foreign matter identification method and river foreign matter monitoring platform system |
| CN111721361A (en) * | 2020-06-29 | 2020-09-29 | 杭州鲁尔物联科技有限公司 | Embankment monitoring system, method and equipment |
| CN111901566A (en) * | 2020-07-29 | 2020-11-06 | 浪潮云信息技术股份公司 | Monitoring data storage system and storage method |
| CN111815916A (en) * | 2020-08-06 | 2020-10-23 | 汪先锋 | Monitoring and early warning method and system for target area and mobile terminal |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113630463A (en) * | 2021-08-09 | 2021-11-09 | 成都华栖云科技有限公司 | Kubedead-based intelligent classroom recording and broadcasting terminal equipment management system and method |
| CN113630463B (en) * | 2021-08-09 | 2023-06-27 | 成都华栖云科技有限公司 | Intelligent classroom recording and broadcasting terminal equipment management system and method based on kubeedge |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112291520B (en) | Abnormal event identification method and device, storage medium and electronic device | |
| US20220043838A1 (en) | Automated learning of anomalies in media streams with external feed labels | |
| US10115005B2 (en) | Methods and systems of updating motion models for object trackers in video analytics | |
| CN103475856A (en) | Video monitoring system applied to broadcast and TV network | |
| CN113112813A (en) | Illegal parking detection method and device | |
| CN113658394A (en) | River monitoring method and device | |
| WO2018031096A1 (en) | Methods and systems of performing blob filtering in video analytics | |
| CN112511803A (en) | Water flow management system, method and equipment based on cloud edge end | |
| CN114078233A (en) | Intelligent river length system based on cloud-edge collaborative silence upgrading and upgrading method | |
| TWI382367B (en) | Event announcing system and operating method thereof | |
| CN110175535A (en) | A kind of ship identification scheme and its recognition methods based on deep learning | |
| CN112187407A (en) | Real-time signaling message processing method, device, equipment and computer storage medium | |
| CN110855947A (en) | Image snapshot processing method and device | |
| CN117998150A (en) | Method, device, equipment and storage medium for acquiring monitoring video data | |
| CN111402446A (en) | A power dispatching automatic communication line maintenance management system | |
| CN116630866A (en) | Abnormal event monitoring method, device, equipment and medium for audio-video radar fusion | |
| CN104767969A (en) | Intelligent operation safety monitoring system and method for railway crossing | |
| JP3681175B1 (en) | Monitoring system using location information | |
| CN110072072B (en) | Method and device for reporting and displaying data | |
| CN115529451B (en) | Data transmission method and device, storage medium, and electronic device | |
| CN118570521A (en) | A method and device for identifying alarms based on intelligent analysis equipment and business models | |
| CN111526475A (en) | Target vehicle tracking method and device, electronic equipment and storage medium | |
| CN115601904A (en) | AI intelligent edge computing system and method based on 5G | |
| JP3611851B1 (en) | Monitoring system using location information | |
| KR20140126167A (en) | Apparatus and method for proviing tracking video |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210316 |
|
| RJ01 | Rejection of invention patent application after publication |