CN111060079A - River foreign matter identification method and river foreign matter monitoring platform system - Google Patents
River foreign matter identification method and river foreign matter monitoring platform system Download PDFInfo
- Publication number
- CN111060079A CN111060079A CN201911421334.5A CN201911421334A CN111060079A CN 111060079 A CN111060079 A CN 111060079A CN 201911421334 A CN201911421334 A CN 201911421334A CN 111060079 A CN111060079 A CN 111060079A
- Authority
- CN
- China
- Prior art keywords
- data
- river
- foreign matter
- node
- video data
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C13/00—Surveying specially adapted to open water, e.g. sea, lake, river or canal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
- G06V10/464—Salient features, e.g. scale invariant feature transforms [SIFT] using a plurality of salient features, e.g. bag-of-words [BoW] representations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Hydrology & Water Resources (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The application discloses a river foreign matter identification method and a river foreign matter monitoring platform system, wherein the river foreign matter identification method comprises the following steps: the method comprises the steps of node setting, node data acquisition, video data acquisition, data uploading and identification. The invention has the technical effects that the acquisition and transmission of the river water quality hydrological data are carried out by utilizing an Internet of things networking mode based on LoRa and taking an unmanned aerial vehicle as a mobile meter reading gateway. The monitoring cloud platform is built on the server, so that a user can see river channel videos, river channel detection data and river channel foreign matter identification conditions in real time, manpower and material resources are saved, and the efficiency is improved.
Description
Technical Field
The invention relates to the field of remote monitoring of river water quality environments, in particular to a river foreign matter identification method and a river foreign matter monitoring platform system.
Background
With the further advance of urbanization, the problem of river pollution in China is becoming more and more serious. The requirements for river water quality hydrology monitoring and river foreign matter identification and positioning are becoming more and more serious. In the traditional river channel treatment, the water quality hydrological data acquisition usually depends on a manual acquisition mode, the water quality hydrological data acquired by the mode has the defect of inaccuracy, and a large amount of time and labor cost are consumed; the traditional river foreign matter cleaning method adopts a manual cruising mode, the foreign matter position is not clear, the cleaning process is long in time consumption, large in workload and slow in effect.
Disclosure of Invention
The invention aims to solve the technical problem that the position and the type of foreign matters are difficult to judge by the conventional river channel treatment method.
In order to achieve the purpose, the invention provides a river foreign matter identification method, which comprises the following steps: a node setting step, in which a plurality of nodes are uniformly arranged in the river channel; a node data acquisition step of receiving node data acquired by a node; a video data acquisition step, wherein video data are acquired; a data uploading step of uploading the video data to a server; and an identification step, wherein the video data is input into a classifier to identify the type of the foreign matter.
Further, the identifying step comprises the steps of: a picture inputting step, namely inputting at least one picture in the video data; a characteristic extraction step, namely extracting at least one characteristic map of the picture; a candidate region generation step, namely sending the feature maps into respective region suggestion networks to form candidate regions; a characteristic map processing step of processing the characteristic map in a normalization manner; a transmission step, wherein at least one feature map after normalization processing is input into a classifier; and a foreign matter identification step of identifying the foreign matter category in the video data according to the feature map.
Further, in the node data acquisition step, an activation signal is sent to the node to activate the node; collecting node data; uploading the node data to the drone.
Further, the node data comprises at least one of temperature, pH value, turbidity and conductivity of the water in the river channel.
Further, in the data uploading step, the position data where the video data is shot is uploaded to the server.
Further, the river foreign matter identification method further comprises the following steps: and a real-time display step of displaying the node data, the video data, the position data and the recognized foreign matter category from the unmanned aerial vehicle in real time.
In order to achieve the above object, the present invention further provides a river foreign matter monitoring platform system, including: the node is used for collecting node data of the river water quality; the unmanned aerial vehicle platform is used for receiving and forwarding the node data and acquiring video data of a river channel; and the monitoring cloud platform is used for identifying and displaying the node data and the video data in real time.
Further, the monitoring cloud platform comprises: the river foreign matter identification module is used for identifying video data sent by the unmanned aerial vehicle platform; and the data display module is used for displaying data in real time.
Further, the data comprises the node data, the video data and position data of the video shooting position uploaded by the unmanned aerial vehicle.
Further, the node comprises: the processor module is used for analyzing and detecting the data of the water quality in the river channel; the LoRa wireless module is used for transmitting data; the data acquisition module is used for acquiring the data of the water quality in the river channel; and the solar power supply module is used for supplying power to the node.
The invention has the technical effects that the acquisition and transmission of the river water quality hydrological data are carried out by utilizing an Internet of things networking mode based on LoRa and taking an unmanned aerial vehicle as a mobile meter reading gateway. A monitoring cloud platform is built on a server, so that a user can see river channel videos, river channel detection data, river channel foreign matter identification categories and positions in real time, and river channel water quality hydrological change trend prediction is carried out by combining detection data of previous times, so that the method is beneficial to positioning and removing river channel foreign matters, predicting and preventing water quality change, a data base is provided for river channel treatment, manpower and material resources are saved, and the efficiency is improved.
Drawings
The technical solution and other advantages of the present application will become apparent from the detailed description of the embodiments of the present application with reference to the accompanying drawings.
Fig. 1 is a flowchart of a river foreign matter identification method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a river foreign matter identification module according to an embodiment of the present invention;
fig. 3 is a schematic view of a river foreign matter monitoring platform system according to an embodiment of the present method;
and 4 is a schematic diagram of the node according to the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It is to be understood that the embodiments described are only a few embodiments of the present application and not all 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.
In the description of the present application, it is to be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," and the like are used in the orientations and positional relationships indicated in the drawings for convenience in describing the present application and for simplicity in description, and are not intended to indicate or imply that the referenced devices or elements must have a particular orientation, be constructed in a particular orientation, and be operated in a particular manner, and are not to be construed as limiting the present application. Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first", "second", may explicitly or implicitly include one or more of the described features. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
In the description of the present application, it is to be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; may be mechanically connected, may be electrically connected or may be in communication with each other; either directly or indirectly through intervening media, either internally or in any other relationship. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as appropriate.
In this application, unless expressly stated or limited otherwise, the first feature "on" or "under" the second feature may comprise direct contact of the first and second features, or may comprise contact of the first and second features not directly but through another feature in between. Also, the first feature being "on," "above" and "over" the second feature includes the first feature being directly on and obliquely above the second feature, or merely indicating that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature includes the first feature being directly under and obliquely below the second feature, or simply meaning that the first feature is at a lesser elevation than the second feature.
The following disclosure provides many different embodiments or examples for implementing different features of the application. In order to simplify the disclosure of the present application, specific example components and arrangements are described below. Of course, they are merely examples and are not intended to limit the present application. Moreover, the present application may repeat reference numerals and/or letters in the various examples, such repetition is for the purpose of simplicity and clarity and does not in itself dictate a relationship between the various embodiments and/or configurations discussed. In addition, examples of various specific processes and materials are provided herein, but one of ordinary skill in the art may recognize applications of other processes and/or use of other materials.
Specifically, referring to fig. 1, an embodiment of the present application provides a method for identifying foreign matters in a river, including steps S1-S6.
And S1 node setting, namely uniformly setting a plurality of nodes in the river channel, wherein the nodes comprise a processor module, a LoRa wireless module, a data acquisition module, a solar power supply module, a debugging module, an alarm module and the like. The node is normally set to be in a low power consumption mode, and the node is activated and started once an activation instruction from a gateway is received.
The processor module is a control core of the nodes of the Internet of things and is mainly used for functions of data analysis, data packaging, node state monitoring and the like of the acquisition module. The data acquisition module acquires the temperature, the pH value and the turbidity of water quality in the river channel through the ADC, and acquires the conductivity and the dissolved oxygen of the water quality in the river channel through the RS485 to form node data. In this embodiment, the wireless communication module preferably uses a low power consumption LoRa module for data transmission. The solar power supply module supplies power for the nodes in a mode of selecting a solar cell panel and a lithium battery. The alarm module and the debugging module are used for comprehensively judging parameters of water quality in the river channel after the node data are collected, and judging whether the water quality in the river channel is foreign matter garbage or not.
And S2, acquiring node data, namely receiving the node data acquired by the node. Specifically, when flying above the river channel, the unmanned aerial vehicle, as a gateway of the Internet of things for water quality detection, sends an activation command to a water quality detection node in the river channel, and activates the node. When the node is started, the node starts to continuously acquire node data of water quality in the river channel through the data acquisition module, wherein the node data comprises at least one of temperature, pH value, turbidity and conductivity of the water quality in the river channel. Through loRa wireless module will node data upload reach unmanned aerial vehicle, unmanned aerial vehicle receives node data that the node sent out.
And S3, carrying a pod after the unmanned aerial vehicle is started, collecting video data above the river channel, shooting river channel videos, and providing basic video data for line patrol flight and subsequent river channel foreign matter identification. The unmanned aerial vehicle carries a TX2 processor as an onboard processor to perform image control processing, and the video shot by the pod is subjected to primary processing to obtain river channel outline information in the field of view of the pod, so that functions of unmanned aerial vehicle river channel line patrol flight and the like are realized. The unmanned aerial vehicle uses the ROS system to carry out unmanned aerial vehicle application development, fuses image processing data and GPS positioning data, and realizes autonomous take-off inspection, meter reading and landing of the unmanned aerial vehicle.
And S4 data uploading step, wherein the unmanned aerial vehicle carries a 4G module and uploads the node data obtained by the unmanned aerial vehicle, the video data and the collected node position data at the video data position to the server, so that the server can further detect and identify the node data and the video data.
And an identification step of S5, wherein the type of the foreign matter is identified. Specifically, the video data is identified and processed by adopting a multi-scale image pyramid fusion algorithm, a rough image pyramid is established for an input image, and small target detection is completed by fusing high-level semantic information and low-level position information. The algorithm introduces multi-scale detection to the fast-RCNN, that is, the detection is not performed solely by means of the feature map (feature map) of the last layer, but the operation of generating candidate regions is performed on feature maps (feature maps) of multiple scales in the network, as shown in fig. 2, and specifically includes a picture entry step, a feature extraction step, a candidate region generation step, a feature map processing step, a transmission step, and a foreign object identification step.
And in the picture inputting step, inputting at least one picture in the video data.
In the characteristic extraction step, the picture is subjected to characteristic extraction through a convolutional neural network, and a plurality of characteristic maps with different scales of the picture are extracted from different layers.
In the candidate Region generating step, the feature maps are sent to respective Region suggestion networks to form candidate Regions (RPNs). In the process, RPNs corresponding to different scales are different, because the receptive field of low-level neurons is small, and the sizes of corresponding anchor frames (anchor boxes) are also small, the candidate regions obtained by the features of lower levels are smaller, and the specific anchor setting is explained in detail in an experimental link.
And in the transmission step, transmitting the normalized feature map to a classifier. For the ZF network, the output of 3 layers, conv2 and conv5, is sent to a candidate region generating network and ROI pooling for multi-scale detection; for the VGGl6 network, the 5 layers of outputs conv1_2, conv2_2, conv3_3, conv4_3 and conv5_3 are sent to the candidate region generation network and ROI posing for multi-scale detection.
In the foreign matter identification step, the foreign matter category in the video data is identified according to the feature map.
And S6, displaying the processed video data, the node data, the position data, the foreign matter category information judged by the classifier and the like on a monitoring screen in real time, so that the related data can be conveniently known in real time. In the real-time display step, the core is a monitoring cloud platform, the monitoring cloud platform comprises a database server, a monitoring center large screen and the like, and is used for receiving video data, node data and position data from an unmanned aerial vehicle, foreign matter category information obtained by the classifier and the like, processing the foreign matter category information and displaying the processed foreign matter category information on the monitoring center large screen.
The monitoring cloud platform adopts a B-S framework, a front-end webpage takes ES6 as a main part, a act + ant framework is adopted, and an application service layer of the monitoring cloud platform comprises login authentication, unmanned aerial vehicle state display, unmanned aerial vehicle track display, water quality data real-time display, water quality data analysis, river channel video display, river channel foreign matter identification display, water quality historical data display and the like. The login authentication of an administrator is realized, the real-time display of the flight track of the unmanned aerial vehicle is realized, the real-time data and the historical data of the water quality parameters of the monitoring nodes are displayed, and the real-time display and the historical video of the videos shot by the unmanned aerial vehicle and the videos processed by the images are viewed. The unmanned aerial vehicle positioning is realized, and the real-time video display of the unmanned aerial vehicle and the actual position matching interaction function of the unmanned aerial vehicle are completed.
The background mainly uses python + flash development technology, selects PostgreSQL to build a monitoring platform database, records include but not limited to real-time river channel water quality data and historical data after analysis, and records video stream data and river channel foreign matter recognition results transmitted by the unmanned aerial vehicle.
In the water quality analysis module, not only are traditional data statistics modules such as basic mean values, variances and the most values designed, but also a gray prediction model is provided for predicting the future development trend of the parameters. The gray prediction has the advantages of less sample data, simple principle, convenient operation, high short-term prediction precision, capability of inspection and the like.
Because untreated raw actual measurement data of water quality monitoring cannot be compared, in order to eliminate some unreasonable influences possibly caused by different dimensions, the raw data of water quality monitoring should be standardized in a unified manner. The method for standardizing the water quality monitoring original data comprises the following steps:
wherein x isiData for the ith batch is represented, u represents the mean of all data of that type, and σ represents the variance of the batch of data.
The monitoring cloud platform receives node data and river course real-time video data transmitted by the unmanned aerial vehicle, and carries out real-time processing on river course videos through the river course rubbish recognition module. Through the data analysis module, historical data and the detection data are combined, the river water quality hydrological information is analyzed and predicted, and relevant departments can manage in time according to analysis results.
The technical effect of the river foreign matter identification method is that the river water quality hydrology data acquisition and transmission are carried out by using an internet of things networking mode based on LoRa and using an unmanned aerial vehicle as a mobile meter reading gateway. A monitoring cloud platform is built on a server, so that a user can see river channel videos, river channel detection data and river channel foreign matter identification results in real time, and river channel water quality hydrological change trend prediction is carried out by combining detection data of previous times in the follow-up process, so that the positioning and removal of river channel foreign matters and the prediction and prevention of water quality change are facilitated, and a data basis is provided for river channel treatment.
The embodiment also provides a river foreign matter monitoring platform system, including and node, unmanned aerial vehicle platform and control cloud platform (see fig. 3).
As shown in fig. 4, the node is a water quality data acquisition unit, and includes a processor module, a LoRa wireless module, a data acquisition module, a solar power supply module, a debugging module, an alarm module, and the like.
The processor module is a control core of the nodes of the Internet of things and is mainly used for functions of data analysis, data packaging, node state monitoring and the like of the acquisition module.
The data acquisition module acquires the temperature, the pH value and the turbidity of water quality in the river channel through the ADC, and acquires the conductivity and the dissolved oxygen of the water quality in the river channel through the RS485 to form node data.
In this embodiment, the wireless communication module preferably uses a low power consumption LoRa module for data transmission.
The solar power supply module supplies power for the nodes in a mode of selecting a solar cell panel and a lithium battery.
The alarm module and the debugging module are used for comprehensively judging parameters of water quality in the river channel after the node data are collected, and judging whether the water quality in the river channel is foreign matter garbage or not.
The drone platform includes a drone entity, a LoRa module, a GPRS/4G module, a pod module, and a TX2 processor. The unmanned aerial vehicle platform is mainly responsible for receiving and forwarding river channel node data and shooting river channel monitoring videos.
The unmanned aerial vehicle entity carries on LoRa module and GPRS/4G module, realizes right the activation of water quality testing node is handled, and follows the node data that its collection was received to the water quality testing node.
The unmanned aerial vehicle entity carries on the LoRa module and the GPRS/4G module, and data transmission and control instruction feedback between the cloud platforms are achieved and monitored.
The unmanned aerial vehicle entity carries on the nacelle module, realizes the holistic shooting function in river course, obtains video data.
The unmanned aerial vehicle entity carries a TX2 processor as an onboard processor to perform image control processing, and the video shot by the pod is subjected to primary processing to obtain river course outline information in the field of view of the pod, so that functions of unmanned aerial vehicle river course line patrol flight and the like are realized. The unmanned aerial vehicle uses the ROS system to carry out unmanned aerial vehicle application development, fuses image processing data and GPS positioning data, and realizes autonomous take-off inspection, meter reading and landing of the unmanned aerial vehicle.
The monitoring cloud platform comprises a database server, a large monitoring center screen, a river foreign matter identification module and the like, and is used for receiving video data, node data and position data from the unmanned aerial vehicle, processing the video data, the node data and the position data and displaying the processed data on the large monitoring center screen.
The river foreign matter identification module adopts a multi-scale image pyramid fusion algorithm, a rough image pyramid is established for an input picture, and small target detection is completed by fusing high-level semantic information and low-level position information. The algorithm introduces multi-scale detection to the fast-RCNN, namely, the detection is not only carried out by depending on the feature map (feature map) of the last layer, but the operation of generating candidate regions is carried out on the feature maps (feature maps) of multiple scales in the network.
The monitoring cloud platform adopts a B-S framework, a front-end webpage takes ES6 as a main part, a act + ant framework is adopted, and an application service layer of the monitoring cloud platform comprises login authentication, unmanned aerial vehicle state display, unmanned aerial vehicle track display, water quality data real-time display, water quality data analysis, river channel video display, river channel foreign matter identification display, water quality historical data display and the like. The login authentication of an administrator is realized, the real-time display of the flight track of the unmanned aerial vehicle is realized, the real-time data and the historical data of the water quality parameters of the monitoring nodes are displayed, and the real-time display and the historical video of the videos shot by the unmanned aerial vehicle and the videos processed by the images are viewed. The unmanned aerial vehicle positioning is realized, and the real-time video display of the unmanned aerial vehicle and the actual position matching interaction function of the unmanned aerial vehicle are completed.
The background mainly uses python + flash development technology, selects PostgreSQL to build a monitoring platform database, records include but not limited to real-time river channel water quality data and historical data after analysis, and records video stream data and river channel foreign matter recognition results transmitted by the unmanned aerial vehicle.
In the water quality analysis module, not only are traditional data statistics modules such as basic mean values, variances and the most values designed, but also a gray prediction model is provided for predicting the future development trend of the parameters. The gray prediction has the advantages of less sample data, simple principle, convenient operation, high short-term prediction precision, capability of inspection and the like.
Because untreated raw actual measurement data of water quality monitoring cannot be compared, in order to eliminate some unreasonable influences possibly caused by different dimensions, the raw data of water quality monitoring should be standardized in a unified manner. The method for standardizing the water quality monitoring original data comprises the following steps:
wherein x isiData for the ith batch is represented, u represents the mean of all data of that type, and σ represents the variance of the batch of data.
The monitoring cloud platform receives node data and river course real-time video data transmitted by the unmanned aerial vehicle, and carries out real-time processing on river course videos through the river course rubbish recognition module. Through the data analysis module, historical data and the detection data are combined, the river water quality hydrological information is analyzed and predicted, and relevant departments can manage in time according to analysis results.
This embodiment river foreign matter monitoring platform system's technical effect lies in, utilizes the thing networking mode based on loRa to unmanned aerial vehicle is the removal gateway of checking meter, carries out river course quality of water hydrology data acquisition and transmission. A monitoring cloud platform is built on a server, so that a user can see river channel videos, river channel detection data and river channel foreign matter identification results in real time, and river channel water quality hydrological change trend prediction is carried out by combining detection data of previous times in the follow-up process, so that the positioning and removal of river channel foreign matters and the prediction and prevention of water quality change are facilitated, and a data basis is provided for river channel treatment.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
The river foreign matter identification method and the river foreign matter monitoring platform system provided by the embodiment of the application are introduced in detail, a specific example is applied in the text to explain the principle and the implementation mode of the application, and the description of the embodiment is only used for helping to understand the technical scheme and the core idea of the application; those of ordinary skill in the art will understand that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications or substitutions do not depart from the spirit and scope of the present disclosure as defined by the appended claims.
Claims (10)
1. A river foreign matter identification method is characterized by comprising the following steps:
a node setting step, in which a plurality of nodes are uniformly arranged in the river channel;
a node data acquisition step of receiving node data acquired by a node;
a video data acquisition step, wherein video data are acquired;
a data uploading step of uploading the video data to a server; and
and an identification step, wherein the video data is input into a classifier so as to identify the type of the foreign matter.
2. The method for identifying a foreign matter in a river according to claim 1,
the identifying step includes the steps of:
a picture inputting step, namely inputting at least one picture in the video data;
a characteristic extraction step, namely extracting at least one characteristic map of the picture;
a candidate region generation step, namely sending the feature maps into respective region suggestion networks to form candidate regions;
a characteristic map processing step of processing the characteristic map in a normalization manner;
a transmission step, wherein at least one feature map after normalization processing is input into a classifier; and
and a foreign matter identification step, namely identifying the foreign matter category in the video data according to the characteristic map.
3. The method for identifying a foreign matter in a river according to claim 1,
in the node-data collecting step,
sending an activation signal to the node to activate the node;
collecting node data;
and uploading the node data to an unmanned aerial vehicle or a server.
4. The method for identifying a foreign matter in a river according to claim 1,
the node data comprises at least one of temperature, pH value, turbidity and conductivity of water in the river channel.
5. The method for identifying a foreign matter in a river according to claim 1,
in the data uploading step, the data is uploaded,
and uploading the position data of the nodes to the server.
6. The river foreign matter identification method according to claim 5, further comprising the steps of:
and a real-time display step of displaying the node data, the video data, the position data and the recognized foreign matter category from the unmanned aerial vehicle in real time.
7. The utility model provides a river foreign matter monitoring platform system which characterized in that includes:
the node is used for collecting node data of the river water quality;
the unmanned aerial vehicle platform is used for receiving and forwarding the node data and acquiring video data of a river channel; and
and the monitoring cloud platform is used for identifying and displaying the node data and the video data in real time.
8. The river foreign matter monitoring platform system of claim 7,
the monitoring cloud platform comprises:
the river foreign matter identification module is used for identifying video data sent by the unmanned aerial vehicle platform; and
and the data display module is used for displaying data in real time.
9. The river foreign matter monitoring platform system of claim 8,
the data includes the node data, the video data, and location data of the node.
10. The river foreign matter monitoring platform system of claim 8,
the node comprises:
the processor module is used for analyzing and detecting the data of the water quality in the river channel;
the LoRa wireless module is used for transmitting data;
the data acquisition module is used for acquiring the data of the water quality in the river channel; and
and the solar power supply module is used for supplying power to the node.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911421334.5A CN111060079A (en) | 2019-12-31 | 2019-12-31 | River foreign matter identification method and river foreign matter monitoring platform system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911421334.5A CN111060079A (en) | 2019-12-31 | 2019-12-31 | River foreign matter identification method and river foreign matter monitoring platform system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111060079A true CN111060079A (en) | 2020-04-24 |
Family
ID=70306011
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911421334.5A Pending CN111060079A (en) | 2019-12-31 | 2019-12-31 | River foreign matter identification method and river foreign matter monitoring platform system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111060079A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112118421A (en) * | 2020-09-11 | 2020-12-22 | 杭州市地下管道开发有限公司 | Intelligent river patrol method, device, storage medium and electronic equipment |
| CN112511803A (en) * | 2020-11-20 | 2021-03-16 | 济南浪潮高新科技投资发展有限公司 | Water flow management system, method and equipment based on cloud edge end |
| CN113344885A (en) * | 2021-06-15 | 2021-09-03 | 温州大学 | River floating object detection method based on cascade convolution neural network |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102608567A (en) * | 2012-01-19 | 2012-07-25 | 中国人民解放军第三军医大学野战外科研究所 | Method for positioning soldier on battlefield on basis of mobile beacon of unmanned aerial vehicle |
| CN106534811A (en) * | 2017-01-12 | 2017-03-22 | 王昱淇 | Unmanned aerial vehicle monitoring system for monitoring floating objects in water |
| CN206505070U (en) * | 2017-02-06 | 2017-09-19 | 无锡市太湖闸站工程管理处 | Its clean ship integrated water quality supervision examining system |
| CN107727081A (en) * | 2017-09-28 | 2018-02-23 | 成都万江港利科技股份有限公司 | A kind of intelligence based on He Hu storehouses ditch patrols river system system |
| CN109040302A (en) * | 2018-09-06 | 2018-12-18 | 中天飞龙（北京）智能科技股份有限公司 | Vacant lot information on soil moisture acquisition system |
| CN109300336A (en) * | 2018-11-05 | 2019-02-01 | 华南农业大学 | A kind of unmanned plane traversal Route optimization method and system of farmland quality monitoring node |
| CN109460754A (en) * | 2019-01-31 | 2019-03-12 | 深兰人工智能芯片研究院（江苏）有限公司 | A kind of water surface foreign matter detecting method, device, equipment and storage medium |
| CN208921175U (en) * | 2018-10-23 | 2019-05-31 | 武汉奥恒胜科技有限公司 | A kind of monitoring water quality on line system |
| CN110062345A (en) * | 2019-04-09 | 2019-07-26 | 深圳大学 | A kind of unmanned plane-internet of things data acquisition method and system |
| CN110060177A (en) * | 2019-04-17 | 2019-07-26 | 四川万江一泓环境科技有限责任公司 | It is a kind of sky Incorporate monitoring water quality on line and pollution traceability system |
| CN110082295A (en) * | 2018-01-25 | 2019-08-02 | 芯视界（北京）科技有限公司 | Water quality monitoring system and method |
| CN110082498A (en) * | 2019-04-08 | 2019-08-02 | 三峡大学 | A kind of landslide monitoring data unmanned plane acquisition system based on wireless sensor Internet of Things |
| CN110146675A (en) * | 2019-05-31 | 2019-08-20 | 甘肃省祁连山水源涵养林研究院 | A kind of hydrographic information monitoring system |
| CN110169340A (en) * | 2019-05-24 | 2019-08-27 | 华南农业大学 | A kind of orchard management based on UAV Communication and control system and method |
| CN110414334A (en) * | 2019-06-20 | 2019-11-05 | 浙江大学 | A kind of smart water quality recognition methods maked an inspection tour based on unmanned plane |
| CN110456016A (en) * | 2019-07-30 | 2019-11-15 | 苏州雷蓝遥感科技有限公司 | A kind of water pollution multi-source remote sensing monitoring method based on Internet of Things |
| CN110611797A (en) * | 2019-09-26 | 2019-12-24 | 武汉神州地理软件开发有限公司 | Water quality map achievement display system |
-
2019
- 2019-12-31 CN CN201911421334.5A patent/CN111060079A/en active Pending
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102608567A (en) * | 2012-01-19 | 2012-07-25 | 中国人民解放军第三军医大学野战外科研究所 | Method for positioning soldier on battlefield on basis of mobile beacon of unmanned aerial vehicle |
| CN106534811A (en) * | 2017-01-12 | 2017-03-22 | 王昱淇 | Unmanned aerial vehicle monitoring system for monitoring floating objects in water |
| CN206505070U (en) * | 2017-02-06 | 2017-09-19 | 无锡市太湖闸站工程管理处 | Its clean ship integrated water quality supervision examining system |
| CN107727081A (en) * | 2017-09-28 | 2018-02-23 | 成都万江港利科技股份有限公司 | A kind of intelligence based on He Hu storehouses ditch patrols river system system |
| CN110082295A (en) * | 2018-01-25 | 2019-08-02 | 芯视界（北京）科技有限公司 | Water quality monitoring system and method |
| CN109040302A (en) * | 2018-09-06 | 2018-12-18 | 中天飞龙（北京）智能科技股份有限公司 | Vacant lot information on soil moisture acquisition system |
| CN208921175U (en) * | 2018-10-23 | 2019-05-31 | 武汉奥恒胜科技有限公司 | A kind of monitoring water quality on line system |
| CN109300336A (en) * | 2018-11-05 | 2019-02-01 | 华南农业大学 | A kind of unmanned plane traversal Route optimization method and system of farmland quality monitoring node |
| CN109460754A (en) * | 2019-01-31 | 2019-03-12 | 深兰人工智能芯片研究院（江苏）有限公司 | A kind of water surface foreign matter detecting method, device, equipment and storage medium |
| CN110082498A (en) * | 2019-04-08 | 2019-08-02 | 三峡大学 | A kind of landslide monitoring data unmanned plane acquisition system based on wireless sensor Internet of Things |
| CN110062345A (en) * | 2019-04-09 | 2019-07-26 | 深圳大学 | A kind of unmanned plane-internet of things data acquisition method and system |
| CN110060177A (en) * | 2019-04-17 | 2019-07-26 | 四川万江一泓环境科技有限责任公司 | It is a kind of sky Incorporate monitoring water quality on line and pollution traceability system |
| CN110169340A (en) * | 2019-05-24 | 2019-08-27 | 华南农业大学 | A kind of orchard management based on UAV Communication and control system and method |
| CN110146675A (en) * | 2019-05-31 | 2019-08-20 | 甘肃省祁连山水源涵养林研究院 | A kind of hydrographic information monitoring system |
| CN110414334A (en) * | 2019-06-20 | 2019-11-05 | 浙江大学 | A kind of smart water quality recognition methods maked an inspection tour based on unmanned plane |
| CN110456016A (en) * | 2019-07-30 | 2019-11-15 | 苏州雷蓝遥感科技有限公司 | A kind of water pollution multi-source remote sensing monitoring method based on Internet of Things |
| CN110611797A (en) * | 2019-09-26 | 2019-12-24 | 武汉神州地理软件开发有限公司 | Water quality map achievement display system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112118421A (en) * | 2020-09-11 | 2020-12-22 | 杭州市地下管道开发有限公司 | Intelligent river patrol method, device, storage medium and electronic equipment |
| CN112511803A (en) * | 2020-11-20 | 2021-03-16 | 济南浪潮高新科技投资发展有限公司 | Water flow management system, method and equipment based on cloud edge end |
| CN113344885A (en) * | 2021-06-15 | 2021-09-03 | 温州大学 | River floating object detection method based on cascade convolution neural network |
| CN113344885B (en) * | 2021-06-15 | 2024-07-02 | 温州大学 | River float detection method based on cascade convolution neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210389293A1 (en) | Methods and Systems for Water Area Pollution Intelligent Monitoring and Analysis | |
| CN108109385B (en) | System and method for identifying and judging dangerous behaviors of power transmission line anti-external damage vehicle | |
| CN111060079A (en) | River foreign matter identification method and river foreign matter monitoring platform system | |
| CN110472510A (en) | Based on infrared and visual picture electrical equipment fault detection method and assessment equipment | |
| CN208119426U (en) | A kind of more rotor automatically taking water sample unmanned planes | |
| CN109376660B (en) | Target monitoring method, device and system | |
| CN111831430A (en) | Electrical equipment defect identification system based on edge calculation | |
| CN113589837A (en) | Electric power real-time inspection method based on edge cloud | |
| CN113205039B (en) | Power equipment fault image recognition disaster investigation system and method based on multiple DCNN networks | |
| CN113850562B (en) | Intelligent side station supervision method and system | |
| CN113450573A (en) | Traffic monitoring method and traffic monitoring system based on unmanned aerial vehicle image recognition | |
| CN115082813A (en) | Detection method, unmanned aerial vehicle, detection system and medium | |
| CN112508911A (en) | Rail joint touch net suspension support component crack detection system based on inspection robot and detection method thereof | |
| CN112016380B (en) | Wild animal monitoring method and system | |
| CN114744756A (en) | Intelligent power transmission line inspection system based on machine vision | |
| CN113723184A (en) | Scene recognition system, method and device based on intelligent gateway and intelligent gateway | |
| CN115457297B (en) | Oil leakage detection method and device for aviation oil depot and aviation oil safety operation and maintenance system | |
| CN116866512A (en) | Photovoltaic power station inspection system and operation method thereof | |
| CN118038216B (en) | Automatic upgrading method and system for edge equipment target detection algorithm | |
| CN114882682B (en) | High-voltage cable state monitoring platform and monitoring method | |
| CN115355952B (en) | Intelligent inspection system for crude oil storage tank | |
| CN203788047U (en) | Patrol management system for state of equipment in transformer station based on video accurate recognition | |
| CN117095316A (en) | Road surface inspection method, device, equipment and readable storage medium | |
| CN113433874B (en) | Unmanned ship integrated control management system based on 5G | |
| CN115905348A (en) | Industrial electricity utilization abnormity early warning method and system of multi-source heterogeneous data |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200424 |