CN112418128B - Surface water monitoring and management system and method - Google Patents
Surface water monitoring and management system and method Download PDFInfo
- Publication number
- CN112418128B CN112418128B CN202011379262.5A CN202011379262A CN112418128B CN 112418128 B CN112418128 B CN 112418128B CN 202011379262 A CN202011379262 A CN 202011379262A CN 112418128 B CN112418128 B CN 112418128B
- Authority
- CN
- China
- Prior art keywords
- water body
- body image
- water
- image
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
-
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- 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
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
Abstract
The invention relates to the technical field of water resource monitoring, in particular to a surface water monitoring and management system, which comprises: the acquisition unit is used for acquiring a water body image of the surface water surface in real time; the filtering unit is used for filtering the water body image; the storage unit is used for storing the filtered water body image; the training unit is used for obtaining a neural network model; the processing unit is used for carrying out floater identification and color identification on the filtered water body image, judging whether the water body is abnormal or not, and marking an abnormal area in the water body image when the water body is abnormal; and the display unit is used for displaying the marked area on the visual interface. The invention combines the neural network to identify the floaters and the color of the water sample image, marks the abnormal area and displays the abnormal area in a visual mode, thereby solving the technical problem that the prior art ignores the obvious changes of the floaters, the color of the water body and the like, and cannot perform early warning in time when the water quality changes.
Description
Technical Field
The invention relates to the technical field of water resource monitoring, in particular to a surface water monitoring management system and a surface water monitoring management method.
Background
Surface water is a general term for dynamic water and static water on the surface of land, and includes various liquid and solid water bodies, mainly rivers, lakes and glaciers, which are very important sources of domestic water for human beings. With the increasing environmental pollution, it is very important to monitor the quality of surface water such as rivers and lakes.
For example, chinese patent CN110456722A discloses a lake water quality monitoring and predicting system, which includes an image acquisition module, an image preprocessing module, a water quality detection module, a temperature detection module, a processing module, a water quality database, a prediction and evaluation module, and a display terminal; the image acquisition module is connected with the image preprocessing module, the processing module is respectively connected with the image preprocessing module, the water quality detection module, the temperature detection module, the water quality database and the prediction evaluation module, the water quality database is respectively connected with the image preprocessing module and the water quality detection module, and the prediction evaluation module is respectively connected with the display terminal.
According to the technical scheme, the lake water color is obtained by collecting and comparing the images of the lake water surface, the safety influence coefficient of the lake water quality is comprehensively counted according to the detected lake water color and by combining the pH value, the dissolved oxygen amount and the bacteria content, and the monitoring and the prediction of the water quality can be realized. However, this method requires a long database as a basis, and is mainly used to detect water quality from a microscopic level, and ignores the obvious changes of water surface floaters, water color and the like, so that early warning cannot be given in time when the water quality changes.
Disclosure of Invention
The invention provides a surface water monitoring and management system, which solves the technical problem that in the prior art, obvious changes such as water surface floaters, water body colors and the like are ignored, so that early warning cannot be timely performed when the water quality changes.
The basic scheme provided by the invention is as follows: surface water monitoring management system includes:
the acquisition unit is used for acquiring a water body image of the surface water surface in real time and transmitting the water body image;
the filtering unit is used for receiving the water body image, filtering the water body image and sending the filtered water body image;
the storage unit is used for receiving the filtered water body image and storing the filtered water body image;
the training unit is used for acquiring the filtered water body image, generating corresponding multi-scale training sample data on the basis of the filtered water body image, and training the neural network by using the multi-scale training sample data to obtain a neural network model;
the processing unit is used for identifying floaters in the filtered water body image according to the neural network model to obtain the number of the floaters on the water surface; carrying out color recognition on the filtered water body image to obtain an RGB difference value between the water body image and a normal image; judging whether the water body is abnormal or not according to the number of the floaters and the RGB difference value, and marking an abnormal area in the water body image when the water body is abnormal;
and the display unit is used for displaying the marked area on the visual interface.
The working principle and the advantages of the invention are as follows: firstly, generating corresponding multi-scale training sample data on the basis of the filtered water body image, and training the neural network by using the multi-scale training sample data, thereby obtaining a neural network model. And then, identifying floaters and colors of the water sample image by combining an image analysis method based on a neural network, marking abnormal areas, and displaying in a visual mode. Therefore, the floating objects on the water surface and the color of the water body can be monitored in real time through image processing and visualization technology processing, so that the obvious change of the water body can be found in time, and related personnel can conveniently master the space state of the water body in time and make a strategy in a pertinence manner.
The invention combines the image analysis method of the neural network, identifies the floaters and the colors of the water sample image, marks abnormal areas and displays the abnormal areas in a visual mode, thereby solving the technical problem that the prior art ignores the obvious changes of the floaters, the colors of the water body and the like, and cannot perform early warning in time when the water quality changes.
Further, the identifying the floating objects specifically includes: extracting key point data of the water sample image, and performing consistency matching through a neural network model to obtain a matching result; and determining the identification result of the floating object according to the matching result.
Has the advantages that: since the key point data represents the essential characteristics of the floating object, the floating object can be quickly and accurately identified in such a way.
Further, the identifying the floating objects specifically includes: performing image segmentation processing on the water body image, and removing information irrelevant to the water body to obtain a segmented image; carrying out gray level processing on the segmented image, and processing the colorful water body image into a gray water body image; and identifying the floating objects in the water body image with the gray scale by adopting an edge detection algorithm.
Has the advantages that: in most cases, floaters are identified based on edge characteristics, in such a way that they can be readily identified using edge detection algorithms.
Further, obtaining the RGB difference between the water body image and the normal image specifically includes: reading RGB values of each pixel point in the water body image and the normal image, converting the RGB values into 16 systems, and storing the 16 systems into two arrays with the width multiplied by the height of the water body image as the size; comparing the data at the same position, and if the data are not equal, calculating the data as 1; and counting the number of the pixels which is 1 and dividing the number by the total number of the pixels of the water body image to obtain the RGB difference value.
Has the advantages that: by the method, the RGB difference value of the water body image and the normal image can be obtained, so that an accurate reference basis is provided for subsequent judgment.
Further, judging whether the water body is abnormal according to the number of the floating objects and the RGB difference specifically includes judging that the water body is abnormal when the number of the floating objects is greater than or equal to the number threshold and the RGB difference is greater than or equal to the difference threshold.
Has the advantages that: by the mode, the number of the floating objects is considered, the color of the water surface is considered, whether the water body is abnormal or not can be accurately judged, and therefore misjudgment is prevented.
The invention also provides a surface water monitoring and management method, which comprises the following steps:
s1, acquiring a water body image of the surface water surface in real time;
s2, filtering the water body image, and storing the filtered water body image;
s3, acquiring the filtered water body image, generating corresponding multi-scale training sample data based on the filtered water body image, and training the neural network by using the multi-scale training sample data to obtain a neural network model;
s4, identifying floaters in the filtered water body image according to the neural network model to obtain the number of the floaters on the water surface; carrying out color recognition on the filtered water body image to obtain an RGB difference value between the water body image and a normal image; judging whether the water body is abnormal or not according to the number of the floaters and the RGB difference value, and marking an abnormal area in the water body image when the water body is abnormal;
and S5, displaying the marked area on the visual interface.
The working principle and the advantages of the invention are as follows: and generating corresponding multi-scale training sample data on the basis of the filtered water body image, and training the neural network by using the multi-scale training sample data so as to obtain a neural network model. And (3) identifying floaters and colors of the water sample image by combining an image analysis method based on a neural network, marking abnormal areas, and displaying in a visual mode. By the method, the floating objects on the water surface and the color of the water body can be monitored in real time.
Further, in S4, the identifying the floating objects specifically includes:
a1, extracting key point data of the water sample image, and performing consistency matching through a neural network model to obtain a matching result;
and A2, determining the identification result of the floating object according to the matching result.
Has the advantages that: in this way, the floating objects can be identified quickly and accurately.
Further, in S4, the identifying the floating objects specifically includes:
b1, carrying out image segmentation processing on the water body image, and removing information irrelevant to the water body to obtain a segmented image;
b2, carrying out gray scale processing on the segmented image, and processing the color water body image into a gray water body image;
and B3, adopting an edge detection algorithm to identify the floating objects in the water body image with the gray scale.
Has the advantages that: in most cases, in this way, floaters can be identified conveniently by using an edge detection algorithm, thereby improving the efficiency of identification.
Further, obtaining the RGB difference between the water body image and the normal image specifically includes:
c1, reading the RGB values of each pixel point in the water body image and the normal image, converting the RGB values into a 16-system value, and storing the 16-system value into two arrays with the width multiplied by the height of the water body image as the size;
c2, comparing the data at the same position, and if not, counting as 1;
and C3, counting the number of 1, and dividing by the total number of pixel points of the water body image to obtain the RGB difference value.
Has the advantages that: by the method, the RGB difference value of the water body image and the normal image can be obtained, so that an accurate reference basis is provided for subsequent judgment.
Further, in S4, it is determined whether the water body is abnormal or not according to the number of the floating objects and the RGB difference value, specifically, when the number of the floating objects is greater than or equal to the number threshold value and the RGB difference value is greater than or equal to the difference threshold value, it is determined that the water body is abnormal.
Has the advantages that: therefore, the number of the floating objects and the color of the water surface are considered, whether the water body is abnormal or not can be accurately judged, and misjudgment is prevented.
Drawings
Fig. 1 is a block diagram of a system structure of an embodiment of a surface water monitoring and management system of the present invention.
Fig. 2 is a schematic structural diagram of an acquisition device in an embodiment 3 of a water environment big data monitoring system according to the present invention.
Detailed Description
The following is further detailed by the specific embodiments:
reference numerals in the drawings of the specification include: the device comprises a first supporting rod 1, a second supporting rod 2, a rotating rod 3, a pin 4, a spring 5, a tension sensor 6, a controller 7, a water quality detector 8, a filter plate 9 and a shell 10.
Example 1
The embodiment of the surface water monitoring and management system of the invention is basically as shown in the attached figure 1, and comprises the following components:
the acquisition unit is used for acquiring a water body image of the surface water surface in real time and transmitting the water body image;
the filtering unit is used for receiving the water body image, filtering the water body image and sending the filtered water body image;
the storage unit is used for receiving the filtered water body image and storing the filtered water body image;
the training unit is used for acquiring the filtered water body image, generating corresponding multi-scale training sample data on the basis of the filtered water body image, and training the neural network by using the multi-scale training sample data to obtain a neural network model;
the processing unit is used for identifying floaters in the filtered water body image according to the neural network model to obtain the number of the floaters on the water surface; carrying out color recognition on the filtered water body image to obtain an RGB difference value between the water body image and a normal image; judging whether the water body is abnormal or not according to the number of the floaters and the RGB difference value, and marking an abnormal area in the water body image when the water body is abnormal;
and the display unit is used for displaying the marked area on the visual interface.
In this embodiment, the acquisition unit is a camera or a video camera; the filtering unit, the training unit and the processing unit are all integrated on the server, and the functions of the filtering unit, the training unit and the processing unit are realized through software/programs/codes; the storage unit is a solid state disk and is arranged on the server; the display unit is a display screen.
The specific implementation process is as follows:
and S1, acquiring the water body image of the surface water surface in real time.
The method comprises the steps of acquiring water body images of the surface water surface of the surface water in real time for 24 hours through a camera or a video camera, for example, a river, and sending the water body images to a server after the acquisition is finished.
And S2, filtering the water body image, and storing the filtered water body image.
After the server receives the water body image, the filtering unit performs filtering processing on the water body image, specifically, in this embodiment, a median filtering algorithm is used to filter the water body image, and the water body image is stored in a solid state disk on the server after the processing is completed.
And S3, acquiring the filtered water body image, generating corresponding multi-scale training sample data based on the filtered water body image, and training the neural network by using the multi-scale training sample data to obtain a neural network model.
In this embodiment, a large number of previously acquired water body images are stored in the solid state disk in advance, and the water body images acquired each time are filtered and then placed in the solid state disk, so that the number of the water body images in the solid state disk is continuously increased. Therefore, in this embodiment, the water body image acquired from the solid state disk includes both the water body image acquired this time and the water body image acquired in the past time, and a large number of water sample images in the solid state disk may be used as training data to train the neural network model.
Specifically, firstly, extracting key point data from an obtained water sample image, and generating multi-scale training sample data corresponding to the water sample image, wherein the key point data comprises color gradient data, size data, shape data and curvature data of an observed floater under different scales and water bloom form data near the floater; and then, taking the multi-scale training sample data as a training data set, training the neural network, and obtaining a corresponding neural network model.
S4, identifying floaters in the filtered water body image according to the neural network model to obtain the number of the floaters on the water surface; carrying out color recognition on the filtered water body image to obtain an RGB difference value between the water body image and a normal image; and judging whether the water body is abnormal or not according to the number of the floating objects and the RGB difference value, and marking the abnormal area in the water body image when the water body is abnormal.
First, float identification is performed. That is, the key point data of the water sample image collected this time, for example, the color gradient data, the size data, the shape data, the curvature data of the floating object, and the water bloom shape data near the floating object are extracted. After extraction is finished, consistency matching is carried out through the neural network model to obtain a matching result, and the identification result of the floater is determined. For example, the result of consistency matching performed by the neural network model indicates that the color gradient data, the size data, the shape data and the curvature data of the floating objects in the water sample image collected this time and the water bloom form data near the floating objects are consistent with the color gradient data, the size data, the shape data and the curvature data of the plastic bottles in a certain water sample image in the database and the water bloom form data near the plastic bottles, so that the floating objects in the water sample image collected this time are plastic bottles, and the number of the plastic bottles is counted.
And then, calculating the RGB difference value between the water body image and the normal image. Specifically, in this embodiment, the solid-state hard disk further stores a normal image of the surface water level. Extracting a normal picture from the solid state disk, reading the RGB value of each pixel point in the collected water body image and the normal image, converting the RGB value of each pixel point into a 16-system form, and storing the form into two arrays with the width multiplied by the height of the collected water body image as the size. And comparing the data at the same position, counting the number of the data as 1 if the data are not equal to 1, and dividing the number by the total number of the pixel points of the water body image acquired at this time to obtain an RGB difference value, wherein the RGB difference value is 0.05 for example.
And finally, judging whether the water body is abnormal or not according to the number of the floating objects and the RGB difference value. In this embodiment, the number threshold is 10, the difference threshold is 0.10, and when the number of the floating objects is greater than or equal to 10 and the RGB difference is greater than or equal to 0.10, it is determined that the water body is abnormal; otherwise, the water body is judged to be normal. When the water body is abnormal, the abnormal area in the water body image acquired this time is marked in a wire frame or highlight mode.
And S5, displaying the marked area on the visual interface.
And finally, displaying the area marked with the water body abnormity in the acquired water body image on a display screen, thereby facilitating relevant personnel to take measures in time.
Example 2
The difference from embodiment 1 is that, when the floating object is identified, the floating object is identified by the edge detection algorithm, and if the floating object cannot be identified, the floating object is identified according to the key point data. The steps of identifying the float by the edge detection algorithm are as follows: firstly, image segmentation processing is carried out on a water body image, for example, the water body image acquired at this time is subjected to image segmentation processing by adopting a region segmentation technology, information irrelevant to the water body is removed, and a segmented image is obtained. Then, the segmented image is subjected to gray scale processing, for example, a maximum value method, an average value method or a weighted average value method is adopted to process the color water body image into a gray water body image. And finally, identifying the floating objects in the water body image with the gray scale by adopting an edge detection algorithm. That is, the edge is detected according to the extreme value of the gray scale weighting difference of the upper and lower and left and right adjacent points of the pixel point, and the contour of the region in the water body image is extracted, so that the floater is identified.
Example 3
The difference from the embodiment 2 is only that the device further comprises a collecting device, as shown in the attached figure 2, the collecting device comprises: the device comprises a first supporting rod 1, a second supporting rod 2, a rotating rod 3, a pin 4, a spring 5, a tension sensor 6, a controller 7, a water quality detector 8, a filter plate 9 and a shell 10. The shell 10 is cylindrical, and the filter plates 9 are mounted at the left end and the right end of the shell 10, for example, by screws; a plurality of filter holes are drilled on the filter plates 9. One end of the first supporting rod 1 is welded on the inner wall of the shell 10, and the controller 7 and the water quality detector 8 are fixedly arranged on the other end of the first supporting rod 1, for example, by screws or fixed by steel wires. One end of the second supporting rod 2 is welded on the inner wall of the shell 10, and the other end is hinged with the rotating rod 3, namely hinged through the pin 4, and the rotating rod 3 can freely rotate around the axis of the pin 4. The tension sensor 6 is fixedly installed on the upper wall surface of the inner wall of the shell 10, one end of the spring 5 is fixedly connected with the tension sensor 6, and the other end of the spring is welded on the rotating rod.
In this embodiment, ecological environment data passes through water quality detector 8 and gathers, and initial time, dwang 3 is in the natural state of drooping, and spring 5 is in the natural length state, puts into the river with collection system. When river water flows through the collecting device from right to left, impurities such as weeds, green moss and duckweeds can be blocked due to the filter plates 9 arranged at the two ends of the shell 10, so that the impurities are prevented from being attached to the water quality detector 8, and the water quality detector 8 is prevented from being incapable of working normally. Under the action of the impact force of the river water to the left, the rotating rod 3 deflects to the left, so that the length of the spring 5 is lengthened, the tension sensor 6 detects the tension of the spring 5 and sends the tension to the controller 7.
According to the basic physics knowledge, if the river water flows at a constant speed in a period of time, namely the flow velocity of the river water does not change along with the time, the tension detected by the tension sensor 6 should be approximately equal; if the river water is flowing at an accelerated speed, that is, the flow velocity of the river water is gradually increased along with the time, the tension detected by the tension sensor 6 should be gradually increased; if the river water flows at a reduced speed, that is, the flow velocity of the river water gradually decreases with time, the tension detected by the tension sensor 6 should also gradually decrease.
In this embodiment, the water quality detector 8 starts to collect data after the flow velocity of the river is stabilized, specifically: the tension sensor 6 collects tension of the spring 5 in real time and sends the collected tension to the controller 7; after receiving the pulling force, the controller 7 judges whether the pulling force is approximately equal within a preset time: if the tension is approximately equal within the preset time, sending a control signal to the water quality detector 8, and starting to acquire data after the water quality detector 8 receives the control signal; on the contrary, if the tensile force is not approximately equal for the preset time period, the control signal is not transmitted to the water quality detector 8. By the mode, data acquisition is carried out after the tension is stable, namely the flow velocity of river water is stable; compared with the method of directly starting data acquisition, the method has the advantages that the obtained data are more reliable and are less influenced by accidental factors.
For example, the preset time is 5 minutes, if the tension in the time fluctuates around 2N, the maximum tension is 2.1N, the minimum tension is 1.9N, and the tension fluctuation does not exceed 5%, it is indicated that the flow rate of river water in the time is relatively stable, and the acquired data is relatively reliable, so that data acquisition is started; on the contrary, if the maximum tension is 2.5N and the minimum tension is 1.0N in the period of time, the tension fluctuation even reaches 50%, which indicates that the flow velocity of the river water in the period of time is unstable, the acquired data has strong randomness and cannot reflect the real condition of the river water, so the data acquisition is not started.
The foregoing is merely an example of the present invention, and common general knowledge in the field of known specific structures and characteristics is not described herein in any greater extent than that known in the art at the filing date or prior to the priority date of the application, so that those skilled in the art can now appreciate that all of the above-described techniques in this field and have the ability to apply routine experimentation before this date can be combined with one or more of the present teachings to complete and implement the present invention, and that certain typical known structures or known methods do not pose any impediments to the implementation of the present invention by those skilled in the art. It should be noted that, for those skilled in the art, without departing from the structure of the present invention, several changes and modifications can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicability of the patent. The scope of the claims of the present application shall be determined by the contents of the claims, and the description of the embodiments and the like in the specification shall be used to explain the contents of the claims.
Claims (10)
1. Surface water control management system, its characterized in that includes:
the acquisition unit is used for acquiring a water body image of the surface water surface in real time and transmitting the water body image;
the filtering unit is used for receiving the water body image, filtering the water body image and sending the filtered water body image;
the storage unit is used for receiving the filtered water body image and storing the filtered water body image;
the training unit is used for acquiring the filtered water body image, generating corresponding multi-scale training sample data on the basis of the filtered water body image, and training the neural network by using the multi-scale training sample data to obtain a neural network model;
the processing unit is used for identifying floaters in the filtered water body image according to the neural network model, extracting key point data of the water sample image, and performing consistency matching through the neural network model to obtain a matching result, wherein the key point data comprises color gradient data, size data, shape data and curvature data of the floaters observed under different scales and water bloom form data near the floaters; determining the identification result of the floaters according to the matching result to obtain the number of the floaters on the water surface; carrying out color recognition on the filtered water body image to obtain an RGB difference value between the water body image and a normal image; judging whether the water body is abnormal or not according to the number of the floaters and the RGB difference value, and marking an abnormal area in the water body image when the water body is abnormal;
the display unit is used for displaying the marked area on the visual interface;
the device comprises an acquisition device, a control device and a control device, wherein the acquisition device comprises a first supporting rod, a second supporting rod, a rotating rod, a pin nail, a spring, a tension sensor, a controller, a water quality detector, a filter plate and a shell; the shell is cylindrical, the left end and the right end of the shell are both fixedly provided with filter plates, and the filter plates are provided with a plurality of filter holes; one end of the first supporting rod is fixed on the inner wall of the shell, and the controller and the water quality detector are fixed on the other end of the first supporting rod; one end of the second supporting rod is fixed on the inner wall of the shell, and the other end of the second supporting rod is hinged with the rotating rod; the tension sensor is fixed on the upper wall surface of the inner wall of the shell, one end of the spring is fixedly connected with the tension sensor, and the other end of the spring is fixedly connected with the rotating rod.
2. The surface water monitoring and management system of claim 1, wherein the flotage identification specifically comprises: extracting key point data of the water sample image, and performing consistency matching through a neural network model to obtain a matching result; and determining the identification result of the floating object according to the matching result.
3. The surface water monitoring and management system of claim 2, wherein the flotage identification specifically comprises: performing image segmentation processing on the water body image, and removing information irrelevant to the water body to obtain a segmented image; carrying out gray level processing on the segmented image, and processing the colorful water body image into a gray water body image; and identifying the floating objects in the water body image with the gray scale by adopting an edge detection algorithm.
4. The surface water monitoring and management system of claim 3, wherein obtaining the RGB difference between the water body image and the normal image specifically comprises: reading RGB values of each pixel point in the water body image and the normal image, converting the RGB values into 16 systems, and storing the 16 systems into two arrays with the width multiplied by the height of the water body image as the size; comparing the data at the same position, and if the data are not equal, calculating the data as 1; and counting the number of the pixels which is 1 and dividing the number by the total number of the pixels of the water body image to obtain the RGB difference value.
5. The surface water monitoring and management system according to claim 4, wherein the determination of whether the water body is abnormal is based on the number of floats and the RGB difference value, specifically, when the number of floats is greater than or equal to the number threshold value and the RGB difference value is greater than or equal to the difference threshold value, the determination of the water body is abnormal.
6. The surface water monitoring and managing method is characterized by comprising the following steps:
s1, acquiring a water body image of the surface water surface in real time; the tension sensor collects tension of the spring in real time and sends the collected tension to the controller; after receiving the pulling force, the controller judges whether the pulling force is approximately equal within a preset time: if the tension is approximately equal within the preset time, sending a control signal to the water quality detector, and starting to acquire data after the water quality detector receives the control signal; on the contrary, if the tension is not approximately equal within the preset time, the control signal is not sent to the water quality detector;
s2, filtering the water body image, and storing the filtered water body image;
s3, acquiring the filtered water body image, generating corresponding multi-scale training sample data based on the filtered water body image, and training the neural network by using the multi-scale training sample data to obtain a neural network model;
s4, identifying floaters in the filtered water body image according to the neural network model, extracting key point data of the water sample image, and performing consistency matching through the neural network model to obtain a matching result, wherein the key point data comprises color gradient data, size data, shape data and curvature data of the observed floaters under different scales and water bloom form data near the floaters; determining the identification result of the floaters according to the matching result to obtain the number of the floaters on the water surface; carrying out color recognition on the filtered water body image to obtain an RGB difference value between the water body image and a normal image; judging whether the water body is abnormal or not according to the number of the floaters and the RGB difference value, and marking an abnormal area in the water body image when the water body is abnormal;
and S5, displaying the marked area on the visual interface.
7. The surface water monitoring and management method according to claim 6, wherein in S4, the identifying the floating objects specifically comprises:
a1, extracting key point data of the water sample image, and performing consistency matching through a neural network model to obtain a matching result;
and A2, determining the identification result of the floating object according to the matching result.
8. The surface water monitoring and management method according to claim 7, wherein in S4, the identifying the floating objects specifically comprises:
b1, carrying out image segmentation processing on the water body image, and removing information irrelevant to the water body to obtain a segmented image;
b2, carrying out gray scale processing on the segmented image, and processing the color water body image into a gray water body image;
and B3, adopting an edge detection algorithm to identify the floating objects in the water body image with the gray scale.
9. The surface water monitoring and management method of claim 8, wherein obtaining the RGB difference between the water body image and the normal image specifically comprises:
c1, reading the RGB values of each pixel point in the water body image and the normal image, converting the RGB values into a 16-system value, and storing the 16-system value into two arrays with the width multiplied by the height of the water body image as the size;
c2, comparing the data at the same position, and if not, counting as 1;
and C3, counting the number of 1, and dividing by the total number of pixel points of the water body image to obtain the RGB difference value.
10. The surface water monitoring and management method according to claim 9, wherein in S4, the determining whether the water body is abnormal according to the number of floating objects and the RGB difference value is specifically, when the number of floating objects is greater than or equal to the number threshold value and the RGB difference value is greater than or equal to the difference threshold value, determining that the water body is abnormal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011379262.5A CN112418128B (en) | 2020-11-30 | 2020-11-30 | Surface water monitoring and management system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011379262.5A CN112418128B (en) | 2020-11-30 | 2020-11-30 | Surface water monitoring and management system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112418128A CN112418128A (en) | 2021-02-26 |
| CN112418128B true CN112418128B (en) | 2022-01-21 |
Family
ID=74830693
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011379262.5A Active CN112418128B (en) | 2020-11-30 | 2020-11-30 | Surface water monitoring and management system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112418128B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022217589A1 (en) * | 2021-04-16 | 2022-10-20 | 长沙有色冶金设计研究院有限公司 | Water quality image analysis method and system based on deep learning, and device and medium |
| CN114445699B (en) * | 2021-11-16 | 2022-11-04 | 广州山水怡人园林生态有限公司 | Water landscape water changing management method, management device and management system |
| CN113903007A (en) * | 2021-12-10 | 2022-01-07 | 宁波弘泰水利信息科技有限公司 | Intelligent scene analysis system for water conservancy industry |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108647574A (en) * | 2018-04-10 | 2018-10-12 | 江河瑞通（北京）技术有限公司 | Floating material image detection model generating method, recognition methods and equipment |
| CN109187534A (en) * | 2018-08-01 | 2019-01-11 | 江苏凯纳水处理技术有限公司 | Water quality detection method and its water sample pattern recognition device |
| CN109242861A (en) * | 2018-08-23 | 2019-01-18 | 成都信息工程大学 | A kind of monitoring water quality method based on image procossing |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140025481A1 (en) * | 2012-07-20 | 2014-01-23 | Lg Cns Co., Ltd. | Benefit promotion advertising in an augmented reality environment |
| CN108020443A (en) * | 2016-11-02 | 2018-05-11 | 郑州富铭环保科技有限公司 | A kind of sampling apparatus for water quality online analyzer measure equal proportion mixed sample |
| CN108535269A (en) * | 2018-04-24 | 2018-09-14 | 中国水利水电科学研究院 | Spillway safety detecting system and method based on sheet flow hydrodynamic characterisitic |
| CN208420967U (en) * | 2018-06-28 | 2019-01-22 | 梅府 | A kind of nuclear power plant's warm water discharge monitoring device |
| CN111289768B (en) * | 2020-03-25 | 2022-08-30 | 南京管科智能科技有限公司 | Flexible electronic water gauge and method for measuring flow velocity by using same |
-
2020
- 2020-11-30 CN CN202011379262.5A patent/CN112418128B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108647574A (en) * | 2018-04-10 | 2018-10-12 | 江河瑞通（北京）技术有限公司 | Floating material image detection model generating method, recognition methods and equipment |
| CN109187534A (en) * | 2018-08-01 | 2019-01-11 | 江苏凯纳水处理技术有限公司 | Water quality detection method and its water sample pattern recognition device |
| CN109242861A (en) * | 2018-08-23 | 2019-01-18 | 成都信息工程大学 | A kind of monitoring water quality method based on image procossing |
Non-Patent Citations (1)
| Title |
|---|
| 智慧视频识别在水利信息化中的应用;程诚 等;《四川水利》;20190630;第124-128页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112418128A (en) | 2021-02-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112418128B (en) | Surface water monitoring and management system and method | |
| CN108759973B (en) | Water level measuring method | |
| KR101858339B1 (en) | Apparatus for weather observation using camera captured images and method thereof | |
| CN105225523B (en) | A kind of parking space state detection method and device | |
| CN112857471B (en) | Industrial Internet of things chemical wastewater treatment emission on-line monitoring and early warning management cloud platform | |
| CN111950812B (en) | Method and device for automatically identifying and predicting rainfall | |
| CN113658174B (en) | Microkernel histology image detection method based on deep learning and image processing algorithm | |
| CN111598098A (en) | Water gauge water line detection and effectiveness identification method based on full convolution neural network | |
| CN111141653B (en) | Tunnel leakage rate prediction method based on neural network | |
| CN109859170A (en) | A kind of steel wire rope surface damage intelligent monitoring method and system based on LBP feature | |
| CN105930852A (en) | Method for identifying bubble image | |
| CN115526515B (en) | Safety monitoring system of gate for water conservancy and hydropower | |
| CN112883802A (en) | Method for identifying destructive event of pipeline optical fiber vibration safety early warning system | |
| CN116012701A (en) | Water treatment dosing control method and device based on alum blossom detection | |
| CN107977531B (en) | A kind of ground resistance flexible measurement method based on image procossing and mathematical model | |
| CN114494826A (en) | Multi-water-gauge water level identification method and system, electronic equipment and storable medium | |
| CN111753610A (en) | Weather identification method and device | |
| CN110363749A (en) | Stockbridge damper corrosion degree evaluation method based on image procossing | |
| CN117372377A (en) | Broken line detection method and device for monocrystalline silicon ridge line and electronic equipment | |
| CN112507869A (en) | Underwater target behavior observation and water body environment monitoring method based on machine vision | |
| CN107886049B (en) | Visibility recognition early warning method based on camera probe | |
| KR102281100B1 (en) | System and method for providing heat transporting pipe status information | |
| DE112018000224T5 (en) | Method and device for positioning sample slots | |
| CN108764311A (en) | A kind of shelter target detection method, electronic equipment, storage medium and system | |
| CN112241691B (en) | Channel ice condition intelligent identification method based on unmanned aerial vehicle inspection and image characteristics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |